-
-### [Version 1.18.1](https://github.com/lobehub/lobe-chat/compare/v1.18.0...v1.18.1)
-
-Released on **2024-09-18**
-
-
+#### Styles
-
-Improvements and Fixes
+- **misc**: Add `gpt-4.5-preview` for OpenAI, closes [#6618](https://github.com/lobehub/lobe-chat/issues/6618) ([3ec3af0](https://github.com/lobehub/lobe-chat/commit/3ec3af0))
@@ -898,22 +847,22 @@
-## [Version 1.18.0](https://github.com/lobehub/lobe-chat/compare/v1.17.7...v1.18.0)
+### [Version 1.66.5](https://github.com/lobehub/lobe-chat/compare/v1.66.4...v1.66.5)
-Released on **2024-09-18**
+Released on **2025-02-28**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Add Discover Page.
+- **misc**: Improve portal style.
Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Add Discover Page, closes [#3848](https://github.com/lobehub/lobe-chat/issues/3848) ([f83cab6](https://github.com/lobehub/lobe-chat/commit/f83cab6))
+- **misc**: Improve portal style, closes [#6588](https://github.com/lobehub/lobe-chat/issues/6588) ([55b5416](https://github.com/lobehub/lobe-chat/commit/55b5416))
@@ -923,30 +872,22 @@
-### [Version 1.17.7](https://github.com/lobehub/lobe-chat/compare/v1.17.6...v1.17.7)
-
-Released on **2024-09-16**
-
-#### 🐛 Bug Fixes
+### [Version 1.66.4](https://github.com/lobehub/lobe-chat/compare/v1.66.3...v1.66.4)
-- **misc**: Fix a corner case of `tools_call` with empty object.
+Released on **2025-02-28**
#### 💄 Styles
-- **misc**: Delete duplicate models in ollama.
+- **misc**: Optimize smooth output.
Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix a corner case of `tools_call` with empty object, closes [#3955](https://github.com/lobehub/lobe-chat/issues/3955) ([d3fabdc](https://github.com/lobehub/lobe-chat/commit/d3fabdc))
-
#### Styles
-- **misc**: Delete duplicate models in ollama, closes [#3989](https://github.com/lobehub/lobe-chat/issues/3989) ([ece60ee](https://github.com/lobehub/lobe-chat/commit/ece60ee))
+- **misc**: Optimize smooth output, closes [#5824](https://github.com/lobehub/lobe-chat/issues/5824) ([7a84ad9](https://github.com/lobehub/lobe-chat/commit/7a84ad9))
@@ -956,22 +897,22 @@
-### [Version 1.17.6](https://github.com/lobehub/lobe-chat/compare/v1.17.5...v1.17.6)
+### [Version 1.66.3](https://github.com/lobehub/lobe-chat/compare/v1.66.2...v1.66.3)
-Released on **2024-09-15**
+Released on **2025-02-27**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Rename artifacts to plugins in portal.
+- **misc**: Fix fetch assistants plugin error.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Rename artifacts to plugins in portal, closes [#3986](https://github.com/lobehub/lobe-chat/issues/3986) ([073b936](https://github.com/lobehub/lobe-chat/commit/073b936))
+- **misc**: Fix fetch assistants plugin error, closes [#6576](https://github.com/lobehub/lobe-chat/issues/6576) ([9669a02](https://github.com/lobehub/lobe-chat/commit/9669a02))
@@ -981,22 +922,22 @@
-### [Version 1.17.5](https://github.com/lobehub/lobe-chat/compare/v1.17.4...v1.17.5)
+### [Version 1.66.2](https://github.com/lobehub/lobe-chat/compare/v1.66.1...v1.66.2)
-Released on **2024-09-15**
+Released on **2025-02-27**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Add MiniCPM-V 8B model entries to Ollama model providers.
+- **misc**: Update Claude sonnet 3.7 model ID.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Add MiniCPM-V 8B model entries to Ollama model providers, closes [#3984](https://github.com/lobehub/lobe-chat/issues/3984) ([f9c26de](https://github.com/lobehub/lobe-chat/commit/f9c26de))
+- **misc**: Update Claude sonnet 3.7 model ID, closes [#6567](https://github.com/lobehub/lobe-chat/issues/6567) ([d1039d6](https://github.com/lobehub/lobe-chat/commit/d1039d6))
@@ -1006,13 +947,13 @@
-### [Version 1.17.4](https://github.com/lobehub/lobe-chat/compare/v1.17.3...v1.17.4)
+### [Version 1.66.1](https://github.com/lobehub/lobe-chat/compare/v1.66.0...v1.66.1)
-Released on **2024-09-15**
+Released on **2025-02-27**
#### 💄 Styles
-- **misc**: Update fullscreen loading style.
+- **misc**: Added eu-central-1 region for bedrock.
@@ -1021,7 +962,7 @@
#### Styles
-- **misc**: Update fullscreen loading style, closes [#3948](https://github.com/lobehub/lobe-chat/issues/3948) ([aec21d2](https://github.com/lobehub/lobe-chat/commit/aec21d2))
+- **misc**: Added eu-central-1 region for bedrock, closes [#6555](https://github.com/lobehub/lobe-chat/issues/6555) ([6f1e599](https://github.com/lobehub/lobe-chat/commit/6f1e599))
@@ -1031,22 +972,22 @@
-### [Version 1.17.3](https://github.com/lobehub/lobe-chat/compare/v1.17.2...v1.17.3)
+## [Version 1.66.0](https://github.com/lobehub/lobe-chat/compare/v1.65.2...v1.66.0)
-Released on **2024-09-14**
+Released on **2025-02-27**
-#### 💄 Styles
+#### ✨ Features
-- **misc**: Delete "-" in deepseek displayname.
+- **misc**: Add online search support for available providers.
Improvements and Fixes
-#### Styles
+#### What's improved
-- **misc**: Delete "-" in deepseek displayname, closes [#3958](https://github.com/lobehub/lobe-chat/issues/3958) ([c0e89f5](https://github.com/lobehub/lobe-chat/commit/c0e89f5))
+- **misc**: Add online search support for available providers, closes [#6475](https://github.com/lobehub/lobe-chat/issues/6475) ([cb0a3bc](https://github.com/lobehub/lobe-chat/commit/cb0a3bc))
@@ -1056,30 +997,23 @@
-### [Version 1.17.2](https://github.com/lobehub/lobe-chat/compare/v1.17.1...v1.17.2)
-
-Released on **2024-09-13**
-
-#### 🐛 Bug Fixes
+### [Version 1.65.2](https://github.com/lobehub/lobe-chat/compare/v1.65.1...v1.65.2)
-- **misc**: Fix o1 model list.
+Released on **2025-02-27**
#### 💄 Styles
-- **misc**: Update openrouter model list.
+- **misc**: Support parsing the search flag when parsing the model list, Update Gemini & Qwen models.
Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix o1 model list, closes [#3957](https://github.com/lobehub/lobe-chat/issues/3957) ([e04cdd9](https://github.com/lobehub/lobe-chat/commit/e04cdd9))
-
#### Styles
-- **misc**: Update openrouter model list, closes [#3954](https://github.com/lobehub/lobe-chat/issues/3954) ([1a1572b](https://github.com/lobehub/lobe-chat/commit/1a1572b))
+- **misc**: Support parsing the search flag when parsing the model list, closes [#6546](https://github.com/lobehub/lobe-chat/issues/6546) ([8c768ed](https://github.com/lobehub/lobe-chat/commit/8c768ed))
+- **misc**: Update Gemini & Qwen models, closes [#6531](https://github.com/lobehub/lobe-chat/issues/6531) ([efde928](https://github.com/lobehub/lobe-chat/commit/efde928))
@@ -1089,22 +1023,22 @@
-### [Version 1.17.1](https://github.com/lobehub/lobe-chat/compare/v1.17.0...v1.17.1)
+### [Version 1.65.1](https://github.com/lobehub/lobe-chat/compare/v1.65.0...v1.65.1)
-Released on **2024-09-13**
+Released on **2025-02-26**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Update zhipu model info.
+- **misc**: Fix claude 3.7 sonnet thinking with tool use.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Update zhipu model info, closes [#3949](https://github.com/lobehub/lobe-chat/issues/3949) ([bbdbfde](https://github.com/lobehub/lobe-chat/commit/bbdbfde))
+- **misc**: Fix claude 3.7 sonnet thinking with tool use, closes [#6528](https://github.com/lobehub/lobe-chat/issues/6528) ([a76d2bf](https://github.com/lobehub/lobe-chat/commit/a76d2bf))
@@ -1114,17 +1048,17 @@
-## [Version 1.17.0](https://github.com/lobehub/lobe-chat/compare/v1.16.14...v1.17.0)
+## [Version 1.65.0](https://github.com/lobehub/lobe-chat/compare/v1.64.3...v1.65.0)
-Released on **2024-09-13**
+Released on **2025-02-25**
#### ✨ Features
-- **misc**: Support openai new OpenAI o1-preview/o1-mini models.
+- **misc**: Support claude sonnet 3.7 thinking.
#### 💄 Styles
-- **misc**: Support Google Model List.
+- **misc**: Update Gemini 2.0 search settings.
@@ -1133,11 +1067,11 @@
#### What's improved
-- **misc**: Support openai new OpenAI o1-preview/o1-mini models, closes [#3943](https://github.com/lobehub/lobe-chat/issues/3943) ([61bfeb2](https://github.com/lobehub/lobe-chat/commit/61bfeb2))
+- **misc**: Support claude sonnet 3.7 thinking, closes [#6515](https://github.com/lobehub/lobe-chat/issues/6515) ([bc9829f](https://github.com/lobehub/lobe-chat/commit/bc9829f))
#### Styles
-- **misc**: Support Google Model List, closes [#3938](https://github.com/lobehub/lobe-chat/issues/3938) ([be4efc7](https://github.com/lobehub/lobe-chat/commit/be4efc7))
+- **misc**: Update Gemini 2.0 search settings, closes [#6516](https://github.com/lobehub/lobe-chat/issues/6516) ([250bbcb](https://github.com/lobehub/lobe-chat/commit/250bbcb))
@@ -1147,13 +1081,13 @@
-### [Version 1.16.14](https://github.com/lobehub/lobe-chat/compare/v1.16.13...v1.16.14)
+### [Version 1.64.3](https://github.com/lobehub/lobe-chat/compare/v1.64.2...v1.64.3)
-Released on **2024-09-13**
+Released on **2025-02-25**
#### 💄 Styles
-- **model**: Remove `OpenAI` deprecated model.
+- **misc**: Add Claude 3.7 Sonnet and Haiku 3.5.
@@ -1162,7 +1096,7 @@
#### Styles
-- **model**: Remove `OpenAI` deprecated model, closes [#3465](https://github.com/lobehub/lobe-chat/issues/3465) ([68a4fb2](https://github.com/lobehub/lobe-chat/commit/68a4fb2))
+- **misc**: Add Claude 3.7 Sonnet and Haiku 3.5, closes [#6512](https://github.com/lobehub/lobe-chat/issues/6512) ([c8db2bb](https://github.com/lobehub/lobe-chat/commit/c8db2bb))
@@ -1172,22 +1106,22 @@
-### [Version 1.16.13](https://github.com/lobehub/lobe-chat/compare/v1.16.12...v1.16.13)
+### [Version 1.64.2](https://github.com/lobehub/lobe-chat/compare/v1.64.1...v1.64.2)
-Released on **2024-09-13**
+Released on **2025-02-25**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Update siliconcloud model.
+- **misc**: Fix 0 search results with specific search engine.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Update siliconcloud model, closes [#3935](https://github.com/lobehub/lobe-chat/issues/3935) ([882e981](https://github.com/lobehub/lobe-chat/commit/882e981))
+- **misc**: Fix 0 search results with specific search engine, closes [#6487](https://github.com/lobehub/lobe-chat/issues/6487) ([74a09e2](https://github.com/lobehub/lobe-chat/commit/74a09e2))
@@ -1197,22 +1131,22 @@
-### [Version 1.16.12](https://github.com/lobehub/lobe-chat/compare/v1.16.11...v1.16.12)
+### [Version 1.64.1](https://github.com/lobehub/lobe-chat/compare/v1.64.0...v1.64.1)
-Released on **2024-09-12**
+Released on **2025-02-25**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Remove brackets from model names with dates in OpenAI.
+- **misc**: Disable fc for ds-v3 series.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Remove brackets from model names with dates in OpenAI, closes [#3927](https://github.com/lobehub/lobe-chat/issues/3927) ([2a937bc](https://github.com/lobehub/lobe-chat/commit/2a937bc))
+- **misc**: Disable fc for ds-v3 series, closes [#6486](https://github.com/lobehub/lobe-chat/issues/6486) ([0092213](https://github.com/lobehub/lobe-chat/commit/0092213))
@@ -1222,30 +1156,22 @@
-### [Version 1.16.11](https://github.com/lobehub/lobe-chat/compare/v1.16.10...v1.16.11)
-
-Released on **2024-09-12**
-
-#### 🐛 Bug Fixes
+## [Version 1.64.0](https://github.com/lobehub/lobe-chat/compare/v1.63.3...v1.64.0)
-- **misc**: Support webhooks for logto.
+Released on **2025-02-24**
-#### 💄 Styles
+#### ✨ Features
-- **misc**: Default disable mistral provider useless models.
+- **misc**: Support application search with searchXNG.
Improvements and Fixes
-#### What's fixed
-
-- **misc**: Support webhooks for logto, closes [#3774](https://github.com/lobehub/lobe-chat/issues/3774) ([0cfee6b](https://github.com/lobehub/lobe-chat/commit/0cfee6b))
-
-#### Styles
+#### What's improved
-- **misc**: Default disable mistral provider useless models, closes [#3922](https://github.com/lobehub/lobe-chat/issues/3922) ([bdbc647](https://github.com/lobehub/lobe-chat/commit/bdbc647))
+- **misc**: Support application search with searchXNG, closes [#6452](https://github.com/lobehub/lobe-chat/issues/6452) ([b61b5fc](https://github.com/lobehub/lobe-chat/commit/b61b5fc))
@@ -1255,30 +1181,22 @@
-### [Version 1.16.10](https://github.com/lobehub/lobe-chat/compare/v1.16.9...v1.16.10)
-
-Released on **2024-09-12**
-
-#### ♻ Code Refactoring
+### [Version 1.63.3](https://github.com/lobehub/lobe-chat/compare/v1.63.2...v1.63.3)
-- **misc**: Support Environment Variable Inference For NextAuth.
+Released on **2025-02-24**
#### 🐛 Bug Fixes
-- **misc**: Qwen model param error.
+- **misc**: Fix citation=null issue in stream.
Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Support Environment Variable Inference For NextAuth, closes [#3701](https://github.com/lobehub/lobe-chat/issues/3701) ([b956755](https://github.com/lobehub/lobe-chat/commit/b956755))
-
#### What's fixed
-- **misc**: Qwen model param error, closes [#3902](https://github.com/lobehub/lobe-chat/issues/3902) ([c9f00e5](https://github.com/lobehub/lobe-chat/commit/c9f00e5))
+- **misc**: Fix citation=null issue in stream, closes [#6461](https://github.com/lobehub/lobe-chat/issues/6461) ([3f9498e](https://github.com/lobehub/lobe-chat/commit/3f9498e))
@@ -1288,22 +1206,22 @@
-### [Version 1.16.9](https://github.com/lobehub/lobe-chat/compare/v1.16.8...v1.16.9)
+### [Version 1.63.2](https://github.com/lobehub/lobe-chat/compare/v1.63.1...v1.63.2)
-Released on **2024-09-12**
+Released on **2025-02-24**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Add model and provider desc and url.
+- **misc**: Fix model settings config.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Add model and provider desc and url, closes [#3920](https://github.com/lobehub/lobe-chat/issues/3920) ([ea9ff00](https://github.com/lobehub/lobe-chat/commit/ea9ff00))
+- **misc**: Fix model settings config, closes [#6459](https://github.com/lobehub/lobe-chat/issues/6459) ([469bd10](https://github.com/lobehub/lobe-chat/commit/469bd10))
@@ -1313,22 +1231,30 @@
-### [Version 1.16.8](https://github.com/lobehub/lobe-chat/compare/v1.16.7...v1.16.8)
+### [Version 1.63.1](https://github.com/lobehub/lobe-chat/compare/v1.63.0...v1.63.1)
-Released on **2024-09-12**
+Released on **2025-02-23**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix groq location request.
#### 💄 Styles
-- **misc**: Improve models and add more info for providers and models.
+- **misc**: Improve plugin calling style.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix groq location request, closes [#6449](https://github.com/lobehub/lobe-chat/issues/6449) ([8c8af6b](https://github.com/lobehub/lobe-chat/commit/8c8af6b))
+
#### Styles
-- **misc**: Improve models and add more info for providers and models, closes [#3911](https://github.com/lobehub/lobe-chat/issues/3911) ([8a8fc6a](https://github.com/lobehub/lobe-chat/commit/8a8fc6a))
+- **misc**: Improve plugin calling style, closes [#6446](https://github.com/lobehub/lobe-chat/issues/6446) ([406cd46](https://github.com/lobehub/lobe-chat/commit/406cd46))
@@ -1338,22 +1264,30 @@
-### [Version 1.16.7](https://github.com/lobehub/lobe-chat/compare/v1.16.6...v1.16.7)
+## [Version 1.63.0](https://github.com/lobehub/lobe-chat/compare/v1.62.11...v1.63.0)
-Released on **2024-09-11**
+Released on **2025-02-23**
+
+#### ✨ Features
+
+- **misc**: Support model-level search for Google/Qwen.
#### 💄 Styles
-- **misc**: Optimize model token display method.
+- **misc**: Update many models info.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Support model-level search for Google/Qwen, closes [#6420](https://github.com/lobehub/lobe-chat/issues/6420) ([f1b97cd](https://github.com/lobehub/lobe-chat/commit/f1b97cd))
+
#### Styles
-- **misc**: Optimize model token display method, closes [#3697](https://github.com/lobehub/lobe-chat/issues/3697) ([249795c](https://github.com/lobehub/lobe-chat/commit/249795c))
+- **misc**: Update many models info, closes [#6205](https://github.com/lobehub/lobe-chat/issues/6205) ([c477588](https://github.com/lobehub/lobe-chat/commit/c477588))
@@ -1363,13 +1297,17 @@
-### [Version 1.16.6](https://github.com/lobehub/lobe-chat/compare/v1.16.5...v1.16.6)
+### [Version 1.62.11](https://github.com/lobehub/lobe-chat/compare/v1.62.10...v1.62.11)
-Released on **2024-09-11**
+Released on **2025-02-23**
#### 🐛 Bug Fixes
-- **misc**: Pin `next@14.2.8` to fix Internal error.
+- **misc**: Refine role assignment logic for specific Azure OpenAI models & Sensitive URL.
+
+#### 💄 Styles
+
+- **misc**: Add custom `proxyUrl` support for Volcengine.
@@ -1378,7 +1316,11 @@
#### What's fixed
-- **misc**: Pin `next@14.2.8` to fix Internal error, closes [#3905](https://github.com/lobehub/lobe-chat/issues/3905) ([1013652](https://github.com/lobehub/lobe-chat/commit/1013652))
+- **misc**: Refine role assignment logic for specific Azure OpenAI models & Sensitive URL, closes [#6366](https://github.com/lobehub/lobe-chat/issues/6366) ([d47c2c6](https://github.com/lobehub/lobe-chat/commit/d47c2c6))
+
+#### Styles
+
+- **misc**: Add custom `proxyUrl` support for Volcengine, closes [#6433](https://github.com/lobehub/lobe-chat/issues/6433) ([2b1aca9](https://github.com/lobehub/lobe-chat/commit/2b1aca9))
@@ -1388,15 +1330,23 @@
-### [Version 1.16.5](https://github.com/lobehub/lobe-chat/compare/v1.16.4...v1.16.5)
+### [Version 1.62.10](https://github.com/lobehub/lobe-chat/compare/v1.62.9...v1.62.10)
-Released on **2024-09-11**
+Released on **2025-02-22**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix fetch on client check status display.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix fetch on client check status display, closes [#6405](https://github.com/lobehub/lobe-chat/issues/6405) ([9579e41](https://github.com/lobehub/lobe-chat/commit/9579e41))
+
@@ -1405,22 +1355,22 @@
-### [Version 1.16.4](https://github.com/lobehub/lobe-chat/compare/v1.16.3...v1.16.4)
+### [Version 1.62.9](https://github.com/lobehub/lobe-chat/compare/v1.62.8...v1.62.9)
-Released on **2024-09-11**
+Released on **2025-02-22**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **ui**: Improve UI layout and text.
+- **misc**: Next-auth user id not found in create agent index.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **ui**: Improve UI layout and text, closes [#3762](https://github.com/lobehub/lobe-chat/issues/3762) ([7c08f29](https://github.com/lobehub/lobe-chat/commit/7c08f29))
+- **misc**: Next-auth user id not found in create agent index, closes [#6410](https://github.com/lobehub/lobe-chat/issues/6410) ([704c7c8](https://github.com/lobehub/lobe-chat/commit/704c7c8))
@@ -1430,13 +1380,13 @@
-### [Version 1.16.3](https://github.com/lobehub/lobe-chat/compare/v1.16.2...v1.16.3)
+### [Version 1.62.8](https://github.com/lobehub/lobe-chat/compare/v1.62.7...v1.62.8)
-Released on **2024-09-11**
+Released on **2025-02-22**
#### 🐛 Bug Fixes
-- **misc**: Add `LLM_VISION_IMAGE_USE_BASE64` to support local s3 in vision model.
+- **misc**: Fix image prompts with some user cases.
@@ -1445,7 +1395,7 @@
#### What's fixed
-- **misc**: Add `LLM_VISION_IMAGE_USE_BASE64` to support local s3 in vision model, closes [#3887](https://github.com/lobehub/lobe-chat/issues/3887) ([16e57ed](https://github.com/lobehub/lobe-chat/commit/16e57ed))
+- **misc**: Fix image prompts with some user cases, closes [#6406](https://github.com/lobehub/lobe-chat/issues/6406) ([e9df49d](https://github.com/lobehub/lobe-chat/commit/e9df49d))
@@ -1455,13 +1405,13 @@
-### [Version 1.16.2](https://github.com/lobehub/lobe-chat/compare/v1.16.1...v1.16.2)
+### [Version 1.62.7](https://github.com/lobehub/lobe-chat/compare/v1.62.6...v1.62.7)
-Released on **2024-09-11**
+Released on **2025-02-21**
#### 💄 Styles
-- **misc**: Update Upstage model list.
+- **misc**: Add Volcano Ark models.
@@ -1470,7 +1420,7 @@
#### Styles
-- **misc**: Update Upstage model list, closes [#3890](https://github.com/lobehub/lobe-chat/issues/3890) ([82e2570](https://github.com/lobehub/lobe-chat/commit/82e2570))
+- **misc**: Add Volcano Ark models, closes [#6368](https://github.com/lobehub/lobe-chat/issues/6368) ([02136f5](https://github.com/lobehub/lobe-chat/commit/02136f5))
@@ -1480,13 +1430,13 @@
-### [Version 1.16.1](https://github.com/lobehub/lobe-chat/compare/v1.16.0...v1.16.1)
+### [Version 1.62.6](https://github.com/lobehub/lobe-chat/compare/v1.62.5...v1.62.6)
-Released on **2024-09-10**
+Released on **2025-02-21**
#### 💄 Styles
-- **misc**: Reorder the provider list, update spark check model to spark-lite & default disable useless model.
+- **misc**: Refactor the plugin render style.
@@ -1495,8 +1445,7 @@
#### Styles
-- **misc**: Reorder the provider list, closes [#3886](https://github.com/lobehub/lobe-chat/issues/3886) ([4d641f5](https://github.com/lobehub/lobe-chat/commit/4d641f5))
-- **misc**: Update spark check model to spark-lite & default disable useless model, closes [#3885](https://github.com/lobehub/lobe-chat/issues/3885) ([9d7e47c](https://github.com/lobehub/lobe-chat/commit/9d7e47c))
+- **misc**: Refactor the plugin render style, closes [#6390](https://github.com/lobehub/lobe-chat/issues/6390) ([3ecdba1](https://github.com/lobehub/lobe-chat/commit/3ecdba1))
@@ -1506,23 +1455,22 @@
-## [Version 1.16.0](https://github.com/lobehub/lobe-chat/compare/v1.15.35...v1.16.0)
+### [Version 1.62.5](https://github.com/lobehub/lobe-chat/compare/v1.62.4...v1.62.5)
-Released on **2024-09-10**
+Released on **2025-02-21**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Add Fireworks AI Model Provider, Add Spark model provider.
+- **misc**: Fix default agent loading.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Add Fireworks AI Model Provider, closes [#3392](https://github.com/lobehub/lobe-chat/issues/3392) [#48](https://github.com/lobehub/lobe-chat/issues/48) ([fa0d84d](https://github.com/lobehub/lobe-chat/commit/fa0d84d))
-- **misc**: Add Spark model provider, closes [#3098](https://github.com/lobehub/lobe-chat/issues/3098) [#25](https://github.com/lobehub/lobe-chat/issues/25) ([fc85c20](https://github.com/lobehub/lobe-chat/commit/fc85c20))
+- **misc**: Fix default agent loading, closes [#6393](https://github.com/lobehub/lobe-chat/issues/6393) ([7841122](https://github.com/lobehub/lobe-chat/commit/7841122))
@@ -1532,22 +1480,30 @@
-### [Version 1.15.35](https://github.com/lobehub/lobe-chat/compare/v1.15.34...v1.15.35)
+### [Version 1.62.4](https://github.com/lobehub/lobe-chat/compare/v1.62.3...v1.62.4)
-Released on **2024-09-10**
+Released on **2025-02-20**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix hotkeys of open agent settings.
#### 💄 Styles
-- **misc**: Update CustomLogo.
+- **misc**: Add some error types.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix hotkeys of open agent settings, closes [#6363](https://github.com/lobehub/lobe-chat/issues/6363) ([3219c54](https://github.com/lobehub/lobe-chat/commit/3219c54))
+
#### Styles
-- **misc**: Update CustomLogo, closes [#3874](https://github.com/lobehub/lobe-chat/issues/3874) ([dd7c8df](https://github.com/lobehub/lobe-chat/commit/dd7c8df))
+- **misc**: Add some error types, closes [#6377](https://github.com/lobehub/lobe-chat/issues/6377) ([f7a7138](https://github.com/lobehub/lobe-chat/commit/f7a7138))
@@ -1557,22 +1513,22 @@
-### [Version 1.15.34](https://github.com/lobehub/lobe-chat/compare/v1.15.33...v1.15.34)
+### [Version 1.62.3](https://github.com/lobehub/lobe-chat/compare/v1.62.2...v1.62.3)
-Released on **2024-09-10**
+Released on **2025-02-20**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Change empty content stream behavior.
+- **misc**: Fix a feature flag.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Change empty content stream behavior, closes [#3883](https://github.com/lobehub/lobe-chat/issues/3883) ([e910f68](https://github.com/lobehub/lobe-chat/commit/e910f68))
+- **misc**: Fix a feature flag, closes [#6354](https://github.com/lobehub/lobe-chat/issues/6354) ([6667334](https://github.com/lobehub/lobe-chat/commit/6667334))
@@ -1582,13 +1538,13 @@
-### [Version 1.15.33](https://github.com/lobehub/lobe-chat/compare/v1.15.32...v1.15.33)
+### [Version 1.62.2](https://github.com/lobehub/lobe-chat/compare/v1.62.1...v1.62.2)
-Released on **2024-09-10**
+Released on **2025-02-20**
#### 🐛 Bug Fixes
-- **misc**: Fix `/etc/resolv.conf`edit permission in docker image.
+- **misc**: Fix message roles for specific Azure OpenAI models.
@@ -1597,7 +1553,7 @@
#### What's fixed
-- **misc**: Fix `/etc/resolv.conf`edit permission in docker image, closes [#3880](https://github.com/lobehub/lobe-chat/issues/3880) ([fdaa190](https://github.com/lobehub/lobe-chat/commit/fdaa190))
+- **misc**: Fix message roles for specific Azure OpenAI models, closes [#6222](https://github.com/lobehub/lobe-chat/issues/6222) ([d49329a](https://github.com/lobehub/lobe-chat/commit/d49329a))
@@ -1607,13 +1563,13 @@
-### [Version 1.15.32](https://github.com/lobehub/lobe-chat/compare/v1.15.31...v1.15.32)
+### [Version 1.62.1](https://github.com/lobehub/lobe-chat/compare/v1.62.0...v1.62.1)
-Released on **2024-09-10**
+Released on **2025-02-20**
#### 🐛 Bug Fixes
-- **misc**: Fix tools calling in some edge cases.
+- **misc**: Add sambanova proxy url.
@@ -1622,7 +1578,7 @@
#### What's fixed
-- **misc**: Fix tools calling in some edge cases, closes [#3872](https://github.com/lobehub/lobe-chat/issues/3872) ([2ed759d](https://github.com/lobehub/lobe-chat/commit/2ed759d))
+- **misc**: Add sambanova proxy url, closes [#6348](https://github.com/lobehub/lobe-chat/issues/6348) ([c9cb7d9](https://github.com/lobehub/lobe-chat/commit/c9cb7d9))
@@ -1632,22 +1588,30 @@
-### [Version 1.15.31](https://github.com/lobehub/lobe-chat/compare/v1.15.30...v1.15.31)
+## [Version 1.62.0](https://github.com/lobehub/lobe-chat/compare/v1.61.6...v1.62.0)
-Released on **2024-09-10**
+Released on **2025-02-20**
+
+#### ✨ Features
+
+- **misc**: Support pplx search grounding.
#### 🐛 Bug Fixes
-- **misc**: Baichuan should not introduce `freequency_penality` parameters.
+- **misc**: Azure AI env var configuration issue..
Improvements and Fixes
+#### What's improved
+
+- **misc**: Support pplx search grounding, closes [#6331](https://github.com/lobehub/lobe-chat/issues/6331) ([ccb0003](https://github.com/lobehub/lobe-chat/commit/ccb0003))
+
#### What's fixed
-- **misc**: Baichuan should not introduce `freequency_penality` parameters, closes [#3871](https://github.com/lobehub/lobe-chat/issues/3871) ([66a061e](https://github.com/lobehub/lobe-chat/commit/66a061e))
+- **misc**: Azure AI env var configuration issue., closes [#6346](https://github.com/lobehub/lobe-chat/issues/6346) ([3fc61bb](https://github.com/lobehub/lobe-chat/commit/3fc61bb))
@@ -1657,13 +1621,13 @@
-### [Version 1.15.30](https://github.com/lobehub/lobe-chat/compare/v1.15.29...v1.15.30)
+### [Version 1.61.6](https://github.com/lobehub/lobe-chat/compare/v1.61.5...v1.61.6)
-Released on **2024-09-09**
+Released on **2025-02-20**
#### 🐛 Bug Fixes
-- **misc**: Fix claude 3.5 image with s3 url.
+- **misc**: Casdoor webhooks error.
@@ -1672,7 +1636,7 @@
#### What's fixed
-- **misc**: Fix claude 3.5 image with s3 url, closes [#3870](https://github.com/lobehub/lobe-chat/issues/3870) ([89c8dd4](https://github.com/lobehub/lobe-chat/commit/89c8dd4))
+- **misc**: Casdoor webhooks error, closes [#6304](https://github.com/lobehub/lobe-chat/issues/6304) ([7a458b9](https://github.com/lobehub/lobe-chat/commit/7a458b9))
@@ -1682,22 +1646,22 @@
-### [Version 1.15.29](https://github.com/lobehub/lobe-chat/compare/v1.15.28...v1.15.29)
+### [Version 1.61.5](https://github.com/lobehub/lobe-chat/compare/v1.61.4...v1.61.5)
-Released on **2024-09-09**
+Released on **2025-02-19**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Gemini cannot input images when server database is enabled.
+- **misc**: Show sso providers for next-auth in profile page.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Gemini cannot input images when server database is enabled, closes [#3370](https://github.com/lobehub/lobe-chat/issues/3370) ([eb552d2](https://github.com/lobehub/lobe-chat/commit/eb552d2))
+- **misc**: Show sso providers for next-auth in profile page, closes [#5303](https://github.com/lobehub/lobe-chat/issues/5303) ([dd61bce](https://github.com/lobehub/lobe-chat/commit/dd61bce))
@@ -1707,22 +1671,22 @@
-### [Version 1.15.28](https://github.com/lobehub/lobe-chat/compare/v1.15.27...v1.15.28)
+### [Version 1.61.4](https://github.com/lobehub/lobe-chat/compare/v1.61.3...v1.61.4)
-Released on **2024-09-09**
+Released on **2025-02-18**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Update baichuan param.
+- **misc**: Improve perplexity models.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Update baichuan param, closes [#3356](https://github.com/lobehub/lobe-chat/issues/3356) ([29bced1](https://github.com/lobehub/lobe-chat/commit/29bced1))
+- **misc**: Improve perplexity models, closes [#6307](https://github.com/lobehub/lobe-chat/issues/6307) ([c99908d](https://github.com/lobehub/lobe-chat/commit/c99908d))
@@ -1732,30 +1696,22 @@
-### [Version 1.15.27](https://github.com/lobehub/lobe-chat/compare/v1.15.26...v1.15.27)
-
-Released on **2024-09-09**
-
-#### ♻ Code Refactoring
+### [Version 1.61.3](https://github.com/lobehub/lobe-chat/compare/v1.61.2...v1.61.3)
-- **misc**: Refactor brand implement for better custom.
+Released on **2025-02-18**
#### 💄 Styles
-- **misc**: Add siliconcloud new model.
+- **misc**: Improve error content and console error.
Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Refactor brand implement for better custom, closes [#3868](https://github.com/lobehub/lobe-chat/issues/3868) ([815b366](https://github.com/lobehub/lobe-chat/commit/815b366))
-
#### Styles
-- **misc**: Add siliconcloud new model, closes [#3865](https://github.com/lobehub/lobe-chat/issues/3865) ([c6b5a45](https://github.com/lobehub/lobe-chat/commit/c6b5a45))
+- **misc**: Improve error content and console error, closes [#6305](https://github.com/lobehub/lobe-chat/issues/6305) ([6a35f55](https://github.com/lobehub/lobe-chat/commit/6a35f55))
@@ -1765,13 +1721,13 @@
-### [Version 1.15.26](https://github.com/lobehub/lobe-chat/compare/v1.15.25...v1.15.26)
+### [Version 1.61.2](https://github.com/lobehub/lobe-chat/compare/v1.61.1...v1.61.2)
-Released on **2024-09-09**
+Released on **2025-02-18**
#### 💄 Styles
-- **misc**: Update perplexity model list.
+- **misc**: Add `kimi-latest` for Moonshot.
@@ -1780,7 +1736,7 @@
#### Styles
-- **misc**: Update perplexity model list, closes [#3836](https://github.com/lobehub/lobe-chat/issues/3836) ([b70671b](https://github.com/lobehub/lobe-chat/commit/b70671b))
+- **misc**: Add `kimi-latest` for Moonshot, closes [#6295](https://github.com/lobehub/lobe-chat/issues/6295) ([4fb98da](https://github.com/lobehub/lobe-chat/commit/4fb98da))
@@ -1790,15 +1746,23 @@
-### [Version 1.15.25](https://github.com/lobehub/lobe-chat/compare/v1.15.24...v1.15.25)
+### [Version 1.61.1](https://github.com/lobehub/lobe-chat/compare/v1.61.0...v1.61.1)
-Released on **2024-09-09**
+Released on **2025-02-18**
+
+#### 💄 Styles
+
+- **misc**: Improve serveral error code.
Improvements and Fixes
+#### Styles
+
+- **misc**: Improve serveral error code, closes [#6299](https://github.com/lobehub/lobe-chat/issues/6299) ([352cb90](https://github.com/lobehub/lobe-chat/commit/352cb90))
+
@@ -1807,22 +1771,30 @@
-### [Version 1.15.24](https://github.com/lobehub/lobe-chat/compare/v1.15.23...v1.15.24)
+## [Version 1.61.0](https://github.com/lobehub/lobe-chat/compare/v1.60.9...v1.61.0)
-Released on **2024-09-09**
+Released on **2025-02-18**
-#### 💄 Styles
+#### ✨ Features
-- **misc**: Fix title in about settings.
+- **misc**: Support google vertex ai as a new provider.
+
+#### 🐛 Bug Fixes
+
+- **misc**: Try to fix pglite worker.
Improvements and Fixes
-#### Styles
+#### What's improved
-- **misc**: Fix title in about settings, closes [#3841](https://github.com/lobehub/lobe-chat/issues/3841) ([6b7a366](https://github.com/lobehub/lobe-chat/commit/6b7a366))
+- **misc**: Support google vertex ai as a new provider, closes [#4487](https://github.com/lobehub/lobe-chat/issues/4487) ([a0a9592](https://github.com/lobehub/lobe-chat/commit/a0a9592))
+
+#### What's fixed
+
+- **misc**: Try to fix pglite worker, closes [#6169](https://github.com/lobehub/lobe-chat/issues/6169) ([b3f4f13](https://github.com/lobehub/lobe-chat/commit/b3f4f13))
@@ -1832,23 +1804,15 @@
-### [Version 1.15.23](https://github.com/lobehub/lobe-chat/compare/v1.15.22...v1.15.23)
-
-Released on **2024-09-08**
-
-#### ♻ Code Refactoring
+### [Version 1.60.9](https://github.com/lobehub/lobe-chat/compare/v1.60.8...v1.60.9)
-- **misc**: Improve branding implement.
+Released on **2025-02-18** Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Improve branding implement, closes [#3832](https://github.com/lobehub/lobe-chat/issues/3832) ([b5e6b8b](https://github.com/lobehub/lobe-chat/commit/b5e6b8b))
-
@@ -1857,13 +1821,13 @@
-### [Version 1.15.22](https://github.com/lobehub/lobe-chat/compare/v1.15.21...v1.15.22)
+### [Version 1.60.8](https://github.com/lobehub/lobe-chat/compare/v1.60.7...v1.60.8)
-Released on **2024-09-08**
+Released on **2025-02-18**
#### 💄 Styles
-- **misc**: Update model display name & Remove Qwen preview model.
+- **misc**: Sync chat limit.
@@ -1872,7 +1836,7 @@
#### Styles
-- **misc**: Update model display name & Remove Qwen preview model, closes [#3757](https://github.com/lobehub/lobe-chat/issues/3757) ([dd439ba](https://github.com/lobehub/lobe-chat/commit/dd439ba))
+- **misc**: Sync chat limit, closes [#6207](https://github.com/lobehub/lobe-chat/issues/6207) ([cc2f536](https://github.com/lobehub/lobe-chat/commit/cc2f536))
@@ -1882,22 +1846,23 @@
-### [Version 1.15.21](https://github.com/lobehub/lobe-chat/compare/v1.15.20...v1.15.21)
+### [Version 1.60.7](https://github.com/lobehub/lobe-chat/compare/v1.60.6...v1.60.7)
-Released on **2024-09-08**
+Released on **2025-02-17**
-#### ♻ Code Refactoring
+#### 💄 Styles
-- **misc**: Temperature range from 0 to 2.
+- **misc**: Remove deprecated gemini models, update MiniMax models.
Improvements and Fixes
-#### Code refactoring
+#### Styles
-- **misc**: Temperature range from 0 to 2, closes [#3355](https://github.com/lobehub/lobe-chat/issues/3355) ([4a9114e](https://github.com/lobehub/lobe-chat/commit/4a9114e))
+- **misc**: Remove deprecated gemini models, closes [#6269](https://github.com/lobehub/lobe-chat/issues/6269) ([45977c3](https://github.com/lobehub/lobe-chat/commit/45977c3))
+- **misc**: Update MiniMax models, closes [#6270](https://github.com/lobehub/lobe-chat/issues/6270) ([2d7803a](https://github.com/lobehub/lobe-chat/commit/2d7803a))
@@ -1907,15 +1872,23 @@
-### [Version 1.15.20](https://github.com/lobehub/lobe-chat/compare/v1.15.19...v1.15.20)
+### [Version 1.60.6](https://github.com/lobehub/lobe-chat/compare/v1.60.5...v1.60.6)
-Released on **2024-09-08**
+Released on **2025-02-17**
+
+#### 💄 Styles
+
+- **misc**: Add o1 vision metadata.
Improvements and Fixes
+#### Styles
+
+- **misc**: Add o1 vision metadata, closes [#6263](https://github.com/lobehub/lobe-chat/issues/6263) ([261d068](https://github.com/lobehub/lobe-chat/commit/261d068))
+
@@ -1924,15 +1897,23 @@
-### [Version 1.15.19](https://github.com/lobehub/lobe-chat/compare/v1.15.18...v1.15.19)
+### [Version 1.60.5](https://github.com/lobehub/lobe-chat/compare/v1.60.4...v1.60.5)
-Released on **2024-09-08**
+Released on **2025-02-17**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix loading on not login for db.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix loading on not login for db, closes [#6258](https://github.com/lobehub/lobe-chat/issues/6258) ([61692b9](https://github.com/lobehub/lobe-chat/commit/61692b9))
+
@@ -1941,22 +1922,22 @@
-### [Version 1.15.18](https://github.com/lobehub/lobe-chat/compare/v1.15.17...v1.15.18)
+### [Version 1.60.4](https://github.com/lobehub/lobe-chat/compare/v1.60.3...v1.60.4)
-Released on **2024-09-06**
+Released on **2025-02-17**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Support anthropic browser request.
+- **misc**: Fix agent config not load correctly.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Support anthropic browser request, closes [#3798](https://github.com/lobehub/lobe-chat/issues/3798) ([743df51](https://github.com/lobehub/lobe-chat/commit/743df51))
+- **misc**: Fix agent config not load correctly, closes [#6252](https://github.com/lobehub/lobe-chat/issues/6252) ([fe9bc16](https://github.com/lobehub/lobe-chat/commit/fe9bc16))
@@ -1966,13 +1947,13 @@
-### [Version 1.15.17](https://github.com/lobehub/lobe-chat/compare/v1.15.16...v1.15.17)
+### [Version 1.60.3](https://github.com/lobehub/lobe-chat/compare/v1.60.2...v1.60.3)
-Released on **2024-09-06**
+Released on **2025-02-17**
#### 🐛 Bug Fixes
-- **misc**: Fix auth log.
+- **misc**: User feedback for empty/long group names in create/edit group modals.
@@ -1981,7 +1962,7 @@
#### What's fixed
-- **misc**: Fix auth log, closes [#3795](https://github.com/lobehub/lobe-chat/issues/3795) ([71aa405](https://github.com/lobehub/lobe-chat/commit/71aa405))
+- **misc**: User feedback for empty/long group names in create/edit group modals, closes [#6247](https://github.com/lobehub/lobe-chat/issues/6247) ([25c80d1](https://github.com/lobehub/lobe-chat/commit/25c80d1))
@@ -1991,22 +1972,22 @@
-### [Version 1.15.16](https://github.com/lobehub/lobe-chat/compare/v1.15.15...v1.15.16)
+### [Version 1.60.2](https://github.com/lobehub/lobe-chat/compare/v1.60.1...v1.60.2)
-Released on **2024-09-06**
+Released on **2025-02-17**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Update Bedrock model list & add `AWS_BEDROCK_MODEL_LIST` support.
+- **misc**: Fix model list issue in client mode.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Update Bedrock model list & add `AWS_BEDROCK_MODEL_LIST` support, closes [#3723](https://github.com/lobehub/lobe-chat/issues/3723) ([0aad972](https://github.com/lobehub/lobe-chat/commit/0aad972))
+- **misc**: Fix model list issue in client mode, closes [#6240](https://github.com/lobehub/lobe-chat/issues/6240) ([d6c6cda](https://github.com/lobehub/lobe-chat/commit/d6c6cda))
@@ -2016,13 +1997,13 @@
-### [Version 1.15.15](https://github.com/lobehub/lobe-chat/compare/v1.15.14...v1.15.15)
+### [Version 1.60.1](https://github.com/lobehub/lobe-chat/compare/v1.60.0...v1.60.1)
-Released on **2024-09-06**
+Released on **2025-02-17**
#### 💄 Styles
-- **misc**: Add `LLaVA 1.5 7B` model in Groq.
+- **misc**: Update Jina AI Provider name & model info.
@@ -2031,7 +2012,7 @@
#### Styles
-- **misc**: Add `LLaVA 1.5 7B` model in Groq, closes [#3769](https://github.com/lobehub/lobe-chat/issues/3769) ([f78a0b1](https://github.com/lobehub/lobe-chat/commit/f78a0b1))
+- **misc**: Update Jina AI Provider name & model info, closes [#6243](https://github.com/lobehub/lobe-chat/issues/6243) ([ddbe482](https://github.com/lobehub/lobe-chat/commit/ddbe482))
@@ -2041,15 +2022,23 @@
-### [Version 1.15.14](https://github.com/lobehub/lobe-chat/compare/v1.15.13...v1.15.14)
+## [Version 1.60.0](https://github.com/lobehub/lobe-chat/compare/v1.59.0...v1.60.0)
-Released on **2024-09-06**
+Released on **2025-02-17**
+
+#### ✨ Features
+
+- **misc**: Add SambaNova provider support.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Add SambaNova provider support, closes [#6218](https://github.com/lobehub/lobe-chat/issues/6218) ([a46eadf](https://github.com/lobehub/lobe-chat/commit/a46eadf))
+
@@ -2058,15 +2047,23 @@
-### [Version 1.15.13](https://github.com/lobehub/lobe-chat/compare/v1.15.12...v1.15.13)
+## [Version 1.59.0](https://github.com/lobehub/lobe-chat/compare/v1.58.0...v1.59.0)
-Released on **2024-09-06**
+Released on **2025-02-16**
+
+#### ✨ Features
+
+- **misc**: Add volcengine as a new provider.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Add volcengine as a new provider, closes [#6221](https://github.com/lobehub/lobe-chat/issues/6221) ([09bf8f0](https://github.com/lobehub/lobe-chat/commit/09bf8f0))
+
@@ -2075,22 +2072,22 @@
-### [Version 1.15.12](https://github.com/lobehub/lobe-chat/compare/v1.15.11...v1.15.12)
+## [Version 1.58.0](https://github.com/lobehub/lobe-chat/compare/v1.57.1...v1.58.0)
-Released on **2024-09-04**
+Released on **2025-02-16**
-#### 🐛 Bug Fixes
+#### ✨ Features
-- **misc**: Fix typo in RAG prompt.
+- **misc**: Add Azure AI as new Provider.
Improvements and Fixes
-#### What's fixed
+#### What's improved
-- **misc**: Fix typo in RAG prompt, closes [#3764](https://github.com/lobehub/lobe-chat/issues/3764) ([ff61fa6](https://github.com/lobehub/lobe-chat/commit/ff61fa6))
+- **misc**: Add Azure AI as new Provider, closes [#6214](https://github.com/lobehub/lobe-chat/issues/6214) ([30e010f](https://github.com/lobehub/lobe-chat/commit/30e010f))
@@ -2100,15 +2097,23 @@
-### [Version 1.15.11](https://github.com/lobehub/lobe-chat/compare/v1.15.10...v1.15.11)
+### [Version 1.57.1](https://github.com/lobehub/lobe-chat/compare/v1.57.0...v1.57.1)
-Released on **2024-09-04**
+Released on **2025-02-16**
+
+#### 💄 Styles
+
+- **misc**: Fix mobile agent settings not show correctly.
Improvements and Fixes
+#### Styles
+
+- **misc**: Fix mobile agent settings not show correctly, closes [#6203](https://github.com/lobehub/lobe-chat/issues/6203) ([0285d95](https://github.com/lobehub/lobe-chat/commit/0285d95))
+
@@ -2117,15 +2122,23 @@
-### [Version 1.15.10](https://github.com/lobehub/lobe-chat/compare/v1.15.9...v1.15.10)
+## [Version 1.57.0](https://github.com/lobehub/lobe-chat/compare/v1.56.5...v1.57.0)
-Released on **2024-09-03**
+Released on **2025-02-16**
+
+#### ✨ Features
+
+- **misc**: Add Jina AI model provider support.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Add Jina AI model provider support, closes [#6140](https://github.com/lobehub/lobe-chat/issues/6140) ([6b4c15b](https://github.com/lobehub/lobe-chat/commit/6b4c15b))
+
@@ -2134,13 +2147,13 @@
-### [Version 1.15.9](https://github.com/lobehub/lobe-chat/compare/v1.15.8...v1.15.9)
+### [Version 1.56.5](https://github.com/lobehub/lobe-chat/compare/v1.56.4...v1.56.5)
-Released on **2024-09-03**
+Released on **2025-02-16**
#### 🐛 Bug Fixes
-- **misc**: Fix speed and rag prompt.
+- **misc**: Match o1 series models more robust in Azure OpenAI provider, set max_completion_tokens to null for Azure OpenAI.
@@ -2149,7 +2162,8 @@
#### What's fixed
-- **misc**: Fix speed and rag prompt, closes [#3751](https://github.com/lobehub/lobe-chat/issues/3751) ([dce200c](https://github.com/lobehub/lobe-chat/commit/dce200c))
+- **misc**: Match o1 series models more robust in Azure OpenAI provider, closes [#6193](https://github.com/lobehub/lobe-chat/issues/6193) ([f444e66](https://github.com/lobehub/lobe-chat/commit/f444e66))
+- **misc**: Set max_completion_tokens to null for Azure OpenAI, closes [#6198](https://github.com/lobehub/lobe-chat/issues/6198) ([e9e8da4](https://github.com/lobehub/lobe-chat/commit/e9e8da4))
@@ -2159,13 +2173,13 @@
-### [Version 1.15.8](https://github.com/lobehub/lobe-chat/compare/v1.15.7...v1.15.8)
+### [Version 1.56.4](https://github.com/lobehub/lobe-chat/compare/v1.56.3...v1.56.4)
-Released on **2024-09-03**
+Released on **2025-02-16**
#### 🐛 Bug Fixes
-- **misc**: Fix `.PDF` can not be chunked.
+- **misc**: Fix ai provider description not show correctly.
@@ -2174,7 +2188,7 @@
#### What's fixed
-- **misc**: Fix `.PDF` can not be chunked, closes [#3720](https://github.com/lobehub/lobe-chat/issues/3720) ([4244c04](https://github.com/lobehub/lobe-chat/commit/4244c04))
+- **misc**: Fix ai provider description not show correctly, closes [#6199](https://github.com/lobehub/lobe-chat/issues/6199) ([3e8d9c5](https://github.com/lobehub/lobe-chat/commit/3e8d9c5))
@@ -2184,13 +2198,13 @@
-### [Version 1.15.7](https://github.com/lobehub/lobe-chat/compare/v1.15.6...v1.15.7)
+### [Version 1.56.3](https://github.com/lobehub/lobe-chat/compare/v1.56.2...v1.56.3)
-Released on **2024-09-03**
+Released on **2025-02-16**
#### 💄 Styles
-- **misc**: Fix provider disabled title style.
+- **misc**: Improve inbox agent settings.
@@ -2199,7 +2213,7 @@
#### Styles
-- **misc**: Fix provider disabled title style, closes [#3743](https://github.com/lobehub/lobe-chat/issues/3743) ([2c72452](https://github.com/lobehub/lobe-chat/commit/2c72452))
+- **misc**: Improve inbox agent settings, closes [#6197](https://github.com/lobehub/lobe-chat/issues/6197) ([37b70f0](https://github.com/lobehub/lobe-chat/commit/37b70f0))
@@ -2209,23 +2223,22 @@
-### [Version 1.15.6](https://github.com/lobehub/lobe-chat/compare/v1.15.5...v1.15.6)
+### [Version 1.56.2](https://github.com/lobehub/lobe-chat/compare/v1.56.1...v1.56.2)
-Released on **2024-09-01**
+Released on **2025-02-16**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Stepfun default enabled model, update Groq model list & add `GROQ_MODEL_LIST` support.
+- **misc**: Fix inbox agent can not save config.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Stepfun default enabled model, closes [#3712](https://github.com/lobehub/lobe-chat/issues/3712) ([7e41d54](https://github.com/lobehub/lobe-chat/commit/7e41d54))
-- **misc**: Update Groq model list & add `GROQ_MODEL_LIST` support, closes [#3716](https://github.com/lobehub/lobe-chat/issues/3716) ([75c9247](https://github.com/lobehub/lobe-chat/commit/75c9247))
+- **misc**: Fix inbox agent can not save config, closes [#6186](https://github.com/lobehub/lobe-chat/issues/6186) ([588cba7](https://github.com/lobehub/lobe-chat/commit/588cba7))
@@ -2235,22 +2248,22 @@
-### [Version 1.15.5](https://github.com/lobehub/lobe-chat/compare/v1.15.4...v1.15.5)
+### [Version 1.56.1](https://github.com/lobehub/lobe-chat/compare/v1.56.0...v1.56.1)
-Released on **2024-09-01**
+Released on **2025-02-16**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Update Together AI model list.
+- **misc**: Fix inbox agent edit way in the new mode.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Update Together AI model list, closes [#3713](https://github.com/lobehub/lobe-chat/issues/3713) ([0dde3b1](https://github.com/lobehub/lobe-chat/commit/0dde3b1))
+- **misc**: Fix inbox agent edit way in the new mode, closes [#6190](https://github.com/lobehub/lobe-chat/issues/6190) ([6398362](https://github.com/lobehub/lobe-chat/commit/6398362))
@@ -2260,22 +2273,22 @@
-### [Version 1.15.4](https://github.com/lobehub/lobe-chat/compare/v1.15.3...v1.15.4)
+## [Version 1.56.0](https://github.com/lobehub/lobe-chat/compare/v1.55.4...v1.56.0)
-Released on **2024-09-01**
+Released on **2025-02-15**
-#### 💄 Styles
+#### ✨ Features
-- **misc**: Update Novita AI model info & add `NOVITA_MODEL_LIST` support.
+- **misc**: Add configurable PDF processing method with Unstructured.
Improvements and Fixes
-#### Styles
+#### What's improved
-- **misc**: Update Novita AI model info & add `NOVITA_MODEL_LIST` support, closes [#3715](https://github.com/lobehub/lobe-chat/issues/3715) ([4ab33f6](https://github.com/lobehub/lobe-chat/commit/4ab33f6))
+- **misc**: Add configurable PDF processing method with Unstructured, closes [#5927](https://github.com/lobehub/lobe-chat/issues/5927) ([35fa3ee](https://github.com/lobehub/lobe-chat/commit/35fa3ee))
@@ -2285,13 +2298,13 @@
-### [Version 1.15.3](https://github.com/lobehub/lobe-chat/compare/v1.15.2...v1.15.3)
+### [Version 1.55.4](https://github.com/lobehub/lobe-chat/compare/v1.55.3...v1.55.4)
-Released on **2024-09-01**
+Released on **2025-02-15**
#### 💄 Styles
-- **misc**: Add `*_MODEL_LIST` for Qwen and ZeroOne, fix model info, update Claude 3.5 Sonnet maxOutput vaule.
+- **misc**: Improve mobile params style.
@@ -2300,9 +2313,7 @@
#### Styles
-- **misc**: Add `*_MODEL_LIST` for Qwen and ZeroOne, closes [#3704](https://github.com/lobehub/lobe-chat/issues/3704) ([05419dc](https://github.com/lobehub/lobe-chat/commit/05419dc))
-- **misc**: Fix model info, closes [#3696](https://github.com/lobehub/lobe-chat/issues/3696) ([4d98037](https://github.com/lobehub/lobe-chat/commit/4d98037))
-- **misc**: Update Claude 3.5 Sonnet maxOutput vaule, closes [#3705](https://github.com/lobehub/lobe-chat/issues/3705) ([685bd74](https://github.com/lobehub/lobe-chat/commit/685bd74))
+- **misc**: Improve mobile params style, closes [#6176](https://github.com/lobehub/lobe-chat/issues/6176) ([b5276de](https://github.com/lobehub/lobe-chat/commit/b5276de))
@@ -2312,13 +2323,13 @@
-### [Version 1.15.2](https://github.com/lobehub/lobe-chat/compare/v1.15.1...v1.15.2)
+### [Version 1.55.3](https://github.com/lobehub/lobe-chat/compare/v1.55.2...v1.55.3)
-Released on **2024-08-30**
+Released on **2025-02-15**
#### 💄 Styles
-- **misc**: Update Qwen and Gemini models info.
+- **misc**: Add deepseek r1 distill models for qwen series.
@@ -2327,7 +2338,7 @@
#### Styles
-- **misc**: Update Qwen and Gemini models info, closes [#3693](https://github.com/lobehub/lobe-chat/issues/3693) ([ba01641](https://github.com/lobehub/lobe-chat/commit/ba01641))
+- **misc**: Add deepseek r1 distill models for qwen series, closes [#5850](https://github.com/lobehub/lobe-chat/issues/5850) ([4a96a05](https://github.com/lobehub/lobe-chat/commit/4a96a05))
@@ -2337,22 +2348,22 @@
-### [Version 1.15.1](https://github.com/lobehub/lobe-chat/compare/v1.15.0...v1.15.1)
+### [Version 1.55.2](https://github.com/lobehub/lobe-chat/compare/v1.55.1...v1.55.2)
-Released on **2024-08-30**
+Released on **2025-02-15**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Update the sorting of each provider model.
+- **misc**: Avoid blank reasoning with OpenRouter.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Update the sorting of each provider model, closes [#3689](https://github.com/lobehub/lobe-chat/issues/3689) ([e82c9dd](https://github.com/lobehub/lobe-chat/commit/e82c9dd))
+- **misc**: Avoid blank reasoning with OpenRouter, closes [#6153](https://github.com/lobehub/lobe-chat/issues/6153) ([c2278d1](https://github.com/lobehub/lobe-chat/commit/c2278d1))
@@ -2362,22 +2373,30 @@
-## [Version 1.15.0](https://github.com/lobehub/lobe-chat/compare/v1.14.12...v1.15.0)
+### [Version 1.55.1](https://github.com/lobehub/lobe-chat/compare/v1.55.0...v1.55.1)
-Released on **2024-08-30**
+Released on **2025-02-15**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Add Upstage model provider support.
+- **misc**: Fix Azure OpenAI O1 models and refactor the Azure OpenAI implement.
+
+#### 💄 Styles
+
+- **misc**: Update openrouter model list and descriptions.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Add Upstage model provider support, closes [#3670](https://github.com/lobehub/lobe-chat/issues/3670) ([4b8591b](https://github.com/lobehub/lobe-chat/commit/4b8591b))
+- **misc**: Fix Azure OpenAI O1 models and refactor the Azure OpenAI implement, closes [#6079](https://github.com/lobehub/lobe-chat/issues/6079) ([6a89a8c](https://github.com/lobehub/lobe-chat/commit/6a89a8c))
+
+#### Styles
+
+- **misc**: Update openrouter model list and descriptions, closes [#6160](https://github.com/lobehub/lobe-chat/issues/6160) ([3ce0485](https://github.com/lobehub/lobe-chat/commit/3ce0485))
@@ -2387,23 +2406,22 @@
-### [Version 1.14.12](https://github.com/lobehub/lobe-chat/compare/v1.14.11...v1.14.12)
+## [Version 1.55.0](https://github.com/lobehub/lobe-chat/compare/v1.54.0...v1.55.0)
-Released on **2024-08-30**
+Released on **2025-02-14**
-#### 💄 Styles
+#### ✨ Features
-- **misc**: Fix ms doc file preview, Update the sorting of each provider model.
+- **misc**: Add vLLM provider support.
Improvements and Fixes
-#### Styles
+#### What's improved
-- **misc**: Fix ms doc file preview, closes [#3686](https://github.com/lobehub/lobe-chat/issues/3686) ([2cd78cf](https://github.com/lobehub/lobe-chat/commit/2cd78cf))
-- **misc**: Update the sorting of each provider model, closes [#3688](https://github.com/lobehub/lobe-chat/issues/3688) ([2630bbc](https://github.com/lobehub/lobe-chat/commit/2630bbc))
+- **misc**: Add vLLM provider support, closes [#6154](https://github.com/lobehub/lobe-chat/issues/6154) ([1708e32](https://github.com/lobehub/lobe-chat/commit/1708e32))
@@ -2413,22 +2431,30 @@
-### [Version 1.14.11](https://github.com/lobehub/lobe-chat/compare/v1.14.10...v1.14.11)
+## [Version 1.54.0](https://github.com/lobehub/lobe-chat/compare/v1.53.12...v1.54.0)
-Released on **2024-08-30**
+Released on **2025-02-14**
+
+#### ✨ Features
+
+- **misc**: Add Nvidia NIM provider support.
#### 💄 Styles
-- **misc**: Update Stepfun models info.
+- **misc**: Improve advanced params settings.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Add Nvidia NIM provider support, closes [#6142](https://github.com/lobehub/lobe-chat/issues/6142) ([ab796a7](https://github.com/lobehub/lobe-chat/commit/ab796a7))
+
#### Styles
-- **misc**: Update Stepfun models info, closes [#3685](https://github.com/lobehub/lobe-chat/issues/3685) ([478b40a](https://github.com/lobehub/lobe-chat/commit/478b40a))
+- **misc**: Improve advanced params settings, closes [#6149](https://github.com/lobehub/lobe-chat/issues/6149) ([bf6699c](https://github.com/lobehub/lobe-chat/commit/bf6699c))
@@ -2438,22 +2464,22 @@
-### [Version 1.14.10](https://github.com/lobehub/lobe-chat/compare/v1.14.9...v1.14.10)
+### [Version 1.53.12](https://github.com/lobehub/lobe-chat/compare/v1.53.11...v1.53.12)
-Released on **2024-08-30**
+Released on **2025-02-14**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fix file relative chunks.
+- **misc**: Improve model fetch behavior.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix file relative chunks, closes [#3676](https://github.com/lobehub/lobe-chat/issues/3676) ([afe1906](https://github.com/lobehub/lobe-chat/commit/afe1906))
+- **misc**: Improve model fetch behavior, closes [#6055](https://github.com/lobehub/lobe-chat/issues/6055) ([4c2aaf6](https://github.com/lobehub/lobe-chat/commit/4c2aaf6))
@@ -2463,15 +2489,23 @@
-### [Version 1.14.9](https://github.com/lobehub/lobe-chat/compare/v1.14.8...v1.14.9)
+### [Version 1.53.11](https://github.com/lobehub/lobe-chat/compare/v1.53.10...v1.53.11)
-Released on **2024-08-29**
+Released on **2025-02-13**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix provider form api key.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix provider form api key, closes [#6115](https://github.com/lobehub/lobe-chat/issues/6115) ([d074238](https://github.com/lobehub/lobe-chat/commit/d074238))
+
@@ -2480,13 +2514,13 @@
-### [Version 1.14.8](https://github.com/lobehub/lobe-chat/compare/v1.14.7...v1.14.8)
+### [Version 1.53.10](https://github.com/lobehub/lobe-chat/compare/v1.53.9...v1.53.10)
-Released on **2024-08-29**
+Released on **2025-02-13**
#### 🐛 Bug Fixes
-- **misc**: Fix whisper-1 typo.
+- **misc**: Fix api key input issue.
@@ -2495,7 +2529,7 @@
#### What's fixed
-- **misc**: Fix whisper-1 typo, closes [#3665](https://github.com/lobehub/lobe-chat/issues/3665) ([084c971](https://github.com/lobehub/lobe-chat/commit/084c971))
+- **misc**: Fix api key input issue, closes [#6112](https://github.com/lobehub/lobe-chat/issues/6112) ([48e3b85](https://github.com/lobehub/lobe-chat/commit/48e3b85))
@@ -2505,30 +2539,22 @@
-### [Version 1.14.7](https://github.com/lobehub/lobe-chat/compare/v1.14.6...v1.14.7)
-
-Released on **2024-08-28**
-
-#### 🐛 Bug Fixes
+### [Version 1.53.9](https://github.com/lobehub/lobe-chat/compare/v1.53.8...v1.53.9)
-- **misc**: Disable ChatGPT-4o Tools Calling.
+Released on **2025-02-13**
#### 💄 Styles
-- **misc**: Improve chunk and file preview.
+- **misc**: Support select check models.
Improvements and Fixes
-#### What's fixed
-
-- **misc**: Disable ChatGPT-4o Tools Calling, closes [#3659](https://github.com/lobehub/lobe-chat/issues/3659) ([c94077d](https://github.com/lobehub/lobe-chat/commit/c94077d))
-
#### Styles
-- **misc**: Improve chunk and file preview, closes [#3658](https://github.com/lobehub/lobe-chat/issues/3658) ([4c9155c](https://github.com/lobehub/lobe-chat/commit/4c9155c))
+- **misc**: Support select check models, closes [#6106](https://github.com/lobehub/lobe-chat/issues/6106) ([2243bbb](https://github.com/lobehub/lobe-chat/commit/2243bbb))
@@ -2538,22 +2564,22 @@
-### [Version 1.14.6](https://github.com/lobehub/lobe-chat/compare/v1.14.5...v1.14.6)
+### [Version 1.53.8](https://github.com/lobehub/lobe-chat/compare/v1.53.7...v1.53.8)
-Released on **2024-08-28**
+Released on **2025-02-13**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Update Gemini models.
+- **misc**: Fix model fetch for spark and fix the support of model reset.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Update Gemini models, closes [#3653](https://github.com/lobehub/lobe-chat/issues/3653) ([b61ca4c](https://github.com/lobehub/lobe-chat/commit/b61ca4c))
+- **misc**: Fix model fetch for spark and fix the support of model reset, closes [#6080](https://github.com/lobehub/lobe-chat/issues/6080) ([257fda1](https://github.com/lobehub/lobe-chat/commit/257fda1))
@@ -2563,22 +2589,22 @@
-### [Version 1.14.5](https://github.com/lobehub/lobe-chat/compare/v1.14.4...v1.14.5)
+### [Version 1.53.7](https://github.com/lobehub/lobe-chat/compare/v1.53.6...v1.53.7)
-Released on **2024-08-28**
+Released on **2025-02-13**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: No user name if Cloudflare Zero Trust with onetimepin.
+- **misc**: Update model list.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: No user name if Cloudflare Zero Trust with onetimepin, closes [#3649](https://github.com/lobehub/lobe-chat/issues/3649) ([5bfee5a](https://github.com/lobehub/lobe-chat/commit/5bfee5a))
+- **misc**: Update model list, closes [#6056](https://github.com/lobehub/lobe-chat/issues/6056) ([be0d7f6](https://github.com/lobehub/lobe-chat/commit/be0d7f6))
@@ -2588,22 +2614,22 @@
-### [Version 1.14.4](https://github.com/lobehub/lobe-chat/compare/v1.14.3...v1.14.4)
+### [Version 1.53.6](https://github.com/lobehub/lobe-chat/compare/v1.53.5...v1.53.6)
-Released on **2024-08-28**
+Released on **2025-02-13**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Move model and provider icon components to `@lobehub/icons`.
+- **misc**: Fix not enable models correctly.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Move model and provider icon components to `@lobehub/icons`, closes [#3634](https://github.com/lobehub/lobe-chat/issues/3634) ([5c7e17a](https://github.com/lobehub/lobe-chat/commit/5c7e17a))
+- **misc**: Fix not enable models correctly, closes [#6071](https://github.com/lobehub/lobe-chat/issues/6071) ([b78328e](https://github.com/lobehub/lobe-chat/commit/b78328e))
@@ -2613,13 +2639,13 @@
-### [Version 1.14.3](https://github.com/lobehub/lobe-chat/compare/v1.14.2...v1.14.3)
+### [Version 1.53.5](https://github.com/lobehub/lobe-chat/compare/v1.53.4...v1.53.5)
-Released on **2024-08-27**
+Released on **2025-02-13**
#### 🐛 Bug Fixes
-- **misc**: Improve aysnc error type.
+- **misc**: Fix latex in thinking tag render.
@@ -2628,7 +2654,7 @@
#### What's fixed
-- **misc**: Improve aysnc error type, closes [#3638](https://github.com/lobehub/lobe-chat/issues/3638) ([dbae456](https://github.com/lobehub/lobe-chat/commit/dbae456))
+- **misc**: Fix latex in thinking tag render, closes [#6063](https://github.com/lobehub/lobe-chat/issues/6063) ([7e89b2d](https://github.com/lobehub/lobe-chat/commit/7e89b2d))
@@ -2638,13 +2664,13 @@
-### [Version 1.14.2](https://github.com/lobehub/lobe-chat/compare/v1.14.1...v1.14.2)
+### [Version 1.53.4](https://github.com/lobehub/lobe-chat/compare/v1.53.3...v1.53.4)
-Released on **2024-08-27**
+Released on **2025-02-12**
#### 🐛 Bug Fixes
-- **misc**: Fix agent setting.
+- **misc**: Fix ai model abilities issue.
@@ -2653,7 +2679,7 @@
#### What's fixed
-- **misc**: Fix agent setting, closes [#3633](https://github.com/lobehub/lobe-chat/issues/3633) ([298fddb](https://github.com/lobehub/lobe-chat/commit/298fddb))
+- **misc**: Fix ai model abilities issue, closes [#6060](https://github.com/lobehub/lobe-chat/issues/6060) ([718f477](https://github.com/lobehub/lobe-chat/commit/718f477))
@@ -2663,22 +2689,22 @@
-### [Version 1.14.1](https://github.com/lobehub/lobe-chat/compare/v1.14.0...v1.14.1)
+### [Version 1.53.3](https://github.com/lobehub/lobe-chat/compare/v1.53.2...v1.53.3)
-Released on **2024-08-27**
+Released on **2025-02-12**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Improve zhipu model config.
+- **misc**: Fix tencent cloud api issue.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Improve zhipu model config, closes [#3635](https://github.com/lobehub/lobe-chat/issues/3635) ([1274e6a](https://github.com/lobehub/lobe-chat/commit/1274e6a))
+- **misc**: Fix tencent cloud api issue, closes [#6058](https://github.com/lobehub/lobe-chat/issues/6058) ([025d0bc](https://github.com/lobehub/lobe-chat/commit/025d0bc))
@@ -2688,22 +2714,22 @@
-## [Version 1.14.0](https://github.com/lobehub/lobe-chat/compare/v1.13.2...v1.14.0)
+### [Version 1.53.2](https://github.com/lobehub/lobe-chat/compare/v1.53.1...v1.53.2)
-Released on **2024-08-27**
+Released on **2025-02-12**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Supports Cloudflare Zero Trust login.
+- **misc**: Disable openrouter client fetch.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Supports Cloudflare Zero Trust login, closes [#3624](https://github.com/lobehub/lobe-chat/issues/3624) ([ac2bf68](https://github.com/lobehub/lobe-chat/commit/ac2bf68))
+- **misc**: Disable openrouter client fetch, closes [#6043](https://github.com/lobehub/lobe-chat/issues/6043) ([63b22ce](https://github.com/lobehub/lobe-chat/commit/63b22ce))
@@ -2713,13 +2739,13 @@
-### [Version 1.13.2](https://github.com/lobehub/lobe-chat/compare/v1.13.1...v1.13.2)
+### [Version 1.53.1](https://github.com/lobehub/lobe-chat/compare/v1.53.0...v1.53.1)
-Released on **2024-08-27**
+Released on **2025-02-12**
#### 🐛 Bug Fixes
-- **misc**: Bypass vercel deployment protection, fix can send message on uploading files.
+- **misc**: Fix reasoning output for OpenRouter reasoning models like deepseek-r1.
@@ -2728,8 +2754,7 @@
#### What's fixed
-- **misc**: Bypass vercel deployment protection, closes [#3627](https://github.com/lobehub/lobe-chat/issues/3627) ([47da20d](https://github.com/lobehub/lobe-chat/commit/47da20d))
-- **misc**: Fix can send message on uploading files, closes [#3618](https://github.com/lobehub/lobe-chat/issues/3618) ([fe4329a](https://github.com/lobehub/lobe-chat/commit/fe4329a))
+- **misc**: Fix reasoning output for OpenRouter reasoning models like deepseek-r1, closes [#5903](https://github.com/lobehub/lobe-chat/issues/5903) [#5766](https://github.com/lobehub/lobe-chat/issues/5766) ([bfd9317](https://github.com/lobehub/lobe-chat/commit/bfd9317))
@@ -2739,22 +2764,31 @@
-### [Version 1.13.1](https://github.com/lobehub/lobe-chat/compare/v1.13.0...v1.13.1)
+## [Version 1.53.0](https://github.com/lobehub/lobe-chat/compare/v1.52.19...v1.53.0)
-Released on **2024-08-27**
+Released on **2025-02-11**
+
+#### ✨ Features
+
+- **misc**: Support tencent cloud provider.
#### 💄 Styles
-- **misc**: Update Qwen models.
+- **misc**: Update i18n, update provider i18n.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Support tencent cloud provider, closes [#6029](https://github.com/lobehub/lobe-chat/issues/6029) ([6ec6b08](https://github.com/lobehub/lobe-chat/commit/6ec6b08))
+
#### Styles
-- **misc**: Update Qwen models, closes [#3626](https://github.com/lobehub/lobe-chat/issues/3626) ([4393386](https://github.com/lobehub/lobe-chat/commit/4393386))
+- **misc**: Update i18n, closes [#6030](https://github.com/lobehub/lobe-chat/issues/6030) ([ee48e30](https://github.com/lobehub/lobe-chat/commit/ee48e30))
+- **misc**: Update provider i18n, closes [#6031](https://github.com/lobehub/lobe-chat/issues/6031) ([e0e231c](https://github.com/lobehub/lobe-chat/commit/e0e231c))
@@ -2764,22 +2798,22 @@
-## [Version 1.13.0](https://github.com/lobehub/lobe-chat/compare/v1.12.20...v1.13.0)
+### [Version 1.52.19](https://github.com/lobehub/lobe-chat/compare/v1.52.18...v1.52.19)
-Released on **2024-08-27**
+Released on **2025-02-11**
-#### ✨ Features
+#### ♻ Code Refactoring
-- **misc**: Supports Authelia login.
+- **misc**: Refactor the agent runtime test case.
Improvements and Fixes
-#### What's improved
+#### Code refactoring
-- **misc**: Supports Authelia login, closes [#3589](https://github.com/lobehub/lobe-chat/issues/3589) ([2141ae7](https://github.com/lobehub/lobe-chat/commit/2141ae7))
+- **misc**: Refactor the agent runtime test case, closes [#6025](https://github.com/lobehub/lobe-chat/issues/6025) ([3414fdd](https://github.com/lobehub/lobe-chat/commit/3414fdd))
@@ -2789,23 +2823,15 @@
-### [Version 1.12.20](https://github.com/lobehub/lobe-chat/compare/v1.12.19...v1.12.20)
-
-Released on **2024-08-26**
-
-#### 🐛 Bug Fixes
+### [Version 1.52.18](https://github.com/lobehub/lobe-chat/compare/v1.52.17...v1.52.18)
-- **misc**: Feature flag `knowledge_base` doesn't affect ActionBar.
+Released on **2025-02-11** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Feature flag `knowledge_base` doesn't affect ActionBar, closes [#3609](https://github.com/lobehub/lobe-chat/issues/3609) ([1a5286b](https://github.com/lobehub/lobe-chat/commit/1a5286b))
-
@@ -2814,23 +2840,15 @@
-### [Version 1.12.19](https://github.com/lobehub/lobe-chat/compare/v1.12.18...v1.12.19)
-
-Released on **2024-08-25**
-
-#### 🐛 Bug Fixes
+### [Version 1.52.17](https://github.com/lobehub/lobe-chat/compare/v1.52.16...v1.52.17)
-- **misc**: Fix cannot clone agent when imported from client.
+Released on **2025-02-11** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix cannot clone agent when imported from client, closes [#3606](https://github.com/lobehub/lobe-chat/issues/3606) ([1fd2fa0](https://github.com/lobehub/lobe-chat/commit/1fd2fa0))
-
@@ -2839,22 +2857,22 @@
-### [Version 1.12.18](https://github.com/lobehub/lobe-chat/compare/v1.12.17...v1.12.18)
+### [Version 1.52.16](https://github.com/lobehub/lobe-chat/compare/v1.52.15...v1.52.16)
-Released on **2024-08-25**
+Released on **2025-02-11**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix dayjs error in en-US language.
+- **misc**: Support mistral proxy url.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix dayjs error in en-US language, closes [#3604](https://github.com/lobehub/lobe-chat/issues/3604) ([174f4df](https://github.com/lobehub/lobe-chat/commit/174f4df))
+- **misc**: Support mistral proxy url, closes [#6002](https://github.com/lobehub/lobe-chat/issues/6002) ([dcb465e](https://github.com/lobehub/lobe-chat/commit/dcb465e))
@@ -2864,13 +2882,17 @@
-### [Version 1.12.17](https://github.com/lobehub/lobe-chat/compare/v1.12.16...v1.12.17)
+### [Version 1.52.15](https://github.com/lobehub/lobe-chat/compare/v1.52.14...v1.52.15)
-Released on **2024-08-25**
+Released on **2025-02-10**
#### 🐛 Bug Fixes
-- **misc**: Fix multi file upload dupicate.
+- **misc**: Fix lmstudio baseURL.
+
+#### 💄 Styles
+
+- **misc**: Optimized MaxToken Slider.
@@ -2879,7 +2901,11 @@
#### What's fixed
-- **misc**: Fix multi file upload dupicate, closes [#3603](https://github.com/lobehub/lobe-chat/issues/3603) ([60dbed7](https://github.com/lobehub/lobe-chat/commit/60dbed7))
+- **misc**: Fix lmstudio baseURL, closes [#5988](https://github.com/lobehub/lobe-chat/issues/5988) ([1d19aa6](https://github.com/lobehub/lobe-chat/commit/1d19aa6))
+
+#### Styles
+
+- **misc**: Optimized MaxToken Slider, closes [#5952](https://github.com/lobehub/lobe-chat/issues/5952) ([3cdcb95](https://github.com/lobehub/lobe-chat/commit/3cdcb95))
@@ -2889,22 +2915,22 @@
-### [Version 1.12.16](https://github.com/lobehub/lobe-chat/compare/v1.12.15...v1.12.16)
+### [Version 1.52.14](https://github.com/lobehub/lobe-chat/compare/v1.52.13...v1.52.14)
-Released on **2024-08-24**
+Released on **2025-02-10**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Session not found error on mobile.
+- **misc**: Refactor agent settings modal.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Session not found error on mobile, closes [#3428](https://github.com/lobehub/lobe-chat/issues/3428) ([7e9c15e](https://github.com/lobehub/lobe-chat/commit/7e9c15e))
+- **misc**: Refactor agent settings modal, closes [#5987](https://github.com/lobehub/lobe-chat/issues/5987) ([6482f8a](https://github.com/lobehub/lobe-chat/commit/6482f8a))
@@ -2914,15 +2940,24 @@
-### [Version 1.12.15](https://github.com/lobehub/lobe-chat/compare/v1.12.14...v1.12.15)
+### [Version 1.52.13](https://github.com/lobehub/lobe-chat/compare/v1.52.12...v1.52.13)
-Released on **2024-08-24**
+Released on **2025-02-10**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix Aliyun deepseek-r1 reasoning parsing with oneapi, Support Aliyun deepseek-r1 reasoning.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix Aliyun deepseek-r1 reasoning parsing with oneapi, closes [#5964](https://github.com/lobehub/lobe-chat/issues/5964) ([0d7e665](https://github.com/lobehub/lobe-chat/commit/0d7e665))
+- **misc**: Support Aliyun deepseek-r1 reasoning, closes [#5954](https://github.com/lobehub/lobe-chat/issues/5954) ([cf7a2d6](https://github.com/lobehub/lobe-chat/commit/cf7a2d6))
+
@@ -2931,13 +2966,13 @@
-### [Version 1.12.14](https://github.com/lobehub/lobe-chat/compare/v1.12.13...v1.12.14)
+### [Version 1.52.12](https://github.com/lobehub/lobe-chat/compare/v1.52.11...v1.52.12)
-Released on **2024-08-24**
+Released on **2025-02-10**
#### 🐛 Bug Fixes
-- **misc**: Fix tts file saving in server mode.
+- **misc**: Fix language incorrect on page hydration.
@@ -2946,7 +2981,7 @@
#### What's fixed
-- **misc**: Fix tts file saving in server mode, closes [#3585](https://github.com/lobehub/lobe-chat/issues/3585) ([ab1cb47](https://github.com/lobehub/lobe-chat/commit/ab1cb47))
+- **misc**: Fix language incorrect on page hydration, closes [#5970](https://github.com/lobehub/lobe-chat/issues/5970) ([91912cf](https://github.com/lobehub/lobe-chat/commit/91912cf))
@@ -2956,13 +2991,13 @@
-### [Version 1.12.13](https://github.com/lobehub/lobe-chat/compare/v1.12.12...v1.12.13)
+### [Version 1.52.11](https://github.com/lobehub/lobe-chat/compare/v1.52.10...v1.52.11)
-Released on **2024-08-24**
+Released on **2025-02-10**
#### 💄 Styles
-- **misc**: Update 01.AI models.
+- **misc**: Support Mermaid in Artifacts.
@@ -2971,7 +3006,7 @@
#### Styles
-- **misc**: Update 01.AI models, closes [#3586](https://github.com/lobehub/lobe-chat/issues/3586) ([c4a7f70](https://github.com/lobehub/lobe-chat/commit/c4a7f70))
+- **misc**: Support Mermaid in Artifacts, closes [#5947](https://github.com/lobehub/lobe-chat/issues/5947) ([892f961](https://github.com/lobehub/lobe-chat/commit/892f961))
@@ -2981,9 +3016,9 @@
-### [Version 1.12.12](https://github.com/lobehub/lobe-chat/compare/v1.12.11...v1.12.12)
+### [Version 1.52.10](https://github.com/lobehub/lobe-chat/compare/v1.52.9...v1.52.10)
-Released on **2024-08-24**
+Released on **2025-02-09**
@@ -2998,13 +3033,13 @@
-### [Version 1.12.11](https://github.com/lobehub/lobe-chat/compare/v1.12.10...v1.12.11)
+### [Version 1.52.9](https://github.com/lobehub/lobe-chat/compare/v1.52.8...v1.52.9)
-Released on **2024-08-23**
+Released on **2025-02-09**
#### 🐛 Bug Fixes
-- **misc**: Remove orphan chunks if there is no related file.
+- **misc**: Fix changelog issue.
@@ -3013,7 +3048,7 @@
#### What's fixed
-- **misc**: Remove orphan chunks if there is no related file, closes [#3578](https://github.com/lobehub/lobe-chat/issues/3578) ([36bcaf3](https://github.com/lobehub/lobe-chat/commit/36bcaf3))
+- **misc**: Fix changelog issue, closes [#5941](https://github.com/lobehub/lobe-chat/issues/5941) ([9df47a3](https://github.com/lobehub/lobe-chat/commit/9df47a3))
@@ -3023,22 +3058,23 @@
-### [Version 1.12.10](https://github.com/lobehub/lobe-chat/compare/v1.12.9...v1.12.10)
+### [Version 1.52.8](https://github.com/lobehub/lobe-chat/compare/v1.52.7...v1.52.8)
-Released on **2024-08-23**
+Released on **2025-02-09**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Refactor and fix dalle.
+- **misc**: Update github model list, Update openrouter model list.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Refactor and fix dalle, closes [#3572](https://github.com/lobehub/lobe-chat/issues/3572) ([8b39b61](https://github.com/lobehub/lobe-chat/commit/8b39b61))
+- **misc**: Update github model list, closes [#5920](https://github.com/lobehub/lobe-chat/issues/5920) ([0676d0a](https://github.com/lobehub/lobe-chat/commit/0676d0a))
+- **misc**: Update openrouter model list, closes [#5919](https://github.com/lobehub/lobe-chat/issues/5919) ([8a185d3](https://github.com/lobehub/lobe-chat/commit/8a185d3))
@@ -3048,13 +3084,17 @@
-### [Version 1.12.9](https://github.com/lobehub/lobe-chat/compare/v1.12.8...v1.12.9)
+### [Version 1.52.7](https://github.com/lobehub/lobe-chat/compare/v1.52.6...v1.52.7)
-Released on **2024-08-23**
+Released on **2025-02-09**
#### 🐛 Bug Fixes
-- **misc**: Improve s3 path-style url.
+- **misc**: Rewrite to local container in docker deployment mode.
+
+#### 💄 Styles
+
+- **misc**: Update Cloudflare models.
@@ -3063,7 +3103,11 @@
#### What's fixed
-- **misc**: Improve s3 path-style url, closes [#3567](https://github.com/lobehub/lobe-chat/issues/3567) ([96bb38a](https://github.com/lobehub/lobe-chat/commit/96bb38a))
+- **misc**: Rewrite to local container in docker deployment mode, closes [#5910](https://github.com/lobehub/lobe-chat/issues/5910) ([f399197](https://github.com/lobehub/lobe-chat/commit/f399197))
+
+#### Styles
+
+- **misc**: Update Cloudflare models, closes [#5899](https://github.com/lobehub/lobe-chat/issues/5899) ([b71206d](https://github.com/lobehub/lobe-chat/commit/b71206d))
@@ -3073,22 +3117,22 @@
-### [Version 1.12.8](https://github.com/lobehub/lobe-chat/compare/v1.12.7...v1.12.8)
+### [Version 1.52.6](https://github.com/lobehub/lobe-chat/compare/v1.52.5...v1.52.6)
-Released on **2024-08-22**
+Released on **2025-02-08**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix `NEXT_PUBLIC_S3_DOMAIN` error on Docker.
+- **misc**: Update ZeroOne models.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix `NEXT_PUBLIC_S3_DOMAIN` error on Docker, closes [#3564](https://github.com/lobehub/lobe-chat/issues/3564) ([bc6b64c](https://github.com/lobehub/lobe-chat/commit/bc6b64c))
+- **misc**: Update ZeroOne models, closes [#5904](https://github.com/lobehub/lobe-chat/issues/5904) ([6e8d1a7](https://github.com/lobehub/lobe-chat/commit/6e8d1a7))
@@ -3098,13 +3142,13 @@
-### [Version 1.12.7](https://github.com/lobehub/lobe-chat/compare/v1.12.6...v1.12.7)
+### [Version 1.52.5](https://github.com/lobehub/lobe-chat/compare/v1.52.4...v1.52.5)
-Released on **2024-08-22**
+Released on **2025-02-08**
#### 🐛 Bug Fixes
-- **misc**: Logout button not shown on mobile view when using nextauth.
+- **misc**: Fix changelog modal.
@@ -3113,7 +3157,7 @@
#### What's fixed
-- **misc**: Logout button not shown on mobile view when using nextauth, closes [#3561](https://github.com/lobehub/lobe-chat/issues/3561) ([0c4efe4](https://github.com/lobehub/lobe-chat/commit/0c4efe4))
+- **misc**: Fix changelog modal, closes [#5906](https://github.com/lobehub/lobe-chat/issues/5906) ([cbc5967](https://github.com/lobehub/lobe-chat/commit/cbc5967))
@@ -3123,22 +3167,22 @@
-### [Version 1.12.6](https://github.com/lobehub/lobe-chat/compare/v1.12.5...v1.12.6)
+### [Version 1.52.4](https://github.com/lobehub/lobe-chat/compare/v1.52.3...v1.52.4)
-Released on **2024-08-22**
+Released on **2025-02-08**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Refactor s3 env and support path-style for minio.
+- **misc**: Fix changelog modal.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Refactor s3 env and support path-style for minio, closes [#3559](https://github.com/lobehub/lobe-chat/issues/3559) ([1658403](https://github.com/lobehub/lobe-chat/commit/1658403))
+- **misc**: Fix changelog modal, closes [#5894](https://github.com/lobehub/lobe-chat/issues/5894) ([2a3840b](https://github.com/lobehub/lobe-chat/commit/2a3840b))
@@ -3148,13 +3192,17 @@
-### [Version 1.12.5](https://github.com/lobehub/lobe-chat/compare/v1.12.4...v1.12.5)
+### [Version 1.52.3](https://github.com/lobehub/lobe-chat/compare/v1.52.2...v1.52.3)
-Released on **2024-08-22**
+Released on **2025-02-08**
#### 🐛 Bug Fixes
-- **misc**: Fix clipboard copy issue and improve upload cors feedback.
+- **misc**: Add Zhipu param limit, Fix translation in variants mode.
+
+#### 💄 Styles
+
+- **misc**: Update Gemini 2.0 models.
@@ -3163,7 +3211,12 @@
#### What's fixed
-- **misc**: Fix clipboard copy issue and improve upload cors feedback, closes [#3557](https://github.com/lobehub/lobe-chat/issues/3557) ([86c5a99](https://github.com/lobehub/lobe-chat/commit/86c5a99))
+- **misc**: Add Zhipu param limit, closes [#5858](https://github.com/lobehub/lobe-chat/issues/5858) ([c299d78](https://github.com/lobehub/lobe-chat/commit/c299d78))
+- **misc**: Fix translation in variants mode, closes [#5878](https://github.com/lobehub/lobe-chat/issues/5878) ([fcbc7b9](https://github.com/lobehub/lobe-chat/commit/fcbc7b9))
+
+#### Styles
+
+- **misc**: Update Gemini 2.0 models, closes [#5777](https://github.com/lobehub/lobe-chat/issues/5777) ([89803a5](https://github.com/lobehub/lobe-chat/commit/89803a5))
@@ -3173,13 +3226,13 @@
-### [Version 1.12.4](https://github.com/lobehub/lobe-chat/compare/v1.12.3...v1.12.4)
+### [Version 1.52.2](https://github.com/lobehub/lobe-chat/compare/v1.52.1...v1.52.2)
-Released on **2024-08-22**
+Released on **2025-02-08**
#### 💄 Styles
-- **misc**: Fix link style.
+- **misc**: Add siliconcloud pro models.
@@ -3188,7 +3241,7 @@
#### Styles
-- **misc**: Fix link style, closes [#3552](https://github.com/lobehub/lobe-chat/issues/3552) ([aa936c8](https://github.com/lobehub/lobe-chat/commit/aa936c8))
+- **misc**: Add siliconcloud pro models, closes [#5851](https://github.com/lobehub/lobe-chat/issues/5851) ([9b321e6](https://github.com/lobehub/lobe-chat/commit/9b321e6))
@@ -3198,22 +3251,22 @@
-### [Version 1.12.3](https://github.com/lobehub/lobe-chat/compare/v1.12.2...v1.12.3)
+### [Version 1.52.1](https://github.com/lobehub/lobe-chat/compare/v1.52.0...v1.52.1)
-Released on **2024-08-22**
+Released on **2025-02-08**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Hide settings in repo.
+- **misc**: Fix static relative issues.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Hide settings in repo, closes [#3540](https://github.com/lobehub/lobe-chat/issues/3540) ([86c1165](https://github.com/lobehub/lobe-chat/commit/86c1165))
+- **misc**: Fix static relative issues, closes [#5874](https://github.com/lobehub/lobe-chat/issues/5874) ([419977b](https://github.com/lobehub/lobe-chat/commit/419977b))
@@ -3223,15 +3276,23 @@
-### [Version 1.12.2](https://github.com/lobehub/lobe-chat/compare/v1.12.1...v1.12.2)
+## [Version 1.52.0](https://github.com/lobehub/lobe-chat/compare/v1.51.16...v1.52.0)
-Released on **2024-08-22**
+Released on **2025-02-08**
+
+#### ✨ Features
+
+- **misc**: Refactor the auth condition in Next Auth.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Refactor the auth condition in Next Auth, closes [#5866](https://github.com/lobehub/lobe-chat/issues/5866) ([e529108](https://github.com/lobehub/lobe-chat/commit/e529108))
+
@@ -3240,23 +3301,15 @@
-### [Version 1.12.1](https://github.com/lobehub/lobe-chat/compare/v1.12.0...v1.12.1)
-
-Released on **2024-08-21**
-
-#### 🐛 Bug Fixes
+### [Version 1.51.16](https://github.com/lobehub/lobe-chat/compare/v1.51.15...v1.51.16)
-- **misc**: Fix embeddings multi-insert when there is issues with async task.
+Released on **2025-02-07** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix embeddings multi-insert when there is issues with async task, closes [#3530](https://github.com/lobehub/lobe-chat/issues/3530) ([e2cfff7](https://github.com/lobehub/lobe-chat/commit/e2cfff7))
-
@@ -3265,22 +3318,22 @@
-## [Version 1.12.0](https://github.com/lobehub/lobe-chat/compare/v1.11.9...v1.12.0)
+### [Version 1.51.15](https://github.com/lobehub/lobe-chat/compare/v1.51.14...v1.51.15)
-Released on **2024-08-21**
+Released on **2025-02-07**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Files and knowledge base.
+- **misc**: Fix home next auth error and update pnpm.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Files and knowledge base, closes [#3487](https://github.com/lobehub/lobe-chat/issues/3487) ([6574c01](https://github.com/lobehub/lobe-chat/commit/6574c01))
+- **misc**: Fix home next auth error and update pnpm, closes [#5833](https://github.com/lobehub/lobe-chat/issues/5833) ([aa74d20](https://github.com/lobehub/lobe-chat/commit/aa74d20))
@@ -3290,22 +3343,22 @@
-### [Version 1.11.9](https://github.com/lobehub/lobe-chat/compare/v1.11.8...v1.11.9)
+### [Version 1.51.14](https://github.com/lobehub/lobe-chat/compare/v1.51.13...v1.51.14)
-Released on **2024-08-19**
+Released on **2025-02-07**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fixed bedrock llama model id.
+- **misc**: Update changelog cache and upgrade anthropic sdk.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fixed bedrock llama model id, closes [#3518](https://github.com/lobehub/lobe-chat/issues/3518) ([34b4c69](https://github.com/lobehub/lobe-chat/commit/34b4c69))
+- **misc**: Update changelog cache and upgrade anthropic sdk, closes [#5829](https://github.com/lobehub/lobe-chat/issues/5829) ([620df2f](https://github.com/lobehub/lobe-chat/commit/620df2f))
@@ -3315,22 +3368,22 @@
-### [Version 1.11.8](https://github.com/lobehub/lobe-chat/compare/v1.11.7...v1.11.8)
+### [Version 1.51.13](https://github.com/lobehub/lobe-chat/compare/v1.51.12...v1.51.13)
-Released on **2024-08-19**
+Released on **2025-02-07**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Update zhipu models.
+- **misc**: Fix next auth error.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Update zhipu models, closes [#3509](https://github.com/lobehub/lobe-chat/issues/3509) ([e323b50](https://github.com/lobehub/lobe-chat/commit/e323b50))
+- **misc**: Fix next auth error, closes [#5825](https://github.com/lobehub/lobe-chat/issues/5825) ([4509b7a](https://github.com/lobehub/lobe-chat/commit/4509b7a))
@@ -3340,13 +3393,13 @@
-### [Version 1.11.7](https://github.com/lobehub/lobe-chat/compare/v1.11.6...v1.11.7)
+### [Version 1.51.12](https://github.com/lobehub/lobe-chat/compare/v1.51.11...v1.51.12)
-Released on **2024-08-18**
+Released on **2025-02-07**
#### 🐛 Bug Fixes
-- **misc**: Fix topic scroll issue.
+- **misc**: Try to fix next-auth issue.
@@ -3355,7 +3408,7 @@
#### What's fixed
-- **misc**: Fix topic scroll issue, closes [#3505](https://github.com/lobehub/lobe-chat/issues/3505) ([c719c7a](https://github.com/lobehub/lobe-chat/commit/c719c7a))
+- **misc**: Try to fix next-auth issue, closes [#5813](https://github.com/lobehub/lobe-chat/issues/5813) ([8e316bd](https://github.com/lobehub/lobe-chat/commit/8e316bd))
@@ -3365,22 +3418,22 @@
-### [Version 1.11.6](https://github.com/lobehub/lobe-chat/compare/v1.11.5...v1.11.6)
+### [Version 1.51.11](https://github.com/lobehub/lobe-chat/compare/v1.51.10...v1.51.11)
-Released on **2024-08-18**
+Released on **2025-02-06**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Refactor the `SITE_URL` to `APP_URL`.
+- **misc**: Fix `/file/[id]` 500 issue.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Refactor the `SITE_URL` to `APP_URL`, closes [#3504](https://github.com/lobehub/lobe-chat/issues/3504) ([46bdcea](https://github.com/lobehub/lobe-chat/commit/46bdcea))
+- **misc**: Fix `/file/[id]` 500 issue, closes [#5812](https://github.com/lobehub/lobe-chat/issues/5812) ([9bb387e](https://github.com/lobehub/lobe-chat/commit/9bb387e))
@@ -3390,22 +3443,22 @@
-### [Version 1.11.5](https://github.com/lobehub/lobe-chat/compare/v1.11.4...v1.11.5)
+### [Version 1.51.10](https://github.com/lobehub/lobe-chat/compare/v1.51.9...v1.51.10)
-Released on **2024-08-18**
+Released on **2025-02-06**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Refactor the fetch method to fix `response.undefined`.
+- **misc**: Fix provider 500 issue.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Refactor the fetch method to fix `response.undefined`, closes [#3493](https://github.com/lobehub/lobe-chat/issues/3493) ([30d0609](https://github.com/lobehub/lobe-chat/commit/30d0609))
+- **misc**: Fix provider 500 issue, closes [#5807](https://github.com/lobehub/lobe-chat/issues/5807) ([db860b5](https://github.com/lobehub/lobe-chat/commit/db860b5))
@@ -3415,13 +3468,13 @@
-### [Version 1.11.4](https://github.com/lobehub/lobe-chat/compare/v1.11.3...v1.11.4)
+### [Version 1.51.9](https://github.com/lobehub/lobe-chat/compare/v1.51.8...v1.51.9)
-Released on **2024-08-18**
+Released on **2025-02-06**
#### 💄 Styles
-- **misc**: Add `SILICONCLOUD_MODEL_LIST` & `SILICONCLOUD_PROXY_URL` support for SiliconCloud.
+- **misc**: Update edtion tag display and improve prerender.
@@ -3430,7 +3483,7 @@
#### Styles
-- **misc**: Add `SILICONCLOUD_MODEL_LIST` & `SILICONCLOUD_PROXY_URL` support for SiliconCloud, closes [#3492](https://github.com/lobehub/lobe-chat/issues/3492) ([e41be6d](https://github.com/lobehub/lobe-chat/commit/e41be6d))
+- **misc**: Update edtion tag display and improve prerender, closes [#5800](https://github.com/lobehub/lobe-chat/issues/5800) ([673109b](https://github.com/lobehub/lobe-chat/commit/673109b))
@@ -3440,13 +3493,13 @@
-### [Version 1.11.3](https://github.com/lobehub/lobe-chat/compare/v1.11.2...v1.11.3)
+### [Version 1.51.8](https://github.com/lobehub/lobe-chat/compare/v1.51.7...v1.51.8)
-Released on **2024-08-17**
+Released on **2025-02-06**
#### ♻ Code Refactoring
-- **misc**: Refactor PanelTitle and move commit from file uploading.
+- **misc**: Refactor model fetch method.
@@ -3455,7 +3508,7 @@
#### Code refactoring
-- **misc**: Refactor PanelTitle and move commit from file uploading, closes [#3491](https://github.com/lobehub/lobe-chat/issues/3491) ([d03d9f6](https://github.com/lobehub/lobe-chat/commit/d03d9f6))
+- **misc**: Refactor model fetch method, closes [#5768](https://github.com/lobehub/lobe-chat/issues/5768) ([e406908](https://github.com/lobehub/lobe-chat/commit/e406908))
@@ -3465,15 +3518,23 @@
-### [Version 1.11.2](https://github.com/lobehub/lobe-chat/compare/v1.11.1...v1.11.2)
+### [Version 1.51.7](https://github.com/lobehub/lobe-chat/compare/v1.51.6...v1.51.7)
-Released on **2024-08-17**
+Released on **2025-02-06**
+
+#### 💄 Styles
+
+- **misc**: Add Aliyun deepseek-r1 distill models.
Improvements and Fixes
+#### Styles
+
+- **misc**: Add Aliyun deepseek-r1 distill models, closes [#5769](https://github.com/lobehub/lobe-chat/issues/5769) ([8b68190](https://github.com/lobehub/lobe-chat/commit/8b68190))
+
@@ -3482,13 +3543,13 @@
-### [Version 1.11.1](https://github.com/lobehub/lobe-chat/compare/v1.11.0...v1.11.1)
+### [Version 1.51.6](https://github.com/lobehub/lobe-chat/compare/v1.51.5...v1.51.6)
-Released on **2024-08-15**
+Released on **2025-02-06**
#### 🐛 Bug Fixes
-- **misc**: Make S3 upload ACL setting optional.
+- **misc**: Try to fix discover error.
@@ -3497,7 +3558,7 @@
#### What's fixed
-- **misc**: Make S3 upload ACL setting optional, closes [#3464](https://github.com/lobehub/lobe-chat/issues/3464) ([53a0b47](https://github.com/lobehub/lobe-chat/commit/53a0b47))
+- **misc**: Try to fix discover error, closes [#5794](https://github.com/lobehub/lobe-chat/issues/5794) ([9b7bd99](https://github.com/lobehub/lobe-chat/commit/9b7bd99))
@@ -3507,22 +3568,22 @@
-## [Version 1.11.0](https://github.com/lobehub/lobe-chat/compare/v1.10.1...v1.11.0)
+### [Version 1.51.5](https://github.com/lobehub/lobe-chat/compare/v1.51.4...v1.51.5)
-Released on **2024-08-14**
+Released on **2025-02-06**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Add 2 new models to openai provider.
+- **misc**: Add siliconcloud models.
Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Add 2 new models to openai provider, closes [#3470](https://github.com/lobehub/lobe-chat/issues/3470) ([cc9ffdd](https://github.com/lobehub/lobe-chat/commit/cc9ffdd))
+- **misc**: Add siliconcloud models, closes [#5725](https://github.com/lobehub/lobe-chat/issues/5725) ([e84853c](https://github.com/lobehub/lobe-chat/commit/e84853c))
@@ -3532,9 +3593,9 @@
-### [Version 1.10.1](https://github.com/lobehub/lobe-chat/compare/v1.10.0...v1.10.1)
+### [Version 1.51.4](https://github.com/lobehub/lobe-chat/compare/v1.51.3...v1.51.4)
-Released on **2024-08-14**
+Released on **2025-02-06**
@@ -3549,22 +3610,38 @@
-## [Version 1.10.0](https://github.com/lobehub/lobe-chat/compare/v1.9.8...v1.10.0)
+### [Version 1.51.3](https://github.com/lobehub/lobe-chat/compare/v1.51.2...v1.51.3)
-Released on **2024-08-14**
+Released on **2025-02-05**
-#### ✨ Features
+#### ♻ Code Refactoring
-- **misc**: Add SiliconCloud model provider.
+- **misc**: Refactor Wenxin with LobeOpenAICompatibleFactory.
+
+#### 🐛 Bug Fixes
+
+- **misc**: Artifact Parsing and Rendering Bug Fix for Gemini 2.0 Flash.
+
+#### 💄 Styles
+
+- **misc**: Add Cache, Metadata, FeatureFlag Viewer to DevPanel.
Improvements and Fixes
-#### What's improved
+#### Code refactoring
-- **misc**: Add SiliconCloud model provider, closes [#3092](https://github.com/lobehub/lobe-chat/issues/3092) ([0781dc5](https://github.com/lobehub/lobe-chat/commit/0781dc5))
+- **misc**: Refactor Wenxin with LobeOpenAICompatibleFactory, closes [#5729](https://github.com/lobehub/lobe-chat/issues/5729) ([a90a75e](https://github.com/lobehub/lobe-chat/commit/a90a75e))
+
+#### What's fixed
+
+- **misc**: Artifact Parsing and Rendering Bug Fix for Gemini 2.0 Flash, closes [#5633](https://github.com/lobehub/lobe-chat/issues/5633) ([7d782b1](https://github.com/lobehub/lobe-chat/commit/7d782b1))
+
+#### Styles
+
+- **misc**: Add Cache, Metadata, FeatureFlag Viewer to DevPanel, closes [#5764](https://github.com/lobehub/lobe-chat/issues/5764) ([db4e9c7](https://github.com/lobehub/lobe-chat/commit/db4e9c7))
@@ -3574,13 +3651,13 @@
-### [Version 1.9.8](https://github.com/lobehub/lobe-chat/compare/v1.9.7...v1.9.8)
+### [Version 1.51.2](https://github.com/lobehub/lobe-chat/compare/v1.51.1...v1.51.2)
-Released on **2024-08-13**
+Released on **2025-02-05**
#### 💄 Styles
-- **misc**: Resize the image size in chat message.
+- **misc**: Update model list, add reasoning tag.
@@ -3589,7 +3666,7 @@
#### Styles
-- **misc**: Resize the image size in chat message, closes [#3462](https://github.com/lobehub/lobe-chat/issues/3462) ([37c7429](https://github.com/lobehub/lobe-chat/commit/37c7429))
+- **misc**: Update model list, add reasoning tag, closes [#5696](https://github.com/lobehub/lobe-chat/issues/5696) ([dedd784](https://github.com/lobehub/lobe-chat/commit/dedd784))
@@ -3599,9 +3676,9 @@
-### [Version 1.9.7](https://github.com/lobehub/lobe-chat/compare/v1.9.6...v1.9.7)
+### [Version 1.51.1](https://github.com/lobehub/lobe-chat/compare/v1.51.0...v1.51.1)
-Released on **2024-08-13**
+Released on **2025-02-05**
@@ -3616,15 +3693,32 @@
-### [Version 1.9.6](https://github.com/lobehub/lobe-chat/compare/v1.9.5...v1.9.6)
+## [Version 1.51.0](https://github.com/lobehub/lobe-chat/compare/v1.50.5...v1.51.0)
-Released on **2024-08-09**
+Released on **2025-02-05**
+
+#### ✨ Features
+
+- **misc**: Add reasoning tag support for custom models via UI or ENV.
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix deepseek-v3 & qvq model tag fetch error from SiliconCloud, fix model ability missing.
Improvements and Fixes
+#### What's improved
+
+- **misc**: Add reasoning tag support for custom models via UI or ENV, closes [#5684](https://github.com/lobehub/lobe-chat/issues/5684) ([3499403](https://github.com/lobehub/lobe-chat/commit/3499403))
+
+#### What's fixed
+
+- **misc**: Fix deepseek-v3 & qvq model tag fetch error from SiliconCloud, closes [#5741](https://github.com/lobehub/lobe-chat/issues/5741) ([ee61653](https://github.com/lobehub/lobe-chat/commit/ee61653))
+- **misc**: Fix model ability missing, closes [#5739](https://github.com/lobehub/lobe-chat/issues/5739) ([0e1a022](https://github.com/lobehub/lobe-chat/commit/0e1a022))
+
@@ -3633,13 +3727,13 @@
-### [Version 1.9.5](https://github.com/lobehub/lobe-chat/compare/v1.9.4...v1.9.5)
+### [Version 1.50.5](https://github.com/lobehub/lobe-chat/compare/v1.50.4...v1.50.5)
-Released on **2024-08-08**
+Released on **2025-02-04**
#### 💄 Styles
-- **misc**: Updated AWS bedrock model list.
+- **misc**: Add/Update Aliyun Cloud Models, update GitHub Models.
@@ -3648,7 +3742,8 @@
#### Styles
-- **misc**: Updated AWS bedrock model list, closes [#3315](https://github.com/lobehub/lobe-chat/issues/3315) ([042f2d3](https://github.com/lobehub/lobe-chat/commit/042f2d3))
+- **misc**: Add/Update Aliyun Cloud Models, closes [#5613](https://github.com/lobehub/lobe-chat/issues/5613) ([95cd822](https://github.com/lobehub/lobe-chat/commit/95cd822))
+- **misc**: Update GitHub Models, closes [#5683](https://github.com/lobehub/lobe-chat/issues/5683) ([ed4e048](https://github.com/lobehub/lobe-chat/commit/ed4e048))
@@ -3658,13 +3753,13 @@
-### [Version 1.9.4](https://github.com/lobehub/lobe-chat/compare/v1.9.3...v1.9.4)
+### [Version 1.50.4](https://github.com/lobehub/lobe-chat/compare/v1.50.3...v1.50.4)
-Released on **2024-08-06**
+Released on **2025-02-04**
#### 🐛 Bug Fixes
-- **misc**: Fix import clerk `AuthObject` from public api.
+- **misc**: Fix invalid utf8 character.
@@ -3673,7 +3768,7 @@
#### What's fixed
-- **misc**: Fix import clerk `AuthObject` from public api, closes [#3416](https://github.com/lobehub/lobe-chat/issues/3416) ([af8960d](https://github.com/lobehub/lobe-chat/commit/af8960d))
+- **misc**: Fix invalid utf8 character, closes [#5732](https://github.com/lobehub/lobe-chat/issues/5732) ([2905cb5](https://github.com/lobehub/lobe-chat/commit/2905cb5))
@@ -3683,22 +3778,22 @@
-### [Version 1.9.3](https://github.com/lobehub/lobe-chat/compare/v1.9.2...v1.9.3)
+### [Version 1.50.3](https://github.com/lobehub/lobe-chat/compare/v1.50.2...v1.50.3)
-Released on **2024-08-06**
+Released on **2025-02-04**
-#### ♻ Code Refactoring
+#### 💄 Styles
-- **misc**: Refactor server db schema for better code organize.
+- **misc**: Update model locale.
Improvements and Fixes
-#### Code refactoring
+#### Styles
-- **misc**: Refactor server db schema for better code organize, closes [#3410](https://github.com/lobehub/lobe-chat/issues/3410) ([4743bfd](https://github.com/lobehub/lobe-chat/commit/4743bfd))
+- **misc**: Update model locale, closes [#5731](https://github.com/lobehub/lobe-chat/issues/5731) ([d3d26d7](https://github.com/lobehub/lobe-chat/commit/d3d26d7))
@@ -3708,22 +3803,22 @@
-### [Version 1.9.2](https://github.com/lobehub/lobe-chat/compare/v1.9.1...v1.9.2)
+### [Version 1.50.2](https://github.com/lobehub/lobe-chat/compare/v1.50.1...v1.50.2)
-Released on **2024-08-05**
+Released on **2025-02-04**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **config**: Update Azure model and API versions.
+- **misc**: Fix `o1` series calling issue.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **config**: Update Azure model and API versions, closes [#3405](https://github.com/lobehub/lobe-chat/issues/3405) ([a4938eb](https://github.com/lobehub/lobe-chat/commit/a4938eb))
+- **misc**: Fix `o1` series calling issue, closes [#5714](https://github.com/lobehub/lobe-chat/issues/5714) ([d74653e](https://github.com/lobehub/lobe-chat/commit/d74653e))
@@ -3733,13 +3828,13 @@
-### [Version 1.9.1](https://github.com/lobehub/lobe-chat/compare/v1.9.0...v1.9.1)
+### [Version 1.50.1](https://github.com/lobehub/lobe-chat/compare/v1.50.0...v1.50.1)
-Released on **2024-08-05**
+Released on **2025-02-03**
#### 🐛 Bug Fixes
-- **misc**: Azure modelTag icon display.
+- **misc**: Bind the selected group name in the rename modal..
@@ -3748,7 +3843,7 @@
#### What's fixed
-- **misc**: Azure modelTag icon display, closes [#3394](https://github.com/lobehub/lobe-chat/issues/3394) ([ee6baa8](https://github.com/lobehub/lobe-chat/commit/ee6baa8))
+- **misc**: Bind the selected group name in the rename modal., closes [#5159](https://github.com/lobehub/lobe-chat/issues/5159) ([7da05ce](https://github.com/lobehub/lobe-chat/commit/7da05ce))
@@ -3758,13 +3853,17 @@
-## [Version 1.9.0](https://github.com/lobehub/lobe-chat/compare/v1.8.2...v1.9.0)
+## [Version 1.50.0](https://github.com/lobehub/lobe-chat/compare/v1.49.16...v1.50.0)
-Released on **2024-08-05**
+Released on **2025-02-03**
#### ✨ Features
-- **misc**: Skip login page if only one provider exists.
+- **misc**: Add `o3-mini` support for OpenAI & GitHub Models.
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix parse of deepseek r1 in siliconflow provider.
@@ -3773,7 +3872,11 @@
#### What's improved
-- **misc**: Skip login page if only one provider exists, closes [#3400](https://github.com/lobehub/lobe-chat/issues/3400) ([52da1d8](https://github.com/lobehub/lobe-chat/commit/52da1d8))
+- **misc**: Add `o3-mini` support for OpenAI & GitHub Models, closes [#5657](https://github.com/lobehub/lobe-chat/issues/5657) ([492cfd4](https://github.com/lobehub/lobe-chat/commit/492cfd4))
+
+#### What's fixed
+
+- **misc**: Fix parse of deepseek r1 in siliconflow provider, closes [#5687](https://github.com/lobehub/lobe-chat/issues/5687) ([44e81e2](https://github.com/lobehub/lobe-chat/commit/44e81e2))
@@ -3783,22 +3886,22 @@
-### [Version 1.8.2](https://github.com/lobehub/lobe-chat/compare/v1.8.1...v1.8.2)
+### [Version 1.49.16](https://github.com/lobehub/lobe-chat/compare/v1.49.15...v1.49.16)
-Released on **2024-08-03**
+Released on **2025-02-03**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Add `PROXY_URL` in docker with proxychains-ng.
+- **misc**: Update perplexity models.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Add `PROXY_URL` in docker with proxychains-ng, closes [#3362](https://github.com/lobehub/lobe-chat/issues/3362) ([920de7c](https://github.com/lobehub/lobe-chat/commit/920de7c))
+- **misc**: Update perplexity models, closes [#5624](https://github.com/lobehub/lobe-chat/issues/5624) ([58a86fc](https://github.com/lobehub/lobe-chat/commit/58a86fc))
@@ -3808,13 +3911,13 @@
-### [Version 1.8.1](https://github.com/lobehub/lobe-chat/compare/v1.8.0...v1.8.1)
+### [Version 1.49.15](https://github.com/lobehub/lobe-chat/compare/v1.49.14...v1.49.15)
-Released on **2024-08-03**
+Released on **2025-02-03**
#### 💄 Styles
-- **misc**: Fix `aya`, `mathstral` model tag icon & update ollama model info.
+- **misc**: Update Fireworks check model and fix check error.
@@ -3823,7 +3926,7 @@
#### Styles
-- **misc**: Fix `aya`, `mathstral` model tag icon & update ollama model info, closes [#3382](https://github.com/lobehub/lobe-chat/issues/3382) ([ced95a8](https://github.com/lobehub/lobe-chat/commit/ced95a8))
+- **misc**: Update Fireworks check model and fix check error, closes [#5680](https://github.com/lobehub/lobe-chat/issues/5680) ([64ea539](https://github.com/lobehub/lobe-chat/commit/64ea539))
@@ -3833,22 +3936,22 @@
-## [Version 1.8.0](https://github.com/lobehub/lobe-chat/compare/v1.7.10...v1.8.0)
+### [Version 1.49.14](https://github.com/lobehub/lobe-chat/compare/v1.49.13...v1.49.14)
-Released on **2024-08-02**
+Released on **2025-02-03**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Add NextAuth as authentication service in server database.
+- **misc**: Fix provider update issue.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Add NextAuth as authentication service in server database, closes [#2935](https://github.com/lobehub/lobe-chat/issues/2935) ([5a0b972](https://github.com/lobehub/lobe-chat/commit/5a0b972))
+- **misc**: Fix provider update issue, closes [#5676](https://github.com/lobehub/lobe-chat/issues/5676) ([e5d81ea](https://github.com/lobehub/lobe-chat/commit/e5d81ea))
@@ -3858,22 +3961,22 @@
-### [Version 1.7.10](https://github.com/lobehub/lobe-chat/compare/v1.7.9...v1.7.10)
+### [Version 1.49.13](https://github.com/lobehub/lobe-chat/compare/v1.49.12...v1.49.13)
-Released on **2024-08-02**
+Released on **2025-02-03**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Add Gemini 1.5 Pro Exp model.
+- **misc**: Optimize requests without historical messages.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Add Gemini 1.5 Pro Exp model, closes [#3384](https://github.com/lobehub/lobe-chat/issues/3384) ([0de8b7b](https://github.com/lobehub/lobe-chat/commit/0de8b7b))
+- **misc**: Optimize requests without historical messages, closes [#5174](https://github.com/lobehub/lobe-chat/issues/5174) ([182f8d9](https://github.com/lobehub/lobe-chat/commit/182f8d9))
@@ -3883,17 +3986,13 @@
-### [Version 1.7.9](https://github.com/lobehub/lobe-chat/compare/v1.7.8...v1.7.9)
+### [Version 1.49.12](https://github.com/lobehub/lobe-chat/compare/v1.49.11...v1.49.12)
-Released on **2024-08-01**
+Released on **2025-02-02**
#### 🐛 Bug Fixes
-- **misc**: Fix Mistral models calling & update model info.
-
-#### 💄 Styles
-
-- **misc**: Fix stepfun & baichuan model tag icon missing, update Perplexity models.
+- **misc**: Fix can not stop generating.
@@ -3902,12 +4001,7 @@
#### What's fixed
-- **misc**: Fix Mistral models calling & update model info, closes [#3377](https://github.com/lobehub/lobe-chat/issues/3377) [#3098](https://github.com/lobehub/lobe-chat/issues/3098) ([66274d0](https://github.com/lobehub/lobe-chat/commit/66274d0))
-
-#### Styles
-
-- **misc**: Fix stepfun & baichuan model tag icon missing, closes [#3379](https://github.com/lobehub/lobe-chat/issues/3379) ([e283ef4](https://github.com/lobehub/lobe-chat/commit/e283ef4))
-- **misc**: Update Perplexity models, closes [#3380](https://github.com/lobehub/lobe-chat/issues/3380) ([06cb946](https://github.com/lobehub/lobe-chat/commit/06cb946))
+- **misc**: Fix can not stop generating, closes [#5671](https://github.com/lobehub/lobe-chat/issues/5671) ([ae39c35](https://github.com/lobehub/lobe-chat/commit/ae39c35))
@@ -3917,22 +4011,22 @@
-### [Version 1.7.8](https://github.com/lobehub/lobe-chat/compare/v1.7.7...v1.7.8)
+### [Version 1.49.11](https://github.com/lobehub/lobe-chat/compare/v1.49.10...v1.49.11)
-Released on **2024-07-30**
+Released on **2025-02-02**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **ui**: Modify and repair UI layout.
+- **misc**: Fix ollama intergration checker and client fetch issue.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **ui**: Modify and repair UI layout, closes [#3321](https://github.com/lobehub/lobe-chat/issues/3321) ([cda776f](https://github.com/lobehub/lobe-chat/commit/cda776f))
+- **misc**: Fix ollama intergration checker and client fetch issue, closes [#5665](https://github.com/lobehub/lobe-chat/issues/5665) ([cd09a07](https://github.com/lobehub/lobe-chat/commit/cd09a07))
@@ -3942,22 +4036,22 @@
-### [Version 1.7.7](https://github.com/lobehub/lobe-chat/compare/v1.7.6...v1.7.7)
+### [Version 1.49.10](https://github.com/lobehub/lobe-chat/compare/v1.49.9...v1.49.10)
-Released on **2024-07-30**
+Released on **2025-02-02**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Improve tools calling UI.
+- **misc**: Fix `` tag crash with special markdown content.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Improve tools calling UI, closes [#3326](https://github.com/lobehub/lobe-chat/issues/3326) ([36cabc0](https://github.com/lobehub/lobe-chat/commit/36cabc0))
+- **misc**: Fix `` tag crash with special markdown content, closes [#5670](https://github.com/lobehub/lobe-chat/issues/5670) ([b719522](https://github.com/lobehub/lobe-chat/commit/b719522))
@@ -3967,22 +4061,22 @@
-### [Version 1.7.6](https://github.com/lobehub/lobe-chat/compare/v1.7.5...v1.7.6)
+### [Version 1.49.9](https://github.com/lobehub/lobe-chat/compare/v1.49.8...v1.49.9)
-Released on **2024-07-29**
+Released on **2025-02-01**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Disable anthropic browser request.
+- **misc**: Update siliconcloud models.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Disable anthropic browser request, closes [#3359](https://github.com/lobehub/lobe-chat/issues/3359) ([a519837](https://github.com/lobehub/lobe-chat/commit/a519837))
+- **misc**: Update siliconcloud models, closes [#5647](https://github.com/lobehub/lobe-chat/issues/5647) ([4b41ad4](https://github.com/lobehub/lobe-chat/commit/4b41ad4))
@@ -3992,30 +4086,22 @@
-### [Version 1.7.5](https://github.com/lobehub/lobe-chat/compare/v1.7.4...v1.7.5)
-
-Released on **2024-07-29**
-
-#### 🐛 Bug Fixes
+### [Version 1.49.8](https://github.com/lobehub/lobe-chat/compare/v1.49.7...v1.49.8)
-- **misc**: Fix `create_session ` `edit_agent` feature flags and add more flags.
+Released on **2025-02-01**
#### 💄 Styles
-- **misc**: Update 360GPT model (360GPT2 Pro).
+- **misc**: Support thinking for all non DeepSeek official api R1 models.
Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix `create_session ` `edit_agent` feature flags and add more flags, closes [#3289](https://github.com/lobehub/lobe-chat/issues/3289) ([ebfd3cf](https://github.com/lobehub/lobe-chat/commit/ebfd3cf))
-
#### Styles
-- **misc**: Update 360GPT model (360GPT2 Pro), closes [#3339](https://github.com/lobehub/lobe-chat/issues/3339) ([c8ed85e](https://github.com/lobehub/lobe-chat/commit/c8ed85e))
+- **misc**: Support thinking for all non DeepSeek official api R1 models, closes [#5654](https://github.com/lobehub/lobe-chat/issues/5654) ([9b32137](https://github.com/lobehub/lobe-chat/commit/9b32137))
@@ -4025,13 +4111,13 @@
-### [Version 1.7.4](https://github.com/lobehub/lobe-chat/compare/v1.7.3...v1.7.4)
+### [Version 1.49.7](https://github.com/lobehub/lobe-chat/compare/v1.49.6...v1.49.7)
-Released on **2024-07-29**
+Released on **2025-02-01**
#### 🐛 Bug Fixes
-- **misc**: Improve remote model list fetching for Novita AI.
+- **misc**: Multiple deepseek-reasoner request errors.
@@ -4040,7 +4126,7 @@
#### What's fixed
-- **misc**: Improve remote model list fetching for Novita AI, closes [#3311](https://github.com/lobehub/lobe-chat/issues/3311) ([67b9ff0](https://github.com/lobehub/lobe-chat/commit/67b9ff0))
+- **misc**: Multiple deepseek-reasoner request errors, closes [#5601](https://github.com/lobehub/lobe-chat/issues/5601) ([71cc32b](https://github.com/lobehub/lobe-chat/commit/71cc32b))
@@ -4050,13 +4136,13 @@
-### [Version 1.7.3](https://github.com/lobehub/lobe-chat/compare/v1.7.2...v1.7.3)
+### [Version 1.49.6](https://github.com/lobehub/lobe-chat/compare/v1.49.5...v1.49.6)
-Released on **2024-07-28**
+Released on **2025-01-30**
#### 🐛 Bug Fixes
-- **misc**: Update minimax models.
+- **misc**: Support litellm reasoning streaming.
@@ -4065,7 +4151,7 @@
#### What's fixed
-- **misc**: Update minimax models, closes [#3354](https://github.com/lobehub/lobe-chat/issues/3354) ([8113729](https://github.com/lobehub/lobe-chat/commit/8113729))
+- **misc**: Support litellm reasoning streaming, closes [#5632](https://github.com/lobehub/lobe-chat/issues/5632) ([9942fb3](https://github.com/lobehub/lobe-chat/commit/9942fb3))
@@ -4075,13 +4161,13 @@
-### [Version 1.7.2](https://github.com/lobehub/lobe-chat/compare/v1.7.1...v1.7.2)
+### [Version 1.49.5](https://github.com/lobehub/lobe-chat/compare/v1.49.4...v1.49.5)
-Released on **2024-07-26**
+Released on **2025-01-28**
#### 🐛 Bug Fixes
-- **misc**: Avoid baseURL being an empty string, resulting in incorrect client fetch.
+- **misc**: Pin `@clerk/nextjs@6.10.2` to avoid build error.
@@ -4090,7 +4176,7 @@
#### What's fixed
-- **misc**: Avoid baseURL being an empty string, resulting in incorrect client fetch, closes [#3308](https://github.com/lobehub/lobe-chat/issues/3308) ([15a9bc1](https://github.com/lobehub/lobe-chat/commit/15a9bc1))
+- **misc**: Pin `@clerk/nextjs@6.10.2` to avoid build error, closes [#5611](https://github.com/lobehub/lobe-chat/issues/5611) ([deb03ad](https://github.com/lobehub/lobe-chat/commit/deb03ad))
@@ -4100,13 +4186,13 @@
-### [Version 1.7.1](https://github.com/lobehub/lobe-chat/compare/v1.7.0...v1.7.1)
+### [Version 1.49.4](https://github.com/lobehub/lobe-chat/compare/v1.49.3...v1.49.4)
-Released on **2024-07-26**
+Released on **2025-01-28**
#### 🐛 Bug Fixes
-- **misc**: Fix dalle tools calling prompts to avoid content risk.
+- **misc**: Fix changelog locale not showing English.
@@ -4115,7 +4201,7 @@
#### What's fixed
-- **misc**: Fix dalle tools calling prompts to avoid content risk, closes [#3325](https://github.com/lobehub/lobe-chat/issues/3325) ([3e21240](https://github.com/lobehub/lobe-chat/commit/3e21240))
+- **misc**: Fix changelog locale not showing English, closes [#5607](https://github.com/lobehub/lobe-chat/issues/5607) ([9104242](https://github.com/lobehub/lobe-chat/commit/9104242))
@@ -4125,22 +4211,22 @@
-## [Version 1.7.0](https://github.com/lobehub/lobe-chat/compare/v1.6.15...v1.7.0)
+### [Version 1.49.3](https://github.com/lobehub/lobe-chat/compare/v1.49.2...v1.49.3)
-Released on **2024-07-26**
+Released on **2025-01-27**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Enabled function calling on Deepseek models.
+- **misc**: Fix discover ssr hydration error.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Enabled function calling on Deepseek models, closes [#3312](https://github.com/lobehub/lobe-chat/issues/3312) ([35f31cb](https://github.com/lobehub/lobe-chat/commit/35f31cb))
+- **misc**: Fix discover ssr hydration error, closes [#5605](https://github.com/lobehub/lobe-chat/issues/5605) ([e3702a6](https://github.com/lobehub/lobe-chat/commit/e3702a6))
@@ -4150,22 +4236,22 @@
-### [Version 1.6.15](https://github.com/lobehub/lobe-chat/compare/v1.6.14...v1.6.15)
+### [Version 1.49.2](https://github.com/lobehub/lobe-chat/compare/v1.49.1...v1.49.2)
-Released on **2024-07-26**
+Released on **2025-01-27**
-#### 💄 Styles
+#### ♻ Code Refactoring
-- **misc**: Fix file upload height.
+- **misc**: Remove use query.
Improvements and Fixes
-#### Styles
+#### Code refactoring
-- **misc**: Fix file upload height, closes [#3319](https://github.com/lobehub/lobe-chat/issues/3319) ([8343f35](https://github.com/lobehub/lobe-chat/commit/8343f35))
+- **misc**: Remove use query, closes [#5604](https://github.com/lobehub/lobe-chat/issues/5604) ([58c60de](https://github.com/lobehub/lobe-chat/commit/58c60de))
@@ -4175,22 +4261,22 @@
-### [Version 1.6.14](https://github.com/lobehub/lobe-chat/compare/v1.6.13...v1.6.14)
+### [Version 1.49.1](https://github.com/lobehub/lobe-chat/compare/v1.49.0...v1.49.1)
-Released on **2024-07-26**
+Released on **2025-01-27**
-#### 💄 Styles
+#### ♻ Code Refactoring
-- **misc**: Improve input file upload.
+- **misc**: UseMobileWorkspace use nqus to replace useQuery.
Improvements and Fixes
-#### Styles
+#### Code refactoring
-- **misc**: Improve input file upload, closes [#3314](https://github.com/lobehub/lobe-chat/issues/3314) ([de85553](https://github.com/lobehub/lobe-chat/commit/de85553))
+- **misc**: UseMobileWorkspace use nqus to replace useQuery, closes [#5603](https://github.com/lobehub/lobe-chat/issues/5603) ([70e5272](https://github.com/lobehub/lobe-chat/commit/70e5272))
@@ -4200,22 +4286,22 @@
-### [Version 1.6.13](https://github.com/lobehub/lobe-chat/compare/v1.6.12...v1.6.13)
+## [Version 1.49.0](https://github.com/lobehub/lobe-chat/compare/v1.48.4...v1.49.0)
-Released on **2024-07-25**
+Released on **2025-01-27**
-#### 💄 Styles
+#### ✨ Features
-- **misc**: Updated Groq model list to include llama-3.1 and llama3-Groq.
+- **misc**: Support Doubao Models.
Improvements and Fixes
-#### Styles
+#### What's improved
-- **misc**: Updated Groq model list to include llama-3.1 and llama3-Groq, closes [#3313](https://github.com/lobehub/lobe-chat/issues/3313) ([a9cfad6](https://github.com/lobehub/lobe-chat/commit/a9cfad6))
+- **misc**: Support Doubao Models, closes [#5481](https://github.com/lobehub/lobe-chat/issues/5481) ([d8afe47](https://github.com/lobehub/lobe-chat/commit/d8afe47))
@@ -4225,13 +4311,13 @@
-### [Version 1.6.12](https://github.com/lobehub/lobe-chat/compare/v1.6.11...v1.6.12)
+### [Version 1.48.4](https://github.com/lobehub/lobe-chat/compare/v1.48.3...v1.48.4)
-Released on **2024-07-25**
+Released on **2025-01-27**
#### 💄 Styles
-- **misc**: Add new models to groq which are llama 3.1.
+- **misc**: Improve thinking style.
@@ -4240,7 +4326,7 @@
#### Styles
-- **misc**: Add new models to groq which are llama 3.1, closes [#3301](https://github.com/lobehub/lobe-chat/issues/3301) ([ec20fd0](https://github.com/lobehub/lobe-chat/commit/ec20fd0))
+- **misc**: Improve thinking style, closes [#5602](https://github.com/lobehub/lobe-chat/issues/5602) ([d4dc3f2](https://github.com/lobehub/lobe-chat/commit/d4dc3f2))
@@ -4250,22 +4336,22 @@
-### [Version 1.6.11](https://github.com/lobehub/lobe-chat/compare/v1.6.10...v1.6.11)
+### [Version 1.48.3](https://github.com/lobehub/lobe-chat/compare/v1.48.2...v1.48.3)
-Released on **2024-07-24**
+Released on **2025-01-26**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix `UNAUTHORIZED` issue with clerk auth provider.
+- **misc**: Improve model pricing with CNY.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix `UNAUTHORIZED` issue with clerk auth provider, closes [#3299](https://github.com/lobehub/lobe-chat/issues/3299) ([97bea09](https://github.com/lobehub/lobe-chat/commit/97bea09))
+- **misc**: Improve model pricing with CNY, closes [#5599](https://github.com/lobehub/lobe-chat/issues/5599) ([6d91457](https://github.com/lobehub/lobe-chat/commit/6d91457))
@@ -4275,30 +4361,23 @@
-### [Version 1.6.10](https://github.com/lobehub/lobe-chat/compare/v1.6.9...v1.6.10)
-
-Released on **2024-07-23**
-
-#### ♻ Code Refactoring
+### [Version 1.48.2](https://github.com/lobehub/lobe-chat/compare/v1.48.1...v1.48.2)
-- **misc**: Upgrade snapshot version.
+Released on **2025-01-25**
#### 💄 Styles
-- **misc**: Fix the scrolling of the return result area of function calling.
+- **misc**: Add `parallel_tool_calls` support for Qwen, fix tag version and add provider changelog.
Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Upgrade snapshot version, closes [#3296](https://github.com/lobehub/lobe-chat/issues/3296) ([2c14fef](https://github.com/lobehub/lobe-chat/commit/2c14fef))
-
#### Styles
-- **misc**: Fix the scrolling of the return result area of function calling, closes [#3295](https://github.com/lobehub/lobe-chat/issues/3295) ([9c8f469](https://github.com/lobehub/lobe-chat/commit/9c8f469))
+- **misc**: Add `parallel_tool_calls` support for Qwen, closes [#5584](https://github.com/lobehub/lobe-chat/issues/5584) ([b89aeeb](https://github.com/lobehub/lobe-chat/commit/b89aeeb))
+- **misc**: Fix tag version and add provider changelog, closes [#5582](https://github.com/lobehub/lobe-chat/issues/5582) ([63c571b](https://github.com/lobehub/lobe-chat/commit/63c571b))
@@ -4308,15 +4387,23 @@
-### [Version 1.6.9](https://github.com/lobehub/lobe-chat/compare/v1.6.8...v1.6.9)
+### [Version 1.48.1](https://github.com/lobehub/lobe-chat/compare/v1.48.0...v1.48.1)
-Released on **2024-07-23**
+Released on **2025-01-25**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix ollama Browser Request failed in PG mode.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix ollama Browser Request failed in PG mode, closes [#5585](https://github.com/lobehub/lobe-chat/issues/5585) ([b2f3c33](https://github.com/lobehub/lobe-chat/commit/b2f3c33))
+
@@ -4325,22 +4412,22 @@
-### [Version 1.6.8](https://github.com/lobehub/lobe-chat/compare/v1.6.7...v1.6.8)
+## [Version 1.48.0](https://github.com/lobehub/lobe-chat/compare/v1.47.23...v1.48.0)
-Released on **2024-07-23**
+Released on **2025-01-24**
-#### ♻ Code Refactoring
+#### ✨ Features
-- **misc**: Move server modules.
+- **misc**: Support display thinking for DeepSeek R1.
Improvements and Fixes
-#### Code refactoring
+#### What's improved
-- **misc**: Move server modules, closes [#3291](https://github.com/lobehub/lobe-chat/issues/3291) ([c7c9f39](https://github.com/lobehub/lobe-chat/commit/c7c9f39))
+- **misc**: Support display thinking for DeepSeek R1, closes [#5558](https://github.com/lobehub/lobe-chat/issues/5558) ([f98bb5a](https://github.com/lobehub/lobe-chat/commit/f98bb5a))
@@ -4350,13 +4437,13 @@
-### [Version 1.6.7](https://github.com/lobehub/lobe-chat/compare/v1.6.6...v1.6.7)
+### [Version 1.47.23](https://github.com/lobehub/lobe-chat/compare/v1.47.22...v1.47.23)
-Released on **2024-07-23**
+Released on **2025-01-24**
#### 💄 Styles
-- **misc**: Add new model provider Novita AI.
+- **misc**: Fix model fetch match tag error & add Hunyuan model fetch support.
@@ -4365,7 +4452,7 @@
#### Styles
-- **misc**: Add new model provider Novita AI, closes [#3177](https://github.com/lobehub/lobe-chat/issues/3177) ([08b063f](https://github.com/lobehub/lobe-chat/commit/08b063f))
+- **misc**: Fix model fetch match tag error & add Hunyuan model fetch support, closes [#5566](https://github.com/lobehub/lobe-chat/issues/5566) ([7b075ef](https://github.com/lobehub/lobe-chat/commit/7b075ef))
@@ -4375,22 +4462,22 @@
-### [Version 1.6.6](https://github.com/lobehub/lobe-chat/compare/v1.6.5...v1.6.6)
+### [Version 1.47.22](https://github.com/lobehub/lobe-chat/compare/v1.47.21...v1.47.22)
-Released on **2024-07-22**
+Released on **2025-01-24**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **model**: Clear and add models.
+- **misc**: Fix form input in provider.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **model**: Clear and add models, closes [#3208](https://github.com/lobehub/lobe-chat/issues/3208) ([ef54191](https://github.com/lobehub/lobe-chat/commit/ef54191))
+- **misc**: Fix form input in provider, closes [#5571](https://github.com/lobehub/lobe-chat/issues/5571) ([07e2396](https://github.com/lobehub/lobe-chat/commit/07e2396))
@@ -4400,22 +4487,22 @@
-### [Version 1.6.5](https://github.com/lobehub/lobe-chat/compare/v1.6.4...v1.6.5)
+### [Version 1.47.21](https://github.com/lobehub/lobe-chat/compare/v1.47.20...v1.47.21)
-Released on **2024-07-22**
+Released on **2025-01-23**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Content lost unexpectedly on Qwen provider when `finish_reason` is `stop`.
+- **misc**: Add HuggingFace Model: DeepSeek R1.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Content lost unexpectedly on Qwen provider when `finish_reason` is `stop`, closes [#3252](https://github.com/lobehub/lobe-chat/issues/3252) ([d35c5b0](https://github.com/lobehub/lobe-chat/commit/d35c5b0))
+- **misc**: Add HuggingFace Model: DeepSeek R1, closes [#5564](https://github.com/lobehub/lobe-chat/issues/5564) ([66d4edd](https://github.com/lobehub/lobe-chat/commit/66d4edd))
@@ -4425,22 +4512,22 @@
-### [Version 1.6.4](https://github.com/lobehub/lobe-chat/compare/v1.6.3...v1.6.4)
+### [Version 1.47.20](https://github.com/lobehub/lobe-chat/compare/v1.47.19...v1.47.20)
-Released on **2024-07-21**
+Released on **2025-01-23**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Add trpc query client with react-query.
+- **misc**: Fix tts in new provider model.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Add trpc query client with react-query, closes [#3282](https://github.com/lobehub/lobe-chat/issues/3282) ([013ee54](https://github.com/lobehub/lobe-chat/commit/013ee54))
+- **misc**: Fix tts in new provider model, closes [#5569](https://github.com/lobehub/lobe-chat/issues/5569) ([3fef83e](https://github.com/lobehub/lobe-chat/commit/3fef83e))
@@ -4450,13 +4537,13 @@
-### [Version 1.6.3](https://github.com/lobehub/lobe-chat/compare/v1.6.2...v1.6.3)
+### [Version 1.47.19](https://github.com/lobehub/lobe-chat/compare/v1.47.18...v1.47.19)
-Released on **2024-07-21**
+Released on **2025-01-23**
#### 💄 Styles
-- **misc**: Update Zhipu models (GLM-4-AllTools & CodeGeeX-4).
+- **misc**: Add new stepfun model.
@@ -4465,7 +4552,7 @@
#### Styles
-- **misc**: Update Zhipu models (GLM-4-AllTools & CodeGeeX-4), closes [#3255](https://github.com/lobehub/lobe-chat/issues/3255) ([a92939f](https://github.com/lobehub/lobe-chat/commit/a92939f))
+- **misc**: Add new stepfun model, closes [#5560](https://github.com/lobehub/lobe-chat/issues/5560) ([6e027e8](https://github.com/lobehub/lobe-chat/commit/6e027e8))
@@ -4475,13 +4562,13 @@
-### [Version 1.6.2](https://github.com/lobehub/lobe-chat/compare/v1.6.1...v1.6.2)
+### [Version 1.47.18](https://github.com/lobehub/lobe-chat/compare/v1.47.17...v1.47.18)
-Released on **2024-07-21**
+Released on **2025-01-23**
#### 🐛 Bug Fixes
-- **misc**: Fix dayjs render on server.
+- **misc**: Fix debounce issue of provider config.
@@ -4490,7 +4577,7 @@
#### What's fixed
-- **misc**: Fix dayjs render on server, closes [#3278](https://github.com/lobehub/lobe-chat/issues/3278) ([8c08dd5](https://github.com/lobehub/lobe-chat/commit/8c08dd5))
+- **misc**: Fix debounce issue of provider config, closes [#5557](https://github.com/lobehub/lobe-chat/issues/5557) ([c971530](https://github.com/lobehub/lobe-chat/commit/c971530))
@@ -4500,22 +4587,22 @@
-### [Version 1.6.1](https://github.com/lobehub/lobe-chat/compare/v1.6.0...v1.6.1)
+### [Version 1.47.17](https://github.com/lobehub/lobe-chat/compare/v1.47.16...v1.47.17)
-Released on **2024-07-19**
+Released on **2025-01-22**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Refactor the DragUpload.
+- **misc**: Upgrade `react-i18next` to ^15.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Refactor the DragUpload, closes [#3263](https://github.com/lobehub/lobe-chat/issues/3263) ([19186eb](https://github.com/lobehub/lobe-chat/commit/19186eb))
+- **misc**: Upgrade `react-i18next` to ^15, closes [#5553](https://github.com/lobehub/lobe-chat/issues/5553) ([d0275fd](https://github.com/lobehub/lobe-chat/commit/d0275fd))
@@ -4525,47 +4612,30 @@
-## [Version 1.6.0](https://github.com/lobehub/lobe-chat/compare/v1.5.5...v1.6.0)
-
-Released on **2024-07-19**
-
-#### ✨ Features
-
-- **misc**: Add `gpt-4o-mini` in OpenAI Provider and set it as the default model.
-
-
-
-
-Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Add `gpt-4o-mini` in OpenAI Provider and set it as the default model, closes [#3256](https://github.com/lobehub/lobe-chat/issues/3256) ([a84d807](https://github.com/lobehub/lobe-chat/commit/a84d807))
-
-
-
-
-
-### [Version 0.162.20](https://github.com/lobehub/lobe-chat/compare/v0.162.19...v0.162.20)
-
-Released on **2024-06-08**
-
-
+#### What's improved
-
-Improvements and Fixes
+- **misc**: Support thread in client pglite, closes [#5150](https://github.com/lobehub/lobe-chat/issues/5150) ([848b29f](https://github.com/lobehub/lobe-chat/commit/848b29f))
@@ -6388,22 +6408,22 @@
-### [Version 0.162.19](https://github.com/lobehub/lobe-chat/compare/v0.162.18...v0.162.19)
+### [Version 1.37.2](https://github.com/lobehub/lobe-chat/compare/v1.37.1...v1.37.2)
-Released on **2024-06-07**
+Released on **2024-12-22**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fix OpenAi BaseURL in api form.
+- **misc**: Move pglite to client service.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix OpenAi BaseURL in api form, closes [#2806](https://github.com/lobehub/lobe-chat/issues/2806) ([1392957](https://github.com/lobehub/lobe-chat/commit/1392957))
+- **misc**: Move pglite to client service, closes [#5133](https://github.com/lobehub/lobe-chat/issues/5133) ([c2ded24](https://github.com/lobehub/lobe-chat/commit/c2ded24))
@@ -6413,13 +6433,13 @@
-### [Version 0.162.18](https://github.com/lobehub/lobe-chat/compare/v0.162.17...v0.162.18)
+### [Version 1.37.1](https://github.com/lobehub/lobe-chat/compare/v1.37.0...v1.37.1)
-Released on **2024-06-06**
+Released on **2024-12-22**
#### ♻ Code Refactoring
-- **misc**: Refactor model provider implement.
+- **misc**: Refactor the client service to deprecated.
@@ -6428,7 +6448,7 @@
#### Code refactoring
-- **misc**: Refactor model provider implement, closes [#2801](https://github.com/lobehub/lobe-chat/issues/2801) ([7bb4fec](https://github.com/lobehub/lobe-chat/commit/7bb4fec))
+- **misc**: Refactor the client service to deprecated, closes [#5132](https://github.com/lobehub/lobe-chat/issues/5132) ([e603234](https://github.com/lobehub/lobe-chat/commit/e603234))
@@ -6438,22 +6458,22 @@
-### [Version 0.162.17](https://github.com/lobehub/lobe-chat/compare/v0.162.16...v0.162.17)
+## [Version 1.37.0](https://github.com/lobehub/lobe-chat/compare/v1.36.46...v1.37.0)
-Released on **2024-06-04**
+Released on **2024-12-22**
-#### 🐛 Bug Fixes
+#### ✨ Features
-- **misc**: Fix `response.undefined` error with some provider.
+- **misc**: Support to use pglite as client db.
Improvements and Fixes
-#### What's fixed
+#### What's improved
-- **misc**: Fix `response.undefined` error with some provider, closes [#2782](https://github.com/lobehub/lobe-chat/issues/2782) ([5676899](https://github.com/lobehub/lobe-chat/commit/5676899))
+- **misc**: Support to use pglite as client db, closes [#4873](https://github.com/lobehub/lobe-chat/issues/4873) ([4131f20](https://github.com/lobehub/lobe-chat/commit/4131f20))
@@ -6463,15 +6483,23 @@
-### [Version 0.162.16](https://github.com/lobehub/lobe-chat/compare/v0.162.15...v0.162.16)
+### [Version 1.36.46](https://github.com/lobehub/lobe-chat/compare/v1.36.45...v1.36.46)
+
+Released on **2024-12-21**
+
+#### ♻ Code Refactoring
-Released on **2024-06-04**
+- **misc**: Refactor client mode upload to match server mode.
Improvements and Fixes
+#### Code refactoring
+
+- **misc**: Refactor client mode upload to match server mode, closes [#5111](https://github.com/lobehub/lobe-chat/issues/5111) ([0361ced](https://github.com/lobehub/lobe-chat/commit/0361ced))
+
@@ -6480,22 +6508,22 @@
-### [Version 0.162.15](https://github.com/lobehub/lobe-chat/compare/v0.162.14...v0.162.15)
+### [Version 1.36.45](https://github.com/lobehub/lobe-chat/compare/v1.36.44...v1.36.45)
-Released on **2024-06-03**
+Released on **2024-12-21**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix send button loading on only add user message.
+- **misc**: Add o1 model in GitHub models.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix send button loading on only add user message, closes [#2774](https://github.com/lobehub/lobe-chat/issues/2774) ([a7f2982](https://github.com/lobehub/lobe-chat/commit/a7f2982))
+- **misc**: Add o1 model in GitHub models, closes [#5110](https://github.com/lobehub/lobe-chat/issues/5110) ([91dc5d7](https://github.com/lobehub/lobe-chat/commit/91dc5d7))
@@ -6505,13 +6533,13 @@
-### [Version 0.162.14](https://github.com/lobehub/lobe-chat/compare/v0.162.13...v0.162.14)
+### [Version 1.36.44](https://github.com/lobehub/lobe-chat/compare/v1.36.43...v1.36.44)
-Released on **2024-06-03**
+Released on **2024-12-21**
#### 💄 Styles
-- **misc**: Improve loading state.
+- **misc**: Add Gemini flash thinking model.
@@ -6520,7 +6548,7 @@
#### Styles
-- **misc**: Improve loading state, closes [#2767](https://github.com/lobehub/lobe-chat/issues/2767) ([fbdfde9](https://github.com/lobehub/lobe-chat/commit/fbdfde9))
+- **misc**: Add Gemini flash thinking model, closes [#5103](https://github.com/lobehub/lobe-chat/issues/5103) ([c59c1e2](https://github.com/lobehub/lobe-chat/commit/c59c1e2))
@@ -6530,23 +6558,15 @@
-### [Version 0.162.13](https://github.com/lobehub/lobe-chat/compare/v0.162.12...v0.162.13)
-
-Released on **2024-06-01**
+### [Version 1.36.43](https://github.com/lobehub/lobe-chat/compare/v1.36.42...v1.36.43)
-#### 💄 Styles
-
-- **misc**: Improve config upload modal.
+Released on **2024-12-21** Improvements and Fixes
-#### Styles
-
-- **misc**: Improve config upload modal, closes [#2745](https://github.com/lobehub/lobe-chat/issues/2745) ([af9af9f](https://github.com/lobehub/lobe-chat/commit/af9af9f))
-
@@ -6555,22 +6575,22 @@
-### [Version 0.162.12](https://github.com/lobehub/lobe-chat/compare/v0.162.11...v0.162.12)
+### [Version 1.36.42](https://github.com/lobehub/lobe-chat/compare/v1.36.41...v1.36.42)
-Released on **2024-05-31**
+Released on **2024-12-21**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Refactor session meta method.
+- **misc**: Fix HUGGINGFACE endpoint url.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Refactor session meta method, closes [#2737](https://github.com/lobehub/lobe-chat/issues/2737) ([b103c3c](https://github.com/lobehub/lobe-chat/commit/b103c3c))
+- **misc**: Fix HUGGINGFACE endpoint url, closes [#5099](https://github.com/lobehub/lobe-chat/issues/5099) ([abc80dc](https://github.com/lobehub/lobe-chat/commit/abc80dc))
@@ -6580,22 +6600,22 @@
-### [Version 0.162.11](https://github.com/lobehub/lobe-chat/compare/v0.162.10...v0.162.11)
+### [Version 1.36.41](https://github.com/lobehub/lobe-chat/compare/v1.36.40...v1.36.41)
-Released on **2024-05-29**
+Released on **2024-12-21**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fix import config.
+- **misc**: Upgrade react scan.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix import config, closes [#2720](https://github.com/lobehub/lobe-chat/issues/2720) ([a5ddd9a](https://github.com/lobehub/lobe-chat/commit/a5ddd9a))
+- **misc**: Upgrade react scan, closes [#5104](https://github.com/lobehub/lobe-chat/issues/5104) ([eed69dd](https://github.com/lobehub/lobe-chat/commit/eed69dd))
@@ -6605,13 +6625,13 @@
-### [Version 0.162.10](https://github.com/lobehub/lobe-chat/compare/v0.162.9...v0.162.10)
+### [Version 1.36.40](https://github.com/lobehub/lobe-chat/compare/v1.36.39...v1.36.40)
-Released on **2024-05-29**
+Released on **2024-12-20**
#### ♻ Code Refactoring
-- **misc**: Refactor the config import for server import.
+- **misc**: Seperate user keyVaults encrpyto from user model.
@@ -6620,7 +6640,7 @@
#### Code refactoring
-- **misc**: Refactor the config import for server import, closes [#2718](https://github.com/lobehub/lobe-chat/issues/2718) ([d4ee64b](https://github.com/lobehub/lobe-chat/commit/d4ee64b))
+- **misc**: Seperate user keyVaults encrpyto from user model, closes [#5102](https://github.com/lobehub/lobe-chat/issues/5102) ([09b63cf](https://github.com/lobehub/lobe-chat/commit/09b63cf))
@@ -6630,13 +6650,13 @@
-### [Version 0.162.9](https://github.com/lobehub/lobe-chat/compare/v0.162.8...v0.162.9)
+### [Version 1.36.39](https://github.com/lobehub/lobe-chat/compare/v1.36.38...v1.36.39)
-Released on **2024-05-29**
+Released on **2024-12-20**
#### ♻ Code Refactoring
-- **misc**: Refactor the settings to add optimistic updating.
+- **misc**: Refactor to use async `headers()`.
@@ -6645,7 +6665,7 @@
#### Code refactoring
-- **misc**: Refactor the settings to add optimistic updating, closes [#2709](https://github.com/lobehub/lobe-chat/issues/2709) ([fade53e](https://github.com/lobehub/lobe-chat/commit/fade53e))
+- **misc**: Refactor to use async `headers()`, closes [#5097](https://github.com/lobehub/lobe-chat/issues/5097) ([e368f38](https://github.com/lobehub/lobe-chat/commit/e368f38))
@@ -6655,22 +6675,22 @@
-### [Version 0.162.8](https://github.com/lobehub/lobe-chat/compare/v0.162.7...v0.162.8)
+### [Version 1.36.38](https://github.com/lobehub/lobe-chat/compare/v1.36.37...v1.36.38)
-Released on **2024-05-28**
+Released on **2024-12-20**
-#### 💄 Styles
+#### ♻ Code Refactoring
-- **misc**: Add optimistic loading for image uploading.
+- **misc**: Refactor layout props.
Improvements and Fixes
-#### Styles
+#### Code refactoring
-- **misc**: Add optimistic loading for image uploading, closes [#2700](https://github.com/lobehub/lobe-chat/issues/2700) ([f99c9ce](https://github.com/lobehub/lobe-chat/commit/f99c9ce))
+- **misc**: Refactor layout props, closes [#5093](https://github.com/lobehub/lobe-chat/issues/5093) ([2990b5a](https://github.com/lobehub/lobe-chat/commit/2990b5a))
@@ -6680,23 +6700,15 @@
-### [Version 0.162.7](https://github.com/lobehub/lobe-chat/compare/v0.162.6...v0.162.7)
-
-Released on **2024-05-28**
-
-#### 💄 Styles
+### [Version 1.36.37](https://github.com/lobehub/lobe-chat/compare/v1.36.36...v1.36.37)
-- **misc**: Improve display of `set limited history messages`, `randomness` and `voice input`.
+Released on **2024-12-19** Improvements and Fixes
-#### Styles
-
-- **misc**: Improve display of `set limited history messages`, `randomness` and `voice input`, closes [#2586](https://github.com/lobehub/lobe-chat/issues/2586) ([22c9b9c](https://github.com/lobehub/lobe-chat/commit/22c9b9c))
-
@@ -6705,23 +6717,15 @@
-### [Version 0.162.6](https://github.com/lobehub/lobe-chat/compare/v0.162.5...v0.162.6)
-
-Released on **2024-05-28**
+### [Version 1.36.36](https://github.com/lobehub/lobe-chat/compare/v1.36.35...v1.36.36)
-#### 🐛 Bug Fixes
-
-- **misc**: Fix the default agent not work correctly on new device.
+Released on **2024-12-19** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix the default agent not work correctly on new device, closes [#2699](https://github.com/lobehub/lobe-chat/issues/2699) ([e4c7536](https://github.com/lobehub/lobe-chat/commit/e4c7536))
-
@@ -6730,13 +6734,13 @@
-### [Version 0.162.5](https://github.com/lobehub/lobe-chat/compare/v0.162.4...v0.162.5)
+### [Version 1.36.35](https://github.com/lobehub/lobe-chat/compare/v1.36.34...v1.36.35)
-Released on **2024-05-28**
+Released on **2024-12-18**
#### 💄 Styles
-- **misc**: Add `SYSTEM_AGENT` env.
+- **misc**: Improve home page loading for better UX.
@@ -6745,7 +6749,7 @@
#### Styles
-- **misc**: Add `SYSTEM_AGENT` env, closes [#2694](https://github.com/lobehub/lobe-chat/issues/2694) ([0dfcf8d](https://github.com/lobehub/lobe-chat/commit/0dfcf8d))
+- **misc**: Improve home page loading for better UX, closes [#5075](https://github.com/lobehub/lobe-chat/issues/5075) ([99026bb](https://github.com/lobehub/lobe-chat/commit/99026bb))
@@ -6755,13 +6759,13 @@
-### [Version 0.162.4](https://github.com/lobehub/lobe-chat/compare/v0.162.3...v0.162.4)
+### [Version 1.36.34](https://github.com/lobehub/lobe-chat/compare/v1.36.33...v1.36.34)
-Released on **2024-05-28**
+Released on **2024-12-18**
#### 🐛 Bug Fixes
-- **misc**: Fix auto focus issues.
+- **misc**: Fix pdf preview with capital ext.
@@ -6770,7 +6774,7 @@
#### What's fixed
-- **misc**: Fix auto focus issues, closes [#2697](https://github.com/lobehub/lobe-chat/issues/2697) ([8df856e](https://github.com/lobehub/lobe-chat/commit/8df856e))
+- **misc**: Fix pdf preview with capital ext, closes [#5074](https://github.com/lobehub/lobe-chat/issues/5074) ([3f9470f](https://github.com/lobehub/lobe-chat/commit/3f9470f))
@@ -6780,15 +6784,23 @@
-### [Version 0.162.3](https://github.com/lobehub/lobe-chat/compare/v0.162.2...v0.162.3)
+### [Version 1.36.33](https://github.com/lobehub/lobe-chat/compare/v1.36.32...v1.36.33)
+
+Released on **2024-12-18**
+
+#### 🐛 Bug Fixes
-Released on **2024-05-28**
+- **misc**: Fix GitHub model fetch.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix GitHub model fetch, closes [#4645](https://github.com/lobehub/lobe-chat/issues/4645) ([b69dce3](https://github.com/lobehub/lobe-chat/commit/b69dce3))
+
@@ -6797,13 +6809,13 @@
-### [Version 0.162.2](https://github.com/lobehub/lobe-chat/compare/v0.162.1...v0.162.2)
+### [Version 1.36.32](https://github.com/lobehub/lobe-chat/compare/v1.36.31...v1.36.32)
-Released on **2024-05-28**
+Released on **2024-12-17**
#### ♻ Code Refactoring
-- **misc**: Refactor agent store data.
+- **misc**: Refactor the drizzle code style.
@@ -6812,7 +6824,7 @@
#### Code refactoring
-- **misc**: Refactor agent store data, closes [#2690](https://github.com/lobehub/lobe-chat/issues/2690) ([e201937](https://github.com/lobehub/lobe-chat/commit/e201937))
+- **misc**: Refactor the drizzle code style, closes [#5058](https://github.com/lobehub/lobe-chat/issues/5058) ([4057ad3](https://github.com/lobehub/lobe-chat/commit/4057ad3))
@@ -6822,22 +6834,22 @@
-### [Version 0.162.1](https://github.com/lobehub/lobe-chat/compare/v0.162.0...v0.162.1)
+### [Version 1.36.31](https://github.com/lobehub/lobe-chat/compare/v1.36.30...v1.36.31)
-Released on **2024-05-27**
+Released on **2024-12-17**
-#### 💄 Styles
+#### ♻ Code Refactoring
-- **misc**: Improve the display effect of plug-in API name and description.
+- **misc**: Refactor the data fetch with clientDB init check.
Improvements and Fixes
-#### Styles
+#### Code refactoring
-- **misc**: Improve the display effect of plug-in API name and description, closes [#2678](https://github.com/lobehub/lobe-chat/issues/2678) ([19cd0b9](https://github.com/lobehub/lobe-chat/commit/19cd0b9))
+- **misc**: Refactor the data fetch with clientDB init check, closes [#5049](https://github.com/lobehub/lobe-chat/issues/5049) ([e6d2e09](https://github.com/lobehub/lobe-chat/commit/e6d2e09))
@@ -6847,22 +6859,22 @@
-## [Version 0.162.0](https://github.com/lobehub/lobe-chat/compare/v0.161.25...v0.162.0)
+### [Version 1.36.30](https://github.com/lobehub/lobe-chat/compare/v1.36.29...v1.36.30)
-Released on **2024-05-27**
+Released on **2024-12-16**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Support topic agent.
+- **misc**: Improve page loading state.
Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Support topic agent, closes [#2683](https://github.com/lobehub/lobe-chat/issues/2683) ([56865fe](https://github.com/lobehub/lobe-chat/commit/56865fe))
+- **misc**: Improve page loading state, closes [#5048](https://github.com/lobehub/lobe-chat/issues/5048) ([e63249b](https://github.com/lobehub/lobe-chat/commit/e63249b))
@@ -6872,13 +6884,13 @@
-### [Version 0.161.25](https://github.com/lobehub/lobe-chat/compare/v0.161.24...v0.161.25)
+### [Version 1.36.29](https://github.com/lobehub/lobe-chat/compare/v1.36.28...v1.36.29)
-Released on **2024-05-27**
+Released on **2024-12-16**
#### 🐛 Bug Fixes
-- **misc**: Fix trpc/edge path error when setting `NEXT_PUBLIC_BASE_PATH`.
+- **misc**: Fix discover locale with different default lang.
@@ -6887,7 +6899,7 @@
#### What's fixed
-- **misc**: Fix trpc/edge path error when setting `NEXT_PUBLIC_BASE_PATH`, closes [#2681](https://github.com/lobehub/lobe-chat/issues/2681) ([622b390](https://github.com/lobehub/lobe-chat/commit/622b390))
+- **misc**: Fix discover locale with different default lang, closes [#5045](https://github.com/lobehub/lobe-chat/issues/5045) ([915827e](https://github.com/lobehub/lobe-chat/commit/915827e))
@@ -6897,23 +6909,15 @@
-### [Version 0.161.24](https://github.com/lobehub/lobe-chat/compare/v0.161.23...v0.161.24)
-
-Released on **2024-05-27**
+### [Version 1.36.28](https://github.com/lobehub/lobe-chat/compare/v1.36.27...v1.36.28)
-#### 🐛 Bug Fixes
-
-- **misc**: Fix the missing user id in chat compeletition and fix remove unstarred topic not working.
+Released on **2024-12-16** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix the missing user id in chat compeletition and fix remove unstarred topic not working, closes [#2677](https://github.com/lobehub/lobe-chat/issues/2677) ([c9fb2de](https://github.com/lobehub/lobe-chat/commit/c9fb2de))
-
-## [Version 0.160.0](https://github.com/lobehub/lobe-chat/compare/v0.159.12...v0.160.0)
+### [Version 1.35.10](https://github.com/lobehub/lobe-chat/compare/v1.35.9...v1.35.10)
-Released on **2024-05-18**
+Released on **2024-12-03**
-#### ✨ Features
+#### ♻ Code Refactoring
-- **misc**: Bump version and add enable ollama env.
+- **misc**: Refactor the server db model implement.
Improvements and Fixes
-#### What's improved
+#### Code refactoring
-- **misc**: Bump version and add enable ollama env, closes [#2554](https://github.com/lobehub/lobe-chat/issues/2554) ([f5ce7c9](https://github.com/lobehub/lobe-chat/commit/f5ce7c9))
+- **misc**: Refactor the server db model implement, closes [#4878](https://github.com/lobehub/lobe-chat/issues/4878) ([3814853](https://github.com/lobehub/lobe-chat/commit/3814853))
@@ -7754,23 +7720,15 @@
-### [Version 0.159.12](https://github.com/lobehub/lobe-chat/compare/v0.159.11...v0.159.12)
-
-Released on **2024-05-15**
-
-#### ♻ Code Refactoring
+### [Version 1.35.9](https://github.com/lobehub/lobe-chat/compare/v1.35.8...v1.35.9)
-- **misc**: Refactor the create message flow to fix some bugs.
+Released on **2024-12-03** Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Refactor the create message flow to fix some bugs, closes [#2521](https://github.com/lobehub/lobe-chat/issues/2521) ([7263a33](https://github.com/lobehub/lobe-chat/commit/7263a33))
-
@@ -7779,22 +7737,22 @@
-### [Version 0.159.11](https://github.com/lobehub/lobe-chat/compare/v0.159.10...v0.159.11)
+### [Version 1.35.8](https://github.com/lobehub/lobe-chat/compare/v1.35.7...v1.35.8)
-Released on **2024-05-15**
+Released on **2024-12-03**
-#### 💄 Styles
+#### ♻ Code Refactoring
-- **misc**: Add Gemini 1.5 Flash model.
+- **misc**: Move schema and migration folder.
Improvements and Fixes
-#### Styles
+#### Code refactoring
-- **misc**: Add Gemini 1.5 Flash model, closes [#2507](https://github.com/lobehub/lobe-chat/issues/2507) ([5568472](https://github.com/lobehub/lobe-chat/commit/5568472))
+- **misc**: Move schema and migration folder, closes [#4874](https://github.com/lobehub/lobe-chat/issues/4874) ([9aa16d4](https://github.com/lobehub/lobe-chat/commit/9aa16d4))
@@ -7804,23 +7762,15 @@
-### [Version 0.159.10](https://github.com/lobehub/lobe-chat/compare/v0.159.9...v0.159.10)
-
-Released on **2024-05-15**
+### [Version 1.35.7](https://github.com/lobehub/lobe-chat/compare/v1.35.6...v1.35.7)
-#### 💄 Styles
-
-- **misc**: Fix setting modal on responsive and some other style problem.
+Released on **2024-12-03** Improvements and Fixes
-#### Styles
-
-- **misc**: Fix setting modal on responsive and some other style problem, closes [#2512](https://github.com/lobehub/lobe-chat/issues/2512) ([f6b4ca4](https://github.com/lobehub/lobe-chat/commit/f6b4ca4))
-
@@ -7829,22 +7779,30 @@
-### [Version 0.159.9](https://github.com/lobehub/lobe-chat/compare/v0.159.8...v0.159.9)
+### [Version 1.35.6](https://github.com/lobehub/lobe-chat/compare/v1.35.5...v1.35.6)
-Released on **2024-05-14**
+Released on **2024-12-02**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
+
+- **misc**: Add user server api key method in the server mode.
-- **misc**: Fix agent config on page init.
+#### 💄 Styles
+
+- **misc**: Add QwQ 32B Preview model.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix agent config on page init, closes [#2506](https://github.com/lobehub/lobe-chat/issues/2506) ([90e742d](https://github.com/lobehub/lobe-chat/commit/90e742d))
+- **misc**: Add user server api key method in the server mode, closes [#4870](https://github.com/lobehub/lobe-chat/issues/4870) ([875463a](https://github.com/lobehub/lobe-chat/commit/875463a))
+
+#### Styles
+
+- **misc**: Add QwQ 32B Preview model, closes [#4867](https://github.com/lobehub/lobe-chat/issues/4867) ([edd93e0](https://github.com/lobehub/lobe-chat/commit/edd93e0))
@@ -7854,22 +7812,22 @@
-### [Version 0.159.8](https://github.com/lobehub/lobe-chat/compare/v0.159.7...v0.159.8)
+### [Version 1.35.5](https://github.com/lobehub/lobe-chat/compare/v1.35.4...v1.35.5)
-Released on **2024-05-14**
+Released on **2024-12-02**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fix retry issue when hide page.
+- **misc**: Deprecated the current client mode code.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix retry issue when hide page, closes [#2503](https://github.com/lobehub/lobe-chat/issues/2503) ([24489bc](https://github.com/lobehub/lobe-chat/commit/24489bc))
+- **misc**: Deprecated the current client mode code, closes [#4866](https://github.com/lobehub/lobe-chat/issues/4866) ([7dff458](https://github.com/lobehub/lobe-chat/commit/7dff458))
@@ -7879,9 +7837,9 @@
-### [Version 0.159.7](https://github.com/lobehub/lobe-chat/compare/v0.159.6...v0.159.7)
+### [Version 1.35.4](https://github.com/lobehub/lobe-chat/compare/v1.35.3...v1.35.4)
-Released on **2024-05-14**
+Released on **2024-12-02**
@@ -7896,22 +7854,22 @@
-### [Version 0.159.6](https://github.com/lobehub/lobe-chat/compare/v0.159.5...v0.159.6)
+### [Version 1.35.3](https://github.com/lobehub/lobe-chat/compare/v1.35.2...v1.35.3)
-Released on **2024-05-14**
+Released on **2024-12-01**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Login button not show on user panel.
+- **misc**: Add gpt-4o-2024-11-20 model.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Login button not show on user panel, closes [#2496](https://github.com/lobehub/lobe-chat/issues/2496) ([39637fb](https://github.com/lobehub/lobe-chat/commit/39637fb))
+- **misc**: Add gpt-4o-2024-11-20 model, closes [#4855](https://github.com/lobehub/lobe-chat/issues/4855) ([bc3b396](https://github.com/lobehub/lobe-chat/commit/bc3b396))
@@ -7921,13 +7879,13 @@
-### [Version 0.159.5](https://github.com/lobehub/lobe-chat/compare/v0.159.4...v0.159.5)
+### [Version 1.35.2](https://github.com/lobehub/lobe-chat/compare/v1.35.1...v1.35.2)
-Released on **2024-05-14**
+Released on **2024-12-01**
#### 💄 Styles
-- **misc**: Fix scroll and expand.
+- **misc**: Improve i18n.
@@ -7936,7 +7894,7 @@
#### Styles
-- **misc**: Fix scroll and expand, closes [#2470](https://github.com/lobehub/lobe-chat/issues/2470) ([8b1202a](https://github.com/lobehub/lobe-chat/commit/8b1202a))
+- **misc**: Improve i18n, closes [#4857](https://github.com/lobehub/lobe-chat/issues/4857) ([4b7dbc0](https://github.com/lobehub/lobe-chat/commit/4b7dbc0))
@@ -7946,32 +7904,22 @@
-### [Version 0.159.4](https://github.com/lobehub/lobe-chat/compare/v0.159.3...v0.159.4)
-
-Released on **2024-05-14**
+### [Version 1.35.1](https://github.com/lobehub/lobe-chat/compare/v1.35.0...v1.35.1)
-#### 🐛 Bug Fixes
-
-- **misc**: Refresh model config form & mobile footer button lost.
+Released on **2024-12-01**
#### 💄 Styles
-- **misc**: Add GPT-4o model, update perplexity models, updates 01.AI model list.
+- **misc**: Update ollama models.
Improvements and Fixes
-#### What's fixed
-
-- **misc**: Refresh model config form & mobile footer button lost, closes [#2318](https://github.com/lobehub/lobe-chat/issues/2318) [#2319](https://github.com/lobehub/lobe-chat/issues/2319) [#1811](https://github.com/lobehub/lobe-chat/issues/1811) ([eadcefc](https://github.com/lobehub/lobe-chat/commit/eadcefc))
-
#### Styles
-- **misc**: Add GPT-4o model, closes [#2481](https://github.com/lobehub/lobe-chat/issues/2481) ([ae6a03f](https://github.com/lobehub/lobe-chat/commit/ae6a03f))
-- **misc**: Update perplexity models, closes [#2469](https://github.com/lobehub/lobe-chat/issues/2469) ([488cde7](https://github.com/lobehub/lobe-chat/commit/488cde7))
-- **misc**: Updates 01.AI model list, closes [#2471](https://github.com/lobehub/lobe-chat/issues/2471) ([f28711a](https://github.com/lobehub/lobe-chat/commit/f28711a))
+- **misc**: Update ollama models, closes [#4853](https://github.com/lobehub/lobe-chat/issues/4853) ([18f0a3c](https://github.com/lobehub/lobe-chat/commit/18f0a3c))
@@ -7981,22 +7929,22 @@
-### [Version 0.159.3](https://github.com/lobehub/lobe-chat/compare/v0.159.2...v0.159.3)
+## [Version 1.35.0](https://github.com/lobehub/lobe-chat/compare/v1.34.6...v1.35.0)
-Released on **2024-05-14**
+Released on **2024-12-01**
-#### 🐛 Bug Fixes
+#### ✨ Features
-- **misc**: Fix DeepSeek using wrong model ID.
+- **misc**: Support ollama tools use.
Improvements and Fixes
-#### What's fixed
+#### What's improved
-- **misc**: Fix DeepSeek using wrong model ID, closes [#2484](https://github.com/lobehub/lobe-chat/issues/2484) ([465dbfc](https://github.com/lobehub/lobe-chat/commit/465dbfc))
+- **misc**: Support ollama tools use, closes [#3327](https://github.com/lobehub/lobe-chat/issues/3327) ([72d8835](https://github.com/lobehub/lobe-chat/commit/72d8835))
@@ -8006,22 +7954,23 @@
-### [Version 0.159.2](https://github.com/lobehub/lobe-chat/compare/v0.159.1...v0.159.2)
+### [Version 1.34.6](https://github.com/lobehub/lobe-chat/compare/v1.34.5...v1.34.6)
-Released on **2024-05-14**
+Released on **2024-12-01**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Dragging text mistakenly as image.
+- **misc**: Add `QWEN_PROXY_URL` support for Qwen, update model list, add `qwq-32b-preview`.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Dragging text mistakenly as image, closes [#2111](https://github.com/lobehub/lobe-chat/issues/2111) ([3c047ef](https://github.com/lobehub/lobe-chat/commit/3c047ef))
+- **misc**: Add `QWEN_PROXY_URL` support for Qwen, closes [#4842](https://github.com/lobehub/lobe-chat/issues/4842) ([1b8dad6](https://github.com/lobehub/lobe-chat/commit/1b8dad6))
+- **misc**: Update model list, add `qwq-32b-preview`, closes [#4839](https://github.com/lobehub/lobe-chat/issues/4839) ([32b8596](https://github.com/lobehub/lobe-chat/commit/32b8596))
@@ -8031,30 +7980,22 @@
-### [Version 0.159.1](https://github.com/lobehub/lobe-chat/compare/v0.159.0...v0.159.1)
-
-Released on **2024-05-14**
-
-#### ♻ Code Refactoring
+### [Version 1.34.5](https://github.com/lobehub/lobe-chat/compare/v1.34.4...v1.34.5)
-- **misc**: Move next-auth hooks to user store actions.
+Released on **2024-11-28**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Pin `antd@5.17.0` to fix build error.
+- **misc**: Add Google LearnLM model.
Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Move next-auth hooks to user store actions, closes [#2364](https://github.com/lobehub/lobe-chat/issues/2364) ([6dbcd70](https://github.com/lobehub/lobe-chat/commit/6dbcd70))
-
-#### What's fixed
+#### Styles
-- **misc**: Pin `antd@5.17.0` to fix build error, closes [#2483](https://github.com/lobehub/lobe-chat/issues/2483) ([aa03833](https://github.com/lobehub/lobe-chat/commit/aa03833))
+- **misc**: Add Google LearnLM model, closes [#4821](https://github.com/lobehub/lobe-chat/issues/4821) ([f900c0a](https://github.com/lobehub/lobe-chat/commit/f900c0a))
@@ -8064,22 +8005,22 @@
-## [Version 0.159.0](https://github.com/lobehub/lobe-chat/compare/v0.158.2...v0.159.0)
+### [Version 1.34.4](https://github.com/lobehub/lobe-chat/compare/v1.34.3...v1.34.4)
-Released on **2024-05-14**
+Released on **2024-11-27**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Support DeepSeek as new model provider.
+- **misc**: Add switch portal thread.
Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Support DeepSeek as new model provider, closes [#2446](https://github.com/lobehub/lobe-chat/issues/2446) ([18028f3](https://github.com/lobehub/lobe-chat/commit/18028f3))
+- **misc**: Add switch portal thread, closes [#4819](https://github.com/lobehub/lobe-chat/issues/4819) ([8dbf3ce](https://github.com/lobehub/lobe-chat/commit/8dbf3ce))
@@ -8089,22 +8030,22 @@
-### [Version 0.158.2](https://github.com/lobehub/lobe-chat/compare/v0.158.1...v0.158.2)
+### [Version 1.34.3](https://github.com/lobehub/lobe-chat/compare/v1.34.2...v1.34.3)
-Released on **2024-05-13**
+Released on **2024-11-27**
-#### 💄 Styles
+#### 🐛 Bug Fixes
-- **misc**: Fix TelemetryNotification zindex.
+- **misc**: Fix fallback behavior of default mode in AgentRuntime.
Improvements and Fixes
-#### Styles
+#### What's fixed
-- **misc**: Fix TelemetryNotification zindex, closes [#2476](https://github.com/lobehub/lobe-chat/issues/2476) ([54524ab](https://github.com/lobehub/lobe-chat/commit/54524ab))
+- **misc**: Fix fallback behavior of default mode in AgentRuntime, closes [#4813](https://github.com/lobehub/lobe-chat/issues/4813) ([e7cb62e](https://github.com/lobehub/lobe-chat/commit/e7cb62e))
@@ -8114,13 +8055,13 @@
-### [Version 0.158.1](https://github.com/lobehub/lobe-chat/compare/v0.158.0...v0.158.1)
+### [Version 1.34.2](https://github.com/lobehub/lobe-chat/compare/v1.34.1...v1.34.2)
-Released on **2024-05-13**
+Released on **2024-11-27**
#### 💄 Styles
-- **misc**: Add PWA install and metadata & ld generate.
+- **misc**: Improve thread i18n locale.
@@ -8129,7 +8070,7 @@
#### Styles
-- **misc**: Add PWA install and metadata & ld generate, closes [#2438](https://github.com/lobehub/lobe-chat/issues/2438) ([6e9c69a](https://github.com/lobehub/lobe-chat/commit/6e9c69a))
+- **misc**: Improve thread i18n locale, closes [#4807](https://github.com/lobehub/lobe-chat/issues/4807) ([3da1704](https://github.com/lobehub/lobe-chat/commit/3da1704))
@@ -8139,22 +8080,22 @@
-## [Version 0.158.0](https://github.com/lobehub/lobe-chat/compare/v0.157.2...v0.158.0)
+### [Version 1.34.1](https://github.com/lobehub/lobe-chat/compare/v1.34.0...v1.34.1)
-Released on **2024-05-13**
+Released on **2024-11-26**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Add user profile page.
+- **misc**: Fix Qwen baseUrl calling.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Add user profile page, closes [#2433](https://github.com/lobehub/lobe-chat/issues/2433) ([91f7294](https://github.com/lobehub/lobe-chat/commit/91f7294))
+- **misc**: Fix Qwen baseUrl calling, closes [#4799](https://github.com/lobehub/lobe-chat/issues/4799) ([8fd7eb7](https://github.com/lobehub/lobe-chat/commit/8fd7eb7))
@@ -8164,22 +8105,22 @@
-### [Version 0.157.2](https://github.com/lobehub/lobe-chat/compare/v0.157.1...v0.157.2)
+## [Version 1.34.0](https://github.com/lobehub/lobe-chat/compare/v1.33.5...v1.34.0)
-Released on **2024-05-13**
+Released on **2024-11-26**
-#### 🐛 Bug Fixes
+#### ✨ Features
-- **misc**: Fix azure openai stream.
+- **misc**: Forkable Chat Mode.
Improvements and Fixes
-#### What's fixed
+#### What's improved
-- **misc**: Fix azure openai stream, closes [#2465](https://github.com/lobehub/lobe-chat/issues/2465) ([760fe67](https://github.com/lobehub/lobe-chat/commit/760fe67))
+- **misc**: Forkable Chat Mode, closes [#4632](https://github.com/lobehub/lobe-chat/issues/4632) ([832f0ce](https://github.com/lobehub/lobe-chat/commit/832f0ce))
@@ -8189,22 +8130,22 @@
-### [Version 0.157.1](https://github.com/lobehub/lobe-chat/compare/v0.157.0...v0.157.1)
+### [Version 1.33.5](https://github.com/lobehub/lobe-chat/compare/v1.33.4...v1.33.5)
-Released on **2024-05-12**
+Released on **2024-11-26**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix dalle error.
+- **misc**: Update the description translation of Gitee AI.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix dalle error ([7c493de](https://github.com/lobehub/lobe-chat/commit/7c493de))
+- **misc**: Update the description translation of Gitee AI, closes [#4793](https://github.com/lobehub/lobe-chat/issues/4793) ([6f8eddc](https://github.com/lobehub/lobe-chat/commit/6f8eddc))
@@ -8214,22 +8155,22 @@
-## [Version 0.157.0](https://github.com/lobehub/lobe-chat/compare/v0.156.2...v0.157.0)
+### [Version 1.33.4](https://github.com/lobehub/lobe-chat/compare/v1.33.3...v1.33.4)
-Released on **2024-05-11**
+Released on **2024-11-26**
-#### ✨ Features
+#### ♻ Code Refactoring
-- **misc**: upgrade to the new `tool calls` mode.
+- **misc**: Refactor `getLlmOptionsFromPayload` from AgentRuntime.
Improvements and Fixes
-#### What's improved
+#### Code refactoring
-- **misc**: upgrade to the new `tool calls` mode, closes [#2414](https://github.com/lobehub/lobe-chat/issues/2414) ([7404f3b](https://github.com/lobehub/lobe-chat/commit/7404f3b))
+- **misc**: Refactor `getLlmOptionsFromPayload` from AgentRuntime, closes [#4790](https://github.com/lobehub/lobe-chat/issues/4790) ([e8948e6](https://github.com/lobehub/lobe-chat/commit/e8948e6))
@@ -8239,15 +8180,23 @@
-### [Version 0.156.2](https://github.com/lobehub/lobe-chat/compare/v0.156.1...v0.156.2)
+### [Version 1.33.3](https://github.com/lobehub/lobe-chat/compare/v1.33.2...v1.33.3)
+
+Released on **2024-11-25**
-Released on **2024-05-10**
+#### 🐛 Bug Fixes
+
+- **misc**: Fix `fetchOnClient` functional for Moonshot.
Improvements and Fixes
+#### What's fixed
+
+- **misc**: Fix `fetchOnClient` functional for Moonshot, closes [#4787](https://github.com/lobehub/lobe-chat/issues/4787) ([bef89a7](https://github.com/lobehub/lobe-chat/commit/bef89a7))
+
-
-### [Version 0.147.22](https://github.com/lobehub/lobe-chat/compare/v0.147.21...v0.147.22)
-
-Released on **2024-04-19**
-
-
-
-
-Improvements and Fixes
+- **misc**: Add SenseNova (商汤) model provider, closes [#4162](https://github.com/lobehub/lobe-chat/issues/4162) ([7a4e0b3](https://github.com/lobehub/lobe-chat/commit/7a4e0b3))
@@ -10111,13 +10007,13 @@
-### [Version 0.147.21](https://github.com/lobehub/lobe-chat/compare/v0.147.20...v0.147.21)
+### [Version 1.23.1](https://github.com/lobehub/lobe-chat/compare/v1.23.0...v1.23.1)
-Released on **2024-04-19**
+Released on **2024-10-25**
#### 💄 Styles
-- **misc**: Optimized file upload buttons and prompts.
+- **misc**: Add `*_MODEL_LIST` env to all models, update Spark model id & display name.
@@ -10126,7 +10022,8 @@
#### Styles
-- **misc**: Optimized file upload buttons and prompts, closes [#2050](https://github.com/lobehub/lobe-chat/issues/2050) ([c23087e](https://github.com/lobehub/lobe-chat/commit/c23087e))
+- **misc**: Add `*_MODEL_LIST` env to all models, closes [#4481](https://github.com/lobehub/lobe-chat/issues/4481) ([a969b9c](https://github.com/lobehub/lobe-chat/commit/a969b9c))
+- **misc**: Update Spark model id & display name, closes [#4482](https://github.com/lobehub/lobe-chat/issues/4482) ([852dd47](https://github.com/lobehub/lobe-chat/commit/852dd47))
@@ -10136,22 +10033,22 @@
-### [Version 0.147.20](https://github.com/lobehub/lobe-chat/compare/v0.147.19...v0.147.20)
+## [Version 1.23.0](https://github.com/lobehub/lobe-chat/compare/v1.22.27...v1.23.0)
-Released on **2024-04-18**
+Released on **2024-10-25**
-#### 💄 Styles
+#### ✨ Features
-- **misc**: Improve aync session experience.
+- **misc**: Support system agent config.
Improvements and Fixes
-#### Styles
+#### What's improved
-- **misc**: Improve aync session experience, closes [#2075](https://github.com/lobehub/lobe-chat/issues/2075) ([0f3b19b](https://github.com/lobehub/lobe-chat/commit/0f3b19b))
+- **misc**: Support system agent config, closes [#4474](https://github.com/lobehub/lobe-chat/issues/4474) ([63ba4d3](https://github.com/lobehub/lobe-chat/commit/63ba4d3))
@@ -10161,13 +10058,13 @@
-### [Version 0.147.19](https://github.com/lobehub/lobe-chat/compare/v0.147.18...v0.147.19)
+### [Version 1.22.27](https://github.com/lobehub/lobe-chat/compare/v1.22.26...v1.22.27)
-Released on **2024-04-18**
+Released on **2024-10-25**
#### 💄 Styles
-- **misc**: Add M and B support max token in ModelInfoTags.
+- **misc**: Add bedrock claude-3.5-sonnect-v2.
@@ -10176,7 +10073,7 @@
#### Styles
-- **misc**: Add M and B support max token in ModelInfoTags, closes [#2073](https://github.com/lobehub/lobe-chat/issues/2073) ([a985d8f](https://github.com/lobehub/lobe-chat/commit/a985d8f))
+- **misc**: Add bedrock claude-3.5-sonnect-v2, closes [#4468](https://github.com/lobehub/lobe-chat/issues/4468) ([a7fc251](https://github.com/lobehub/lobe-chat/commit/a7fc251))
@@ -10186,13 +10083,13 @@
-### [Version 0.147.18](https://github.com/lobehub/lobe-chat/compare/v0.147.17...v0.147.18)
+### [Version 1.22.26](https://github.com/lobehub/lobe-chat/compare/v1.22.25...v1.22.26)
-Released on **2024-04-17**
+Released on **2024-10-23**
#### 💄 Styles
-- **misc**: Add claude 3 opus to AWS Bedrock, remove custom models from providers, and update Perplexity model names.
+- **misc**: Fix some custom branding detail.
@@ -10201,8 +10098,7 @@
#### Styles
-- **misc**: Add claude 3 opus to AWS Bedrock, closes [#2072](https://github.com/lobehub/lobe-chat/issues/2072) ([479f562](https://github.com/lobehub/lobe-chat/commit/479f562))
-- **misc**: Remove custom models from providers, and update Perplexity model names, closes [#2069](https://github.com/lobehub/lobe-chat/issues/2069) ([e04754d](https://github.com/lobehub/lobe-chat/commit/e04754d))
+- **misc**: Fix some custom branding detail, closes [#4465](https://github.com/lobehub/lobe-chat/issues/4465) ([3fb1f6a](https://github.com/lobehub/lobe-chat/commit/3fb1f6a))
@@ -10212,13 +10108,13 @@
-### [Version 0.147.17](https://github.com/lobehub/lobe-chat/compare/v0.147.16...v0.147.17)
+### [Version 1.22.25](https://github.com/lobehub/lobe-chat/compare/v1.22.24...v1.22.25)
-Released on **2024-04-16**
+Released on **2024-10-23**
#### ♻ Code Refactoring
-- **misc**: Refactor service to a uniform interface.
+- **misc**: Remove unused user tables.
@@ -10227,7 +10123,7 @@
#### Code refactoring
-- **misc**: Refactor service to a uniform interface, closes [#2062](https://github.com/lobehub/lobe-chat/issues/2062) ([86779e2](https://github.com/lobehub/lobe-chat/commit/86779e2))
+- **misc**: Remove unused user tables, closes [#4464](https://github.com/lobehub/lobe-chat/issues/4464) ([c85a270](https://github.com/lobehub/lobe-chat/commit/c85a270))
@@ -10237,13 +10133,13 @@
-### [Version 0.147.16](https://github.com/lobehub/lobe-chat/compare/v0.147.15...v0.147.16)
+### [Version 1.22.24](https://github.com/lobehub/lobe-chat/compare/v1.22.23...v1.22.24)
-Released on **2024-04-14**
+Released on **2024-10-23**
#### ♻ Code Refactoring
-- **misc**: Refactor the auth.
+- **misc**: Support `plugin` flag.
@@ -10252,7 +10148,7 @@
#### Code refactoring
-- **misc**: Refactor the auth, closes [#2043](https://github.com/lobehub/lobe-chat/issues/2043) ([37ecb41](https://github.com/lobehub/lobe-chat/commit/37ecb41))
+- **misc**: Support `plugin` flag, closes [#4463](https://github.com/lobehub/lobe-chat/issues/4463) ([9b4be23](https://github.com/lobehub/lobe-chat/commit/9b4be23))
@@ -10262,22 +10158,22 @@
-### [Version 0.147.15](https://github.com/lobehub/lobe-chat/compare/v0.147.14...v0.147.15)
+### [Version 1.22.23](https://github.com/lobehub/lobe-chat/compare/v1.22.22...v1.22.23)
-Released on **2024-04-14**
+Released on **2024-10-23**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix tool call error with gpt-4-turbo.
+- **misc**: Improve error i18n.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix tool call error with gpt-4-turbo, closes [#2042](https://github.com/lobehub/lobe-chat/issues/2042) ([63d91b8](https://github.com/lobehub/lobe-chat/commit/63d91b8))
+- **misc**: Improve error i18n, closes [#4462](https://github.com/lobehub/lobe-chat/issues/4462) ([74fb5e7](https://github.com/lobehub/lobe-chat/commit/74fb5e7))
@@ -10287,13 +10183,13 @@
-### [Version 0.147.14](https://github.com/lobehub/lobe-chat/compare/v0.147.13...v0.147.14)
+### [Version 1.22.22](https://github.com/lobehub/lobe-chat/compare/v1.22.21...v1.22.22)
-Released on **2024-04-14**
+Released on **2024-10-23**
#### 💄 Styles
-- **misc**: Enable `gemini-1.5-pro-latest` model by default.
+- **misc**: Improve i18n.
@@ -10302,7 +10198,7 @@
#### Styles
-- **misc**: Enable `gemini-1.5-pro-latest` model by default, closes [#2034](https://github.com/lobehub/lobe-chat/issues/2034) ([e8c65a9](https://github.com/lobehub/lobe-chat/commit/e8c65a9))
+- **misc**: Improve i18n, closes [#4461](https://github.com/lobehub/lobe-chat/issues/4461) ([4c37928](https://github.com/lobehub/lobe-chat/commit/4c37928))
@@ -10312,13 +10208,13 @@
-### [Version 0.147.13](https://github.com/lobehub/lobe-chat/compare/v0.147.12...v0.147.13)
+### [Version 1.22.21](https://github.com/lobehub/lobe-chat/compare/v1.22.20...v1.22.21)
-Released on **2024-04-14**
+Released on **2024-10-23**
#### ♻ Code Refactoring
-- **misc**: Refactor the service with browser db invoke.
+- **misc**: Refactor cookie/headers to async mode.
@@ -10327,7 +10223,7 @@
#### Code refactoring
-- **misc**: Refactor the service with browser db invoke, closes [#2038](https://github.com/lobehub/lobe-chat/issues/2038) ([43a2791](https://github.com/lobehub/lobe-chat/commit/43a2791))
+- **misc**: Refactor cookie/headers to async mode, closes [#4459](https://github.com/lobehub/lobe-chat/issues/4459) ([98c5d21](https://github.com/lobehub/lobe-chat/commit/98c5d21))
@@ -10337,22 +10233,22 @@
-### [Version 0.147.12](https://github.com/lobehub/lobe-chat/compare/v0.147.11...v0.147.12)
+### [Version 1.22.20](https://github.com/lobehub/lobe-chat/compare/v1.22.19...v1.22.20)
-Released on **2024-04-14**
+Released on **2024-10-23**
-#### ♻ Code Refactoring
+#### 💄 Styles
-- **misc**: Move client db to a new folder.
+- **misc**: Add new claude-3.5-sonnet model.
Improvements and Fixes
-#### Code refactoring
+#### Styles
-- **misc**: Move client db to a new folder, closes [#2037](https://github.com/lobehub/lobe-chat/issues/2037) ([ebe65bb](https://github.com/lobehub/lobe-chat/commit/ebe65bb))
+- **misc**: Add new claude-3.5-sonnet model, closes [#4452](https://github.com/lobehub/lobe-chat/issues/4452) ([7102393](https://github.com/lobehub/lobe-chat/commit/7102393))
@@ -10362,22 +10258,22 @@
-### [Version 0.147.11](https://github.com/lobehub/lobe-chat/compare/v0.147.10...v0.147.11)
+### [Version 1.22.19](https://github.com/lobehub/lobe-chat/compare/v1.22.18...v1.22.19)
-Released on **2024-04-14**
+Released on **2024-10-22**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Support drag or copy to upload file by model ability.
+- **misc**: Move responsive to server utils folder.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Support drag or copy to upload file by model ability, closes [#2016](https://github.com/lobehub/lobe-chat/issues/2016) ([2abe37e](https://github.com/lobehub/lobe-chat/commit/2abe37e))
+- **misc**: Move responsive to server utils folder, closes [#4447](https://github.com/lobehub/lobe-chat/issues/4447) ([fe7fe64](https://github.com/lobehub/lobe-chat/commit/fe7fe64))
@@ -10387,9 +10283,9 @@
-### [Version 0.147.10](https://github.com/lobehub/lobe-chat/compare/v0.147.9...v0.147.10)
+### [Version 1.22.18](https://github.com/lobehub/lobe-chat/compare/v1.22.17...v1.22.18)
-Released on **2024-04-13**
+Released on **2024-10-22**
@@ -10404,22 +10300,22 @@
-### [Version 0.147.9](https://github.com/lobehub/lobe-chat/compare/v0.147.8...v0.147.9)
+### [Version 1.22.17](https://github.com/lobehub/lobe-chat/compare/v1.22.16...v1.22.17)
-Released on **2024-04-12**
+Released on **2024-10-22**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fix custom model list not display correctly.
+- **misc**: Fix dynamic import in rsc layout.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix custom model list not display correctly, closes [#2009](https://github.com/lobehub/lobe-chat/issues/2009) ([7d0e220](https://github.com/lobehub/lobe-chat/commit/7d0e220))
+- **misc**: Fix dynamic import in rsc layout, closes [#4445](https://github.com/lobehub/lobe-chat/issues/4445) ([011d62a](https://github.com/lobehub/lobe-chat/commit/011d62a))
@@ -10429,22 +10325,22 @@
-### [Version 0.147.8](https://github.com/lobehub/lobe-chat/compare/v0.147.7...v0.147.8)
+### [Version 1.22.16](https://github.com/lobehub/lobe-chat/compare/v1.22.15...v1.22.16)
-Released on **2024-04-12**
+Released on **2024-10-21**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Update README.md.
+- **misc**: Fix azure-ad.
Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Update README.md ([44b5a23](https://github.com/lobehub/lobe-chat/commit/44b5a23))
+- **misc**: Fix azure-ad, closes [#4438](https://github.com/lobehub/lobe-chat/issues/4438) ([8077317](https://github.com/lobehub/lobe-chat/commit/8077317))
@@ -10454,22 +10350,22 @@
-### [Version 0.147.7](https://github.com/lobehub/lobe-chat/compare/v0.147.6...v0.147.7)
+### [Version 1.22.15](https://github.com/lobehub/lobe-chat/compare/v1.22.14...v1.22.15)
-Released on **2024-04-12**
+Released on **2024-10-21**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Pin next to `14.1.4` to fix deployment.
+- **misc**: Update format utils and shared layout.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Pin next to `14.1.4` to fix deployment, closes [#1998](https://github.com/lobehub/lobe-chat/issues/1998) ([dfa1872](https://github.com/lobehub/lobe-chat/commit/dfa1872))
+- **misc**: Update format utils and shared layout, closes [#4431](https://github.com/lobehub/lobe-chat/issues/4431) ([56ed073](https://github.com/lobehub/lobe-chat/commit/56ed073))
@@ -10479,13 +10375,13 @@
-### [Version 0.147.6](https://github.com/lobehub/lobe-chat/compare/v0.147.5...v0.147.6)
+### [Version 1.22.14](https://github.com/lobehub/lobe-chat/compare/v1.22.13...v1.22.14)
-Released on **2024-04-11**
+Released on **2024-10-20**
#### 💄 Styles
-- **misc**: Add GPT-4-turbo and 2024-04-09 Turbo Vision model and mistral new model name.
+- **misc**: Update wenxin 4.0 turbo model to latest.
@@ -10494,7 +10390,7 @@
#### Styles
-- **misc**: Add GPT-4-turbo and 2024-04-09 Turbo Vision model and mistral new model name, closes [#1984](https://github.com/lobehub/lobe-chat/issues/1984) ([f1795b1](https://github.com/lobehub/lobe-chat/commit/f1795b1))
+- **misc**: Update wenxin 4.0 turbo model to latest, closes [#4428](https://github.com/lobehub/lobe-chat/issues/4428) ([3389fbb](https://github.com/lobehub/lobe-chat/commit/3389fbb))
@@ -10504,22 +10400,23 @@
-### [Version 0.147.5](https://github.com/lobehub/lobe-chat/compare/v0.147.4...v0.147.5)
+### [Version 1.22.13](https://github.com/lobehub/lobe-chat/compare/v1.22.12...v1.22.13)
-Released on **2024-04-11**
+Released on **2024-10-20**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix only search topics in current session.
+- **misc**: Add Ministral model, update Together AI model list, add function call & vision.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix only search topics in current session, closes [#1834](https://github.com/lobehub/lobe-chat/issues/1834) ([9fdcfa4](https://github.com/lobehub/lobe-chat/commit/9fdcfa4))
+- **misc**: Add Ministral model, closes [#4427](https://github.com/lobehub/lobe-chat/issues/4427) ([2042df8](https://github.com/lobehub/lobe-chat/commit/2042df8))
+- **misc**: Update Together AI model list, add function call & vision, closes [#4393](https://github.com/lobehub/lobe-chat/issues/4393) ([d7fbf1b](https://github.com/lobehub/lobe-chat/commit/d7fbf1b))
@@ -10529,30 +10426,22 @@
-### [Version 0.147.4](https://github.com/lobehub/lobe-chat/compare/v0.147.3...v0.147.4)
-
-Released on **2024-04-11**
-
-#### 🐛 Bug Fixes
+### [Version 1.22.12](https://github.com/lobehub/lobe-chat/compare/v1.22.11...v1.22.12)
-- **misc**: Add more builtin OpenRouter models.
+Released on **2024-10-20**
#### 💄 Styles
-- **misc**: Adjust minimum width value for DraggablePanel component.
+- **misc**: Add Llama 3.1 Nemotron 70B model & reorder some provider model list.
Improvements and Fixes
-#### What's fixed
-
-- **misc**: Add more builtin OpenRouter models, closes [#1973](https://github.com/lobehub/lobe-chat/issues/1973) ([0000b1a](https://github.com/lobehub/lobe-chat/commit/0000b1a))
-
#### Styles
-- **misc**: Adjust minimum width value for DraggablePanel component, closes [#1901](https://github.com/lobehub/lobe-chat/issues/1901) ([a696d37](https://github.com/lobehub/lobe-chat/commit/a696d37))
+- **misc**: Add Llama 3.1 Nemotron 70B model & reorder some provider model list, closes [#4424](https://github.com/lobehub/lobe-chat/issues/4424) ([9355a3d](https://github.com/lobehub/lobe-chat/commit/9355a3d))
@@ -10562,22 +10451,22 @@
-### [Version 0.147.3](https://github.com/lobehub/lobe-chat/compare/v0.147.2...v0.147.3)
+### [Version 1.22.11](https://github.com/lobehub/lobe-chat/compare/v1.22.10...v1.22.11)
-Released on **2024-04-11**
+Released on **2024-10-20**
-#### 💄 Styles
+#### ♻ Code Refactoring
-- **misc**: Support Google Proxy URL.
+- **misc**: Refactor azure ad to ms entra id.
Improvements and Fixes
-#### Styles
+#### Code refactoring
-- **misc**: Support Google Proxy URL, closes [#1979](https://github.com/lobehub/lobe-chat/issues/1979) ([fbf2c24](https://github.com/lobehub/lobe-chat/commit/fbf2c24))
+- **misc**: Refactor azure ad to ms entra id, closes [#4168](https://github.com/lobehub/lobe-chat/issues/4168) ([4fa9588](https://github.com/lobehub/lobe-chat/commit/4fa9588))
@@ -10587,23 +10476,15 @@
-### [Version 0.147.2](https://github.com/lobehub/lobe-chat/compare/v0.147.1...v0.147.2)
-
-Released on **2024-04-11**
+### [Version 1.22.10](https://github.com/lobehub/lobe-chat/compare/v1.22.9...v1.22.10)
-#### 🐛 Bug Fixes
-
-- **misc**: Fix custom model not display correctly.
+Released on **2024-10-20** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix custom model not display correctly, closes [#1972](https://github.com/lobehub/lobe-chat/issues/1972) ([5d7cae9](https://github.com/lobehub/lobe-chat/commit/5d7cae9))
-
@@ -10612,22 +10493,22 @@
-### [Version 0.147.1](https://github.com/lobehub/lobe-chat/compare/v0.147.0...v0.147.1)
+### [Version 1.22.9](https://github.com/lobehub/lobe-chat/compare/v1.22.8...v1.22.9)
-Released on **2024-04-11**
+Released on **2024-10-18**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix normalizeLocale with first matching locale.
+- **misc**: Update Fireworks AI model list.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix normalizeLocale with first matching locale, closes [#1767](https://github.com/lobehub/lobe-chat/issues/1767) ([182ff23](https://github.com/lobehub/lobe-chat/commit/182ff23))
+- **misc**: Update Fireworks AI model list, closes [#4394](https://github.com/lobehub/lobe-chat/issues/4394) ([fe8ffdd](https://github.com/lobehub/lobe-chat/commit/fe8ffdd))
@@ -10637,70 +10518,47 @@
-## [Version 0.147.0](https://github.com/lobehub/lobe-chat/compare/v0.146.2...v0.147.0)
+### [Version 1.22.8](https://github.com/lobehub/lobe-chat/compare/v1.22.7...v1.22.8)
-Released on **2024-04-10**
+Released on **2024-10-17**
-#### ♻ Code Refactoring
+#### 💄 Styles
-- **misc**: Add db migration, add migrations from v3 to v4, clean openai azure code, refactor agent runtime with openai compatible factory, refactor api key form locale, refactor openAI to openai and azure, refactor the hidden to enabled, refactor the key, refactor the model config selector, refactor the route auth as a middleware, refactor the server config to migrate model provider env, refactor the server config to migrate model provider env, rename the key to enabledModels.
+- **misc**: Add Yi-Lightning model.
-#### ✨ Features
+
-- **misc**: Refactor to support azure openai provider, support close openai, support display model list, support model config modal, support model list with model providers, support open router auto model list, support openai model fetcher, support update model config, support user config model.
+
+Improvements and Fixes
-#### 🐛 Bug Fixes
+#### Styles
-- **misc**: Fix db migration, fix db migration.
+- **misc**: Add Yi-Lightning model, closes [#4390](https://github.com/lobehub/lobe-chat/issues/4390) ([9e9fb9a](https://github.com/lobehub/lobe-chat/commit/9e9fb9a))
-#### 💄 Styles
+
-- **misc**: Fix i18n of model list fetcher, improve detail design, improve logo style, update locale.
+
-
+[](#readme-top)
-
-Improvements and Fixes
+
-#### Code refactoring
+### [Version 1.22.7](https://github.com/lobehub/lobe-chat/compare/v1.22.6...v1.22.7)
-- **misc**: Add db migration ([6ceb818](https://github.com/lobehub/lobe-chat/commit/6ceb818))
-- **misc**: Add migrations from v3 to v4 ([199ded2](https://github.com/lobehub/lobe-chat/commit/199ded2))
-- **misc**: Clean openai azure code ([be4bcca](https://github.com/lobehub/lobe-chat/commit/be4bcca))
-- **misc**: Refactor agent runtime with openai compatible factory ([89adf9d](https://github.com/lobehub/lobe-chat/commit/89adf9d))
-- **misc**: Refactor api key form locale ([a069169](https://github.com/lobehub/lobe-chat/commit/a069169))
-- **misc**: Refactor openAI to openai and azure ([2190a95](https://github.com/lobehub/lobe-chat/commit/2190a95))
-- **misc**: Refactor the hidden to enabled ([78a1aac](https://github.com/lobehub/lobe-chat/commit/78a1aac))
-- **misc**: Refactor the key ([d5c82f6](https://github.com/lobehub/lobe-chat/commit/d5c82f6))
-- **misc**: Refactor the model config selector ([d865ca1](https://github.com/lobehub/lobe-chat/commit/d865ca1))
-- **misc**: Refactor the route auth as a middleware ([ef5ee2a](https://github.com/lobehub/lobe-chat/commit/ef5ee2a))
-- **misc**: Refactor the server config to migrate model provider env ([e4f110e](https://github.com/lobehub/lobe-chat/commit/e4f110e))
-- **misc**: Refactor the server config to migrate model provider env ([c398063](https://github.com/lobehub/lobe-chat/commit/c398063))
-- **misc**: Rename the key to enabledModels ([ebfa0aa](https://github.com/lobehub/lobe-chat/commit/ebfa0aa))
+Released on **2024-10-17**
-#### What's improved
+#### 💄 Styles
-- **misc**: Refactor to support azure openai provider ([d737afe](https://github.com/lobehub/lobe-chat/commit/d737afe))
-- **misc**: Support close openai ([1ff1aef](https://github.com/lobehub/lobe-chat/commit/1ff1aef))
-- **misc**: Support display model list ([e59635f](https://github.com/lobehub/lobe-chat/commit/e59635f))
-- **misc**: Support model config modal ([62d6bb7](https://github.com/lobehub/lobe-chat/commit/62d6bb7))
-- **misc**: Support model list with model providers, closes [#1916](https://github.com/lobehub/lobe-chat/issues/1916) ([0895dd2](https://github.com/lobehub/lobe-chat/commit/0895dd2))
-- **misc**: Support open router auto model list ([1ba90d3](https://github.com/lobehub/lobe-chat/commit/1ba90d3))
-- **misc**: Support openai model fetcher ([56032e6](https://github.com/lobehub/lobe-chat/commit/56032e6))
-- **misc**: Support update model config ([e8ed847](https://github.com/lobehub/lobe-chat/commit/e8ed847))
-- **misc**: Support user config model ([72fd873](https://github.com/lobehub/lobe-chat/commit/72fd873))
+- **misc**: Add qwen vision model & update qwen2.5 72b to 128k for siliconcloud.
-#### What's fixed
+
-- **misc**: Fix db migration ([4e75074](https://github.com/lobehub/lobe-chat/commit/4e75074))
-- **misc**: Fix db migration ([571b6dd](https://github.com/lobehub/lobe-chat/commit/571b6dd))
+
+Improvements and Fixes
#### Styles
-- **misc**: Fix i18n of model list fetcher ([67ed8c2](https://github.com/lobehub/lobe-chat/commit/67ed8c2))
-- **misc**: Improve detail design ([adcce07](https://github.com/lobehub/lobe-chat/commit/adcce07))
-- **misc**: Improve logo style ([c5826ce](https://github.com/lobehub/lobe-chat/commit/c5826ce))
-- **misc**: Update locale ([021bf91](https://github.com/lobehub/lobe-chat/commit/021bf91))
+- **misc**: Add qwen vision model & update qwen2.5 72b to 128k for siliconcloud, closes [#4380](https://github.com/lobehub/lobe-chat/issues/4380) ([e8c009b](https://github.com/lobehub/lobe-chat/commit/e8c009b))
@@ -10710,13 +10568,13 @@
-### [Version 0.146.2](https://github.com/lobehub/lobe-chat/compare/v0.146.1...v0.146.2)
+### [Version 1.22.6](https://github.com/lobehub/lobe-chat/compare/v1.22.5...v1.22.6)
-Released on **2024-04-10**
+Released on **2024-10-13**
#### 🐛 Bug Fixes
-- **misc**: Pin `ai@3.0.19` to fix error with chat stream output.
+- **misc**: Fix images not go in to chat context.
@@ -10725,7 +10583,7 @@
#### What's fixed
-- **misc**: Pin `ai@3.0.19` to fix error with chat stream output, closes [#1946](https://github.com/lobehub/lobe-chat/issues/1946) ([07d4419](https://github.com/lobehub/lobe-chat/commit/07d4419))
+- **misc**: Fix images not go in to chat context, closes [#4361](https://github.com/lobehub/lobe-chat/issues/4361) ([f17ab49](https://github.com/lobehub/lobe-chat/commit/f17ab49))
@@ -10735,15 +10593,23 @@
-### [Version 0.146.1](https://github.com/lobehub/lobe-chat/compare/v0.146.0...v0.146.1)
+### [Version 1.22.5](https://github.com/lobehub/lobe-chat/compare/v1.22.4...v1.22.5)
-Released on **2024-04-10**
+Released on **2024-10-13**
+
+#### 💄 Styles
+
+- **misc**: Reorder github model list & updata info & add new model.
Improvements and Fixes
+#### Styles
+
+- **misc**: Reorder github model list & updata info & add new model, closes [#4360](https://github.com/lobehub/lobe-chat/issues/4360) ([e7767a5](https://github.com/lobehub/lobe-chat/commit/e7767a5))
+
@@ -10752,22 +10618,22 @@
-## [Version 0.146.0](https://github.com/lobehub/lobe-chat/compare/v0.145.13...v0.146.0)
+### [Version 1.22.4](https://github.com/lobehub/lobe-chat/compare/v1.22.3...v1.22.4)
-Released on **2024-04-08**
+Released on **2024-10-13**
-#### ✨ Features
+#### ♻ Code Refactoring
-- **misc**: Add support for ZITADEL SSO provider.
+- **misc**: Separate message slice and aiChat slice.
Improvements and Fixes
-#### What's improved
+#### Code refactoring
-- **misc**: Add support for ZITADEL SSO provider, closes [#1904](https://github.com/lobehub/lobe-chat/issues/1904) ([44152f7](https://github.com/lobehub/lobe-chat/commit/44152f7))
+- **misc**: Separate message slice and aiChat slice, closes [#4359](https://github.com/lobehub/lobe-chat/issues/4359) ([7d037f6](https://github.com/lobehub/lobe-chat/commit/7d037f6))
@@ -10777,30 +10643,22 @@
-### [Version 0.145.13](https://github.com/lobehub/lobe-chat/compare/v0.145.12...v0.145.13)
-
-Released on **2024-04-07**
-
-#### ♻ Code Refactoring
+### [Version 1.22.3](https://github.com/lobehub/lobe-chat/compare/v1.22.2...v1.22.3)
-- **misc**: Refactor the model settings for more clean code.
+Released on **2024-10-13**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix normalize russian locale.
+- **misc**: Support multi-windows for PWA.
Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Refactor the model settings for more clean code, closes [#1906](https://github.com/lobehub/lobe-chat/issues/1906) ([db5d3ac](https://github.com/lobehub/lobe-chat/commit/db5d3ac))
-
-#### What's fixed
+#### Styles
-- **misc**: Fix normalize russian locale, closes [#1903](https://github.com/lobehub/lobe-chat/issues/1903) ([e86b596](https://github.com/lobehub/lobe-chat/commit/e86b596))
+- **misc**: Support multi-windows for PWA, closes [#4334](https://github.com/lobehub/lobe-chat/issues/4334) ([0284606](https://github.com/lobehub/lobe-chat/commit/0284606))
@@ -10810,13 +10668,13 @@
-### [Version 0.145.12](https://github.com/lobehub/lobe-chat/compare/v0.145.11...v0.145.12)
+### [Version 1.22.2](https://github.com/lobehub/lobe-chat/compare/v1.22.1...v1.22.2)
-Released on **2024-04-04**
+Released on **2024-10-13**
#### 🐛 Bug Fixes
-- **misc**: Fix typo of azure-id sso provider.
+- **misc**: Allow use email as name in logto.
@@ -10825,7 +10683,7 @@
#### What's fixed
-- **misc**: Fix typo of azure-id sso provider, closes [#1898](https://github.com/lobehub/lobe-chat/issues/1898) ([6925b25](https://github.com/lobehub/lobe-chat/commit/6925b25))
+- **misc**: Allow use email as name in logto, closes [#4350](https://github.com/lobehub/lobe-chat/issues/4350) ([d5a046a](https://github.com/lobehub/lobe-chat/commit/d5a046a))
@@ -10835,13 +10693,13 @@
-### [Version 0.145.11](https://github.com/lobehub/lobe-chat/compare/v0.145.10...v0.145.11)
+### [Version 1.22.1](https://github.com/lobehub/lobe-chat/compare/v1.22.0...v1.22.1)
-Released on **2024-04-03**
+Released on **2024-10-12**
#### 🐛 Bug Fixes
-- **misc**: Fix page crash when using browser as the stt engine.
+- **misc**: Fix function calling issue, disable stream when using tools.
@@ -10850,7 +10708,7 @@
#### What's fixed
-- **misc**: Fix page crash when using browser as the stt engine, closes [#1884](https://github.com/lobehub/lobe-chat/issues/1884) ([278820a](https://github.com/lobehub/lobe-chat/commit/278820a))
+- **misc**: Fix function calling issue, disable stream when using tools, closes [#4335](https://github.com/lobehub/lobe-chat/issues/4335) ([9f8e0a9](https://github.com/lobehub/lobe-chat/commit/9f8e0a9))
@@ -10860,15 +10718,31 @@
-### [Version 0.145.10](https://github.com/lobehub/lobe-chat/compare/v0.145.9...v0.145.10)
+## [Version 1.22.0](https://github.com/lobehub/lobe-chat/compare/v1.21.16...v1.22.0)
+
+Released on **2024-10-12**
+
+#### ♻ Code Refactoring
+
+- **misc**: Refactor the chat webapi.
-Released on **2024-04-02**
+#### ✨ Features
+
+- **misc**: Add HuggingFace Model Provider.
Improvements and Fixes
+#### Code refactoring
+
+- **misc**: Refactor the chat webapi, closes [#4339](https://github.com/lobehub/lobe-chat/issues/4339) ([4722444](https://github.com/lobehub/lobe-chat/commit/4722444))
+
+#### What's improved
+
+- **misc**: Add HuggingFace Model Provider, closes [#4225](https://github.com/lobehub/lobe-chat/issues/4225) ([d310931](https://github.com/lobehub/lobe-chat/commit/d310931))
+
-### [Version 0.145.7](https://github.com/lobehub/lobe-chat/compare/v0.145.6...v0.145.7)
+### [Version 1.21.14](https://github.com/lobehub/lobe-chat/compare/v1.21.13...v1.21.14)
-Released on **2024-04-02**
+Released on **2024-10-12**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix DraggablePanel bar interfere with the operation of the scrollbar.
+- **misc**: Fix artifacts render markdown.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix DraggablePanel bar interfere with the operation of the scrollbar, closes [#1775](https://github.com/lobehub/lobe-chat/issues/1775) ([4b7b243](https://github.com/lobehub/lobe-chat/commit/4b7b243))
+- **misc**: Fix artifacts render markdown, closes [#4327](https://github.com/lobehub/lobe-chat/issues/4327) ([6bb6ea6](https://github.com/lobehub/lobe-chat/commit/6bb6ea6))
@@ -10960,15 +10810,23 @@
-### [Version 0.145.6](https://github.com/lobehub/lobe-chat/compare/v0.145.5...v0.145.6)
+### [Version 1.21.13](https://github.com/lobehub/lobe-chat/compare/v1.21.12...v1.21.13)
+
+Released on **2024-10-11**
+
+#### ♻ Code Refactoring
-Released on **2024-04-02**
+- **misc**: Refactor agent runtime implement of stream and ZHIPU provider.
Improvements and Fixes
+#### Code refactoring
+
+- **misc**: Refactor agent runtime implement of stream and ZHIPU provider, closes [#4323](https://github.com/lobehub/lobe-chat/issues/4323) ([59661a1](https://github.com/lobehub/lobe-chat/commit/59661a1))
+
@@ -10977,22 +10835,22 @@
-### [Version 0.145.5](https://github.com/lobehub/lobe-chat/compare/v0.145.4...v0.145.5)
+### [Version 1.21.12](https://github.com/lobehub/lobe-chat/compare/v1.21.11...v1.21.12)
-Released on **2024-03-30**
+Released on **2024-10-11**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Add qwen api models patch in ollama.
+- **misc**: Refactor the jwt code.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Add qwen api models patch in ollama, closes [#1630](https://github.com/lobehub/lobe-chat/issues/1630) ([a1e754c](https://github.com/lobehub/lobe-chat/commit/a1e754c))
+- **misc**: Refactor the jwt code, closes [#4322](https://github.com/lobehub/lobe-chat/issues/4322) ([b7258b9](https://github.com/lobehub/lobe-chat/commit/b7258b9))
@@ -11002,22 +10860,22 @@
-### [Version 0.145.4](https://github.com/lobehub/lobe-chat/compare/v0.145.3...v0.145.4)
+### [Version 1.21.11](https://github.com/lobehub/lobe-chat/compare/v1.21.10...v1.21.11)
-Released on **2024-03-29**
+Released on **2024-10-11**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fix plugin install loading state error.
+- **misc**: Refactor the backend code for better organization.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix plugin install loading state error, closes [#1815](https://github.com/lobehub/lobe-chat/issues/1815) ([2412a73](https://github.com/lobehub/lobe-chat/commit/2412a73))
+- **misc**: Refactor the backend code for better organization, closes [#4287](https://github.com/lobehub/lobe-chat/issues/4287) ([9a369ac](https://github.com/lobehub/lobe-chat/commit/9a369ac))
@@ -11027,22 +10885,22 @@
-### [Version 0.145.3](https://github.com/lobehub/lobe-chat/compare/v0.145.2...v0.145.3)
+### [Version 1.21.10](https://github.com/lobehub/lobe-chat/compare/v1.21.9...v1.21.10)
-Released on **2024-03-29**
+Released on **2024-10-11**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix antd locale.
+- **misc**: Updata gpt-4o model info.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix antd locale, closes [#1814](https://github.com/lobehub/lobe-chat/issues/1814) ([e7fc148](https://github.com/lobehub/lobe-chat/commit/e7fc148))
+- **misc**: Updata gpt-4o model info, closes [#4318](https://github.com/lobehub/lobe-chat/issues/4318) ([fa27ddf](https://github.com/lobehub/lobe-chat/commit/fa27ddf))
@@ -11052,22 +10910,22 @@
-### [Version 0.145.2](https://github.com/lobehub/lobe-chat/compare/v0.145.1...v0.145.2)
+### [Version 1.21.9](https://github.com/lobehub/lobe-chat/compare/v1.21.8...v1.21.9)
-Released on **2024-03-29**
+Released on **2024-10-10**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix google ultra model id.
+- **misc**: Update qwen vl model to latest.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix google ultra model id, closes [#1813](https://github.com/lobehub/lobe-chat/issues/1813) ([c96ba12](https://github.com/lobehub/lobe-chat/commit/c96ba12))
+- **misc**: Update qwen vl model to latest, closes [#4307](https://github.com/lobehub/lobe-chat/issues/4307) ([25a7ea2](https://github.com/lobehub/lobe-chat/commit/25a7ea2))
@@ -11077,13 +10935,17 @@
-### [Version 0.145.1](https://github.com/lobehub/lobe-chat/compare/v0.145.0...v0.145.1)
+### [Version 1.21.8](https://github.com/lobehub/lobe-chat/compare/v1.21.7...v1.21.8)
-Released on **2024-03-29**
+Released on **2024-10-08**
#### 🐛 Bug Fixes
-- **misc**: Fix Google Gemini pro 1.5 and system role not take effect.
+- **misc**: Fix auto rewrite query when user message is too long.
+
+#### 💄 Styles
+
+- **misc**: Support yml in file chunk.
@@ -11092,7 +10954,11 @@
#### What's fixed
-- **misc**: Fix Google Gemini pro 1.5 and system role not take effect, closes [#1801](https://github.com/lobehub/lobe-chat/issues/1801) ([0a3e3f7](https://github.com/lobehub/lobe-chat/commit/0a3e3f7))
+- **misc**: Fix auto rewrite query when user message is too long, closes [#4288](https://github.com/lobehub/lobe-chat/issues/4288) ([a2d3d32](https://github.com/lobehub/lobe-chat/commit/a2d3d32))
+
+#### Styles
+
+- **misc**: Support yml in file chunk, closes [#4283](https://github.com/lobehub/lobe-chat/issues/4283) ([cec7ec0](https://github.com/lobehub/lobe-chat/commit/cec7ec0))
@@ -11102,22 +10968,22 @@
-## [Version 0.145.0](https://github.com/lobehub/lobe-chat/compare/v0.144.1...v0.145.0)
+### [Version 1.21.7](https://github.com/lobehub/lobe-chat/compare/v1.21.6...v1.21.7)
-Released on **2024-03-29**
+Released on **2024-10-08**
-#### ✨ Features
+#### ♻ Code Refactoring
-- **misc**: Support TogetherAI as new model provider.
+- **misc**: Refactor `text-to-image` endpoint.
Improvements and Fixes
-#### What's improved
+#### Code refactoring
-- **misc**: Support TogetherAI as new model provider, closes [#1709](https://github.com/lobehub/lobe-chat/issues/1709) ([d6921ef](https://github.com/lobehub/lobe-chat/commit/d6921ef))
+- **misc**: Refactor `text-to-image` endpoint, closes [#4272](https://github.com/lobehub/lobe-chat/issues/4272) ([0c02073](https://github.com/lobehub/lobe-chat/commit/0c02073))
@@ -11127,22 +10993,30 @@
-### [Version 0.144.1](https://github.com/lobehub/lobe-chat/compare/v0.144.0...v0.144.1)
+### [Version 1.21.6](https://github.com/lobehub/lobe-chat/compare/v1.21.5...v1.21.6)
+
+Released on **2024-10-05**
+
+#### ♻ Code Refactoring
-Released on **2024-03-29**
+- **misc**: Move backend api to (backend) folder group.
#### 🐛 Bug Fixes
-- **ollama**: Suppport vision for LLaVA models.
+- **misc**: Fix txt-to-image api.
Improvements and Fixes
+#### Code refactoring
+
+- **misc**: Move backend api to (backend) folder group, closes [#4262](https://github.com/lobehub/lobe-chat/issues/4262) ([d8afb46](https://github.com/lobehub/lobe-chat/commit/d8afb46))
+
#### What's fixed
-- **ollama**: Suppport vision for LLaVA models, closes [#1791](https://github.com/lobehub/lobe-chat/issues/1791) ([e2d3de6](https://github.com/lobehub/lobe-chat/commit/e2d3de6))
+- **misc**: Fix txt-to-image api, closes [#4264](https://github.com/lobehub/lobe-chat/issues/4264) ([d1ff4ba](https://github.com/lobehub/lobe-chat/commit/d1ff4ba))
@@ -11152,22 +11026,22 @@
-## [Version 0.144.0](https://github.com/lobehub/lobe-chat/compare/v0.143.0...v0.144.0)
+### [Version 1.21.5](https://github.com/lobehub/lobe-chat/compare/v1.21.4...v1.21.5)
-Released on **2024-03-29**
+Released on **2024-10-05**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Support authentik as sso.
+- **misc**: Support shadcn in Artifacts.
Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Support authentik as sso, closes [#1650](https://github.com/lobehub/lobe-chat/issues/1650) ([181dfa5](https://github.com/lobehub/lobe-chat/commit/181dfa5))
+- **misc**: Support shadcn in Artifacts, closes [#4256](https://github.com/lobehub/lobe-chat/issues/4256) ([863bae5](https://github.com/lobehub/lobe-chat/commit/863bae5))
@@ -11177,22 +11051,22 @@
-## [Version 0.143.0](https://github.com/lobehub/lobe-chat/compare/v0.142.9...v0.143.0)
+### [Version 1.21.4](https://github.com/lobehub/lobe-chat/compare/v1.21.3...v1.21.4)
-Released on **2024-03-28**
+Released on **2024-10-02**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Add Bulgarian translation.
+- **misc**: Fix recharts deps in the Artifacts React Renderer.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Add Bulgarian translation, closes [#1732](https://github.com/lobehub/lobe-chat/issues/1732) ([e181dd1](https://github.com/lobehub/lobe-chat/commit/e181dd1))
+- **misc**: Fix recharts deps in the Artifacts React Renderer, closes [#4245](https://github.com/lobehub/lobe-chat/issues/4245) ([a120d21](https://github.com/lobehub/lobe-chat/commit/a120d21))
@@ -11202,22 +11076,22 @@
-### [Version 0.142.9](https://github.com/lobehub/lobe-chat/compare/v0.142.8...v0.142.9)
+### [Version 1.21.3](https://github.com/lobehub/lobe-chat/compare/v1.21.2...v1.21.3)
-Released on **2024-03-28**
+Released on **2024-10-01**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Fix Add agent and Converse button not jump.
+- **misc**: Move most `/api` to `/webapi`.
Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Fix Add agent and Converse button not jump, closes [#1785](https://github.com/lobehub/lobe-chat/issues/1785) ([a52799c](https://github.com/lobehub/lobe-chat/commit/a52799c))
+- **misc**: Move most `/api` to `/webapi`, closes [#4233](https://github.com/lobehub/lobe-chat/issues/4233) ([542c359](https://github.com/lobehub/lobe-chat/commit/542c359))
@@ -11227,22 +11101,22 @@
-### [Version 0.142.8](https://github.com/lobehub/lobe-chat/compare/v0.142.7...v0.142.8)
+### [Version 1.21.2](https://github.com/lobehub/lobe-chat/compare/v1.21.1...v1.21.2)
-Released on **2024-03-28**
+Released on **2024-10-01**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix gemini 1.5 pro model id to support gemini new models.
+- **misc**: Adjust Wenxin icon size.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix gemini 1.5 pro model id to support gemini new models, closes [#1776](https://github.com/lobehub/lobe-chat/issues/1776) ([591dcb3](https://github.com/lobehub/lobe-chat/commit/591dcb3))
+- **misc**: Adjust Wenxin icon size, closes [#4229](https://github.com/lobehub/lobe-chat/issues/4229) ([6ae79ce](https://github.com/lobehub/lobe-chat/commit/6ae79ce))
@@ -11252,23 +11126,15 @@
-### [Version 0.142.7](https://github.com/lobehub/lobe-chat/compare/v0.142.6...v0.142.7)
+### [Version 1.21.1](https://github.com/lobehub/lobe-chat/compare/v1.21.0...v1.21.1)
-Released on **2024-03-27**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fix the missing German locale.
+Released on **2024-09-30** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix the missing German locale, closes [#1753](https://github.com/lobehub/lobe-chat/issues/1753) ([a452612](https://github.com/lobehub/lobe-chat/commit/a452612))
-
@@ -11277,22 +11143,22 @@
-### [Version 0.142.6](https://github.com/lobehub/lobe-chat/compare/v0.142.5...v0.142.6)
+## [Version 1.21.0](https://github.com/lobehub/lobe-chat/compare/v1.20.8...v1.21.0)
-Released on **2024-03-26**
+Released on **2024-09-30**
-#### 🐛 Bug Fixes
+#### ✨ Features
-- **misc**: Fix normalize german locale.
+- **misc**: Add wenxin model provider.
Improvements and Fixes
-#### What's fixed
+#### What's improved
-- **misc**: Fix normalize german locale, closes [#1750](https://github.com/lobehub/lobe-chat/issues/1750) ([69fcc78](https://github.com/lobehub/lobe-chat/commit/69fcc78))
+- **misc**: Add wenxin model provider, closes [#4018](https://github.com/lobehub/lobe-chat/issues/4018) ([4483599](https://github.com/lobehub/lobe-chat/commit/4483599))
@@ -11302,24 +11168,15 @@
-### [Version 0.142.5](https://github.com/lobehub/lobe-chat/compare/v0.142.4...v0.142.5)
-
-Released on **2024-03-26**
-
-#### 🐛 Bug Fixes
+### [Version 1.20.8](https://github.com/lobehub/lobe-chat/compare/v1.20.7...v1.20.8)
-- **misc**: Fix mobile click, fix mobile click issue.
+Released on **2024-09-30** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Fix mobile click ([3775b28](https://github.com/lobehub/lobe-chat/commit/3775b28))
-- **misc**: Fix mobile click issue, closes [#1744](https://github.com/lobehub/lobe-chat/issues/1744) ([a6b1234](https://github.com/lobehub/lobe-chat/commit/a6b1234))
-
@@ -11328,15 +11185,23 @@
-### [Version 0.142.4](https://github.com/lobehub/lobe-chat/compare/v0.142.3...v0.142.4)
+### [Version 1.20.7](https://github.com/lobehub/lobe-chat/compare/v1.20.6...v1.20.7)
-Released on **2024-03-26**
+Released on **2024-09-29**
+
+#### 💄 Styles
+
+- **misc**: Update groq model list.
Improvements and Fixes
+#### Styles
+
+- **misc**: Update groq model list, closes [#4195](https://github.com/lobehub/lobe-chat/issues/4195) ([ef5164d](https://github.com/lobehub/lobe-chat/commit/ef5164d))
+
@@ -11345,23 +11210,15 @@
-### [Version 0.142.3](https://github.com/lobehub/lobe-chat/compare/v0.142.2...v0.142.3)
-
-Released on **2024-03-26**
-
-#### 🐛 Bug Fixes
+### [Version 1.20.6](https://github.com/lobehub/lobe-chat/compare/v1.20.5...v1.20.6)
-- **misc**: Pin `next-auth` temporary to fix build error.
+Released on **2024-09-29** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Pin `next-auth` temporary to fix build error, closes [#1739](https://github.com/lobehub/lobe-chat/issues/1739) ([e9ece9f](https://github.com/lobehub/lobe-chat/commit/e9ece9f))
-
@@ -11370,23 +11227,15 @@
-### [Version 0.142.2](https://github.com/lobehub/lobe-chat/compare/v0.142.1...v0.142.2)
+### [Version 1.20.5](https://github.com/lobehub/lobe-chat/compare/v1.20.4...v1.20.5)
-Released on **2024-03-25**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Support openrouter custom models env.
+Released on **2024-09-29** Improvements and Fixes
-#### What's fixed
-
-- **misc**: Support openrouter custom models env, closes [#1647](https://github.com/lobehub/lobe-chat/issues/1647) ([78baa16](https://github.com/lobehub/lobe-chat/commit/78baa16))
-
@@ -11395,9 +11244,9 @@
-### [Version 0.142.1](https://github.com/lobehub/lobe-chat/compare/v0.142.0...v0.142.1)
+### [Version 1.20.4](https://github.com/lobehub/lobe-chat/compare/v1.20.3...v1.20.4)
-Released on **2024-03-25**
+Released on **2024-09-28**
@@ -11412,22 +11261,22 @@
-## [Version 0.142.0](https://github.com/lobehub/lobe-chat/compare/v0.141.2...v0.142.0)
+### [Version 1.20.3](https://github.com/lobehub/lobe-chat/compare/v1.20.2...v1.20.3)
-Released on **2024-03-25**
+Released on **2024-09-28**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Support 01.AI as a new provider.
+- **misc**: Improve delete orphan chunks when delete files.
Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Support 01.AI as a new provider, closes [#1627](https://github.com/lobehub/lobe-chat/issues/1627) ([08342fd](https://github.com/lobehub/lobe-chat/commit/08342fd))
+- **misc**: Improve delete orphan chunks when delete files, closes [#4179](https://github.com/lobehub/lobe-chat/issues/4179) ([f3e0ffe](https://github.com/lobehub/lobe-chat/commit/f3e0ffe))
@@ -11437,22 +11286,22 @@
-### [Version 0.141.2](https://github.com/lobehub/lobe-chat/compare/v0.141.1...v0.141.2)
+### [Version 1.20.2](https://github.com/lobehub/lobe-chat/compare/v1.20.1...v1.20.2)
-Released on **2024-03-22**
+Released on **2024-09-27**
-#### 🐛 Bug Fixes
+#### 💄 Styles
-- **misc**: Fix window icon and scrollbar style.
+- **misc**: Add zhipu glm-4-flashx model.
Improvements and Fixes
-#### What's fixed
+#### Styles
-- **misc**: Fix window icon and scrollbar style, closes [#1691](https://github.com/lobehub/lobe-chat/issues/1691) ([4f46845](https://github.com/lobehub/lobe-chat/commit/4f46845))
+- **misc**: Add zhipu glm-4-flashx model, closes [#4173](https://github.com/lobehub/lobe-chat/issues/4173) ([b0c3abc](https://github.com/lobehub/lobe-chat/commit/b0c3abc))
@@ -11462,23 +11311,15 @@
-### [Version 0.141.1](https://github.com/lobehub/lobe-chat/compare/v0.141.0...v0.141.1)
-
-Released on **2024-03-22**
-
-#### ♻ Code Refactoring
+### [Version 1.20.1](https://github.com/lobehub/lobe-chat/compare/v1.20.0...v1.20.1)
-- **misc**: Refactor the Vercel Aanlytics and support Google Aanlytics.
+Released on **2024-09-27** Improvements and Fixes
-#### Code refactoring
-
-- **misc**: Refactor the Vercel Aanlytics and support Google Aanlytics, closes [#1688](https://github.com/lobehub/lobe-chat/issues/1688) ([e07e9cf](https://github.com/lobehub/lobe-chat/commit/e07e9cf))
-
@@ -11487,13 +11328,13 @@
-## [Version 0.141.0](https://github.com/lobehub/lobe-chat/compare/v0.140.1...v0.141.0)
+## [Version 1.20.0](https://github.com/lobehub/lobe-chat/compare/v1.19.36...v1.20.0)
-Released on **2024-03-22**
+Released on **2024-09-27**
#### ✨ Features
-- **misc**: Using YJS and WebRTC to support sync data between different devices.
+- **misc**: Add Hunyuan(Tencent) model provider.
@@ -11502,7 +11343,7 @@
#### What's improved
-- **misc**: Using YJS and WebRTC to support sync data between different devices, closes [#1525](https://github.com/lobehub/lobe-chat/issues/1525) ([60d9186](https://github.com/lobehub/lobe-chat/commit/60d9186))
+- **misc**: Add Hunyuan(Tencent) model provider, closes [#4147](https://github.com/lobehub/lobe-chat/issues/4147) ([8ddb41b](https://github.com/lobehub/lobe-chat/commit/8ddb41b))
@@ -11512,13 +11353,13 @@
-### [Version 0.140.1](https://github.com/lobehub/lobe-chat/compare/v0.140.0...v0.140.1)
+### [Version 1.19.36](https://github.com/lobehub/lobe-chat/compare/v1.19.35...v1.19.36)
-Released on **2024-03-22**
+Released on **2024-09-27**
#### 💄 Styles
-- **misc**: add Moonshot Kimi Reverse model to Moonshot model provider..
+- **misc**: Add llama3.2 model for openrouter provider.
@@ -11527,7 +11368,7 @@
#### Styles
-- **misc**: add Moonshot Kimi Reverse model to Moonshot model provider., closes [#1659](https://github.com/lobehub/lobe-chat/issues/1659) ([5bae263](https://github.com/lobehub/lobe-chat/commit/5bae263))
+- **misc**: Add llama3.2 model for openrouter provider, closes [#4151](https://github.com/lobehub/lobe-chat/issues/4151) ([6f1a966](https://github.com/lobehub/lobe-chat/commit/6f1a966))
@@ -11537,22 +11378,22 @@
-## [Version 0.140.0](https://github.com/lobehub/lobe-chat/compare/v0.139.2...v0.140.0)
+### [Version 1.19.35](https://github.com/lobehub/lobe-chat/compare/v1.19.34...v1.19.35)
-Released on **2024-03-22**
+Released on **2024-09-27**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Add gemini 1.5 pro support.
+- **misc**: Add o1-preview and o1-mini model to github model provider.
Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Add gemini 1.5 pro support, closes [#1669](https://github.com/lobehub/lobe-chat/issues/1669) ([2b280af](https://github.com/lobehub/lobe-chat/commit/2b280af))
+- **misc**: Add o1-preview and o1-mini model to github model provider, closes [#4127](https://github.com/lobehub/lobe-chat/issues/4127) ([1e4d016](https://github.com/lobehub/lobe-chat/commit/1e4d016))
@@ -11562,17 +11403,34 @@
-### [Version 0.139.2](https://github.com/lobehub/lobe-chat/compare/v0.139.1...v0.139.2)
+### [Version 1.19.34](https://github.com/lobehub/lobe-chat/compare/v1.19.33...v1.19.34)
-Released on **2024-03-22**
+Released on **2024-09-26**
+
+
+
+
+Improvements and Fixes
+
+
+
+
-## [Version 0.131.0](https://github.com/lobehub/lobe-chat/compare/v0.130.7...v0.131.0)
+### [Version 1.19.9](https://github.com/lobehub/lobe-chat/compare/v1.19.8...v1.19.9)
-Released on **2024-03-05**
+Released on **2024-09-20**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Support langfuse integration.
+- **misc**: Fix a bug with server agent config when user not exist.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Support langfuse integration, closes [#1325](https://github.com/lobehub/lobe-chat/issues/1325) ([aaedfa7](https://github.com/lobehub/lobe-chat/commit/aaedfa7))
+- **misc**: Fix a bug with server agent config when user not exist, closes [#4034](https://github.com/lobehub/lobe-chat/issues/4034) ([f6a232b](https://github.com/lobehub/lobe-chat/commit/f6a232b))
-### [Version 0.130.3](https://github.com/lobehub/lobe-chat/compare/v0.130.2...v0.130.3)
+### [Version 1.19.4](https://github.com/lobehub/lobe-chat/compare/v1.19.3...v1.19.4)
-Released on **2024-02-29**
+Released on **2024-09-19**
#### ♻ Code Refactoring
-- **misc**: Refactor the google api route and add more tests for chat route.
+- **misc**: Refactor the sitemap implement.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### Code refactoring
-- **misc**: Refactor the google api route and add more tests for chat route, closes [#1424](https://github.com/lobehub/lobe-chat/issues/1424) ([063a4d5](https://github.com/lobehub/lobe-chat/commit/063a4d5))
+- **misc**: Refactor the sitemap implement, closes [#4012](https://github.com/lobehub/lobe-chat/issues/4012) ([d93a161](https://github.com/lobehub/lobe-chat/commit/d93a161))
+- **misc**: Fix a corner case of `tools_call` with empty object.
-## [Version 0.129.0](https://github.com/lobehub/lobe-chat/compare/v0.128.10...v0.129.0)
+#### 💄 Styles
-Released on **2024-02-22**
+- **misc**: Delete duplicate models in ollama.
-#### ✨ Features
+
-- **misc**: Support perplexity AI provider.
+
+Improvements and Fixes
-
+#### What's fixed
-
- Improvements and Fixes
+- **misc**: Fix a corner case of `tools_call` with empty object, closes [#3955](https://github.com/lobehub/lobe-chat/issues/3955) ([d3fabdc](https://github.com/lobehub/lobe-chat/commit/d3fabdc))
-#### What's improved
+#### Styles
-- **misc**: Support perplexity AI provider, closes [#1339](https://github.com/lobehub/lobe-chat/issues/1339) ([61c88fb](https://github.com/lobehub/lobe-chat/commit/61c88fb))
+- **misc**: Delete duplicate models in ollama, closes [#3989](https://github.com/lobehub/lobe-chat/issues/3989) ([ece60ee](https://github.com/lobehub/lobe-chat/commit/ece60ee))
-## [Version 0.128.0](https://github.com/lobehub/lobe-chat/compare/v0.127.2...v0.128.0)
+## [Version 1.17.0](https://github.com/lobehub/lobe-chat/compare/v1.16.14...v1.17.0)
-Released on **2024-02-14**
+Released on **2024-09-13**
#### ✨ Features
-- **misc**: Support define default agent config with `DEFAULT_AGENT_CONFIG` ENV.
+- **misc**: Support openai new OpenAI o1-preview/o1-mini models.
+
+#### 💄 Styles
+
+- **misc**: Support Google Model List.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's improved
-- **misc**: Support define default agent config with `DEFAULT_AGENT_CONFIG` ENV, closes [#1291](https://github.com/lobehub/lobe-chat/issues/1291) ([c7c096e](https://github.com/lobehub/lobe-chat/commit/c7c096e))
+- **misc**: Support openai new OpenAI o1-preview/o1-mini models, closes [#3943](https://github.com/lobehub/lobe-chat/issues/3943) ([61bfeb2](https://github.com/lobehub/lobe-chat/commit/61bfeb2))
+
+#### Styles
+
+- **misc**: Support Google Model List, closes [#3938](https://github.com/lobehub/lobe-chat/issues/3938) ([be4efc7](https://github.com/lobehub/lobe-chat/commit/be4efc7))
-## [Version 0.127.0](https://github.com/lobehub/lobe-chat/compare/v0.126.5...v0.127.0)
+### [Version 1.16.12](https://github.com/lobehub/lobe-chat/compare/v1.16.11...v1.16.12)
-Released on **2024-02-13**
+Released on **2024-09-12**
-#### ✨ Features
+#### 💄 Styles
-- **llm**: Support Ollama AI Provider for local LLM.
+- **misc**: Remove brackets from model names with dates in OpenAI.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### Styles
-- **llm**: Support Ollama AI Provider for local LLM ([3b6f249](https://github.com/lobehub/lobe-chat/commit/3b6f249))
+- **misc**: Remove brackets from model names with dates in OpenAI, closes [#3927](https://github.com/lobehub/lobe-chat/issues/3927) ([2a937bc](https://github.com/lobehub/lobe-chat/commit/2a937bc))
-
-## [Version 0.126.0](https://github.com/lobehub/lobe-chat/compare/v0.125.0...v0.126.0)
-
-Released on **2024-02-09**
-
-#### ✨ Features
-
-- **misc**: Support umami analytics.
-
-#### 🐛 Bug Fixes
-
-- **misc**: The back button on the chat setting page can correctly return to the configured Agent chat page.
-
-
-
-
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Support umami analytics, closes [#1267](https://github.com/lobehub/lobe-chat/issues/1267) ([da7beba](https://github.com/lobehub/lobe-chat/commit/da7beba))
-
-#### What's fixed
-
-- **misc**: The back button on the chat setting page can correctly return to the configured Agent chat page, closes [#1272](https://github.com/lobehub/lobe-chat/issues/1272) ([4cc1ad5](https://github.com/lobehub/lobe-chat/commit/4cc1ad5))
-
-
-
-
-
-### [Version 0.122.6](https://github.com/lobehub/lobe-chat/compare/v0.122.5...v0.122.6)
-
-Released on **2024-01-31**
-
-#### 🐛 Bug Fixes
-
-- **check**: The state of connectivity can only be singular.
-
-
-
-
- Improvements and Fixes
-
-#### What's fixed
-
-- **check**: The state of connectivity can only be singular, closes [#1201](https://github.com/lobehub/lobe-chat/issues/1201) ([c412baf](https://github.com/lobehub/lobe-chat/commit/c412baf))
-
-
-
-
-
-### [Version 0.119.12](https://github.com/lobehub/lobe-chat/compare/v0.119.11...v0.119.12)
-
-Released on **2024-01-09**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fix new line after sending messages with enter key.
-
-
-
-
- Improvements and Fixes
-
-#### What's fixed
-
-- **misc**: Fix new line after sending messages with enter key, closes [#990](https://github.com/lobehub/lobe-chat/issues/990) ([e6ab019](https://github.com/lobehub/lobe-chat/commit/e6ab019))
-
-
-
-
-
-### [Version 0.118.8](https://github.com/lobehub/lobe-chat/compare/v0.118.7...v0.118.8)
-
-Released on **2024-01-03**
-
-#### 💄 Styles
-
-- **misc**: Add Vietnamese files and add the vi-VN option in the General Settings.
-
-
-
-
- Improvements and Fixes
-
-#### Styles
-
-- **misc**: Add Vietnamese files and add the vi-VN option in the General Settings, closes [#860](https://github.com/lobehub/lobe-chat/issues/860) ([c2e5606](https://github.com/lobehub/lobe-chat/commit/c2e5606))
-
-
-
-
-
-### [Version 0.115.11](https://github.com/lobehub/lobe-chat/compare/v0.115.10...v0.115.11)
-
-Released on **2023-12-25**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fix agent system role modal scrolling when content is too long.
-
-
-
-
- Improvements and Fixes
-
-#### What's fixed
-
-- **misc**: Fix agent system role modal scrolling when content is too long, closes [#801](https://github.com/lobehub/lobe-chat/issues/801) ([f482a80](https://github.com/lobehub/lobe-chat/commit/f482a80))
-
-
-
-
-
-### [Version 0.114.4](https://github.com/lobehub/lobe-chat/compare/v0.114.3...v0.114.4)
-
-Released on **2023-12-19**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fix agent system role modal scrolling when content is too long.
-
-
-
-
- Improvements and Fixes
-
-#### What's fixed
-
-- **misc**: Fix agent system role modal scrolling when content is too long, closes [#716](https://github.com/lobehub/lobe-chat/issues/716) ([c3e36d1](https://github.com/lobehub/lobe-chat/commit/c3e36d1))
-
-
-
-
-
-## [Version 0.108.0](https://github.com/lobehub/lobe-chat/compare/v0.107.16...v0.108.0)
-
-Released on **2023-12-03**
-
-#### ✨ Features
-
-- **misc**: Hide the password form item in the settings when there is no `ACCESS_CODE` env.
-
-
-
-
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Hide the password form item in the settings when there is no `ACCESS_CODE` env, closes [#568](https://github.com/lobehub/lobe-chat/issues/568) ([3b5f8b2](https://github.com/lobehub/lobe-chat/commit/3b5f8b2))
-
-
-
-
-
-## [Version 0.105.0](https://github.com/lobehub/lobe-chat/compare/v0.104.0...v0.105.0)
-
-Released on **2023-11-22**
-
-#### ✨ Features
-
-- **misc**: Standalone pluginn can get more arguments on init.
-
-
-
-
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Standalone pluginn can get more arguments on init, closes [#498](https://github.com/lobehub/lobe-chat/issues/498) ([a7624f5](https://github.com/lobehub/lobe-chat/commit/a7624f5))
-
-
-
-
-
-## [Version 0.104.0](https://github.com/lobehub/lobe-chat/compare/v0.103.1...v0.104.0)
-
-Released on **2023-11-21**
-
-#### ✨ Features
-
-- **misc**: Support using env variable to set regions for OpenAI Edge Functions..
-
-
-
-
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Support using env variable to set regions for OpenAI Edge Functions., closes [#473](https://github.com/lobehub/lobe-chat/issues/473) ([de6b79e](https://github.com/lobehub/lobe-chat/commit/de6b79e))
-
-
-
-
-
-### [Version 0.99.1](https://github.com/lobehub/lobe-chat/compare/v0.99.0...v0.99.1)
-
-Released on **2023-11-08**
-
-#### 💄 Styles
-
-- **misc**: Add max height to model menu in chat input area.
-
-
-
-
- Improvements and Fixes
-
-#### Styles
-
-- **misc**: Add max height to model menu in chat input area, closes [#430](https://github.com/lobehub/lobe-chat/issues/430) ([c9a86f3](https://github.com/lobehub/lobe-chat/commit/c9a86f3))
-
-
-
-
-
-## [Version 0.99.0](https://github.com/lobehub/lobe-chat/compare/v0.98.3...v0.99.0)
-
-Released on **2023-11-08**
-
-#### ✨ Features
-
-- **misc**: Add Environment Variable for custom model name when deploying.
-
-
-
-
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Add Environment Variable for custom model name when deploying, closes [#429](https://github.com/lobehub/lobe-chat/issues/429) ([15f9fa2](https://github.com/lobehub/lobe-chat/commit/15f9fa2))
-
-
-
-
-
-### [Version 0.98.3](https://github.com/lobehub/lobe-chat/compare/v0.98.2...v0.98.3)
-
-Released on **2023-11-07**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fix redirect to welcome problem when there are topics in inbox.
-
-
-
-
- Improvements and Fixes
-
-#### What's fixed
-
-- **misc**: Fix redirect to welcome problem when there are topics in inbox, closes [#422](https://github.com/lobehub/lobe-chat/issues/422) ([3d2588a](https://github.com/lobehub/lobe-chat/commit/3d2588a))
-
-
-
-
-
-## [Version 0.97.0](https://github.com/lobehub/lobe-chat/compare/v0.96.9...v0.97.0)
-
-Released on **2023-11-05**
-
-#### ✨ Features
-
-- **misc**: Add open new topic when open a topic.
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fix toggle back to default topic when clearing topic.
-
-
-
-
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Add open new topic when open a topic ([4df6384](https://github.com/lobehub/lobe-chat/commit/4df6384))
-
-#### What's fixed
-
-- **misc**: Fix toggle back to default topic when clearing topic ([6fe0a5c](https://github.com/lobehub/lobe-chat/commit/6fe0a5c))
-
-
-
-
-
-### [Version 0.96.7](https://github.com/lobehub/lobe-chat/compare/v0.96.6...v0.96.7)
-
-Released on **2023-10-31**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fix a bug when click inbox not switch back to chat page.
-
-
-
-
- Improvements and Fixes
-
-#### What's fixed
-
-- **misc**: Fix a bug when click inbox not switch back to chat page ([31f6d29](https://github.com/lobehub/lobe-chat/commit/31f6d29))
-
-
-
-
-
-### [Version 0.96.2](https://github.com/lobehub/lobe-chat/compare/v0.96.1...v0.96.2)
-
-Released on **2023-10-28**
-
-#### 💄 Styles
-
-- **misc**: Fix some styles and make updates to various files.
-
-
-
-
- Improvements and Fixes
-
-#### Styles
-
-- **misc**: Fix some styles and make updates to various files ([44a5f0a](https://github.com/lobehub/lobe-chat/commit/44a5f0a))
-
-
-
-
-
-### [Version 0.94.5](https://github.com/lobehub/lobe-chat/compare/v0.94.4...v0.94.5)
-
-Released on **2023-10-22**
-
-#### 🐛 Bug Fixes
-
-- **misc**: Fallback agent market index to en when not find correct locale.
-
-
-
-
- Improvements and Fixes
-
-#### What's fixed
-
-- **misc**: Fallback agent market index to en when not find correct locale, closes [#355](https://github.com/lobehub/lobe-chat/issues/355) ([7a45ab4](https://github.com/lobehub/lobe-chat/commit/7a45ab4))
-
-
-
-
-## [Version 0.89.0](https://github.com/lobehub/lobe-chat/compare/v0.88.0...v0.89.0)
+### [Version 1.16.8](https://github.com/lobehub/lobe-chat/compare/v1.16.7...v1.16.8)
-Released on **2023-10-12**
+Released on **2024-09-12**
-#### ✨ Features
+#### 💄 Styles
-- **agent-card**: Add and modify features for agent card.
+- **misc**: Improve models and add more info for providers and models.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### Styles
-- **agent-card**: Add and modify features for agent card ([3e3090a](https://github.com/lobehub/lobe-chat/commit/3e3090a))
+- **misc**: Improve models and add more info for providers and models, closes [#3911](https://github.com/lobehub/lobe-chat/issues/3911) ([8a8fc6a](https://github.com/lobehub/lobe-chat/commit/8a8fc6a))
-### [Version 0.85.2](https://github.com/lobehub/lobe-chat/compare/v0.85.1...v0.85.2)
+### [Version 1.15.34](https://github.com/lobehub/lobe-chat/compare/v1.15.33...v1.15.34)
-Released on **2023-10-10**
+Released on **2024-09-10**
-#### 🐛 Bug Fixes
+#### ♻ Code Refactoring
-- **misc**: Add apikey form when there is no default api key in env.
+- **misc**: Change empty content stream behavior.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's fixed
+#### Code refactoring
-- **misc**: Add apikey form when there is no default api key in env, closes [#290](https://github.com/lobehub/lobe-chat/issues/290) ([2c907e9](https://github.com/lobehub/lobe-chat/commit/2c907e9))
+- **misc**: Change empty content stream behavior, closes [#3883](https://github.com/lobehub/lobe-chat/issues/3883) ([e910f68](https://github.com/lobehub/lobe-chat/commit/e910f68))
-## [Version 0.84.0](https://github.com/lobehub/lobe-chat/compare/v0.83.10...v0.84.0)
+### [Version 1.15.31](https://github.com/lobehub/lobe-chat/compare/v1.15.30...v1.15.31)
-Released on **2023-10-10**
+Released on **2024-09-10**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: Support detect new version and upgrade action.
+- **misc**: Baichuan should not introduce `freequency_penality` parameters.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: Support detect new version and upgrade action, closes [#282](https://github.com/lobehub/lobe-chat/issues/282) ([5da19b2](https://github.com/lobehub/lobe-chat/commit/5da19b2))
+- **misc**: Baichuan should not introduce `freequency_penality` parameters, closes [#3871](https://github.com/lobehub/lobe-chat/issues/3871) ([66a061e](https://github.com/lobehub/lobe-chat/commit/66a061e))
-### [Version 0.83.9](https://github.com/lobehub/lobe-chat/compare/v0.83.8...v0.83.9)
+### [Version 1.15.29](https://github.com/lobehub/lobe-chat/compare/v1.15.28...v1.15.29)
-Released on **2023-10-08**
+Released on **2024-09-09**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **agent-market**: Refactor desktop and mobile to improve mobile performance.
+- **misc**: Gemini cannot input images when server database is enabled.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **agent-market**: Refactor desktop and mobile to improve mobile performance, closes [#278](https://github.com/lobehub/lobe-chat/issues/278) ([82b7f60](https://github.com/lobehub/lobe-chat/commit/82b7f60))
+- **misc**: Gemini cannot input images when server database is enabled, closes [#3370](https://github.com/lobehub/lobe-chat/issues/3370) ([eb552d2](https://github.com/lobehub/lobe-chat/commit/eb552d2))
-### [Version 0.83.1](https://github.com/lobehub/lobe-chat/compare/v0.83.0...v0.83.1)
+### [Version 1.15.21](https://github.com/lobehub/lobe-chat/compare/v1.15.20...v1.15.21)
-Released on **2023-10-06**
+Released on **2024-09-08**
#### ♻ Code Refactoring
-- **misc**: Refactor settings page entry.
+- **misc**: Temperature range from 0 to 2.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### Code refactoring
-- **misc**: Refactor settings page entry ([e86aff2](https://github.com/lobehub/lobe-chat/commit/e86aff2))
+- **misc**: Temperature range from 0 to 2, closes [#3355](https://github.com/lobehub/lobe-chat/issues/3355) ([4a9114e](https://github.com/lobehub/lobe-chat/commit/4a9114e))
-### [Version 0.82.5](https://github.com/lobehub/lobe-chat/compare/v0.82.4...v0.82.5)
+### [Version 1.15.16](https://github.com/lobehub/lobe-chat/compare/v1.15.15...v1.15.16)
-Released on **2023-09-29**
+Released on **2024-09-06**
#### 💄 Styles
-- **misc**: Update theme color and styling of mobile settings page.
+- **misc**: Update Bedrock model list & add `AWS_BEDROCK_MODEL_LIST` support.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### Styles
-- **misc**: Update theme color and styling of mobile settings page ([1acfb71](https://github.com/lobehub/lobe-chat/commit/1acfb71))
+- **misc**: Update Bedrock model list & add `AWS_BEDROCK_MODEL_LIST` support, closes [#3723](https://github.com/lobehub/lobe-chat/issues/3723) ([0aad972](https://github.com/lobehub/lobe-chat/commit/0aad972))
-### [Version 0.79.7](https://github.com/lobehub/lobe-chat/compare/v0.79.6...v0.79.7)
+### [Version 1.15.5](https://github.com/lobehub/lobe-chat/compare/v1.15.4...v1.15.5)
-Released on **2023-09-27**
+Released on **2024-09-01**
-#### ♻ Code Refactoring
+#### 💄 Styles
-- **misc**: Use hook to check PWA env.
+- **misc**: Update Together AI model list.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### Code refactoring
+#### Styles
-- **misc**: Use hook to check PWA env ([b4234db](https://github.com/lobehub/lobe-chat/commit/b4234db))
+- **misc**: Update Together AI model list, closes [#3713](https://github.com/lobehub/lobe-chat/issues/3713) ([0dde3b1](https://github.com/lobehub/lobe-chat/commit/0dde3b1))
-### [Version 0.79.3](https://github.com/lobehub/lobe-chat/compare/v0.79.2...v0.79.3)
+### [Version 1.15.1](https://github.com/lobehub/lobe-chat/compare/v1.15.0...v1.15.1)
-Released on **2023-09-25**
+Released on **2024-08-30**
#### 💄 Styles
-- **meta**: Update meta image.
+- **misc**: Update the sorting of each provider model.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### Styles
-- **meta**: Update meta image, closes [#66](https://github.com/lobehub/lobe-chat/issues/66) ([a71ffff](https://github.com/lobehub/lobe-chat/commit/a71ffff))
+- **misc**: Update the sorting of each provider model, closes [#3689](https://github.com/lobehub/lobe-chat/issues/3689) ([e82c9dd](https://github.com/lobehub/lobe-chat/commit/e82c9dd))
-### [Version 0.76.2](https://github.com/lobehub/lobe-chat/compare/v0.76.1...v0.76.2)
+### [Version 1.14.5](https://github.com/lobehub/lobe-chat/compare/v1.14.4...v1.14.5)
-Released on **2023-09-11**
+Released on **2024-08-28**
#### 🐛 Bug Fixes
-- **misc**: Fix client config.
+- **misc**: No user name if Cloudflare Zero Trust with onetimepin.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's fixed
-- **misc**: Fix client config ([d62f1b3](https://github.com/lobehub/lobe-chat/commit/d62f1b3))
+- **misc**: No user name if Cloudflare Zero Trust with onetimepin, closes [#3649](https://github.com/lobehub/lobe-chat/issues/3649) ([5bfee5a](https://github.com/lobehub/lobe-chat/commit/5bfee5a))
-### [Version 0.72.4](https://github.com/lobehub/lobe-chat/compare/v0.72.3...v0.72.4)
+### [Version 1.13.2](https://github.com/lobehub/lobe-chat/compare/v1.13.1...v1.13.2)
-Released on **2023-09-10**
+Released on **2024-08-27**
#### 🐛 Bug Fixes
-- **misc**: Use en-US when no suit lang with plugin index.
+- **misc**: Bypass vercel deployment protection, fix can send message on uploading files.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's fixed
-- **misc**: Use en-US when no suit lang with plugin index ([4e9668d](https://github.com/lobehub/lobe-chat/commit/4e9668d))
+- **misc**: Bypass vercel deployment protection, closes [#3627](https://github.com/lobehub/lobe-chat/issues/3627) ([47da20d](https://github.com/lobehub/lobe-chat/commit/47da20d))
+- **misc**: Fix can send message on uploading files, closes [#3618](https://github.com/lobehub/lobe-chat/issues/3618) ([fe4329a](https://github.com/lobehub/lobe-chat/commit/fe4329a))
-### [Version 0.69.1](https://github.com/lobehub/lobe-chat/compare/v0.69.0...v0.69.1)
+### [Version 1.12.11](https://github.com/lobehub/lobe-chat/compare/v1.12.10...v1.12.11)
-Released on **2023-09-06**
+Released on **2024-08-23**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Migrate openai-edge to openai.
+- **misc**: Remove orphan chunks if there is no related file.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Migrate openai-edge to openai, closes [#145](https://github.com/lobehub/lobe-chat/issues/145) ([75ee574](https://github.com/lobehub/lobe-chat/commit/75ee574))
+- **misc**: Remove orphan chunks if there is no related file, closes [#3578](https://github.com/lobehub/lobe-chat/issues/3578) ([36bcaf3](https://github.com/lobehub/lobe-chat/commit/36bcaf3))
-### [Version 0.63.3](https://github.com/lobehub/lobe-chat/compare/v0.63.2...v0.63.3)
+### [Version 1.12.1](https://github.com/lobehub/lobe-chat/compare/v1.12.0...v1.12.1)
-Released on **2023-08-28**
+Released on **2024-08-21**
-#### ♻ Code Refactoring
+#### 🐛 Bug Fixes
-- **misc**: Refactor with new market url.
+- **misc**: Fix embeddings multi-insert when there is issues with async task.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### Code refactoring
+#### What's fixed
-- **misc**: Refactor with new market url, closes [#123](https://github.com/lobehub/lobe-chat/issues/123) ([34a88f8](https://github.com/lobehub/lobe-chat/commit/34a88f8))
+- **misc**: Fix embeddings multi-insert when there is issues with async task, closes [#3530](https://github.com/lobehub/lobe-chat/issues/3530) ([e2cfff7](https://github.com/lobehub/lobe-chat/commit/e2cfff7))
-## [Version 0.56.0](https://github.com/lobehub/lobe-chat/compare/v0.55.1...v0.56.0)
+[](#readme-top)
-Released on **2023-08-24**
+
-#### ✨ Features
+### [Version 1.9.7](https://github.com/lobehub/lobe-chat/compare/v1.9.6...v1.9.7)
-- **misc**: Use new plugin manifest to support plugin’s multi api.
+Released on **2024-08-13**
-
+
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Use new plugin manifest to support plugin’s multi api, closes [#101](https://github.com/lobehub/lobe-chat/issues/101) ([4534598](https://github.com/lobehub/lobe-chat/commit/4534598))
+Improvements and Fixes
-
-## [Version 0.54.0](https://github.com/lobehub/lobe-chat/compare/v0.53.0...v0.54.0)
-Released on **2023-08-15**
-
-#### ✨ Features
-
-- **misc**: Add new features and improve user interface and functionality.
-
-
-
-
- Improvements and Fixes
-
-#### What's improved
-
-- **misc**: Add new features and improve user interface and functionality ([1543bd1](https://github.com/lobehub/lobe-chat/commit/1543bd1))
-
-
+[](#readme-top)
-
-## [Version 0.53.0](https://github.com/lobehub/lobe-chat/compare/v0.52.1...v0.53.0)
+## [Version 1.9.0](https://github.com/lobehub/lobe-chat/compare/v1.8.2...v1.9.0)
-Released on **2023-08-15**
+Released on **2024-08-05**
#### ✨ Features
-- **sidebar**: Add DraggablePanelContainer and adjust layout and styling.
+- **misc**: Skip login page if only one provider exists.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's improved
-- **sidebar**: Add DraggablePanelContainer and adjust layout and styling ([e8c384f](https://github.com/lobehub/lobe-chat/commit/e8c384f))
+- **misc**: Skip login page if only one provider exists, closes [#3400](https://github.com/lobehub/lobe-chat/issues/3400) ([52da1d8](https://github.com/lobehub/lobe-chat/commit/52da1d8))
-## [Version 0.51.0](https://github.com/lobehub/lobe-chat/compare/v0.50.0...v0.51.0)
+### [Version 1.8.1](https://github.com/lobehub/lobe-chat/compare/v1.8.0...v1.8.1)
-Released on **2023-08-15**
+Released on **2024-08-03**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Add Footer component and modify Token and index files.
+- **misc**: Fix `aya`, `mathstral` model tag icon & update ollama model info.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Add Footer component and modify Token and index files ([41a3823](https://github.com/lobehub/lobe-chat/commit/41a3823))
+- **misc**: Fix `aya`, `mathstral` model tag icon & update ollama model info, closes [#3382](https://github.com/lobehub/lobe-chat/issues/3382) ([ced95a8](https://github.com/lobehub/lobe-chat/commit/ced95a8))
-## [Version 0.50.0](https://github.com/lobehub/lobe-chat/compare/v0.49.0...v0.50.0)
+## [Version 1.8.0](https://github.com/lobehub/lobe-chat/compare/v1.7.10...v1.8.0)
-Released on **2023-08-15**
+Released on **2024-08-02**
#### ✨ Features
-- **misc**: Update messages, settings, error codes, plugin names, weather data display, and UI.
+- **misc**: Add NextAuth as authentication service in server database.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's improved
-- **misc**: Update messages, settings, error codes, plugin names, weather data display, and UI ([a41db51](https://github.com/lobehub/lobe-chat/commit/a41db51))
+- **misc**: Add NextAuth as authentication service in server database, closes [#2935](https://github.com/lobehub/lobe-chat/issues/2935) ([5a0b972](https://github.com/lobehub/lobe-chat/commit/5a0b972))
-## [Version 0.49.0](https://github.com/lobehub/lobe-chat/compare/v0.48.0...v0.49.0)
+### [Version 1.7.10](https://github.com/lobehub/lobe-chat/compare/v1.7.9...v1.7.10)
-Released on **2023-08-15**
+Released on **2024-08-02**
-#### ✨ Features
+#### 💄 Styles
-- **misc**: Add `BackToBottom` to conversation, Update icons and text in various components.
+- **misc**: Add Gemini 1.5 Pro Exp model.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### Styles
-- **misc**: Add `BackToBottom` to conversation ([1433aa9](https://github.com/lobehub/lobe-chat/commit/1433aa9))
-- **misc**: Update icons and text in various components ([0e7a683](https://github.com/lobehub/lobe-chat/commit/0e7a683))
+- **misc**: Add Gemini 1.5 Pro Exp model, closes [#3384](https://github.com/lobehub/lobe-chat/issues/3384) ([0de8b7b](https://github.com/lobehub/lobe-chat/commit/0de8b7b))
-## [Version 0.40.0](https://github.com/lobehub/lobe-chat/compare/v0.39.4...v0.40.0)
+## [Version 1.6.0](https://github.com/lobehub/lobe-chat/compare/v1.5.5...v1.6.0)
-Released on **2023-08-05**
+Released on **2024-07-19**
#### ✨ Features
-- **misc**: Add new dependency, add Tag and PluginTag components, update HeaderTitle.
+- **misc**: Add `gpt-4o-mini` in OpenAI Provider and set it as the default model.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's improved
-- **misc**: Add new dependency, add Tag and PluginTag components, update HeaderTitle, closes [#56](https://github.com/lobehub/lobe-chat/issues/56) [#55](https://github.com/lobehub/lobe-chat/issues/55) [#54](https://github.com/lobehub/lobe-chat/issues/54) ([2812ea2](https://github.com/lobehub/lobe-chat/commit/2812ea2))
+- **misc**: Add `gpt-4o-mini` in OpenAI Provider and set it as the default model, closes [#3256](https://github.com/lobehub/lobe-chat/issues/3256) ([a84d807](https://github.com/lobehub/lobe-chat/commit/a84d807))
-## [Version 0.35.0](https://github.com/lobehub/lobe-chat/compare/v0.34.0...v0.35.0)
+## [Version 1.4.0](https://github.com/lobehub/lobe-chat/compare/v1.3.6...v1.4.0)
-Released on **2023-07-31**
+Released on **2024-07-12**
#### ✨ Features
-- **misc**: Add agent settings functionality, new components, and features for AgentMeta, Add and modify translations for various keys in JSON code files.
+- **misc**: Add 360AI model provider.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's improved
-- **misc**: Add agent settings functionality, new components, and features for AgentMeta ([b1e5ff9](https://github.com/lobehub/lobe-chat/commit/b1e5ff9))
-- **misc**: Add and modify translations for various keys in JSON code files ([503adb4](https://github.com/lobehub/lobe-chat/commit/503adb4))
+- **misc**: Add 360AI model provider, closes [#3130](https://github.com/lobehub/lobe-chat/issues/3130) ([79c5f86](https://github.com/lobehub/lobe-chat/commit/79c5f86))
-## [Version 0.34.0](https://github.com/lobehub/lobe-chat/compare/v0.33.0...v0.34.0)
+### [Version 1.3.6](https://github.com/lobehub/lobe-chat/compare/v1.3.5...v1.3.6)
-Released on **2023-07-31**
+Released on **2024-07-11**
-#### ✨ Features
+#### ♻ Code Refactoring
-- **misc**: Add agent settings functionality, Add new components and features for AgentMeta, Improve organization and functionality of settings and configuration features.
+- **misc**: Improve agent runtime code.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### Code refactoring
-- **misc**: Add agent settings functionality ([b0aaeed](https://github.com/lobehub/lobe-chat/commit/b0aaeed))
-- **misc**: Add new components and features for AgentMeta ([1232d95](https://github.com/lobehub/lobe-chat/commit/1232d95))
-- **misc**: Improve organization and functionality of settings and configuration features ([badde35](https://github.com/lobehub/lobe-chat/commit/badde35))
+- **misc**: Improve agent runtime code, closes [#3199](https://github.com/lobehub/lobe-chat/issues/3199) ([9f211e2](https://github.com/lobehub/lobe-chat/commit/9f211e2))
-## [Version 0.31.0](https://github.com/lobehub/lobe-chat/compare/v0.30.1...v0.31.0)
+### [Version 1.3.3](https://github.com/lobehub/lobe-chat/compare/v1.3.2...v1.3.3)
-Released on **2023-07-30**
+Released on **2024-07-09**
-#### ✨ Features
+#### 🐛 Bug Fixes
-- **misc**: 支持展示 token 使用量.
+- **misc**: Allow user to use their own WebRTC signaling.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### What's fixed
-- **misc**: 支持展示 token 使用量,closes [#31](https://github.com/lobehub/lobe-chat/issues/31) ([e4d4dac](https://github.com/lobehub/lobe-chat/commit/e4d4dac))
+- **misc**: Allow user to use their own WebRTC signaling, closes [#3182](https://github.com/lobehub/lobe-chat/issues/3182) ([c7f8f38](https://github.com/lobehub/lobe-chat/commit/c7f8f38))
-### [Version 0.22.1](https://github.com/lobehub/lobe-chat/compare/v0.22.0...v0.22.1)
+### [Version 1.2.2](https://github.com/lobehub/lobe-chat/compare/v1.2.1...v1.2.2)
-Released on **2023-07-25**
+Released on **2024-07-01**
#### 🐛 Bug Fixes
-- **misc**: 修正自定义 OpenAI API Key 的使用问题.
+- **misc**: Display issue when select default model in System Agent.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's fixed
-- **misc**: 修正自定义 OpenAI API Key 的使用问题 ([84475c0](https://github.com/lobehub/lobe-chat/commit/84475c0))
+- **misc**: Display issue when select default model in System Agent, closes [#3095](https://github.com/lobehub/lobe-chat/issues/3095) ([49f7f33](https://github.com/lobehub/lobe-chat/commit/49f7f33))
-## [Version 0.15.0](https://github.com/lobehub/lobe-chat/compare/v0.14.0...v0.15.0)
+### [Version 1.1.9](https://github.com/lobehub/lobe-chat/compare/v1.1.8...v1.1.9)
+
+Released on **2024-06-24**
-Released on **2023-07-24**
+#### 🐛 Bug Fixes
-#### ✨ Features
+- **misc**: Fix agent tags.
+
+#### 💄 Styles
-- **misc**: Add new features and improve user experience, Import and use constants from "meta.ts" instead of "agentConfig".
+- **ui**: Fixed incorrect text display on connect check.
+- **misc**: Always show action on mobile.
-
+
- Improvements and Fixes
+Improvements and Fixes
-#### What's improved
+#### What's fixed
+
+- **misc**: Fix agent tags, closes [#3015](https://github.com/lobehub/lobe-chat/issues/3015) ([01e965b](https://github.com/lobehub/lobe-chat/commit/01e965b))
+
+#### Styles
-- **misc**: Add new features and improve user experience ([64c8782](https://github.com/lobehub/lobe-chat/commit/64c8782))
-- **misc**: Import and use constants from "meta.ts" instead of "agentConfig" ([1eb6a17](https://github.com/lobehub/lobe-chat/commit/1eb6a17))
+- **ui**: Fixed incorrect text display on connect check, closes [#2994](https://github.com/lobehub/lobe-chat/issues/2994) ([5160f23](https://github.com/lobehub/lobe-chat/commit/5160f23))
+- **misc**: Always show action on mobile, closes [#1863](https://github.com/lobehub/lobe-chat/issues/1863) ([f40292e](https://github.com/lobehub/lobe-chat/commit/f40292e))
-### [Version 0.10.2](https://github.com/lobehub/lobe-chat/compare/v0.10.1...v0.10.2)
+### [Version 1.1.1](https://github.com/lobehub/lobe-chat/compare/v1.1.0...v1.1.1)
-Released on **2023-07-23**
+Released on **2024-06-20**
#### 💄 Styles
-- **misc**: 优化模型在 list 中的展示逻辑.
+- **misc**: Fixed System Agent missing in mobile layout.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### Styles
-- **misc**: 优化模型在 list 中的展示逻辑 ([4bdf3c5](https://github.com/lobehub/lobe-chat/commit/4bdf3c5))
+- **misc**: Fixed System Agent missing in mobile layout, closes [#2954](https://github.com/lobehub/lobe-chat/issues/2954) ([596b9c8](https://github.com/lobehub/lobe-chat/commit/596b9c8))
-### [Version 0.8.2](https://github.com/lobehub/lobe-chat/compare/v0.8.1...v0.8.2)
+### [Version 1.0.12](https://github.com/lobehub/lobe-chat/compare/v1.0.11...v1.0.12)
-Released on **2023-07-22**
+Released on **2024-06-19**
#### 🐛 Bug Fixes
-- **misc**: Fix miss manifest.json link, 优化 model tag 展示逻辑.
+- **misc**: Fix auto avatar.
-
+
- Improvements and Fixes
+Improvements and Fixes
#### What's fixed
-- **misc**: Fix miss manifest.json link ([ac4b2f3](https://github.com/lobehub/lobe-chat/commit/ac4b2f3))
-- **misc**: 优化 model tag 展示逻辑 ([3463ede](https://github.com/lobehub/lobe-chat/commit/3463ede))
+- **misc**: Fix auto avatar, closes [#2939](https://github.com/lobehub/lobe-chat/issues/2939) ([f40300c](https://github.com/lobehub/lobe-chat/commit/f40300c))
@@ -52,23 +52,26 @@ One-click **FREE** deployment of your private OpenAI ChatGPT/Claude/Gemini/Groq/
- [👋🏻 Getting Started & Join Our Community](#-getting-started--join-our-community)
- [✨ Features](#-features)
- - [`1` File Upload/Knowledge Base](#1-file-uploadknowledge-base)
- - [`2` Multi-Model Service Provider Support](#2-multi-model-service-provider-support)
- - [`3` Local Large Language Model (LLM) Support](#3-local-large-language-model-llm-support)
- - [`4` Model Visual Recognition](#4-model-visual-recognition)
- - [`5` TTS & STT Voice Conversation](#5-tts--stt-voice-conversation)
- - [`6` Text to Image Generation](#6-text-to-image-generation)
- - [`7` Plugin System (Function Calling)](#7-plugin-system-function-calling)
- - [`8` Agent Market (GPTs)](#8-agent-market-gpts)
- - [`9` Support Local / Remote Database](#9-support-local--remote-database)
- - [`10` Support Multi-User Management](#10-support-multi-user-management)
- - [`11` Progressive Web App (PWA)](#11-progressive-web-app-pwa)
- - [`12` Mobile Device Adaptation](#12-mobile-device-adaptation)
- - [`13` Custom Themes](#13-custom-themes)
+ - [`1` Chain of Thought](#1-chain-of-thought)
+ - [`2` Branching Conversations](#2-branching-conversations)
+ - [`3` Artifacts Support](#3-artifacts-support)
+ - [`4` File Upload /Knowledge Base](#4-file-upload-knowledge-base)
+ - [`5` Multi-Model Service Provider Support](#5-multi-model-service-provider-support)
+ - [`6` Local Large Language Model (LLM) Support](#6-local-large-language-model-llm-support)
+ - [`7` Model Visual Recognition](#7-model-visual-recognition)
+ - [`8` TTS & STT Voice Conversation](#8-tts--stt-voice-conversation)
+ - [`9` Text to Image Generation](#9-text-to-image-generation)
+ - [`10` Plugin System (Function Calling)](#10-plugin-system-function-calling)
+ - [`11` Agent Market (GPTs)](#11-agent-market-gpts)
+ - [`12` Support Local / Remote Database](#12-support-local--remote-database)
+ - [`13` Support Multi-User Management](#13-support-multi-user-management)
+ - [`14` Progressive Web App (PWA)](#14-progressive-web-app-pwa)
+ - [`15` Mobile Device Adaptation](#15-mobile-device-adaptation)
+ - [`16` Custom Themes](#16-custom-themes)
- [`*` What's more](#-whats-more)
- [⚡️ Performance](#️-performance)
- [🛳 Self Hosting](#-self-hosting)
- - [`A` Deploying with Vercel, Zeabur or Sealos](#a-deploying-with-vercel-zeabur-or-sealos)
+ - [`A` Deploying with Vercel, Zeabur , Sealos or Alibaba Cloud](#a-deploying-with-vercel-zeabur--sealos-or-alibaba-cloud)
- [`B` Deploying with Docker](#b-deploying-with-docker)
- [Environment Variable](#environment-variable)
- [📦 Ecosystem](#-ecosystem)
@@ -111,9 +114,48 @@ Whether for users or professional developers, LobeHub will be your AI Agent play
## ✨ Features
+[![][image-feat-cot]][docs-feat-cot]
+
+### `1` [Chain of Thought][docs-feat-cot]
+
+Experience AI reasoning like never before. Watch as complex problems unfold step by step through our innovative Chain of Thought (CoT) visualization. This breakthrough feature provides unprecedented transparency into AI's decision-making process, allowing you to observe how conclusions are reached in real-time.
+
+By breaking down complex reasoning into clear, logical steps, you can better understand and validate the AI's problem-solving approach. Whether you're debugging, learning, or simply curious about AI reasoning, CoT visualization transforms abstract thinking into an engaging, interactive experience.
+
+[![][back-to-top]](#readme-top)
+
+[![][image-feat-branch]][docs-feat-branch]
+
+### `2` [Branching Conversations][docs-feat-branch]
+
+Introducing a more natural and flexible way to chat with AI. With Branch Conversations, your discussions can flow in multiple directions, just like human conversations do. Create new conversation branches from any message, giving you the freedom to explore different paths while preserving the original context.
+
+Choose between two powerful modes:
+
+- **Continuation Mode:** Seamlessly extend your current discussion while maintaining valuable context
+- **Standalone Mode:** Start fresh with a new topic based on any previous message
+
+This groundbreaking feature transforms linear conversations into dynamic, tree-like structures, enabling deeper exploration of ideas and more productive interactions.
+
+[![][back-to-top]](#readme-top)
+
+[![][image-feat-artifacts]][docs-feat-artifacts]
+
+### `3` [Artifacts Support][docs-feat-artifacts]
+
+Experience the power of Claude Artifacts, now integrated into LobeChat. This revolutionary feature expands the boundaries of AI-human interaction, enabling real-time creation and visualization of diverse content formats.
+
+Create and visualize with unprecedented flexibility:
+
+- Generate and display dynamic SVG graphics
+- Build and render interactive HTML pages in real-time
+- Produce professional documents in multiple formats
+
+[![][back-to-top]](#readme-top)
+
[![][image-feat-knowledgebase]][docs-feat-knowledgebase]
-### `1` [File Upload/Knowledge Base][docs-feat-knowledgebase]
+### `4` [File Upload /Knowledge Base][docs-feat-knowledgebase]
LobeChat supports file upload and knowledge base functionality. You can upload various types of files including documents, images, audio, and video, as well as create knowledge bases, making it convenient for users to manage and search for files. Additionally, you can utilize files and knowledge base features during conversations, enabling a richer dialogue experience.
@@ -131,7 +173,7 @@ LobeChat supports file upload and knowledge base functionality. You can upload v
[![][image-feat-privoder]][docs-feat-provider]
-### `2` [Multi-Model Service Provider Support][docs-feat-provider]
+### `5` [Multi-Model Service Provider Support][docs-feat-provider]
In the continuous development of LobeChat, we deeply understand the importance of diversity in model service providers for meeting the needs of the community when providing AI conversation services. Therefore, we have expanded our support to multiple model service providers, rather than being limited to a single one, in order to offer users a more diverse and rich selection of conversations.
@@ -141,21 +183,56 @@ In this way, LobeChat can more flexibly adapt to the needs of different users, w
We have implemented support for the following model service providers:
-- **AWS Bedrock**: Integrated with AWS Bedrock service, supporting models such as **Claude / LLama2**, providing powerful natural language processing capabilities. [Learn more](https://aws.amazon.com/cn/bedrock)
-- **Anthropic (Claude)**: Accessed Anthropic's **Claude** series models, including Claude 3 and Claude 2, with breakthroughs in multi-modal capabilities and extended context, setting a new industry benchmark. [Learn more](https://www.anthropic.com/claude)
-- **Google AI (Gemini Pro, Gemini Vision)**: Access to Google's **Gemini** series models, including Gemini and Gemini Pro, to support advanced language understanding and generation. [Learn more](https://deepmind.google/technologies/gemini/)
-- **Groq**: Accessed Groq's AI models, efficiently processing message sequences and generating responses, capable of multi-turn dialogues and single-interaction tasks. [Learn more](https://groq.com/)
-- **OpenRouter**: Supports routing of models including **Claude 3**, **Gemma**, **Mistral**, **Llama2** and **Cohere**, with intelligent routing optimization to improve usage efficiency, open and flexible. [Learn more](https://openrouter.ai/)
-- **01.AI (Yi Model)**: Integrated the 01.AI models, with series of APIs featuring fast inference speed, which not only shortened the processing time, but also maintained excellent model performance. [Learn more](https://01.ai/)
-- **Together.ai**: Over 100 leading open-source Chat, Language, Image, Code, and Embedding models are available through the Together Inference API. For these models you pay just for what you use. [Learn more](https://www.together.ai/)
-- **ChatGLM**: Added the **ChatGLM** series models from Zhipuai (GLM-4/GLM-4-vision/GLM-3-turbo), providing users with another efficient conversation model choice. [Learn more](https://www.zhipuai.cn/)
-- **Moonshot AI (Dark Side of the Moon)**: Integrated with the Moonshot series models, an innovative AI startup from China, aiming to provide deeper conversation understanding. [Learn more](https://www.moonshot.cn/)
-- **Minimax**: Integrated the Minimax models, including the MoE model **abab6**, offers a broader range of choices. [Learn more](https://www.minimaxi.com/)
-- **DeepSeek**: Integrated with the DeepSeek series models, an innovative AI startup from China, The product has been designed to provide a model that balances performance with price. [Learn more](https://www.deepseek.com/)
-- **Qwen**: Integrated the Qwen series models, including the latest **qwen-turbo**, **qwen-plus** and **qwen-max**. [Lean more](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction)
-- **Novita AI**: Access **Llama**, **Mistral**, and other leading open-source models at cheapest prices. Engage in uncensored role-play, spark creative discussions, and foster unrestricted innovation. **Pay For What You Use.** [Learn more](https://novita.ai/llm-api?utm_source=lobechat&utm_medium=ch&utm_campaign=api)
-
-At the same time, we are also planning to support more model service providers, such as Replicate and Perplexity, to further enrich our service provider library. If you would like LobeChat to support your favorite service provider, feel free to join our [community discussion](https://github.com/lobehub/lobe-chat/discussions/1284).
+
+
+- **[OpenAI](https://lobechat.com/discover/provider/openai)**: OpenAI is a global leader in artificial intelligence research, with models like the GPT series pushing the frontiers of natural language processing. OpenAI is committed to transforming multiple industries through innovative and efficient AI solutions. Their products demonstrate significant performance and cost-effectiveness, widely used in research, business, and innovative applications.
+- **[Ollama](https://lobechat.com/discover/provider/ollama)**: Ollama provides models that cover a wide range of fields, including code generation, mathematical operations, multilingual processing, and conversational interaction, catering to diverse enterprise-level and localized deployment needs.
+- **[Anthropic](https://lobechat.com/discover/provider/anthropic)**: Anthropic is a company focused on AI research and development, offering a range of advanced language models such as Claude 3.5 Sonnet, Claude 3 Sonnet, Claude 3 Opus, and Claude 3 Haiku. These models achieve an ideal balance between intelligence, speed, and cost, suitable for various applications from enterprise workloads to rapid-response scenarios. Claude 3.5 Sonnet, as their latest model, has excelled in multiple evaluations while maintaining a high cost-performance ratio.
+- **[Bedrock](https://lobechat.com/discover/provider/bedrock)**: Bedrock is a service provided by Amazon AWS, focusing on delivering advanced AI language and visual models for enterprises. Its model family includes Anthropic's Claude series, Meta's Llama 3.1 series, and more, offering a range of options from lightweight to high-performance, supporting tasks such as text generation, conversation, and image processing for businesses of varying scales and needs.
+- **[Google](https://lobechat.com/discover/provider/google)**: Google's Gemini series represents its most advanced, versatile AI models, developed by Google DeepMind, designed for multimodal capabilities, supporting seamless understanding and processing of text, code, images, audio, and video. Suitable for various environments from data centers to mobile devices, it significantly enhances the efficiency and applicability of AI models.
+- **[DeepSeek](https://lobechat.com/discover/provider/deepseek)**: DeepSeek is a company focused on AI technology research and application, with its latest model DeepSeek-V2.5 integrating general dialogue and code processing capabilities, achieving significant improvements in human preference alignment, writing tasks, and instruction following.
+- **[HuggingFace](https://lobechat.com/discover/provider/huggingface)**: The HuggingFace Inference API provides a fast and free way for you to explore thousands of models for various tasks. Whether you are prototyping for a new application or experimenting with the capabilities of machine learning, this API gives you instant access to high-performance models across multiple domains.
+- **[OpenRouter](https://lobechat.com/discover/provider/openrouter)**: OpenRouter is a service platform providing access to various cutting-edge large model interfaces, supporting OpenAI, Anthropic, LLaMA, and more, suitable for diverse development and application needs. Users can flexibly choose the optimal model and pricing based on their requirements, enhancing the AI experience.
+- **[Cloudflare Workers AI](https://lobechat.com/discover/provider/cloudflare)**: Run serverless GPU-powered machine learning models on Cloudflare's global network.
+- **[GitHub](https://lobechat.com/discover/provider/github)**: With GitHub Models, developers can become AI engineers and leverage the industry's leading AI models.
+
+See more providers (+27)
+
+- **[Novita](https://lobechat.com/discover/provider/novita)**: Novita AI is a platform providing a variety of large language models and AI image generation API services, flexible, reliable, and cost-effective. It supports the latest open-source models like Llama3 and Mistral, offering a comprehensive, user-friendly, and auto-scaling API solution for generative AI application development, suitable for the rapid growth of AI startups.
+- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO supports stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.
+- **[Together AI](https://lobechat.com/discover/provider/togetherai)**: Together AI is dedicated to achieving leading performance through innovative AI models, offering extensive customization capabilities, including rapid scaling support and intuitive deployment processes to meet various enterprise needs.
+- **[Fireworks AI](https://lobechat.com/discover/provider/fireworksai)**: Fireworks AI is a leading provider of advanced language model services, focusing on functional calling and multimodal processing. Its latest model, Firefunction V2, is based on Llama-3, optimized for function calling, conversation, and instruction following. The visual language model FireLLaVA-13B supports mixed input of images and text. Other notable models include the Llama series and Mixtral series, providing efficient multilingual instruction following and generation support.
+- **[Groq](https://lobechat.com/discover/provider/groq)**: Groq's LPU inference engine has excelled in the latest independent large language model (LLM) benchmarks, redefining the standards for AI solutions with its remarkable speed and efficiency. Groq represents instant inference speed, demonstrating strong performance in cloud-based deployments.
+- **[Perplexity](https://lobechat.com/discover/provider/perplexity)**: Perplexity is a leading provider of conversational generation models, offering various advanced Llama 3.1 models that support both online and offline applications, particularly suited for complex natural language processing tasks.
+- **[Mistral](https://lobechat.com/discover/provider/mistral)**: Mistral provides advanced general, specialized, and research models widely used in complex reasoning, multilingual tasks, and code generation. Through functional calling interfaces, users can integrate custom functionalities for specific applications.
+- **[Ai21Labs](https://lobechat.com/discover/provider/ai21)**: AI21 Labs builds foundational models and AI systems for enterprises, accelerating the application of generative AI in production.
+- **[Upstage](https://lobechat.com/discover/provider/upstage)**: Upstage focuses on developing AI models for various business needs, including Solar LLM and document AI, aiming to achieve artificial general intelligence (AGI) for work. It allows for the creation of simple conversational agents through Chat API and supports functional calling, translation, embedding, and domain-specific applications.
+- **[xAI](https://lobechat.com/discover/provider/xai)**: xAI is a company dedicated to building artificial intelligence to accelerate human scientific discovery. Our mission is to advance our collective understanding of the universe.
+- **[Qwen](https://lobechat.com/discover/provider/qwen)**: Tongyi Qianwen is a large-scale language model independently developed by Alibaba Cloud, featuring strong natural language understanding and generation capabilities. It can answer various questions, create written content, express opinions, and write code, playing a role in multiple fields.
+- **[Wenxin](https://lobechat.com/discover/provider/wenxin)**: An enterprise-level one-stop platform for large model and AI-native application development and services, providing the most comprehensive and user-friendly toolchain for the entire process of generative artificial intelligence model development and application development.
+- **[Hunyuan](https://lobechat.com/discover/provider/hunyuan)**: A large language model developed by Tencent, equipped with powerful Chinese creative capabilities, logical reasoning abilities in complex contexts, and reliable task execution skills.
+- **[ZhiPu](https://lobechat.com/discover/provider/zhipu)**: Zhipu AI offers an open platform for multimodal and language models, supporting a wide range of AI application scenarios, including text processing, image understanding, and programming assistance.
+- **[SiliconCloud](https://lobechat.com/discover/provider/siliconcloud)**: SiliconFlow is dedicated to accelerating AGI for the benefit of humanity, enhancing large-scale AI efficiency through an easy-to-use and cost-effective GenAI stack.
+- **[01.AI](https://lobechat.com/discover/provider/zeroone)**: 01.AI focuses on AI 2.0 era technologies, vigorously promoting the innovation and application of 'human + artificial intelligence', using powerful models and advanced AI technologies to enhance human productivity and achieve technological empowerment.
+- **[Spark](https://lobechat.com/discover/provider/spark)**: iFlytek's Spark model provides powerful AI capabilities across multiple domains and languages, utilizing advanced natural language processing technology to build innovative applications suitable for smart hardware, smart healthcare, smart finance, and other vertical scenarios.
+- **[SenseNova](https://lobechat.com/discover/provider/sensenova)**: SenseNova, backed by SenseTime's robust infrastructure, offers efficient and user-friendly full-stack large model services.
+- **[Stepfun](https://lobechat.com/discover/provider/stepfun)**: StepFun's large model possesses industry-leading multimodal and complex reasoning capabilities, supporting ultra-long text understanding and powerful autonomous scheduling search engine functions.
+- **[Moonshot](https://lobechat.com/discover/provider/moonshot)**: Moonshot is an open-source platform launched by Beijing Dark Side Technology Co., Ltd., providing various natural language processing models with a wide range of applications, including but not limited to content creation, academic research, intelligent recommendations, and medical diagnosis, supporting long text processing and complex generation tasks.
+- **[Baichuan](https://lobechat.com/discover/provider/baichuan)**: Baichuan Intelligence is a company focused on the research and development of large AI models, with its models excelling in domestic knowledge encyclopedias, long text processing, and generative creation tasks in Chinese, surpassing mainstream foreign models. Baichuan Intelligence also possesses industry-leading multimodal capabilities, performing excellently in multiple authoritative evaluations. Its models include Baichuan 4, Baichuan 3 Turbo, and Baichuan 3 Turbo 128k, each optimized for different application scenarios, providing cost-effective solutions.
+- **[Minimax](https://lobechat.com/discover/provider/minimax)**: MiniMax is a general artificial intelligence technology company established in 2021, dedicated to co-creating intelligence with users. MiniMax has independently developed general large models of different modalities, including trillion-parameter MoE text models, voice models, and image models, and has launched applications such as Conch AI.
+- **[InternLM](https://lobechat.com/discover/provider/internlm)**: An open-source organization dedicated to the research and development of large model toolchains. It provides an efficient and user-friendly open-source platform for all AI developers, making cutting-edge large models and algorithm technologies easily accessible.
+- **[Higress](https://lobechat.com/discover/provider/higress)**: Higress is a cloud-native API gateway that was developed internally at Alibaba to address the issues of Tengine reload affecting long-lived connections and the insufficient load balancing capabilities for gRPC/Dubbo.
+- **[Gitee AI](https://lobechat.com/discover/provider/giteeai)**: Gitee AI's Serverless API provides AI developers with an out of the box large model inference API service.
+- **[Taichu](https://lobechat.com/discover/provider/taichu)**: The Institute of Automation, Chinese Academy of Sciences, and Wuhan Artificial Intelligence Research Institute have launched a new generation of multimodal large models, supporting comprehensive question-answering tasks such as multi-turn Q\&A, text creation, image generation, 3D understanding, and signal analysis, with stronger cognitive, understanding, and creative abilities, providing a new interactive experience.
+- **[360 AI](https://lobechat.com/discover/provider/ai360)**: 360 AI is an AI model and service platform launched by 360 Company, offering various advanced natural language processing models, including 360GPT2 Pro, 360GPT Pro, 360GPT Turbo, and 360GPT Turbo Responsibility 8K. These models combine large-scale parameters and multimodal capabilities, widely applied in text generation, semantic understanding, dialogue systems, and code generation. With flexible pricing strategies, 360 AI meets diverse user needs, supports developer integration, and promotes the innovation and development of intelligent applications.
+
+
+
+> 📊 Total providers: [**37**](https://lobechat.com/discover/providers)
+
+
+
+At the same time, we are also planning to support more model service providers. If you would like LobeChat to support your favorite service provider, feel free to join our [💬 community discussion](https://github.com/lobehub/lobe-chat/discussions/1284).
@@ -165,7 +242,7 @@ At the same time, we are also planning to support more model service providers,
[![][image-feat-local]][docs-feat-local]
-### `3` [Local Large Language Model (LLM) Support][docs-feat-local]
+### `6` [Local Large Language Model (LLM) Support][docs-feat-local]
To meet the specific needs of users, LobeChat also supports the use of local models based on [Ollama](https://ollama.ai), allowing users to flexibly use their own or third-party models.
@@ -181,7 +258,7 @@ To meet the specific needs of users, LobeChat also supports the use of local mod
[![][image-feat-vision]][docs-feat-vision]
-### `4` [Model Visual Recognition][docs-feat-vision]
+### `7` [Model Visual Recognition][docs-feat-vision]
LobeChat now supports OpenAI's latest [`gpt-4-vision`](https://platform.openai.com/docs/guides/vision) model with visual recognition capabilities,
a multimodal intelligence that can perceive visuals. Users can easily upload or drag and drop images into the dialogue box,
@@ -199,7 +276,7 @@ Whether it's sharing images in daily use or interpreting images within specific
[![][image-feat-tts]][docs-feat-tts]
-### `5` [TTS & STT Voice Conversation][docs-feat-tts]
+### `8` [TTS & STT Voice Conversation][docs-feat-tts]
LobeChat supports Text-to-Speech (TTS) and Speech-to-Text (STT) technologies, enabling our application to convert text messages into clear voice outputs,
allowing users to interact with our conversational agent as if they were talking to a real person. Users can choose from a variety of voices to pair with the agent.
@@ -216,7 +293,7 @@ Users can choose the voice that suits their personal preferences or specific sce
[![][image-feat-t2i]][docs-feat-t2i]
-### `6` [Text to Image Generation][docs-feat-t2i]
+### `9` [Text to Image Generation][docs-feat-t2i]
With support for the latest text-to-image generation technology, LobeChat now allows users to invoke image creation tools directly within conversations with the agent. By leveraging the capabilities of AI tools such as [`DALL-E 3`](https://openai.com/dall-e-3), [`MidJourney`](https://www.midjourney.com/), and [`Pollinations`](https://pollinations.ai/), the agents are now equipped to transform your ideas into images.
@@ -230,7 +307,7 @@ This enables a more private and immersive creative process, allowing for the sea
[![][image-feat-plugin]][docs-feat-plugin]
-### `7` [Plugin System (Function Calling)][docs-feat-plugin]
+### `10` [Plugin System (Function Calling)][docs-feat-plugin]
The plugin ecosystem of LobeChat is an important extension of its core functionality, greatly enhancing the practicality and flexibility of the LobeChat assistant.
@@ -246,14 +323,14 @@ In addition, these plugins are not limited to news aggregation, but can also ext
-| Recent Submits | Description |
-| ---------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
-| [Tongyi wanxiang Image Generator](https://chat-preview.lobehub.com/settings/agent) By **YoungTx** on **2024-08-09** | This plugin uses Alibaba's Tongyi Wanxiang model to generate images based on text prompts. `image` `tongyi` `wanxiang` |
-| [Shopping tools](https://chat-preview.lobehub.com/settings/agent) By **shoppingtools** on **2024-07-19** | Search for products on eBay & AliExpress, find eBay events & coupons. Get prompt examples. `shopping` `e-bay` `ali-express` `coupons` |
-| [Savvy Trader AI](https://chat-preview.lobehub.com/settings/agent) By **savvytrader** on **2024-06-27** | Realtime stock, crypto and other investment data. `stock` `analyze` |
-| [Search1API](https://chat-preview.lobehub.com/settings/agent) By **fatwang2** on **2024-05-06** | Search aggregation service, specifically designed for LLMs `web` `search` |
+| Recent Submits | Description |
+| ---------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
+| [Web](https://lobechat.com/discover/plugin/web) By **Proghit** on **2025-01-24** | Smart web search that reads and analyzes pages to deliver comprehensive answers from Google results. `web` `search` |
+| [MintbaseSearch](https://lobechat.com/discover/plugin/mintbasesearch) By **mintbase** on **2024-12-31** | Find any NFT data on the NEAR Protocol. `crypto` `nft` |
+| [Bing_websearch](https://lobechat.com/discover/plugin/Bingsearch-identifier) By **FineHow** on **2024-12-22** | Search for information from the internet base BingApi `bingsearch` |
+| [PortfolioMeta](https://lobechat.com/discover/plugin/StockData) By **portfoliometa** on **2024-12-22** | Analyze stocks and get comprehensive real-time investment data and analytics. `stock` |
-> 📊 Total plugins: [**50**](https://github.com/lobehub/lobe-chat-plugins)
+> 📊 Total plugins: [**46**](https://lobechat.com/discover/plugins)
@@ -265,7 +342,7 @@ In addition, these plugins are not limited to news aggregation, but can also ext
[![][image-feat-agent]][docs-feat-agent]
-### `8` [Agent Market (GPTs)][docs-feat-agent]
+### `11` [Agent Market (GPTs)][docs-feat-agent]
In LobeChat Agent Marketplace, creators can discover a vibrant and innovative community that brings together a multitude of well-designed agents,
which not only play an important role in work scenarios but also offer great convenience in learning processes.
@@ -285,14 +362,14 @@ Our marketplace is not just a showcase platform but also a collaborative space.
-| Recent Submits | Description |
-| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| [Contract Clause Refiner v1.0](https://chat-preview.lobehub.com/market?agent=business-contract) By **[houhoufm](https://github.com/houhoufm)** on **2024-09-24** | Output: {Optimize contract clauses for professional and concise expression} `contract-optimization` `legal-consultation` `copywriting` `terminology` `project-management` |
-| [Meeting Assistant v1.0](https://chat-preview.lobehub.com/market?agent=meeting) By **[houhoufm](https://github.com/houhoufm)** on **2024-09-24** | Professional meeting report assistant, distilling meeting key points into report sentences `meeting-reports` `writing` `communication` `workflow` `professional-skills` |
-| [Stable Album Cover Prompter](https://chat-preview.lobehub.com/market?agent=title-bpm-stimmung) By **[MellowTrixX](https://github.com/MellowTrixX)** on **2024-09-24** | Professional graphic designer for front cover design specializing in creating visual concepts and designs for melodic techno music albums. `album-cover` `prompt` `stable-diffusion` `cover-design` `cover-prompts` |
-| [Advertising Copywriting Master](https://chat-preview.lobehub.com/market?agent=advertising-copywriting-master) By **[leter](https://github.com/leter)** on **2024-09-23** | Specializing in product function analysis and advertising copywriting that resonates with user values `advertising-copy` `user-values` `marketing-strategy` |
+| Recent Submits | Description |
+| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [审稿回复专家](https://lobechat.com/discover/assistant/academic-paper-overview) By **[arvinxx](https://github.com/arvinxx)** on **2025-03-11** | 擅长高质量文献检索与分析的学术研究助手 `学术研究` `文献检索` `数据分析` `信息提取` `咨询` |
+| [Cron Expression Assistant](https://lobechat.com/discover/assistant/crontab-generate) By **[edgesider](https://github.com/edgesider)** on **2025-02-17** | Crontab Expression Generator `crontab` `time-expression` `trigger-time` `generator` `technical-assistance` |
+| [Xiao Zhi French Translation Assistant](https://lobechat.com/discover/assistant/xiao-zhi-french-translation-asst-v-1) By **[WeR-Best](https://github.com/WeR-Best)** on **2025-02-10** | A friendly, professional, and empathetic AI assistant for French translation `ai-assistant` `french-translation` `cross-cultural-communication` `creativity` |
+| [Investment Assistant](https://lobechat.com/discover/assistant/graham-investmentassi) By **[farsightlin](https://github.com/farsightlin)** on **2025-02-06** | Helps users calculate the data needed for valuation `investment` `valuation` `financial-analysis` `calculator` |
-> 📊 Total agents: [**392** ](https://github.com/lobehub/lobe-chat-agents)
+> 📊 Total agents: [**488** ](https://lobechat.com/discover/assistants)
@@ -304,7 +381,7 @@ Our marketplace is not just a showcase platform but also a collaborative space.
[![][image-feat-database]][docs-feat-database]
-### `9` [Support Local / Remote Database][docs-feat-database]
+### `12` [Support Local / Remote Database][docs-feat-database]
LobeChat supports the use of both server-side and local databases. Depending on your needs, you can choose the appropriate deployment solution:
@@ -321,7 +398,7 @@ Regardless of which database you choose, LobeChat can provide you with an excell
[![][image-feat-auth]][docs-feat-auth]
-### `10` [Support Multi-User Management][docs-feat-auth]
+### `13` [Support Multi-User Management][docs-feat-auth]
LobeChat supports multi-user management and provides two main user authentication and management solutions to meet different needs:
@@ -339,7 +416,7 @@ Regardless of which user management solution you choose, LobeChat can provide yo
[![][image-feat-pwa]][docs-feat-pwa]
-### `11` [Progressive Web App (PWA)][docs-feat-pwa]
+### `14` [Progressive Web App (PWA)][docs-feat-pwa]
We deeply understand the importance of providing a seamless experience for users in today's multi-device environment.
Therefore, we have adopted Progressive Web Application ([PWA](https://support.google.com/chrome/answer/9658361)) technology,
@@ -366,7 +443,7 @@ providing smooth animations, responsive layouts, and adapting to different devic
[![][image-feat-mobile]][docs-feat-mobile]
-### `12` [Mobile Device Adaptation][docs-feat-mobile]
+### `15` [Mobile Device Adaptation][docs-feat-mobile]
We have carried out a series of optimization designs for mobile devices to enhance the user's mobile experience. Currently, we are iterating on the mobile user experience to achieve smoother and more intuitive interactions. If you have any suggestions or ideas, we welcome you to provide feedback through GitHub Issues or Pull Requests.
@@ -378,7 +455,7 @@ We have carried out a series of optimization designs for mobile devices to enhan
[![][image-feat-theme]][docs-feat-theme]
-### `13` [Custom Themes][docs-feat-theme]
+### `16` [Custom Themes][docs-feat-theme]
As a design-engineering-oriented application, LobeChat places great emphasis on users' personalized experiences,
hence introducing flexible and diverse theme modes, including a light mode for daytime and a dark mode for nighttime.
@@ -439,15 +516,15 @@ Beside these features, LobeChat also have much better basic technique undergroun
## 🛳 Self Hosting
-LobeChat provides Self-Hosted Version with Vercel and [Docker Image][docker-release-link]. This allows you to deploy your own chatbot within a few minutes without any prior knowledge.
+LobeChat provides Self-Hosted Version with Vercel, Alibaba Cloud, and [Docker Image][docker-release-link]. This allows you to deploy your own chatbot within a few minutes without any prior knowledge.
> \[!TIP]
>
> Learn more about [📘 Build your own LobeChat][docs-self-hosting] by checking it out.
-### `A` Deploying with Vercel, Zeabur or Sealos
+### `A` Deploying with Vercel, Zeabur , Sealos or Alibaba Cloud
-If you want to deploy this service yourself on either Vercel or Zeabur, you can follow these steps:
+"If you want to deploy this service yourself on Vercel, Zeabur or Alibaba Cloud, you can follow these steps:
- Prepare your [OpenAI API Key](https://platform.openai.com/account/api-keys).
- Click the button below to start deployment: Log in directly with your GitHub account, and remember to fill in the `OPENAI_API_KEY`(required) and `ACCESS_CODE` (recommended) on the environment variable section.
@@ -456,9 +533,9 @@ If you want to deploy this service yourself on either Vercel or Zeabur, you can
-| Deploy with Vercel | Deploy with Zeabur | Deploy with Sealos | Deploy with RepoCloud |
-| :-------------------------------------: | :---------------------------------------------------------: | :---------------------------------------------------------: | :---------------------------------------------------------------: |
-| [![][deploy-button-image]][deploy-link] | [![][deploy-on-zeabur-button-image]][deploy-on-zeabur-link] | [![][deploy-on-sealos-button-image]][deploy-on-sealos-link] | [![][deploy-on-repocloud-button-image]][deploy-on-repocloud-link] |
+| Deploy with Vercel | Deploy with Zeabur | Deploy with Sealos | Deploy with RepoCloud | Deploy with Alibaba Cloud |
+| :-------------------------------------: | :---------------------------------------------------------: | :---------------------------------------------------------: | :---------------------------------------------------------------: | :-----------------------------------------------------------------------: |
+| [![][deploy-button-image]][deploy-link] | [![][deploy-on-zeabur-button-image]][deploy-on-zeabur-link] | [![][deploy-on-sealos-button-image]][deploy-on-sealos-link] | [![][deploy-on-repocloud-button-image]][deploy-on-repocloud-link] | [![][deploy-on-alibaba-cloud-button-image]][deploy-on-alibaba-cloud-link] |
@@ -484,25 +561,22 @@ If you have deployed your own project following the one-click deployment steps i
We provide a Docker image for deploying the LobeChat service on your own private device. Use the following command to start the LobeChat service:
+1. create a folder to for storage files
+
```fish
-$ docker run -d -p 3210:3210 \
- -e OPENAI_API_KEY=sk-xxxx \
- -e ACCESS_CODE=lobe66 \
- --name lobe-chat \
- lobehub/lobe-chat
+$ mkdir lobe-chat-db && cd lobe-chat-db
```
-> \[!TIP]
->
-> If you need to use the OpenAI service through a proxy, you can configure the proxy address using the `OPENAI_PROXY_URL` environment variable:
+2. init the LobeChat infrastructure
+
+```fish
+bash <(curl -fsSL https://lobe.li/setup.sh)
+```
+
+3. Start the LobeChat service
```fish
-$ docker run -d -p 3210:3210 \
- -e OPENAI_API_KEY=sk-xxxx \
- -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
- -e ACCESS_CODE=lobe66 \
- --name lobe-chat \
- lobehub/lobe-chat
+docker compose up -d
```
> \[!NOTE]
@@ -595,7 +669,7 @@ If you would like to learn more details, please feel free to look at our [📘 D
## 🤝 Contributing
-Contributions of all types are more than welcome; if you are interested in contributing code, feel free to check out our GitHub [Issues][github-issues-link] and [Projects][github-project-link] to get stuck in to show us what you’re made of.
+Contributions of all types are more than welcome; if you are interested in contributing code, feel free to check out our GitHub [Issues][github-issues-link] and [Projects][github-project-link] to get stuck in to show us what you're made of.
> \[!TIP]
>
@@ -692,6 +766,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
[back-to-top]: https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square
[blog]: https://lobehub.com/blog
+[changelog]: https://lobehub.com/changelog
[chat-desktop]: https://raw.githubusercontent.com/lobehub/lobe-chat/lighthouse/lighthouse/chat/desktop/pagespeed.svg
[chat-desktop-report]: https://lobehub.github.io/lobe-chat/lighthouse/chat/desktop/chat_preview_lobehub_com_chat.html
[chat-mobile]: https://raw.githubusercontent.com/lobehub/lobe-chat/lighthouse/lighthouse/chat/mobile/pagespeed.svg
@@ -705,27 +780,32 @@ This project is [Apache 2.0](./LICENSE) licensed.
[codespaces-shield]: https://github.com/codespaces/badge.svg
[deploy-button-image]: https://vercel.com/button
[deploy-link]: https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flobehub%2Flobe-chat&env=OPENAI_API_KEY,ACCESS_CODE&envDescription=Find%20your%20OpenAI%20API%20Key%20by%20click%20the%20right%20Learn%20More%20button.%20%7C%20Access%20Code%20can%20protect%20your%20website&envLink=https%3A%2F%2Fplatform.openai.com%2Faccount%2Fapi-keys&project-name=lobe-chat&repository-name=lobe-chat
+[deploy-on-alibaba-cloud-button-image]: https://service-info-public.oss-cn-hangzhou.aliyuncs.com/computenest-en.svg
+[deploy-on-alibaba-cloud-link]: https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=LobeChat%E7%A4%BE%E5%8C%BA%E7%89%88
[deploy-on-repocloud-button-image]: https://d16t0pc4846x52.cloudfront.net/deploylobe.svg
[deploy-on-repocloud-link]: https://repocloud.io/details/?app_id=248
[deploy-on-sealos-button-image]: https://raw.githubusercontent.com/labring-actions/templates/main/Deploy-on-Sealos.svg
-[deploy-on-sealos-link]: https://cloud.sealos.io/?openapp=system-template%3FtemplateName%3Dlobe-chat
+[deploy-on-sealos-link]: https://template.usw.sealos.io/deploy?templateName=lobe-chat-db
[deploy-on-zeabur-button-image]: https://zeabur.com/button.svg
[deploy-on-zeabur-link]: https://zeabur.com/templates/VZGGTI
[discord-link]: https://discord.gg/AYFPHvv2jT
[discord-shield]: https://img.shields.io/discord/1127171173982154893?color=5865F2&label=discord&labelColor=black&logo=discord&logoColor=white&style=flat-square
[discord-shield-badge]: https://img.shields.io/discord/1127171173982154893?color=5865F2&label=discord&labelColor=black&logo=discord&logoColor=white&style=for-the-badge
-[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
-[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
-[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square
+[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
+[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square&sort=semver
+[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat-database?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square&sort=semver
+[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square&sort=semver
[docs]: https://lobehub.com/docs/usage/start
[docs-dev-guide]: https://github.com/lobehub/lobe-chat/wiki/index
-[docs-docker]: https://lobehub.com/docs/self-hosting/platform/docker
+[docs-docker]: https://lobehub.com/docs/self-hosting/server-database/docker-compose
[docs-env-var]: https://lobehub.com/docs/self-hosting/environment-variables
[docs-feat-agent]: https://lobehub.com/docs/usage/features/agent-market
+[docs-feat-artifacts]: https://lobehub.com/docs/usage/features/artifacts
[docs-feat-auth]: https://lobehub.com/docs/usage/features/auth
+[docs-feat-branch]: https://lobehub.com/docs/usage/features/branching-conversations
+[docs-feat-cot]: https://lobehub.com/docs/usage/features/cot
[docs-feat-database]: https://lobehub.com/docs/usage/features/database
[docs-feat-knowledgebase]: https://lobehub.com/blog/knowledge-base
[docs-feat-local]: https://lobehub.com/docs/usage/features/local-llm
@@ -767,22 +847,25 @@ This project is [Apache 2.0](./LICENSE) licensed.
[github-stars-shield]: https://img.shields.io/github/stars/lobehub/lobe-chat?color=ffcb47&labelColor=black&style=flat-square
[github-trending-shield]: https://trendshift.io/api/badge/repositories/2256
[github-trending-url]: https://trendshift.io/repositories/2256
-[image-banner]: https://github.com/lobehub/lobe-chat/assets/28616219/9f155dff-4737-429f-9cad-a70a1a860c5f
-[image-feat-agent]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png
-[image-feat-auth]: https://github.com/lobehub/lobe-chat/assets/17870709/8ce70e15-40df-451e-b700-66090fe5b8c2
-[image-feat-database]: https://github.com/lobehub/lobe-chat/assets/17870709/c27a0234-a4e9-40e5-8bcb-42d5ce7e40f9
-[image-feat-knowledgebase]: https://github.com/user-attachments/assets/77e58e1c-c82f-4341-b159-f4eeede9967f
-[image-feat-local]: https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c
-[image-feat-mobile]: https://gw.alipayobjects.com/zos/kitchen/R441AuFS4W/mobile.webp
-[image-feat-plugin]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670883-33c43a5c-a512-467e-855c-fa299548cce5.png
-[image-feat-privoder]: https://github.com/lobehub/lobe-chat/assets/28616219/b164bc54-8ba2-4c1e-b2f2-f4d7f7e7a551
-[image-feat-pwa]: https://gw.alipayobjects.com/zos/kitchen/69x6bllkX3/pwa.webp
-[image-feat-t2i]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/297746445-0ff762b9-aa08-4337-afb7-12f932b6efbb.png
-[image-feat-theme]: https://gw.alipayobjects.com/zos/kitchen/pvus1lo%26Z7/darkmode.webp
-[image-feat-tts]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/284072124-c9853d8d-f1b5-44a8-a305-45ebc0f6d19a.png
-[image-feat-vision]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/284072129-382bdf30-e3d6-4411-b5a0-249710b8ba08.png
-[image-overview]: https://github.com/lobehub/lobe-chat/assets/17870709/56b95d48-f573-41cd-8b38-387bf88bc4bf
-[image-star]: https://github.com/lobehub/lobe-chat/assets/17870709/cb06b748-513f-47c2-8740-d876858d7855
+[image-banner]: https://github.com/user-attachments/assets/6f293c7f-47b4-47eb-9202-fe68a942d35b
+[image-feat-agent]: https://github.com/user-attachments/assets/b3ab6e35-4fbc-468d-af10-e3e0c687350f
+[image-feat-artifacts]: https://github.com/user-attachments/assets/7f95fad6-b210-4e6e-84a0-7f39e96f3a00
+[image-feat-auth]: https://github.com/user-attachments/assets/80bb232e-19d1-4f97-98d6-e291f3585e6d
+[image-feat-branch]: https://github.com/user-attachments/assets/92f72082-02bd-4835-9c54-b089aad7fd41
+[image-feat-cot]: https://github.com/user-attachments/assets/f74f1139-d115-4e9c-8c43-040a53797a5e
+[image-feat-database]: https://github.com/user-attachments/assets/f1697c8b-d1fb-4dac-ba05-153c6295d91d
+[image-feat-knowledgebase]: https://github.com/user-attachments/assets/7da7a3b2-92fd-4630-9f4e-8560c74955ae
+[image-feat-local]: https://github.com/user-attachments/assets/1239da50-d832-4632-a7ef-bd754c0f3850
+[image-feat-mobile]: https://github.com/user-attachments/assets/32cf43c4-96bd-4a4c-bfb6-59acde6fe380
+[image-feat-plugin]: https://github.com/user-attachments/assets/66a891ac-01b6-4e3f-b978-2eb07b489b1b
+[image-feat-privoder]: https://github.com/user-attachments/assets/e553e407-42de-4919-977d-7dbfcf44a821
+[image-feat-pwa]: https://github.com/user-attachments/assets/9647f70f-b71b-43b6-9564-7cdd12d1c24d
+[image-feat-t2i]: https://github.com/user-attachments/assets/708274a7-2458-494b-a6ec-b73dfa1fa7c2
+[image-feat-theme]: https://github.com/user-attachments/assets/b47c39f1-806f-492b-8fcb-b0fa973937c1
+[image-feat-tts]: https://github.com/user-attachments/assets/50189597-2cc3-4002-b4c8-756a52ad5c0a
+[image-feat-vision]: https://github.com/user-attachments/assets/18574a1f-46c2-4cbc-af2c-35a86e128a07
+[image-overview]: https://github.com/user-attachments/assets/dbfaa84a-2c82-4dd9-815c-5be616f264a4
+[image-star]: https://github.com/user-attachments/assets/c3b482e7-cef5-4e94-bef9-226900ecfaab
[issues-link]: https://img.shields.io/github/issues/lobehub/lobe-chat.svg?style=flat
[lobe-chat-plugins]: https://github.com/lobehub/lobe-chat-plugins
[lobe-commit]: https://github.com/lobehub/lobe-commit/tree/master/packages/lobe-commit
@@ -807,7 +890,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
[profile-link]: https://github.com/lobehub
[share-linkedin-link]: https://linkedin.com/feed
[share-linkedin-shield]: https://img.shields.io/badge/-share%20on%20linkedin-black?labelColor=black&logo=linkedin&logoColor=white&style=flat-square
-[share-mastodon-link]: https://mastodon.social/share?text=Check%20this%20GitHub%20repository%20out%20%F0%9F%A4%AF%20LobeChat%20-%20An%20open-source,%20extensible%20(Function%20Calling),%20high-performance%20chatbot%20framework.%20It%20supports%20one-click%20free%20deployment%20of%20your%20private%20ChatGPT/LLM%20web%20application.%20https://github.com/lobehub/lobe-chat%20#chatbot%20#chatGPT%20#openAI
+[share-mastodon-link]: https://mastodon.social/share?text=Check%20this%20GitHub%20repository%20out%20%F0%9F%A4%AF%20LobeChat%20-%20An%20open-source,%20extensible%20%28Function%20Calling%29,%20high-performance%20chatbot%20framework.%20It%20supports%20one-click%20free%20deployment%20of%20your%20private%20ChatGPT%2FLLM%20web%20application.%20https://github.com/lobehub/lobe-chat%20#chatbot%20#chatGPT%20#openAI
[share-mastodon-shield]: https://img.shields.io/badge/-share%20on%20mastodon-black?labelColor=black&logo=mastodon&logoColor=white&style=flat-square
[share-reddit-link]: https://www.reddit.com/submit?title=Check%20this%20GitHub%20repository%20out%20%F0%9F%A4%AF%20LobeChat%20-%20An%20open-source%2C%20extensible%20%28Function%20Calling%29%2C%20high-performance%20chatbot%20framework.%20It%20supports%20one-click%20free%20deployment%20of%20your%20private%20ChatGPT%2FLLM%20web%20application.%20%23chatbot%20%23chatGPT%20%23openAI&url=https%3A%2F%2Fgithub.com%2Flobehub%2Flobe-chat
[share-reddit-shield]: https://img.shields.io/badge/-share%20on%20reddit-black?labelColor=black&logo=reddit&logoColor=white&style=flat-square
diff --git a/DigitalHumanWeb/README.zh-CN.md b/DigitalHumanWeb/README.zh-CN.md
index 95781a2..51698d4 100644
--- a/DigitalHumanWeb/README.zh-CN.md
+++ b/DigitalHumanWeb/README.zh-CN.md
@@ -8,7 +8,7 @@
支持语音合成、多模态、可扩展的([function call][docs-functionc-call])插件系统
一键**免费**拥有你自己的 ChatGPT/Gemini/Claude/Ollama 应用
-[English](./README.md) · **简体中文** · [日本語](./README.ja-JP.md) · [官网][official-site] · [更新日志](./CHANGELOG.md) · [文档][docs] · [博客][blog] · [反馈问题][github-issues-link]
+[English](./README.md) · **简体中文** · [官网][official-site] · [更新日志][changelog] · [文档][docs] · [博客][blog] · [反馈问题][github-issues-link]
@@ -41,7 +41,7 @@
[![][github-trending-shield]][github-trending-url]
[![][github-hello-shield]][github-hello-url]
-[![][image-overview]][vercel-link]
+![][image-overview]
+
+### [Version 0.162.21](https://github.com/lobehub/lobe-chat/compare/v0.162.20...v0.162.21)
+
+Released on **2024-06-09**
+
+#### 💄 Styles
+
+- **misc**: Do not show noDescription in new sesstion.
+
+
+
+
+Improvements and Fixes
+
+#### Styles
+
+- **misc**: Do not show noDescription in new sesstion, closes [#2749](https://github.com/lobehub/lobe-chat/issues/2749) ([30b00aa](https://github.com/lobehub/lobe-chat/commit/30b00aa))
+
+
+
+
+
+### [Version 0.162.6](https://github.com/lobehub/lobe-chat/compare/v0.162.5...v0.162.6)
+
+Released on **2024-05-28**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix the default agent not work correctly on new device.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix the default agent not work correctly on new device, closes [#2699](https://github.com/lobehub/lobe-chat/issues/2699) ([e4c7536](https://github.com/lobehub/lobe-chat/commit/e4c7536))
+
+
+
+
+
+### [Version 0.162.1](https://github.com/lobehub/lobe-chat/compare/v0.162.0...v0.162.1)
+
+Released on **2024-05-27**
+
+#### 💄 Styles
+
+- **misc**: Improve the display effect of plug-in API name and description.
+
+
+
+
+Improvements and Fixes
+
+#### Styles
+
+- **misc**: Improve the display effect of plug-in API name and description, closes [#2678](https://github.com/lobehub/lobe-chat/issues/2678) ([19cd0b9](https://github.com/lobehub/lobe-chat/commit/19cd0b9))
+
+
+
+
+
+### [Version 0.161.24](https://github.com/lobehub/lobe-chat/compare/v0.161.23...v0.161.24)
+
+Released on **2024-05-27**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix the missing user id in chat compeletition and fix remove unstarred topic not working.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix the missing user id in chat compeletition and fix remove unstarred topic not working, closes [#2677](https://github.com/lobehub/lobe-chat/issues/2677) ([c9fb2de](https://github.com/lobehub/lobe-chat/commit/c9fb2de))
+
+
+
+
+
+### [Version 0.161.10](https://github.com/lobehub/lobe-chat/compare/v0.161.9...v0.161.10)
+
+Released on **2024-05-23**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Refactor user store and fix custom model list form.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Refactor user store and fix custom model list form, closes [#2620](https://github.com/lobehub/lobe-chat/issues/2620) ([81ea886](https://github.com/lobehub/lobe-chat/commit/81ea886))
+
+
+
+
+
+## [Version 0.161.0](https://github.com/lobehub/lobe-chat/compare/v0.160.8...v0.161.0)
+
+Released on **2024-05-21**
+
+#### ✨ Features
+
+- **misc**: Add system agent to select another model provider for translation.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add system agent to select another model provider for translation, closes [#1902](https://github.com/lobehub/lobe-chat/issues/1902) ([3945387](https://github.com/lobehub/lobe-chat/commit/3945387))
+
+
+
+
+
+## [Version 0.159.0](https://github.com/lobehub/lobe-chat/compare/v0.158.2...v0.159.0)
+
+Released on **2024-05-14**
+
+#### ✨ Features
+
+- **misc**: Support DeepSeek as new model provider.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support DeepSeek as new model provider, closes [#2446](https://github.com/lobehub/lobe-chat/issues/2446) ([18028f3](https://github.com/lobehub/lobe-chat/commit/18028f3))
+
+
+
+
+
+## [Version 0.151.0](https://github.com/lobehub/lobe-chat/compare/v0.150.10...v0.151.0)
+
+Released on **2024-04-29**
+
+#### ✨ Features
+
+- **misc**: Support minimax as a new provider.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support minimax as a new provider, closes [#2087](https://github.com/lobehub/lobe-chat/issues/2087) ([00abd82](https://github.com/lobehub/lobe-chat/commit/00abd82))
+
+
+
+
+
+### [Version 0.150.4](https://github.com/lobehub/lobe-chat/compare/v0.150.3...v0.150.4)
+
+Released on **2024-04-27**
+
+#### 💄 Styles
+
+- **misc**: Hide default model tag and show ollama provider by default.
+
+
+
+
+Improvements and Fixes
+
+#### Styles
+
+- **misc**: Hide default model tag and show ollama provider by default, closes [#2238](https://github.com/lobehub/lobe-chat/issues/2238) ([baa4780](https://github.com/lobehub/lobe-chat/commit/baa4780))
+
+
+
+
+
+### [Version 0.148.5](https://github.com/lobehub/lobe-chat/compare/v0.148.4...v0.148.5)
+
+Released on **2024-04-22**
+
+#### 💄 Styles
+
+- **misc**: Support together ai to fetch model list.
+
+
+
+
+Improvements and Fixes
+
+#### Styles
+
+- **misc**: Support together ai to fetch model list, closes [#2138](https://github.com/lobehub/lobe-chat/issues/2138) ([e6d3e4a](https://github.com/lobehub/lobe-chat/commit/e6d3e4a))
+
+
+
+
+
+### [Version 0.148.3](https://github.com/lobehub/lobe-chat/compare/v0.148.2...v0.148.3)
+
+Released on **2024-04-21**
+
+#### 💄 Styles
+
+- **ollama**: Show size info while download, support cancel donwload, optimize calculation for speed.
+
+
+
+
+Improvements and Fixes
+
+#### Styles
+
+- **ollama**: Show size info while download, support cancel donwload, optimize calculation for speed, closes [#1664](https://github.com/lobehub/lobe-chat/issues/1664) ([9b18f47](https://github.com/lobehub/lobe-chat/commit/9b18f47))
+
+
+
+
+
+### [Version 0.147.19](https://github.com/lobehub/lobe-chat/compare/v0.147.18...v0.147.19)
+
+Released on **2024-04-18**
+
+#### 💄 Styles
+
+- **misc**: Add M and B support max token in ModelInfoTags.
+
+
+
+
+Improvements and Fixes
+
+#### Styles
+
+- **misc**: Add M and B support max token in ModelInfoTags, closes [#2073](https://github.com/lobehub/lobe-chat/issues/2073) ([a985d8f](https://github.com/lobehub/lobe-chat/commit/a985d8f))
+
+
+
+
+
+### [Version 0.147.11](https://github.com/lobehub/lobe-chat/compare/v0.147.10...v0.147.11)
+
+Released on **2024-04-14**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Support drag or copy to upload file by model ability.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Support drag or copy to upload file by model ability, closes [#2016](https://github.com/lobehub/lobe-chat/issues/2016) ([2abe37e](https://github.com/lobehub/lobe-chat/commit/2abe37e))
+
+
+
+
+
+### [Version 0.147.6](https://github.com/lobehub/lobe-chat/compare/v0.147.5...v0.147.6)
+
+Released on **2024-04-11**
+
+#### 💄 Styles
+
+- **misc**: Add GPT-4-turbo and 2024-04-09 Turbo Vision model and mistral new model name.
+
+
+
+
+Improvements and Fixes
+
+#### Styles
+
+- **misc**: Add GPT-4-turbo and 2024-04-09 Turbo Vision model and mistral new model name, closes [#1984](https://github.com/lobehub/lobe-chat/issues/1984) ([f1795b1](https://github.com/lobehub/lobe-chat/commit/f1795b1))
+
+
+
+
+
+## [Version 0.147.0](https://github.com/lobehub/lobe-chat/compare/v0.146.2...v0.147.0)
+
+Released on **2024-04-10**
+
+#### ♻ Code Refactoring
+
+- **misc**: Add db migration, add migrations from v3 to v4, clean openai azure code, refactor agent runtime with openai compatible factory, refactor api key form locale, refactor openAI to openai and azure, refactor the hidden to enabled, refactor the key, refactor the model config selector, refactor the route auth as a middleware, refactor the server config to migrate model provider env, refactor the server config to migrate model provider env, rename the key to enabledModels.
+
+#### ✨ Features
+
+- **misc**: Refactor to support azure openai provider, support close openai, support display model list, support model config modal, support model list with model providers, support open router auto model list, support openai model fetcher, support update model config, support user config model.
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix db migration, fix db migration.
+
+#### 💄 Styles
+
+- **misc**: Fix i18n of model list fetcher, improve detail design, improve logo style, update locale.
+
+
+
+
+Improvements and Fixes
+
+#### Code refactoring
+
+- **misc**: Add db migration ([6ceb818](https://github.com/lobehub/lobe-chat/commit/6ceb818))
+- **misc**: Add migrations from v3 to v4 ([199ded2](https://github.com/lobehub/lobe-chat/commit/199ded2))
+- **misc**: Clean openai azure code ([be4bcca](https://github.com/lobehub/lobe-chat/commit/be4bcca))
+- **misc**: Refactor agent runtime with openai compatible factory ([89adf9d](https://github.com/lobehub/lobe-chat/commit/89adf9d))
+- **misc**: Refactor api key form locale ([a069169](https://github.com/lobehub/lobe-chat/commit/a069169))
+- **misc**: Refactor openAI to openai and azure ([2190a95](https://github.com/lobehub/lobe-chat/commit/2190a95))
+- **misc**: Refactor the hidden to enabled ([78a1aac](https://github.com/lobehub/lobe-chat/commit/78a1aac))
+- **misc**: Refactor the key ([d5c82f6](https://github.com/lobehub/lobe-chat/commit/d5c82f6))
+- **misc**: Refactor the model config selector ([d865ca1](https://github.com/lobehub/lobe-chat/commit/d865ca1))
+- **misc**: Refactor the route auth as a middleware ([ef5ee2a](https://github.com/lobehub/lobe-chat/commit/ef5ee2a))
+- **misc**: Refactor the server config to migrate model provider env ([e4f110e](https://github.com/lobehub/lobe-chat/commit/e4f110e))
+- **misc**: Refactor the server config to migrate model provider env ([c398063](https://github.com/lobehub/lobe-chat/commit/c398063))
+- **misc**: Rename the key to enabledModels ([ebfa0aa](https://github.com/lobehub/lobe-chat/commit/ebfa0aa))
+
+#### What's improved
+
+- **misc**: Refactor to support azure openai provider ([d737afe](https://github.com/lobehub/lobe-chat/commit/d737afe))
+- **misc**: Support close openai ([1ff1aef](https://github.com/lobehub/lobe-chat/commit/1ff1aef))
+- **misc**: Support display model list ([e59635f](https://github.com/lobehub/lobe-chat/commit/e59635f))
+- **misc**: Support model config modal ([62d6bb7](https://github.com/lobehub/lobe-chat/commit/62d6bb7))
+- **misc**: Support model list with model providers, closes [#1916](https://github.com/lobehub/lobe-chat/issues/1916) ([0895dd2](https://github.com/lobehub/lobe-chat/commit/0895dd2))
+- **misc**: Support open router auto model list ([1ba90d3](https://github.com/lobehub/lobe-chat/commit/1ba90d3))
+- **misc**: Support openai model fetcher ([56032e6](https://github.com/lobehub/lobe-chat/commit/56032e6))
+- **misc**: Support update model config ([e8ed847](https://github.com/lobehub/lobe-chat/commit/e8ed847))
+- **misc**: Support user config model ([72fd873](https://github.com/lobehub/lobe-chat/commit/72fd873))
+
+#### What's fixed
+
+- **misc**: Fix db migration ([4e75074](https://github.com/lobehub/lobe-chat/commit/4e75074))
+- **misc**: Fix db migration ([571b6dd](https://github.com/lobehub/lobe-chat/commit/571b6dd))
+
+#### Styles
+
+- **misc**: Fix i18n of model list fetcher ([67ed8c2](https://github.com/lobehub/lobe-chat/commit/67ed8c2))
+- **misc**: Improve detail design ([adcce07](https://github.com/lobehub/lobe-chat/commit/adcce07))
+- **misc**: Improve logo style ([c5826ce](https://github.com/lobehub/lobe-chat/commit/c5826ce))
+- **misc**: Update locale ([021bf91](https://github.com/lobehub/lobe-chat/commit/021bf91))
+
+
+
+
+
+### [Version 0.145.7](https://github.com/lobehub/lobe-chat/compare/v0.145.6...v0.145.7)
+
+Released on **2024-04-02**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix DraggablePanel bar interfere with the operation of the scrollbar.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix DraggablePanel bar interfere with the operation of the scrollbar, closes [#1775](https://github.com/lobehub/lobe-chat/issues/1775) ([4b7b243](https://github.com/lobehub/lobe-chat/commit/4b7b243))
+
+
+
+
+
+### [Version 0.145.1](https://github.com/lobehub/lobe-chat/compare/v0.145.0...v0.145.1)
+
+Released on **2024-03-29**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix Google Gemini pro 1.5 and system role not take effect.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix Google Gemini pro 1.5 and system role not take effect, closes [#1801](https://github.com/lobehub/lobe-chat/issues/1801) ([0a3e3f7](https://github.com/lobehub/lobe-chat/commit/0a3e3f7))
+
+
+
+
+
+## [Version 0.145.0](https://github.com/lobehub/lobe-chat/compare/v0.144.1...v0.145.0)
+
+Released on **2024-03-29**
+
+#### ✨ Features
+
+- **misc**: Support TogetherAI as new model provider.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support TogetherAI as new model provider, closes [#1709](https://github.com/lobehub/lobe-chat/issues/1709) ([d6921ef](https://github.com/lobehub/lobe-chat/commit/d6921ef))
+
+
+
+
+
+### [Version 0.142.8](https://github.com/lobehub/lobe-chat/compare/v0.142.7...v0.142.8)
+
+Released on **2024-03-28**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix gemini 1.5 pro model id to support gemini new models.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix gemini 1.5 pro model id to support gemini new models, closes [#1776](https://github.com/lobehub/lobe-chat/issues/1776) ([591dcb3](https://github.com/lobehub/lobe-chat/commit/591dcb3))
+
+
+
+
+
+## [Version 0.142.0](https://github.com/lobehub/lobe-chat/compare/v0.141.2...v0.142.0)
+
+Released on **2024-03-25**
+
+#### ✨ Features
+
+- **misc**: Support 01.AI as a new provider.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support 01.AI as a new provider, closes [#1627](https://github.com/lobehub/lobe-chat/issues/1627) ([08342fd](https://github.com/lobehub/lobe-chat/commit/08342fd))
+
+
+
+
+
+## [Version 0.141.0](https://github.com/lobehub/lobe-chat/compare/v0.140.1...v0.141.0)
+
+Released on **2024-03-22**
+
+#### ✨ Features
+
+- **misc**: Using YJS and WebRTC to support sync data between different devices.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Using YJS and WebRTC to support sync data between different devices, closes [#1525](https://github.com/lobehub/lobe-chat/issues/1525) ([60d9186](https://github.com/lobehub/lobe-chat/commit/60d9186))
+
+
+
+
+
+## [Version 0.139.0](https://github.com/lobehub/lobe-chat/compare/v0.138.2...v0.139.0)
+
+Released on **2024-03-16**
+
+#### ✨ Features
+
+- **misc**: Support openrouter as a new model provider.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support openrouter as a new model provider, closes [#1572](https://github.com/lobehub/lobe-chat/issues/1572) ([780b1a2](https://github.com/lobehub/lobe-chat/commit/780b1a2))
+
+
+
+
+
+## [Version 0.138.0](https://github.com/lobehub/lobe-chat/compare/v0.137.0...v0.138.0)
+
+Released on **2024-03-15**
+
+#### ✨ Features
+
+- **misc**: Support groq as a model provider.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support groq as a model provider, closes [#1569](https://github.com/lobehub/lobe-chat/issues/1569) [#1562](https://github.com/lobehub/lobe-chat/issues/1562) [#1570](https://github.com/lobehub/lobe-chat/issues/1570) ([a04c364](https://github.com/lobehub/lobe-chat/commit/a04c364))
+
+
+
+
+
+## [Version 0.137.0](https://github.com/lobehub/lobe-chat/compare/v0.136.0...v0.137.0)
+
+Released on **2024-03-15**
+
+#### ✨ Features
+
+- **ollama**: Improve connection check method and provide selector for user to control model options.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **ollama**: Improve connection check method and provide selector for user to control model options, closes [#1397](https://github.com/lobehub/lobe-chat/issues/1397) ([675902f](https://github.com/lobehub/lobe-chat/commit/675902f))
+
+
+
+
+
+## [Version 0.136.0](https://github.com/lobehub/lobe-chat/compare/v0.135.4...v0.136.0)
+
+Released on **2024-03-15**
+
+#### ✨ Features
+
+- **misc**: Support azure-ad as a new sso provider.
+
+
+
+
+Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support azure-ad as a new sso provider, closes [#1456](https://github.com/lobehub/lobe-chat/issues/1456) ([6649cd1](https://github.com/lobehub/lobe-chat/commit/6649cd1))
+
+
+
+
+
+### [Version 0.133.2](https://github.com/lobehub/lobe-chat/compare/v0.133.1...v0.133.2)
+
+Released on **2024-03-10**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix qwen model id and improve anthropic logo text color.
+
+
+
+
+Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix qwen model id and improve anthropic logo text color, closes [#1524](https://github.com/lobehub/lobe-chat/issues/1524) ([c68f5da](https://github.com/lobehub/lobe-chat/commit/c68f5da))
+
+
+
+
+
+### [Version 0.130.3](https://github.com/lobehub/lobe-chat/compare/v0.130.2...v0.130.3)
+
+Released on **2024-02-29**
+
+#### ♻ Code Refactoring
+
+- **misc**: Refactor the google api route and add more tests for chat route.
+
+
+
+
+ Improvements and Fixes
+
+#### Code refactoring
+
+- **misc**: Refactor the google api route and add more tests for chat route, closes [#1424](https://github.com/lobehub/lobe-chat/issues/1424) ([063a4d5](https://github.com/lobehub/lobe-chat/commit/063a4d5))
+
+
+
+
+
+## [Version 0.127.0](https://github.com/lobehub/lobe-chat/compare/v0.126.5...v0.127.0)
+
+Released on **2024-02-13**
+
+#### ✨ Features
+
+- **llm**: Support Ollama AI Provider for local LLM.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **llm**: Support Ollama AI Provider for local LLM ([3b6f249](https://github.com/lobehub/lobe-chat/commit/3b6f249))
+
+
+
+
+
+## [Version 0.126.0](https://github.com/lobehub/lobe-chat/compare/v0.125.0...v0.126.0)
+
+Released on **2024-02-09**
+
+#### ✨ Features
+
+- **misc**: Support umami analytics.
+
+#### 🐛 Bug Fixes
+
+- **misc**: The back button on the chat setting page can correctly return to the configured Agent chat page.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support umami analytics, closes [#1267](https://github.com/lobehub/lobe-chat/issues/1267) ([da7beba](https://github.com/lobehub/lobe-chat/commit/da7beba))
+
+#### What's fixed
+
+- **misc**: The back button on the chat setting page can correctly return to the configured Agent chat page, closes [#1272](https://github.com/lobehub/lobe-chat/issues/1272) ([4cc1ad5](https://github.com/lobehub/lobe-chat/commit/4cc1ad5))
+
+
+
+
+
+### [Version 0.122.6](https://github.com/lobehub/lobe-chat/compare/v0.122.5...v0.122.6)
+
+Released on **2024-01-31**
+
+#### 🐛 Bug Fixes
+
+- **check**: The state of connectivity can only be singular.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **check**: The state of connectivity can only be singular, closes [#1201](https://github.com/lobehub/lobe-chat/issues/1201) ([c412baf](https://github.com/lobehub/lobe-chat/commit/c412baf))
+
+
+
+
+
+### [Version 0.119.12](https://github.com/lobehub/lobe-chat/compare/v0.119.11...v0.119.12)
+
+Released on **2024-01-09**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix new line after sending messages with enter key.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix new line after sending messages with enter key, closes [#990](https://github.com/lobehub/lobe-chat/issues/990) ([e6ab019](https://github.com/lobehub/lobe-chat/commit/e6ab019))
+
+
+
+
+
+### [Version 0.118.8](https://github.com/lobehub/lobe-chat/compare/v0.118.7...v0.118.8)
+
+Released on **2024-01-03**
+
+#### 💄 Styles
+
+- **misc**: Add Vietnamese files and add the vi-VN option in the General Settings.
+
+
+
+
+ Improvements and Fixes
+
+#### Styles
+
+- **misc**: Add Vietnamese files and add the vi-VN option in the General Settings, closes [#860](https://github.com/lobehub/lobe-chat/issues/860) ([c2e5606](https://github.com/lobehub/lobe-chat/commit/c2e5606))
+
+
+
+
+
+### [Version 0.115.11](https://github.com/lobehub/lobe-chat/compare/v0.115.10...v0.115.11)
+
+Released on **2023-12-25**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix agent system role modal scrolling when content is too long.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix agent system role modal scrolling when content is too long, closes [#801](https://github.com/lobehub/lobe-chat/issues/801) ([f482a80](https://github.com/lobehub/lobe-chat/commit/f482a80))
+
+
+
+
+
+### [Version 0.114.4](https://github.com/lobehub/lobe-chat/compare/v0.114.3...v0.114.4)
+
+Released on **2023-12-19**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix agent system role modal scrolling when content is too long.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix agent system role modal scrolling when content is too long, closes [#716](https://github.com/lobehub/lobe-chat/issues/716) ([c3e36d1](https://github.com/lobehub/lobe-chat/commit/c3e36d1))
+
+
+
+
+
+## [Version 0.108.0](https://github.com/lobehub/lobe-chat/compare/v0.107.16...v0.108.0)
+
+Released on **2023-12-03**
+
+#### ✨ Features
+
+- **misc**: Hide the password form item in the settings when there is no `ACCESS_CODE` env.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Hide the password form item in the settings when there is no `ACCESS_CODE` env, closes [#568](https://github.com/lobehub/lobe-chat/issues/568) ([3b5f8b2](https://github.com/lobehub/lobe-chat/commit/3b5f8b2))
+
+
+
+
+
+## [Version 0.105.0](https://github.com/lobehub/lobe-chat/compare/v0.104.0...v0.105.0)
+
+Released on **2023-11-22**
+
+#### ✨ Features
+
+- **misc**: Standalone pluginn can get more arguments on init.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Standalone pluginn can get more arguments on init, closes [#498](https://github.com/lobehub/lobe-chat/issues/498) ([a7624f5](https://github.com/lobehub/lobe-chat/commit/a7624f5))
+
+
+
+
+
+## [Version 0.104.0](https://github.com/lobehub/lobe-chat/compare/v0.103.1...v0.104.0)
+
+Released on **2023-11-21**
+
+#### ✨ Features
+
+- **misc**: Support using env variable to set regions for OpenAI Edge Functions..
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support using env variable to set regions for OpenAI Edge Functions., closes [#473](https://github.com/lobehub/lobe-chat/issues/473) ([de6b79e](https://github.com/lobehub/lobe-chat/commit/de6b79e))
+
+
+
+
+
+### [Version 0.99.1](https://github.com/lobehub/lobe-chat/compare/v0.99.0...v0.99.1)
+
+Released on **2023-11-08**
+
+#### 💄 Styles
+
+- **misc**: Add max height to model menu in chat input area.
+
+
+
+
+ Improvements and Fixes
+
+#### Styles
+
+- **misc**: Add max height to model menu in chat input area, closes [#430](https://github.com/lobehub/lobe-chat/issues/430) ([c9a86f3](https://github.com/lobehub/lobe-chat/commit/c9a86f3))
+
+
+
+
+
+## [Version 0.99.0](https://github.com/lobehub/lobe-chat/compare/v0.98.3...v0.99.0)
+
+Released on **2023-11-08**
+
+#### ✨ Features
+
+- **misc**: Add Environment Variable for custom model name when deploying.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add Environment Variable for custom model name when deploying, closes [#429](https://github.com/lobehub/lobe-chat/issues/429) ([15f9fa2](https://github.com/lobehub/lobe-chat/commit/15f9fa2))
+
+
+
+
+
+### [Version 0.98.3](https://github.com/lobehub/lobe-chat/compare/v0.98.2...v0.98.3)
+
+Released on **2023-11-07**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix redirect to welcome problem when there are topics in inbox.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix redirect to welcome problem when there are topics in inbox, closes [#422](https://github.com/lobehub/lobe-chat/issues/422) ([3d2588a](https://github.com/lobehub/lobe-chat/commit/3d2588a))
+
+
+
+
+
+## [Version 0.97.0](https://github.com/lobehub/lobe-chat/compare/v0.96.9...v0.97.0)
+
+Released on **2023-11-05**
+
+#### ✨ Features
+
+- **misc**: Add open new topic when open a topic.
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix toggle back to default topic when clearing topic.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add open new topic when open a topic ([4df6384](https://github.com/lobehub/lobe-chat/commit/4df6384))
+
+#### What's fixed
+
+- **misc**: Fix toggle back to default topic when clearing topic ([6fe0a5c](https://github.com/lobehub/lobe-chat/commit/6fe0a5c))
+
+
+
+
+
+### [Version 0.96.7](https://github.com/lobehub/lobe-chat/compare/v0.96.6...v0.96.7)
+
+Released on **2023-10-31**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix a bug when click inbox not switch back to chat page.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fix a bug when click inbox not switch back to chat page ([31f6d29](https://github.com/lobehub/lobe-chat/commit/31f6d29))
+
+
+
+
+
+### [Version 0.96.2](https://github.com/lobehub/lobe-chat/compare/v0.96.1...v0.96.2)
+
+Released on **2023-10-28**
+
+#### 💄 Styles
+
+- **misc**: Fix some styles and make updates to various files.
+
+
+
+
+ Improvements and Fixes
+
+#### Styles
+
+- **misc**: Fix some styles and make updates to various files ([44a5f0a](https://github.com/lobehub/lobe-chat/commit/44a5f0a))
+
+
+
+
+
+### [Version 0.94.5](https://github.com/lobehub/lobe-chat/compare/v0.94.4...v0.94.5)
+
+Released on **2023-10-22**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fallback agent market index to en when not find correct locale.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Fallback agent market index to en when not find correct locale, closes [#355](https://github.com/lobehub/lobe-chat/issues/355) ([7a45ab4](https://github.com/lobehub/lobe-chat/commit/7a45ab4))
+
+
+
+
+
+### [Version 0.85.2](https://github.com/lobehub/lobe-chat/compare/v0.85.1...v0.85.2)
+
+Released on **2023-10-10**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Add apikey form when there is no default api key in env.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Add apikey form when there is no default api key in env, closes [#290](https://github.com/lobehub/lobe-chat/issues/290) ([2c907e9](https://github.com/lobehub/lobe-chat/commit/2c907e9))
+
+
+
+
+
+## [Version 0.84.0](https://github.com/lobehub/lobe-chat/compare/v0.83.10...v0.84.0)
+
+Released on **2023-10-10**
+
+#### ✨ Features
+
+- **misc**: Support detect new version and upgrade action.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Support detect new version and upgrade action, closes [#282](https://github.com/lobehub/lobe-chat/issues/282) ([5da19b2](https://github.com/lobehub/lobe-chat/commit/5da19b2))
+
+
+
+
+
+### [Version 0.72.4](https://github.com/lobehub/lobe-chat/compare/v0.72.3...v0.72.4)
+
+Released on **2023-09-10**
+
+#### 🐛 Bug Fixes
+
+- **misc**: Use en-US when no suit lang with plugin index.
+
+
+
+
+ Improvements and Fixes
+
+#### What's fixed
+
+- **misc**: Use en-US when no suit lang with plugin index ([4e9668d](https://github.com/lobehub/lobe-chat/commit/4e9668d))
+
+
+
+
+
+## [Version 0.56.0](https://github.com/lobehub/lobe-chat/compare/v0.55.1...v0.56.0)
+
+Released on **2023-08-24**
+
+#### ✨ Features
+
+- **misc**: Use new plugin manifest to support plugin’s multi api.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Use new plugin manifest to support plugin’s multi api, closes [#101](https://github.com/lobehub/lobe-chat/issues/101) ([4534598](https://github.com/lobehub/lobe-chat/commit/4534598))
+
+
+
+
+
+## [Version 0.54.0](https://github.com/lobehub/lobe-chat/compare/v0.53.0...v0.54.0)
+
+Released on **2023-08-15**
+
+#### ✨ Features
+
+- **misc**: Add new features and improve user interface and functionality.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add new features and improve user interface and functionality ([1543bd1](https://github.com/lobehub/lobe-chat/commit/1543bd1))
+
+
+
+
+
+## [Version 0.49.0](https://github.com/lobehub/lobe-chat/compare/v0.48.0...v0.49.0)
+
+Released on **2023-08-15**
+
+#### ✨ Features
+
+- **misc**: Add `BackToBottom` to conversation, Update icons and text in various components.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add `BackToBottom` to conversation ([1433aa9](https://github.com/lobehub/lobe-chat/commit/1433aa9))
+- **misc**: Update icons and text in various components ([0e7a683](https://github.com/lobehub/lobe-chat/commit/0e7a683))
+
+
+
+
+
+## [Version 0.35.0](https://github.com/lobehub/lobe-chat/compare/v0.34.0...v0.35.0)
+
+Released on **2023-07-31**
+
+#### ✨ Features
+
+- **misc**: Add agent settings functionality, new components, and features for AgentMeta, Add and modify translations for various keys in JSON code files.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add agent settings functionality, new components, and features for AgentMeta ([b1e5ff9](https://github.com/lobehub/lobe-chat/commit/b1e5ff9))
+- **misc**: Add and modify translations for various keys in JSON code files ([503adb4](https://github.com/lobehub/lobe-chat/commit/503adb4))
+
+
+
+
+
+## [Version 0.34.0](https://github.com/lobehub/lobe-chat/compare/v0.33.0...v0.34.0)
+
+Released on **2023-07-31**
+
+#### ✨ Features
+
+- **misc**: Add agent settings functionality, Add new components and features for AgentMeta, Improve organization and functionality of settings and configuration features.
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add agent settings functionality ([b0aaeed](https://github.com/lobehub/lobe-chat/commit/b0aaeed))
+- **misc**: Add new components and features for AgentMeta ([1232d95](https://github.com/lobehub/lobe-chat/commit/1232d95))
+- **misc**: Improve organization and functionality of settings and configuration features ([badde35](https://github.com/lobehub/lobe-chat/commit/badde35))
+
+
+
+
+
+## [Version 0.15.0](https://github.com/lobehub/lobe-chat/compare/v0.14.0...v0.15.0)
+
+Released on **2023-07-24**
+
+#### ✨ Features
+
+- **misc**: Add new features and improve user experience, Import and use constants from "meta.ts" instead of "agentConfig".
+
+
+
+
+ Improvements and Fixes
+
+#### What's improved
+
+- **misc**: Add new features and improve user experience ([64c8782](https://github.com/lobehub/lobe-chat/commit/64c8782))
+- **misc**: Import and use constants from "meta.ts" instead of "agentConfig" ([1eb6a17](https://github.com/lobehub/lobe-chat/commit/1eb6a17))
+
+
+
+
We provide a [Docker image][docker-release-link] for deploying the LobeChat service on your private device.
+ ### Install Docker Container Environment
-### Install Docker Container Environment
-
-(Skip this step if already installed)
-
-
-
-
-
-```fish
-$ apt install docker.io
-```
-
-
-
-
-
-```fish
-$ yum install docker
-```
-
-
+ (Skip this step if already installed)
-
+
+
+ ```fish
+ $ apt install docker.io
+ ```
+
-### Run Docker Compose Deployment Command
+
+ ```fish
+ $ yum install docker
+ ```
+
+
-When using `docker-compose`, the configuration file is as follows:
+ ### Run Docker Compose Deployment Command
-```yml
-version: '3.8'
+ When using `docker-compose`, the configuration file is as follows:
-services:
- lobe-chat:
- image: lobehub/lobe-chat
- container_name: lobe-chat
- restart: always
- ports:
- - '3210:3210'
- environment:
- OPENAI_API_KEY: sk-xxxx
- OPENAI_PROXY_URL: https://api-proxy.com/v1
- ACCESS_CODE: lobe66
-```
+ ```yml
+ version: '3.8'
-Run the following command to start the Lobe Chat service:
+ services:
+ lobe-chat:
+ image: lobehub/lobe-chat
+ container_name: lobe-chat
+ restart: always
+ ports:
+ - '3210:3210'
+ environment:
+ OPENAI_API_KEY: sk-xxxx
+ OPENAI_PROXY_URL: https://api-proxy.com/v1
+ ACCESS_CODE: lobe66
+ ```
-```bash
-$ docker-compose up -d
-```
+ Run the following command to start the Lobe Chat service:
-### Crontab Automatic Update Script (Optional)
+ ```bash
+ $ docker-compose up -d
+ ```
-Similarly, you can use the following script to automatically update Lobe Chat. When using `Docker Compose`, no additional configuration of environment variables is required.
+ ### Crontab Automatic Update Script (Optional)
-```bash
-#!/bin/bash
-# auto-update-lobe-chat.sh
+ Similarly, you can use the following script to automatically update Lobe Chat. When using `Docker Compose`, no additional configuration of environment variables is required.
-# Set proxy (optional)
-export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
+ ```bash
+ #!/bin/bash
+ # auto-update-lobe-chat.sh
-# Pull the latest image and store the output in a variable
-output=$(docker pull lobehub/lobe-chat:latest 2>&1)
+ # Set proxy (optional)
+ export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
-# Check if the pull command was executed successfully
-if [ $? -ne 0 ]; then
- exit 1
-fi
+ # Pull the latest image and store the output in a variable
+ output=$(docker pull lobehub/lobe-chat:latest 2>&1)
-# Check if the output contains a specific string
-echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
+ # Check if the pull command was executed successfully
+ if [ $? -ne 0 ]; then
+ exit 1
+ fi
-# If the image is already up to date, do nothing
-if [ $? -eq 0 ]; then
- exit 0
-fi
+ # Check if the output contains a specific string
+ echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
-echo "Detected Lobe-Chat update"
+ # If the image is already up to date, do nothing
+ if [ $? -eq 0 ]; then
+ exit 0
+ fi
-# Remove the old container
-echo "Removed: $(docker rm -f Lobe-Chat)"
+ echo "Detected Lobe-Chat update"
-# You may need to navigate to the directory where `docker-compose.yml` is located first
-# cd /path/to/docker-compose-folder
+ # Remove the old container
+ echo "Removed: $(docker rm -f Lobe-Chat)"
-# Run the new container
-echo "Started: $(docker-compose up)"
+ # You may need to navigate to the directory where `docker-compose.yml` is located first
+ # cd /path/to/docker-compose-folder
-# Print the update time and version
-echo "Update time: $(date)"
-echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
+ # Run the new container
+ echo "Started: $(docker-compose up)"
-# Clean up unused images
-docker images | grep 'lobehub/lobe-chat' | grep -v 'lobehub/lobe-chat-database' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
-echo "Removed old images."
-```
+ # Print the update time and version
+ echo "Update time: $(date)"
+ echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
-This script can also be used in Crontab, but ensure that your Crontab can find the correct Docker command. It is recommended to use absolute paths.
+ # Clean up unused images
+ docker images | grep 'lobehub/lobe-chat' | grep -v 'lobehub/lobe-chat-database' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
+ echo "Removed old images."
+ ```
-Configure Crontab to execute the script every 5 minutes:
+ This script can also be used in Crontab, but ensure that your Crontab can find the correct Docker command. It is recommended to use absolute paths.
-```bash
-*/5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
-```
+ Configure Crontab to execute the script every 5 minutes:
+ ```bash
+ */5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
+ ```
[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square&sort=semver
[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square&sort=semver
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/docker-compose.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/docker-compose.zh-CN.mdx
index ac28171..21c7dc5 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/docker-compose.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/docker-compose.zh-CN.mdx
@@ -12,122 +12,121 @@ tags:
# Docker Compose 部署指引
We provide a [Docker image][docker-release-link] for you to deploy the LobeChat service on your private device.
@@ -27,143 +26,139 @@ We provide a [Docker image][docker-release-link] for you to deploy the LobeChat
### Install Docker Container Environment
-(If already installed, skip this step)
+ (If already installed, skip this step)
```fish
$ apt install docker.io
```
-
-
+
```fish
$ yum install docker
```
+
+
-
-
-
-
-### Docker Command Deployment
-
-Use the following command to start the LobeChat service with one click:
+ ### Docker Command Deployment
-```fish
-$ docker run -d -p 3210:3210 \
- -e OPENAI_API_KEY=sk-xxxx \
- -e ACCESS_CODE=lobe66 \
- --name lobe-chat \
- lobehub/lobe-chat
-```
+ Use the following command to start the LobeChat service with one click:
-Command explanation:
+ ```fish
+ $ docker run -d -p 3210:3210 \
+ -e OPENAI_API_KEY=sk-xxxx \
+ -e ACCESS_CODE=lobe66 \
+ --name lobe-chat \
+ lobehub/lobe-chat
+ ```
-- The default port mapping is `3210`, please ensure it is not occupied or manually change the port mapping.
+ Command explanation:
-- Replace `sk-xxxx` in the above command with your OpenAI API Key.
+ - The default port mapping is `3210`, please ensure it is not occupied or manually change the port mapping.
-- For the complete list of environment variables supported by LobeChat, please refer to the [Environment Variables](/docs/self-hosting/environment-variables) section.
+ - Replace `sk-xxxx` in the above command with your OpenAI API Key.
-
- Since the official Docker image build takes about half an hour, if you see the "update available"
- prompt after deployment, you can wait for the image to finish building before deploying again.
-
+ - For the complete list of environment variables supported by LobeChat, please refer to the [Environment Variables](/docs/self-hosting/environment-variables) section.
-
- The official Docker image does not have a password set. It is strongly recommended to add a
- password to enhance security, otherwise you may encounter situations like [My API Key was
- stolen!!!](https://github.com/lobehub/lobe-chat/issues/1123).
-
+
+ Since the official Docker image build takes about half an hour, if you see the "update available"
+ prompt after deployment, you can wait for the image to finish building before deploying again.
+
-
- Note that when the **deployment architecture is inconsistent with the image**, you need to
- cross-compile **Sharp**, see [Sharp
- Cross-Compilation](https://sharp.pixelplumbing.com/install#cross-platform) for details.
-
+
+ The official Docker image does not have a password set. It is strongly recommended to add a
+ password to enhance security, otherwise you may encounter situations like [My API Key was
+ stolen!!!](https://github.com/lobehub/lobe-chat/issues/1123).
+
-#### Using a Proxy Address
+
+ Note that when the **deployment architecture is inconsistent with the image**, you need to
+ cross-compile **Sharp**, see [Sharp
+ Cross-Compilation](https://sharp.pixelplumbing.com/install#cross-platform) for details.
+
-If you need to use the OpenAI service through a proxy, you can configure the proxy address using the `OPENAI_PROXY_URL` environment variable:
+ #### Using a Proxy Address
-```fish
-$ docker run -d -p 3210:3210 \
- -e OPENAI_API_KEY=sk-xxxx \
- -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
- -e ACCESS_CODE=lobe66 \
- --name lobe-chat \
- lobehub/lobe-chat
-```
+ If you need to use the OpenAI service through a proxy, you can configure the proxy address using the `OPENAI_PROXY_URL` environment variable:
-### Crontab Automatic Update Script (Optional)
+ ```fish
+ $ docker run -d -p 3210:3210 \
+ -e OPENAI_API_KEY=sk-xxxx \
+ -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
+ -e ACCESS_CODE=lobe66 \
+ --name lobe-chat \
+ lobehub/lobe-chat
+ ```
-If you want to automatically obtain the latest image, you can follow these steps.
+ ### Crontab Automatic Update Script (Optional)
-First, create a `lobe.env` configuration file with various environment variables, for example:
+ If you want to automatically obtain the latest image, you can follow these steps.
-```env
-OPENAI_API_KEY=sk-xxxx
-OPENAI_PROXY_URL=https://api-proxy.com/v1
-ACCESS_CODE=arthals2333
-OPENAI_MODEL_LIST=-gpt-4,-gpt-4-32k,-gpt-3.5-turbo-16k,gpt-3.5-turbo-1106=gpt-3.5-turbo-16k,gpt-4-0125-preview=gpt-4-turbo,gpt-4-vision-preview=gpt-4-vision
-```
+ First, create a `lobe.env` configuration file with various environment variables, for example:
-Then, you can use the following script to automate the update:
+ ```env
+ OPENAI_API_KEY=sk-xxxx
+ OPENAI_PROXY_URL=https://api-proxy.com/v1
+ ACCESS_CODE=arthals2333
+ OPENAI_MODEL_LIST=-gpt-4,-gpt-4-32k,-gpt-3.5-turbo-16k,gpt-3.5-turbo-1106=gpt-3.5-turbo-16k,gpt-4-0125-preview=gpt-4-turbo,gpt-4-vision-preview=gpt-4-vision
+ ```
-```bash
-#!/bin/bash
-# auto-update-lobe-chat.sh
+ Then, you can use the following script to automate the update:
-# Set up proxy (optional)
-export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
+ ```bash
+ #!/bin/bash
+ # auto-update-lobe-chat.sh
-# Pull the latest image and store the output in a variable
-output=$(docker pull lobehub/lobe-chat:latest 2>&1)
+ # Set up proxy (optional)
+ export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
-# Check if the pull command was executed successfully
-if [ $? -ne 0 ]; then
- exit 1
-fi
+ # Pull the latest image and store the output in a variable
+ output=$(docker pull lobehub/lobe-chat:latest 2>&1)
-# Check if the output contains a specific string
-echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
+ # Check if the pull command was executed successfully
+ if [ $? -ne 0 ]; then
+ exit 1
+ fi
-# If the image is already up to date, do nothing
-if [ $? -eq 0 ]; then
- exit 0
-fi
+ # Check if the output contains a specific string
+ echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
-echo "Detected Lobe-Chat update"
+ # If the image is already up to date, do nothing
+ if [ $? -eq 0 ]; then
+ exit 0
+ fi
-# Remove the old container
-echo "Removed: $(docker rm -f Lobe-Chat)"
+ echo "Detected Lobe-Chat update"
-# Run the new container
-echo "Started: $(docker run -d --network=host --env-file /path/to/lobe.env --name=Lobe-Chat --restart=always lobehub/lobe-chat)"
+ # Remove the old container
+ echo "Removed: $(docker rm -f Lobe-Chat)"
-# Print the update time and version
-echo "Update time: $(date)"
-echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
+ # Run the new container
+ echo "Started: $(docker run -d --network=host --env-file /path/to/lobe.env --name=Lobe-Chat --restart=always lobehub/lobe-chat)"
-# Clean up unused images
-docker images | grep 'lobehub/lobe-chat' | grep -v 'lobehub/lobe-chat-database' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
-echo "Removed old images."
-```
+ # Print the update time and version
+ echo "Update time: $(date)"
+ echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
-This script can be used in Crontab, but please ensure that your Crontab can find the correct Docker command. It is recommended to use absolute paths.
+ # Clean up unused images
+ docker images | grep 'lobehub/lobe-chat' | grep -v 'lobehub/lobe-chat-database' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
+ echo "Removed old images."
+ ```
-Configure Crontab to execute the script every 5 minutes:
+ This script can be used in Crontab, but please ensure that your Crontab can find the correct Docker command. It is recommended to use absolute paths.
-```bash
-*/5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
-```
+ Configure Crontab to execute the script every 5 minutes:
+ ```bash
+ */5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
+ ```
[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square&sort=semver
[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square&sort=semver
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/docker.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/docker.zh-CN.mdx
index 4c6e3f0..c68f414 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/docker.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/docker.zh-CN.mdx
@@ -15,10 +15,9 @@ tags:
我们提供了 [Docker 镜像][docker-release-link],供你在自己的私有设备上部署 LobeChat 服务。
@@ -28,137 +27,134 @@ tags:
### 安装 Docker 容器环境
-(如果已安装,请跳过此步)
+ (如果已安装,请跳过此步)
```fish
$ apt install docker.io
```
-
-
+
```fish
$ yum install docker
```
+
+
-
-
-
+ ### Docker 指令部署
-### Docker 指令部署
+ 使用以下命令即可使用一键启动 LobeChat 服务:
-使用以下命令即可使用一键启动 LobeChat 服务:
+ ```fish
+ $ docker run -d -p 3210:3210 \
+ -e OPENAI_API_KEY=sk-xxxx \
+ -e ACCESS_CODE=lobe66 \
+ --name lobe-chat \
+ lobehub/lobe-chat
+ ```
-```fish
-$ docker run -d -p 3210:3210 \
- -e OPENAI_API_KEY=sk-xxxx \
- -e ACCESS_CODE=lobe66 \
- --name lobe-chat \
- lobehub/lobe-chat
-```
+ 指令说明:
-指令说明:
-
-- 默认映射端口为 `3210`, 请确保未被占用或手动更改端口映射
-- 使用你的 OpenAI API Key 替换上述命令中的 `sk-xxxx` ,获取 API Key 的方式详见最后一节。
-
-
- LobeChat 支持的完整环境变量列表请参考 [📘 环境变量](/zh/docs/self-hosting/environment-variables) 部分
-
+ - 默认映射端口为 `3210`, 请确保未被占用或手动更改端口映射
+ - 使用你的 OpenAI API Key 替换上述命令中的 `sk-xxxx` ,获取 API Key 的方式详见最后一节。
-
- 由于官方的 Docker
- 镜像构建大约需要半小时左右,如果在更新部署后会出现「存在更新」的提示,可以等待镜像构建完成后再次部署。
-
+
+ LobeChat 支持的完整环境变量列表请参考 [📘 环境变量](/zh/docs/self-hosting/environment-variables)
+ 部分
+
-
- 官方 Docker 镜像中未设定密码,强烈建议添加密码以提升安全性,否则你可能会遇到 [My API Key was
- stolen!!!](https://github.com/lobehub/lobe-chat/issues/1123) 这样的情况
-
+
+ 由于官方的 Docker
+ 镜像构建大约需要半小时左右,如果在更新部署后会出现「存在更新」的提示,可以等待镜像构建完成后再次部署。
+
-
- 注意,当**部署架构与镜像的不一致时**,需要对 **Sharp** 进行交叉编译,详见 [Sharp
- 交叉编译](https://sharp.pixelplumbing.com/install#cross-platform)
-
+
+ 官方 Docker 镜像中未设定密码,强烈建议添加密码以提升安全性,否则你可能会遇到 [My API Key was
+ stolen!!!](https://github.com/lobehub/lobe-chat/issues/1123) 这样的情况
+
-#### 使用代理地址
+
+ 注意,当**部署架构与镜像的不一致时**,需要对 **Sharp** 进行交叉编译,详见 [Sharp
+ 交叉编译](https://sharp.pixelplumbing.com/install#cross-platform)
+
-如果你需要通过代理使用 OpenAI 服务,你可以使用 `OPENAI_PROXY_URL` 环境变量来配置代理地址:
+ #### 使用代理地址
-```fish
-$ docker run -d -p 3210:3210 \
- -e OPENAI_API_KEY=sk-xxxx \
- -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
- -e ACCESS_CODE=lobe66 \
- --name lobe-chat \
- lobehub/lobe-chat
-```
+ 如果你需要通过代理使用 OpenAI 服务,你可以使用 `OPENAI_PROXY_URL` 环境变量来配置代理地址:
-### Crontab 自动更新脚本(可选)
+ ```fish
+ $ docker run -d -p 3210:3210 \
+ -e OPENAI_API_KEY=sk-xxxx \
+ -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
+ -e ACCESS_CODE=lobe66 \
+ --name lobe-chat \
+ lobehub/lobe-chat
+ ```
-如果你想自动获得最新的镜像,你可以如下操作。
+ ### Crontab 自动更新脚本(可选)
-首先,新建一个 `lobe.env` 配置文件,内容为各种环境变量,例如:
+ 如果你想自动获得最新的镜像,你可以如下操作。
-```env
-OPENAI_API_KEY=sk-xxxx
-OPENAI_PROXY_URL=https://api-proxy.com/v1
-ACCESS_CODE=arthals2333
-OPENAI_MODEL_LIST=-gpt-4,-gpt-4-32k,-gpt-3.5-turbo-16k,gpt-3.5-turbo-1106=gpt-3.5-turbo-16k,gpt-4-0125-preview=gpt-4-turbo,gpt-4-vision-preview=gpt-4-vision
-```
+ 首先,新建一个 `lobe.env` 配置文件,内容为各种环境变量,例如:
-然后,你可以使用以下脚本来自动更新:
+ ```env
+ OPENAI_API_KEY=sk-xxxx
+ OPENAI_PROXY_URL=https://api-proxy.com/v1
+ ACCESS_CODE=arthals2333
+ OPENAI_MODEL_LIST=-gpt-4,-gpt-4-32k,-gpt-3.5-turbo-16k,gpt-3.5-turbo-1106=gpt-3.5-turbo-16k,gpt-4-0125-preview=gpt-4-turbo,gpt-4-vision-preview=gpt-4-vision
+ ```
-```bash
-#!/bin/bash
-# auto-update-lobe-chat.sh
+ 然后,你可以使用以下脚本来自动更新:
-# 设置代理(可选)
-export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
+ ```bash
+ #!/bin/bash
+ # auto-update-lobe-chat.sh
-# 拉取最新的镜像并将输出存储在变量中
-output=$(docker pull lobehub/lobe-chat:latest 2>&1)
+ # 设置代理(可选)
+ export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
-# 检查拉取命令是否成功执行
-if [ $? -ne 0 ]; then
- exit 1
-fi
+ # 拉取最新的镜像并将输出存储在变量中
+ output=$(docker pull lobehub/lobe-chat:latest 2>&1)
-# 检查输出中是否包含特定的字符串
-echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
+ # 检查拉取命令是否成功执行
+ if [ $? -ne 0 ]; then
+ exit 1
+ fi
-# 如果镜像已经是最新的,则不执行任何操作
-if [ $? -eq 0 ]; then
- exit 0
-fi
+ # 检查输出中是否包含特定的字符串
+ echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
-echo "Detected Lobe-Chat update"
+ # 如果镜像已经是最新的,则不执行任何操作
+ if [ $? -eq 0 ]; then
+ exit 0
+ fi
-# 删除旧的容器
-echo "Removed: $(docker rm -f Lobe-Chat)"
+ echo "Detected Lobe-Chat update"
-# 运行新的容器
-echo "Started: $(docker run -d --network=host --env-file /path/to/lobe.env --name=Lobe-Chat --restart=always lobehub/lobe-chat)"
+ # 删除旧的容器
+ echo "Removed: $(docker rm -f Lobe-Chat)"
-# 打印更新的时间和版本
-echo "Update time: $(date)"
-echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
+ # 运行新的容器
+ echo "Started: $(docker run -d --network=host --env-file /path/to/lobe.env --name=Lobe-Chat --restart=always lobehub/lobe-chat)"
-# 清理不再使用的镜像
-docker images | grep 'lobehub/lobe-chat' | grep -v 'lobehub/lobe-chat-database' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
-echo "Removed old images."
-```
+ # 打印更新的时间和版本
+ echo "Update time: $(date)"
+ echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
-此脚本可以在 Crontab 中使用,但请确认你的 Crontab 可以找到正确的 Docker 命令。建议使用绝对路径。
+ # 清理不再使用的镜像
+ docker images | grep 'lobehub/lobe-chat' | grep -v 'lobehub/lobe-chat-database' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
+ echo "Removed old images."
+ ```
-配置 Crontab,每 5 分钟执行一次脚本:
+ 此脚本可以在 Crontab 中使用,但请确认你的 Crontab 可以找到正确的 Docker 命令。建议使用绝对路径。
-```bash
-*/5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
-```
+ 配置 Crontab,每 5 分钟执行一次脚本:
+ ```bash
+ */5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
+ ```
## 获取 OpenAI API Key
@@ -171,31 +167,17 @@ API Key 是使用 LobeChat 进行大语言模型会话的必要信息,本节
- 注册完毕后,前往 [API Keys](https://platform.openai.com/api-keys) 页面,点击 `Create new secret key` 创建新的 API Key:
+ #### 步骤 1:打开创建窗口
-#### 步骤 1:打开创建窗口
-
-
-
-#### 步骤 2:创建 API Key
+
-
+ #### 步骤 2:创建 API Key
-#### 步骤 3:获取 API Key
+
-
+ #### 步骤 3:获取 API Key
+
将此 API Key 填写到 LobeChat 的 API Key 配置中,即可开始使用。
@@ -210,8 +192,8 @@ API Key 是使用 LobeChat 进行大语言模型会话的必要信息,本节
如果你发现注册 OpenAI 账户或者绑定外币信用卡比较麻烦,可以考虑借助一些知名的 OpenAI 第三方代理商来获取 API Key,这可以有效降低获取 OpenAI API Key 的门槛。但与此同时,一旦使用三方服务,你可能也需要承担潜在的风险,请根据你自己的实际情况自行决策。以下是常见的第三方模型代理商列表,供你参考:
-| Logo | 服务商 | 特性说明 | Proxy 代理地址 | 链接 |
-| --- | --- | --- | --- | --- |
+| Logo | 服务商 | 特性说明 | Proxy 代理地址 | 链接 |
+| ------------------------------------------------------------------------------------------------------------------------------------------------- | ------------ | -------------------------------------------------------- | ------------------------- | ----------------------------- |
| | **AiHubMix** | 使用 OpenAI 企业接口,全站模型价格为官方 **86 折**(含 GPT-4 、Cluade 3.5 等) | `https://aihubmix.com/v1` | [获取](https://lobe.li/CnsM6fH) |
@@ -222,6 +204,6 @@ API Key 是使用 LobeChat 进行大语言模型会话的必要信息,本节
[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square&sort=semver
[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
-[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square&sort=semver
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/netlify.mdx b/DigitalHumanWeb/docs/self-hosting/platform/netlify.mdx
index f20084b..7b86e48 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/netlify.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/netlify.mdx
@@ -22,129 +22,79 @@ If you want to deploy LobeChat on Netlify, you can follow these steps:
### Fork the LobeChat Repository
-Click the Fork button to fork the LobeChat repository to your GitHub account.
+ Click the Fork button to fork the LobeChat repository to your GitHub account.
-### Prepare your OpenAI API Key
+ ### Prepare your OpenAI API Key
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to obtain your OpenAI API Key.
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to obtain your OpenAI API Key.
-### Import to Netlify Workspace
+ ### Import to Netlify Workspace
-
- After testing, it is currently not supported to have a one-click deployment button similar to
- Vercel/Zeabur. The reason is unknown. Therefore, manual import is required.
-
+
+ After testing, it is currently not supported to have a one-click deployment button similar to
+ Vercel/Zeabur. The reason is unknown. Therefore, manual import is required.
+
-Click "Import from git"
+ Click "Import from git"
-
+
-Then click "Deploy with Github" and authorize Netlify to access your GitHub account.
+ Then click "Deploy with Github" and authorize Netlify to access your GitHub account.
-
+
-Next, select the LobeChat project:
+ Next, select the LobeChat project:
-
+
-### Configure Site Name and Environment Variables
+ ### Configure Site Name and Environment Variables
-In this step, you need to configure your site, including the site name, build command, and publish directory. Fill in your site name in the "Site Name" field. If there are no special requirements, you do not need to modify the remaining configurations as we have already set the default configurations.
+ In this step, you need to configure your site, including the site name, build command, and publish directory. Fill in your site name in the "Site Name" field. If there are no special requirements, you do not need to modify the remaining configurations as we have already set the default configurations.
-
+
-Click the "Add environment variables" button to add site environment variables:
+ Click the "Add environment variables" button to add site environment variables:
-
+
-Taking OpenAI as an example, the environment variables you need to add are as follows:
+ Taking OpenAI as an example, the environment variables you need to add are as follows:
-| Environment Variable | Type | Description | Example |
-| --- | --- | --- | --- |
-| `OPENAI_API_KEY` | Required | This is the API key you applied for on the OpenAI account page | `sk-xxxxxx...xxxxxx` |
-| `ACCESS_CODE` | Required | Add a password to access this service. You can set a long password to prevent brute force attacks. When this value is separated by commas, it becomes an array of passwords | `awCT74` or `e3@09!` or `code1,code2,code3` |
-| `OPENAI_PROXY_URL` | Optional | If you manually configure the OpenAI interface proxy, you can use this configuration to override the default OpenAI API request base URL | `https://aihubmix.com/v1`, default value: `https://api.openai.com/v1` |
+ | Environment Variable | Type | Description | Example |
+ | -------------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------- |
+ | `OPENAI_API_KEY` | Required | This is the API key you applied for on the OpenAI account page | `sk-xxxxxx...xxxxxx` |
+ | `ACCESS_CODE` | Required | Add a password to access this service. You can set a long password to prevent brute force attacks. When this value is separated by commas, it becomes an array of passwords | `awCT74` or `e3@09!` or `code1,code2,code3` |
+ | `OPENAI_PROXY_URL` | Optional | If you manually configure the OpenAI interface proxy, you can use this configuration to override the default OpenAI API request base URL | `https://aihubmix.com/v1`, default value: `https://api.openai.com/v1` |
-
- For a complete list of environment variables supported by LobeChat, please refer to the [📘
- Environment Variables](/docs/self-hosting/environment-variables)
-
+
+ For a complete list of environment variables supported by LobeChat, please refer to the [📘
+ Environment Variables](/docs/self-hosting/environment-variables)
+
-Afteradding the variables, finally click "Deploy lobe-chat" to enter the deployment phase
+ Afteradding the variables, finally click "Deploy lobe-chat" to enter the deployment phase
-
+
-### Wait for Deployment to Complete
+ ### Wait for Deployment to Complete
-After clicking deploy, you will enter the site details page, where you can click the "Deploying your site" in blue or the "Building" in yellow to view the deployment progress.
+ After clicking deploy, you will enter the site details page, where you can click the "Deploying your site" in blue or the "Building" in yellow to view the deployment progress.
-
+
-Upon entering the deployment details, you will see the following interface, indicating that your LobeChat is currently being deployed. Simply wait for the deployment to complete.
+ Upon entering the deployment details, you will see the following interface, indicating that your LobeChat is currently being deployed. Simply wait for the deployment to complete.
-
+
-During the deployment and build process:
+ During the deployment and build process:
-
-
-### Deployment Successful, Start Using
+
-If your Deploy Log in the interface looks like the following, it means your LobeChat has been successfully deployed.
-
-
+ ### Deployment Successful, Start Using
-At this point, you can click on "Open production deploy" to access your LobeChat site.
+ If your Deploy Log in the interface looks like the following, it means your LobeChat has been successfully deployed.
+
+
+
+ At this point, you can click on "Open production deploy" to access your LobeChat site.
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/netlify.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/netlify.zh-CN.mdx
index 60db352..0078a80 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/netlify.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/netlify.zh-CN.mdx
@@ -20,125 +20,76 @@ tags:
### Fork LobeChat 仓库
-点击 Fork 按钮,将 LobeChat 仓库 Fork 到你的 GitHub 账号下。
+ 点击 Fork 按钮,将 LobeChat 仓库 Fork 到你的 GitHub 账号下。
-### 准备好你的 OpenAI API Key
+ ### 准备好你的 OpenAI API Key
-前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+ 前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
-### 在 Netlify 工作台导入
+ ### 在 Netlify 工作台导入
-经过测试,暂不支持类似 Vercel/Zeabur 的一键部署按钮,原因未知。因此需要手动导入
+ 经过测试,暂不支持类似 Vercel/Zeabur 的一键部署按钮,原因未知。因此需要手动导入
-点击 「Import from git」
+ 点击 「Import from git」
-
+
-然后点击 「Deploy with Github」,并授权 Netlify 访问你的 GitHub 账号
+ 然后点击 「Deploy with Github」,并授权 Netlify 访问你的 GitHub 账号
-
+
-然后选择 LobeChat 项目:
+ 然后选择 LobeChat 项目:
-
+
-### 配置站点名称与环境变量
+ ### 配置站点名称与环境变量
-在这一步,你需要配置你的站点,包括站点名称、构建命令、发布目录等。在「Site Name」字段填写上你的站点名称。其余配置如果没有特殊要求,无需修改,我们已经设定好了默认配置。
+ 在这一步,你需要配置你的站点,包括站点名称、构建命令、发布目录等。在「Site Name」字段填写上你的站点名称。其余配置如果没有特殊要求,无需修改,我们已经设定好了默认配置。
-
+
-点击 「Add environment variables」按钮,添加站点环境变量:
+ 点击 「Add environment variables」按钮,添加站点环境变量:
-
+
-以配置 OpenAI 为例,你需要添加的环境变量如下:
+ 以配置 OpenAI 为例,你需要添加的环境变量如下:
-| 环境变量 | 类型 | 描述 | 示例 |
-| --- | --- | --- | --- |
-| `OPENAI_API_KEY` | 必选 | 这是你在 OpenAI 账户页面申请的 API 密钥 | `sk-xxxxxx...xxxxxx` |
-| `ACCESS_CODE` | 必选 | 添加访问此服务的密码,你可以设置一个长密码以防被爆破,该值用逗号分隔时为密码数组 | `awCT74` 或 `e3@09!` or `code1,code2,code3` |
-| `OPENAI_PROXY_URL` | 可选 | 如果你手动配置了 OpenAI 接口代理,可以使用此配置项来覆盖默认的 OpenAI API 请求基础 URL | `https://aihubmix.com/v1` ,默认值:`https://api.openai.com/v1` |
+ | 环境变量 | 类型 | 描述 | 示例 |
+ | ------------------ | -- | ------------------------------------------------------- | ---------------------------------------------------------- |
+ | `OPENAI_API_KEY` | 必选 | 这是你在 OpenAI 账户页面申请的 API 密钥 | `sk-xxxxxx...xxxxxx` |
+ | `ACCESS_CODE` | 必选 | 添加访问此服务的密码,你可以设置一个长密码以防被爆破,该值用逗号分隔时为密码数组 | `awCT74` 或 `e3@09!` or `code1,code2,code3` |
+ | `OPENAI_PROXY_URL` | 可选 | 如果你手动配置了 OpenAI 接口代理,可以使用此配置项来覆盖默认的 OpenAI API 请求基础 URL | `https://aihubmix.com/v1` ,默认值:`https://api.openai.com/v1` |
-
- LobeChat 支持的完整环境变量列表请参考 [📘 环境变量](/zh/docs/self-hosting/environment-variables) 部分
-
+
+ LobeChat 支持的完整环境变量列表请参考 [📘 环境变量](/zh/docs/self-hosting/environment-variables)
+ 部分
+
-添加完成后,最后点击「Deploy lobe-chat」 进入部署阶段。
+ 添加完成后,最后点击「Deploy lobe-chat」 进入部署阶段。
-
+
-### 等待部署完成
+ ### 等待部署完成
-点击部署后,会进入站点详情页面,你可以点击青色字样的「Deploying your site」或者 「Building」 黄色标签查看部署进度。
+ 点击部署后,会进入站点详情页面,你可以点击青色字样的「Deploying your site」或者 「Building」 黄色标签查看部署进度。
-
+
-进入部署详情,你会看到下述界面,这意味着你的 LobeChat 正在部署中,只需等待部署完成即可。
+ 进入部署详情,你会看到下述界面,这意味着你的 LobeChat 正在部署中,只需等待部署完成即可。
-
+
-部署构建过程中:
+ 部署构建过程中:
-
+
-### 部署成功,开始使用
+ ### 部署成功,开始使用
-如果你的界面中的 Deploy Log 如下所示,意味着你的 LobeChat 部署成功了。
-
-
+ 如果你的界面中的 Deploy Log 如下所示,意味着你的 LobeChat 部署成功了。
-此时,你可以点击「Open production deploy」,即可访问你的 LobeChat 站点
+
+
+ 此时,你可以点击「Open production deploy」,即可访问你的 LobeChat 站点
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/railway.mdx b/DigitalHumanWeb/docs/self-hosting/platform/railway.mdx
index f312329..3c6d683 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/railway.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/railway.mdx
@@ -20,16 +20,15 @@ If you want to deploy LobeChat on Railway, you can follow the steps below:
### Prepare your OpenAI API Key
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-### Click the button below to deploy
+ ### Click the button below to deploy
-[](https://railway.app/template/FB6HrV?referralCode=9bD9mT)
+ [](https://railway.app/template/FB6HrV?referralCode=9bD9mT)
-### Once deployed, you can start using it
+ ### Once deployed, you can start using it
-### Bind a custom domain (optional)
-
-You can use the subdomain provided by Railway, or choose to bind a custom domain. Currently, the domains provided by Railway have not been contaminated, and most regions can connect directly.
+ ### Bind a custom domain (optional)
+ You can use the subdomain provided by Railway, or choose to bind a custom domain. Currently, the domains provided by Railway have not been contaminated, and most regions can connect directly.
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/railway.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/railway.zh-CN.mdx
index 57fb29a..4f466ed 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/railway.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/railway.zh-CN.mdx
@@ -19,16 +19,15 @@ tags:
### 准备好你的 OpenAI API Key
-前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+ 前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
-### 点击下方按钮进行部署
+ ### 点击下方按钮进行部署
-[](https://railway.app/template/FB6HrV?referralCode=9bD9mT)
+ [](https://railway.app/template/FB6HrV?referralCode=9bD9mT)
-### 部署完毕后,即可开始使用
+ ### 部署完毕后,即可开始使用
-### 绑定自定义域名(可选)
-
-你可以使用 Railway 提供的子域名,也可以选择绑定自定义域名。目前 Railway 提供的域名还未被污染,大多数地区都可以直连。
+ ### 绑定自定义域名(可选)
+ 你可以使用 Railway 提供的子域名,也可以选择绑定自定义域名。目前 Railway 提供的域名还未被污染,大多数地区都可以直连。
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/repocloud.mdx b/DigitalHumanWeb/docs/self-hosting/platform/repocloud.mdx
index 2b07870..a0bf8bc 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/repocloud.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/repocloud.mdx
@@ -20,18 +20,17 @@ If you want to deploy LobeChat on RepoCloud, you can follow the steps below:
### Prepare your OpenAI API Key
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-### One-click to deploy
+ ### One-click to deploy
-[![][deploy-button-image]][deploy-link]
+ [![][deploy-button-image]][deploy-link]
-### Once deployed, you can start using it
+ ### Once deployed, you can start using it
-### Bind a custom domain (optional)
-
-You can use the subdomain provided by RepoCloud, or choose to bind a custom domain. Currently, the domains provided by RepoCloud have not been contaminated, and most regions can connect directly.
+ ### Bind a custom domain (optional)
+ You can use the subdomain provided by RepoCloud, or choose to bind a custom domain. Currently, the domains provided by RepoCloud have not been contaminated, and most regions can connect directly.
[deploy-button-image]: https://d16t0pc4846x52.cloudfront.net/deploy.svg
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/repocloud.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/repocloud.zh-CN.mdx
index 0bdaabc..58d0e80 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/repocloud.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/repocloud.zh-CN.mdx
@@ -18,18 +18,17 @@ tags:
### 准备好你的 OpenAI API Key
-前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+ 前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
-### 点击下方按钮进行部署
+ ### 点击下方按钮进行部署
-[![][deploy-button-image]][deploy-link]
+ [![][deploy-button-image]][deploy-link]
-### 部署完毕后,即可开始使用
+ ### 部署完毕后,即可开始使用
-### 绑定自定义域名(可选)
-
-你可以使用 RepoCloud 提供的子域名,也可以选择绑定自定义域名。目前 RepoCloud 提供的域名还未被污染,大多数地区都可以直连。
+ ### 绑定自定义域名(可选)
+ 你可以使用 RepoCloud 提供的子域名,也可以选择绑定自定义域名。目前 RepoCloud 提供的域名还未被污染,大多数地区都可以直连。
[deploy-button-image]: https://d16t0pc4846x52.cloudfront.net/deploy.svg
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/sealos.mdx b/DigitalHumanWeb/docs/self-hosting/platform/sealos.mdx
index 440510e..74c7cfc 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/sealos.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/sealos.mdx
@@ -1,37 +1,36 @@
---
-title: Deploy LobeChat on SealOS
+title: Deploy LobeChat on Sealos
description: >-
- Learn how to deploy LobeChat on SealOS with ease. Follow the provided steps to
+ Learn how to deploy LobeChat on Sealos with ease. Follow the provided steps to
set up LobeChat and start using it efficiently.
tags:
- Deploy LobeChat
- - SealOS Deployment
+ - Sealos Deployment
- OpenAI API Key
- Custom Domain Binding
---
-# Deploy LobeChat with SealOS
+# Deploy LobeChat with Sealos
-If you want to deploy LobeChat on SealOS, you can follow the steps below:
+If you want to deploy LobeChat on Sealos, you can follow the steps below:
-## SealOS Deployment Process
+## Sealos Deployment Process
### Prepare your OpenAI API Key
-Go to [OpenAI](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+ Go to [OpenAI](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-### Click the button below to deploy
+ ### Click the button below to deploy
-[![][deploy-button-image]][deploy-link]
+ [![][deploy-button-image]][deploy-link]
-### After deployment, you can start using it
+ ### After deployment, you can start using it
-### Bind a custom domain (optional)
-
-You can use the subdomain provided by SealOS, or choose to bind a custom domain. Currently, the domains provided by SealOS have not been contaminated, and can be directly accessed in most regions.
+ ### Bind a custom domain (optional)
+ You can use the subdomain provided by Sealos, or choose to bind a custom domain. Currently, the domains provided by Sealos have not been contaminated, and can be directly accessed in most regions.
[deploy-button-image]: https://raw.githubusercontent.com/labring-actions/templates/main/Deploy-on-Sealos.svg
-[deploy-link]: https://cloud.sealos.io/?openapp=system-template%3FtemplateName%3Dlobe-chat
+[deploy-link]: https://template.usw.sealos.io/deploy?templateName=lobe-chat
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/sealos.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/sealos.zh-CN.mdx
index b0bf457..ee76690 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/sealos.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/sealos.zh-CN.mdx
@@ -1,35 +1,34 @@
---
-title: 在 SealOS 上部署 LobeChat
-description: 学习如何在 SealOS 上部署 LobeChat,包括准备 OpenAI API Key、点击部署按钮、绑定自定义域名等操作。
+title: 在 Sealos 上部署 LobeChat
+description: 学习如何在 Sealos 上部署 LobeChat,包括准备 OpenAI API Key、点击部署按钮、绑定自定义域名等操作。
tags:
- - SealOS
+ - Sealos
- LobeChat
- OpenAI API Key
- 部署流程
- 自定义域名
---
-# 使用 SealOS 部署
+# 使用 Sealos 部署
-如果想在 SealOS 上部署 LobeChat,可以按照以下步骤进行操作:
+如果想在 Sealos 上部署 LobeChat,可以按照以下步骤进行操作:
-## SealOS 部署流程
+## Sealos 部署流程
### 准备好你的 OpenAI API Key
-前往 [OpenAI](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+ 前往 [OpenAI](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
-### 点击下方按钮进行部署
+ ### 点击下方按钮进行部署
-[![][deploy-button-image]][deploy-link]
+ [![][deploy-button-image]][deploy-link]
-### 部署完毕后,即可开始使用
+ ### 部署完毕后,即可开始使用
-### 绑定自定义域名(可选)
-
-你可以使用 SealOS 提供的子域名,也可以选择绑定自定义域名。目前 SealOS 提供的域名还未被污染,大多数地区都可以直连。
+ ### 绑定自定义域名(可选)
+ 你可以使用 Sealos 提供的子域名,也可以选择绑定自定义域名。目前 Sealos 提供的域名还未被污染,大多数地区都可以直连。
[deploy-button-image]: https://raw.githubusercontent.com/labring-actions/templates/main/Deploy-on-Sealos.svg
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/tencentcloud-lighthouse.mdx b/DigitalHumanWeb/docs/self-hosting/platform/tencentcloud-lighthouse.mdx
new file mode 100644
index 0000000..85d8f10
--- /dev/null
+++ b/DigitalHumanWeb/docs/self-hosting/platform/tencentcloud-lighthouse.mdx
@@ -0,0 +1,33 @@
+---
+title: Deploy LobeChat on TencentCloud Lighthouse
+description: >-
+ Learn how to deploy the LobeChat application on TencentCloud Lighthouse,
+ including preparing the large model API Key, clicking the deploy button, and
+ other operations.
+tags:
+ - TencentCloud Lighthouse
+ - TencentCloud
+ - LobeChat
+ - API Key
+---
+
+# Deploy LobeChat with TencentCloud Lighthouse
+
+If you want to deploy LobeChat on TencentCloud Lighthouse, you can follow the steps below:
+
+## Tencent Cloud Deployment Process
+
+
+ ### Prepare your API Key
+
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+
+ ### One-click to deploy
+
+ [![][deploy-button-image]][deploy-link]
+
+ ### Once deployed, you can start using it
+
+
+[deploy-button-image]: https://cloudcache.tencent-cloud.com/qcloud/ui/static/static_source_business/d65fb782-4fb0-4348-ad85-f2943d6bee8f.svg
+[deploy-link]: https://buy.tencentcloud.com/lighthouse?blueprintType=APP_OS&blueprintOfficialId=lhbp-6u0ti132®ionId=9&zone=ap-singapore-3&bundleId=bundle_starter_nmc_lin_med2_01&loginSet=AUTO&rule=true&from=lobechat
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/tencentcloud-lighthouse.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/tencentcloud-lighthouse.zh-CN.mdx
new file mode 100644
index 0000000..395ca10
--- /dev/null
+++ b/DigitalHumanWeb/docs/self-hosting/platform/tencentcloud-lighthouse.zh-CN.mdx
@@ -0,0 +1,31 @@
+---
+title: 在 腾讯轻量云 上部署 LobeChat
+description: 学习如何快速在腾讯轻量云上部署LobeChat应用,包括准备大模型 API Key、点击部署按钮等操作。
+tags:
+ - 腾讯云
+ - 腾讯轻量云
+ - LobeChat
+ - 部署流程
+ - 大模型 API Key
+---
+
+# 使用 腾讯轻量云 部署
+
+如果想在 腾讯云 上部署 LobeChat,可以按照以下步骤进行操作:
+
+## 腾讯轻量云 部署流程
+
+
+ ### 准备好你的 API Key
+
+ 前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+
+ ### 点击下方按钮进行部署
+
+ [![][deploy-button-image]][deploy-link]
+
+ ### 部署完毕后,即可开始使用
+
+
+[deploy-button-image]: https://cloudcache.tencent-cloud.com/qcloud/ui/static/static_source_business/d65fb782-4fb0-4348-ad85-f2943d6bee8f.svg
+[deploy-link]: https://buy.cloud.tencent.com/lighthouse?blueprintType=APP_OS&blueprintOfficialId=lhbp-6u0ti132®ionId=8&zone=ap-beijing-3&bundleId=bundle_starter_mc_med2_01&loginSet=AUTO&rule=true&from=lobechat
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/vercel.mdx b/DigitalHumanWeb/docs/self-hosting/platform/vercel.mdx
index a521cf7..0c9efe2 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/vercel.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/vercel.mdx
@@ -20,20 +20,19 @@ If you want to deploy LobeChat on Vercel, you can follow the steps below:
### Prepare your OpenAI API Key
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-### Click the button below to deploy
+ ### Click the button below to deploy
-[](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flobehub%2Flobe-chat&env=OPENAI_API_KEY,ACCESS_CODE&envDescription=Find%20your%20OpenAI%20API%20Key%20by%20click%20the%20right%20Learn%20More%20button.%20%7C%20Access%20Code%20can%20protect%20your%20website&envLink=https%3A%2F%2Fplatform.openai.com%2Faccount%2Fapi-keys&project-name=lobe-chat&repository-name=lobe-chat)
+ [](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flobehub%2Flobe-chat\&env=OPENAI_API_KEY,ACCESS_CODE\&envDescription=Find%20your%20OpenAI%20API%20Key%20by%20click%20the%20right%20Learn%20More%20button.%20%7C%20Access%20Code%20can%20protect%20your%20website\&envLink=https%3A%2F%2Fplatform.openai.com%2Faccount%2Fapi-keys\&project-name=lobe-chat\&repository-name=lobe-chat)
-Simply log in with your GitHub account, and remember to fill in `OPENAI_API_KEY` (required) and `ACCESS_CODE` (recommended) in the environment variables page.
+ Simply log in with your GitHub account, and remember to fill in `OPENAI_API_KEY` (required) and `ACCESS_CODE` (recommended) in the environment variables page.
-### After deployment, you can start using it
+ ### After deployment, you can start using it
-### Bind a custom domain (optional)
-
-Vercel's assigned domain DNS may be polluted in some regions, so binding a custom domain can establish a direct connection.
+ ### Bind a custom domain (optional)
+ Vercel's assigned domain DNS may be polluted in some regions, so binding a custom domain can establish a direct connection.
## Automatic Synchronization of Updates
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/vercel.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/vercel.zh-CN.mdx
index 60fc6d0..acf6874 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/vercel.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/vercel.zh-CN.mdx
@@ -19,20 +19,19 @@ tags:
### 准备好你的 OpenAI API Key
-前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+ 前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
-### 点击下方按钮进行部署
+ ### 点击下方按钮进行部署
-[![][deploy-button-image]][deploy-link]
+ [![][deploy-button-image]][deploy-link]
-直接使用 GitHub 账号登录即可,记得在环境变量页填入 `OPENAI_API_KEY` (必填) and `ACCESS_CODE`(推荐);
+ 直接使用 GitHub 账号登录即可,记得在环境变量页填入 `OPENAI_API_KEY` (必填) and `ACCESS_CODE`(推荐);
-### 部署完毕后,即可开始使用
+ ### 部署完毕后,即可开始使用
-### 绑定自定义域名(可选)
-
-Vercel 分配的域名 DNS 在某些区域被污染了,绑定自定义域名即可直连。
+ ### 绑定自定义域名(可选)
+ Vercel 分配的域名 DNS 在某些区域被污染了,绑定自定义域名即可直连。
## 自动同步更新
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/zeabur.mdx b/DigitalHumanWeb/docs/self-hosting/platform/zeabur.mdx
index d6a4705..50baf76 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/zeabur.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/zeabur.mdx
@@ -19,23 +19,19 @@ If you want to deploy LobeChat on Zeabur, you can follow the steps below:
### Prepare your OpenAI API Key
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-### Click the button below to deploy
+ ### Click the button below to deploy
-[![][deploy-button-image]][deploy-link]
+ [![][deploy-button-image]][deploy-link]
-### Once deployed, you can start using it
+ ### Once deployed, you can start using it
-### Bind a custom domain (optional)
-
-You can use the subdomain provided by Zeabur, or choose to bind a custom domain. Currently, the domains provided by Zeabur have not been contaminated, and most regions can connect directly.
+ ### Bind a custom domain (optional)
+ You can use the subdomain provided by Zeabur, or choose to bind a custom domain. Currently, the domains provided by Zeabur have not been contaminated, and most regions can connect directly.
-[deploy-button-image]: https://zeabur.com/button.svg
-[deploy-link]: https://zeabur.com/templates/VZGGTI
-
# Deploy LobeChat with Zeabur as serverless function
> Note: There are still issues with [middlewares and rewrites of next.js on Zeabur](https://github.com/lobehub/lobe-chat/pull/2775?notification_referrer_id=NT_kwDOAdi2DrQxMDkyODQ4MDc2NTozMDk3OTU5OA#issuecomment-2146713899), use at your own risk!
@@ -45,40 +41,41 @@ Since Zeabur does NOT officially support FREE users deploy containerized service
## Zeabur Deployment Process
+ ### Fork LobeChat
-### Fork LobeChat
-
-### Add Zeabur pack config file
+ ### Add Zeabur pack config file
-Add a `zbpack.json` configuration file with the following content to the root dir of your fork:
+ Add a `zbpack.json` configuration file with the following content to the root dir of your fork:
-```json
-{
- "ignore_dockerfile": true,
- "serverless": true
-}
-```
+ ```json
+ {
+ "ignore_dockerfile": true,
+ "serverless": true
+ }
+ ```
-### Prepare your OpenAI API Key
-
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+ ### Prepare your OpenAI API Key
-### Login to your [Zeabur dashboard](https://dash.zeabur.com)
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-If you do not already have an account, you will need to register one.
+ ### Login to your [Zeabur dashboard](https://dash.zeabur.com)
-### Create a project and service
+ If you do not already have an account, you will need to register one.
-Create a project, then create a service under this project.
+ ### Create a project and service
-### Link your fork of LobeChat to the just created Zeabur service.
+ Create a project, then create a service under this project.
-When adding service, choose github. This may triger a oAuth depend on varies factors like how you login to Zeabur and if you have already authorized Zeabur to access all your repos
+ ### Link your fork of LobeChat to the just created Zeabur service.
-### Bind a custom domain (optional)
+ When adding service, choose github. This may triger a oAuth depend on varies factors like how you login to Zeabur and if you have already authorized Zeabur to access all your repos
-You can create a subdomain provided by Zeabur, or choose to bind a custom domain. Currently, the domains provided by Zeabur have not been contaminated, and most regions can connect directly.
+ ### Bind a custom domain (optional)
-### Zeabur shall start auto build and you should be able to access it by the domain of your choice after a while.
+ You can create a subdomain provided by Zeabur, or choose to bind a custom domain. Currently, the domains provided by Zeabur have not been contaminated, and most regions can connect directly.
+ ### Zeabur shall start auto build and you should be able to access it by the domain of your choice after a while.
+
+[deploy-button-image]: https://zeabur.com/button.svg
+[deploy-link]: https://zeabur.com/templates/VZGGTI
diff --git a/DigitalHumanWeb/docs/self-hosting/platform/zeabur.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/platform/zeabur.zh-CN.mdx
index 00ee9aa..8b6fc7e 100644
--- a/DigitalHumanWeb/docs/self-hosting/platform/zeabur.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/platform/zeabur.zh-CN.mdx
@@ -18,23 +18,19 @@ tags:
### 准备好你的 OpenAI API Key
-前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+ 前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
-### 点击下方按钮进行部署
+ ### 点击下方按钮进行部署
-[![][deploy-button-image]][deploy-link]
+ [![][deploy-button-image]][deploy-link]
-### 部署完毕后,即可开始使用
+ ### 部署完毕后,即可开始使用
-### 绑定自定义域名(可选)
-
-你可以使用 Zeabur 提供的子域名,也可以选择绑定自定义域名。目前 Zeabur 提供的域名还未被污染,大多数地区都可以直连。
+ ### 绑定自定义域名(可选)
+ 你可以使用 Zeabur 提供的子域名,也可以选择绑定自定义域名。目前 Zeabur 提供的域名还未被污染,大多数地区都可以直连。
-[deploy-button-image]: https://zeabur.com/button.svg
-[deploy-link]: https://zeabur.com/templates/VZGGTI
-
# 使用 Zeabur 将 LobeChat 部署为无服务器函数
> **注意:** 仍然存在关于 [Zeabur 上 next.js 的中间件和重写问题](https://github.com/lobehub/lobe-chat/pull/2775?notification_referrer_id=NT_kwDOAdi2DrQxMDkyODQ4MDc2NTozMDk3OTU5OA#issuecomment-2146713899),请自担风险!
@@ -44,40 +40,41 @@ tags:
## Zeabur 部署流程
+ ### Fork LobeChat
-### Fork LobeChat
-
-### 添加 Zeabur 打包配置文件
+ ### 添加 Zeabur 打包配置文件
-在您的分支的根目录下添加一个 `zbpack.json` 配置文件,内容如下:
+ 在您的分支的根目录下添加一个 `zbpack.json` 配置文件,内容如下:
-```json
-{
- "ignore_dockerfile": true,
- "serverless": true
-}
-```
+ ```json
+ {
+ "ignore_dockerfile": true,
+ "serverless": true
+ }
+ ```
-### 准备您的 OpenAI API 密钥
+ ### 准备您的 OpenAI API 密钥
-前往 [OpenAI API 密钥](https://platform.openai.com/account/api-keys) 获取您的 OpenAI API 密钥。
+ 前往 [OpenAI API 密钥](https://platform.openai.com/account/api-keys) 获取您的 OpenAI API 密钥。
-### 登录到您的 [Zeabur 仪表板](https://dash.zeabur.com)
+ ### 登录到您的 [Zeabur 仪表板](https://dash.zeabur.com)
-如果您尚未拥有一个账号,您需要注册一个。
+ 如果您尚未拥有一个账号,您需要注册一个。
-### 创建项目与服务。
+ ### 创建项目与服务。
-创建一个项目,并再这个项目下新建一个服务。
+ 创建一个项目,并再这个项目下新建一个服务。
-### 将您的 LobeChat 分支链接到刚创建的 Zeabur 服务。
+ ### 将您的 LobeChat 分支链接到刚创建的 Zeabur 服务。
-在添加服务时,选择 github。这可能会触发一个 oAuth,取决于诸如您如何登录到 Zeabur以及您是否已经授权 Zeabur 访问所有您的存储库等各种因素。
+ 在添加服务时,选择 github。这可能会触发一个 oAuth,取决于诸如您如何登录到 Zeabur 以及您是否已经授权 Zeabur 访问所有您的存储库等各种因素。
-### 绑定自定义域名(可选)
+ ### 绑定自定义域名(可选)
-您可以创建 Zeabur 提供的子域名,或选择绑定自定义域名。目前,Zeabur 提供的域名尚未受到污染,大多数地区可以直接连接。
-
-### Zeabur 将开始自动构建,您应该可以在一段时间后通过您选择的域名访问它。
+ 您可以创建 Zeabur 提供的子域名,或选择绑定自定义域名。目前,Zeabur 提供的域名尚未受到污染,大多数地区可以直接连接。
+ ### Zeabur 将开始自动构建,您应该可以在一段时间后通过您选择的域名访问它。
+
+[deploy-button-image]: https://zeabur.com/button.svg
+[deploy-link]: https://zeabur.com/templates/VZGGTI
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database.mdx b/DigitalHumanWeb/docs/self-hosting/server-database.mdx
index 0e7d476..833720b 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database.mdx
@@ -7,12 +7,16 @@ tags:
- Postgres
- Deployment Guide
---
+
# Deploying Server-Side Database
LobeChat defaults to using a client-side database (IndexedDB) but also supports deploying a server-side database. LobeChat uses Postgres as the backend storage database.
- PostgreSQL is a powerful open-source relational database management system with high scalability and standard SQL support. It provides rich data types, concurrency control, data integrity, security, and programmability, making it suitable for complex applications and large-scale data management.
+ PostgreSQL is a powerful open-source relational database management system with high scalability
+ and standard SQL support. It provides rich data types, concurrency control, data integrity,
+ security, and programmability, making it suitable for complex applications and large-scale data
+ management.
This guide will introduce the process and principles of deploying the server-side database version of LobeChat on any platform from a framework perspective, so you can understand both the what and the why, and then deploy according to your specific needs.
@@ -36,57 +40,63 @@ Before deployment, make sure you have a Postgres database instance ready. You ca
- `A.` Use Serverless Postgres instances like Vercel/Neon;
- `B.` Use self-deployed Postgres instances like Docker/Railway/Zeabur, collectively referred to as Node Postgres instances;
-There is a slight difference in the way they are configured in terms of environment variables.
+
+ There is a slight difference in the way they are configured in terms of environment variables.
+
Since we support file-based conversations/knowledge base conversations, we need to install the `pgvector` plugin for Postgres. This plugin provides vector search capabilities and is a key component for LobeChat to implement RAG.
-### `NEXT_PUBLIC_SERVICE_MODE`
+ ### `NEXT_PUBLIC_SERVICE_MODE`
-LobeChat supports both client-side and server-side databases, so we provide an environment variable for switching modes, which is `NEXT_PUBLIC_SERVICE_MODE`, with a default value of `client`.
+ LobeChat supports both client-side and server-side databases, so we provide an environment variable for switching modes, which is `NEXT_PUBLIC_SERVICE_MODE`, with a default value of `client`.
-For server-side database deployment scenarios, you need to set `NEXT_PUBLIC_SERVICE_MODE` to `server`.
+ For server-side database deployment scenarios, you need to set `NEXT_PUBLIC_SERVICE_MODE` to `server`.
-
-In the official `lobe-chat-database` Docker image, this environment variable is already set to `server` by default. Therefore, if you deploy using the Docker image, you do not need to configure this environment variable again.
-
+
+ In the official `lobe-chat-database` Docker image, this environment variable is already set to
+ `server` by default. Therefore, if you deploy using the Docker image, you do not need to configure
+ this environment variable again.
+
-
-Since environment variables starting with `NEXT_PUBLIC` take effect in the front-end code, they cannot be modified through container runtime injection. (Refer to the `next.js` documentation [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables)). This is why we chose to create a separate DB version image.
+
+ Since environment variables starting with `NEXT_PUBLIC` take effect in the front-end code, they cannot be modified through container runtime injection. (Refer to the `next.js` documentation [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables)). This is why we chose to create a separate DB version image.
-If you need to modify variables with the `NEXT_PUBLIC` prefix in a Docker deployment, you must build the image yourself and inject your own `NEXT_PUBLIC` prefixed environment variables during the build.
-
+ If you need to modify variables with the `NEXT_PUBLIC` prefix in a Docker deployment, you must build the image yourself and inject your own `NEXT_PUBLIC` prefixed environment variables during the build.
+
-### `DATABASE_URL`
+ ### `DATABASE_URL`
-The core of configuring the database is to add the `DATABASE_URL` environment variable and fill in the Postgres database connection URL you have prepared. The typical format of the database connection URL is `postgres://username:password@host:port/database`.
+ The core of configuring the database is to add the `DATABASE_URL` environment variable and fill in the Postgres database connection URL you have prepared. The typical format of the database connection URL is `postgres://username:password@host:port/database`.
-
-If you want to enable SSL when connecting to the database, please refer to the [documentation](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode) for setup instructions.
-
-
-### `DATABASE_DRIVER`
+
+ If you want to enable SSL when connecting to the database, please refer to the
+ [documentation](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)
+ for setup instructions.
+
-The `DATABASE_DRIVER` environment variable is used to distinguish between the two types of Postgres database instances, with values of `node` or `neon`.
+ ### `DATABASE_DRIVER`
-To streamline deployment, we have set default values based on the characteristics of different platforms:
+ The `DATABASE_DRIVER` environment variable is used to distinguish between the two types of Postgres database instances, with values of `node` or `neon`.
-- On the Vercel platform, `DATABASE_DRIVER` defaults to `neon`;
-- In our provided Docker image `lobe-chat-database`, `DATABASE_DRIVER` defaults to `node`.
+ To streamline deployment, we have set default values based on the characteristics of different platforms:
-Therefore, if you follow the standard deployment methods below, you do not need to manually configure the `DATABASE_DRIVER` environment variable:
+ - On the Vercel platform, `DATABASE_DRIVER` defaults to `neon`;
+ - In our provided Docker image `lobe-chat-database`, `DATABASE_DRIVER` defaults to `node`.
-- Vercel + Serverless Postgres
-- Docker image + Node Postgres
+ Therefore, if you follow the standard deployment methods below, you do not need to manually configure the `DATABASE_DRIVER` environment variable:
-### `KEY_VAULTS_SECRET`
+ - Vercel + Serverless Postgres
+ - Docker image + Node Postgres
-Considering that users will store sensitive information such as their API Key and baseURL in the database, we need a key to encrypt this information to prevent leakage in case of a database breach. Hence, the `KEY_VAULTS_SECRET` environment variable is used to encrypt sensitive information like user-stored apikeys.
+ ### `KEY_VAULTS_SECRET`
-
-You can generate a random 32-character string as the value of `KEY_VAULTS_SECRET` using `openssl rand -base64 32`.
-
+ Considering that users will store sensitive information such as their API Key and baseURL in the database, we need a key to encrypt this information to prevent leakage in case of a database breach. Hence, the `KEY_VAULTS_SECRET` environment variable is used to encrypt sensitive information like user-stored apikeys.
+
+ You can generate a random 32-character string as the value of `KEY_VAULTS_SECRET` using `openssl
+ rand -base64 32`.
+
## Configuring Authentication Services
@@ -95,12 +105,16 @@ In the server-side database mode, we need an authentication service to distingui
### Clerk
-[Clerk](https://clerk.com?utm_source=lobehub&utm_medium=docs) is an authentication SaaS service that provides out-of-the-box authentication capabilities with high productization, low integration costs, and a great user experience. For those who offer SaaS products, Clerk is a good choice. Our official [LobeChat Cloud](https://lobechat.com) uses Clerk as the authentication service.
+[Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) is an authentication SaaS service that provides out-of-the-box authentication capabilities with high productization, low integration costs, and a great user experience. For those who offer SaaS products, Clerk is a good choice. Our official [LobeChat Cloud](https://lobechat.com) uses Clerk as the authentication service.
+
+The integration of Clerk is relatively simple, requiring only the configuration of these environment variables:
-The integration of Clerk is relatively simple, requiring only the configuration of the `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY`, `CLERK_SECRET_KEY`, and `CLERK_WEBHOOK_SECRET` environment variables, which can be obtained from the Clerk console.
+- `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` and `CLERK_SECRET_KEY`, which can be obtained from the Clerk console
+- `CLERK_WEBHOOK_SECRET`, which is generated by following these instructions: [Configure Clerk Authentication Service](/docs/self-hosting/advanced/auth/clerk#create-and-configure-webhook-in-clerk).
-In Vercel deployment mode, we recommend using Clerk as the authentication service for a better user experience.
+ In Vercel deployment mode, we recommend using Clerk as the authentication service for a better
+ user experience.
However, this type of authentication relies on Clerk's official service, so there may be some limitations in certain scenarios:
@@ -118,7 +132,8 @@ NextAuth is an open-source authentication library that supports multiple identit
For information on configuring NextAuth, you can refer to the [Authentication](/docs/self-hosting/advanced/authentication) documentation.
-In the official Docker image `lobe-chat-database`, we recommend using NextAuth as the authentication service.
+ In the official Docker image `lobe-chat-database`, we recommend using NextAuth as the
+ authentication service.
## Configuring S3 Storage Service
@@ -128,7 +143,9 @@ LobeChat has supported multimodal AI conversations since [a long time ago](https
The best practice in this area is to use a file storage service (S3) to store image files, which is also the storage solution relied upon for subsequent file uploads/knowledge base functions.
-In this documentation, S3 refers to a compatible S3 storage solution, which supports the Amazon S3 API-compatible object storage system. Common examples include Cloudflare R2, Alibaba Cloud OSS, and self-deployable Minio, all of which support the S3-compatible API.
+ In this documentation, S3 refers to a compatible S3 storage solution, which supports the Amazon S3
+ API-compatible object storage system. Common examples include Cloudflare R2, Alibaba Cloud OSS,
+ and self-deployable Minio, all of which support the S3-compatible API.
For detailed configuration guidelines on S3, please refer to [S3 Object Storage](/docs/self-hosting/advanced/s3) for more information.
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database.zh-CN.mdx
index 8f0c966..fc8a0c9 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database.zh-CN.mdx
@@ -15,7 +15,7 @@ tags:
LobeChat 默认使用客户端数据库(IndexedDB),同时也支持使用服务端数据库(下简称 DB 版)。LobeChat 采用了 Postgres 作为后端存储数据库。
- PostgreSQL是一种强大的开源关系型数据库管理系统,具备高度扩展性和标准SQL支持。它提供了丰富的数据类型、并发处理、数据完整性、安全性及可编程性,适用于复杂应用和大规模数据管理。
+ PostgreSQL 是一种强大的开源关系型数据库管理系统,具备高度扩展性和标准 SQL 支持。它提供了丰富的数据类型、并发处理、数据完整性、安全性及可编程性,适用于复杂应用和大规模数据管理。
本文将从框架角度介绍在任何一个平台中部署 DB 版 LobeChat 的流程和原理,让你知其然也知其所以然,最后可以根据自己的实际情况进行部署。
@@ -41,59 +41,56 @@ LobeChat 默认使用客户端数据库(IndexedDB),同时也支持使用
两者的配置方式在环境变量的取值上会略有一点区别,其他方面是一样的。
-同时,由于我们支持了文件对话/知识库对话的能力,因此我们需要为 Postgres 安装 `pgvector` 插件,该插件提供了向量搜索的能力,是 LobeChat 实现 RAG 的重要构件之一。
+同时,由于我们支持了文件对话 / 知识库对话的能力,因此我们需要为 Postgres 安装 `pgvector` 插件,该插件提供了向量搜索的能力,是 LobeChat 实现 RAG 的重要构件之一。
+ ### `NEXT_PUBLIC_SERVICE_MODE`
-### `NEXT_PUBLIC_SERVICE_MODE`
+ LobeChat 同时支持了客户端数据库和服务端数据库,因此我们提供了一个环境变量用于切换模式,这个变量为 `NEXT_PUBLIC_SERVICE_MODE`,该值默认为 `client`。
-LobeChat 同时支持了客户端数据库和服务端数据库,因此我们提供了一个环境变量用于切换模式,这个变量为 `NEXT_PUBLIC_SERVICE_MODE`,该值默认为 `client`。
+ 针对服务端数据库部署场景,你需要将 `NEXT_PUBLIC_SERVICE_MODE` 设置为 `server`。
-针对服务端数据库部署场景,你需要将 `NEXT_PUBLIC_SERVICE_MODE` 设置为 `server`。
+
+ 在官方的 `lobe-chat-database` Docker 镜像中,已经默认将该环境变量设为 `server`,因此如果你使用
+ Docker 镜像部署,则无需再配置该环境变量。
+
-
- 在官方的 `lobe-chat-database` Docker 镜像中,已经默认将该环境变量设为 `server`,因此如果你使用
- Docker 镜像部署,则无需再配置该环境变量。
-
+
+ 由于 `NEXT_PUBLIC` 开头的环境变量是在前端代码中生效的,而因此无法通过容器运行时注入进行修改。 (`next.js`的参考文档 [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables) ) 这也是为什么我们选择再打一个 DB 版镜像的原因。
-
- 由于 `NEXT_PUBLIC` 开头的环境变量是在前端代码中生效的,而因此无法通过容器运行时注入进行修改。 (`next.js`的参考文档 [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables) ) 这也是为什么我们选择再打一个 DB 版镜像的原因。
+ 如果你需要在 Docker 部署中修改 `NEXT_PUBLIC` 前缀的变量,你必须自行构建镜像,在 build 时就把自己的 `NEXT_PUBLIC` 开头的环境变量打进去。
+
-如果你需要在 Docker 部署中修改 `NEXT_PUBLIC` 前缀的变量,你必须自行构建镜像,在 build 时就把自己的 `NEXT_PUBLIC` 开头的环境变量打进去。
+ ### `DATABASE_URL`
-
+ 配置数据库,核心是添加 `DATABASE_URL` 环境变量,将你准备好的 Postgres 数据库连接 URL 填入其中。数据库连接 URL 的通常格式为 `postgres://username:password@host:port/database`。
-### `DATABASE_URL`
+
+ 如果希望连接数据库时启用 SSL
+ ,请自行参考[文档](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)进行设置
+
-配置数据库,核心是添加 `DATABASE_URL` 环境变量,将你准备好的 Postgres 数据库连接 URL 填入其中。数据库连接 URL 的通常格式为 `postgres://username:password@host:port/database`。
+ ### `DATABASE_DRIVER`
-
- 如果希望连接数据库时启用 SSL
- ,请自行参考[文档](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)进行设置
-
+ `DATABASE_DRIVER` 环境变量用于区分两种 Postgres 数据库实例,`DATABASE_DRIVER` 的取值为 `node` 或 `neon`。
-### `DATABASE_DRIVER`
+ 为提升部署便捷性,我们根据不同的平台特点设置了默认值:
-`DATABASE_DRIVER` 环境变量用于区分两种 Postgres 数据库实例,`DATABASE_DRIVER` 的取值为 `node` 或 `neon`。
+ - 在 Vercel 平台下,`DATABASE_DRIVER` 默认为 `neon`;
+ - 在我们提供的 Docker 镜像 `lobe-chat-database` 中,`DATABASE_DRIVER` 默认为 `node`。
-为提升部署便捷性,我们根据不同的平台特点设置了默认值:
+ 因此如果你采用了以下标准的部署方式,你无需手动配置 `DATABASE_DRIVER` 环境变量:
-- 在 Vercel 平台下,`DATABASE_DRIVER` 默认为 `neon`;
-- 在我们提供的 Docker 镜像 `lobe-chat-database` 中,`DATABASE_DRIVER` 默认为 `node`。
+ - Vercel + Serverless Postgres
+ - Docker 镜像 + Node Postgres
-因此如果你采用了以下标准的部署方式,你无需手动配置 `DATABASE_DRIVER` 环境变量:
+ ### `KEY_VAULTS_SECRET`
-- Vercel + Serverless Postgres
-- Docker 镜像 + Node Postgres
-
-### `KEY_VAULTS_SECRET`
-
-考虑到用户会存储自己的 API Key 和 baseURL 等敏感信息到数据库中,因此我们需要一个密钥来加密这些信息,避免数据库被爆破/脱库时这些关键信息被泄露。 因此有了 `KEY_VAULTS_SECRET` 环境变量,用于加密用户存储的 apikey 等敏感信息。
-
-
- 你可以使用 `openssl rand -base64 32` 生成一个随机的 32 位字符串作为 `KEY_VAULTS_SECRET` 的值。
-
+ 考虑到用户会存储自己的 API Key 和 baseURL 等敏感信息到数据库中,因此我们需要一个密钥来加密这些信息,避免数据库被爆破 / 脱库时这些关键信息被泄露。 因此有了 `KEY_VAULTS_SECRET` 环境变量,用于加密用户存储的 apikey 等敏感信息。
+
+ 你可以使用 `openssl rand -base64 32` 生成一个随机的 32 位字符串作为 `KEY_VAULTS_SECRET` 的值。
+
## 配置身份验证服务
@@ -102,7 +99,7 @@ LobeChat 同时支持了客户端数据库和服务端数据库,因此我们
### Clerk
-[Clerk](https://clerk.com?utm_source=lobehub&utm_medium=docs) 是一个身份验证 SaaS 服务,提供了开箱即用的身份验证能力,产品化程度很高,集成成本较低,体验很好。对于提供 SaaS 化产品的诉求来说,Clerk 是一个不错的选择。我们官方提供的 [LobeChat Cloud](https://lobechat.com),就是使用了 Clerk 作为身份验证服务。
+[Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) 是一个身份验证 SaaS 服务,提供了开箱即用的身份验证能力,产品化程度很高,集成成本较低,体验很好。对于提供 SaaS 化产品的诉求来说,Clerk 是一个不错的选择。我们官方提供的 [LobeChat Cloud](https://lobechat.com),就是使用了 Clerk 作为身份验证服务。
Clerk 的集成也相对简单,只需要配置 `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` 、 `CLERK_SECRET_KEY` 和 `CLERK_WEBHOOK_SECRET` 环境变量即可,这三个环境变量可以在 Clerk 控制台中获取。
@@ -132,7 +129,7 @@ NextAuth 是一个开源的身份验证库,支持多种身份验证提供商
LobeChat 在 [很早以前](https://x.com/lobehub/status/1724289575672291782) 就支持了多模态的 AI 会话,其中涉及到图片上传给大模型的功能。在客户端数据库方案中,图片文件直接以二进制数据存储在浏览器 IndexedDB 数据库,但在服务端数据库中这个方案并不可行。因为在 Postgres 中直接存储文件类二进制数据会大大浪费宝贵的数据库存储空间,并拖慢计算性能。
-这块最佳实践是使用文件存储服务(S3)来存储图片文件,同时 S3 也是文件上传/知识库功能所依赖的大容量静态文件存储方案。
+这块最佳实践是使用文件存储服务(S3)来存储图片文件,同时 S3 也是文件上传 / 知识库功能所依赖的大容量静态文件存储方案。
在本文档库中,S3 所指代的是指兼容 S3 存储方案,即支持 Amazon S3 API 的对象存储系统,常见例如
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.mdx
index edbd634..beb3a60 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.mdx
@@ -1,7 +1,7 @@
---
-title: Deploying LobeChat Server Database with Docker Compose
+title: Deploying LobeChat with Docker Compose
description: >-
- Learn how to deploy LobeChat Server Database using Docker Compose, including
+ Learn how to deploy the LobeChat service using Docker Compose, including
configuration tutorials for various services.
tags:
- Docker Compose
@@ -10,93 +10,438 @@ tags:
- Deployment Guide
---
-# Deploying LobeChat server database with Docker Compose
+# Deploying LobeChat Server Database Version with Docker Compose
+
+ **Note on Docker Deployment Limitations**
+ The Docker and Docker Compose deployment options do not support injecting the `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` through environment variables, which prevents enabling the Clerk authentication service. Recommended alternatives include:
+
+ - Hosting deployment via Vercel
+
+ - Running a local image build process
+
+
+## Quick Start
+
- This article assumes that you are familiar with the basic principles and processes of deploying
- the LobeChat server database version (hereinafter referred to as DB version), so it only includes
- the core environment variable configuration. If you are not familiar with the deployment
- principles of LobeChat DB version, please refer to [Deploying using a Server
- Database](/zh/docs/self-hosting/server-database).
+ **System Compatibility Notes**
+
+ - One-click deployment is supported in Unix environments (Linux/macOS).
+
+ - Windows users must run through [WSL 2](https://aka.ms/wsl).
+
+ - The one-click startup script is only for initial deployment; for subsequent deployments, please refer to the [Custom Deployment](#custom-deployment) section.
+
+ - Port occupation check: Ensure that ports `3210`, `8000`, `9000`, and `9001` are available.
-
- Due to the inability to expose `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` using Docker environment variables, you cannot use Clerk as an authentication service when deploying LobeChat using Docker / Docker Compose.
+Execute the following commands to set up the deployment environment; the directory `lobe-chat-db` will be used to store your configuration files and subsequent database files.
+
+```sh
+mkdir lobe-chat-db && cd lobe-chat-db
+```
-If you do need Clerk as an authentication service, you might consider deploying using Vercel or building your own image.
+Fetch and execute the deployment script:
+```sh
+bash <(curl -fsSL https://lobe.li/setup.sh) -l en
+```
+
+The script supports the following deployment modes; please choose the appropriate mode based on your needs and read the rest of the documentation.
+
+- [Local Mode (default)](#local-mode): Accessible only locally, not supporting LAN/public access; suitable for initial experiences.
+- [Port Mode](#port-mode): Supports LAN/public `http` access; suitable for no domain or private network use.
+- [Domain Mode](#domain-mode): Supports LAN/public `http/https` access with reverse proxy; suitable for personal or team use.
+
+
+ In the script's options prompt `(Option1/Option2)[Option1]`: `(Option1 / Option2)` indicates selectable options, while `[Option1]` indicates the default option; simply press enter to choose the default.
-Generally speaking, to fully run the LobeChat database version, you need at least the following four services:
+### Local Mode
-- LobeChat database version itself
-- PostgreSQL database with PGVector plugin
-- Object storage service supporting S3 protocol
-- SSO authentication service supported by LobeChat
+
+ ### Complete Remaining Configuration in Interactive Script
-These services can be combined through self-hosting or online cloud services to meet your needs.
+ Continue pressing enter to use the default configuration.
-We provide a fully self-built Docker Compose configuration, which you can use directly to start the LobeChat database version or modify to suit your needs.
+ ### Check Configuration Generation Report
-We default to using [MinIO](https://github.com/minio/minio) as the local S3 object storage service and [Logto](https://github.com/logto-io/logto) as the local authentication service.
+ After the script finishes running, you need to check the configuration generation report, which includes the accounts and initial login passwords for the Casdoor administrator and user.
-## Quick Start
+
+ Please log in to LobeChat using the user account; the administrator account is only for managing Casdoor.
+
+
+ ```log
+ The results of the secure key generation are as follows:
+ LobeChat:
+ - URL: http://localhost:3210
+ - Username: user
+ - Password: c66f8c
+ Casdoor:
+ - URL: http://localhost:8000
+ - Username: admin
+ - Password: c66f8c
+ Minio:
+ - URL: http://localhost:9000
+ - Username: admin
+ - Password: 8c82ea41
+ ```
+
+ ### Start Docker
+
+ ```sh
+ docker compose up -d
+ ```
+
+ ### Check Logs
+
+ ```sh
+ docker logs -f lobe-chat
+ ```
+
+ If you see the following logs in the container, it means the startup was successful:
+
+ ```log
+ [Database] Start to migration...
+ ✅ database migration pass.
+ -------------------------------------
+ ▲ Next.js 14.x.x
+ - Local: http://localhost:3210
+ - Network: http://0.0.0.0:3210
+
+ ✓ Starting...
+ ✓ Ready in 95ms
+ ```
+
+ ### Access Application
+
+ Visit your LobeChat service at [http://localhost:3210](http://localhost:3210). The account credentials for the application can be found in the report from step `2`.
+
-To facilitate quick start, this chapter uses the docker-compose configuration file in the `docker-compose/local` directory. The LobeChat application runs at `http://localhost:3210` after startup and can be run locally.
+### Port Mode
-
- To facilitate quick start, this docker-compose.yml omits a large number of Secret/Password configurations and is only suitable for quick demonstration or personal local use. Do not use it directly in a production environment! Otherwise, you will be responsible for any security issues!
-
+
+ ### Complete Remaining Configuration in Interactive Script
+
+ In port mode, you need to complete the following based on the script prompts:
+
+ - Server IP address settings: for LAN/public access.
+ - Regenerate secure keys: We highly recommend regenerating the secure keys; if you lack the key generation library required by the script, we suggest referring to the [Custom Deployment](#custom-deployment) section for key modifications.
+
+ ### Check Configuration Generation Report
+
+ After the script finishes running, please check the configuration generation report for the Casdoor administrator account, user account, and their initial login passwords.
+
+
+ Please log in to LobeChat using the user account; the administrator account is only for managing Casdoor.
+
+
+ ```log
+ The results of the secure key generation are as follows:
+ LobeChat:
+ - URL: http://your_server_ip:3210
+ - Username: user
+ - Password: 837e26
+ Casdoor:
+ - URL: http://your_server_ip:8000
+ - Username: admin
+ - Password: 837e26
+ Minio:
+ - URL: http://your_server_ip:9000
+ - Username: admin
+ - Password: dbac8440
+ ```
+
+ ### Start Docker
+
+ ```sh
+ docker compose up -d
+ ```
+
+ ### Check Logs
+
+ ```sh
+ docker logs -f lobe-chat
+ ```
+
+ If you see the following logs in the container, it means the startup was successful:
+
+ ```log
+ [Database] Start to migration...
+ ✅ database migration pass.
+ -------------------------------------
+ ▲ Next.js 14.x.x
+ - Local: http://your_server_ip:3210
+ - Network: http://0.0.0.0:3210
+ ✓ Starting...
+ ✓ Ready in 95ms
+ ```
+
+ ### Access Application
+
+ You can access your LobeChat service at `http://your_server_ip:3210`. The account credentials for the application can be found in the report from step `2`.
+
+
+ If your service can accessed via the public network,
+ we strongly recommend disabling the registration,
+ refer to the [documentation](https://lobehub.com/docs/self-hosting/advanced/auth/next-auth/casdoor)
+ for more information.
+
+
+
+### Domain Mode
- ### Create Configuration Files
+ ### Complete Reverse Proxy Configuration
+
+ In domain mode, you need to complete the reverse proxy configuration and ensure that the LAN/public can access the following services. Please use a reverse proxy to map the following service ports to the domain names:
+
+ | Domain | Proxy Port | Required |
+ | ---------------------- | ---------- | -------- |
+ | `lobe.example.com` | `3210` | Yes |
+ | `auth.example.com` | `8000` | Yes |
+ | `minio.example.com` | `9000` | Yes |
+ | `minio-ui.example.com` | `9001` | |
+
+
+ If you are using panel software like [aaPanel](https://www.bt.cn/) for reverse proxy configuration,
+ ensure it does not intercept requests to the `.well-known` path to facilitate the proper functioning of Casdoor's OAuth2 configuration.
+ Below is a whitelist configuration for the Nginx server block concerning paths for Casdoor reverse proxy:
+
+ ```nginx
+ location /.well-known/openid-configuration {
+ proxy_pass http://localhost:8000; # Forward to localhost:8000
+ proxy_set_header Host $host; # Keep the original host header
+ proxy_set_header X-Real-IP $remote_addr; # Keep the client's real IP
+ proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; # Keep the forwarded IP
+ proxy_set_header X-Forwarded-Proto $scheme; # Keep the request protocol
+ }
+ ```
+
+ ⚠️ If you are using such panel software,
+ please do not enable any form of caching in the reverse proxy settings of such panel software to avoid affecting the normal operation of the service.
+ Read more at https://github.com/lobehub/lobe-chat/discussions/5986
+
+
+ ### Complete Remaining Configuration in Interactive Script
+
+ In domain mode, you need to complete the following configurations based on script prompts:
+
+ - Domain setup for the LobeChat service: `lobe.example.com`
+ - Domain setup for the Minio service: `minio.example.com`
+ - Domain setup for the Casdoor service: `auth.example.com`
+ - Choose the access protocol: `http` or `https`
+ - Regenerate secure keys: We highly recommend regenerating the secure keys; if you lack the key generation library required by the script, we suggest referring to the [Custom Deployment](#custom-deployment) section for key modifications.
+
+
+ The following issues may impede access to your service:
-Create a new `lobe-chat-db` directory to store your configuration files and subsequent database files.
+ - The domain configuration here must match the reverse proxy configuration in step `1`.
+
+ - If you are using Cloudflare for domain resolution and have activated `full proxy`, please use the `https` protocol.
+
+ - If you have used the HTTPS protocol, ensure that your domain certificate is correctly configured; one-click deployment does not support self-signed certificates by default.
+
+
+ ### Check Configuration Generation Report
+
+ After the script finishes running, you need to check the configuration generation report, which includes the initial login password for the Casdoor administrator.
+
+
+ Please log in to LobeChat using the user account; the administrator account is only for managing Casdoor.
+
+
+ ```log
+ The results of the secure key generation are as follows:
+ LobeChat:
+ - URL: https://lobe.example.com
+ - Username: user
+ - Password: 837e26
+ Casdoor:
+ - URL: https://auth.example.com
+ - Username: admin
+ - Password: 837e26
+ Minio:
+ - URL: https://minio.example.com
+ - Username: admin
+ - Password: dbac8440
+ ```
+
+ ### Start Docker
+
+ ```sh
+ docker compose up -d
+ ```
+
+ ### Check Logs
+
+ ```sh
+ docker logs -f lobe-chat
+ ```
+
+ If you see the following logs in the container, it indicates a successful startup:
+
+ ```log
+ [Database] Start to migration...
+ ✅ database migration pass.
+ -------------------------------------
+ ▲ Next.js 14.x.x
+ - Local: https://localhost:3210
+ - Network: http://0.0.0.0:3210
+ ✓ Starting...
+ ✓ Ready in 95ms
+ ```
+
+ ### Access Application
+
+ You can access your LobeChat service via `https://lobe.example.com`. The account credentials for the application can be found in the report from step `3`.
+
+
+ If your service can accessed via the public network,
+ we strongly recommend disabling the registration,
+ refer to the [documentation](https://lobehub.com/docs/self-hosting/advanced/auth/next-auth/casdoor)
+ for more information.
+
+
+
+## Custom Deployment
+
+This section mainly introduces the configurations that need to be modified to customize the deployment of the LobeChat service in different network environments. Before starting, you can download the [Docker Compose configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml) and the [environment variable configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/refs/heads/main/docker-compose/local/.env.example).
```sh
-mkdir lobe-chat-db
+curl -O https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml
+curl -O https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/.env.en_US.example
+mv .env.en_US.example .env
```
-Pull the configuration files into your directory:
+
+ This section does not cover all complete variables; remaining variables can be referenced in [Deploying with the Server Database](/en/docs/self-hosting/server-database).
+
-```sh
-curl -fsSL https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local-logto/docker-compose.yml > docker-compose.yml
-curl -fsSL https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local-logto/.env.example > .env
+### Prerequisites
+
+Generally, to fully run the LobeChat database version, you will need at least the following four services:
+
+- The LobeChat database version itself
+- PostgreSQL database with PGVector plugin
+- Object storage service that supports S3 protocol
+- An SSO authentication service supported by LobeChat
+
+These services can be combined through self-hosting or online cloud services to meet various deployment needs. In this article, we provide a Docker Compose configuration entirely based on open-source self-hosted services, which can be used directly to start the LobeChat database version or modified to suit your requirements.
+
+We use [MinIO](https://github.com/minio/minio) as the local S3 object storage service and [Casdoor](https://github.com/casdoor/casdoor) as the local authentication service by default.
+
+
+ If your network topology is complex, please make sure these services can communicate properly within your network environment.
+
+
+### Necessary Configuration
+
+Now, we will introduce the necessary configurations for running these services:
+
+1. Casdoor
+
+- LobeChat requires communication with Casdoor, so you need to configure Casdoor's Issuer.
+
+```env
+AUTH_CASDOOR_ISSUER=https://auth.example.com
```
-### Start Services
+This configuration will affect LobeChat's login authentication service, and you need to ensure that the URL of the Casdoor service is correct. You can find common manifestations and solutions for errors in this configuration in the [FAQ](#faq).
+
+- Additionally, you need to allow the callback URL in Casdoor to point to the LobeChat address:
+
+Please add a line in the `Authentication -> Application` -> `` -> `Redirect URI` in Casdoor's web panel:
+
+```
+https://auth.example.com/api/auth/callback/casdoor
+```
+
+- Casdoor needs to provide the Origin information for access in the environment variables:
+
+```env
+origin=https://auth.example.com
+```
+
+2. MinIO
+
+- LobeChat needs to provide a public access URL for object files for the LLM service provider, hence you need to configure MinIO's Endpoint.
+
+```env
+S3_PUBLIC_DOMAIN=https://minio.example.com
+S3_ENDPOINT=https://minio.example.com
+```
+
+3. PostgreSQL
+
+This configuration is found in the `docker-compose.yml` file, and you will need to configure the database name and password:
+
+```yaml
+services:
+ lobe:
+ environment:
+ - 'DATABASE_URL=postgresql://postgres:${POSTGRES_PASSWORD}@postgresql:5432/${LOBE_DB_NAME}'
+```
+
+## FAQ
+
+#### Unable to Log In Properly
+
+Check for the following errors based on the container logs:
```sh
-docker compose up -d
+docker logs -f lobe-chat
+```
+
+- r3: "response" is not a conform Authorization Server Metadata response (unexpected HTTP status code)
+
+```log
+lobe-chat | [auth][error] r3: "response" is not a conform Authorization Server Metadata response (unexpected HTTP status code)
+```
+
+Cause: This issue is typically caused by improper reverse proxy configuration; you need to ensure your reverse proxy configuration does not intercept the Casdoor OAuth2 configuration requests.
+
+Solutions:
+
+- Please refer to the reverse proxy configuration notes in the [Domain Mode](#domain-mode) section.
+
+- A direct troubleshooting method is to access `https://auth.example.com/.well-known/openid-configuration` directly; if:
+ - Non-JSON format data is returned, it indicates your reverse proxy configuration is incorrect.
+ - If the returned JSON format data contains an `"issuer": "URL"` field that does not match your configured `https://auth.example.com`, it indicates your environment variable configuration is incorrect.
+
+- TypeError: fetch failed
+
+```log
+lobe-chat | [auth][error] TypeError: fetch failed
```
-### Configure Logto
+Cause: LobeChat cannot access the authentication service.
-1. Open `http://localhost:3002` to access the Logto WebUI and register an administrator account.
+Solutions:
-2. Create a `Next.js (App Router)` application and add the following configurations:
+- Check whether your authentication service is running properly and whether LobeChat's network can reach the authentication service.
- - `Redirect URI` should be `http://localhost:3210/api/auth/callback/logto`
- - `Post sign-out redirect URI` should be `http://localhost:3210/`
+- A straightforward troubleshooting method is to use the `curl` command in the LobeChat container terminal to access your authentication service at `https://auth.example.com/.well-known/openid-configuration`. If JSON format data is returned, it indicates your authentication service is functioning correctly.
-3. Obtain the `App ID` and `App secrets`, and fill them into your `.env` file corresponding to `LOGTO_CLIENT_ID` and `LOGTO_CLIENT_SECRET`.
+````markdown
+## Extended Configuration
-### Configure MinIO S3
+To enhance your LobeChat service, you can perform the following extended configurations according to your needs.
-1. Open `http://localhost:9001` to access the MinIO WebUI. The default admin account password is configured in `.env`.
+### Use MinIO to Store Casdoor Avatars
-2. Create a bucket that matches the `MINIO_LOBE_BUCKET` field in your `.env` file, which defaults to `lobe`.
+Allow users to change their avatars in Casdoor.
-3. Choose a custom policy, copy the following content, and paste it in (if you modified the bucket name, please find and replace accordingly):
+1. First, create a bucket named `casdoor` in `buckets`, select a custom policy, and copy and paste the content below (if you modify the bucket name, please find and replace accordingly).
```json
{
@@ -107,7 +452,7 @@ docker compose up -d
"AWS": ["*"]
},
"Action": ["s3:GetBucketLocation"],
- "Resource": ["arn:aws:s3:::lobe"]
+ "Resource": ["arn:aws:s3:::casdoor"]
},
{
"Effect": "Allow",
@@ -115,7 +460,7 @@ docker compose up -d
"AWS": ["*"]
},
"Action": ["s3:ListBucket"],
- "Resource": ["arn:aws:s3:::lobe"],
+ "Resource": ["arn:aws:s3:::casdoor"],
"Condition": {
"StringEquals": {
"s3:prefix": ["files/*"]
@@ -128,239 +473,195 @@ docker compose up -d
"AWS": ["*"]
},
"Action": ["s3:PutObject", "s3:DeleteObject", "s3:GetObject"],
- "Resource": ["arn:aws:s3:::lobe/files/**"]
+ "Resource": ["arn:aws:s3:::casdoor/**"]
}
],
"Version": "2012-10-17"
}
- ```
+````
-4. Create a new access key, and fill the generated `Access Key` and `Secret Key` into your `.env` file under `S3_ACCESS_KEY_ID` and `S3_SECRET_ACCESS_KEY`.
+2. Create a new access key and store the generated `Access Key` and `Secret Key`.
-### Restart LobeChat Service
+3. In Casdoor's `Authentication -> Providers`, associate the MinIO S3 service. Below is an example configuration:
-```sh
-docker compose up -d
-```
+ 
-
- At this point, do not use `docker compose restart lobe` to restart, as this method will not reload the environment variables, and your S3 configuration will not take effect.
-
-
+ Here, the client ID and client secret correspond to the `Access Key` and `Secret Key` from the previous step; replace `192.168.31.251` with `your_server_ip`.
-If you see the following logs in the container, it indicates that it has started successfully:
+4. In Casdoor's `Authentication -> Apps`, add a provider to the `app-built-in` application, select `minio`, and save and exit.
-```log
-[Database] Start to migration...
-✅ database migration pass.
--------------------------------------
- ▲ Next.js 14.x.x
- - Local: http://localhost:3210
- - Network: http://0.0.0.0:3210
-
- ✓ Starting...
- ✓ Ready in 95ms
-```
+5. You can attempt to upload a file in Casdoor's `Authentication -> Resources` to test if the configuration is correct.
-
+### Migrating from `logto` to `Casdoor` in Production Deployment
+
+This is applicable for users who have been using `logto` as their login and authentication service in a production environment.
+
+
+ Due to significant instability when using [Logto](https://logto.io/)
+ as a login and authentication service, the following tutorial is based on deploying with an IP mode, implementing a domain release solution using Casdoor as the authentication service provider.
+ The remainder of this article will illustrate using this as an example. If you are using other login authentication services like Logto, the process should be similar, but be aware that port configurations may differ among different services.
+
-You have successfully deployed the LobeChat database version, and you can access your LobeChat service at `http://localhost:3210`.
+In the following, it is assumed that in addition to the above services, you are also running an **Nginx** layer for reverse proxy and SSL configuration.
-If you encounter issues, please check the Docker logs and console logs, and follow the detailed troubleshooting guide later in the document.
+The domain and corresponding service port descriptions are as follows:
-## Deploying to Production
+- `lobe.example.com`: This is your LobeChat service domain, which needs to reverse proxy to the LobeChat service port, default is `3210`.
+- `auth.example.com`: This is your Logto UI domain, which needs to reverse proxy to the Logto WebUI service port, default is `8000`.
+- `minio.example.com`: This is your MinIO API domain, which needs to reverse proxy to the MinIO API service port, default is `9000`.
+- `minio-ui.example.com`: Optional, this is your MinIO UI domain, which needs to reverse proxy to the MinIO WebUI service port, default is `9001`.
-The main difference between production and local operation is the need to use domain addresses instead of localhost. We assume that in addition to the above services, you are also running an Nginx layer for reverse proxy and SSL configuration.
+#### Configuration File
-The domain names and corresponding service port descriptions are as follows:
+```sh
+bash <(curl -fsSL https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/setup.sh) -f -l zh_CN
+docker compose up -d
+```
-- `lobe.example.com`: your LobeChat service domain, needs to be reverse proxied to the LobeChat service port, default is `3210`
-- `lobe-auth-api.example.com`: your Logto service domain, needs to be reverse proxied to the Logto API service port, default is `3001`
-- `lobe-auth-ui.example.com`: your Logto UI domain, needs to be reverse proxied to the Logto WebUI service port, default is `3002`
-- `lobe-s3-api.example.com`: your MinIO API domain, needs to be reverse proxied to the MinIO API service port, default is `9000`
-- `lobe-s3-ui.example.com`: optional, your MinIO UI domain, needs to be reverse proxied to the MinIO WebUI service port, default is `9001`
+Make sure to save the newly generated password at this time!
-And the service port without reverse proxy:
+After running, you will get three files:
-- `postgresql`: your PostgreSQL database service port, default is `5432`
+- init\_data.json
+- docker-compose.yml
+- .env
-
- Please note that CORS cross-origin is configured internally in MinIO / Logto service, do not configure CORS additionally in your reverse proxy, as this will cause errors.
- For minio ports other than 443, Host must be $http_host (with port number), otherwise a 403 error will occur: proxy_set_header Host $http_host.
+Next, modify the configuration files to achieve domain release.
-If you need to configure SSL certificates, please configure them uniformly in the outer Nginx reverse proxy, rather than in MinIO.
+1. Modify the `docker-compose.yml` file.
+ 1. Change the `MINIO_API_CORS_ALLOW_ORIGIN` field of `minio`.
+ ```yaml
+ 'MINIO_API_CORS_ALLOW_ORIGIN=https://lobe.example.com'
+ ```
+ 2. Modify the `origin` field of `casdoor`.
+ ```yaml
+ origin: 'https://auth.example.com'
+ ```
+ 3. Modify the `environment` field of `lobe`.
+ ```yaml
+ # - 'APP_URL=http://localhost:3210'
+ - 'APP_URL=https://lobe.example.com'
+
+ - 'NEXT_AUTH_SSO_PROVIDERS=casdoor'
+ - 'KEY_VAULTS_SECRET=Kix2wcUONd4CX51E/ZPAd36BqM4wzJgKjPtz2sGztqQ='
+ - 'NEXT_AUTH_SECRET=NX2kaPE923dt6BL2U8e9oSre5RfoT7hg'
+ # - 'AUTH_URL=http://localhost:${LOBE_PORT}/api/auth'
+ - 'AUTH_URL=https://lobe.example.com/api/auth'
+
+ # - 'AUTH_CASDOOR_ISSUER=http://localhost:${CASDOOR_PORT}'
+ - 'AUTH_CASDOOR_ISSUER=https://auth.example.com'
+
+ - 'DATABASE_URL=postgresql://postgres:${POSTGRES_PASSWORD}@postgresql:5432/${LOBE_DB_NAME}'
+ # - 'S3_ENDPOINT=http://localhost:${MINIO_PORT}'
+ - 'S3_ENDPOINT=https://minio.example.com'
+
+ - 'S3_BUCKET=${MINIO_LOBE_BUCKET}'
+ # - 'S3_PUBLIC_DOMAIN=http://localhost:${MINIO_PORT}'
+ - 'S3_PUBLIC_DOMAIN=https://minio.example.com'
+
+ - 'S3_ENABLE_PATH_STYLE=1'
+ - 'LLM_VISION_IMAGE_USE_BASE64=1'
+ ```
+2. Modify the `.env` file.
+
+ For security reasons, modify the ROOT USER field in the `.env` file.
-### Configuration Files
-
```sh
-curl -fsSL https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/production/docker-compose.yml > docker-compose.yml
-curl -fsSL https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/production/.env.example > .env
+# MinIO S3 configuration
+MINIO_ROOT_USER=XXXX
+MINIO_ROOT_PASSWORD=XXXX
```
-The configuration files include `.env` and `docker-compose.yml`, where the `.env` file is used to configure LobeChat's environment variables, and the `docker-compose.yml` file is used to configure the Postgres, MinIO, and Logto services.
-
-In general, you should only modify sensitive information such as domain names and account passwords, while other configuration items should be set according to the default values.
-
-Refer to the example configurations in the appendix of this article.
+#### Postgres Database Configuration
-### PostgreSQL Database Configuration
-
-You can check the logs using the following command:
+You can check the logs with the following command:
```sh
-docker logs -f lobe-database
+docker logs -f lobe-chat
```
- In our official Docker images, the database schema migration will be automatically executed before
- starting the image. Our official image guarantees the stability of the "empty database -> complete
- table" automatic table creation. Therefore, we recommend that your database instance use an empty
- table instance, thereby avoiding the hassle of manually maintaining table structures or
- migrations.
+ In our official Docker images, automatic migration of the database schema is performed before starting the images.
+ Our official images guarantee the stability of "empty database -> complete tables" for automatic table creation. Therefore, we recommend your database instance use an empty table instance to avoid the trouble of manually maintaining table structure or migrations.
-If you encounter issues when creating tables, you can try using the following commands to forcibly remove the database container and restart:
+If you encounter issues during table creation, you can try the following command to forcibly remove the database container and restart:
```sh
-docker compose down # Stop services
+docker compose down # Stop the service
sudo rm -rf ./data # Remove mounted database data
docker compose up -d # Restart
```
-### Authentication Service Configuration
-
-This article uses Logto as an example to explain the configuration process. If you are using other authentication service providers, please refer to their documentation for configuration.
+#### Login Authentication Service Configuration
-
- Please remember to configure the corresponding CORS cross-origin settings for the authentication service provider to ensure that LobeChat can access the authentication service properly.
+You first need to access the WebUI for configuration:
-In this article, you need to allow cross-origin requests from `https://lobe.example.com`.
+- If you have set up the reverse proxy as mentioned before, open `https://auth.example.com`
+- Otherwise, after port mapping, open `http://localhost:8000`
-
+Log in to the admin account:
-You need to first access the WebUI for configuration:
+- The default username is admin.
+- The default password is the random password generated when downloading the config file. If forgotten, you can find it in the `init_data.json` file.
-- If you configured the reverse proxy as mentioned earlier, open `https://lobe-auth-ui.example.com`
-- Otherwise, after port mapping, open `http://localhost:3002`
+After logging in, perform the following actions:
-1. Register a new account; the first registered account will automatically become an administrator.
+1. In `User Management -> Organizations`, add a new organization with the name and display name `Lobe Users`. Keep the rest as default.
+2. In `Authentication -> Apps`, add a new application.
-2. In `Applications`, create a `Next.js (App Router)` application with any name.
+- Name and display name should be `LobeChat`.
+- Organization should be `Lobe Users`.
+- Add a line in Redirect URLs as `https://lobe.example.com/api/auth/callback/casdoor`.
+- Disable all login methods except password.
+- Fill in the client ID and client secret in the `.env` file under `AUTH_CASDOOR_ID` and `AUTH_CASDOOR_SECRET`.
+- (Optional) Design the appearance of the login and registration pages by mimicking the `built-in` application configuration.
+- Save and exit.
-3. Set `Redirect URI` to `https://lobe.example.com/api/auth/callback/logto`, and `Post sign-out redirect URI` to `https://lobe.example.com/`.
-
-4. Set `CORS allowed origins` to `https://lobe.example.com`.
-
-
-
-5. Obtain `App ID` and `App secrets`, and fill them into your `.env` file under `LOGTO_CLIENT_ID` and `LOGTO_CLIENT_SECRET`.
-
-6. Set `LOGTO_ISSUER` in your `.env` file to `https://lobe-auth-api.example.com/oidc`.
-
-
-
-7. Optional: In the left panel under `Sign-in experience`, in `Sign-up and sign-in - Advanced Options`, disable `Enable user registration` to prohibit user self-registration. If you disable user self-registration, you can only manually add users in the left panel under `User Management`.
-
-
-
-8. Restart the LobeChat service:
-
- ```sh
- docker compose up -d
- ```
-
-
- Please note that the administrator account is not the same as a registered user; do not use your
- administrator account to log into LobeChat, as this will only result in an error.
+
+ Following the steps above ensures that not all users are administrators by default, leading to an unsafe situation.
-### S3 Object Storage Service Configuration
+#### S3 Object Storage Service Configuration
-This article uses MinIO as an example to explain the configuration process. If you are using other S3 service providers, please refer to their documentation for configuration.
+This article uses MinIO as an example to explain the configuration process. If you are using another S3 service provider, please refer to their documentation for configuration.
- Please remember to configure the corresponding CORS cross-origin settings for the S3 service provider to ensure that LobeChat can access the S3 service properly.
+ Please remember to configure the corresponding S3 service provider's CORS settings to ensure that LobeChat can access the S3 service correctly.
-In this article, you need to allow cross-origin requests from `https://lobe.example.com`. This can be configured in the MinIO WebUI under `Configuration - API - Cors Allow Origin`, or in the Docker Compose under `minio - environment - MINIO_API_CORS_ALLOW_ORIGIN`.
-
-If you configure using the second method (which is also the default method), you will not be able to configure it in the MinIO WebUI anymore.
+ In this document, you need to allow cross-origin requests from `https://lobe.example.com`. This can either be configured in MinIO WebUI under `Configuration - API - Cors Allow Origin`, or in the Docker Compose configuration under `minio - environment - MINIO_API_CORS_ALLOW_ORIGIN`.
+ If you use the second method (which is also the default), you will no longer be able to configure it in the MinIO WebUI.
-You need to first access the WebUI for configuration:
+You first need to access the WebUI for configuration:
-- If you configured the reverse proxy as mentioned earlier, open `https://lobe-s3-ui.example.com`
+- If you have set up the reverse proxy as mentioned before, open `https://minio-ui.example.com`
- Otherwise, after port mapping, open `http://localhost:9001`
-1. Enter your `MINIO_ROOT_USER` and `MINIO_ROOT_PASSWORD` on the login screen, then click login.
-
-2. In the left panel under Administer / Buckets, click `Create Bucket`, enter `lobe` (corresponding to your `S3_BUCKET` environment variable), and then click `Create`.
-
-
-
-3. Select your bucket, click Summary - Access Policy, edit, choose `Custom`, and input the content from `minio-bucket-config.json` (see appendix) and save (again, assuming your bucket name is `lobe`):
+1. Enter the `MINIO_ROOT_USER` and `MINIO_ROOT_PASSWORD` you set in the login interface, then click login.
-
+2. In the left panel under User / Access Keys, click `Create New Access Key`, no additional modifications needed, and fill the generated `Access Key` and `Secret Key` into your `.env` file under `S3_ACCESS_KEY_ID` and `S3_SECRET_ACCESS_KEY`.
-
+
-4. In the left panel under User / Access Keys, click `Create New Access Key`, make no additional modifications, and fill the generated `Access Key` and `Secret Key` into your `.env` file under `S3_ACCESS_KEY_ID` and `S3_SECRET_ACCESS_KEY`.
-
-
-
-5. Restart the LobeChat service:
+3. Restart the LobeChat service:
```sh
docker compose up -d
```
-You have successfully deployed the LobeChat database version, and you can access your LobeChat service at `https://lobe.example.com`.
+At this point, you have successfully deployed the LobeChat database version, and you can access your LobeChat service at `https://lobe.example.com`.
-## Appendix
+#### Configuration Files
-To facilitate one-click copying, here are the example configuration files needed to configure the server database:
+For convenience, here is a summary of example configuration files required for the production deployment using the Casdoor authentication scheme:
-### Local Deployment
-
-#### `.env`
+- `.env`
```sh
-# Logto secret
-LOGTO_CLIENT_ID=
-LOGTO_CLIENT_SECRET=
-
-# MinIO S3 configuration
-MINIO_ROOT_USER=YOUR_MINIO_USER
-MINIO_ROOT_PASSWORD=YOUR_MINIO_PASSWORD
-
-# Configure the bucket information of MinIO
-MINIO_LOBE_BUCKET=lobe
-S3_ACCESS_KEY_ID=
-S3_SECRET_ACCESS_KEY=
-
# Proxy, if you need it
# HTTP_PROXY=http://localhost:7890
# HTTPS_PROXY=http://localhost:7890
@@ -370,30 +671,44 @@ S3_SECRET_ACCESS_KEY=
# OPENAI_PROXY_URL=https://api.openai.com/v1
# OPENAI_MODEL_LIST=...
-# ----- Other config -----
+# ===========================
+# ====== Preset config ======
+# ===========================
# if no special requirements, no need to change
LOBE_PORT=3210
-LOGTO_PORT=3001
+CASDOOR_PORT=8000
MINIO_PORT=9000
# Postgres related, which are the necessary environment variables for DB
LOBE_DB_NAME=lobechat
POSTGRES_PASSWORD=uWNZugjBqixf8dxC
+# Casdoor secret
+AUTH_CASDOOR_ID=943e627d79d5dd8a22a1
+AUTH_CASDOOR_SECRET=6ec24ac304e92e160ef0d0656ecd86de8cb563f1
+
+# MinIO S3 configuration
+MINIO_ROOT_USER=Joe
+MINIO_ROOT_PASSWORD=Crj1570768
+
+# Configure the bucket information of MinIO
+MINIO_LOBE_BUCKET=lobe
+S3_ACCESS_KEY_ID=dB6Uq9CYZPdWSZouPyEd
+S3_SECRET_ACCESS_KEY=aPBW8CVULkh8bw1GatlT0GjLihcXHLNwRml4pieS
```
-#### `docker-compose.yml`
+- `docker-compose.yml`
```yaml
+name: lobe-chat-database
services:
network-service:
image: alpine
container_name: lobe-network
ports:
- - '${MINIO_PORT}:${MINIO_PORT}' # MinIO API
- - '9001:9001' # MinIO Console
- - '${LOGTO_PORT}:${LOGTO_PORT}' # Logto
- - '3002:3002' # Logto Admin
+ - '${MINIO_PORT}:${MINIO_PORT}' # MinIO API
+ - '9001:9001' # MinIO Console
+ - '${CASDOOR_PORT}:${CASDOOR_PORT}' # Casdoor
- '${LOBE_PORT}:3210' # LobeChat
command: tail -f /dev/null
networks:
@@ -403,7 +718,7 @@ services:
image: pgvector/pgvector:pg16
container_name: lobe-postgres
ports:
- - "5432:5432"
+ - '5432:5432'
volumes:
- './data:/var/lib/postgresql/data'
environment:
@@ -427,29 +742,33 @@ services:
environment:
- 'MINIO_ROOT_USER=${MINIO_ROOT_USER}'
- 'MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD}'
- - 'MINIO_API_CORS_ALLOW_ORIGIN=http://localhost:${LOBE_PORT}'
+ # - 'MINIO_API_CORS_ALLOW_ORIGIN=http://localhost:${LOBE_PORT}'
+ - 'MINIO_API_CORS_ALLOW_ORIGIN=https://lobe.example.com'
restart: always
command: >
server /etc/minio/data --address ":${MINIO_PORT}" --console-address ":9001"
- logto:
- image: svhd/logto
- container_name: lobe-logto
+ casdoor:
+ image: casbin/casdoor
+ container_name: lobe-casdoor
+ entrypoint: /bin/sh -c './server --createDatabase=true'
network_mode: 'service:network-service'
depends_on:
postgresql:
condition: service_healthy
environment:
- - 'TRUST_PROXY_HEADER=1'
- - 'PORT=${LOGTO_PORT}'
- - 'DB_URL=postgresql://postgres:${POSTGRES_PASSWORD}@postgresql:5432/logto'
- - 'ENDPOINT=http://localhost:${LOGTO_PORT}'
- - 'ADMIN_ENDPOINT=http://localhost:3002'
- entrypoint: ['sh', '-c', 'npm run cli db seed -- --swe && npm start']
+ RUNNING_IN_DOCKER: 'true'
+ driverName: 'postgres'
+ dataSourceName: 'user=postgres password=${POSTGRES_PASSWORD} host=postgresql port=5432 sslmode=disable dbname=casdoor'
+ # origin: 'http://localhost:${CASDOOR_PORT}'
+ origin: 'https://auth.example.com'
+ runmode: 'dev'
+ volumes:
+ - ./init_data.json:/init_data.json
lobe:
image: lobehub/lobe-chat-database
- container_name: lobe-database
+ container_name: lobe-chat-database
network_mode: 'service:network-service'
depends_on:
postgresql:
@@ -458,21 +777,32 @@ services:
condition: service_started
minio:
condition: service_started
- logto:
+ casdoor:
condition: service_started
environment:
- - 'APP_URL=http://localhost:3210'
- - 'NEXT_AUTH_SSO_PROVIDERS=logto'
+ # - 'APP_URL=http://localhost:3210'
+ - 'APP_URL=https://lobe.example.com'
+
+ - 'NEXT_AUTH_SSO_PROVIDERS=casdoor'
- 'KEY_VAULTS_SECRET=Kix2wcUONd4CX51E/ZPAd36BqM4wzJgKjPtz2sGztqQ='
- 'NEXT_AUTH_SECRET=NX2kaPE923dt6BL2U8e9oSre5RfoT7hg'
- - 'NEXTAUTH_URL=http://localhost:${LOBE_PORT}/api/auth'
- - 'LOGTO_ISSUER=http://localhost:${LOGTO_PORT}/oidc'
+ # - 'AUTH_URL=http://localhost:${LOBE_PORT}/api/auth'
+ - 'AUTH_URL=https://lobe.example.com/api/auth'
+
+ # - 'AUTH_CASDOOR_ISSUER=http://localhost:${CASDOOR_PORT}'
+ - 'AUTH_CASDOOR_ISSUER=https://auth.example.com'
+
- 'DATABASE_URL=postgresql://postgres:${POSTGRES_PASSWORD}@postgresql:5432/${LOBE_DB_NAME}'
- - 'S3_ENDPOINT=http://localhost:${MINIO_PORT}'
+ # - 'S3_ENDPOINT=http://localhost:${MINIO_PORT}'
+ - 'S3_ENDPOINT=https://minio.example.com'
+
- 'S3_BUCKET=${MINIO_LOBE_BUCKET}'
- - 'S3_PUBLIC_DOMAIN=http://localhost:${MINIO_PORT}'
+ # - 'S3_PUBLIC_DOMAIN=http://localhost:${MINIO_PORT}'
+ - 'S3_PUBLIC_DOMAIN=https://minio.example.com'
+
- 'S3_ENABLE_PATH_STYLE=1'
+ - 'LLM_VISION_IMAGE_USE_BASE64=1'
env_file:
- .env
restart: always
@@ -486,190 +816,11 @@ volumes:
networks:
lobe-network:
driver: bridge
-
-```
-
-### Deploying to Production
-
-#### `.env`
-
-```sh
-# Required: LobeChat domain for tRPC calls
-# Ensure this domain is whitelisted in your NextAuth providers and S3 service CORS settings
-APP_URL=https://lobe.example.com/
-
-# Postgres related environment variables
-# Required: Secret key for encrypting sensitive information. Generate with: openssl rand -base64 32
-KEY_VAULTS_SECRET=Kix2wcUONd4CX51E/ZPAd36BqM4wzJgKjPtz2sGztqQ=
-# Required: Postgres database connection string
-# Format: postgresql://username:password@host:port/dbname
-# If using Docker, you can use the container name as the host
-DATABASE_URL=postgresql://postgres:uWNZugjBqixf8dxC@postgresql:5432/lobe
-
-# NEXT_AUTH related environment variables
-# Supports auth0, Azure AD, GitHub, Authentik, Zitadel, Logto, etc.
-# For supported providers, see: https://lobehub.com/docs/self-hosting/advanced/auth#next-auth
-# If you have ACCESS_CODE, please remove it. We use NEXT_AUTH as the sole authentication source
-# Required: NextAuth secret key. Generate with: openssl rand -base64 32
-NEXT_AUTH_SECRET=NX2kaPE923dt6BL2U8e9oSre5RfoT7hg
-# Required: Specify the authentication provider (e.g., Logto)
-NEXT_AUTH_SSO_PROVIDERS=logto
-# Required: NextAuth URL for callbacks
-NEXTAUTH_URL=https://lobe.example.com/api/auth
-
-# NextAuth providers configuration (example using Logto)
-# For other providers, see: https://lobehub.com/docs/self-hosting/environment-variables/auth
-LOGTO_CLIENT_ID=YOUR_LOGTO_CLIENT_ID
-LOGTO_CLIENT_SECRET=YOUR_LOGTO_CLIENT_SECRET
-LOGTO_ISSUER=https://lobe-auth-api.example.com/oidc
-
-# Proxy settings (if needed, e.g., when using GitHub as an auth provider)
-# HTTP_PROXY=http://localhost:7890
-# HTTPS_PROXY=http://localhost:7890
-
-# S3 related environment variables (example using MinIO)
-# Required: S3 Access Key ID (for MinIO, invalid until manually created in MinIO UI)
-S3_ACCESS_KEY_ID=YOUR_S3_ACCESS_KEY_ID
-# Required: S3 Secret Access Key (for MinIO, invalid until manually created in MinIO UI)
-S3_SECRET_ACCESS_KEY=YOUR_S3_SECRET_ACCESS_KEY
-# Required: S3 Endpoint for server/client connections to S3 API
-S3_ENDPOINT=https://lobe-s3-api.example.com
-# Required: S3 Bucket (invalid until manually created in MinIO UI)
-S3_BUCKET=lobe
-# Required: S3 Public Domain for client access to unstructured data
-S3_PUBLIC_DOMAIN=https://lobe-s3-api.example.com
-# Optional: S3 Enable Path Style
-# Use 0 for mainstream S3 cloud providers; use 1 for self-hosted MinIO
-# See: https://lobehub.com/docs/self-hosting/advanced/s3#s-3-enable-path-style
-S3_ENABLE_PATH_STYLE=1
-
-# Other basic environment variables (as needed)
-# See: https://lobehub.com/docs/self-hosting/environment-variables/basic
-# Note: For server versions, the API must support embedding models (OpenAI text-embedding-3-small) for file processing
-# You don't need to specify this model in OPENAI_MODEL_LIST
-# OPENAI_API_KEY=sk-xxxx
-# OPENAI_PROXY_URL=https://api.openai.com/v1
-# OPENAI_MODEL_LIST=...
-
-```
-
-#### `docker-compose.yml`
-
-```yaml
-services:
- postgresql:
- image: pgvector/pgvector:pg16
- container_name: lobe-postgres
- ports:
- - '5432:5432'
- volumes:
- - './data:/var/lib/postgresql/data'
- environment:
- - 'POSTGRES_DB=lobe'
- - 'POSTGRES_PASSWORD=uWNZugjBqixf8dxC'
- healthcheck:
- test: ['CMD-SHELL', 'pg_isready -U postgres']
- interval: 5s
- timeout: 5s
- retries: 5
- restart: always
-
- minio:
- image: minio/minio
- container_name: lobe-minio
- ports:
- - '9000:9000'
- - '9001:9001'
- volumes:
- - './s3_data:/etc/minio/data'
- environment:
- - 'MINIO_ROOT_USER=YOUR_MINIO_USER'
- - 'MINIO_ROOT_PASSWORD=YOUR_MINIO_PASSWORD'
- - 'MINIO_DOMAIN=lobe-s3-api.example.com'
- - 'MINIO_API_CORS_ALLOW_ORIGIN=https://lobe.example.com' # Your LobeChat's domain name.
- restart: always
- command: >
- server /etc/minio/data --address ":9000" --console-address ":9001"
-
- logto:
- image: svhd/logto
- container_name: lobe-logto
- ports:
- - '3001:3001'
- - '3002:3002'
- depends_on:
- postgresql:
- condition: service_healthy
- environment:
- - 'TRUST_PROXY_HEADER=1'
- - 'DB_URL=postgresql://postgres:uWNZugjBqixf8dxC@postgresql:5432/logto'
- - 'ENDPOINT=https://lobe-auth-api.example.com'
- - 'ADMIN_ENDPOINT=https://lobe-auth-ui.example.com'
- entrypoint: ['sh', '-c', 'npm run cli db seed -- --swe && npm start']
-
- lobe:
- image: lobehub/lobe-chat-database
- container_name: lobe-database
- ports:
- - '3210:3210'
- depends_on:
- - postgresql
- - minio
- - logto
- env_file:
- - .env
- restart: always
-
-volumes:
- data:
- driver: local
- s3_data:
- driver: local
-
-```
-
-#### `minio-bucket-config.json`
-
-```json
-{
- "Statement": [
- {
- "Effect": "Allow",
- "Principal": {
- "AWS": ["*"]
- },
- "Action": ["s3:GetBucketLocation"],
- "Resource": ["arn:aws:s3:::lobe"]
- },
- {
- "Effect": "Allow",
- "Principal": {
- "AWS": ["*"]
- },
- "Action": ["s3:ListBucket"],
- "Resource": ["arn:aws:s3:::lobe"],
- "Condition": {
- "StringEquals": {
- "s3:prefix": ["files/*"]
- }
- }
- },
- {
- "Effect": "Allow",
- "Principal": {
- "AWS": ["*"]
- },
- "Action": ["s3:PutObject", "s3:DeleteObject", "s3:GetObject"],
- "Resource": ["arn:aws:s3:::lobe/files/**"]
- }
- ],
- "Version": "2012-10-17"
-}
```
[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat-database?color=45cc11&labelColor=black&style=flat-square
[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
-[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat-database?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat-database?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square&sort=semver
[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
-[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square&sort=semver
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.zh-CN.mdx
index a518144..db56a49 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/docker-compose.zh-CN.mdx
@@ -13,26 +13,317 @@ tags:
-This article assumes that you are familiar with the basic principles and processes of deploying the LobeChat server database version, so it only includes content related to core environment variable configuration. If you are not familiar with the deployment principles of the LobeChat server database version, please refer to [Deploying Server Database](/docs/self-hosting/server-database) first.
+ This article assumes that you are familiar with the basic principles and processes of deploying
+ the LobeChat server database version, so it only includes content related to core environment
+ variable configuration. If you are not familiar with the deployment principles of the LobeChat
+ server database version, please refer to [Deploying Server
+ Database](/docs/self-hosting/server-database) first.
Due to the inability to expose `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` using Docker environment variables, you cannot use Clerk as an authentication service when deploying LobeChat using Docker / Docker Compose.
-If you do need Clerk as an authentication service, you might consider deploying using Vercel or building your own image.
-
+ If you do need Clerk as an authentication service, you might consider deploying using Vercel or building your own image.
## Deploying on a Linux Server
@@ -36,90 +39,94 @@ If you do need Clerk as an authentication service, you might consider deploying
Here is the process for deploying the LobeChat server database version on a Linux server:
-
-### Create a Postgres Database Instance
-
-Please create a Postgres database instance with the PGVector plugin according to your needs, for example:
-
-```sh
-docker network create pg
-
-docker run --name my-postgres --network pg -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -d pgvector/pgvector:pg16
-```
-
-The above command will create a PG instance named `my-postgres` on the network `pg`, where `pgvector/pgvector:pg16` is a Postgres 16 image with the pgvector plugin installed by default.
-
-
-The pgvector plugin provides vector search capabilities for Postgres, which is an important component for LobeChat to implement RAG.
-
-
-
-The above command does not specify a persistent storage location for the pg instance, so it is only for testing/demonstration purposes. Please configure persistent storage for production environments.
-
-
-### Create a file named `lobe-chat.env` to store environment variables:
-
-```shell
-# Website domain
-APP_URL=https://your-prod-domain.com
-
-# DB required environment variables
-KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
-# Postgres database connection string
-# Format: postgres://username:password@host:port/dbname; if your pg instance is a Docker container, use the container name
-DATABASE_URL=postgres://postgres:mysecretpassword@my-postgres:5432/postgres
-
-# NEXT_AUTH related, can use auth0, Azure AD, GitHub, Authentik, zitadel, etc. If you have other access requirements, feel free to submit a PR
-NEXT_AUTH_SECRET=3904039cd41ea1bdf6c93db0db96e250
-NEXT_AUTH_SSO_PROVIDERS=auth0
-NEXTAUTH_URL=https://your-prod-domain.com/api/auth
-AUTH0_CLIENT_ID=xxxxxx
-AUTH0_CLIENT_SECRET=cSX_xxxxx
-AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com
-
-# S3 related
-S3_ACCESS_KEY_ID=xxxxxxxxxx
-S3_SECRET_ACCESS_KEY=xxxxxxxxxx
-S3_ENDPOINT=https://xxxxxxxxxx.r2.cloudflarestorage.com
-S3_BUCKET=lobechat
-S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com
-
-# Other environment variables, as needed. You can refer to the environment variables configuration for the client version, making sure not to have ACCESS_CODE.
-# OPENAI_API_KEY=sk-xxxx
-# OPENAI_PROXY_URL=https://api.openai.com/v1
-# OPENAI_MODEL_LIST=...
-```
-
-### Start the lobe-chat-database Docker image
-
-```sh
-docker run -it -d -p 3210:3210 --network pg --env-file lobe-chat.env --name lobe-chat-database lobehub/lobe-chat-database
-```
-
-You can use the following command to check the logs:
-
-```sh
-docker logs -f lobe-chat-database
-```
-
-If you see the following logs in the container, it means it has started successfully:
-
-```log
-[Database] Start to migration...
-✅ database migration pass.
--------------------------------------
- ▲ Next.js 14.x.x
- - Local: http://localhost:3210
- - Network: http://0.0.0.0:3210
-
- ✓ Starting...
- ✓ Ready in 95ms
-```
-
+ ### Create a Postgres Database Instance
+
+ Please create a Postgres database instance with the PGVector plugin according to your needs, for example:
+
+ ```sh
+ docker network create pg
+
+ docker run --name my-postgres --network pg -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -d pgvector/pgvector:pg16
+ ```
+
+ The above command will create a PG instance named `my-postgres` on the network `pg`, where `pgvector/pgvector:pg16` is a Postgres 16 image with the pgvector plugin installed by default.
+
+
+ The pgvector plugin provides vector search capabilities for Postgres, which is an important
+ component for LobeChat to implement RAG.
+
+
+
+ The above command does not specify a persistent storage location for the pg instance, so it is
+ only for testing/demonstration purposes. Please configure persistent storage for production
+ environments.
+
+
+ ### Create a file named `lobe-chat.env` to store environment variables:
+
+ ```shell
+ # Website domain
+ APP_URL=https://your-prod-domain.com
+
+ # DB required environment variables
+ KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
+ # Postgres database connection string
+ # Format: postgres://username:password@host:port/dbname; if your pg instance is a Docker container, use the container name
+ DATABASE_URL=postgres://postgres:mysecretpassword@my-postgres:5432/postgres
+
+ # NEXT_AUTH related, can use auth0, Azure AD, GitHub, Authentik, zitadel, etc. If you have other access requirements, feel free to submit a PR
+ NEXT_AUTH_SECRET=3904039cd41ea1bdf6c93db0db96e250
+ NEXT_AUTH_SSO_PROVIDERS=auth0
+ NEXTAUTH_URL=https://your-prod-domain.com/api/auth
+ AUTH_AUTH0_ID=xxxxxx
+ AUTH_AUTH0_SECRET=cSX_xxxxx
+ AUTH_AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com
+
+ # S3 related
+ S3_ACCESS_KEY_ID=xxxxxxxxxx
+ S3_SECRET_ACCESS_KEY=xxxxxxxxxx
+ S3_ENDPOINT=https://xxxxxxxxxx.r2.cloudflarestorage.com
+ S3_BUCKET=lobechat
+ S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com
+
+ # Other environment variables, as needed. You can refer to the environment variables configuration for the client version, making sure not to have ACCESS_CODE.
+ # OPENAI_API_KEY=sk-xxxx
+ # OPENAI_PROXY_URL=https://api.openai.com/v1
+ # OPENAI_MODEL_LIST=...
+ ```
+
+ ### Start the lobe-chat-database Docker image
+
+ ```sh
+ docker run -it -d -p 3210:3210 --network pg --env-file lobe-chat.env --name lobe-chat-database lobehub/lobe-chat-database
+ ```
+
+ You can use the following command to check the logs:
+
+ ```sh
+ docker logs -f lobe-chat-database
+ ```
+
+ If you see the following logs in the container, it means it has started successfully:
+
+ ```log
+ [Database] Start to migration...
+ ✅ database migration pass.
+ -------------------------------------
+ ▲ Next.js 14.x.x
+ - Local: http://localhost:3210
+ - Network: http://0.0.0.0:3210
+
+ ✓ Starting...
+ ✓ Ready in 95ms
+ ```
-In our official Docker image, the database schema migration is automatically executed before starting the image. We ensure stability from an empty database to all tables being formally available. Therefore, we recommend using an empty table instance for your database to avoid the cost of manually maintaining table structure migration.
+ In our official Docker image, the database schema migration is automatically executed before
+ starting the image. We ensure stability from an empty database to all tables being formally
+ available. Therefore, we recommend using an empty table instance for your database to avoid the
+ cost of manually maintaining table structure migration.
## Using Locally (Mac / Windows)
@@ -136,9 +143,9 @@ $ docker run -it -d --name lobe-chat-database -p 3210:3210 \
-e KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk= \
-e NEXT_AUTH_SECRET=3904039cd41ea1bdf6c93db0db96e250 \
-e NEXT_AUTH_SSO_PROVIDERS=auth0 \
- -e AUTH0_CLIENT_ID=xxxxxx \
- -e AUTH0_CLIENT_SECRET=cSX_xxxxx \
- -e AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com \
+ -e AUTH_AUTH0_ID=xxxxxx \
+ -e AUTH_AUTH0_SECRET=cSX_xxxxx \
+ -e AUTH_AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com \
-e APP_URL=http://localhost:3210 \
-e NEXTAUTH_URL=http://localhost:3210/api/auth \
-e S3_ACCESS_KEY_ID=xxxxxxxxxx \
@@ -150,12 +157,14 @@ $ docker run -it -d --name lobe-chat-database -p 3210:3210 \
```
-`Docker` uses a virtual machine solution on `Windows` and `macOS`. If you use `localhost` / `127.0.0.1`, it will refer to the container's `localhost`. In this case, try using `host.docker.internal` instead of `localhost`.
+ `Docker` uses a virtual machine solution on `Windows` and `macOS`. If you use `localhost` /
+ `127.0.0.1`, it will refer to the container's `localhost`. In this case, try using
+ `host.docker.internal` instead of `localhost`.
[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat-database?color=45cc11&labelColor=black&style=flat-square
[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
-[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat-database?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat-database?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square&sort=semver
[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
-[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square&sort=semver
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/docker.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/docker.zh-CN.mdx
index 279437d..5004027 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/docker.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/docker.zh-CN.mdx
@@ -13,16 +13,17 @@ tags:
本文已经假定你了解了 LobeChat 服务端数据库版本(下简称 DB
版)的部署基本原理和流程,因此只包含核心环境变量配置的内容。如果你还不了解 LobeChat DB
版的部署原理,请先查阅 [使用服务端数据库部署](/zh/docs/self-hosting/server-database) 。
+ 此外,针对国内的腾讯云储存桶用户,可查询[配置腾讯云 COS
+ 存储服务](/zh/docs/self-hosting/advanced/s3/tencent-cloud)。
@@ -37,90 +38,90 @@ tags:
以下是在 Linux 服务器上部署 LobeChat DB 版的流程:
-
-### 创建 Postgres 数据库实例
-
-请按照你自己的诉求创建一个带有 PGVector 插件的 Postgres 数据库实例,例如:
-
-```sh
-docker network create pg
-
-docker run --name my-postgres --network pg -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -d pgvector/pgvector:pg16
-```
-
-上述指令会创建一个名为 `my-postgres`,并且网络为 `pg` 的 PG 实例,其中 `pgvector/pgvector:pg16` 是一个 Postgres 16 的镜像,且默认安装了 pgvector 插件。
-
-
- pgvector 插件为 Postgres 提供了向量搜索的能力,是 LobeChat 实现 RAG 的重要构件之一。
-
-
-
- 以上指令得到的 pg
- 实例并没有指定持久化存储位置,因此仅用于测试/演示,生产环境请自行配置持久化存储。
-
-
-### 创建名为 `lobe-chat.env` 文件用于存放环境变量:
-
-```shell
-# 网站域名
-APP_URL=https://your-prod-domain.com
-
-# DB 必须的环境变量
-# 用于加密敏感信息的密钥,可以使用 openssl rand -base64 32 生成
-KEY_VAULTS_SECRET='jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk='
-# Postgres 数据库连接字符串
-# 格式:postgres://username:password@host:port/dbname,如果你的 pg 实例为 Docker 容器,请使用容器名
-DATABASE_URL=postgres://postgres:mysecretpassword@my-postgres:5432/postgres
-
-# NEXT_AUTH 相关,可以使用 auth0、Azure AD、GitHub、Authentik、zitadel 等,如有其他接入诉求欢迎提 PR
-NEXT_AUTH_SECRET=3904039cd41ea1bdf6c93db0db96e250
-NEXT_AUTH_SSO_PROVIDERS=auth0
-NEXTAUTH_URL=https://your-prod-domain.com/api/auth
-AUTH0_CLIENT_ID=xxxxxx
-AUTH0_CLIENT_SECRET=cSX_xxxxx
-AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com
-
-# S3 相关
-S3_ACCESS_KEY_ID=xxxxxxxxxx
-S3_SECRET_ACCESS_KEY=xxxxxxxxxx
-S3_ENDPOINT=https://xxxxxxxxxx.r2.cloudflarestorage.com # 用于 S3 API 访问的域名
-S3_BUCKET=lobechat
-S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com # 用于外网访问 S3 的公共域名,需配置 CORS
-# S3_REGION=ap-chengdu # 如果需要指定地域
-
-# 其他环境变量,视需求而定
-# OPENAI_API_KEY=sk-xxxx
-# OPENAI_PROXY_URL=https://api.openai.com/v1
-# OPENAI_MODEL_LIST=...
-# ...
-```
-
-### 启动 lobe-chat-database docker 镜像
-
-```sh
-docker run -it -d -p 3210:3210 --network pg --env-file lobe-chat.env --name lobe-chat-database lobehub/lobe-chat-database
-```
-
-你可以使用下述指令检查日志:
-
-```sh
-docker logs -f lobe-chat-database
-```
-
-如果你在容器中看到了以下日志,则说明已经启动成功:
-
-```log
-[Database] Start to migration...
-✅ database migration pass.
--------------------------------------
- ▲ Next.js 14.x.x
- - Local: http://localhost:3210
- - Network: http://0.0.0.0:3210
-
- ✓ Starting...
- ✓ Ready in 95ms
-```
-
+ ### 创建 Postgres 数据库实例
+
+ 请按照你自己的诉求创建一个带有 PGVector 插件的 Postgres 数据库实例,例如:
+
+ ```sh
+ docker network create pg
+
+ docker run --name my-postgres --network pg -e POSTGRES_PASSWORD=mysecretpassword -p 5432:5432 -d pgvector/pgvector:pg16
+ ```
+
+ 上述指令会创建一个名为 `my-postgres`,并且网络为 `pg` 的 PG 实例,其中 `pgvector/pgvector:pg16` 是一个 Postgres 16 的镜像,且默认安装了 pgvector 插件。
+
+
+ pgvector 插件为 Postgres 提供了向量搜索的能力,是 LobeChat 实现 RAG 的重要构件之一。
+
+
+
+ 以上指令得到的 pg
+ 实例并没有指定持久化存储位置,因此仅用于测试 / 演示,生产环境请自行配置持久化存储。
+
+
+ ### 创建名为 `lobe-chat.env` 文件用于存放环境变量:
+
+ ```shell
+ # 网站域名
+ APP_URL=https://your-prod-domain.com
+
+ # DB 必须的环境变量
+ # 用于加密敏感信息的密钥,可以使用 openssl rand -base64 32 生成
+ KEY_VAULTS_SECRET='jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk='
+ # Postgres 数据库连接字符串
+ # 格式:postgres://username:password@host:port/dbname,如果你的 pg 实例为 Docker 容器,请使用容器名
+ DATABASE_URL=postgres://postgres:mysecretpassword@my-postgres:5432/postgres
+
+ # NEXT_AUTH 相关,可以使用 auth0、Azure AD、GitHub、Authentik、zitadel 等,如有其他接入诉求欢迎提 PR
+ NEXT_AUTH_SECRET=3904039cd41ea1bdf6c93db0db96e250
+ NEXT_AUTH_SSO_PROVIDERS=auth0
+ NEXTAUTH_URL=https://your-prod-domain.com/api/auth
+ AUTH_AUTH0_ID=xxxxxx
+ AUTH_AUTH0_SECRET=cSX_xxxxx
+ AUTH_AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com
+
+ # S3 相关
+ S3_ACCESS_KEY_ID=xxxxxxxxxx
+ S3_SECRET_ACCESS_KEY=xxxxxxxxxx
+ # 用于 S3 API 访问的域名
+ S3_ENDPOINT=https://xxxxxxxxxx.r2.cloudflarestorage.com
+ S3_BUCKET=lobechat
+ # 用于外网访问 S3 的公共域名,需配置 CORS
+ S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com
+ # S3_REGION=ap-chengdu # 如果需要指定地域
+
+ # 其他环境变量,视需求而定
+ # OPENAI_API_KEY=sk-xxxx
+ # OPENAI_PROXY_URL=https://api.openai.com/v1
+ # OPENAI_MODEL_LIST=...
+ # ...
+ ```
+
+ ### 启动 lobe-chat-database docker 镜像
+
+ ```sh
+ docker run -it -d -p 3210:3210 --network pg --env-file lobe-chat.env --name lobe-chat-database lobehub/lobe-chat-database
+ ```
+
+ 你可以使用下述指令检查日志:
+
+ ```sh
+ docker logs -f lobe-chat-database
+ ```
+
+ 如果你在容器中看到了以下日志,则说明已经启动成功:
+
+ ```log
+ [Database] Start to migration...
+ ✅ database migration pass.
+ -------------------------------------
+ ▲ Next.js 14.x.x
+ - Local: http://localhost:3210
+ - Network: http://0.0.0.0:3210
+
+ ✓ Starting...
+ ✓ Ready in 95ms
+ ```
@@ -144,9 +145,9 @@ $ docker run -it -d --name lobe-chat-database -p 3210:3210 \
-e KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk= \
-e NEXT_AUTH_SECRET=3904039cd41ea1bdf6c93db0db96e250 \
-e NEXT_AUTH_SSO_PROVIDERS=auth0 \
- -e AUTH0_CLIENT_ID=xxxxxx \
- -e AUTH0_CLIENT_SECRET=cSX_xxxxx \
- -e AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com \
+ -e AUTH_AUTH0_ID=xxxxxx \
+ -e AUTH_AUTH0_SECRET=cSX_xxxxx \
+ -e AUTH_AUTH0_ISSUER=https://lobe-chat-demo.us.auth0.com \
-e APP_URL=http://localhost:3210 \
-e NEXTAUTH_URL=http://localhost:3210/api/auth \
-e S3_ACCESS_KEY_ID=xxxxxxxxxx \
@@ -165,6 +166,6 @@ $ docker run -it -d --name lobe-chat-database -p 3210:3210 \
[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat-database?color=45cc11&labelColor=black&style=flat-square
[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
-[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat-database?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat-database?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square&sort=semver
[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat-database
-[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square&sort=semver
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/dokploy.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/dokploy.mdx
new file mode 100644
index 0000000..849e403
--- /dev/null
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/dokploy.mdx
@@ -0,0 +1,137 @@
+---
+title: Deploy LobeChat with database on Dokploy
+description: >-
+ Learn how to deploy LobeChat with database on Dokploy with ease, including:
+ database, authentication and S3 storage service.
+tags:
+ - Deploy LobeChat
+ - Vercel Deployment
+ - OpenAI API Key
+ - Custom Domain Binding
+---
+
+# Deploying Server Database Version on Dokploy.
+
+This article will detail how to deploy the server database version of LobeChat.
+
+## 1. Preparation Work
+
+### Deploy Dokploy and configure related settings.
+
+```shell
+curl -sSL https://dokploy.com/install.sh | sh
+```
+
+1. Connect your GitHub to Dokploy in the Settings / Git section according to the prompt.
+
+
+
+2. Enter the Projects interface to create a Project.
+
+
+
+### Configure S3 Storage Service
+
+In the server-side database, we need to configure the S3 storage service to store files. For detailed configuration instructions, please refer to the section [Configure S3 Storage Service](https://lobehub.com/docs/self-hosting/server-database/vercel#3-configure-s-3-storage-service) in the Vercel deployment guide。After the configuration is complete, you will obtain the following environment variables:
+
+```shell
+S3_ACCESS_KEY_ID=
+S3_SECRET_ACCESS_KEY=
+S3_ENDPOINT=
+S3_BUCKET=
+S3_PUBLIC_DOMAIN=
+S3_ENABLE_PATH_STYLE=
+```
+
+### Configure the Clerk authentication service.
+
+Obtain the three environment variables: `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY`, `CLERK_SECRET_KEY`, and `CLERK_WEBHOOK_SECRET`. For detailed configuration steps for Clerk, please refer to the section [Configure Authentication Service](https://lobehub.com/docs/self-hosting/server-database/vercel#2-configure-authentication-service) in the Vercel deployment guide.
+
+```shell
+NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
+CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
+CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
+```
+
+## 2. Deploying the database on Dokploy
+
+Enter the previously created Project, click on Create Service, and select Database. In the Database interface, choose PostgreSQL, then set the database name, user, and password. In the Docker image field, enter `pgvector/pgvector:pg17`, and finally click Create to create the database.
+
+
+
+Enter the created database and set an unused port in External Credentials to allow external access; otherwise, LobeChat will not be able to connect to the database.
+You can view the Postgres database connection URL in External Host, as shown below:
+
+```shell
+postgresql://postgres:wAbLxfXSwkxxxxxx@45.577.281.48:5432/postgres
+```
+
+Finally, click Deploy to deploy the database.
+
+
+
+## Deploy LobeChat on Dokploy.
+
+Click "Create Service", select "Application", and create the LobeChat application.
+
+
+
+Enter the created LobeChat application, select the forked lobe-chat project and branch, and click Save to save.
+
+
+
+Switch to the Environment section, fill in the environment variables, and click Save.
+
+
+
+```shell
+# Environment variables required for building
+NIXPACKS_PKGS="pnpm bun"
+NIXPACKS_INSTALL_CMD="pnpm install"
+NIXPACKS_BUILD_CMD="pnpm run build"
+NIXPACKS_START_CMD="pnpm start"
+
+APP_URL=
+
+# Set the service mode to server
+NEXT_PUBLIC_SERVICE_MODE=server
+
+# Configuration related to Postgres database
+DATABASE_DRIVER=node
+DATABASE_URL=
+
+# You can use openssl rand -base64 32 to generate a random 32-character string as a key.
+KEY_VAULTS_SECRET=
+
+# Clerk related configuration
+NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=
+CLERK_SECRET_KEY=
+CLERK_WEBHOOK_SECRET=
+
+# S3 related configuration
+S3_ACCESS_KEY_ID=
+S3_SECRET_ACCESS_KEY=
+S3_ENDPOINT=
+S3_BUCKET=
+S3_PUBLIC_DOMAIN=
+S3_ENABLE_PATH_STYLE=
+
+# OpenAI related configuration
+OPENAI_API_KEY=
+OPENAI_MODEL_LIST=
+OPENAI_PROXY_URL=
+```
+
+After adding the environment variables and saving, click Deploy to initiate the deployment. You can check the deployment progress and log information under Deployments.
+
+
+
+After a successful deployment, bind your own domain to your LobeChat application and request a certificate on the Domains page.
+
+
+
+## Check if LobeChat is working properly.
+
+Go to your LobeChat website, and if you click on the login button in the upper left corner and the login pop-up appears normally, it means you have configured it successfully. Enjoy it to the fullest!
+
+
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/dokploy.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/dokploy.zh-CN.mdx
new file mode 100644
index 0000000..c8f2842
--- /dev/null
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/dokploy.zh-CN.mdx
@@ -0,0 +1,138 @@
+---
+title: 在 Dokploy 上部署 LobeChat 的服务端数据库版本
+description: 本文详细介绍如何在 Dokploy 中部署服务端数据库版 LobeChat,包括数据库配置、身份验证服务配置的设置步骤。
+tags:
+ - 服务端数据库
+ - Postgres
+ - Clerk
+ - Dokploy部署
+ - 数据库配置
+ - 身份验证服务
+ - 环境变量配置
+---
+
+# 在 Dokploy 上部署服务端数据库版
+
+本文将详细介绍如何在 Dokploy 中部署服务端数据库版 LobeChat。
+
+## 一、准备工作
+
+### 部署 Dokploy 并进行相关设置
+
+```shell
+curl -sSL https://dokploy.com/install.sh | sh
+```
+
+1. 在 Dokploy 的 Settings / Git 处根据提示将 Github 绑定到 Dokploy
+
+
+
+2. 进入 Projects 界面创建一个 Project
+
+
+
+### 配置 S3 存储服务
+
+在服务端数据库中我们需要配置 S3 存储服务来存储文件,详细配置教程请参考 使用 Vercel 部署中 [配置 S3 储存服务](https://lobehub.com/zh/docs/self-hosting/server-database/vercel#%E4%B8%89%E3%80%81-%E9%85%8D%E7%BD%AE-s-3-%E5%AD%98%E5%82%A8%E6%9C%8D%E5%8A%A1)。配置完成后你将获得以下环境变量:
+
+```shell
+S3_ACCESS_KEY_ID=
+S3_SECRET_ACCESS_KEY=
+S3_ENDPOINT=
+S3_BUCKET=
+S3_PUBLIC_DOMAIN=
+S3_ENABLE_PATH_STYLE=
+```
+
+### 配置 Clerk 身份验证服务
+
+获取 `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` 、`CLERK_SECRET_KEY` 、`CLERK_WEBHOOK_SECRET` 这三个环境变量,Clerk 的详细配置流程请参考 使用 Vercel 部署中 [配置身份验证服务](https://lobehub.com/zh/docs/self-hosting/server-database/vercel#二、-配置身份验证服务)
+
+```shell
+NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
+CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
+CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
+```
+
+## 二、在 Dokploy 上部署数据库
+
+进入前面创建的 Project,点击 Create Service 选择 Database,在 Database 界面选择 PostgreSQL ,然后设置数据库名、用户、密码,在 Docker image 中填入 `pgvector/pgvector:pg17` 最后点击 Create 创建数据库。
+
+
+
+进入创建的数据库,在 External Credentials 设置一个未被占用的端口,使其能能通过外部访问,否则 LobeChat 将无法连接到该数据库。
+你可以在 External Host 查看 Postgres 数据库连接 URL ,如下:
+
+```shell
+postgresql://postgres:wAbLxfXSwkxxxxxx@45.577.281.48:5432/postgres
+```
+
+最后点击 Deploy 部署数据库
+
+
+
+## 在 Dokploy 上部署 LobeChat
+
+点击 Create Service 选择 Application,创建 LobeChat 应用
+
+
+
+进入创建的 LobeChat 应用,选择你 fork 的 lobe-chat 项目及分支,点击 Save 保存
+
+
+
+切换到 Environment ,在其中填入环境变量,点击保存。
+
+
+
+```shell
+# 构建所必需的环境变量
+NIXPACKS_PKGS="pnpm bun"
+NIXPACKS_INSTALL_CMD="pnpm install"
+NIXPACKS_BUILD_CMD="pnpm run build"
+NIXPACKS_START_CMD="pnpm start"
+
+APP_URL=
+
+# 指定服务模式为 server
+NEXT_PUBLIC_SERVICE_MODE=server
+
+# Postgres 数据库相关配置
+DATABASE_DRIVER=node
+DATABASE_URL=
+
+# 你可以使用 openssl rand -base64 32 生成一个随机的 32 位字符串作为密钥。
+KEY_VAULTS_SECRET=
+
+# Clerk 相关配置
+NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=
+CLERK_SECRET_KEY=
+CLERK_WEBHOOK_SECRET=
+
+# S3 相关配置
+S3_ACCESS_KEY_ID=
+S3_SECRET_ACCESS_KEY=
+S3_ENDPOINT=
+S3_BUCKET=
+S3_PUBLIC_DOMAIN=
+S3_ENABLE_PATH_STYLE=
+
+# OpenAI 相关配置
+OPENAI_API_KEY=
+OPENAI_MODEL_LIST=
+OPENAI_PROXY_URL=
+```
+
+添加完环境变量并保存后,点击 Deploy 进行部署,你可以在 Deployments 处查看部署进程及日志信息
+
+
+
+部署成功后在 Domains 页面,为你的 LobeChat 应用绑定自己的域名并申请证书。
+
+
+
+## 验证 LobeChat 是否正常工作
+
+进入你的 LobeChat 网址,如果你点击左上角登录,可以正常显示登录弹窗,那么说明你已经配置成功了,尽情享用吧~
+
+
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/netlify.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/netlify.mdx
index b637e20..bcc0e0f 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/netlify.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/netlify.mdx
@@ -11,4 +11,3 @@ tags:
# Deploy LobeChat with Database on Netlify
TODO
-
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/railway.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/railway.mdx
index f213064..d59f124 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/railway.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/railway.mdx
@@ -11,4 +11,3 @@ tags:
# Deploy LobeChat with Database on Railway
TODO
-
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.mdx
index d29b715..ee95f96 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.mdx
@@ -1,6 +1,8 @@
---
title: Deploy LobeChat with Database on RepoCloud
-description: Learn how to deploy LobeChat on RepoCloud with ease, including: database, authentication and S3 storage service.
+description: >-
+ Learn how to deploy LobeChat on RepoCloud with ease, including database,
+ authentication and S3 storage service.
tags:
- Deploy LobeChat
- RepoCloud Deployment
@@ -17,16 +19,15 @@ If you want to deploy LobeChat Database Edition on RepoCloud, you can follow the
### Prepare your OpenAI API Key
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+ Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-### One-click to deploy
+ ### One-click to deploy
-[](https://repocloud.io/details/?app_id=248)
+ [](https://repocloud.io/details/?app_id=248)
-### Once deployed, you can start using it
+ ### Once deployed, you can start using it
-### Bind a custom domain (optional)
-
-You can use the subdomain provided by RepoCloud, or choose to bind a custom domain. Currently, the domains provided by RepoCloud have not been contaminated, and most regions can connect directly.
+ ### Bind a custom domain (optional)
+ You can use the subdomain provided by RepoCloud, or choose to bind a custom domain. Currently, the domains provided by RepoCloud have not been contaminated, and most regions can connect directly.
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.zh-CN.mdx
index 00efa59..dd9bfbc 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/repocloud.zh-CN.mdx
@@ -1,6 +1,6 @@
---
title: 在 RepoCloud 上部署 LobeChat 数据库版
-description: 学习如何在RepoCloud上部署LobeChat应用,包括准备OpenAI API Key、点击部署按钮、绑定自定义域名等操作。
+description: 学习如何在 RepoCloud 上部署 LobeChat 应用,包括准备 OpenAI API Key、点击部署按钮、绑定自定义域名等操作。
tags:
- RepoCloud
- LobeChat
@@ -9,6 +9,24 @@ tags:
- 自定义域名
---
-# 使用 RepoCloud 部署 LobeChat 数据库版
+# 在 RepoCloud 上部署 LobeChat 数据库版
-TODO
+如果您想在 RepoCloud 上部署 LobeChat 数据库版,可以按照以下步骤进行操作:
+
+## RepoCloud 部署流程
+
+
+ ### 准备您的 OpenAI API 密钥
+
+ 请访问 [OpenAI API 密钥](https://platform.openai.com/account/api-keys) 获取您的 OpenAI API 密钥。
+
+ ### 一键部署
+
+ [](https://repocloud.io/details/?app_id=248)
+
+ ### 部署完成后,您可以开始使用
+
+ ### 绑定自定义域名(可选)
+
+ 您可以使用 RepoCloud 提供的子域名,或选择绑定自定义域名。目前,RepoCloud 提供的域名尚未被污染,大多数地区可以直接连接。
+
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/sealos.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/sealos.mdx
index 92a5135..f75c709 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/sealos.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/sealos.mdx
@@ -1,12 +1,98 @@
---
-title: Deploy LobeChat on SealOS
+title: Deploy Lobe Chat Database Version on Sealos
description: >-
- Learn how to deploy LobeChat on SealOS with ease. Follow the provided steps to
+ Learn how to deploy LobeChat on Sealos with ease. Follow the provided steps to
set up LobeChat and start using it efficiently.
tags:
- Deploy LobeChat
- - SealOS Deployment
+ - Sealos Deployment
- OpenAI API Key
- Custom Domain Binding
---
+# Deploying Lobe Chat Database Version on Sealos
+
+
+ This article assumes that you are familiar with the basic principles and processes of deploying
+ the LobeChat server database version, so it only includes content related to core environment
+ variable configuration. If you are not familiar with the deployment principles of the LobeChat
+ server database version, please refer to [Deploying Server
+ Database](/docs/self-hosting/server-database) first.
+
+
+The application on Sealos includes 4 services:
+
+- Logto for authrization(need to deploy separately).
+- PostgreSQL with Vector plugin for data storage and indexing.
+- One object storage Bucket.
+- Lobe Chat database version.
+
+Here is the process for deploying the Lobe Chat server database version on Sealos:
+
+## Pre-Deployment Setup
+
+**Step 1**:Click the button below to deploy a Logto service:
+
+[](https://template.usw.sealos.io/deploy?templateName=logto)
+
+> Logto is an open-source identity and access management (IAM) platform, an open-source alternative to Auth0, designed to help developers quickly build secure and scalable login and registration systems and user identity systems.
+
+**Step 2**:After the deployment is complete, wait for all the components of the application to be in the "Running" state, click the application's "Details" button to enter the application details page.
+
+
+
+Click the public address corresponding to port 3002, you can use the public address to access the Logto service.
+
+
+
+**Step 3**:Register a management account, then click the `Applications` menu on the left, enter the application list page. Click the `Create application` button in the upper right corner to create an application.
+
+
+
+Select `Next.js (App Router)` as the framework, then click the `Start building` button.
+
+
+
+**Step 4**:In the pop-up window, fill in the application name as `Lobe Chat`, then click the `Create application` button. Next, do not fill in anything, just click the bottom `Finish and done` button to create it.
+
+
+
+**Step 5**:In the `Lobe Chat` application, find the following three parameters, which will be used later when deploying the Lobe Chat database version.
+
+
+
+## Deploy Lobe Chat Database Version
+
+**Step 1**:Click the button below to visit the Lobe Chat database version application deployment page:
+
+[](https://template.usw.sealos.io/deploy?templateName=lobe-chat-db)
+
+Fill in the following three required parameters:
+
+- `AUTH_LOGTO_ID`:The App ID of the Logto application
+- `AUTH_LOGTO_SECRET`:The App Secret of the Logto application
+- `AUTH_LOGTO_ISSUER`:The Issuer endpoint of the Logto application
+
+**Step 2**:Click the `Deploy App` button, after the deployment is complete, wait for all the components of the application to be in the "Running" state, click the application's "Details" button to enter the application details page.
+
+
+
+**Step 3**:Find the public address, copy it, and use it later.
+
+## Post-Deployment Configuration
+
+**Step 1**:Enter the `Applications` page of Logto, find the `Lobe Chat` application, click to enter the application details page.
+
+**Step 2**:In the `Settings` page, find the `Redirect URI` and `Post sign-out redirect URI` parameters, fill in the following values:
+
+- Redirect URI: `https:///api/auth/callback/logto`
+- Post sign-out redirect URI: `https://`
+
+**Step 3**:Click the `Save changes` button to save the configuration.
+
+**Step 4**:Now, access the Lobe Chat database version through `https://`, click the avatar in the upper left corner, and then click the [Log in / Sign up] button.
+
+**Step 5**:Next, you will be redirected to the Logto login page, click the [Create account] button to register an account.
+
+**Step 6**:After registration, you can use Logto to login to the Lobe Chat database version.
+
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/sealos.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/sealos.zh-CN.mdx
index f880f45..c650fdb 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/sealos.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/sealos.zh-CN.mdx
@@ -1,14 +1,114 @@
---
-title: 在 SealOS 上部署 LobeChat
-description: 学习如何在 SealOS 上部署 LobeChat,包括准备 OpenAI API Key、点击部署按钮、绑定自定义域名等操作。
+title: 在 Sealos 上部署 LobeChat 数据库版
+description: 学习如何在 Sealos 上部署 LobeChat,包括准备 OpenAI API Key、点击部署按钮、绑定自定义域名等操作。
tags:
- - SealOS
+ - Sealos
- LobeChat
- OpenAI API Key
- 部署流程
- 自定义域名
---
-# 使用 SealOS 部署 LobeChat 数据库版
+# 使用 Sealos 部署 LobeChat 数据库版
-TODO
+
+ 本文假设你已经熟悉 Lobe Chat
+ 服务器数据库版的部署基本原理和流程,因此只包含与核心环境变量配置相关的内容。如果你对 Lobe Chat
+ 服务器数据库版的部署原理不熟悉,请先参考[部署服务器数据库](/zh/docs/self-hosting/server-database)。
+
+
+在 Sealos 的 Lobe Chat 数据库版应用中总共包含有以下四个服务:
+
+- Logto 提供身份校验(需额外部署)
+- 带有 Vector 插件的 PostgreSQL 来做数据存储和向量化
+- 一个对象存储 Bucket
+- LobeChat Database 的实例
+
+这里是在 Sealos 上部署 Lobe Chat 服务器数据库版的流程:
+
+## 预部署配置
+
+在开始部署之前,您需要完成以下配置:
+
+
+
+ ### 部署 Logto 服务
+
+ 点击下方按钮部署一个 Logto 服务:
+
+ [](https://template.hzh.sealos.run/deploy?templateName=logto)
+
+ > Logto 是一个开源的身份与访问管理(IAM)平台,是 Auth0 的开源替代方案,旨在帮助开发者快速构建安全、可扩展的登录注册系统和用户身份体系。
+
+ 部署完成后,等待应用的所有组件状态都变成“运行中”,点击应用的【详情】按钮,进入应用详情页面。
+
+ 
+
+ 点击 3002 端口对应的公网地址,即可使用公网域名访问 Logto 服务。
+
+ 
+
+ ### 创建 Application
+
+ 注册一个管理员账号,然后点击左侧的 `Applications` 菜单,进入应用列表页面。再点击右上角的 `Create application` 按钮创建应用。
+
+ 
+
+ 选择 `Next.js (App Router)` 作为框架,然后点击 `Start building` 按钮。
+
+ 
+
+ 在弹窗中填写应用的名称为 `Lobe Chat`,然后点击 `Create application` 按钮。接下来啥也不用填,直接点击底部的 `Finish and done` 按钮就创建完成了。
+
+ 
+
+ 在 `Lobe Chat` 应用中找到以下三个参数,后面部署 Lobe Chat 数据库版时需要用到。
+
+ 
+
+
+
+## 部署 Lobe Chat 数据库版
+
+点击下方按钮访问 Lobe Chat 数据库版应用部署页面:
+
+[](https://template.hzh.sealos.run/deploy?templateName=lobe-chat-db)
+
+填入三个必填参数:
+
+- `AUTH_LOGTO_ID`:Logto 应用的 App ID
+- `AUTH_LOGTO_SECRET`:Logto 应用的 App Secret
+- `AUTH_LOGTO_ISSUER`:Logto 应用的 Issuer endpoint
+
+点击【部署】按钮,部署完成后,等待应用的所有组件状态都变成“运行中”,点击应用的【详情】按钮,进入应用详情页面。
+
+
+
+找到公网地址,复制下来,后面需要用到。
+
+
+
+## 部署后配置
+
+进入 Logto 的 `Applications` 页面,找到 `Lobe Chat` 应用,点击进入应用详情页面。
+
+在 `Settings` 页面中找到 “Redirect URI” 和 “Post sign-out redirect URI” 这两个参数,填入以下值:
+
+- Redirect URI:`https:///api/auth/callback/logto`
+- Post sign-out redirect URI:`https://`
+
+其中 `https://` 为 Lobe Chat 数据库版的公网地址。
+
+填完之后点击 `Save changes` 按钮保存配置。
+
+现在通过 `https://` 访问 Lobe Chat 数据库版,点击左上角的头像,然后点击【登录 / 注册】按钮:
+
+
+
+接下来会跳转到 Logto 的登录页面,点击【注册】注册一个账号。
+
+
+
+注册完成后,即可使用 Logto 登录 Lobe Chat 数据库版。
+
+
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/vercel.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/vercel.mdx
index 4861d97..29a5056 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/vercel.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/vercel.mdx
@@ -15,104 +15,90 @@ tags:
This article will detail how to deploy the server database version of LobeChat on Vercel, including: 1) database configuration; 2) identity authentication service configuration; 3) steps for setting up the S3 storage service.
-Before proceeding, please make sure of the following:
-
-- Export all data, as after deploying the server-side database, existing user data cannot be automatically migrated and can only be manually imported after backup!
-- The `ACCESS_CODE` in the environment variables is either unset or cleared!
-- When configuring the environment variables required for the server-side database, make sure to fill in all of them before deployment, otherwise you may encounter database migration issues!
+ Before proceeding, please make sure of the following:
+ - Export all data, as after deploying the server-side database, existing user data cannot be automatically migrated and can only be manually imported after backup!
+ - The `ACCESS_CODE` in the environment variables is either unset or cleared!
+ - When configuring the environment variables required for the server-side database, make sure to fill in all of them before deployment, otherwise you may encounter database migration issues!
## 1. Configure the Database
+ ### Prepare the Server Database Instance and Obtain the Connection URL
-### Prepare the Server Database Instance and Obtain the Connection URL
+ Before deployment, make sure you have prepared a Postgres database instance. You can choose one of the following methods:
-Before deployment, make sure you have prepared a Postgres database instance. You can choose one of the following methods:
+ - `A.` Use Serverless Postgres instances like Vercel / Neon;
+ - `B.` Use self-deployed Postgres instances like Docker.
-- `A.` Use Serverless Postgres instances like Vercel / Neon;
-- `B.` Use self-deployed Postgres instances like Docker.
+ The configuration for both methods is slightly different, and will be distinguished in the next step.
-The configuration for both methods is slightly different, and will be distinguished in the next step.
+ ### Add Environment Variables in Vercel
-### Add Environment Variables in Vercel
+ In Vercel's deployment environment variables, add `DATABASE_URL` and other environment variables, and fill in the Postgres database connection URL prepared in the previous step. The typical format for the database connection URL is `postgres://username:password@host:port/database`.
-In Vercel's deployment environment variables, add `DATABASE_URL` and other environment variables, and fill in the Postgres database connection URL prepared in the previous step. The typical format for the database connection URL is `postgres://username:password@host:port/database`.
+
+
+
+ Please confirm the `Postgres` type provided by your vendor. If it is `Node Postgres`, switch to
+ the `Node Postgres` Tab.
+
-
+ Variables to be filled for Serverless Postgres are as follows:
-
+ ```shell
+ # Serverless Postgres DB Url
+ DATABASE_URL=
-
- Please confirm the `Postgres` type provided by your vendor. If it is `Node Postgres`, switch to
- the `Node Postgres` Tab.
-
+ # Specify service mode as server, otherwise it will not enter the server-side database
+ NEXT_PUBLIC_SERVICE_MODE=server
+ ```
-Variables to be filled for Serverless Postgres are as follows:
+ An example of filling in Vercel is as follows:
-```shell
-# Serverless Postgres DB Url
-DATABASE_URL=
+
+
-# Specify service mode as server, otherwise it will not enter the server-side database
-NEXT_PUBLIC_SERVICE_MODE=server
-```
+
+ Variables to be filled for Node Postgres are as follows:
-An example of filling in Vercel is as follows:
+ ```shell
+ # Node Postgres DB Url
+ DATABASE_URL=
-
+ # Specify Postgres database driver as node
+ DATABASE_DRIVER=node
-
+ # Specify service mode as server, otherwise it will not enter the server-side database
+ NEXT_PUBLIC_SERVICE_MODE=server
+ ```
-
- Variables to be filled for Node Postgres are as follows:
+ An example of filling in Vercel is as follows:
-```shell
-# Node Postgres DB Url
-DATABASE_URL=
+
+
+
-# Specify Postgres database driver as node
-DATABASE_DRIVER=node
+
+ If you wish to enable SSL when connecting to the database, please refer to the
+ [link](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)
+ for setup instructions.
+
-# Specify service mode as server, otherwise it will not enter the server-side database
-NEXT_PUBLIC_SERVICE_MODE=server
-```
-
-An example of filling in Vercel is as follows:
-
-
+ ### Add the `KEY_VAULTS_SECRET` Environment Variable
-
+ After adding the `DATABASE_URL` environment variable for the database, you need to add a `KEY_VAULTS_SECRET` environment variable. This variable is used to encrypt sensitive information such as apikeys stored by users. You can generate a random 32-character string as the key using `openssl rand -base64 32`.
-
+ ```shell
+ KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
+ ```
-
- If you wish to enable SSL when connecting to the database, please refer to the
- [link](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)
- for setup instructions.
-
+ Make sure to add this to the Vercel environment variables as well.
-### Add the `KEY_VAULTS_SECRET` Environment Variable
-
-After adding the DATABASE_URL environment variable for the database, you need to add a `KEY_VAULTS_SECRET` environment variable. This variable is used to encrypt sensitive information such as apikeys stored by users. You can generate a random 32-character string as the key using `openssl rand -base64 32`.
-
-```shell
-KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
-```
-
-Make sure to add this to the Vercel environment variables as well.
-
-### Add the `APP_URL` Environment Variable
-
-Finally, you need to add the `APP_URL` environment variable, which specifies the URL address of the LobeChat application.
+ ### Add the `APP_URL` Environment Variable
+ Finally, you need to add the `APP_URL` environment variable, which specifies the URL address of the LobeChat application.
## 2. Configure Authentication Service
@@ -120,89 +106,63 @@ Finally, you need to add the `APP_URL` environment variable, which specifies the
The server-side database needs to be paired with a user authentication service to function properly. Therefore, the corresponding authentication service needs to be configured.
+ ### Prepare Clerk Authentication Service
-### Prepare Clerk Authentication Service
-
-Go to [Clerk](https://clerk.com?utm_source=lobehub&utm_medium=docs) to register and create an application to obtain the corresponding Public Key and Secret Key.
-
-
- If you are not familiar with Clerk, you can refer to [Authentication
- Service-Clerk](/en/docs/self-hosting/advanced/authentication#clerk) for details on using Clerk.
-
-
-### Add Public and Private Key Environment Variables in Vercel
-
-In Vercel's deployment environment variables, add the `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` and `CLERK_SECRET_KEY` environment variables. You can click on "API Keys" in the menu, then copy the corresponding values and paste them into Vercel's environment variables.
+ Go to [Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) to register and create an application to obtain the corresponding Public Key and Secret Key.
-
-
-The environment variables required for this step are as follows:
-
-```shell
-NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
-CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
-```
+
+ If you are not familiar with Clerk, you can refer to [Authentication
+ Service-Clerk](/en/docs/self-hosting/advanced/authentication#clerk) for details on using Clerk.
+
-Add the above variables to Vercel:
+ ### Add Public and Private Key Environment Variables in Vercel
-
+ In Vercel's deployment environment variables, add the `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` and `CLERK_SECRET_KEY` environment variables. You can click on "API Keys" in the menu, then copy the corresponding values and paste them into Vercel's environment variables.
-### Create and Configure Webhook in Clerk
+
-Since we let Clerk fully handle user authentication and management, we need Clerk to notify our application and store data in the database when there are changes in the user's lifecycle (create, update, delete). We achieve this requirement through the Webhook provided by Clerk.
+ The environment variables required for this step are as follows:
-We need to add an endpoint in Clerk's Webhooks to inform Clerk to send notifications to this endpoint when a user's information changes.
+ ```shell
+ NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
+ CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
+ ```
-
+ Add the above variables to Vercel:
-Fill in the endpoint with the URL of your Vercel project, such as `https://your-project.vercel.app/api/webhooks/clerk`. Then, subscribe to events by checking the three user events (`user.created`, `user.deleted`, `user.updated`), and click create.
+
-
- The `https://` in the URL is essential to maintain the integrity of the URL.
-
+ ### Create and Configure Webhook in Clerk
-
+ Since we let Clerk fully handle user authentication and management, we need Clerk to notify our application and store data in the database when there are changes in the user's lifecycle (create, update, delete). We achieve this requirement through the Webhook provided by Clerk.
->
+ We need to add an endpoint in Clerk's Webhooks to inform Clerk to send notifications to this endpoint when a user's information changes.
-
+
-### Add Webhook Secret to Vercel Environment Variables
+ Fill in the endpoint with the URL of your Vercel project, such as `https://your-project.vercel.app/api/webhooks/clerk`. Then, subscribe to events by checking the three user events (`user.created`, `user.deleted`, `user.updated`), and click create.
-After creation, you can find the secret of this Webhook in the bottom right corner:
+
+ The `https://` in the URL is essential to maintain the integrity of the URL.
+
-
+
->
+ ### Add Webhook Secret to Vercel Environment Variables
-
+ After creation, you can find the secret of this Webhook in the bottom right corner:
-The environment variable corresponding to this secret is `CLERK_WEBHOOK_SECRET`:
+
-```shell
-CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
-```
+ The environment variable corresponding to this secret is `CLERK_WEBHOOK_SECRET`:
-Add it to Vercel's environment variables:
+ ```shell
+ CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
+ ```
-
+ Add it to Vercel's environment variables:
+
By completing these steps, you have successfully configured the Clerk authentication service. Next, we will configure the S3 storage service.
@@ -212,155 +172,121 @@ By completing these steps, you have successfully configured the Clerk authentica
In the server-side database, we need to configure the S3 storage service to store files.
- In this article, S3 refers to a compatible S3 storage solution, which supports object storage
- systems that comply with the Amazon S3 API. Common examples include Cloudflare R2, Alibaba Cloud
- OSS, etc., all of which support S3-compatible APIs.
+ In this article, S3 refers to a compatible S3 storage solution, which supports object storage systems that comply with the Amazon S3 API. Common examples include Cloudflare R2, Alibaba Cloud OSS, etc., all of which support S3-compatible APIs.
+ ### Configure and Obtain S3 Bucket
-### Configure and Obtain S3 Bucket
+ You need to go to your S3 service provider (such as AWS S3, Cloudflare R2, etc.) and create a new storage bucket. The following steps will use Cloudflare R2 as an example to explain the creation process.
-You need to go to your S3 service provider (such as AWS S3, Cloudflare R2, etc.) and create a new storage bucket. The following steps will use Cloudflare R2 as an example to explain the creation process.
+ The interface of Cloudflare R2 is shown below:
-The interface of Cloudflare R2 is shown below:
+
-
+ When creating a storage bucket, specify its name and then click create.
-When creating a storage bucket, specify its name and then click create.
+
-
+ ### Obtain Environment Variables for the Bucket
-### Obtain Environment Variables for the Bucket
+ In the settings of the R2 storage bucket, you can view the bucket configuration information:
-In the settings of the R2 storage bucket, you can view the bucket configuration information:
+
-
+ The corresponding environment variables are:
-The corresponding environment variables are:
+ ```shell
+ # Storage bucket name
+ S3_BUCKET=lobechat
+ # Storage bucket request endpoint (note that the path in this link includes the bucket name, which must be removed, or use the link provided on the S3 API token application page)
+ S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
+ # Public access domain for the storage bucket
+ S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com
+ ```
-```shell
-# Storage bucket name
-S3_BUCKET=lobechat
-# Storage bucket request endpoint (note that the path in this link includes the bucket name, which must be removed, or use the link provided on the S3 API token application page)
-S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
-# Public access domain for the storage bucket
-S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com
-```
+
+ `S3_ENDPOINT` must have its path removed, otherwise uploaded files will not be accessible
+
-
- `S3_ENDPOINT` must have its path removed, otherwise uploaded files will not be accessible
-
+ ### Obtain S3 Key Environment Variables
-### Obtain S3 Key Environment Variables
+ You need to obtain the access key for S3 so that the LobeChat server has permission to access the S3 storage service. In R2, you can configure the access key in the account details:
-You need to obtain the access key for S3 so that the LobeChat server has permission to access the S3 storage service. In R2, you can configure the access key in the account details:
+
-
+ Click the button in the upper right corner to create an API token and enter the create API Token page.
-Click the button in the upper right corner to create an API token and enter the create API Token page.
+
-
+ Since our server-side database needs to read and write to the S3 storage service, the permission needs to be set to `Object Read and Write`, then click create.
-Since our server-side database needs to read and write to the S3 storage service, the permission needs to be set to `Object Read and Write`, then click create.
+
-
+ After creation, you can see the corresponding S3 API token.
-After creation, you can see the corresponding S3 API token.
+
-
+ The corresponding environment variables are:
-The corresponding environment variables are:
+ ```shell
+ S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
+ S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
+ ```
-```shell
-S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
-S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
-```
-
-### Adding Corresponding Environment Variables in Vercel
+ ### Adding Corresponding Environment Variables in Vercel
-The steps to obtain the required environment variables may vary for different S3 service providers, but the obtained environment variables should be consistent:
-
-
- The `https://` in the URL is essential and must be maintained for the completeness of the URL.
-
+ The steps to obtain the required environment variables may vary for different S3 service providers, but the obtained environment variables should be consistent:
-```shell
-# S3 Keys
-S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
-S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
+
+ The `https://` in the URL is essential and must be maintained for the completeness of the URL.
+
-# Bucket name
-S3_BUCKET=lobechat
-# Bucket request endpoint
-S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
-# Public domain for bucket access
-S3_PUBLIC_DOMAIN=https://s3-dev.your-domain.com
+ ```shell
+ # S3 Keys
+ S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
+ S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
-# Bucket region, such as us-west-1, generally not required, but some providers may need to configure
-# S3_REGION=us-west-1
-```
+ # Bucket name
+ S3_BUCKET=lobechat
+ # Bucket request endpoint
+ S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
+ # Public domain for bucket access
+ S3_PUBLIC_DOMAIN=https://s3-dev.your-domain.com
-Then, insert the above environment variables into Vercel's environment variables:
+ # Bucket region, such as us-west-1, generally not required, but some providers may need to configure
+ # S3_REGION=us-west-1
+ ```
-
+ Then, insert the above environment variables into Vercel's environment variables:
-### Configuring Cross-Origin Resource Sharing (CORS)
+
-Since S3 storage services are often on a separate domain, cross-origin access needs to be configured.
+ ### Configuring Cross-Origin Resource Sharing (CORS)
-In R2, you can find the CORS configuration in the bucket settings:
+ Since S3 storage services are often on a separate domain, cross-origin access needs to be configured.
-
+ In R2, you can find the CORS configuration in the bucket settings:
-Add a CORS rule to allow requests from your domain (in this case, `https://your-project.vercel.app`):
+
-
+ Add a CORS rule to allow requests from your domain (in this case, `https://your-project.vercel.app`):
-Example configuration:
+
-```json
-[
- {
- "AllowedOrigins": ["https://your-project.vercel.app"],
- "AllowedMethods": ["GET", "PUT", "HEAD", "POST", "DELETE"],
- "AllowedHeaders": ["*"]
- }
-]
-```
+ Example configuration:
-After configuring, click save.
+ ```json
+ [
+ {
+ "AllowedOrigins": ["https://your-project.vercel.app"],
+ "AllowedMethods": ["GET", "PUT", "HEAD", "POST", "DELETE"],
+ "AllowedHeaders": ["*"]
+ }
+ ]
+ ```
+ After configuring, click save.
## Four, Deployment and Verification
@@ -370,25 +296,17 @@ After completing the steps above, the configuration of the server-side database
### Redeploy the latest commit
-After configuring the environment variables, you need to redeploy the latest commit and wait for the deployment to complete.
-
-
+ After configuring the environment variables, you need to redeploy the latest commit and wait for the deployment to complete.
-### Check if the features are working properly
+
-If you click on the login button in the top left corner and the login popup appears normally, then you have successfully configured it. Enjoy using it\~
+ ### Check if the features are working properly
-
+ If you click on the login button in the top left corner and the login popup appears normally, then you have successfully configured it. Enjoy using it\~
-
+
+
## Appendix
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/vercel.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/vercel.zh-CN.mdx
index 1586530..db7f347 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/vercel.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/vercel.zh-CN.mdx
@@ -17,7 +17,8 @@ tags:
本文将详细介绍如何在 Vercel 中部署服务端数据库版 LobeChat,包括: 1)数据库配置;2)身份验证服务配置;3) S3 存储服务的设置步骤。
-进行后续操作前,请务必确认以下事项:
+ 进行后续操作前,请务必确认以下事项:
+
- 导出所有数据,部署服务端数据库后,原有用户数据无法自动迁移,只能提前备份后进行手动导入!
- 环境变量中的`ACCESS_CODE`未设置或已清除!
- 配置服务端数据库所需要的环境变量时,需全部填入后再进行部署,否则可能遭遇数据库迁移问题!
@@ -26,28 +27,24 @@ tags:
## 一、 配置数据库
+ ### 准备服务端数据库实例,获取连接 URL
-### 准备服务端数据库实例,获取连接 URL
-
-在部署之前,请确保你已经准备好 Postgres 数据库实例,你可以选择以下任一方式:
+ 在部署之前,请确保你已经准备好 Postgres 数据库实例,你可以选择以下任一方式:
-- `A.` 使用 Vercel / Neon 等 Serverless Postgres 实例;
-- `B.` 使用 Docker 等自部署 Postgres 实例。
+ - `A.` 使用 Vercel / Neon 等 Serverless Postgres 实例;
+ - `B.` 使用 Docker 等自部署 Postgres 实例。
-两者的配置方式略有不同,在下一步会有所区分。
+ 两者的配置方式略有不同,在下一步会有所区分。
-### 在 Vercel 中添加环境变量
+ ### 在 Vercel 中添加环境变量
-在 Vercel 的部署环境变量中,添加 `DATABASE_URL` 等环境变量,将上一步准备好的 Postgres 数据库连接 URL 填入其中。数据库连接 URL 的通常格式为 `postgres://username:password@host:port/database`。
+ 在 Vercel 的部署环境变量中,添加 `DATABASE_URL` 等环境变量,将上一步准备好的 Postgres 数据库连接 URL 填入其中。数据库连接 URL 的通常格式为 `postgres://username:password@host:port/database`。
-
-
请确认您的供应商所提供的 `Postgres` 类型,若为 `Node Postgres`,请切换到 `Node Postgres` Tab 。
-
-
+
Serverless Postgres 需要填写的变量如下:
@@ -61,9 +58,8 @@ tags:
在 Vercel 中填写的示例如下:
-
-
-
+
+
Node Postgres 需要填写的变量如下:
@@ -81,31 +77,28 @@ tags:
在 Vercel 中填写的示例如下:
-
+
+
+
-
+
+ 如果希望连接数据库时启用 SSL
+ ,请自行参考[链接](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)进行设置
+
-
+ ### 添加 `KEY_VAULTS_SECRET` 环境变量
-
- 如果希望连接数据库时启用 SSL
- ,请自行参考[链接](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)进行设置
-
-
-### 添加 `KEY_VAULTS_SECRET` 环境变量
-
-在完成数据库 DATABASE_URL 环境变量添加后,需要添加一个 `KEY_VAULTS_SECRET` 环境变量。该变量用于加密用户存储的 apikey 等敏感信息。你可以使用 `openssl rand -base64 32` 生成一个随机的 32 位字符串作为密钥。
-
-```shell
-KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
-```
+ 在完成数据库 `DATABASE_URL` 环境变量添加后,需要添加一个 `KEY_VAULTS_SECRET` 环境变量。该变量用于加密用户存储的 apikey 等敏感信息。你可以使用 `openssl rand -base64 32` 生成一个随机的 32 位字符串作为密钥。
-同样需要将其添加到 Vercel 环境变量中。
+ ```shell
+ KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
+ ```
-### 添加 `APP_URL` 环境变量
+ 同样需要将其添加到 Vercel 环境变量中。
-该部分最后需要添加 APP_URL 环境变量,用于指定LobeChat 应用的 URL 地址。
+ ### 添加 `APP_URL` 环境变量
+ 该部分最后需要添加 `APP_URL` 环境变量,用于指定 LobeChat 应用的 URL 地址。
## 二、 配置身份验证服务
@@ -113,81 +106,61 @@ KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
服务端数据库需要搭配用户身份验证服务才可以正常使用。因此需要配置对应的身份验证服务。
+ ### 准备 Clerk 身份验证服务
-### 准备 Clerk 身份验证服务
+ 前往 [Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) 注册并创建应用,获取相应的 Public Key 和 Secret Key。
-前往 [Clerk](https://clerk.com?utm_source=lobehub&utm_medium=docs) 注册并创建应用,获取相应的 Public Key 和 Secret Key。
+
+ 如果对 Clerk 不太了解,可以查阅
+ [身份验证服务 - Clerk](/zh/docs/self-hosting/advanced/authentication#clerk) 了解 Clerk 的使用详情。
+
-
- 如果对 Clerk 不太了解,可以查阅
- [身份验证服务-Clerk](/zh/docs/self-hosting/advanced/authentication#clerk) 了解 Clerk 的使用详情。
-
+ ### 在 Vercel 中添加公、私钥环境变量
-### 在 Vercel 中添加公、私钥环境变量
+ 在 Vercel 的部署环境变量中,添加 `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` 和 `CLERK_SECRET_KEY` 环境变量。你可以在菜单中点击「API Keys」,然后复制对应的值填入 Vercel 的环境变量中。
-在 Vercel 的部署环境变量中,添加 `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` 和 `CLERK_SECRET_KEY` 环境变量。你可以在菜单中点击「API Keys」,然后复制对应的值填入 Vercel 的环境变量中。
+
-
+ 此步骤所需的环境变量如下:
-此步骤所需的环境变量如下:
+ ```shell
+ NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
+ CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
+ ```
-```shell
-NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
-CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
-```
-
-添加上述变量到 Vercel 中:
-
-
+ 添加上述变量到 Vercel 中:
-### 在 Clerk 中创建并配置 Webhook
+
-由于我们让 Clerk 完全接管用户鉴权与管理,因此我们需要在 Clerk 用户生命周期变更时(创建、更新、删除)中通知我们的应用并存储落库。我们通过 Clerk 提供的 Webhook 来实现这一诉求。
+ ### 在 Clerk 中创建并配置 Webhook
-我们需要在 Clerk 的 Webhooks 中添加一个端点(Endpoint),告诉 Clerk 当用户发生变更时,向这个端点发送通知。
+ 由于我们让 Clerk 完全接管用户鉴权与管理,因此我们需要在 Clerk 用户生命周期变更时(创建、更新、删除)中通知我们的应用并存储落库。我们通过 Clerk 提供的 Webhook 来实现这一诉求。
-
+ 我们需要在 Clerk 的 Webhooks 中添加一个端点(Endpoint),告诉 Clerk 当用户发生变更时,向这个端点发送通知。
-在 endppint 中填写你的 Vercel 项目的 URL,如 `https://your-project.vercel.app/api/webhooks/clerk`。然后在订阅事件(Subscribe to events)中,勾选 user 的三个事件(`user.created` 、`user.deleted`、`user.updated`),然后点击创建。
+
-URL的`https://`不可缺失,须保持URL的完整性
+ 在 endpoint 中填写你的 Vercel 项目的 URL,如 `https://your-project.vercel.app/api/webhooks/clerk`。然后在订阅事件(Subscribe to events)中,勾选 user 的三个事件(`user.created` 、`user.deleted`、`user.updated`),然后点击创建。
-
+ URL 的`https://`不可缺失,须保持 URL 的完整性
-### 将 Webhook 秘钥添加到 Vercel 环境变量
+
-创建完毕后,可以在右下角找到该 Webhook 的秘钥:
+ ### 将 Webhook 秘钥添加到 Vercel 环境变量
-
+ 创建完毕后,可以在右下角找到该 Webhook 的秘钥:
-这个秘钥所对应的环境变量名为 `CLERK_WEBHOOK_SECRET`:
+
-```shell
-CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
-```
+ 这个秘钥所对应的环境变量名为 `CLERK_WEBHOOK_SECRET`:
-将其添加到 Vercel 的环境变量中:
+ ```shell
+ CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
+ ```
-
+ 将其添加到 Vercel 的环境变量中:
+
这样,你已经成功配置了 Clerk 身份验证服务。接下来我们将配置 S3 存储服务。
@@ -197,149 +170,118 @@ CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
在服务端数据库中我们需要配置 S3 存储服务来存储文件。
- 在本文,S3所指代的是指兼容 S3 存储方案,即支持 Amazon S3 API 的对象存储系统,常见例如 Cloudflare
+ 在本文,S3 所指代的是指兼容 S3 存储方案,即支持 Amazon S3 API 的对象存储系统,常见例如 Cloudflare
R2 、阿里云 OSS 等均支持 S3 兼容 API。
+ ### 配置并获取 S3 存储桶
- ### 配置并获取 S3 存储桶
+ 你需要前往你的 S3 服务提供商(如 AWS S3、Cloudflare R2 等)并创建一个新的存储桶(Bucket)。接下来以 Cloudflare R2 为例,介绍创建流程。
- 你需要前往你的 S3 服务提供商(如 AWS S3、Cloudflare R2 等)并创建一个新的存储桶(Bucket)。接下来以 Cloudflare R2 为例,介绍创建流程。
+ 下图是 Cloudflare R2 的界面:
- 下图是 Cloudflare R2 的界面:
+
-
+ 创建存储桶时将指定其名称,然后点击创建。
- 创建存储桶时将指定其名称,然后点击创建。
-
+
- ### 获取存储桶相关环境变量
+ ### 获取存储桶相关环境变量
- 在 R2 存储桶的设置中,可以看到桶配置的信息:
+ 在 R2 存储桶的设置中,可以看到桶配置的信息:
-
+
-其对应的环境变量为:
+ 其对应的环境变量为:
-```shell
-# 存储桶的名称
-S3_BUCKET=lobechat
-# 存储桶的请求端点(注意此处链接的路径带存储桶名称,必须删除该路径,或使用申请 S3 API token 页面所提供的链接)
-S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
-# 存储桶对外的访问域名
-S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com
-```
+ ```shell
+ # 存储桶的名称
+ S3_BUCKET=lobechat
+ # 存储桶的请求端点(注意此处链接的路径带存储桶名称,必须删除该路径,或使用申请 S3 API token 页面所提供的链接)
+ S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
+ # 存储桶对外的访问域名
+ S3_PUBLIC_DOMAIN=https://s3-for-lobechat.your-domain.com
+ ```
-`S3_ENDPOINT`必须删除其路径,否则会无法访问所上传文件
+ `S3_ENDPOINT`必须删除其路径,否则会无法访问所上传文件
- ### 获取 S3 密钥环境变量
+ ### 获取 S3 密钥环境变量
- 你需要获取 S3 的访问密钥,以便 LobeChat 的服务端有权限访问 S3 存储服务。在 R2 中,你可以在账户详情中配置访问密钥:
+ 你需要获取 S3 的访问密钥,以便 LobeChat 的服务端有权限访问 S3 存储服务。在 R2 中,你可以在账户详情中配置访问密钥:
-
+
- 点击右上角按钮创建 API token,进入创建 API Token 页面
+ 点击右上角按钮创建 API token,进入创建 API Token 页面
-
+
- 鉴于我们的服务端数据库需要读写 S3 存储服务,因此权限需要选择`对象读与写`,然后点击创建。
+ 鉴于我们的服务端数据库需要读写 S3 存储服务,因此权限需要选择`对象读与写`,然后点击创建。
-
+
- 创建完成后,就可以看到对应的 S3 API token
+ 创建完成后,就可以看到对应的 S3 API token
-
+
- 其对应的环境变量为:
+ 其对应的环境变量为:
-```shell
-S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
-S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
-```
-
-### 在 Vercel 中添加对应的环境变量
+ ```shell
+ S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
+ S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
+ ```
- 不同 S3 服务商获取所需环境变量的步骤可能有所不同,但最终获得到的环境变量应该都是一致的:
+ ### 在 Vercel 中添加对应的环境变量
-URL的`https://`不可缺失,须保持URL的完整性
+ 不同 S3 服务商获取所需环境变量的步骤可能有所不同,但最终获得到的环境变量应该都是一致的:
-```shell
-# S3 秘钥
-S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
-S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
+ URL 的`https://`不可缺失,须保持 URL 的完整性
-# 存储桶的名称
-S3_BUCKET=lobechat
-# 存储桶的请求端点
-S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
-# 存储桶对外的访问域名
-S3_PUBLIC_DOMAIN=https://s3-dev.your-domain.com
+ ```shell
+ # S3 秘钥
+ S3_ACCESS_KEY_ID=9998d6757e276cf9f1edbd325b7083a6
+ S3_SECRET_ACCESS_KEY=55af75d8eb6b99f189f6a35f855336ea62cd9c4751a5cf4337c53c1d3f497ac2
-# 桶的区域,如 us-west-1,一般来说不需要添加,但某些服务商则需要配置
-# S3_REGION=us-west-1
-```
+ # 存储桶的名称
+ S3_BUCKET=lobechat
+ # 存储桶的请求端点
+ S3_ENDPOINT=https://0b33a03b5c993fd2f453379dc36558e5.r2.cloudflarestorage.com
+ # 存储桶对外的访问域名
+ S3_PUBLIC_DOMAIN=https://s3-dev.your-domain.com
-然后将上述环境变量填入 Vercel 的环境变量中:
+ # 桶的区域,如 us-west-1,一般来说不需要添加,但某些服务商则需要配置
+ # S3_REGION=us-west-1
+ ```
-
+ 然后将上述环境变量填入 Vercel 的环境变量中:
- ### 配置跨域
+
- 由于 S3 存储服务往往是一个独立的网址,因此需要配置跨域访问。
+ ### 配置跨域
- 在 R2 中,你可以在存储桶的设置中找到跨域配置:
+ 由于 S3 存储服务往往是一个独立的网址,因此需要配置跨域访问。
-
+ 在 R2 中,你可以在存储桶的设置中找到跨域配置:
- 添加跨域规则,允许你的域名(在上文是 `https://your-project.vercel.app`)来源的请求:
+
-
+ 添加跨域规则,允许你的域名(在上文是 `https://your-project.vercel.app`)来源的请求:
-示例配置如下:
+
-```json
-[
- {
- "AllowedOrigins": ["https://your-project.vercel.app"],
- "AllowedMethods": ["GET", "PUT", "HEAD", "POST", "DELETE"],
- "AllowedHeaders": ["*"]
- }
-]
-```
+ 示例配置如下:
-配置后点击保存即可。
+ ```json
+ [
+ {
+ "AllowedOrigins": ["https://your-project.vercel.app"],
+ "AllowedMethods": ["GET", "PUT", "HEAD", "POST", "DELETE"],
+ "AllowedHeaders": ["*"]
+ }
+ ]
+ ```
+ 配置后点击保存即可。
## 四、部署并验证
@@ -349,27 +291,17 @@ S3_PUBLIC_DOMAIN=https://s3-dev.your-domain.com
### 重新部署最新的 commit
-配置好环境变量后,你需要重新部署最新的 commit,并等待部署完成。
-
-
+ 配置好环境变量后,你需要重新部署最新的 commit,并等待部署完成。
-### 检查功能是否正常
+
-如果你点击左上角登录,可以正常显示登录弹窗,那么说明你已经配置成功了,尽情享用吧~
+ ### 检查功能是否正常
-
+ 如果你点击左上角登录,可以正常显示登录弹窗,那么说明你已经配置成功了,尽情享用吧~
-
+
+
## 附录
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.mdx
index d7b99d3..5f9dc55 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.mdx
@@ -21,6 +21,7 @@ tags:
The template on Zeabur includes 4 services:
+
- Logto for authrization.
- PostgreSQL with Vector plugin for data storage and indexing.
- MinIO for image storage.
@@ -31,52 +32,45 @@ The template on Zeabur includes 4 services:
Here is the process for deploying the LobeChat server database version on Zeabur:
+ ### Go to the template page on Zeabur
-### Go to the template page on Zeabur
-
-Go to the [LobeChat Database template page](https://zeabur.com/templates/RRSPSD) on Zeabur and click on the "Deploy" button.
-
-### Fill in the required environment variables
-
-After you click on the "Deploy" button, you will see a modal pop-up where you can fill in the required environment variables.
+ Go to the [LobeChat Database template page](https://zeabur.com/templates/RRSPSD) on Zeabur and click on the "Deploy" button.
-Here are the environment variables you need to fill in:
+ ### Fill in the required environment variables
-- OpenAI API key: Your OpenAI API key to get responses from OpenAI.
+ After you click on the "Deploy" button, you will see a modal pop-up where you can fill in the required environment variables.
-- LobeChat Domain: A free subdomain with `.zeabur.app` suffix.
+ Here are the environment variables you need to fill in:
-- MinIO Public Domain: A free subdomain with `.zeabur.app` suffix for yout MinIO web port to enable public access for the uploaded files.
+ - OpenAI API key: Your OpenAI API key to get responses from OpenAI.
-- Logto Console Domain: A free subdomain with `.zeabur.app` suffix for your Logto console.
+ - LobeChat Domain: A free subdomain with `.zeabur.app` suffix.
-- Logto API Domain: A free subdomain with `.zeabur.app` suffix for your Logto api.
+ - MinIO Public Domain: A free subdomain with `.zeabur.app` suffix for yout MinIO web port to enable public access for the uploaded files.
+ - Logto Console Domain: A free subdomain with `.zeabur.app` suffix for your Logto console.
-### Select a region and deploy
+ - Logto API Domain: A free subdomain with `.zeabur.app` suffix for your Logto api.
-After you fill all the required environment variables, select a region where you want to deploy your LobeChat Database and click on the "Deploy" button.
+ ### Select a region and deploy
-You will see another modal pop-up where you can see the deployment progress.
+ After you fill all the required environment variables, select a region where you want to deploy your LobeChat Database and click on the "Deploy" button.
-### Configure Logto
+ You will see another modal pop-up where you can see the deployment progress.
-After the deployment is done, you need to configure your Logto service to enable authrization.
+ ### Configure Logto
-Access your Logto console with the console domain you just binded, and then create a `Next.js 14(App router)` application to get the client ID and client secret, and fill in the cors and callback URLs.
-You can check [this document](../advanced/auth.mdx) for a more detailed guide.
+ After the deployment is done, you need to configure your Logto service to enable authrization.
-Fill in those variables into your LobeChat service on Zeabur, here is a more detailed guide for [editing environment variables on Zeabur](https://zeabur.com/docs/deploy/variables).
+ Access your Logto console with the console domain you just binded, and then create a `Next.js 14(App router)` application to get the client ID and client secret, and fill in the cors and callback URLs. You can check [this document](../advanced/auth.mdx) for a more detailed guide.
-```
-LOGTO_CLIENT_ID=your_logto_client_id
-LOGTO_CLIENT_SECRET=your_logto_client_secret
-```
+ Fill in those variables into your LobeChat service on Zeabur, here is a more detailed guide for [editing environment variables on Zeabur](https://zeabur.com/docs/deploy/variables).
-### Access your LobeChat Instance
+ For detailed configuration of Logto, refer to [this document](/docs/self-hosting/advanced/auth/next-auth/logto).
-Press on the `LobeChat-Database` and you can see the public domain you just created, click on it to access your LobeChat Database.
+ ### Access your LobeChat Instance
-You can also bind a custom domain for your services if you want, here is a guide on how to [bind a custom domain on Zeabur](https://zeabur.com/docs/deploy/domain-binding).
+ Press on the `LobeChat-Database` and you can see the public domain you just created, click on it to access your LobeChat Database.
+ You can also bind a custom domain for your services if you want, here is a guide on how to [bind a custom domain on Zeabur](https://zeabur.com/docs/deploy/domain-binding).
diff --git a/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.zh-CN.mdx
index 9057e7a..a1d7fab 100644
--- a/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/server-database/zeabur.zh-CN.mdx
@@ -18,6 +18,7 @@ tags:
在 Zeabur 的模板中总共包含有以下四个服务:
+
- Logto 提供身份校验
- 带有 Vector 插件的 PostgreSQL 来做数据存储和向量化
- MinIO 作为对象存储
@@ -28,43 +29,39 @@ tags:
这里是在 Zeabur 上部署 LobeChat 服务器数据库版的流程:
+ ### 前往 Zeabur 上的模板页面
-### 前往 Zeabur 上的模板页面
-
-前往 [Zeabur 上的 LobeChat 数据库模板页面](https://zeabur.com/templates/RRSPSD) 并点击 "Deploy" 按钮。
-
-### 填写必要的环境变量
+ 前往 [Zeabur 上的 LobeChat 数据库模板页面](https://zeabur.com/templates/RRSPSD) 并点击 "Deploy" 按钮。
-在你点击“部署“按钮后,你会看到一个模态弹窗,你可以在这里填写必要的环境变量。
+ ### 填写必要的环境变量
-以下是你需要填写的环境变量:
+ 在你点击 “部署 “按钮后,你会看到一个模态弹窗,你可以在这里填写必要的环境变量。
-- OpenAI API key: 你的 OpenAI API key 用于获取模型的访问权限。
-- LobeChat Domain: 一个免费的 `.zeabur.app` 后缀的域名。
-- MinIO Public Domain: 一个免费的 `.zeabur.app` 后缀的域名为了暴露 MinIO 服务以公开访问资源。
-- Logto Console Domain: 一个免费的 `.zeabur.app` 后缀的域名来访问 Logto 的控制台。
-- Logto API Domain: 一个免费的 `.zeabur.app` 后缀的域名来访问 Logto 的 API。
+ 以下是你需要填写的环境变量:
-### 选择一个区域并部署
+ - OpenAI API key: 你的 OpenAI API key 用于获取模型的访问权限。
+ - LobeChat Domain: 一个免费的 `.zeabur.app` 后缀的域名。
+ - MinIO Public Domain: 一个免费的 `.zeabur.app` 后缀的域名为了暴露 MinIO 服务以公开访问资源。
+ - Logto Console Domain: 一个免费的 `.zeabur.app` 后缀的域名来访问 Logto 的控制台。
+ - Logto API Domain: 一个免费的 `.zeabur.app` 后缀的域名来访问 Logto 的 API。
-在你填写完所有必要的环境变量后,选择一个你想要部署 LobeChat 数据库的区域并点击“部署”按钮。
+ ### 选择一个区域并部署
-你会看到另一个模态弹窗,你可以在这里看到部署的进度。
+ 在你填写完所有必要的环境变量后,选择一个你想要部署 LobeChat 数据库的区域并点击 “部署” 按钮。
-### 配置 Logto
+ 你会看到另一个模态弹窗,你可以在这里看到部署的进度。
-当部署完成后,你会被自动导航到你在 Zeabur 控制台上刚刚创建的项目。
-你需要再进一步配置你的 Logto 服务。
+ ### 配置 Logto
-使用你刚绑定的域名来访问你的 Logto 控制台,创建一个新项目以获得对应的客户端 ID 与密钥,将它们填入你的 LobeChat 服务的变量中。
-关于如何填入变量,可以参照 [Zeabur 的官方文档](https://zeabur.com/docs/deploy/variables)。
+ 当部署完成后,你会被自动导航到你在 Zeabur 控制台上刚刚创建的项目。你需要再进一步配置你的 Logto 服务。
-Logto 的详细配置可以参考[这篇文档](../advanced/auth.zh-CN.mdx)。
+ 使用你刚绑定的域名来访问你的 Logto 控制台,创建一个新项目以获得对应的客户端 ID 与密钥,将它们填入你的 LobeChat 服务的变量中。关于如何填入变量,可以参照 [Zeabur 的官方文档](https://zeabur.com/docs/deploy/variables)。
-### 访问你的 LobeChat
+ Logto 的详细配置可以参考[这篇文档](/zh/docs/self-hosting/advanced/auth/next-auth/logto)。
-按下 `LobeChat-Database` 你会看到你刚刚创建的公共域名,点击它以访问你的 LobeChat 数据库。
+ ### 访问你的 LobeChat
-你可以选择绑定一个自定义域名,这里有一个关于如何在 Zeabur 上[绑定自定义域名](https://zeabur.com/docs/deploy/domain-binding)的指南。
+ 按下 `LobeChat-Database` 你会看到你刚刚创建的公共域名,点击它以访问你的 LobeChat 数据库。
+ 你可以选择绑定一个自定义域名,这里有一个关于如何在 Zeabur 上[绑定自定义域名](https://zeabur.com/docs/deploy/domain-binding)的指南。
diff --git a/DigitalHumanWeb/docs/self-hosting/start.mdx b/DigitalHumanWeb/docs/self-hosting/start.mdx
index b56d9c1..4f5aa21 100644
--- a/DigitalHumanWeb/docs/self-hosting/start.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/start.mdx
@@ -9,7 +9,9 @@ tags:
- Vercel
- Docker
- Docker Compose
+ - Alibaba Cloud
---
+
# Build Your Own Lobe Chat
LobeChat supports various deployment platforms, including Vercel, Docker, and Docker Compose. You can choose a deployment platform that suits you to build your own Lobe Chat.
@@ -23,7 +25,9 @@ You can follow the guide below for quick deployment of LobeChat:
- In the client-side database mode, data is stored locally on the user's device, without cross-device synchronization, and does not support advanced features such as file uploads and knowledge base.
+ In the client-side database mode, data is stored locally on the user's device, without
+ cross-device synchronization, and does not support advanced features such as file uploads and
+ knowledge base.
## Advanced Mode: Server-Side Database
@@ -31,5 +35,5 @@ You can follow the guide below for quick deployment of LobeChat:
For users who are already familiar with LobeChat or need cross-device synchronization, you can deploy a version with a server-side database to access a more complete and powerful LobeChat.
-
+
diff --git a/DigitalHumanWeb/docs/self-hosting/start.zh-CN.mdx b/DigitalHumanWeb/docs/self-hosting/start.zh-CN.mdx
index 26c31a9..bad5849 100644
--- a/DigitalHumanWeb/docs/self-hosting/start.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/self-hosting/start.zh-CN.mdx
@@ -2,23 +2,27 @@
title: 构建属于自己的 LobeChat - 自选部署平台
description: >-
选择适合自己的部署平台,构建个性化的 Lobe Chat。支持 Docker、Docker
- Compose、Netlify、Railway、Repocloud、SealOS、Vercel 和 Zeabur 部署。
+ Compose、Netlify、Railway、Repocloud、Sealos、Vercel 和 Zeabur 部署。
tags:
- Lobe Chat
- 部署平台
- Docker
- Netlify
- Vercel
+ - Sealos
+ - 阿里云计算巢
- 个性化
+ - 腾讯云
+ - 腾讯轻量云
---
# 构建属于自己的 Lobe Chat
-LobeChat 支持多种部署平台,包括 Vercel、Docker 和 Docker Compose 等,你可以选择适合自己的部署平台进行部署,构建属于自己的 Lobe Chat。
+LobeChat 支持多种部署平台,包括 Vercel、Docker、 Docker Compose 、阿里云计算巢 和腾讯轻量云 等,你可以选择适合自己的部署平台进行部署,构建属于自己的 Lobe Chat。
## 快速部署
-对于第一次了解 LobeChat 的用户,我们推荐使用客户端数据库的模式快速部署,该模式的优势是一行指令/一个按钮即可快捷完成部署,便于你快速上手与体验 LobeChat。
+对于第一次了解 LobeChat 的用户,我们推荐使用客户端数据库的模式快速部署,该模式的优势是一行指令 / 一个按钮即可快捷完成部署,便于你快速上手与体验 LobeChat。
你可以通过以下指南快速部署 LobeChat:
diff --git a/DigitalHumanWeb/docs/usage/agents/agent-organization.mdx b/DigitalHumanWeb/docs/usage/agents/agent-organization.mdx
index 477dccc..3ecdeff 100644
--- a/DigitalHumanWeb/docs/usage/agents/agent-organization.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/agent-organization.mdx
@@ -14,11 +14,7 @@ tags:
# Assistant Organization Guide
-
+
LobeChat provides a rich variety of AI assistant resources. Users can easily add various assistants through the assistant market, offering a wide range of application scenarios for AI applications.
@@ -30,39 +26,27 @@ Firstly, LobeChat's AI assistants support organization through grouping. You can
### Assistant Settings
-
+
- In the menu of an individual assistant, selecting the `Move to Group` option can quickly categorize the assistant into the specified group.
- If you don't find the group you want, you can choose `Add Group` to quickly create a new group.
### Group Settings
-
+
- In the group menu, you can quickly create a new assistant under that group.
- Clicking the `Group Management` button allows you to `rename`, `delete`, `sort`, and perform other operations on all groups.
## Assistant Search
-
+
- At the top of the assistant list, you can use the assistant search function to easily locate the assistant you need using keywords.
## Assistant Pinning
-
+
- In the assistant menu, you can use the `Pin` function to pin the assistant to the top.
- After pinning an assistant, a pinned area will appear at the top of the assistant list, displaying all pinned assistants.
diff --git a/DigitalHumanWeb/docs/usage/agents/agent-organization.zh-CN.mdx b/DigitalHumanWeb/docs/usage/agents/agent-organization.zh-CN.mdx
index 5ce6aa5..5bff869 100644
--- a/DigitalHumanWeb/docs/usage/agents/agent-organization.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/agent-organization.zh-CN.mdx
@@ -12,11 +12,7 @@ tags:
# 助手组织指南
-
+
LobeChat 提供了丰富的 AI 助手资源,用户可以通过助手市场方便地添加各类助手,为 AI 应用提供了广泛的应用场景。
@@ -28,39 +24,27 @@ LobeChat 提供了丰富的 AI 助手资源,用户可以通过助手市场方
### 助手设置
-
+
- 在单个助手的菜单中,选择`移动到分组`选项可以快速将该助手归类到指定分组。
- 如果没有你想要的分组,可以选择`添加分组`,快速创建一个新的分组。
### 分组设置
-
+
- 在分组菜单中,可以快速在该分组下新建助手
- 点击`分组管理`按钮可以对所有分组进行`重命名`、`删除`、`排序`等操作。
## 助手搜索
-
+
- 在助手列表的顶部,您可以通过助手搜索功能,方便地使用关键词定位到您所需的助手。
## 助手固定
-
+
- 在助手菜单中,你可以使用`固定`功能将该助手固定在顶部。
- 固定助手后,助手列表的上方将出现一个固定区域,显示所有已固定的助手列表。
diff --git a/DigitalHumanWeb/docs/usage/agents/concepts.mdx b/DigitalHumanWeb/docs/usage/agents/concepts.mdx
index 3589579..61cba73 100644
--- a/DigitalHumanWeb/docs/usage/agents/concepts.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/concepts.mdx
@@ -21,8 +21,8 @@ In the official ChatGPT application, there is only the concept of "topics." As s
However, in our usage, we have found that this model has many issues. For example, the information indexing of historical conversations is too scattered. Additionally, when dealing with repetitive tasks, it is difficult to have a stable entry point. For instance, if I want ChatGPT to help me translate a document, in this model, I would need to constantly create new topics and then set up the translation prompt I had previously created. When there are high-frequency tasks, this will result in a very inefficient interaction format.
@@ -34,8 +34,8 @@ Therefore, in LobeChat, we have introduced the concept of **Agents**. An agent i
At the same time, we have integrated topics into each agent. The benefit of this approach is that each agent has an independent topic list. You can choose the corresponding agent based on the current task and quickly switch between historical conversation records. This method is more in line with users' habits in common chat software, improving interaction efficiency.
diff --git a/DigitalHumanWeb/docs/usage/agents/concepts.zh-CN.mdx b/DigitalHumanWeb/docs/usage/agents/concepts.zh-CN.mdx
index d76dcad..cfee63f 100644
--- a/DigitalHumanWeb/docs/usage/agents/concepts.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/concepts.zh-CN.mdx
@@ -18,8 +18,8 @@ tags:
但在我们的使用过程中其实会发现这种模式存在很多问题,比如历史对话的信息索引过于分散问题,同时当处理一些重复任务时很难有一个稳定的入口,比如我希望有一个稳定的入口可以让 ChatGPT 帮助我翻译文档,在这个模式下,我需要不断新建新的话题同时再设置我之前创建好的翻译 Prompt 设定,当有高频任务存在时,这将是一个效率很低的交互形式。
@@ -31,8 +31,8 @@ tags:
与此同时,我们将话题索引到每个助手内部。这样做的好处是,每个助手都有一个独立的话题列表,你可以根据当前任务选择对应的助手,并快速切换历史对话记录。这种方式更符合用户对常见聊天软件的使用习惯,提高了交互的效率。
diff --git a/DigitalHumanWeb/docs/usage/agents/custom-agent.mdx b/DigitalHumanWeb/docs/usage/agents/custom-agent.mdx
index c34eac5..34a36e2 100644
--- a/DigitalHumanWeb/docs/usage/agents/custom-agent.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/custom-agent.mdx
@@ -24,8 +24,8 @@ If you are a beginner in Prompt writing, you might want to browse the assistant
## `B` Create a custom assistant
diff --git a/DigitalHumanWeb/docs/usage/agents/custom-agent.zh-CN.mdx b/DigitalHumanWeb/docs/usage/agents/custom-agent.zh-CN.mdx
index 2011e07..62b6dc7 100644
--- a/DigitalHumanWeb/docs/usage/agents/custom-agent.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/custom-agent.zh-CN.mdx
@@ -22,8 +22,8 @@ tags:
## `B` 通过新建自定义助手
diff --git a/DigitalHumanWeb/docs/usage/agents/model.mdx b/DigitalHumanWeb/docs/usage/agents/model.mdx
index 57f3504..e8056cb 100644
--- a/DigitalHumanWeb/docs/usage/agents/model.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/model.mdx
@@ -17,7 +17,7 @@ tags:
## ChatGPT
- **gpt-3.5-turbo**: Currently the fastest generating ChatGPT model, it is faster but may sacrifice some text quality, with a context length of 4k.
-- **gpt-4**: ChatGPT 4.0 has improved language understanding and generation capabilities compared to 3.5. It can better understand context and context, and generate more accurate and natural responses. This is thanks to improvements in the GPT-4 model, including better language modeling and deeper semantic understanding, but it may be slower than other models, with a context length of 8k.
+- **gpt-4**: ChatGPT 4.0 has improved language understanding and generation capabilities compared to 3.5. It can better understand context and generate more accurate and natural responses. This is thanks to improvements in the GPT-4 model, including better language modeling and deeper semantic understanding, but it may be slower than other models, with a context length of 8k.
- **gpt-4-32k**: Similar to gpt-4, the context limit is increased to 32k tokens, with a higher cost.
## Concept of Model Parameters
@@ -43,10 +43,10 @@ This parameter controls the randomness of the model's output. The higher the val
### `top_p`
-Top_p is also a sampling parameter, but it differs from temperature in its sampling method. Before outputting, the model generates a bunch of tokens, and these tokens are ranked based on their quality. In the top-p sampling mode, the candidate word list is dynamic, and tokens are selected from the tokens based on a percentage. Top_p introduces randomness in token selection, allowing other high-scoring tokens to have a chance of being selected, rather than always choosing the highest-scoring one.
+`top_p` is also a sampling parameter, but it differs from temperature in its sampling method. Before outputting, the model generates a bunch of tokens, and these tokens are ranked based on their quality. In the top-p sampling mode, the candidate word list is dynamic, and tokens are selected from the tokens based on a percentage. Top\_p introduces randomness in token selection, allowing other high-scoring tokens to have a chance of being selected, rather than always choosing the highest-scoring one.
- Top\_p is similar to randomness, and it is generally not recommended to change it together with
+ `top_p` is similar to randomness, and it is generally not recommended to change it together with
the randomness of temperature.
@@ -75,5 +75,21 @@ It is a mechanism that penalizes frequently occurring new vocabulary in the text
- `-2.0` When the morning news started broadcasting, I found that my TV now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now **(The highest frequency word is "now", accounting for 44.79%)**
- `-1.0` He always watches the news in the early morning, in front of the TV watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch **(The highest frequency word is "watch", accounting for 57.69%)**
- `0.0` When the morning sun poured into the small diner, a tired postman appeared at the door, carrying a bag of letters in his hands. The owner warmly prepared a breakfast for him, and he started sorting the mail while enjoying his breakfast. **(The highest frequency word is "of", accounting for 8.45%)**
-- `1.0` A girl in deep sleep was woken up by a warm ray of sunshine, she saw the first ray of morning light, surrounded by birdsong and flowers, everything was full of vitality. \_ (The highest frequency word is "of", accounting for 5.45%)
-- `2.0` Every morning, he would sit on the balcony to have breakfast. Under the soft setting sun, everything looked very peaceful. However, one day, when he was about to pick up his breakfast, an optimistic little bird flew by, bringing him a good mood for the day. \_ (The highest frequency word is "of", accounting for 4.94%)
+- `1.0` A girl in deep sleep was woken up by a warm ray of sunshine, she saw the first ray of morning light, surrounded by birdsong and flowers, everything was full of vitality. (The highest frequency word is "of", accounting for 5.45%)
+- `2.0` Every morning, he would sit on the balcony to have breakfast. Under the soft setting sun, everything looked very peaceful. However, one day, when he was about to pick up his breakfast, an optimistic little bird flew by, bringing him a good mood for the day. (The highest frequency word is "of", accounting for 4.94%)
+
+
+
+### `reasoning_effort`
+
+The `reasoning_effort` parameter controls the strength of the reasoning process. This setting affects the depth of reasoning the model performs when generating a response. The available values are **`low`**, **`medium`**, and **`high`**, with the following meanings:
+
+- **low**: Lower reasoning effort, resulting in faster response times. Suitable for scenarios where quick responses are needed, but it may sacrifice some reasoning accuracy.
+- **medium** (default): Balances reasoning accuracy and response speed, suitable for most scenarios.
+- **high**: Higher reasoning effort, producing more detailed and complex responses, but slower response times and greater token consumption.
+
+By adjusting the `reasoning_effort` parameter, you can find an appropriate balance between response speed and reasoning depth based on your needs. For example, in conversational scenarios, if fast responses are a priority, you can choose low reasoning effort; if more complex analysis or reasoning is needed, you can opt for high reasoning effort.
+
+
+ This parameter is only applicable to reasoning models, such as OpenAI's `o1`, `o1-mini`, `o3-mini`, etc.
+
diff --git a/DigitalHumanWeb/docs/usage/agents/model.zh-CN.mdx b/DigitalHumanWeb/docs/usage/agents/model.zh-CN.mdx
index 95264e4..578dd40 100644
--- a/DigitalHumanWeb/docs/usage/agents/model.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/model.zh-CN.mdx
@@ -41,9 +41,9 @@ LLM 看似很神奇,但本质还是一个概率问题,神经网络根据输
### `top_p`
-核采样 top_p 也是采样参数,跟 temperature 不一样的采样方式。模型在输出之前,会生成一堆 token,这些 token 根据质量高低排名,核采样模式中候选词列表是动态的,从 tokens 里按百分比选择候选词。 top_p 为选择 token 引入了随机性,让其他高分的 token 有被选择的机会,不会总是选最高分的。
+核采样 `top_p` 也是采样参数,跟 temperature 不一样的采样方式。模型在输出之前,会生成一堆 token,这些 token 根据质量高低排名,核采样模式中候选词列表是动态的,从 tokens 里按百分比选择候选词。 top\_p 为选择 token 引入了随机性,让其他高分的 token 有被选择的机会,不会总是选最高分的。
-top\_p 与随机性类似,一般来说不建议和随机性 temperature 一起更改
+`top_p` 与随机性类似,一般来说不建议和随机性 temperature 一起更改
@@ -67,8 +67,24 @@ Presence Penalty 参数可以看作是对生成文本中重复内容的一种惩
是一种机制,通过对文本中频繁出现的新词汇施加惩罚,以减少模型重复同一词语的可能性,值越大,越有可能降低重复字词。
-- `-2.0` 当早间新闻开始播出,我发现我家电视现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在 _(频率最高的词是 “现在”,占比 44.79%)_
-- `-1.0` 他总是在清晨看新闻,在电视前看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看 _(频率最高的词是 “看”,占比 57.69%)_
+- `-2.0` 当早间新闻开始播出,我发现我家电视现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在 *(频率最高的词是 “现在”,占比 44.79%)*
+- `-1.0` 他总是在清晨看新闻,在电视前看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看 *(频率最高的词是 “看”,占比 57.69%)*
- `0.0` 当清晨的阳光洒进小餐馆时,一名疲倦的邮递员出现在门口,他的手中提着一袋信件。店主热情地为他准备了一份早餐,他在享用早餐的同时开始整理邮件。**(频率最高的词是 “的”,占比 8.45%)**
-- `1.0` 一个深度睡眠的女孩被一阵温暖的阳光唤醒,她看到了早晨的第一缕阳光,周围是鸟语花香,一切都充满了生机。_(频率最高的词是 “的”,占比 5.45%)_
-- `2.0` 每天早上,他都会在阳台上坐着吃早餐。在柔和的夕阳照耀下,一切看起来都非常宁静。然而有一天,当他准备端起早餐的时候,一只乐观的小鸟飞过,给他带来了一天的好心情。 _(频率最高的词是 “的”,占比 4.94%)_
+- `1.0` 一个深度睡眠的女孩被一阵温暖的阳光唤醒,她看到了早晨的第一缕阳光,周围是鸟语花香,一切都充满了生机。*(频率最高的词是 “的”,占比 5.45%)*
+- `2.0` 每天早上,他都会在阳台上坐着吃早餐。在柔和的夕阳照耀下,一切看起来都非常宁静。然而有一天,当他准备端起早餐的时候,一只乐观的小鸟飞过,给他带来了一天的好心情。 *(频率最高的词是 “的”,占比 4.94%)*
+
+
+
+### `reasoning_effort`
+
+`reasoning_effort` 参数用于控制推理过程的强度。此参数的设置会影响模型在生成回答时的推理深度。可选值包括 **`low`**、**`medium`** 和 **`high`**,具体含义如下:
+
+- **low(低)**:推理强度较低,生成速度较快,适用于需要快速响应的场景,但可能牺牲一定的推理精度。
+- **medium(中,默认值)**:平衡推理精度与响应速度,适用于大多数场景。
+- **high(高)**:推理强度较高,生成更为详细和复杂的回答,但响应时间较长,且消耗更多的 Token。
+
+通过调整 `reasoning_effort` 参数,可以根据需求在生成速度与推理深度之间找到适合的平衡。例如,在对话场景中,如果更关注快速响应,可以选择低推理强度;如果需要更复杂的分析或推理,可以选择高推理强度。
+
+
+ 该参数仅适用于推理模型,如 OpenAI 的 `o1`、`o1-mini`、`o3-mini` 等。
+
diff --git a/DigitalHumanWeb/docs/usage/agents/prompt.mdx b/DigitalHumanWeb/docs/usage/agents/prompt.mdx
index 6d38cf6..9a9e094 100644
--- a/DigitalHumanWeb/docs/usage/agents/prompt.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/prompt.mdx
@@ -30,7 +30,7 @@ Generative AI is very useful, but it requires human guidance. In most cases, gen
Let's look at a basic discussion prompt example:
-> _"What are the most urgent environmental issues facing our planet, and what actions can individuals take to help address these issues?"_
+> *"What are the most urgent environmental issues facing our planet, and what actions can individuals take to help address these issues?"*
We can convert it into a simple prompt for the assistant to answer the following questions: placed at the front.
@@ -54,17 +54,16 @@ The second prompt generates longer output and better structure. The use of the t
There are several ways to improve the quality and effectiveness of prompts:
-- **Be Clear About Your Needs:** The model's output will strive to meet your needs, so if your needs are not clear, the output may not meet expectations.
-- **Use Correct Grammar and Spelling:** The model will try to mimic your language style, so if your language style is problematic, the output may also be problematic.
-- **Provide Sufficient Contextual Information:** The model will generate output based on the contextual information you provide, so if the information is insufficient, it may not produce the desired results.
-
+ - **Be Clear About Your Needs:** The model's output will strive to meet your needs, so if your needs are not clear, the output may not meet expectations.
+ - **Use Correct Grammar and Spelling:** The model will try to mimic your language style, so if your language style is problematic, the output may also be problematic.
+ - **Provide Sufficient Contextual Information:** The model will generate output based on the contextual information you provide, so if the information is insufficient, it may not produce the desired results.
After formulating effective prompts for discussing issues, you now need to refine the generated results. This may involve adjusting the output to fit constraints such as word count or combining concepts from different generated results.
A simple method of iteration is to generate multiple outputs and review them to understand the concepts and structures being used. Once the outputs have been evaluated, you can select the most suitable ones and combine them into a coherent response. Another iterative method is to start small and **gradually expand**. This requires more than one prompt: an initial prompt for drafting the initial one or two paragraphs, followed by additional prompts to expand on the content already written. Here is a potential philosophical discussion prompt:
-> _"Is mathematics an invention or a discovery? Use careful reasoning to explain your answer."_
+> *"Is mathematics an invention or a discovery? Use careful reasoning to explain your answer."*
Add it to a simple prompt as follows:
diff --git a/DigitalHumanWeb/docs/usage/agents/prompt.zh-CN.mdx b/DigitalHumanWeb/docs/usage/agents/prompt.zh-CN.mdx
index 3157892..5c2e7de 100644
--- a/DigitalHumanWeb/docs/usage/agents/prompt.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/prompt.zh-CN.mdx
@@ -24,7 +24,7 @@ tags:
让我们看一个基本的讨论问题的例子:
-> _"我们星球面临的最紧迫的环境问题是什么,个人可以采取哪些措施来帮助解决这些问题?"_
+> *"我们星球面临的最紧迫的环境问题是什么,个人可以采取哪些措施来帮助解决这些问题?"*
我们可以将其转化为简单的助手提示,将回答以下问题:放在前面。
@@ -50,17 +50,16 @@ tags:
提升 prompt 质量和效果的方法主要有以下几点:
-- **尽量明确你的需求:** 模型的输出会尽可能满足你的需求,所以如果你的需求不明确,输出可能会不如预期。
-- **使用正确的语法和拼写:** 模型会尽可能模仿你的语言风格,所以如果你的语言风格有问题,输出可能也会有问题。
-- **提供足够的上下文信息:** 模型会根据你提供的上下文信息生成输出,所以如果你提供的上下文信息不足,可能无法生成你想要的结果。
-
+ - **尽量明确你的需求:** 模型的输出会尽可能满足你的需求,所以如果你的需求不明确,输出可能会不如预期。
+ - **使用正确的语法和拼写:** 模型会尽可能模仿你的语言风格,所以如果你的语言风格有问题,输出可能也会有问题。
+ - **提供足够的上下文信息:** 模型会根据你提供的上下文信息生成输出,所以如果你提供的上下文信息不足,可能无法生成你想要的结果。
在为讨论问题制定有效的提示后,您现在需要细化生成的结果。这可能涉及到调整输出以符合诸如字数等限制,或将不同生成的结果的概念组合在一起。
迭代的一个简单方法是生成多个输出并查看它们,以了解正在使用的概念和结构。一旦评估了输出,您就可以选择最合适的输出并将它们组合成一个连贯的回答。另一种迭代的方法是逐步开始,然后**逐步扩展**。这需要不止一个提示:一个起始提示,用于撰写最初的一两段,然后是其他提示,以扩展已经写过的内容。以下是一个潜在的哲学讨论问题:
-> _"数学是发明还是发现?用仔细的推理来解释你的答案。"_
+> *"数学是发明还是发现?用仔细的推理来解释你的答案。"*
将其添加到一个简单的提示中,如下所示:
diff --git a/DigitalHumanWeb/docs/usage/agents/topics.mdx b/DigitalHumanWeb/docs/usage/agents/topics.mdx
index 1c8f296..88048a8 100644
--- a/DigitalHumanWeb/docs/usage/agents/topics.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/topics.mdx
@@ -19,8 +19,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
- }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
+}
/>
- **Save Topic:** During a conversation, if you want to save the current context and start a new topic, you can click the save button next to the send button.
diff --git a/DigitalHumanWeb/docs/usage/agents/topics.zh-CN.mdx b/DigitalHumanWeb/docs/usage/agents/topics.zh-CN.mdx
index 2a90338..bdf1527 100644
--- a/DigitalHumanWeb/docs/usage/agents/topics.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/agents/topics.zh-CN.mdx
@@ -17,8 +17,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
- }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
+}
/>
- **保存话题:** 在聊天过程中,如果想要保存当前上下文并开启新的话题,可以点击发送按钮旁边的保存按钮。
diff --git a/DigitalHumanWeb/docs/usage/features/agent-market.mdx b/DigitalHumanWeb/docs/usage/features/agent-market.mdx
index fca028f..8037690 100644
--- a/DigitalHumanWeb/docs/usage/features/agent-market.mdx
+++ b/DigitalHumanWeb/docs/usage/features/agent-market.mdx
@@ -19,8 +19,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png'
- }
+'https://github.com/user-attachments/assets/b3ab6e35-4fbc-468d-af10-e3e0c687350f'
+}
/>
In LobeChat's Assistant Market, creators can discover a vibrant and innovative community that brings together numerous carefully designed assistants. These assistants not only play a crucial role in work scenarios but also provide great convenience in the learning process. Our market is not just a showcase platform, but also a collaborative space. Here, everyone can contribute their wisdom and share their personally developed assistants.
diff --git a/DigitalHumanWeb/docs/usage/features/agent-market.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/agent-market.zh-CN.mdx
index 91d6927..38f1136 100644
--- a/DigitalHumanWeb/docs/usage/features/agent-market.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/agent-market.zh-CN.mdx
@@ -18,8 +18,8 @@ tags:
alt={'助手市场'}
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png'
- }
+'https://github.com/user-attachments/assets/b3ab6e35-4fbc-468d-af10-e3e0c687350f'
+}
/>
在 LobeChat 的助手市场中,创作者们可以发现一个充满活力和创新的社区,它汇聚了众多精心设计的助手,这些助手不仅在工作场景中发挥着重要作用,也在学习过程中提供了极大的便利。我们的市场不仅是一个展示平台,更是一个协作的空间。在这里,每个人都可以贡献自己的智慧,分享个人开发的助手。
diff --git a/DigitalHumanWeb/docs/usage/features/artifacts.mdx b/DigitalHumanWeb/docs/usage/features/artifacts.mdx
new file mode 100644
index 0000000..dcbe923
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/artifacts.mdx
@@ -0,0 +1,23 @@
+---
+title: Artifacts Support
+description: >-
+ Discover the power of Claude Artifacts for dynamic content creation and
+ visualization.
+tags:
+ - Claude Artifacts
+ - LobeChat
+ - AI Interaction
+ - Dynamic Content
+---
+
+# Artifacts Support
+
+
+
+Experience the power of Claude Artifacts, now integrated into LobeChat. This revolutionary feature expands the boundaries of AI-human interaction, enabling real-time creation and visualization of diverse content formats.
+
+Create and visualize with unprecedented flexibility:
+
+- Generate and display dynamic SVG graphics
+- Build and render interactive HTML pages in real-time
+- Produce professional documents in multiple formats
diff --git a/DigitalHumanWeb/docs/usage/features/artifacts.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/artifacts.zh-CN.mdx
new file mode 100644
index 0000000..07b2b3e
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/artifacts.zh-CN.mdx
@@ -0,0 +1,22 @@
+---
+title: 支持白板 (Artifacts)
+description: 体验 LobeChat 的 Claude Artifacts,实时创建和可视化内容。
+tags:
+ - Claude Artifacts
+ - LobeChat
+ - 实时创作
+ - 动态 SVG
+ - 交互式 HTML
+---
+
+# 支持白板 (Artifacts)
+
+
+
+体验集成于 LobeChat 的 Claude Artifacts 能力。这项革命性功能突破了 AI 人机交互的边界,让您能够实时创建和可视化各种格式的内容。
+
+以前所未有的灵活度进行创作与可视化:
+
+- 生成并展示动态 SVG 图形
+- 实时构建与渲染交互式 HTML 页面
+- 输出多种格式的专业文档
diff --git a/DigitalHumanWeb/docs/usage/features/auth.mdx b/DigitalHumanWeb/docs/usage/features/auth.mdx
index ba9afb9..4bc91b4 100644
--- a/DigitalHumanWeb/docs/usage/features/auth.mdx
+++ b/DigitalHumanWeb/docs/usage/features/auth.mdx
@@ -17,11 +17,7 @@ tags:
# Support Multi-User Management
-
+
In modern applications, user management and identity verification are essential functions. To meet the diverse needs of different users, LobeChat provides two main user authentication and management solutions: `next-auth` and `Clerk`. Whether you are looking for simple user registration and login or need advanced multi-factor authentication and user management, LobeChat can flexibly accommodate your requirements.
diff --git a/DigitalHumanWeb/docs/usage/features/auth.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/auth.zh-CN.mdx
index 983c0c7..32dda43 100644
--- a/DigitalHumanWeb/docs/usage/features/auth.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/auth.zh-CN.mdx
@@ -12,11 +12,7 @@ tags:
# 身份验证系统 / 多用户管理支持
-
+
在现代应用中,用户管理和身份验证是至关重要的功能。为满足不同用户的多样化需求,LobeChat 提供了两种主要的用户认证和管理方案:`next-auth` 和 `Clerk`。无论您是追求简便的用户注册登录,还是需要更高级的多因素认证和用户管理,LobeChat 都可以灵活实现。
diff --git a/DigitalHumanWeb/docs/usage/features/branching-conversations.mdx b/DigitalHumanWeb/docs/usage/features/branching-conversations.mdx
new file mode 100644
index 0000000..1cc5d4f
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/branching-conversations.mdx
@@ -0,0 +1,21 @@
+---
+title: Branching Conversations
+description: Explore dynamic AI chats with Branching Conversations for deeper interactions.
+tags:
+ - Branching Conversations
+ - AI Chat
+ - Dynamic Conversations
+---
+
+# Branching Conversations
+
+
+
+Introducing a more natural and flexible way to chat with AI. With Branch Conversations, your discussions can flow in multiple directions, just like human conversations do. Create new conversation branches from any message, giving you the freedom to explore different paths while preserving the original context.
+
+Choose between two powerful modes:
+
+- **Continuation Mode:** Seamlessly extend your current discussion while maintaining valuable context
+- **Standalone Mode:** Start fresh with a new topic based on any previous message
+
+This groundbreaking feature transforms linear conversations into dynamic, tree-like structures, enabling deeper exploration of ideas and more productive interactions.
diff --git a/DigitalHumanWeb/docs/usage/features/branching-conversations.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/branching-conversations.zh-CN.mdx
new file mode 100644
index 0000000..16caf10
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/branching-conversations.zh-CN.mdx
@@ -0,0 +1,21 @@
+---
+title: 分支对话
+description: 探索分支对话功能,提升 AI 交流的自然性与灵活性。
+tags:
+ - 分支对话
+ - AI 交流
+ - 对话模式
+---
+
+# 分支对话
+
+
+
+为您带来更自然、更灵活的 AI 对话方式。通过分支对话功能,您的讨论可以像人类对话一样自然延伸。在任意消息处创建新的对话分支,让您在保留原有上下文的同时,自由探索不同的对话方向。
+
+两种强大模式任您选择:
+
+- **延续模式**:无缝延展当前讨论,保持宝贵的对话上下文
+- **独立模式**:基于任意历史消息,开启全新话题探讨
+
+这项突破性功能将线性对话转变为动态的树状结构,让您能够更深入地探索想法,实现更高效的互动体验。
diff --git a/DigitalHumanWeb/docs/usage/features/cot.mdx b/DigitalHumanWeb/docs/usage/features/cot.mdx
new file mode 100644
index 0000000..f901182
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/cot.mdx
@@ -0,0 +1,18 @@
+---
+title: Chain of Thought
+description: >-
+ Explore AI's decision-making with Chain of Thought visualization for clear
+ insights.
+tags:
+ - AI Reasoning
+ - Chain of Thought
+ - CoT Visualization
+---
+
+# Chain of Thought
+
+
+
+Experience AI reasoning like never before. Watch as complex problems unfold step by step through our innovative Chain of Thought (CoT) visualization. This breakthrough feature provides unprecedented transparency into AI's decision-making process, allowing you to observe how conclusions are reached in real-time.
+
+By breaking down complex reasoning into clear, logical steps, you can better understand and validate the AI's problem-solving approach. Whether you're debugging, learning, or simply curious about AI reasoning, CoT visualization transforms abstract thinking into an engaging, interactive experience.
diff --git a/DigitalHumanWeb/docs/usage/features/cot.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/cot.zh-CN.mdx
new file mode 100644
index 0000000..c2890b4
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/cot.zh-CN.mdx
@@ -0,0 +1,18 @@
+---
+title: 思维链 (CoT)
+description: 体验思维链 (CoT) 的 AI 推理过程,了解复杂问题的解析步骤。
+tags:
+ - 思维链
+ - AI 推理
+ - 可视化
+ - 逻辑步骤
+ - 决策过程
+---
+
+# 思维链 (CoT)
+
+
+
+体验前所未有的 AI 推理过程。通过创新的思维链(CoT)可视化功能,您可以实时观察复杂问题是如何一步步被解析的。这项突破性的功能为 AI 的决策过程提供了前所未有的透明度,让您能够清晰地了解结论是如何得出的。
+
+通过将复杂的推理过程分解为清晰的逻辑步骤,您可以更好地理解和验证 AI 的解题思路。无论您是在调试问题、学习知识,还是单纯对 AI 推理感兴趣,思维链可视化都能将抽象思维转化为一种引人入胜的互动体验。
diff --git a/DigitalHumanWeb/docs/usage/features/database.mdx b/DigitalHumanWeb/docs/usage/features/database.mdx
index 83ef17b..db0d345 100644
--- a/DigitalHumanWeb/docs/usage/features/database.mdx
+++ b/DigitalHumanWeb/docs/usage/features/database.mdx
@@ -16,11 +16,7 @@ tags:
# Local / Cloud Database
-
+
In modern application development, the choice of data storage solution is crucial. To meet the needs of different users, LobeChat offers flexible configurations that support both local and server-side databases. Whether you prioritize data privacy and control or seek a convenient user experience, LobeChat can provide excellent solutions for you.
diff --git a/DigitalHumanWeb/docs/usage/features/database.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/database.zh-CN.mdx
index 5716320..68b7dc4 100644
--- a/DigitalHumanWeb/docs/usage/features/database.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/database.zh-CN.mdx
@@ -12,11 +12,7 @@ tags:
# 本地 / 云端数据存储
-
+
在现代应用开发中,数据存储方案的选择至关重要。为了满足不同用户的需求,LobeChat 提供了同时支持本地数据库和服务端数据库的灵活配置。无论您是注重数据隐私与掌控,还是追求便捷的使用体验,LobeChat 都能为您提供卓越的解决方案。
@@ -32,12 +28,12 @@ tags:
## 服务端数据库:便捷与高效的使用体验
-对于追求便捷使用体验的用户,LobeChat 支持 PostgreSQL 作为服务端数据库。通过 Dirzzle ORM 管理数据,结合 Clerk 进行身份验证,LobeChat 能够为用户提供高效、可靠的服务端数据管理方案。
+对于追求便捷使用体验的用户,LobeChat 支持 PostgreSQL 作为服务端数据库。通过 Drizzle ORM 管理数据,结合 Clerk 进行身份验证,LobeChat 能够为用户提供高效、可靠的服务端数据管理方案。
### 服务端数据库技术栈
- **DB**: PostgreSQL(默认使用 Neon)
-- **ORM**: Dirzzle ORM
+- **ORM**: Drizzle ORM
- **Auth**: Clerk
- **Server Router**: tRPC
diff --git a/DigitalHumanWeb/docs/usage/features/knowledge-base.mdx b/DigitalHumanWeb/docs/usage/features/knowledge-base.mdx
new file mode 100644
index 0000000..151fadf
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/knowledge-base.mdx
@@ -0,0 +1,24 @@
+---
+title: File Upload / Knowledge Base
+description: >-
+ Discover LobeChat's file upload and knowledge base features for enhanced user
+ experience.
+tags:
+ - File Upload
+ - Knowledge Base
+ - LobeChat
+ - User Management
+ - File Management
+---
+
+# File Upload / Knowledge Base
+
+
+
+LobeChat supports file upload and knowledge base functionality. You can upload various types of files including documents, images, audio, and video, as well as create knowledge bases, making it convenient for users to manage and search for files. Additionally, you can utilize files and knowledge base features during conversations, enabling a richer dialogue experience.
+
+
+
+
+ Learn more on [📘 LobeChat Knowledge Base Launch — From Now On, Every Step Counts](https://lobehub.com/blog/knowledge-base)
+
diff --git a/DigitalHumanWeb/docs/usage/features/knowledge-base.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/knowledge-base.zh-CN.mdx
new file mode 100644
index 0000000..0506a24
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/features/knowledge-base.zh-CN.mdx
@@ -0,0 +1,21 @@
+---
+title: 文件上传 / 知识库
+description: 了解LobeChat的文件上传与知识库功能,提升对话体验。
+tags:
+ - 文件上传
+ - 知识库
+ - LobeChat
+ - 对话体验
+---
+
+# 文件上传 / 知识库
+
+
+
+LobeChat 支持文件上传与知识库功能,你可以上传文件、图片、音频、视频等多种类型的文件,以及创建知识库,方便用户管理和查找文件。同时在对话中使用文件和知识库功能,实现更加丰富的对话体验。
+
+
+
+
+ 查阅 [📘 LobeChat 知识库上线 —— 此刻起,跬步千里](https://lobehub.com/zh/blog/knowledge-base) 了解详情。
+
diff --git a/DigitalHumanWeb/docs/usage/features/local-llm.mdx b/DigitalHumanWeb/docs/usage/features/local-llm.mdx
index a84df3c..3a07271 100644
--- a/DigitalHumanWeb/docs/usage/features/local-llm.mdx
+++ b/DigitalHumanWeb/docs/usage/features/local-llm.mdx
@@ -15,12 +15,7 @@ tags:
# Local Large Language Model (LLM) Support
-
+Available in >=0.127.0, currently only supports Docker deployment
@@ -52,5 +47,6 @@ Now, let's embark on this exciting journey together! Through the collaboration o
+
diff --git a/DigitalHumanWeb/docs/usage/features/local-llm.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/local-llm.zh-CN.mdx
index c48643a..b4c044e 100644
--- a/DigitalHumanWeb/docs/usage/features/local-llm.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/local-llm.zh-CN.mdx
@@ -7,12 +7,7 @@ tags:
# 支持本地大语言模型(LLM)
-
+在 >=v0.127.0 版本中可用,目前仅支持 Docker 部署
@@ -44,5 +39,6 @@ docker run -d -p 3210:3210 -e OLLAMA_PROXY_URL=http://host.docker.internal:11434
+
diff --git a/DigitalHumanWeb/docs/usage/features/mobile.mdx b/DigitalHumanWeb/docs/usage/features/mobile.mdx
index d74d728..1cd4175 100644
--- a/DigitalHumanWeb/docs/usage/features/mobile.mdx
+++ b/DigitalHumanWeb/docs/usage/features/mobile.mdx
@@ -13,11 +13,7 @@ tags:
# Mobile Device Adaptation
-
+
LobeChat has undergone a series of optimized designs for mobile devices to enhance the user's mobile experience.
diff --git a/DigitalHumanWeb/docs/usage/features/mobile.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/mobile.zh-CN.mdx
index 5b881eb..f90421c 100644
--- a/DigitalHumanWeb/docs/usage/features/mobile.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/mobile.zh-CN.mdx
@@ -12,11 +12,7 @@ tags:
# 移动设备适配
-
+
LobeChat 针对移动设备进行了一系列的优化设计,以提升用户的移动体验。
diff --git a/DigitalHumanWeb/docs/usage/features/multi-ai-providers.mdx b/DigitalHumanWeb/docs/usage/features/multi-ai-providers.mdx
index c212bad..0c02536 100644
--- a/DigitalHumanWeb/docs/usage/features/multi-ai-providers.mdx
+++ b/DigitalHumanWeb/docs/usage/features/multi-ai-providers.mdx
@@ -18,12 +18,7 @@ tags:
# Multi-Model Service Provider Support
-
+Available in version 0.123.0 and later
@@ -48,19 +43,16 @@ We have implemented support for the following model service providers:
- **DeepSeek**: Integrated with the DeepSeek series models, an innovative AI startup from China, The product has been designed to provide a model that balances performance with price. [Learn more](https://www.deepseek.com/)
- **Qwen**: Integrated with the Qwen series models, including the latest **qwen-turbo**, **qwen-plus** and **qwen-max**. [Learn more](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction)
-At the same time, we are also planning to support more model service providers, such as Replicate and Perplexity, to further enrich our service provider library. If you would like LobeChat to support your favorite service provider, feel free to join our [community discussion](https://github.com/lobehub/lobe-chat/discussions/1284).
+At the same time, we are also planning to support more model service providers, such as Replicate and Perplexity, to further enrich our service provider library. If you would like LobeChat to support your favorite service provider, feel free to join our [community discussion](https://github.com/lobehub/lobe-chat/discussions/6157).
## Local Model Support
-
+
To meet the specific needs of users, LobeChat also supports the use of local models based on [Ollama](https://ollama.ai), allowing users to flexibly use their own or third-party models. For more details, see [Local Model Support](/docs/usage/features/local-llm).
+
diff --git a/DigitalHumanWeb/docs/usage/features/multi-ai-providers.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/multi-ai-providers.zh-CN.mdx
index 761f6e7..8d490d4 100644
--- a/DigitalHumanWeb/docs/usage/features/multi-ai-providers.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/multi-ai-providers.zh-CN.mdx
@@ -18,12 +18,7 @@ tags:
# 多模型服务商支持
-
+在 0.123.0 及以后版本中可用
@@ -48,19 +43,16 @@ tags:
- **DeepSeek**: 接入了 DeepSeek 的 AI 模型,包括最新的 **DeepSeek-V2**,提供兼顾性能与价格的模型。[了解更多](https://www.deepseek.com/)
- **Qwen (通义千问)**: 接入了 Qwen 的 AI 模型,包括最新的 **qwen-turbo**,**qwen-plus** 和 **qwen-max** 等模型。[了解更多](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction)
-同时,我们也在计划支持更多的模型服务商,如 Replicate 和 Perplexity 等,以进一步丰富我们的服务商库。如果你希望让 LobeChat 支持你喜爱的服务商,欢迎加入我们的[社区讨论](https://github.com/lobehub/lobe-chat/discussions/1284)。
+同时,我们也在计划支持更多的模型服务商,如 Replicate 和 Perplexity 等,以进一步丰富我们的服务商库。如果你希望让 LobeChat 支持你喜爱的服务商,欢迎加入我们的[社区讨论](https://github.com/lobehub/lobe-chat/discussions/6157)。
## 本地模型支持
-
+
为了满足特定用户的需求,LobeChat 还基于 [Ollama](https://ollama.ai) 支持了本地模型的使用,让用户能够更灵活地使用自己的或第三方的模型,详见 [本地模型支持](/zh/docs/usage/features/local-llm)。
+
diff --git a/DigitalHumanWeb/docs/usage/features/plugin-system.mdx b/DigitalHumanWeb/docs/usage/features/plugin-system.mdx
index 80165cf..28db924 100644
--- a/DigitalHumanWeb/docs/usage/features/plugin-system.mdx
+++ b/DigitalHumanWeb/docs/usage/features/plugin-system.mdx
@@ -20,8 +20,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670883-33c43a5c-a512-467e-855c-fa299548cce5.png'
- }
+'https://github.com/user-attachments/assets/66a891ac-01b6-4e3f-b978-2eb07b489b1b'
+}
/>
The plugin ecosystem of LobeChat is an important extension of its core functionality, greatly enhancing the practicality and flexibility of the LobeChat assistant.
@@ -32,7 +32,7 @@ By utilizing plugins, LobeChat assistants can obtain and process real-time infor
In addition, these plugins are not limited to news aggregation, but can also extend to other practical functions, such as quickly searching documents, generating images, obtaining data from various platforms like Bilibili, Steam, and interacting with various third-party services.
-Learn more about [plugin usage](/docs/usage/plugins/basic) by checking it out.
+Learn more about [plugin usage](/docs/usage/plugins/basic-usage) by checking it out.
To help developers better participate in this ecosystem, we provide comprehensive development
@@ -67,20 +67,19 @@ The plugin system of LobeChat has now entered a stable stage, and we have basica
### ✅ Phase One of Plugins
-Implementing the separation of plugins from the main body, splitting the plugins into independent repositories for maintenance, and implementing dynamic loading of plugins. [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
+ Implementing the separation of plugins from the main body, splitting the plugins into independent repositories for maintenance, and implementing dynamic loading of plugins. [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
-### ✅ Phase Two of Plugins
+ ### ✅ Phase Two of Plugins
-The security and stability of plugin usage, more accurate presentation of abnormal states, maintainability and developer-friendliness of the plugin architecture. [**#97**](https://github.com/lobehub/lobe-chat/issues/97)
+ The security and stability of plugin usage, more accurate presentation of abnormal states, maintainability and developer-friendliness of the plugin architecture. [**#97**](https://github.com/lobehub/lobe-chat/issues/97)
-### ✅ Phase Three of Plugins
+ ### ✅ Phase Three of Plugins
-Higher-level and improved customization capabilities, support for OpenAPI schema invocation, compatibility with ChatGPT plugins, and the addition of Midjourney plugins. [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
+ Higher-level and improved customization capabilities, support for OpenAPI schema invocation, compatibility with ChatGPT plugins, and the addition of Midjourney plugins. [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
-### 💭 Phase Four of Plugins
-
-Comprehensive authentication, visual configuration of plugin definitions, Plugin SDK CLI, Python language development template, any other ideas? Join the discussion: [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
+ ### 💭 Phase Four of Plugins
+ Comprehensive authentication, visual configuration of plugin definitions, Plugin SDK CLI, Python language development template, any other ideas? Join the discussion: [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
[chat-plugin-sdk]: https://github.com/lobehub/chat-plugin-sdk
diff --git a/DigitalHumanWeb/docs/usage/features/plugin-system.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/plugin-system.zh-CN.mdx
index 1313ab1..bf0074a 100644
--- a/DigitalHumanWeb/docs/usage/features/plugin-system.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/plugin-system.zh-CN.mdx
@@ -15,8 +15,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670883-33c43a5c-a512-467e-855c-fa299548cce5.png'
- }
+'https://github.com/user-attachments/assets/66a891ac-01b6-4e3f-b978-2eb07b489b1b'
+}
/>
LobeChat 的插件生态系统是其核心功能的重要扩展,它极大地增强了 LobeChat 助手的实用性和灵活性。
@@ -27,7 +27,7 @@ LobeChat 的插件生态系统是其核心功能的重要扩展,它极大地
此外,这些插件不仅局限于新闻聚合,还可以扩展到其他实用的功能,如快速检索文档、生成图片、获取 Bilibili 、Steam 等各种平台数据,以及与其他各式各样的第三方服务交互。
-通过查看 [插件使用](/zh/docs/usage/plugins/basic) 了解更多。
+通过查看 [插件使用](/zh/docs/usage/plugins/basic-usage) 了解更多。
为了帮助开发者更好地参与到这个生态中来,我们在提供了全面的开发资源。这包括详尽的组件开发文档、功能齐全的软件开发工具包(SDK),以及样板示例,这些都是为了简化开发过程,降低开发者的入门门槛。
@@ -56,20 +56,19 @@ LobeChat 的插件系统目前已初步进入一个稳定阶段,我们已基
### ✅ 插件一期
-实现插件与主体分离,将插件拆分为独立仓库维护,并实现插件的动态加载。 [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
+ 实现插件与主体分离,将插件拆分为独立仓库维护,并实现插件的动态加载。 [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
-### ✅ 插件二期
+ ### ✅ 插件二期
-插件的安全性与使用的稳定性,更加精准地呈现异常状态,插件架构的可维护性与开发者友好。[**#97**](https://github.com/lobehub/lobe-chat/issues/97)
+ 插件的安全性与使用的稳定性,更加精准地呈现异常状态,插件架构的可维护性与开发者友好。[**#97**](https://github.com/lobehub/lobe-chat/issues/97)
-### ✅ 插件三期
+ ### ✅ 插件三期
-更高阶与完善的自定义能力,支持 OpenAPI schema 调用、兼容 ChatGPT 插件、新增 Midjourney 插件。 [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
+ 更高阶与完善的自定义能力,支持 OpenAPI schema 调用、兼容 ChatGPT 插件、新增 Midjourney 插件。 [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
-### 💭 插件四期
-
-完善的鉴权、可视化配置插件定义、 Plugin SDK CLI 、 Python 语言研发模板、还有什么想法?欢迎参与讨论: [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
+ ### 💭 插件四期
+ 完善的鉴权、可视化配置插件定义、 Plugin SDK CLI 、 Python 语言研发模板、还有什么想法?欢迎参与讨论: [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
[chat-plugin-sdk]: https://github.com/lobehub/chat-plugin-sdk
diff --git a/DigitalHumanWeb/docs/usage/features/pwa.mdx b/DigitalHumanWeb/docs/usage/features/pwa.mdx
index 606093d..c4ee493 100644
--- a/DigitalHumanWeb/docs/usage/features/pwa.mdx
+++ b/DigitalHumanWeb/docs/usage/features/pwa.mdx
@@ -14,12 +14,7 @@ tags:
# Progressive Web App (PWA)
-
+
We understand the importance of providing a seamless experience for users in today's multi-device environment. To achieve this, we have adopted Progressive Web App [PWA](https://support.google.com/chrome/answer/9658361) technology, which is a modern web technology that elevates web applications to a near-native app experience. Through PWA, LobeChat is able to provide a highly optimized user experience on both desktop and mobile devices, while maintaining lightweight and high performance characteristics. Visually and perceptually, we have also carefully designed it to ensure that its interface is indistinguishable from a native app, providing smooth animations, responsive layouts, and adaptation to different screen resolutions of various devices.
@@ -33,15 +28,13 @@ If you are unfamiliar with the installation process of PWA, you can follow the s
+ ### Run Chrome or Edge browser on your computer
-### Run Chrome or Edge browser on your computer
+ ### Visit the LobeChat webpage
-### Visit the LobeChat webpage
-
-### In the top right corner of the address bar, click the Install icon
-
-### Follow the on-screen instructions to complete the PWA installation
+ ### In the top right corner of the address bar, click the Install icon
+ ### Follow the on-screen instructions to complete the PWA installation
## Running on Safari
@@ -49,26 +42,19 @@ If you are unfamiliar with the installation process of PWA, you can follow the s
Safari PWA requires macOS Ventura or later. The PWA installed by Safari does not require Safari to be open; you can directly open the PWA app.
+ ### Run Safari browser on your computer
-### Run Safari browser on your computer
-
-### Visit the LobeChat webpage
-
-### In the top right corner of the address bar, click the Share icon
+ ### Visit the LobeChat webpage
-### Click Add to Dock
+ ### In the top right corner of the address bar, click the Share icon
-### Follow the on-screen instructions to complete the PWA installation
+ ### Click Add to Dock
+ ### Follow the on-screen instructions to complete the PWA installation
The default installed LobeChat PWA icon has a black background, you can use cmd + i to paste the following image to replace it with a white background.
-
+
diff --git a/DigitalHumanWeb/docs/usage/features/pwa.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/pwa.zh-CN.mdx
index b7b5564..39fe52c 100644
--- a/DigitalHumanWeb/docs/usage/features/pwa.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/pwa.zh-CN.mdx
@@ -14,12 +14,7 @@ tags:
# 渐进式 Web 应用(PWA)
-
+
我们深知在当今多设备环境下为用户提供无缝体验的重要性。为此,我们采用了渐进式 Web 应用 [PWA](https://support.google.com/chrome/answer/9658361) 技术,这是一种能够将网页应用提升至接近原生应用体验的现代 Web 技术。通过 PWA,LobeChat 能够在桌面和移动设备上提供高度优化的用户体验,同时保持轻量级和高性能的特点。在视觉和感觉上,我们也经过精心设计,以确保它的界面与原生应用无差别,提供流畅的动画、响应式布局和适配不同设备的屏幕分辨率。
@@ -33,15 +28,13 @@ tags:
+ ### 在电脑上运行 Chrome 或 Edge 浏览器
-### 在电脑上运行 Chrome 或 Edge 浏览器
+ ### 访问 LobeChat 网页
-### 访问 LobeChat 网页
-
-### 在地址栏的右上角,单击 安装 图标
-
-### 根据屏幕上的指示完成 PWA 的安装
+ ### 在地址栏的右上角,单击 安装 图标
+ ### 根据屏幕上的指示完成 PWA 的安装
## Safari 浏览器上运行
@@ -49,26 +42,19 @@ tags:
Safari PWA 需要 macOS Ventura 或更高版本。Safari 安装的 PWA 并不要求 Safari 是打开状态,可以直接打开 PWA 应用。
+ ### 在电脑上运行 Safari 浏览器
-### 在电脑上运行 Safari 浏览器
-
-### 访问 LobeChat 网页
-
-### 在地址栏的右上角,单击 分享 图标
+ ### 访问 LobeChat 网页
-### 点选 添加到程序坞
+ ### 在地址栏的右上角,单击 分享 图标
-### 根据屏幕上的指示完成 PWA 的安装
+ ### 点选 添加到程序坞
+ ### 根据屏幕上的指示完成 PWA 的安装
默认安装的 LobeChat PWA 图标是黑色背景的,您可以在自行使用 cmd + i 粘贴如下图片替换为白色背景的。
-
+
diff --git a/DigitalHumanWeb/docs/usage/features/text-to-image.mdx b/DigitalHumanWeb/docs/usage/features/text-to-image.mdx
index 01a7a26..83aa958 100644
--- a/DigitalHumanWeb/docs/usage/features/text-to-image.mdx
+++ b/DigitalHumanWeb/docs/usage/features/text-to-image.mdx
@@ -19,8 +19,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/297746445-0ff762b9-aa08-4337-afb7-12f932b6efbb.png'
- }
+'https://github.com/user-attachments/assets/708274a7-2458-494b-a6ec-b73dfa1fa7c2'
+}
/>
Supporting the latest text-to-image generation technology, LobeChat now enables users to directly utilize the Text to Image tool during conversations with the assistant. By harnessing the capabilities of AI tools such as [DALL-E 3](https://openai.com/dall-e-3), [MidJourney](https://www.midjourney.com/), and [Pollinations](https://pollinations.ai/), assistants can now transform your ideas into images. This allows for a more private and immersive creative process.
diff --git a/DigitalHumanWeb/docs/usage/features/text-to-image.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/text-to-image.zh-CN.mdx
index c512847..56af451 100644
--- a/DigitalHumanWeb/docs/usage/features/text-to-image.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/text-to-image.zh-CN.mdx
@@ -19,8 +19,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/297746445-0ff762b9-aa08-4337-afb7-12f932b6efbb.png'
- }
+'https://github.com/user-attachments/assets/708274a7-2458-494b-a6ec-b73dfa1fa7c2'
+}
/>
支持最新的文本到图片生成技术,LobeChat 现在能够让用户在与助手对话中直接调用文成图工具进行创作。通过利用 [`DALL-E 3`](https://openai.com/dall-e-3)、[`MidJourney`](https://www.midjourney.com/) 和 [`Pollinations`](https://pollinations.ai/) 等 AI 工具的能力, 助手们现在可以将你的想法转化为图像。同时可以更私密和沉浸式的完成你的创造过程。
diff --git a/DigitalHumanWeb/docs/usage/features/theme.mdx b/DigitalHumanWeb/docs/usage/features/theme.mdx
index 6172ff5..76be42c 100644
--- a/DigitalHumanWeb/docs/usage/features/theme.mdx
+++ b/DigitalHumanWeb/docs/usage/features/theme.mdx
@@ -15,12 +15,7 @@ tags:
# Custom Themes
-
+
LobeChat places a strong emphasis on personalized user experiences in its interface design, and thus introduces flexible and diverse theme modes, including a light mode for daytime and a dark mode for nighttime.
diff --git a/DigitalHumanWeb/docs/usage/features/theme.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/theme.zh-CN.mdx
index 778cf2c..1a39235 100644
--- a/DigitalHumanWeb/docs/usage/features/theme.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/theme.zh-CN.mdx
@@ -12,12 +12,7 @@ tags:
# 自定义主题
-
+
LobeChat 在界面设计上十分考虑用户的个性化体验,因此引入了灵活多变的主题模式,其中包括日间的亮色模式和夜间的深色模式。
diff --git a/DigitalHumanWeb/docs/usage/features/tts.mdx b/DigitalHumanWeb/docs/usage/features/tts.mdx
index 755c784..fcff7d0 100644
--- a/DigitalHumanWeb/docs/usage/features/tts.mdx
+++ b/DigitalHumanWeb/docs/usage/features/tts.mdx
@@ -22,8 +22,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/284072124-c9853d8d-f1b5-44a8-a305-45ebc0f6d19a.png'
- }
+'https://github.com/user-attachments/assets/50189597-2cc3-4002-b4c8-756a52ad5c0a'
+}
/>
LobeChat supports Text-to-Speech (TTS) and Speech-to-Text (STT) technologies. Our application can convert text information into clear voice output, allowing users to interact with our conversational agents as if they were talking to a real person. Users can choose from a variety of voices and pair the appropriate audio with the assistant. Additionally, for users who prefer auditory learning or need to obtain information while busy, TTS provides an excellent solution.
@@ -32,11 +32,7 @@ In LobeChat, we have carefully selected a series of high-quality voice options (
## Lobe TTS
-
+
[`@lobehub/tts`](https://tts.lobehub.com) is a high-quality TTS toolkit developed using the TS language, supporting usage in both server and browser environments.
diff --git a/DigitalHumanWeb/docs/usage/features/tts.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/tts.zh-CN.mdx
index 6b5a72d..10cceec 100644
--- a/DigitalHumanWeb/docs/usage/features/tts.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/tts.zh-CN.mdx
@@ -18,8 +18,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/284072124-c9853d8d-f1b5-44a8-a305-45ebc0f6d19a.png'
- }
+'https://github.com/user-attachments/assets/50189597-2cc3-4002-b4c8-756a52ad5c0a'
+}
/>
LobeChat 支持文字转语音(Text-to-Speech,TTS)和语音转文字(Speech-to-Text,STT)技术,我们的应用能够将文本信息转化为清晰的语音输出,用户可以像与真人交谈一样与我们的对话代理进行交流。用户可以从多种声音中选择,给助手搭配合适的音源。 同时,对于那些倾向于听觉学习或者想要在忙碌中获取信息的用户来说,TTS 提供了一个极佳的解决方案。
@@ -28,11 +28,7 @@ LobeChat 支持文字转语音(Text-to-Speech,TTS)和语音转文字(Spe
## Lobe TTS
-
+
[`@lobehub/tts`](https://tts.lobehub.com) 是一个使用 TS 语言开发的,高质量 TTS 工具包,支持在服务端和浏览器中使用。
diff --git a/DigitalHumanWeb/docs/usage/features/vision.mdx b/DigitalHumanWeb/docs/usage/features/vision.mdx
index bf14216..6bc3c95 100644
--- a/DigitalHumanWeb/docs/usage/features/vision.mdx
+++ b/DigitalHumanWeb/docs/usage/features/vision.mdx
@@ -19,8 +19,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/284072129-382bdf30-e3d6-4411-b5a0-249710b8ba08.png'
- }
+'https://github.com/user-attachments/assets/18574a1f-46c2-4cbc-af2c-35a86e128a07'
+}
/>
LobeChat now supports large language models with visual recognition capabilities such as OpenAI's [`gpt-4-vision`](https://platform.openai.com/docs/guides/vision), Google Gemini Pro vision, and Zhipu GLM-4 Vision, enabling LobeChat to have multimodal interaction capabilities. Users can easily upload or drag and drop images into the chat box, and the assistant will be able to recognize the content of the images and engage in intelligent conversations based on them, creating more intelligent and diverse chat scenarios.
diff --git a/DigitalHumanWeb/docs/usage/features/vision.zh-CN.mdx b/DigitalHumanWeb/docs/usage/features/vision.zh-CN.mdx
index 1e2bf3b..e2f8c9a 100644
--- a/DigitalHumanWeb/docs/usage/features/vision.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/features/vision.zh-CN.mdx
@@ -16,8 +16,8 @@ tags:
borderless
cover
src={
- 'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/284072129-382bdf30-e3d6-4411-b5a0-249710b8ba08.png'
- }
+'https://github.com/user-attachments/assets/18574a1f-46c2-4cbc-af2c-35a86e128a07'
+}
/>
LobeChat 已经支持 OpenAI 的 [`gpt-4-vision`](https://platform.openai.com/docs/guides/vision) 、Google Gemini Pro vision、智谱 GLM-4 Vision 等具有视觉识别能力的大语言模型,这使得 LobeChat 具备了多模态交互的能力。用户可以轻松上传图片或者拖拽图片到对话框中,助手将能够识别图片内容,并在此基础上进行智能对话,构建更智能、更多元化的聊天场景。
diff --git a/DigitalHumanWeb/docs/usage/foundation/basic.mdx b/DigitalHumanWeb/docs/usage/foundation/basic.mdx
index 015032b..5b35869 100644
--- a/DigitalHumanWeb/docs/usage/foundation/basic.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/basic.mdx
@@ -15,20 +15,13 @@ tags:
# Basic Usage Guide for Conversations
-
+
In general, the basic interaction with Large Language Models (LLMs) can be done through the fundamental functions provided in this area (as shown above).
## Basic Function Description
-
+
1. **Model Selection**: Choose the Large Language Model (LLM) to be used in the current conversation. For model settings, refer to [Model Providers](/docs/usage/providers).
2. **File/Image Upload**: When the selected model supports file or image recognition, users can upload files or images during the conversation with the model.
@@ -40,16 +33,12 @@ In general, the basic interaction with Large Language Models (LLMs) can be done
8. **Start New Topic**: End the current conversation and start a new topic. For more information, refer to [Topic Usage](/docs/usage/agents/topics).
9. **Send Button**: Send the current input content to the model. The dropdown menu provides additional send operation options.
-
+
- **Send Shortcut**: Set a shortcut to send messages and line breaks using the Enter key or ⌘ +
- Enter key. - **Add an AI Message**: Manually add and edit a message input by an AI character in
- the conversation context, which will not trigger a model response. - **Add a User Message**: Add
- the current input content as a message input by the user character to the conversation context,
- which will not trigger a model response.
+ Enter key. - **Add an AI Message**: Manually add and edit a message input by an AI character in
+ the conversation context, which will not trigger a model response. - **Add a User Message**: Add
+ the current input content as a message input by the user character to the conversation context,
+ which will not trigger a model response.
diff --git a/DigitalHumanWeb/docs/usage/foundation/basic.zh-CN.mdx b/DigitalHumanWeb/docs/usage/foundation/basic.zh-CN.mdx
index 1d6ecf3..5c858e7 100644
--- a/DigitalHumanWeb/docs/usage/foundation/basic.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/basic.zh-CN.mdx
@@ -17,23 +17,16 @@ tags:
# 会话基本使用指南
-
+
通常情况下,与大型语言模型 (LLMs) 的基本交互可以通过此区域(如上图)提供的基础功能进行。
## 基本功能说明
-
+
1. **模型选择**:选择当前对话所使用的大型语言模型 (LLM)。模型的设置详见[模型服务商](/zh/docs/usage/providers)。
-2. **文件/图片上传**:当所选模型支持文件或图片识别功能时,用户可以在与模型的对话中上传文件或图片。
+2. **文件 / 图片上传**:当所选模型支持文件或图片识别功能时,用户可以在与模型的对话中上传文件或图片。
3. **温度设置**:调节模型输出的随机性程度。数值越高,输出结果越随机。详细说明请参考[大语言模型指南](/zh/docs/usage/agents/model)。
4. **历史记录设置**:设定本次对话中模型需要记忆的聊天记录数量。历史记录越长,模型能够记忆的对话内容越多,但同时也会消耗更多的上下文 token。
5. **语音输入**:点击该按钮后,可以将语音转换为文字输入。有关详细信息,请参考[语音文字转换](/zh/docs/usage/foundation/tts-stt)。
@@ -42,15 +35,12 @@ tags:
8. **新建话题**:结束当前对话并开启一个新的对话主题。有关详细信息,请参考[话题使用](/zh/docs/usage/agents/topics)。
9. **发送按钮**:将当前输入内容发送至模型。下拉菜单提供额外的发送操作选项。
-
+
- **发送快捷键**:设置使用 Enter 键或 ⌘ + Enter 键发送消息和换行的快捷方式。 -
- **添加一条AI消息**:在对话上下文中手动添加并编辑一条由 AI 角色输入的消息,该操作不会触发模型响应。
+ **添加一条 AI 消息**:在对话上下文中手动添加并编辑一条由 AI 角色输入的消息,该操作不会触发模型响应。
-
+
**添加一条用户消息**:将当前输入内容作为用户角色输入的消息添加到对话上下文中,该操作不会触发模型响应。
diff --git a/DigitalHumanWeb/docs/usage/foundation/share.mdx b/DigitalHumanWeb/docs/usage/foundation/share.mdx
index 25b438f..c981a98 100644
--- a/DigitalHumanWeb/docs/usage/foundation/share.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/share.mdx
@@ -14,20 +14,13 @@ tags:
# Share Conversation Records
-
+
By clicking the `Share` button in the top right corner of the chat window, you can share the current conversation records with others. LobeChat supports two sharing methods: `Screenshot Sharing` and `ShareGPT Sharing`.
## Screenshot Sharing
-
+
The screenshot sharing feature will generate and save an image of the current conversation records, with the following options:
@@ -38,9 +31,6 @@ The screenshot sharing feature will generate and save an image of the current co
## ShareGPT
-
+
[ShareGPT](https://sharegpt.com/) is an AI conversation sharing platform that allows users to easily share their conversations with Large Language Models (LLMs). Users can generate a permanent link with just one click, making it convenient to share these conversations with friends or others. By integrating ShareGPT functionality, LobeChat can generate links for conversation records with just one click, making sharing easy.
diff --git a/DigitalHumanWeb/docs/usage/foundation/share.zh-CN.mdx b/DigitalHumanWeb/docs/usage/foundation/share.zh-CN.mdx
index c8be6fa..397f4b4 100644
--- a/DigitalHumanWeb/docs/usage/foundation/share.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/share.zh-CN.mdx
@@ -11,20 +11,13 @@ tags:
# 分享会话记录
-
+
通过会话窗口右上角的`分享`按钮,您可以将当前会话记录分享给其他人。LobeChat 支持两种分享方式:`截图分享`和 `ShareGPT 分享`。
## 截图分享
-
+
截图分享功能将生成当前会话记录的图片并保存,其选项说明如下:
@@ -35,9 +28,6 @@ tags:
## ShareGPT
-
+
[ShareGPT](https://sharegpt.com/) 是一个 AI 对话分享平台,允许用户便捷地分享他们与大型语言模型 (LLM) 的对话。用户只需点击即可生成永久链接,方便与朋友或其他人分享这些对话。LobeChat 通过集成 ShareGPT 功能,可以一键将对话记录生成链接,方便分享。
diff --git a/DigitalHumanWeb/docs/usage/foundation/text2image.mdx b/DigitalHumanWeb/docs/usage/foundation/text2image.mdx
index 8cb18cd..4e08631 100644
--- a/DigitalHumanWeb/docs/usage/foundation/text2image.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/text2image.mdx
@@ -20,10 +20,7 @@ LobeChat supports text-to-image generation through a plugin mechanism. Currently
If you have configured the OpenAI API, you can enable the DALL-E plugin directly in the assistant interface and input prompts in the conversation for AI to generate images for you.
-
+
If the DALL-E plugin is not available, please check if the OpenAI API key has been correctly configured.
@@ -31,19 +28,12 @@ If the DALL-E plugin is not available, please check if the OpenAI API key has be
LobeChat also offers the Midjourney plugin, which generates images by calling the Midjourney API. Please install the Midjourney plugin in the plugin store beforehand.
-
+
- info For plugin installation, please refer to [Plugin
- Usage](/docs/usage/plugins/basic-usage)
+ info For plugin installation, please refer to [Plugin Usage](/docs/usage/plugins/basic-usage)
When using the Midjourney plugin for the first time, you will need to fill in your Midjourney API key in the plugin settings.
-
+
diff --git a/DigitalHumanWeb/docs/usage/foundation/text2image.zh-CN.mdx b/DigitalHumanWeb/docs/usage/foundation/text2image.zh-CN.mdx
index 3d6b189..18434dc 100644
--- a/DigitalHumanWeb/docs/usage/foundation/text2image.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/text2image.zh-CN.mdx
@@ -18,10 +18,7 @@ LobeChat 通过插件机制支持文本生成图片功能。目前,LobeChat
如果您已配置 OpenAI API,可以直接在助手界面启用 DALL-E 插件,并在对话中输入提示词,让 AI 为您生成图片。
-
+
如果 DALL-E 插件不可用,请检查 OpenAI API 密钥是否已正确配置。
@@ -29,18 +26,10 @@ LobeChat 通过插件机制支持文本生成图片功能。目前,LobeChat
LobeChat 还提供 Midjourney 插件,通过 API 调用 Midjourney 生成图片。请提前在插件商店中安装 Midjourney 插件。
-
+
-
- 插件安装请参考[插件使用](/zh/docs/usage/plugins/basic-usage)
-
+插件安装请参考[插件使用](/zh/docs/usage/plugins/basic-usage)
首次使用 Midjourney 插件时,您需要在插件设置中填写您的 Midjourney API 密钥。
-
+
diff --git a/DigitalHumanWeb/docs/usage/foundation/translate.mdx b/DigitalHumanWeb/docs/usage/foundation/translate.mdx
index 43f8b76..90f078d 100644
--- a/DigitalHumanWeb/docs/usage/foundation/translate.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/translate.mdx
@@ -11,29 +11,19 @@ tags:
# Translation of Conversation Records
-
+
## Translating Conversation Content
LobeChat supports users to translate conversation content into a specified language with just one click. After selecting the target language, LobeChat will use a pre-set AI model for translation and display the translated results in real-time in the chat window.
-
+
## Translation Model Settings
You can specify the model you wish to use as a translation assistant in the settings.
-
+
- Open the `Settings` panel
- Find the `Translation Settings` option under `System Assistants`
diff --git a/DigitalHumanWeb/docs/usage/foundation/translate.zh-CN.mdx b/DigitalHumanWeb/docs/usage/foundation/translate.zh-CN.mdx
index 5ba9784..3449ac5 100644
--- a/DigitalHumanWeb/docs/usage/foundation/translate.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/translate.zh-CN.mdx
@@ -10,29 +10,19 @@ tags:
# 翻译会话记录
-
+
## 翻译对话中的内容
LobeChat 支持用户一键将对话内容翻译成指定语言。选择目标语言后,LobeChat 将调用预先设置的 AI 模型进行翻译,并将翻译结果实时显示在聊天窗口中。
-
+
## 翻译模型设置
你可以在设置中指定您希望使用的模型作为翻译助手。
-
+
- 打开`设置`面板
- 在`系统助手`中找到`翻译设置`选项
diff --git a/DigitalHumanWeb/docs/usage/foundation/tts-stt.mdx b/DigitalHumanWeb/docs/usage/foundation/tts-stt.mdx
index a99925d..59675a2 100644
--- a/DigitalHumanWeb/docs/usage/foundation/tts-stt.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/tts-stt.mdx
@@ -19,28 +19,19 @@ LobeChat supports text-to-speech conversion, allowing users to input content thr
Select any content in the chat window, choose `Text-to-Speech`, and the AI will use the TTS model to read the text content aloud.
-
+
## Speech-to-Text (STT)
Select the voice input feature in the input window, and LobeChat will convert your speech to text and input it into the text box. After completing the input, you can send it directly to the AI.
-
+
## Text-to-Speech Conversion Settings
You can specify the model you want to use for text-to-speech conversion in the settings.
-
+
- Open the `Settings` panel
- Find the `Text-to-Speech` settings
diff --git a/DigitalHumanWeb/docs/usage/foundation/tts-stt.zh-CN.mdx b/DigitalHumanWeb/docs/usage/foundation/tts-stt.zh-CN.mdx
index b0f885d..f5199c9 100644
--- a/DigitalHumanWeb/docs/usage/foundation/tts-stt.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/tts-stt.zh-CN.mdx
@@ -17,28 +17,19 @@ LobeChat 支持文字语音转换功能,允许用户通过语音输入内容
在对话窗口中选中任意内容,选择`文字转语音`,AI 将通过 TTS 模型对文本内容进行语音播报。
-
+
## 语音转文字(STT)
在输入窗口中选择语音输入功能,LobeChat 将您的语音转换为文字并输入到文本框中,完成输入后可以直接发送给 AI。
-
+
## 文字语音转换设置
你可以在设置中为文字语音转换功能指定您希望使用的模型。
-
+
- 打开`设置`面板
- 找到`文字转语音`设置
diff --git a/DigitalHumanWeb/docs/usage/foundation/vision.mdx b/DigitalHumanWeb/docs/usage/foundation/vision.mdx
index 319bf99..449e6af 100644
--- a/DigitalHumanWeb/docs/usage/foundation/vision.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/vision.mdx
@@ -16,34 +16,22 @@ tags:
The ecosystem of large language models that support visual recognition is becoming increasingly rich. Starting from `gpt-4-vision`, LobeChat now supports various large language models with visual recognition capabilities, enabling LobeChat to have multimodal interaction capabilities.
-
+
## Image Input
If the model you are currently using supports visual recognition, you can input image content by uploading a file or dragging the image directly into the input box. The model will automatically recognize the image content and provide feedback based on your prompts.
-
+
## Visual Models
In the model list, models with a `👁️` icon next to their names indicate that the model supports visual recognition. Selecting such a model allows you to send image content.
-
+
## Custom Model Configuration
If you need to add a custom model that is not currently in the list and explicitly supports visual recognition, you can enable the `Visual Recognition` feature in the `Custom Model Configuration` to allow the model to interact with images.
-
+
diff --git a/DigitalHumanWeb/docs/usage/foundation/vision.zh-CN.mdx b/DigitalHumanWeb/docs/usage/foundation/vision.zh-CN.mdx
index 07d1dc7..8df2678 100644
--- a/DigitalHumanWeb/docs/usage/foundation/vision.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/foundation/vision.zh-CN.mdx
@@ -12,34 +12,22 @@ tags:
当前支持视觉识别的大语言模型生态日益丰富。从 `gpt-4-vision` 开始,LobeChat 开始支持各类具有视觉识别能力的大语言模型,这使得 LobeChat 具备了多模态交互的能力。
-
+
## 图片输入
如果你当前使用的模型支持视觉识别功能,您可以通过上传文件或直接将图片拖入输入框的方式输入图片内容。模型会自动识别图片内容,并根据您的提示词给出反馈。
-
+
## 视觉模型
在模型列表中,模型名称后面带有`👁️`图标表示该模型支持视觉识别功能。选择该模型后即可发送图片内容。
-
+
## 自定义模型配置
如果您需要添加当前列表中没有的自定义模型,并且该模型明确支持视觉识别功能,您可以在`自定义模型配置`中开启`视觉识别`功能,使该模型能够与图片进行交互。
-
+
diff --git a/DigitalHumanWeb/docs/usage/plugins/basic-usage.mdx b/DigitalHumanWeb/docs/usage/plugins/basic-usage.mdx
index 51374bc..3b0146b 100644
--- a/DigitalHumanWeb/docs/usage/plugins/basic-usage.mdx
+++ b/DigitalHumanWeb/docs/usage/plugins/basic-usage.mdx
@@ -17,38 +17,23 @@ The plugin system is a key element in expanding the capabilities of assistants i
Watch the following video to quickly get started with using LobeChat plugins:
-
+
## Plugin Store
You can access the Plugin Store by navigating to "Extension Tools" -> "Plugin Store" in the session toolbar.
-
+
The Plugin Store allows you to directly install and use plugins within LobeChat.
-
+
## Using Plugins
After installing a plugin, simply enable it under the current assistant to use it.
-
+
## Plugin Configuration
@@ -56,14 +41,6 @@ Some plugins may require specific configurations, such as API keys.
After installing a plugin, you can click on "Settings" to enter the plugin's settings and fill in the required configurations:
-
-
-
+
+
+
diff --git a/DigitalHumanWeb/docs/usage/plugins/basic-usage.zh-CN.mdx b/DigitalHumanWeb/docs/usage/plugins/basic-usage.zh-CN.mdx
index a6d5335..6ec4ee5 100644
--- a/DigitalHumanWeb/docs/usage/plugins/basic-usage.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/plugins/basic-usage.zh-CN.mdx
@@ -15,38 +15,23 @@ tags:
查看以下视频,快速上手使用 LobeChat 插件:
-
+
## 插件商店
你可以在会话工具条中的 「扩展工具」 -> 「插件商店」,进入插件商店。
-
+
插件商店中会在 LobeChat 中可以直接安装并使用的插件。
-
+
## 使用插件
安装完毕插件后,只需在当前助手下开启插件即可使用。
-
+
## 插件配置
@@ -54,14 +39,6 @@ tags:
你可以在安装插件后,点击设置进入插件的设置填写配置:
-
-
-
+
+
+
diff --git a/DigitalHumanWeb/docs/usage/plugins/development.mdx b/DigitalHumanWeb/docs/usage/plugins/development.mdx
index 286bd8b..45b9818 100644
--- a/DigitalHumanWeb/docs/usage/plugins/development.mdx
+++ b/DigitalHumanWeb/docs/usage/plugins/development.mdx
@@ -36,88 +36,52 @@ This section will introduce how to add and use a custom plugin in LobeChat.
### Create and Launch Plugin Project
-You need to first create a plugin project locally, you can use the template we have prepared [lobe-chat-plugin-template][lobe-chat-plugin-template-url]
+ You need to first create a plugin project locally, you can use the template we have prepared [lobe-chat-plugin-template][lobe-chat-plugin-template-url]
-```bash
-$ git clone https://github.com/lobehub/chat-plugin-template.git
-$ cd chat-plugin-template
-$ npm i
-$ npm run dev
-```
-
-When you see `ready started server on 0.0.0.0:3400, url: http://localhost:3400`, it means the plugin service has been successfully launched locally.
+ ```bash
+ $ git clone https://github.com/lobehub/chat-plugin-template.git
+ $ cd chat-plugin-template
+ $ npm i
+ $ npm run dev
+ ```
-
+ When you see `ready started server on 0.0.0.0:3400, url: http://localhost:3400`, it means the plugin service has been successfully launched locally.
-### Add Local Plugin in LobeChat Role Settings
+
-Next, go to LobeChat, create a new assistant, and go to its session settings page:
+ ### Add Local Plugin in LobeChat Role Settings
-
+ Next, go to LobeChat, create a new assistant, and go to its session settings page:
-Click the Add button on the right of the plugin list to open the custom plugin adding popup:
+
-
+ Click the Add button on the right of the plugin list to open the custom plugin adding popup:
-Fill in the **Plugin Description File Url** with `http://localhost:3400/manifest-dev.json`, which is the manifest address of the plugin we started locally.
+
-At this point, you should see that the identifier of the plugin has been automatically recognized as `chat-plugin-template`. Next, you need to fill in the remaining form fields (only the title is required), and then click the Save button to complete the custom plugin addition.
+ Fill in the **Plugin Description File Url** with `http://localhost:3400/manifest-dev.json`, which is the manifest address of the plugin we started locally.
-
+ At this point, you should see that the identifier of the plugin has been automatically recognized as `chat-plugin-template`. Next, you need to fill in the remaining form fields (only the title is required), and then click the Save button to complete the custom plugin addition.
-After adding, you can see the newly added plugin in the plugin list. If you need to modify the plugin configuration, you can click the Settings button on the far right to make changes.
+
-
+ After adding, you can see the newly added plugin in the plugin list. If you need to modify the plugin configuration, you can click the Settings button on the far right to make changes.
-### Test Plugin Function in Session
+
-Next, we need to test whether the plugin's function is working properly.
+ ### Test Plugin Function in Session
-Click the Back button to return to the session area, and then send a message to the assistant: "What should I wear?" At this point, the assistant will try to ask you about your gender and current mood.
+ Next, we need to test whether the plugin's function is working properly.
-
+ Click the Back button to return to the session area, and then send a message to the assistant: "What should I wear?" At this point, the assistant will try to ask you about your gender and current mood.
-After answering, the assistant will initiate the plugin call, retrieve recommended clothing data from the server based on your gender and mood, and push it to you. Finally, it will provide a text summary based on this information.
+
-
+ After answering, the assistant will initiate the plugin call, retrieve recommended clothing data from the server based on your gender and mood, and push it to you. Finally, it will provide a text summary based on this information.
-After completing these operations, you have understood the basic process of adding custom plugins and using them in LobeChat.
+
+ After completing these operations, you have understood the basic process of adding custom plugins and using them in LobeChat.
## Local Plugin Development
@@ -247,29 +211,17 @@ export default createLobeChatPluginGateway();
The custom UI interface for plugins is optional. For example, the official plugin [Web Content Extraction](https://github.com/lobehub/chat-plugin-web-crawler) does not have a corresponding user interface.
-
+
If you want to display richer information in plugin messages or include some interactive operations, you can customize a user interface for the plugin. For example, the following image shows the user interface for the [Search Engine](https://github.com/lobehub/chat-plugin-search-engine) plugin.
-
+
#### Implementation of Plugin UI Interface
LobeChat implements the loading of plugin UI through `iframe` and uses `postMessage` to communicate with the plugin. Therefore, the implementation of the plugin UI is consistent with regular web development. You can use any frontend framework and development language you are familiar with.
-
+
In the template we provide, we use React + Next.js + [antd](https://ant.design/) as the frontend interface framework. You can find the implementation of the user interface in [`src/pages/index.tsx`](https://github.com/lobehub/chat-plugin-template/blob/main/src/pages/index.tsx).
@@ -307,7 +259,7 @@ If you want more people to use your plugin, feel free to [submit it for listing]
### Plugin Shield
-[](https://github.com/lobehub/lobe-chat-plugins)
+[](https://github.com/lobehub/lobe-chat-plugins)
```md
[](https://github.com/lobehub/lobe-chat-plugins)
diff --git a/DigitalHumanWeb/docs/usage/plugins/development.zh-CN.mdx b/DigitalHumanWeb/docs/usage/plugins/development.zh-CN.mdx
index 052f516..7ac82ce 100644
--- a/DigitalHumanWeb/docs/usage/plugins/development.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/plugins/development.zh-CN.mdx
@@ -30,88 +30,52 @@ tags:
### 创建并启动插件项目
-你需要先在本地创建一个插件项目,可以使用我们准备好的模板 [lobe-chat-plugin-template][lobe-chat-plugin-template-url]
+ 你需要先在本地创建一个插件项目,可以使用我们准备好的模板 [lobe-chat-plugin-template][lobe-chat-plugin-template-url]
-```bash
-$ git clone https://github.com/lobehub/chat-plugin-template.git
-$ cd chat-plugin-template
-$ npm i
-$ npm run dev
-```
-
-当出现`ready started server on 0.0.0.0:3400, url: http://localhost:3400` 时,说明插件服务已经在本地启动成功。
+ ```bash
+ $ git clone https://github.com/lobehub/chat-plugin-template.git
+ $ cd chat-plugin-template
+ $ npm i
+ $ npm run dev
+ ```
-
+ 当出现`ready started server on 0.0.0.0:3400, url: http://localhost:3400` 时,说明插件服务已经在本地启动成功。
-### 在 LobeChat 角色设置中添加本地插件
+
-接下来进入到 LobeChat 中,创建一个新的助手,并进入它的会话设置页:
+ ### 在 LobeChat 角色设置中添加本地插件
-
+ 接下来进入到 LobeChat 中,创建一个新的助手,并进入它的会话设置页:
-点击插件列表右侧的 添加 按钮,打开自定义插件添加弹窗:
+
-
+ 点击插件列表右侧的 添加 按钮,打开自定义插件添加弹窗:
-在 **插件描述文件 Url** 地址 中填入 `http://localhost:3400/manifest-dev.json` ,这是我们本地启动的插件描述清单地址。
+
-此时,你应该可以看到看到插件的标识符一栏已经被自动识别为 `chat-plugin-template`。接下来你需要填写剩下的表单字段(只有标题必填),然后点击 保存 按钮,即可完成自定义插件添加。
+ 在 **插件描述文件 Url** 地址 中填入 `http://localhost:3400/manifest-dev.json` ,这是我们本地启动的插件描述清单地址。
-
+ 此时,你应该可以看到看到插件的标识符一栏已经被自动识别为 `chat-plugin-template`。接下来你需要填写剩下的表单字段(只有标题必填),然后点击 保存 按钮,即可完成自定义插件添加。
-完成添加后,在插件列表中就能看到刚刚添加的插件,如果需要修改插件的配置,可以点击最右侧的 设置 按钮进行修改。
+
-
+ 完成添加后,在插件列表中就能看到刚刚添加的插件,如果需要修改插件的配置,可以点击最右侧的 设置 按钮进行修改。
-### 会话测试插件功能
+
-接来下我们需要测试这个插件的功能是否正常。
+ ### 会话测试插件功能
-点击 返回 按钮回到会话区,然后向助手发送消息:「我应该穿什么? 」此时助手将会尝试向你询问,了解你的性别与当前的心情。
+ 接来下我们需要测试这个插件的功能是否正常。
-
+ 点击 返回 按钮回到会话区,然后向助手发送消息:「我应该穿什么? 」此时助手将会尝试向你询问,了解你的性别与当前的心情。
-当回答完毕后,助手将会发起插件的调用,根据你的性别、心情,从服务端获取推荐的衣服数据,并推送给你。最后基于这些信息做一轮文本总结。
+
-
+ 当回答完毕后,助手将会发起插件的调用,根据你的性别、心情,从服务端获取推荐的衣服数据,并推送给你。最后基于这些信息做一轮文本总结。
-当完成这些操作后,你已经了解了添加自定义插件,并在 LobeChat 中使用的基础流程。
+
+ 当完成这些操作后,你已经了解了添加自定义插件,并在 LobeChat 中使用的基础流程。
## 本地插件开发
@@ -223,7 +187,7 @@ export default async (req: Request) => {
由于 LobeChat 默认的插件网关是云端服务 `/api/plugins`,云端服务通过 manifest 上的 `api.url` 地址发送请求,以解决跨域问题。
-针对自定义插件,插件请求需要发送给本地服务, 因此通过在 manifest 中指定网关 ([http://localhost:3400/api/gateway),LobeChat]() 将会直接请求该地址,然后只需要在该地址下创建对应的网关即可。
+针对自定义插件,插件请求需要发送给本地服务, 因此通过在 manifest 中指定网关 ([http://localhost:3400/api/gateway),LobeChat](http://localhost:3400/api/gateway\),LobeChat) 将会直接请求该地址,然后只需要在该地址下创建对应的网关即可。
```ts
import { createLobeChatPluginGateway } from '@lobehub/chat-plugins-gateway';
@@ -241,29 +205,17 @@ export default createLobeChatPluginGateway();
自定义插件的 UI 界面是一个可选项。例如 官方插件 [「🧩 / 🕸 网页内容提取」](https://github.com/lobehub/chat-plugin-web-crawler),没有实现相应的用户界面。
-
+
如果你希望在插件消息中展示更加丰富的信息,或者包含一些富交互操作,你可以为插件定制一个用户界面。例如下图则为[「搜索引擎」](https://github.com/lobehub/chat-plugin-search-engine)插件的用户界面。
-
+
#### 插件 UI 界面实现
LobeChat 通过 `iframe` 实现插件 ui 的加载,使用 `postMessage` 实现主体与插件的通信。因此, 插件 UI 的实现方式与普通的网页开发一致,你可以使用任何你熟悉的前端框架与开发语言。
-
+
在我们提供的模板中使用了 React + Next.js + [antd](https://ant.design/) 作为前端界面框架,你可以在 [`src/pages/index.tsx`](https://github.com/lobehub/chat-plugin-template/blob/main/src/pages/index.tsx) 中找到用户界面的实现。
@@ -301,7 +253,7 @@ export default Render;
### 插件 Shield
-[](https://github.com/lobehub/lobe-chat-plugins)
+[](https://github.com/lobehub/lobe-chat-plugins)
```markdown
[](https://github.com/lobehub/lobe-chat-plugins)
diff --git a/DigitalHumanWeb/docs/usage/plugins/store.mdx b/DigitalHumanWeb/docs/usage/plugins/store.mdx
index 049688c..614d1cc 100644
--- a/DigitalHumanWeb/docs/usage/plugins/store.mdx
+++ b/DigitalHumanWeb/docs/usage/plugins/store.mdx
@@ -15,16 +15,8 @@ tags:
You can access the plugin store by going to `Extension Tools` -> `Plugin Store` in the session toolbar.
-
+
In the plugin store, you can directly install and use plugins in LobeChat.
-
+
diff --git a/DigitalHumanWeb/docs/usage/plugins/store.zh-CN.mdx b/DigitalHumanWeb/docs/usage/plugins/store.zh-CN.mdx
index 75fa365..8484231 100644
--- a/DigitalHumanWeb/docs/usage/plugins/store.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/plugins/store.zh-CN.mdx
@@ -12,16 +12,8 @@ tags:
你可以在会话工具条中的 `扩展工具` -> `插件商店`,进入插件商店。
-
+
插件商店中会在 LobeChat 中可以直接安装并使用的插件。
-
+
diff --git a/DigitalHumanWeb/docs/usage/providers.mdx b/DigitalHumanWeb/docs/usage/providers.mdx
index 75be2d0..8874388 100644
--- a/DigitalHumanWeb/docs/usage/providers.mdx
+++ b/DigitalHumanWeb/docs/usage/providers.mdx
@@ -20,12 +20,7 @@ tags:
# Using Multiple Model Providers in LobeChat
-
+
In the continuous development of LobeChat, we deeply understand the importance of diversity in model providers for providing AI conversation services to meet the needs of the community. Therefore, we have expanded our support to multiple model providers instead of being limited to a single one, in order to offer users a more diverse and rich selection of conversation options.
diff --git a/DigitalHumanWeb/docs/usage/providers.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers.zh-CN.mdx
index 83abd4c..0760cbd 100644
--- a/DigitalHumanWeb/docs/usage/providers.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers.zh-CN.mdx
@@ -18,12 +18,7 @@ tags:
# 在 LobeChat 中使用多模型服务商
-
+
在 LobeChat 的不断发展过程中,我们深刻理解到在提供 AI 会话服务时模型服务商的多样性对于满足社区需求的重要性。因此,我们不再局限于单一的模型服务商,而是拓展了对多种模型服务商的支持,以便为用户提供更为丰富和多样化的会话选择。
diff --git a/DigitalHumanWeb/docs/usage/providers/01ai.mdx b/DigitalHumanWeb/docs/usage/providers/01ai.mdx
deleted file mode 100644
index 6904dbc..0000000
--- a/DigitalHumanWeb/docs/usage/providers/01ai.mdx
+++ /dev/null
@@ -1,85 +0,0 @@
----
-title: Using Zero One AI API Key in LobeChat
-description: >-
- Learn how to integrate and use Zero One AI in LobeChat with step-by-step
- instructions. Obtain an API key, configure Zero One AI, and start
- conversations with AI models.
-tags:
- - 01.AI
- - Zero One AI
- - Web UI
- - API key
- - AI models
----
-
-# Using Zero One AI in LobeChat
-
-
-
-[Zero One AI](https://www.01.ai/) is a global company dedicated to AI 2.0 large model technology and applications. Its billion-parameter Yi-Large closed-source model, when evaluated on Stanford University's English ranking AlpacaEval 2.0, is on par with GPT-4.
-
-This document will guide you on how to use Zero One AI in LobeChat:
-
-
-
-### Step 1: Obtain Zero One AI API Key
-
-- Register and log in to the [Zero One AI Large Model Open Platform](https://platform.lingyiwanwu.com/)
-- Go to the `Dashboard` and access the `API Key Management` menu
-- A system-generated API key has been created for you automatically, or you can create a new one on this interface
-
-
-
-- Account verification is required for first-time use
-
-
-
-- Click on the created API key
-- Copy and save the API key in the pop-up dialog box
-
-
-
-### Step 2: Configure Zero One AI in LobeChat
-
-- Access the `Settings` interface in LobeChat
-- Find the setting for `Zero One AI` under `Language Model`
-
-
-
-- Open Zero One AI and enter the obtained API key
-- Choose a 01.AI model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider. Please refer to Zero One AI's relevant
- fee policies.
-
-
-
-
-You can now use the models provided by Zero One AI for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/01ai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/01ai.zh-CN.mdx
deleted file mode 100644
index 0a31699..0000000
--- a/DigitalHumanWeb/docs/usage/providers/01ai.zh-CN.mdx
+++ /dev/null
@@ -1,85 +0,0 @@
----
-title: 在 LobeChat 中使用 01.AI 零一万物 API Key
-description: >-
- 学习如何在 LobeChat 中配置并使用 01.AI 零一万物提供的 AI 模型进行对话。获取 API 密钥、填入设置项、选择模型,开始与 AI
- 助手交流。
-tags:
- - LobeChat
- - 01.AI
- - Zero One AI
- - 零一万物
- - Web UI
- - API密钥
- - 配置指南
----
-
-# 在 LobeChat 中使用零一万物
-
-
-
-[零一万物](https://www.01.ai/)是一家致力于AI 2.0大模型技术和应用的全球公司,其发布的千亿参数的Yi-Large闭源模型,在斯坦福大学的英语排行AlpacaEval 2.0上,与GPT-4互有第一。
-
-本文档将指导你如何在 LobeChat 中使用零一万物:
-
-
-
-### 步骤一:获取零一万物 API 密钥
-
-- 注册并登录 [零一万物大模型开放平台](https://platform.lingyiwanwu.com/)
-- 进入`工作台`并访问`API Key管理`菜单
-- 系统已为你自动创建了一个 API 密钥,你也可以在此界面创建新的 API 密钥
-
-
-
-- 初次使用时需要完成账号认证
-
-
-
-- 点击创建好的 API 密钥
-- 在弹出的对话框中复制并保存 API 密钥
-
-
-
-### 步骤二:在LobeChat 中配置零一万物
-
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`零一万物`的设置项
-
-
-
-- 打开零一万物并填入获得的 API 密钥
-- 为你的 AI 助手选择一个 01.AI 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考零一万物的相关费用政策。
-
-
-
-
-至此你已经可以在 LobeChat 中使用零一万物提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/ai21.mdx b/DigitalHumanWeb/docs/usage/providers/ai21.mdx
new file mode 100644
index 0000000..9fab656
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/ai21.mdx
@@ -0,0 +1,48 @@
+---
+title: Using AI21 Labs in LobeChat
+description: >-
+ Learn how to integrate and utilize AI21 Labs's language model APIs in
+ LobeChat.
+tags:
+ - LobeChat
+ - AI21 Labs
+ - API Key
+ - Web UI
+---
+
+# Using AI21 Labs in LobeChat
+
+
+
+[AI21 Labs](https://www.ai21.com/) is a company focused on artificial intelligence, offering advanced language models and API services designed to help developers and businesses leverage natural language processing technology. Their flagship product, the "Jamba" series of models, can perform complex language understanding and generation tasks, widely utilized in fields such as content creation and conversational systems.
+
+This article will guide you on how to use AI21 Labs within LobeChat.
+
+
+ ### Step 1: Obtain the AI21 Labs API Key
+
+ - Register and log in to [AI21 Studio](https://studio.ai21.com)
+ - Click on the `User Avatar` menu, then select `API Key`
+ - Copy and save the generated API key
+
+
+
+ ### Step 2: Configure AI21 Labs in LobeChat
+
+ - Go to the `Settings` page in LobeChat
+ - Under `Language Model`, find the setting for `AI21 Labs`
+
+
+
+ - Enter the API key you obtained
+ - Choose an AI21 Labs model for your AI assistant to begin the conversation
+
+
+
+
+ During use, you may need to pay the API service provider; please refer to the relevant fee policy
+ of AI21 Labs.
+
+
+
+Now you are ready to engage in conversations using the models provided by AI21 Labs in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/ai21.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/ai21.zh-CN.mdx
new file mode 100644
index 0000000..57c0c87
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/ai21.zh-CN.mdx
@@ -0,0 +1,45 @@
+---
+title: 在 LobeChat 中使用 AI21 Labs
+description: 学习如何在 LobeChat 中配置和使用 AI21 Labs 的API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - AI21 Labs
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 AI21 Labs
+
+
+
+[AI21 Labs](https://www.ai21.com/) 是一家专注于人工智能的公司,提供先进的语言模型和 API 服务,旨在帮助开发者和企业利用自然语言处理技术。其旗舰产品 "Jamba" 系列模型能够进行复杂的语言理解和生成任务,广泛应用于内容创作、对话系统等领域。
+
+本文将指导你如何在 LobeChat 中使用 AI21 Labs。
+
+
+ ### 步骤一:获得 AI21 Labs 的 API Key
+
+ - 注册并登录 [AI21 Studio](https://studio.ai21.com)
+ - 点击 `用户头像` 菜单,点击 `API Key`
+ - 复制并保存生成的 API 密钥
+
+
+
+ ### 步骤二:在 LobeChat 中配置 AI21 Labs
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `AI21labs` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 AI21 Labs 的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 AI21 Labs 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 AI21 Labs 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/ai360.mdx b/DigitalHumanWeb/docs/usage/providers/ai360.mdx
new file mode 100644
index 0000000..ddae022
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/ai360.mdx
@@ -0,0 +1,46 @@
+---
+title: Using the 360AI in LobeChat
+description: Learn how to integrate and utilize 360AI's language model APIs in LobeChat.
+tags:
+ - LobeChat
+ - 360AI
+ - API Key
+ - Web UI
+---
+
+# Using the 360AI in LobeChat
+
+
+
+The [360AI](https://ai.360.com/) is a cognitive general model independently developed by 360 Company, aimed at providing powerful natural language processing capabilities for enterprises and developers. This model has been upgraded to version 4.0 and supports various application scenarios, including conversational services, image generation, vector database services, and more.
+
+This article will guide you on how to use the 360AI in LobeChat.
+
+
+ ### Step 1: Obtain the 360AI API Key
+
+ - Register and log in to the [360AI API Open Platform](https://ai.360.com/platform/keys)
+ - Click on the `API Keys` menu on the left
+ - Create an API key and copy it
+
+
+
+ ### Step 2: Configure 360AI in LobeChat
+
+ - Access the `Settings` interface in LobeChat
+ - Under `Language Models`, find the option for `360`
+
+
+
+ - Enter the API key you obtained
+ - Choose a 360AI model for your AI assistant to start chatting
+
+
+
+
+ Please note that you may need to pay the API service provider during use, refer to the relevant
+ pricing policy of the 360AI.
+
+
+
+You can now use the models provided by the 360AI for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/ai360.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/ai360.zh-CN.mdx
new file mode 100644
index 0000000..b1c7b8f
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/ai360.zh-CN.mdx
@@ -0,0 +1,45 @@
+---
+title: 在 LobeChat 中使用360智脑
+description: 学习如何在 LobeChat 中配置和使用360智脑的API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - 360智脑
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 360 智脑
+
+
+
+[360 智脑](https://ai.360.com/)是 360 公司自主研发的认知型通用大模型,旨在为企业和开发者提供强大的自然语言处理能力。该模型已升级至 4.0 版本,能够支持多种应用场景,包括对话服务、图片生成、向量数据库服务等。
+
+本文将指导你如何在 LobeChat 中使用 360 智脑。
+
+
+ ### 步骤一:获得 360 智脑的 API Key
+
+ - 注册并登录 [360 智脑 API 开放平台](https://ai.360.com/platform/keys)
+ - 点击左侧 `API Keys` 菜单
+ - 创建一个 API 密钥并复制
+
+
+
+ ### 步骤二:在 LobeChat 中配置 360 智脑
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `360` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 360 智脑的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 360 智脑的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 360 智脑提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/anthropic.mdx b/DigitalHumanWeb/docs/usage/providers/anthropic.mdx
index c652159..bd24ed1 100644
--- a/DigitalHumanWeb/docs/usage/providers/anthropic.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/anthropic.mdx
@@ -13,66 +13,44 @@ tags:
# Using Anthropic Claude in LobeChat
-
+
The Anthropic Claude API is now available for everyone to use. This document will guide you on how to use [Anthropic Claude](https://www.anthropic.com/api) in LobeChat:
+ ### Step 1: Obtain Anthropic Claude API Key
-### Step 1: Obtain Anthropic Claude API Key
+ - Create an [Anthropic Claude API](https://www.anthropic.com/api) account.
+ - Get your [API key](https://console.anthropic.com/settings/keys).
-- Create an [Anthropic Claude API](https://www.anthropic.com/api) account.
-- Get your [API key](https://console.anthropic.com/settings/keys).
+
-
+
+ The Claude API currently offers $5 of free credits, but it is only available in certain specific
+ countries/regions. You can go to Dashboard > Claim to see if it is applicable to your
+ country/region.
+
-
- The Claude API currently offers $5 of free credits, but it is only available in certain specific
- countries/regions. You can go to Dashboard > Claim to see if it is applicable to your
- country/region.
-
+ - Set up your billing for the API key to work on [https://console.anthropic.com/settings/plans](https://console.anthropic.com/settings/plans) (choose the "Build" plan so you can add credits and only pay for usage).
-- Set up your billing for the API key to work on [https://console.anthropic.com/settings/plans](https://console.anthropic.com/settings/plans) (choose the "Build" plan so you can add credits and only pay for usage).
+
-
+ ### Step 2: Configure Anthropic Claude in LobeChat
-### Step 2: Configure Anthropic Claude in LobeChat
+ - Access the `Settings` interface in LobeChat.
+ - Find the setting for `Anthropic Claude` under `Language Models`.
-- Access the `Settings` interface in LobeChat.
-- Find the setting for `Anthropic Claude` under `Language Models`.
+
-
+ - Enter the obtained API key.
+ - Choose an Anthropic Claude model for your AI assistant to start the conversation.
-- Enter the obtained API key.
-- Choose an Anthropic Claude model for your AI assistant to start the conversation.
-
-
-
-
- During usage, you may need to pay the API service provider. Please refer to Anthropic Claude's
- relevant pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider. Please refer to Anthropic Claude's
+ relevant pricing policies.
+
You can now engage in conversations using the models provided by Anthropic Claude in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/anthropic.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/anthropic.zh-CN.mdx
index 866d9e8..0d6ba1c 100644
--- a/DigitalHumanWeb/docs/usage/providers/anthropic.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/anthropic.zh-CN.mdx
@@ -12,64 +12,42 @@ tags:
# 在 LobeChat 中使用 Anthropic Claude
-
+
-Anthropic Claude API 现在可供所有人使用, 本文档将指导你如何在 LobeChat 中使用 [Anthropic Claude](https://www.anthropic.com/api):
+Anthropic Claude API 现在可供所有人使用,本文档将指导你如何在 LobeChat 中使用 [Anthropic Claude](https://www.anthropic.com/api):
+ ### 步骤一:获取 Anthropic Claude API 密钥
-### 步骤一:获取 Anthropic Claude API 密钥
+ - 创建一个 [Anthropic Claude API](https://www.anthropic.com/api) 帐户
+ - 获取您的 [API 密钥](https://console.anthropic.com/settings/keys)
-- 创建一个 [Anthropic Claude API](https://www.anthropic.com/api) 帐户
-- 获取您的 [API 密钥](https://console.anthropic.com/settings/keys)
+
-
+
+ Claude API 现在提供 5 美元的免费积分,但是,它仅适用于某些特定国家 / 地区,您可以转到 Dashboard >
+ Claim 查看它是否适用于您所在的国家 / 地区。
+
-
- Claude API 现在提供 5 美元的免费积分,但是,它仅适用于某些特定国家/地区,您可以转到 Dashboard >
- Claim 查看它是否适用于您所在的国家/地区。
-
+ - 设置您的账单,让 API 密钥在 [https://console.anthropic.com/settings/plans](https://console.anthropic.com/settings/plans) 上工作(选择 “生成” 计划,以便您可以添加积分并仅为使用量付费)
-- 设置您的账单,让 API 密钥在 https://console.anthropic.com/settings/plans 上工作(选择“生成”计划,以便您可以添加积分并仅为使用量付费)
+
-
+ ### 步骤二:在 LobeChat 中配置 Anthropic Claude
-### 步骤二:在 LobeChat 中配置 Anthropic Claude
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`Anthropic Claude`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`Anthropic Claude`的设置项
+
-
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Anthropic Claude 的模型即可开始对话
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个 Anthropic Claude 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Anthropic Claude 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Anthropic Claude 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Anthropic Claude 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/azure.mdx b/DigitalHumanWeb/docs/usage/providers/azure.mdx
index 102039b..520c771 100644
--- a/DigitalHumanWeb/docs/usage/providers/azure.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/azure.mdx
@@ -14,75 +14,45 @@ tags:
# Using Azure OpenAI in LobeChat
-
+
This document will guide you on how to use [Azure OpenAI](https://oai.azure.com/) in LobeChat:
+ ### Step 1: Obtain Azure OpenAI API Key
-### Step 1: Obtain Azure OpenAI API Key
+ - If you haven't registered yet, you need to create an [Azure OpenAI account](https://oai.azure.com/).
-- If you haven't registered yet, you need to create an [Azure OpenAI account](https://oai.azure.com/).
+
-
+ - After registration, go to the `Deployments` page and create a new deployment with your selected model.
-- After registration, go to the `Deployments` page and create a new deployment with your selected model.
+ 
-
+
-
+ - Navigate to the `Chat` page and click on `View Code` to obtain your endpoint and key.
-- Navigate to the `Chat` page and click on `View Code` to obtain your endpoint and key.
+
-
+
-
+ ### Step 2: Configure Azure OpenAI in LobeChat
-### Step 2: Configure Azure OpenAI in LobeChat
+ - Access the `Settings` interface in LobeChat.
+ - Find the setting for `Azure OpenAI` under `Language Model`.
-- Access the `Settings` interface in LobeChat.
-- Find the setting for `Azure OpenAI` under `Language Model`.
+
-
+ - Enter the API key you obtained.
+ - Choose an Azure OpenAI model for your AI assistant to start the conversation.
-- Enter the API key you obtained.
-- Choose an Azure OpenAI model for your AI assistant to start the conversation.
-
-
-
-
- During usage, you may need to pay the API service provider. Please refer to Azure OpenAI's
- relevant pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider. Please refer to Azure OpenAI's
+ relevant pricing policies.
+
Now you can engage in conversations using the models provided by Azure OpenAI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/azure.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/azure.zh-CN.mdx
index 9346a27..ac8d399 100644
--- a/DigitalHumanWeb/docs/usage/providers/azure.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/azure.zh-CN.mdx
@@ -9,71 +9,42 @@ tags:
# 在 LobeChat 中使用 Azure OpenAI
-
+
本文档将指导你如何在 LobeChat 中使用 [Azure OpenAI](https://oai.azure.com/):
+ ### 步骤一:获取 Azure OpenAI API 密钥
-### 步骤一:获取 Azure OpenAI API 密钥
+ - 如果尚未注册,则必须注册 [Azure OpenAI 帐户](https://oai.azure.com/)。
-- 如果尚未注册,则必须注册 [Azure OpenAI 帐户](https://oai.azure.com/)。
+
-
+ - 注册完毕后,转到 `Deployments` 页面,然后使用您选择的模型创建新部署。
-- 注册完毕后,转到 `Deployments` 页面,然后使用您选择的模型创建新部署。
+
-
+ - 转到 `Chat` 页面,然后单击 `View Code` 以获取您的终结点和密钥。
-- 转到 `Chat` 页面,然后单击 `View Code` 以获取您的终结点和密钥。
+
-
-
+
-### 步骤二:在 LobeChat 中配置 Azure OpenAI
+ ### 步骤二:在 LobeChat 中配置 Azure OpenAI
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`Azure OpenAI`的设置项
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`Azure OpenAI`的设置项
-
+
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个 Azure OpenAI 的模型即可开始对话
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Azure OpenAI 的模型即可开始对话
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Azure OpenAI 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Azure OpenAI 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Azure OpenAI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/azureai.mdx b/DigitalHumanWeb/docs/usage/providers/azureai.mdx
new file mode 100644
index 0000000..697403a
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/azureai.mdx
@@ -0,0 +1,69 @@
+---
+title: Using Azure AI API Key in LobeChat
+description: Learn how to configure and use Azure AI models in LobeChat, get the API key, and start a conversation.
+tags:
+ - LobeChat
+ - Azure AI
+ - API Key
+ - Web UI
+---
+
+# Using Azure AI in LobeChat
+
+
+
+[Azure AI](https://azure.microsoft.com) is an open artificial intelligence technology platform based on the Microsoft Azure cloud platform. It provides various AI functionalities, including natural language processing, machine learning, and computer vision, helping businesses easily develop and deploy AI applications.
+
+This document will guide you on how to integrate Azure AI models into LobeChat:
+
+
+ ### Step 1: Deploy Azure AI Project and Model
+
+ - First, visit [Azure AI Foundry](https://ai.azure.com/) and complete the registration and login process.
+ - After logging in, select `Browse models` on the homepage.
+
+
+
+ - Choose the model you want in the model marketplace.
+ - Enter the model details and click the `Deploy` button.
+
+
+
+ - In the pop-up dialog, create a new project.
+
+
+
+
+ For detailed configuration of Azure AI Foundry, please refer to the [official documentation](https://learn.microsoft.com/azure/ai-foundry/model-inference/).
+
+
+ ### Step 2: Obtain the Model's API Key and Endpoint
+
+ - In the details of the deployed model, you can find the Endpoint and API Key information.
+ - Copy and save the obtained information.
+
+
+
+ ### Step 3: Configure Azure AI in LobeChat
+
+ - Visit the `App Settings` and `AI Service Provider` interface in LobeChat.
+ - Find the settings for `Azure AI` in the list of providers.
+
+
+
+ - Enable the Azure AI service provider and fill in the obtained Endpoint and API Key.
+
+
+ For the Endpoint, you only need to fill in the first part: `https://xxxxxx.services.ai.azure.com/models`.
+
+
+ - Choose an Azure AI model for your assistant and start the conversation.
+
+
+
+
+ You may need to pay the API service provider for usage. Please refer to Azure AI's relevant pricing policies.
+
+
+
+Now you can use the models provided by Azure AI in LobeChat for conversations.
diff --git a/DigitalHumanWeb/docs/usage/providers/azureai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/azureai.zh-CN.mdx
new file mode 100644
index 0000000..84f6ba7
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/azureai.zh-CN.mdx
@@ -0,0 +1,69 @@
+---
+title: 在 LobeChat 中使用 Azure AI API Key
+description: 学习如何在 LobeChat 中配置和使用 Azure AI 模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - Azure AI
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Azure AI
+
+
+
+[Azure AI](https://azure.microsoft.com) 是一个基于 Microsoft Azure 云平台的开放式人工智能技术平台,提供包括自然语言处理、机器学习、计算机视觉等多种 AI 功能,帮助企业轻松开发和部署 AI 应用。
+
+本文档将指导你如何在 LobeChat 中接入 Azure AI 的模型:
+
+
+ ### 步骤一:部署 Azure AI 项目以及模型
+
+ - 首先,访问[Azure AI Foundry](https://ai.azure.com/)并完成注册登录
+ - 登录后在首页选择`浏览模型`
+
+
+
+ - 在模型广场中选择你想要模型
+ - 进入模型详情,点击`部署`按钮
+
+
+
+ - 在弹出的对话框中创建一个新的项目
+
+
+
+
+ Azure AI Foundry 的详细配置请参考[官方文档](https://learn.microsoft.com/azure/ai-foundry/model-inference/)
+
+
+ ### 步骤二:获取模型的 API Key 及 Endpoint
+
+ - 在已部署的模型详情里,可以查询到 Endpoint 以及 API Key 信息
+ - 复制并保存好获取的信息
+
+
+
+ ### 步骤三:在 LobeChat 中配置 Azure AI
+
+ - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+ - 在供应商列表中找到 `Azure AI` 的设置项
+
+
+
+ - 打开 Azure AI 服务商并填入获取的 Endpoint 以及 API 密钥
+
+
+ Endpoint 只需要填入前面部分 `https://xxxxxx.services.ai.azure.com/models` 即可
+
+
+ - 为你的助手选择一个 Azure AI 模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Azure AI 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Azure AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/baichuan.mdx b/DigitalHumanWeb/docs/usage/providers/baichuan.mdx
index f1ee996..4d1579e 100644
--- a/DigitalHumanWeb/docs/usage/providers/baichuan.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/baichuan.mdx
@@ -13,52 +13,34 @@ tags:
# Using Baichuan in LobeChat
-
+
This article will guide you on how to use Baichuan in LobeChat:
+ ### Step 1: Obtain Baichuan Intelligent API Key
-### Step 1: Obtain Baichuan Intelligent API Key
+ - Create a [Baichuan Intelligent](https://platform.baichuan-ai.com/homePage) account
+ - Create and obtain an [API key](https://platform.baichuan-ai.com/console/apikey)
-- Create a [Baichuan Intelligent](https://platform.baichuan-ai.com/homePage) account
-- Create and obtain an [API key](https://platform.baichuan-ai.com/console/apikey)
+
-
+ ### Step 2: Configure Baichuan in LobeChat
-### Step 2: Configure Baichuan in LobeChat
+ - Visit the `Settings` interface in LobeChat
+ - Find the setting for `Baichuan` under `Language Model`
-- Visit the `Settings` interface in LobeChat
-- Find the setting for `Baichuan` under `Language Model`
+
-
+ - Enter the obtained API key
+ - Choose a Baichuan model for your AI assistant to start the conversation
-- Enter the obtained API key
-- Choose a Baichuan model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Baichuan's relevant
- pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Baichuan's relevant
+ pricing policies.
+
You can now use the models provided by Baichuan for conversation in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/baichuan.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/baichuan.zh-CN.mdx
index f4101be..6756126 100644
--- a/DigitalHumanWeb/docs/usage/providers/baichuan.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/baichuan.zh-CN.mdx
@@ -11,51 +11,33 @@ tags:
# 在 LobeChat 中使用百川
-
+
本文将指导你如何在 LobeChat 中使用百川:
+ ### 步骤一:获取百川智能 API 密钥
-### 步骤一:获取百川智能 API 密钥
+ - 创建一个[百川智能](https://platform.baichuan-ai.com/homePage)账户
+ - 创建并获取 [API 密钥](https://platform.baichuan-ai.com/console/apikey)
-- 创建一个[百川智能](https://platform.baichuan-ai.com/homePage)账户
-- 创建并获取 [API 密钥](https://platform.baichuan-ai.com/console/apikey)
+
-
+ ### 步骤二:在 LobeChat 中配置百川
-### 步骤二:在 LobeChat 中配置百川
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`百川`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`百川`的设置项
+
-
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个百川的模型即可开始对话
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个百川的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考百川的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考百川的相关费用政策。
+
至此你已经可以在 LobeChat 中使用百川提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/bedrock.mdx b/DigitalHumanWeb/docs/usage/providers/bedrock.mdx
index 4770bd2..e02f2e6 100644
--- a/DigitalHumanWeb/docs/usage/providers/bedrock.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/bedrock.mdx
@@ -14,126 +14,77 @@ tags:
# Using Amazon Bedrock in LobeChat
-
+
Amazon Bedrock is a fully managed foundational model API service that allows users to access models from leading AI companies (such as AI21 Labs, Anthropic, Cohere, Meta, Stability AI) and Amazon's own foundational models.
This document will guide you on how to use Amazon Bedrock in LobeChat:
-### Step 1: Grant Access to Amazon Bedrock Models in AWS
+ ### Step 1: Grant Access to Amazon Bedrock Models in AWS
-- Access and log in to the [AWS Console](https://console.aws.amazon.com/)
-- Search for `bedrock` and enter the `Amazon Bedrock` service
+ - Access and log in to the [AWS Console](https://console.aws.amazon.com/)
+ - Search for `bedrock` and enter the `Amazon Bedrock` service
-
+
-- Select `Models access` from the left menu
+ - Select `Models access` from the left menu
-
+
-- Open model access permissions based on your needs
+ - Open model access permissions based on your needs
-
+
-Some models may require additional information from you
+ Some models may require additional information from you
-### Step 2: Obtain API Access Keys
+ ### Step 2: Obtain API Access Keys
-- Continue searching for IAM in the AWS console and enter the IAM service
+ - Continue searching for IAM in the AWS console and enter the IAM service
-
+
-- In the `Users` menu, create a new IAM user
+ - In the `Users` menu, create a new IAM user
-
+
-- Enter the user name in the pop-up dialog box
+ - Enter the user name in the pop-up dialog box
-
+
-- Add permissions for this user or join an existing user group to ensure access to Amazon Bedrock
+ - Add permissions for this user or join an existing user group to ensure access to Amazon Bedrock
-
+
-- Create an access key for the added user
+ - Create an access key for the added user
-
+
-- Copy and securely store the access key and secret access key, as they will be needed later
+ - Copy and securely store the access key and secret access key, as they will be needed later
-
+
-
- Please securely store the keys as they will only be shown once. If you lose them accidentally, you
- will need to create a new access key.
-
+
+ Please securely store the keys as they will only be shown once. If you lose them accidentally, you
+ will need to create a new access key.
+
-### Step 3: Configure Amazon Bedrock in LobeChat
+ ### Step 3: Configure Amazon Bedrock in LobeChat
-- Access the `Settings` interface in LobeChat
-- Find the setting for `Amazon Bedrock` under `Language Models` and open it
+ - Access the `Settings` interface in LobeChat
+ - Find the setting for `Amazon Bedrock` under `Language Models` and open it
-
+
-- Open Amazon Bedrock and enter the obtained access key and secret access key
-- Choose an Amazon Bedrock model for your assistant to start the conversation
+ - Open Amazon Bedrock and enter the obtained access key and secret access key
+ - Choose an Amazon Bedrock model for your assistant to start the conversation
-
-
-
- You may incur charges while using the API service, please refer to Amazon Bedrock's pricing
- policy.
-
+
+
+ You may incur charges while using the API service, please refer to Amazon Bedrock's pricing
+ policy.
+
You can now engage in conversations using the models provided by Amazon Bedrock in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/bedrock.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/bedrock.zh-CN.mdx
index ef70dc3..e19563b 100644
--- a/DigitalHumanWeb/docs/usage/providers/bedrock.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/bedrock.zh-CN.mdx
@@ -11,124 +11,75 @@ tags:
# 在 LobeChat 中使用 Amazon Bedrock
-
+
-Amazon Bedrock 是一个完全托管的基础模型API服务,允许用户通过API访问来自领先AI公司(如AI21 Labs、Anthropic、Cohere、Meta、Stability AI)和Amazon自家的基础模型。
+Amazon Bedrock 是一个完全托管的基础模型 API 服务,允许用户通过 API 访问来自领先 AI 公司 (如 AI21 Labs、Anthropic、Cohere、Meta、Stability AI) 和 Amazon 自家的基础模型。
本文档将指导你如何在 LobeChat 中使用 Amazon Bedrock:
-### 步骤一:在 AWS 中打开 Amazon Bedrock 模型的访问权限
+ ### 步骤一:在 AWS 中打开 Amazon Bedrock 模型的访问权限
-- 访问并登录 [AWS Console](https://console.aws.amazon.com/)
-- 搜索 beckrock 并进入 `Amazon Bedrock` 服务
+ - 访问并登录 [AWS Console](https://console.aws.amazon.com/)
+ - 搜索 beckrock 并进入 `Amazon Bedrock` 服务
-
+
-- 在左侧菜单中选择 `Models acess`
+ - 在左侧菜单中选择 `Models acess`
-
+
-- 根据你所需要的模型,打开模型访问权限
+ - 根据你所需要的模型,打开模型访问权限
-
+
-某些模型可能需要你提供额外的信息
+ 某些模型可能需要你提供额外的信息
-### 步骤二:获取 API 访问密钥
+ ### 步骤二:获取 API 访问密钥
-- 继续在 AWS console 中搜索 IAM,进入 IAM 服务
+ - 继续在 AWS console 中搜索 IAM,进入 IAM 服务
-
+
-- 在 `用户` 菜单中,创建一个新的 IAM 用户
+ - 在 `用户` 菜单中,创建一个新的 IAM 用户
-
+
-- 在弹出的对话框中,输入用户名称
+ - 在弹出的对话框中,输入用户名称
-
+
-- 为这个用户添加权限,或者加入一个已有的用户组,确保用户拥有 Amazon Bedrock 的访问权限
+ - 为这个用户添加权限,或者加入一个已有的用户组,确保用户拥有 Amazon Bedrock 的访问权限
-
+
-- 为已添加的用户创建访问密钥
+ - 为已添加的用户创建访问密钥
-
+
-- 复制并妥善保存访问密钥以及秘密访问密钥,后续将会用到
+ - 复制并妥善保存访问密钥以及秘密访问密钥,后续将会用到
-
+
-
- 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新访问密钥。
-
+
+ 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新访问密钥。
+
-### 步骤三:在 LobeChat 中配置 Amazon Bedrock
+ ### 步骤三:在 LobeChat 中配置 Amazon Bedrock
-- 访问LobeChat的`设置`界面
-- 在`语言模型`下找到`Amazon Bedrock`的设置项并打开
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`Amazon Bedrock`的设置项并打开
-
+
-- 打开 Amazon Bedrock 并填入获得的访问密钥与秘密访问密钥
-- 为你的助手选择一个 Amazone Bedrock 的模型即可开始对话
+ - 打开 Amazon Bedrock 并填入获得的访问密钥与秘密访问密钥
+ - 为你的助手选择一个 Amazone Bedrock 的模型即可开始对话
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Amazon Bedrock 的费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Amazon Bedrock 的费用政策。
+
至此你已经可以在 LobeChat 中使用 Amazone Bedrock 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/cloudflare.mdx b/DigitalHumanWeb/docs/usage/providers/cloudflare.mdx
new file mode 100644
index 0000000..98dbedd
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/cloudflare.mdx
@@ -0,0 +1,59 @@
+---
+title: Using Cloudflare Workers AI in LobeChat
+description: Learn how to integrate and utilize Cloudflare Workers AI Models in LobeChat.
+tags:
+ - LobeChat
+ - Cloudflare
+ - Workers AI
+ - Provider
+ - API Key
+ - Web UI
+---
+
+# Using Cloudflare Workers AI in LobeChat
+
+
+
+[Cloudflare Workers AI](https://www.cloudflare.com/developer-platform/products/workers-ai/) is a service that integrates AI capabilities into the Cloudflare Workers serverless computing platform. Its core functionality lies in delivering fast, scalable computing power through Cloudflare's global network, thereby reducing operational overhead.
+
+This document will guide you on how to use Cloudflare Workers AI in LobeChat:
+
+
+ ### Step 1: Obtain Your Cloudflare Workers AI API Key
+
+ - Visit the [Cloudflare website](https://www.cloudflare.com/) and sign up for an account.
+ - Log in to the [Cloudflare dashboard](https://dash.cloudflare.com/).
+ - In the left-hand menu, locate the `AI` > `Workers AI` option.
+
+
+
+ - In the `Using REST API` section, click the `Create Workers AI API Token` button.
+ - In the drawer dialog, copy and save your `API token`.
+ - Also, copy and save your `Account ID`.
+
+
+
+
+ - Please store your API token securely, as it will only be displayed once. If you accidentally lose it, you will need to create a new token.
+
+
+ ### Step 2: Configure Cloudflare Workers AI in LobeChat
+
+ - Go to the `Settings` interface in LobeChat.
+ - Under `Language Model`, find the `Cloudflare` settings.
+
+
+
+ - Enter the `API Token` you obtained.
+ - Input your `Account ID`.
+ - Choose a Cloudflare Workers AI model for your AI assistant to start the conversation.
+
+
+
+
+ You may incur charges while using the API service, please refer to Cloudflare's pricing policy for
+ details.
+
+
+
+At this point, you can start conversing with the model provided by Cloudflare Workers AI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/cloudflare.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/cloudflare.zh-CN.mdx
new file mode 100644
index 0000000..95769ae
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/cloudflare.zh-CN.mdx
@@ -0,0 +1,58 @@
+---
+title: 在 LobeChat 中使用 Cloudflare Workers AI
+description: 学习如何在 LobeChat 中配置和使用 Cloudflare Workers AI 的 API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - Cloudflare
+ - Workers AI
+ - 供应商
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Cloudflare Workers AI
+
+
+
+[Cloudflare Workers AI](https://www.cloudflare.com/developer-platform/products/workers-ai/) 是一种将人工智能能力集成到 Cloudflare Workers 无服务器计算平台的服务。其核心功能在于通过 Cloudflare 的全球网络提供快速、可扩展的计算能力,降低运维开销。
+
+本文档将指导你如何在 LobeChat 中使用 Cloudflare Workers AI:
+
+
+ ### 步骤一:获取 Cloudflare Workers AI 的 API Key
+
+ - 访问 [Cloudflare 官网](https://www.cloudflare.com/) 并注册一个账号。
+ - 登录 [Cloudflare 控制台](https://dash.cloudflare.com/).
+ - 在左侧的菜单中找到 `AI` > `Workers AI` 选项。
+
+
+
+ - 在 `使用 REST API` 中点击 `创建 Workers AI API 令牌` 按钮
+ - 在弹出的侧边栏中复制并保存你的 `API 令牌`
+ - 同时也复制并保存你的 `账户ID`
+
+
+
+
+ - 请安全地存储 API 令牌,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新令牌。
+
+
+ ### 步骤二:在 LobeChat 中配置 Cloudflare Workers AI
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `Cloudflare` 的设置项
+
+
+
+ - 填入获得的 `API 令牌`
+ - 填入你的`账户ID`
+ - 为你的 AI 助手选择一个 Cloudflare Workers AI 的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Cloudflare 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Cloudflare Workers AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/deepseek.mdx b/DigitalHumanWeb/docs/usage/providers/deepseek.mdx
index fb5c77c..23a2275 100644
--- a/DigitalHumanWeb/docs/usage/providers/deepseek.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/deepseek.mdx
@@ -13,78 +13,52 @@ tags:
# Using DeepSeek in LobeChat
-
+
-[DeepSeek](https://www.deepseek.com/) is an advanced open-source Large Language Model (LLM). The latest version, DeepSeek-V2, has made significant optimizations in architecture and performance, reducing training costs by 42.5% and inference costs by 93.3%.
+[DeepSeek](https://www.deepseek.com/) represents a cutting-edge open-source large language model. The latest versions, DeepSeek-V3 and DeepSeek-R1, have undergone substantial improvements in both architecture and performance, particularly shining in their inference capabilities. By leveraging innovative training methodologies and reinforcement learning, the model has effectively boosted its inference prowess, now nearly matching the pinnacle performance of OpenAI.
This document will guide you on how to use DeepSeek in LobeChat:
+ ### Step 1: Obtain DeepSeek API Key
-### Step 1: Obtain DeepSeek API Key
+ - First, you need to register and log in to the [DeepSeek](https://platform.deepseek.com/) open platform.
-- First, you need to register and log in to the [DeepSeek](https://platform.deepseek.com/) open platform.
+ New users will receive a free quota of 500M Tokens
-New users will receive a free quota of 500M Tokens
+ - Go to the `API keys` menu and click on `Create API Key`.
-- Go to the `API keys` menu and click on `Create API Key`.
+
-
+ - Enter the API key name in the pop-up dialog box.
-- Enter the API key name in the pop-up dialog box.
+
-
+ - Copy the generated API key and save it securely.
-- Copy the generated API key and save it securely.
+
-
+
+ Please store the key securely as it will only appear once. If you accidentally lose it, you will
+ need to create a new key.
+
-
- Please store the key securely as it will only appear once. If you accidentally lose it, you will
- need to create a new key.
-
+ ### Step 2: Configure DeepSeek in LobeChat
-### Step 2: Configure DeepSeek in LobeChat
+ - Access the `App Settings` interface in LobeChat.
+ - Find the setting for `DeepSeek` under `Language Models`.
-- Access the `App Settings` interface in LobeChat.
-- Find the setting for `DeepSeek` under `Language Models`.
+
-
+ - Open DeepSeek and enter the obtained API key.
+ - Choose a DeepSeek model for your assistant to start the conversation.
-- Open DeepSeek and enter the obtained API key.
-- Choose a DeepSeek model for your assistant to start the conversation.
-
-
-
-
- You may need to pay the API service provider during usage, please refer to DeepSeek's relevant
- pricing policies.
-
+
+
+ You may need to pay the API service provider during usage, please refer to DeepSeek's relevant
+ pricing policies.
+
You can now engage in conversations using the models provided by Deepseek in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/deepseek.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/deepseek.zh-CN.mdx
index 7cbb4a0..5cfe290 100644
--- a/DigitalHumanWeb/docs/usage/providers/deepseek.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/deepseek.zh-CN.mdx
@@ -4,82 +4,57 @@ description: 学习如何在 LobeChat 中配置和使用 DeepSeek 语言模型
tags:
- LobeChat
- DeepSeek
+ - DeepSeek R1
- API密钥
- Web UI
---
# 在 LobeChat 中使用 DeepSeek
-
+
-[DeepSeek](https://www.deepseek.com/) 是一款先进的开源大型语言模型(LLM)。最新版本 DeepSeek-V2 在架构和性能上进行了显著优化,同时训练成本降低了42.5%,推理成本降低了93.3%。
+[DeepSeek](https://www.deepseek.com/) 是一款先进的开源大型语言模型(LLM)。最新的 DeepSeek-V3 和 DeepSeek-R1 在架构和性能上进行了显著优化,特别是在推理能力方面表现出色。它通过创新性的训练方法和强化学习技术,成功地提升了模型的推理能力,并且其性能已逼近 OpenAI 的顶尖水平。
-本文档将指导你如何在 LobeChat 中使用 DeepSeek:
+本文档将指导你如何在 LobeChat 中使用 DeepSeek:
+ ### 步骤一:获取 DeepSeek API 密钥
-### 步骤一:获取 DeepSeek API 密钥
+ - 首先,你需要注册并登录 [DeepSeek](https://platform.deepseek.com/) 开放平台
-- 首先,你需要注册并登录 [DeepSeek](https://platform.deepseek.com/) 开放平台
+ 当前新用户将会获赠 500M Tokens 的免费额度
-当前新用户将会获赠 500M Tokens 的免费额度
+ - 进入 `API keys` 菜单,并点击 `创建 API Key`
-- 进入 `API keys` 菜单,并点击 `创建 API Key`
+
-
+ - 在弹出的对话框中输入 API 密钥名称
-- 在弹出的对话框中输入 API 密钥名称
+
-
+ - 复制得到的 API 密钥并妥善保存
-- 复制得到的 API 密钥并妥善保存
+
-
+
+ 请安全地存储密钥,因为它只会出现一次。如果你意外丢失它,您将需要创建一个新密钥。
+
-
- 请安全地存储密钥,因为它只会出现一次。如果你意外丢失它,您将需要创建一个新密钥。
-
+ ### 步骤二:在 LobeChat 中配置 DeepSeek
-### 步骤二:在 LobeChat 中配置 DeepSeek
+ - 访问 LobeChat 的 `应用设置`界面
+ - 在 `语言模型` 下找到 `DeepSeek` 的设置项
-- 访问 LobeChat 的 `应用设置`界面
-- 在 `语言模型` 下找到 `DeepSeek` 的设置项
+
-
+ - 打开 DeepSeek 并填入获取的 API 密钥
+ - 为你的助手选择一个 DeepSeek 模型即可开始对话
-- 打开 DeepSeek 并填入获取的 API 密钥
-- 为你的助手选择一个 DeepSeek 模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 DeepSeek 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 DeepSeek 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Deepseek 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/fireworksai.mdx b/DigitalHumanWeb/docs/usage/providers/fireworksai.mdx
new file mode 100644
index 0000000..297b776
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/fireworksai.mdx
@@ -0,0 +1,57 @@
+---
+title: Using Fireworks AI in LobeChat
+description: >-
+ Learn how to integrate and utilize Fireworks AI's language model APIs in
+ LobeChat.
+tags:
+ - LobeChat
+ - Fireworks AI
+ - API Key
+ - Web UI
+---
+
+# Using Fireworks AI in LobeChat
+
+
+
+[Fireworks.ai](https://fireworks.ai/) is a high-performance generative AI model inference platform that allows users to access and utilize various models through its API. The platform supports multiple modalities, including text and visual language models, and offers features like function calls and JSON schemas to enhance the flexibility of application development.
+
+This article will guide you on how to use Fireworks AI in LobeChat.
+
+
+ ### Step 1: Obtain an API Key for Fireworks AI
+
+ - Log in to the [Fireworks.ai Console](https://fireworks.ai/account/api-keys)
+ - Navigate to the `User` page and click on `API Keys`
+ - Create a new API key
+
+
+
+ - Copy and securely save the generated API key
+
+
+
+
+ Please store the key securely, as it will appear only once. If you accidentally lose it, you will
+ need to create a new key.
+
+
+ ### Step 2: Configure Fireworks AI in LobeChat
+
+ - Access the `Settings` interface in LobeChat
+ - Under `Language Model`, locate the settings for `Fireworks AI`
+
+
+
+ - Enter the obtained API key
+ - Select a Fireworks AI model for your AI assistant to start a conversation
+
+
+
+
+ Please note that you may need to pay fees to the API service provider during use; refer to
+ Fireworks AI's pricing policy for details.
+
+
+
+You are now ready to use the models provided by Fireworks AI for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/fireworksai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/fireworksai.zh-CN.mdx
new file mode 100644
index 0000000..5d86191
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/fireworksai.zh-CN.mdx
@@ -0,0 +1,53 @@
+---
+title: 在 LobeChat 中使用 Fireworks AI
+description: 学习如何在 LobeChat 中配置和使用 Fireworks AI 的API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - Fireworks AI
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Fireworks AI
+
+
+
+[Fireworks.ai](https://fireworks.ai/) 是一个高性能的生成式 AI 模型推理平台,允许用户通过其 API 访问和使用各种模型。该平台支持多种模态,包括文本和视觉语言模型,并提供函数调用和 JSON 模式等功能,以增强应用开发的灵活性。
+
+本文将指导你如何在 LobeChat 中使用 Fireworks AI。
+
+
+ ### 步骤一:获得 Fireworks AI 的 API Key
+
+ - 登录 [Fireworks.ai 控制台](https://fireworks.ai/account/api-keys)
+ - 进入 `User` 页面,点击 `API Keys`
+ - 创建一个新的 API 密钥
+
+
+
+ - 复制并保存生成的 API 密钥
+
+
+
+
+ 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新密钥。
+
+
+ ### 步骤二:在 LobeChat 中配置 Fireworks AI
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `Fireworks AI` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Fireworks AI 的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Fireworks AI 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Fireworks AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/gemini.mdx b/DigitalHumanWeb/docs/usage/providers/gemini.mdx
index 7492937..d71ffc3 100644
--- a/DigitalHumanWeb/docs/usage/providers/gemini.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/gemini.mdx
@@ -13,70 +13,44 @@ tags:
# Using Google Gemini in LobeChat
-
+
Gemini AI is a set of large language models (LLMs) created by Google AI, known for its cutting-edge advancements in multimodal understanding and processing. It is essentially a powerful artificial intelligence tool capable of handling various tasks involving different types of data, not just text.
This document will guide you on how to use Google Gemini in LobeChat:
+ ### Step 1: Obtain Google API Key
-### Step 1: Obtain Google API Key
+ - Visit and log in to [Google AI Studio](https://aistudio.google.com/)
+ - Navigate to `Get API Key` in the menu and click on `Create API Key`
-- Visit and log in to [Google AI Studio](https://aistudio.google.com/)
-- Navigate to `Get API Key` in the menu and click on `Create API Key`
+
-
+ - Select a project and create an API key, or create one in a new project
-- Select a project and create an API key, or create one in a new project
+
-
+ - Copy the API key from the pop-up dialog
-- Copy the API key from the pop-up dialog
+
-
+ ### Step 2: Configure OpenAI in LobeChat
-### Step 2: Configure OpenAI in LobeChat
+ - Go to the `Settings` interface in LobeChat
+ - Find the setting for `Google Gemini` under `Language Models`
-- Go to the `Settings` interface in LobeChat
-- Find the setting for `Google Gemini` under `Language Models`
+
-
+ - Enable Google Gemini and enter the obtained API key
+ - Choose a Gemini model for your assistant to start the conversation
-- Enable Google Gemini and enter the obtained API key
-- Choose a Gemini model for your assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Google Gemini's
- pricing policy.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Google Gemini's
+ pricing policy.
+
Congratulations! You can now use Google Gemini in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/gemini.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/gemini.zh-CN.mdx
index de796fc..8e55e54 100644
--- a/DigitalHumanWeb/docs/usage/providers/gemini.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/gemini.zh-CN.mdx
@@ -10,69 +10,43 @@ tags:
# 在 LobeChat 中使用 Google Gemini
-
+
-Gemini AI是由 Google AI 创建的一组大型语言模型(LLM),以其在多模式理解和处理方面的尖端进步而闻名。它本质上是一个强大的人工智能工具,可以处理涉及不同类型数据的各种任务,而不仅仅是文本。
+Gemini AI 是由 Google AI 创建的一组大型语言模型(LLM),以其在多模式理解和处理方面的尖端进步而闻名。它本质上是一个强大的人工智能工具,可以处理涉及不同类型数据的各种任务,而不仅仅是文本。
本文档将指导你如何在 LobeChat 中使用 Google Gemini:
+ ### 步骤一:获取 Google 的 API 密钥
-### 步骤一:获取 Google 的 API 密钥
+ - 访问并登录 [Google AI Studio](https://aistudio.google.com/)
+ - 在 `获取 API 密钥` 菜单中 `创建 API 密钥`
-- 访问并登录 [Google AI Studio](https://aistudio.google.com/)
-- 在 `获取 API 密钥` 菜单中 `创建 API 密钥`
+
-
+ - 选择一个项目并创建 API 密钥,或者在新项目中创建 API 密钥
-- 选择一个项目并创建 API 密钥,或者在新项目中创建 API 密钥
+
-
+ - 在弹出的对话框中复制 API 密钥
-- 在弹出的对话框中复制 API 密钥
+
-
+ ### 步骤二:在 LobeChat 中配置 OpenAI
-### 步骤二:在 LobeChat 中配置OpenAI
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`Google Gemini`的设置项
-- 访问LobeChat的`设置`界面
-- 在`语言模型`下找到`Google Gemini`的设置项
+
-
+ - 打开 Google Gemini 并填入获得的 API 密钥
+ - 为你的助手选择一个 Gemini 的模型即可开始对话
-- 打开 Google Gemini 并填入获得的 API 密钥
-- 为你的助手选择一个 Gemini 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Google Gemini 的费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Google Gemini 的费用政策。
+
至此,你已经可以在 LobeChat 中使用 Google Gemini 啦。
diff --git a/DigitalHumanWeb/docs/usage/providers/giteeai.mdx b/DigitalHumanWeb/docs/usage/providers/giteeai.mdx
new file mode 100644
index 0000000..189b2f8
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/giteeai.mdx
@@ -0,0 +1,58 @@
+---
+title: Using Gitee AI in LobeChat
+description: >-
+ Learn how to configure and use Gitee AI's API Key in LobeChat to start
+ conversations and interactions.
+tags:
+ - LobeChat
+ - Gitee AI
+ - API Key
+ - Web UI
+---
+
+# Using Gitee AI in LobeChat
+
+
+
+[Gitee AI](https://ai.gitee.com/) is an open-source platform based on Git code hosting technology, specifically designed for AI application scenarios. It aims to provide developers and businesses with a one-stop solution for AI application development services, including model experience, inference, fine-tuning, and deployment.
+
+This article will guide you on how to use Gitee AI in LobeChat.
+
+
+ ### Step 1: Obtain the Gitee AI API Key
+
+ - Register and log in to the [Gitee AI official website](https://ai.gitee.com/)
+ - Purchase and recharge `Serverless API` from your dashboard
+
+
+
+ - In `Settings`, click on the `Access Tokens` section
+ - Create a new access token
+ - Save the access token in the pop-up window
+
+
+
+
+ Please keep the access token safe as it will only appear once. If you accidentally lose it, you
+ will need to create a new one.
+
+
+ ### Step 2: Configure Gitee AI in LobeChat
+
+ - Access the `Settings` page in LobeChat
+ - Under `Language Models`, find the settings for `Gitee AI`
+
+
+
+ - Enter the obtained API key
+ - Select a Gitee AI model for your AI assistant to begin chatting
+
+
+
+
+ During usage, you may need to make payments to the API service provider; please refer to Gitee
+ AI's relevant pricing policy.
+
+
+
+Now you can start having conversations using the models provided by Gitee AI in LobeChat!
diff --git a/DigitalHumanWeb/docs/usage/providers/giteeai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/giteeai.zh-CN.mdx
new file mode 100644
index 0000000..9d5ae4a
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/giteeai.zh-CN.mdx
@@ -0,0 +1,54 @@
+---
+title: 在 LobeChat 中使用 Gitee AI
+description: 学习如何在 LobeChat 中配置和使用 Gitee AI 的 API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - Gitee AI
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Gitee AI
+
+
+
+[Gitee AI](https://ai.gitee.com/) 是一个基于 Git 代码托管技术的开源平台,专为人工智能(AI)应用场景设计。它旨在为开发者和企业提供一站式的 AI 应用开发服务,包括模型体验、推理、微调和部署等功能。
+
+本文将指导你如何在 LobeChat 中使用 Gitee AI。
+
+
+ ### 步骤一:获取 Gitee AI 的 API 密钥
+
+ - 注册并登录 [Gitee AI 官网](https://ai.gitee.com/)
+ - 在工作台中购买并充值 `Serverless API`
+
+
+
+ - 在 `设置` 中点击 `访问令牌` 界面
+ - 创建一个新的访问令牌
+ - 在弹出窗口中保存访问令牌
+
+
+
+
+ 妥善保存弹窗中的访问令牌,它只会出现一次,如果不小心丢失了,你需要重新创建一个访问令牌。
+
+
+ ### 步骤二:在 LobeChat 中配置 Gitee AI
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `Gitee AI` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Gitee AI 的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Gitee AI 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Gitee AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/github.mdx b/DigitalHumanWeb/docs/usage/providers/github.mdx
new file mode 100644
index 0000000..30fc3a7
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/github.mdx
@@ -0,0 +1,67 @@
+---
+title: Using GitHub Models in LobeChat
+description: Learn how to integrate and utilize GitHub Models in LobeChat.
+tags:
+ - LobeChat
+ - GitHub
+ - GitHub Models
+ - API Key
+ - Web UI
+---
+
+# Using GitHub Models in LobeChat
+
+
+
+[GitHub Models](https://github.com/marketplace/models) is a new feature recently launched by GitHub, designed to provide developers with a free platform to access and experiment with various AI models. GitHub Models offers an interactive sandbox environment where users can test different model parameters and prompts, and observe the responses of the models. The platform supports advanced language models, including OpenAI's GPT-4o, Meta's Llama 3.1, and Mistral's Large 2, covering a wide range of applications from large-scale language models to task-specific models.
+
+This article will guide you on how to use GitHub Models in LobeChat.
+
+## Rate Limits for GitHub Models
+
+Currently, the usage of the Playground and free API is subject to limits on the number of requests per minute, the number of requests per day, the number of tokens per request, and the number of concurrent requests. If you hit the rate limit, you will need to wait for the limit to reset before making further requests. The rate limits vary for different models (low, high, and embedding models). For model type information, please refer to the GitHub Marketplace.
+
+
+
+
+ These limits are subject to change at any time. For specific information, please refer to the
+ [GitHub Official
+ Documentation](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits).
+
+
+---
+
+## Configuration Guide for GitHub Models
+
+
+ ### Step 1: Obtain a GitHub Access Token
+
+ - Log in to GitHub and open the [Access Tokens](https://github.com/settings/tokens) page.
+ - Create and configure a new access token.
+
+
+
+ - Copy and save the generated token from the results returned.
+
+
+
+
+ - During the testing phase of GitHub Models, users must apply to join the [waitlist](https://github.com/marketplace/models/waitlist/join) in order to gain access.
+
+ - Please store the access token securely, as it will only be displayed once. If you accidentally lose it, you will need to create a new token.
+
+
+ ### Step 2: Configure GitHub Models in LobeChat
+
+ - Navigate to the `Settings` interface in LobeChat.
+ - Under `Language Models`, find the GitHub settings.
+
+
+
+ - Enter the access token you obtained.
+ - Select a GitHub model for your AI assistant to start the conversation.
+
+
+
+
+You are now ready to use the models provided by GitHub for conversations within LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/github.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/github.zh-CN.mdx
new file mode 100644
index 0000000..7b4bfa4
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/github.zh-CN.mdx
@@ -0,0 +1,66 @@
+---
+title: 在 LobeChat 中使用 GitHub Models
+description: 学习如何在 LobeChat 中配置和使用 GitHub 的 API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - GitHub
+ - GitHub Models
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 GitHub Models
+
+
+
+[GitHub Models](https://github.com/marketplace/models) 是 GitHub 最近推出的一项新功能,旨在为开发者提供一个免费的平台来访问和实验多种 AI 模型。GitHub Models 提供了一个互动沙盒环境,用户可以在此测试不同的模型参数和提示语,观察模型的响应。该平台支持多种先进的语言模型,包括 OpenAI 的 GPT-4o、Meta 的 Llama 3.1 和 Mistral 的 Large 2 等,覆盖了从大规模语言模型到特定任务模型的广泛应用。
+
+本文将指导你如何在 LobeChat 中使用 GitHub Models。
+
+## GitHub Models 速率限制
+
+当前 Playground 和免费 API 的使用受到每分钟请求数、每日请求数、每个请求的令牌数以及并发请求数的限制。若达到速率限制,则需等待限制重置后方可继续发出请求。不同模型(低、高及嵌入模型)的速率限制有所不同。 模型类型信息请参阅 GitHub Marketplace。
+
+
+
+
+ 这些限制可能随时更改,具体信息请参考 [GitHub
+ 官方文档](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits)。
+
+
+---
+
+## GitHub Models 配置指南
+
+
+ ### 步骤一:获得 GitHub 的访问令牌
+
+ - 登录 GitHub 并打开 [访问令牌](https://github.com/settings/tokens) 页面
+ - 创建并设置一个新的访问令牌
+
+
+
+ - 在返回的结果中复制并保存生成的令牌
+
+
+
+
+ - GitHub Models 测试期间,要使用 GitHub Models,用户需要申请加入[等待名单(waitlist)](https://github.com/marketplace/models/waitlist/join) 通过后才能获得访问权限。
+
+ - 请安全地存储访问令牌,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新令牌。
+
+
+ ### 步骤二:在 LobeChat 中配置 GitHub Models
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `GitHub` 的设置项
+
+
+
+ - 填入获得的访问令牌
+ - 为你的 AI 助手选择一个 GitHub 的模型即可开始对话
+
+
+
+
+至此你已经可以在 LobeChat 中使用 GitHub 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/groq.mdx b/DigitalHumanWeb/docs/usage/providers/groq.mdx
index 7bf7e75..c03a45d 100644
--- a/DigitalHumanWeb/docs/usage/providers/groq.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/groq.mdx
@@ -14,11 +14,7 @@ tags:
# Using Groq in LobeChat
-
+
Groq's [LPU Inference Engine](https://wow.groq.com/news_press/groq-lpu-inference-engine-leads-in-first-independent-llm-benchmark/) has excelled in the latest independent Large Language Model (LLM) benchmark, redefining the standard for AI solutions with its remarkable speed and efficiency. By integrating LobeChat with Groq Cloud, you can now easily leverage Groq's technology to accelerate the operation of large language models in LobeChat.
@@ -34,39 +30,26 @@ This document will guide you on how to use Groq in LobeChat:
### Obtaining GroqCloud API Keys
-First, you need to obtain an API Key from the [GroqCloud Console](https://console.groq.com/).
+ First, you need to obtain an API Key from the [GroqCloud Console](https://console.groq.com/).
-
+
-Create an API Key in the `API Keys` menu of the console.
+ Create an API Key in the `API Keys` menu of the console.
-
+
-
- Safely store the key from the pop-up as it will only appear once. If you accidentally lose it, you
- will need to create a new key.
-
+
+ Safely store the key from the pop-up as it will only appear once. If you accidentally lose it, you
+ will need to create a new key.
+
-### Configure Groq in LobeChat
+ ### Configure Groq in LobeChat
-You can find the Groq configuration option in `Settings` -> `Language Model`, where you can input the API Key you just obtained.
+ You can find the Groq configuration option in `Settings` -> `Language Model`, where you can input the API Key you just obtained.
Next, select a Groq-supported model in the assistant's model options, and you can experience the powerful performance of Groq in LobeChat.
-
+
diff --git a/DigitalHumanWeb/docs/usage/providers/groq.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/groq.zh-CN.mdx
index 20cf478..750b301 100644
--- a/DigitalHumanWeb/docs/usage/providers/groq.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/groq.zh-CN.mdx
@@ -11,11 +11,7 @@ tags:
# 在 LobeChat 中使用 Groq
-
+
Groq 的 [LPU 推理引擎](https://wow.groq.com/news_press/groq-lpu-inference-engine-leads-in-first-independent-llm-benchmark/) 在最新的独立大语言模型(LLM)基准测试中表现卓越,以其惊人的速度和效率重新定义了 AI 解决方案的标准。通过 LobeChat 与 Groq Cloud 的集成,你现在可以轻松地利用 Groq 的技术,在 LobeChat 中加速大语言模型的运行。
@@ -30,38 +26,25 @@ Groq 的 [LPU 推理引擎](https://wow.groq.com/news_press/groq-lpu-inference-e
### 获取 GroqCloud API Key
-首先,你需要到 [GroqCloud Console](https://console.groq.com/) 中获取一个 API Key。
+ 首先,你需要到 [GroqCloud Console](https://console.groq.com/) 中获取一个 API Key。
-
+
-在控制台的 `API Keys` 菜单中创建一个 API Key。
+ 在控制台的 `API Keys` 菜单中创建一个 API Key。
-
+
-
- 妥善保存弹窗中的 key,它只会出现一次,如果不小心丢失了,你需要重新创建一个 key。
-
+
+ 妥善保存弹窗中的 key,它只会出现一次,如果不小心丢失了,你需要重新创建一个 key。
+
-### 在 LobeChat 中配置 Groq
+ ### 在 LobeChat 中配置 Groq
-你可以在 `设置` -> `语言模型` 中找到 Groq 的配置选项,将刚才获取的 API Key 填入。
+ 你可以在 `设置` -> `语言模型` 中找到 Groq 的配置选项,将刚才获取的 API Key 填入。
接下来,在助手的模型选项中,选中一个 Groq 支持的模型,就可以在 LobeChat 中体验 Groq 强大的性能了。
-
+
diff --git a/DigitalHumanWeb/docs/usage/providers/hunyuan.mdx b/DigitalHumanWeb/docs/usage/providers/hunyuan.mdx
new file mode 100644
index 0000000..0b84e4b
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/hunyuan.mdx
@@ -0,0 +1,52 @@
+---
+title: Using Tencent Hunyuan in LobeChat
+description: >-
+ Learn how to integrate and utilize Tencent Hunyuan's language model APIs in
+ LobeChat.
+tags:
+ - LobeChat
+ - Tencent Hunyuan
+ - API Key
+ - Web UI
+---
+
+# Using Tencent Hunyuan in LobeChat
+
+
+
+[Tencent Hunyuan](https://hunyuan.tencent.com/) is a large model launched by Tencent, designed to provide users with intelligent assistant services. It utilizes natural language processing technology to help users solve problems, offer suggestions, and generate content. By conversing with the model, users can quickly access the information they need, thereby enhancing work efficiency.
+
+This article will guide you on how to use Tencent Hunyuan in LobeChat.
+
+
+ ### Step 1: Obtain the Tencent Hunyuan API Key
+
+ - Register and log in to the [Tencent Cloud Console](https://console.cloud.tencent.com/hunyuan/api-key)
+ - Navigate to `Hunyuan Large Model` and click on `API KEY Management`
+ - Create an API key
+
+
+
+ - Click `View`, and copy the API key from the pop-up panel, ensuring you save it securely
+
+
+
+ ### Step 2: Configure Tencent Hunyuan in LobeChat
+
+ - Go to the `Settings` page in LobeChat
+ - Find the `Tencent Hunyuan` settings under `Language Models`
+
+
+
+ - Enter the API key you obtained
+ - Select a Tencent Hunyuan model for your AI assistant to start the conversation
+
+
+
+
+ During usage, you may need to pay the API service provider, please refer to Tencent Hunyuan's
+ relevant pricing policy.
+
+
+
+You can now engage in conversations using the models provided by Tencent Hunyuan in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/hunyuan.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/hunyuan.zh-CN.mdx
new file mode 100644
index 0000000..2b6aea1
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/hunyuan.zh-CN.mdx
@@ -0,0 +1,49 @@
+---
+title: 在 LobeChat 中使用腾讯混元
+description: 学习如何在 LobeChat 中配置和使用腾讯混元的API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - 腾讯混元
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用腾讯混元
+
+
+
+[腾讯混元](https://hunyuan.tencent.com/)是由腾讯推出的一款大模型,旨在为用户提供智能助手服务。它能够通过自然语言处理技术,帮助用户解决问题、提供建议以及进行内容生成等任务。用户可以通过与模型的对话,快速获取所需信息,从而提高工作效率。
+
+本文将指导你如何在 LobeChat 中使用腾讯混元。
+
+
+ ### 步骤一:获得腾讯混元的 API Key
+
+ - 注册并登录 [腾讯云控制台](https://console.cloud.tencent.com/hunyuan/api-key)
+ - 进入 `混元大模型` 并点击 `API KEY 管理`
+ - 创建一个 API 密钥
+
+
+
+ - 点击`查看`,在弹出面板中复制 API 密钥,并妥善保存
+
+
+
+ ### 步骤二:在 LobeChat 中配置腾讯混元
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `腾讯混元` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个腾讯混元的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考腾讯混元的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用腾讯混元提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/internlm.mdx b/DigitalHumanWeb/docs/usage/providers/internlm.mdx
new file mode 100644
index 0000000..8474b5e
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/internlm.mdx
@@ -0,0 +1,53 @@
+---
+title: Using InternLM in LobeChat
+description: >-
+ Learn how to configure and use SenseNova's API Key in LobeChat to start
+ conversations and interactions.
+tags:
+ - LobeChat
+ - InternLM
+ - API Key
+ - Web UI
+---
+
+# Using InternLM in LobeChat
+
+
+
+[InternLM](https://platform.sensenova.cn/home) is a large pre-trained language model jointly launched by the Shanghai Artificial Intelligence Laboratory and Shusheng Group. This model focuses on natural language processing, aimed at understanding and generating human language, boasting powerful semantic comprehension and text generation capabilities.
+
+This article will guide you on how to use InternLM in LobeChat.
+
+
+ ### Step 1: Obtain the InternLM API Key
+
+ - Register and log in to [InternLM API](https://InternLM.intern-ai.org.cn/api/tokens)
+ - Create an API token
+ - Save the API token in the pop-up window
+
+
+
+
+ Please store the API token shown in the pop-up securely; it will only appear once. If you lose it,
+ you will need to create a new API token.
+
+
+ ### Step 2: Configure InternLM in LobeChat
+
+ - Go to the `Settings` interface in LobeChat
+ - Find the settings option for `InternLM` under `Language Models`
+
+
+
+ - Enter the obtained `AccessKey ID` and `AccessKey Secret`
+ - Choose a InternLM model for your AI assistant to start a conversation
+
+
+
+
+ During usage, you may need to pay the API service provider; please refer to the pricing policy
+ regarding InternLM.
+
+
+
+You are now ready to engage in conversations using the models provided by InternLM in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/internlm.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/internlm.zh-CN.mdx
new file mode 100644
index 0000000..d4a3b7c
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/internlm.zh-CN.mdx
@@ -0,0 +1,49 @@
+---
+title: 在 LobeChat 中使用书生浦语
+description: 学习如何在 LobeChat 中配置和使用书生浦语的 API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - 书生浦语
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用书生浦语
+
+
+
+[书生浦语(InternLM)](https://platform.sensenova.cn/home) 是由上海人工智能实验室与书生集团联合推出的一款大型预训练语言模型。该模型专注于自然语言处理,旨在理解和生成自然语言,具备强大的语义理解和文本生成能力。
+
+本文将指导你如何在 LobeChat 中使用书生浦语。
+
+
+ ### 步骤一:获取书生浦语的 API 密钥
+
+ - 注册并登录 [浦语 API](https://internlm.intern-ai.org.cn/api/tokens)
+ - 创建一个 API 令牌
+ - 在弹出窗口中保存 API 令牌
+
+
+
+
+ 妥善保存弹窗中的 API 令牌,它只会出现一次,如果不小心丢失了,你需要重新创建一个 API 令牌。
+
+
+ ### 步骤二:在 LobeChat 中配置书生浦语
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `书生浦语` 的设置项
+
+
+
+ - 填入获得的 `AccessKey ID` 和 `AccessKey Secret`
+ - 为你的 AI 助手选择一个书生浦语的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考书生浦语的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用书生浦语提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/jina.mdx b/DigitalHumanWeb/docs/usage/providers/jina.mdx
new file mode 100644
index 0000000..cba6543
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/jina.mdx
@@ -0,0 +1,51 @@
+---
+title: Using Jina AI API Key in LobeChat
+description: Learn how to configure and use Jina AI models in LobeChat, obtain an API key, and start conversations.
+tags:
+ - LobeChat
+ - Jina AI
+ - API Key
+ - Web UI
+---
+
+# Using Jina AI in LobeChat
+
+
+
+[Jina AI](https://jina.ai/) is an open-source neural search company founded in 2020. It focuses on using deep learning technology to process multimodal data, providing efficient information retrieval solutions and supporting search for various data types such as text, images, and videos.
+
+This document will guide you on how to use Jina AI in LobeChat:
+
+
+ ### Step 1: Obtain a Jina AI API Key
+
+ - Visit the [Jina AI official website](https://jina.ai/) and click the `API` button on the homepage.
+
+
+
+ - Find the API Key generated for you in the `API Key` menu below.
+ - Copy and save the generated API Key.
+
+
+ * Jina AI provides each user with 1M free API Tokens, and the API can be used without registration.
+ * If you need to manage the API Key or recharge the API, you need to register and log in to the [Jina AI Console](https://jina.ai/api-dashboard/).
+
+
+ ### Step 2: Configure Jina AI in LobeChat
+
+ - Visit LobeChat's `Application Settings` interface.
+ - Find the `Jina AI` setting under `Language Model`.
+
+
+
+ - Enable Jina AI and fill in the obtained API Key.
+ - Select a Jina AI model for your assistant and start the conversation.
+
+
+
+
+ You may need to pay the API service provider during use. Please refer to Jina AI's relevant fee policy.
+
+
+
+Now you can use the models provided by Jina AI in LobeChat to have conversations.
\ No newline at end of file
diff --git a/DigitalHumanWeb/docs/usage/providers/jina.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/jina.zh-CN.mdx
new file mode 100644
index 0000000..04bff33
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/jina.zh-CN.mdx
@@ -0,0 +1,51 @@
+---
+title: 在 LobeChat 中使用 Jina AI API Key
+description: 学习如何在 LobeChat 中配置和使用 Jina AI 模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - Jina AI
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Jina AI
+
+
+
+[Jina AI](https://jina.ai/) 是一家成立于 2020 年的开源神经搜索公司,专注于利用深度学习技术处理多模态数据,提供高效的信息检索解决方案,支持文本、图像、视频等多种数据类型的搜索。
+
+本文档将指导你如何在 LobeChat 中使用 Jina AI:
+
+
+ ### 步骤一:获取 Jina AI API 密钥
+
+ - 访问 [Jina AI 官方网站](https://jina.ai/),点击首页的 `API` 按钮
+
+
+
+ - 在下方的 `API Key` 菜单中找到系统为你生成的 API Key
+ - 复制并保存生成的 API Key
+
+
+ * Jina AI 会为每个用户提供 1M 免费的 API Token,无需注册即可使用 API
+ * 如果需要管理 API Key,或为 API 充值,你需要注册并登录 [Jina AI 控制台](https://jina.ai/api-dashboard/)
+
+
+ ### 步骤二:在 LobeChat 中配置 Jina AI
+
+ - 访问 LobeChat 的 `应用设置`界面
+ - 在 `语言模型` 下找到 `Jina AI` 的设置项
+
+
+
+ - 打开 Jina AI 并填入获取的 API 密钥
+ - 为你的助手选择一个 Jina AI 模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Jina AI 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Jina AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/lmstudio.mdx b/DigitalHumanWeb/docs/usage/providers/lmstudio.mdx
new file mode 100644
index 0000000..97d0736
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/lmstudio.mdx
@@ -0,0 +1,75 @@
+---
+title: Using LM Studio in LobeChat
+description: Learn how to configure and use LM Studio, and run AI models for conversations in LobeChat through LM Studio.
+tags:
+ - LobeChat
+ - LM Studio
+ - Open Source Model
+ - Web UI
+---
+
+# Using LM Studio in LobeChat
+
+
+
+[LM Studio](https://lmstudio.ai/) is a platform for testing and running large language models (LLMs), providing an intuitive and easy-to-use interface suitable for developers and AI enthusiasts. It supports deploying and running various open-source LLM models, such as Deepseek or Qwen, on local computers, enabling offline AI chatbot functionality, thereby protecting user privacy and providing greater flexibility.
+
+This document will guide you on how to use LM Studio in LobeChat:
+
+
+ ### Step 1: Obtain and Install LM Studio
+
+ - Go to the [LM Studio official website](https://lmstudio.ai/)
+ - Choose your platform and download the installation package. LM Studio currently supports MacOS, Windows, and Linux platforms.
+ - Follow the prompts to complete the installation and run LM Studio.
+
+
+
+ ### Step 2: Search and Download Models
+
+ - Open the `Discover` menu on the left, search for and download the model you want to use.
+ - Find a suitable model (such as Deepseek R1) and click download.
+ - The download may take some time, please wait patiently for it to complete.
+
+
+
+ ### Step 3: Deploy and Run Models
+
+ - Select the downloaded model in the top model selection bar and load the model.
+ - Configure the model runtime parameters in the pop-up panel. Refer to the [LM Studio official documentation](https://lmstudio.ai/docs) for detailed parameter settings.
+
+
+
+ - Click the `Load Model` button and wait for the model to finish loading and running.
+ - Once the model is loaded, you can use it in the chat interface for conversations.
+
+ ### Step 4: Enable Local Service
+
+ - If you want to use the model through other programs, you need to start a local API service. Start the service through the `Developer` panel or the software menu. The LM Studio service starts on port `1234` on your local machine by default.
+
+
+
+ - After the local service is started, you also need to enable the `CORS (Cross-Origin Resource Sharing)` option in the service settings so that the model can be used in other programs.
+
+
+
+ ### Step 5: Use LM Studio in LobeChat
+
+ - Visit the `AI Service Provider` interface in LobeChat's `Application Settings`.
+ - Find the settings for `LM Studio` in the list of providers.
+
+
+
+ - Open the LM Studio service provider and fill in the API service address.
+
+
+ If your LM Studio is running locally, make sure to turn on `Client Request Mode`.
+
+
+ - Add the model you are running in the model list below.
+ - Select a Volcano Engine model for your assistant to start the conversation.
+
+
+
+
+Now you can use the model running in LM Studio in LobeChat for conversations.
diff --git a/DigitalHumanWeb/docs/usage/providers/lmstudio.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/lmstudio.zh-CN.mdx
new file mode 100644
index 0000000..b749de9
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/lmstudio.zh-CN.mdx
@@ -0,0 +1,75 @@
+---
+title: 在 LobeChat 中使用 LM Studio
+description: 学习如何配置和使用 LM Studio,并在 LobeChat 中 通过 LM Studio 运行 AI 模型进行对话。
+tags:
+ - LobeChat
+ - LM Studio
+ - 开源模型
+ - Web UI
+---
+
+# 在 LobeChat 中使用 LM Studio
+
+
+
+[LM Studio](https://lmstudio.ai/) 是一个用于测试和运行大型语言模型(LLM)的平台,提供了直观易用的界面,适合开发人员和 AI 爱好者使用。它支持在本地电脑上部署和运行各种开源 LLM 模型,例如 Deepseek 或 Qwen,实现离线 AI 聊天机器人的功能,从而保护用户隐私并提供更大的灵活性。
+
+本文档将指导你如何在 LobeChat 中使用 LM Studio:
+
+
+ ### 步骤一:获取并安装 LM Studio
+
+ - 前往 [LM Studio 官网](https://lmstudio.ai/)
+ - 选择你的平台并下载安装包,LM Studio 目前支持 MacOS、Windows 和 Linux 平台
+ - 按照提示完成安装,运行 LM Studio
+
+
+
+ ### 步骤二:搜索并下载模型
+
+ - 打开左侧的 `Discover` 菜单,搜索并下载你想要使用的模型
+ - 找到合适的模型(如 Deepseek R1),点击下载
+ - 下载可能需要一些时间,耐心等待完成
+
+
+
+ ### 步骤三:部署并运行模型
+
+ - 在顶部的模型选择栏中选择下载好的模型,并加载模型
+ - 在弹出的面板中配置模型运行参数,详细的参数设置请参考 [LM Studio 官方文档](https://lmstudio.ai/docs)
+
+
+
+ - 点击 `加载模型` 按钮,等待模型完成加载并运行
+ - 模型加载完成后,你可以在聊天界面中使用该模型进行对话
+
+ ### 步骤四:启用本地服务
+
+ - 如果你希望通过其它程序使用该模型,需要启动一个本地 API 服务,通过 `Developer` 面板或软件菜单启动服务,LM Studio 服务默认启动在本机的 `1234` 端口
+
+
+
+ - 本地服务启动后,你还需要在服务设置中开启 `CORS(跨域资源共享)`选项,这样才能在其它程序中使用该模型
+
+
+
+ ### 步骤五:在 LobeChat 中使用 LM Studio
+
+ - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+ - 在供应商列表中找到 `LM Studio` 的设置项
+
+
+
+ - 打开 LM Studio 服务商并填入 API 服务地址
+
+
+ 如果你的 LM Studio 运行在本地,请确保打开`客户端请求模式`
+
+
+ - 在下方的模型列表中添加你运行的模型
+ - 为你的助手选择一个火山引擎模型即可开始对话
+
+
+
+
+至此你已经可以在 LobeChat 中使用 LM Studio 运行的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/minimax.mdx b/DigitalHumanWeb/docs/usage/providers/minimax.mdx
index 5841e5d..1d16529 100644
--- a/DigitalHumanWeb/docs/usage/providers/minimax.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/minimax.mdx
@@ -13,75 +13,49 @@ tags:
# Using Minimax in LobeChat
-
+
[MiniMax](https://www.minimaxi.com/) is a general artificial intelligence technology company founded in 2021, dedicated to co-creating intelligence with users. MiniMax has independently developed universal large models of different modalities, including trillion-parameter MoE text large models, speech large models, and image large models. They have also launched applications like Hai Luo AI.
This document will guide you on how to use Minimax in LobeChat:
+ ### Step 1: Obtain MiniMax API Key
-### Step 1: Obtain MiniMax API Key
+ - Register and log in to the [MiniMax Open Platform](https://www.minimaxi.com/platform)
+ - In `Account Management`, locate the `API Key` menu and create a new key
-- Register and log in to the [MiniMax Open Platform](https://www.minimaxi.com/platform)
-- In `Account Management`, locate the `API Key` menu and create a new key
+
-
+ - Enter a name for the API key and create it
-- Enter a name for the API key and create it
+
-
+ - Copy the API key from the pop-up dialog box and save it securely
-- Copy the API key from the pop-up dialog box and save it securely
+
-
+
+ Please store the key securely as it will only appear once. If you accidentally lose it, you will
+ need to create a new key.
+
-
- Please store the key securely as it will only appear once. If you accidentally lose it, you will
- need to create a new key.
-
+ ### Step 2: Configure MiniMax in LobeChat
-### Step 2: Configure MiniMax in LobeChat
+ - Go to the `Settings` interface of LobeChat
+ - Find the setting for `MiniMax` under `Language Model`
-- Go to the `Settings` interface of LobeChat
-- Find the setting for `MiniMax` under `Language Model`
+
-
+ - Open Minimax and enter the obtained API key
+ - Choose a MiniMax model for your AI assistant to start the conversation
-- Open Minimax and enter the obtained API key
-- Choose a MiniMax model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to MiniMax's relevant
- pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to MiniMax's relevant
+ pricing policies.
+
You can now use the models provided by MiniMax to have conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/minimax.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/minimax.zh-CN.mdx
index c612b6e..a45abd6 100644
--- a/DigitalHumanWeb/docs/usage/providers/minimax.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/minimax.zh-CN.mdx
@@ -12,73 +12,47 @@ tags:
# 在 LobeChat 中使用 Minimax
-
+
[MiniMax](https://www.minimaxi.com/) 是 2021 年成立的通用人工智能科技公司,致力于与用户共创智能。MiniMax 自主研发了不同模态的通用大模型,其中包括万亿参数的 MoE 文本大模型、语音大模型以及图像大模型。并推出了海螺 AI 等应用。
本文档将指导你如何在 LobeChat 中使用 Minimax:
+ ### 步骤一:获取 MiniMax API 密钥
-### 步骤一:获取 MiniMax API 密钥
+ - 注册并登录 [MiniMax 开放平台](https://www.minimaxi.com/platform)
+ - 在 `账户管理` 中找到 `接口密钥` 菜单,并创建新的密钥
-- 注册并登录 [MiniMax 开放平台](https://www.minimaxi.com/platform)
-- 在 `账户管理` 中找到 `接口密钥` 菜单,并创建新的密钥
+
-
+ - 填写一个 API 密钥的名称并创建
-- 填写一个 API 密钥的名称并创建
+
-
+ - 在弹出的对话框中复制 API 密钥,并妥善保存
-- 在弹出的对话框中复制 API 密钥,并妥善保存
+
-
+
+ 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新密钥。
+
-
- 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新密钥。
-
+ ### 步骤二:在 LobeChat 中配置 MiniMax
-### 步骤二:在LobeChat 中配置 MiniMax
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`MiniMax`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`MiniMax`的设置项
+
-
+ - 打开 Minimax 并填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 MiniMax 的模型即可开始对话
-- 打开 Minimax 并填入获得的 API 密钥
-- 为你的 AI 助手选择一个 MiniMax 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 MiniMax 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 MiniMax 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 MiniMax 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/mistral.mdx b/DigitalHumanWeb/docs/usage/providers/mistral.mdx
index 11dc8d5..7ad7d96 100644
--- a/DigitalHumanWeb/docs/usage/providers/mistral.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/mistral.mdx
@@ -12,58 +12,40 @@ tags:
# Using Mistral AI in LobeChat
-
+
The Mistral AI API is now available for everyone to use. This document will guide you on how to use [Mistral AI](https://mistral.ai/) in LobeChat:
+ ### Step 1: Obtain Mistral AI API Key
-### Step 1: Obtain Mistral AI API Key
+ - Create a [Mistral AI](https://mistral.ai/) account
+ - Obtain your [API key](https://console.mistral.ai/user/api-keys/)
-- Create a [Mistral AI](https://mistral.ai/) account
-- Obtain your [API key](https://console.mistral.ai/user/api-keys/)
+
-
+ ### Step 2: Configure Mistral AI in LobeChat
-### Step 2: Configure Mistral AI in LobeChat
+ - Go to the `Settings` interface in LobeChat
+ - Find the setting for `Mistral AI` under `Language Model`
-- Go to the `Settings` interface in LobeChat
-- Find the setting for `Mistral AI` under `Language Model`
+
-
+
+ If you are using mistral.ai, your account must have a valid subscription for the API key to work
+ properly. Newly created API keys may take 2-3 minutes to become active. If the "Test" button
+ fails, please retry after 2-3 minutes.
+
-
- If you are using mistral.ai, your account must have a valid subscription for the API key to work
- properly. Newly created API keys may take 2-3 minutes to become active. If the "Test" button
- fails, please retry after 2-3 minutes.
-
+ - Enter the obtained API key
+ - Choose a Mistral AI model for your AI assistant to start the conversation
-- Enter the obtained API key
-- Choose a Mistral AI model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Mistral AI's relevant
- pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Mistral AI's relevant
+ pricing policies.
+
You can now engage in conversations using the models provided by Mistral AI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/mistral.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/mistral.zh-CN.mdx
index 7b69167..7670ae8 100644
--- a/DigitalHumanWeb/docs/usage/providers/mistral.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/mistral.zh-CN.mdx
@@ -9,56 +9,38 @@ tags:
# 在 LobeChat 中使用 Mistral AI
-
+
-Mistral AI API 现在可供所有人使用, 本文档将指导你如何在 LobeChat 中使用 [Mistral AI](https://mistral.ai/):
+Mistral AI API 现在可供所有人使用,本文档将指导你如何在 LobeChat 中使用 [Mistral AI](https://mistral.ai/):
+ ### 步骤一:获取 Mistral AI API 密钥
-### 步骤一:获取 Mistral AI API 密钥
+ - 创建一个 [Mistral AI](https://mistral.ai/) 帐户
+ - 获取您的 [API 密钥](https://console.mistral.ai/user/api-keys/)
-- 创建一个 [Mistral AI](https://mistral.ai/) 帐户
-- 获取您的 [API 密钥](https://console.mistral.ai/user/api-keys/)
+
-
+ ### 步骤二:在 LobeChat 中配置 Mistral AI
-### 步骤二:在 LobeChat 中配置 Mistral AI
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`Mistral AI`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`Mistral AI`的设置项
+
-
+
+ 如果您使用的是 mistral.ai,则您的帐户必须具有有效的订阅才能使 API 密钥正常工作。新创建的 API
+ 密钥需要 2-3 分钟才能开始工作。如果单击 “测试” 按钮但失败,请在 2-3 分钟后重试。
+
-
- 如果您使用的是 mistral.ai,则您的帐户必须具有有效的订阅才能使 API 密钥正常工作。新创建的 API
- 密钥需要 2-3 分钟才能开始工作。如果单击“测试”按钮但失败,请在 2-3 分钟后重试。
-
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Mistral AI 的模型即可开始对话
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个 Mistral AI 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Mistral AI 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Mistral AI 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Mistral AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/moonshot.mdx b/DigitalHumanWeb/docs/usage/providers/moonshot.mdx
index 1e57d7a..047f24a 100644
--- a/DigitalHumanWeb/docs/usage/providers/moonshot.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/moonshot.mdx
@@ -12,57 +12,39 @@ tags:
# Using Moonshot AI in LobeChat
-
+
The Moonshot AI API is now available for everyone to use. This document will guide you on how to use [Moonshot AI](https://www.moonshot.cn/) in LobeChat:
+ ### Step 1: Get Moonshot AI API Key
-### Step 1: Get Moonshot AI API Key
+ - Apply for your [API key](https://platform.moonshot.cn/console/api-keys)
-- Apply for your [API key](https://platform.moonshot.cn/console/api-keys)
+
-
+ ### Step 2: Configure Moonshot AI in LobeChat
-### Step 2: Configure Moonshot AI in LobeChat
+ - Visit the `Settings` interface in LobeChat
+ - Find the setting for `Moonshot AI` under `Language Models`
-- Visit the `Settings` interface in LobeChat
-- Find the setting for `Moonshot AI` under `Language Models`
+
-
+
+ If you are using mistral.ai, your account must have a valid subscription for the API key to work
+ properly. Newly created API keys may take 2-3 minutes to become active. If the "Test" button
+ fails, please retry after 2-3 minutes.
+
-
- If you are using mistral.ai, your account must have a valid subscription for the API key to work
- properly. Newly created API keys may take 2-3 minutes to become active. If the "Test" button
- fails, please retry after 2-3 minutes.
-
+ - Enter the API key you obtained
+ - Choose a Moonshot AI model for your AI assistant to start the conversation
-- Enter the API key you obtained
-- Choose a Moonshot AI model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider according to Moonshot AI's related
- pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider according to Moonshot AI's related
+ pricing policies.
+
You can now engage in conversations using the models provided by Moonshot AI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/moonshot.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/moonshot.zh-CN.mdx
index c2a416e..2751ad4 100644
--- a/DigitalHumanWeb/docs/usage/providers/moonshot.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/moonshot.zh-CN.mdx
@@ -9,55 +9,37 @@ tags:
# 在 LobeChat 中使用 Moonshot AI
-
+
-Moonshot AI API 现在可供所有人使用, 本文档将指导你如何在 LobeChat 中使用 [Moonshot AI](https://www.moonshot.cn/):
+Moonshot AI API 现在可供所有人使用,本文档将指导你如何在 LobeChat 中使用 [Moonshot AI](https://www.moonshot.cn/):
+ ### 步骤一:获取 Moonshot AI API 密钥
-### 步骤一:获取 Moonshot AI API 密钥
+ - 申请您的 [API 密钥](https://platform.moonshot.cn/console/api-keys)
-- 申请您的 [API 密钥](https://platform.moonshot.cn/console/api-keys)
+
-
+ ### 步骤二:在 LobeChat 中配置 Moonshot AI
-### 步骤二:在 LobeChat 中配置 Moonshot AI
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`Moonshot AI`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`Moonshot AI`的设置项
+
-
+
+ 如果您使用的是 mistral.ai,则您的帐户必须具有有效的订阅才能使 API 密钥正常工作。新创建的 API
+ 密钥需要 2-3 分钟才能开始工作。如果单击 “测试” 按钮但失败,请在 2-3 分钟后重试。
+
-
- 如果您使用的是 mistral.ai,则您的帐户必须具有有效的订阅才能使 API 密钥正常工作。新创建的 API
- 密钥需要 2-3 分钟才能开始工作。如果单击“测试”按钮但失败,请在 2-3 分钟后重试。
-
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Moonshot AI 的模型即可开始对话
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个 Moonshot AI 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Moonshot AI 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Moonshot AI 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Moonshot AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/novita.mdx b/DigitalHumanWeb/docs/usage/providers/novita.mdx
index 4776b4b..31f4c25 100644
--- a/DigitalHumanWeb/docs/usage/providers/novita.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/novita.mdx
@@ -15,66 +15,43 @@ tags:
# Using Novita AI in LobeChat
-
+
[Novita AI](https://novita.ai/) is an AI API platform that provides a variety of LLM and image generation APIs, supporting Llama3 (8B, 70B), Mistral, and many other cutting-edge models. We offer a variety of censored and uncensored models to meet your different needs.
This document will guide you on how to integrate Novita AI in LobeChat:
+ ### Step 1: Register and Log in to Novita AI
-### Step 1: Register and Log in to Novita AI
+ - Visit [Novita.ai](https://novita.ai/) and create an account
+ - You can log in with your Google or Github account
+ - Upon registration, Novita AI will provide a $0.5 credit.
-- Visit [Novita.ai](https://novita.ai/) and create an account
-- You can log in with your Google or Github account
-- Upon registration, Novita AI will provide a $0.5 credit.
+
-
+ ### Step 2: Obtain the API Key
-### Step 2: Obtain the API Key
+ - Visit Novita AI's [key management page](https://novita.ai/dashboard/key), create and copy an API Key.
-- Visit Novita AI's [key management page](https://novita.ai/dashboard/key), create and copy an API Key.
+
-
+ ### Step 3: Configure Novita AI in LobeChat
-### Step 3: Configure Novita AI in LobeChat
+ - Visit the `Settings` interface in LobeChat
+ - Find the setting for `novita.ai` under `Language Model`
-- Visit the `Settings` interface in LobeChat
-- Find the setting for `novita.ai` under `Language Model`
+
-
+ - Open novita.ai and enter the obtained API key
+ - Choose a Novita AI model for your assistant to start the conversation
-- Open novita.ai and enter the obtained API key
-- Choose a Novita AI model for your assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Novita AI's pricing
- policy.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Novita AI's pricing
+ policy.
+
You can now engage in conversations using the models provided by Novita AI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/novita.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/novita.zh-CN.mdx
index 501496b..fc45766 100644
--- a/DigitalHumanWeb/docs/usage/providers/novita.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/novita.zh-CN.mdx
@@ -14,65 +14,42 @@ tags:
# 在 LobeChat 中使用 Novita AI
-
+
[Novita AI](https://novita.ai/) 是一个 AI API 平台,它提供多种大语言模型与 AI 图像生成的 API 服务。支持 Llama3 (8B, 70B),Mistral 和其他最新的模型。
本文档将指导你如何在 LobeChat 中使用 Novita AI:
+ ### 步骤一:注册 Novita AI 账号并登录
-### 步骤一:注册 Novita AI 账号并登录
+ - 访问 [Novita.ai](https://novita.ai/) 并创建账号
+ - 你可以使用 Google 或者 Github 账号登录
+ - 注册后,Novita AI 会赠送 0.5 美元的使用额度
-- 访问 [Novita.ai](https://novita.ai/) 并创建账号
-- 你可以使用 Google 或者 Github 账号登录
-- 注册后,Novita AI 会赠送 0.5 美元的使用额度
+
-
+ ### 步骤二:创建 API 密钥
-### 步骤二:创建 API 密钥
+ - 访问 Novita AI 的 [密钥管理页面](https://novita.ai/dashboard/key) ,创建并且复制一个 API 密钥.
-- 访问 Novita AI 的 [密钥管理页面](https://novita.ai/dashboard/key) ,创建并且复制一个 API 密钥.
+
-
+ ### 步骤三:在 LobeChat 中配置 Novita AI
-### 步骤三:在 LobeChat 中配置 Novita AI
+ - 访问 LobeChat 的 `设置` 界面
+ - 在 `语言模型` 下找到 `novita.ai` 的设置项
+ - 打开 novita.ai 并填入获得的 API 密钥
-- 访问 LobeChat 的 `设置` 界面
-- 在 `语言模型` 下找到 `novita.ai` 的设置项
-- 打开 novita.ai 并填入获得的 API 密钥
+
-
+ - 为你的助手选择一个 Novita AI 模型即可开始对话
-- 为你的助手选择一个 Novita AI 模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Novita AI 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Novita AI 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Novita AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/nvidia.mdx b/DigitalHumanWeb/docs/usage/providers/nvidia.mdx
new file mode 100644
index 0000000..49667c5
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/nvidia.mdx
@@ -0,0 +1,55 @@
+---
+title: Using Nvidia NIM API Key in LobeChat
+description: Learn how to configure and use Nvidia NIM AI models in LobeChat, obtain an API key, and start a conversation.
+tags:
+ - LobeChat
+ - Nvidia NIM
+ - API Key
+ - Web UI
+---
+
+# Using Nvidia NIM in LobeChat
+
+
+
+[NVIDIA NIM](https://developer.nvidia.com/nim) is part of NVIDIA AI Enterprise and is designed to accelerate the deployment of generative AI applications through microservices. It provides a set of easy-to-use inference microservices that can run on any cloud, data center, or workstation, supporting NVIDIA GPU acceleration.
+
+This document will guide you on how to access and use AI models provided by Nvidia NIM in LobeChat:
+
+
+ ### Step 1: Obtain Nvidia NIM API Key
+
+ - First, visit the [Nvidia NIM console](https://build.nvidia.com/explore/discover) and complete the registration and login.
+ - On the `Models` page, select the model you need, such as Deepseek-R1.
+
+
+
+ - On the model details page, click "Build with this NIM".
+ - In the pop-up dialog, click the `Generate API Key` button.
+
+
+
+ - Copy and save the created API Key.
+
+
+ Please store the key securely as it will only appear once. If you accidentally lose it, you will need to create a new key.
+
+
+ ### Step 2: Configure Nvidia NIM in LobeChat
+
+ - Visit the `Application Settings` -> `AI Service Provider` interface in LobeChat.
+ - Find the settings item for `Nvidia NIM` in the list of providers.
+
+
+
+ - Enable the Nvidia NIM service provider and fill in the obtained API key.
+ - Select an Nvidia NIM model for your assistant and start the conversation.
+
+
+
+
+ You may need to pay the API service provider during use, please refer to Nvidia NIM's related fee policies.
+
+
+
+Now you can use the models provided by Nvidia NIM to have conversations in LobeChat.
\ No newline at end of file
diff --git a/DigitalHumanWeb/docs/usage/providers/nvidia.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/nvidia.zh-CN.mdx
new file mode 100644
index 0000000..ae6ab12
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/nvidia.zh-CN.mdx
@@ -0,0 +1,55 @@
+---
+title: 在 LobeChat 中使用 Nvidia NIM API Key
+description: 学习如何在 LobeChat 中配置和使用 Nvidia NIM AI 模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - Nvidia NIM
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Nvidia NIM
+
+
+
+[NVIDIA NIM](https://developer.nvidia.com/nim) 是 NVIDIA AI Enterprise 的一部分,旨在通过微服务加速生成式 AI 应用的部署。它提供了一组易于使用的推理微服务,可以在任何云、数据中心或工作站上运行,支持 NVIDIA GPU 加速。
+
+本文档将指导你如何在 LobeChat 中接入并使用 Nvidia NIM 提供的 AI 模型:
+
+
+ ### 步骤一:获取 Nvidia NIM API 密钥
+
+ - 首先,访问[Nvidia NIM 控制台](https://build.nvidia.com/explore/discover)并完成注册登录
+ - 在 `Models` 页面选择你需要的模型,例如 Deepseek-R1
+
+
+
+ - 在模型详情页点击`使用此NIM构建`
+ - 在弹出的对话框中点击`生成 API Key` 按钮
+
+
+
+ - 复制并保存创建好的 API Key
+
+
+ 请安全地存储密钥,因为它只会出现一次。如果你意外丢失它,您将需要创建一个新密钥。
+
+
+ ### 步骤二:在 LobeChat 中配置 Nvidia NIM
+
+ - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+ - 在供应商列表中找到 ` Nvidia NIM` 的设置项
+
+
+
+ - 打开 Nvidia NIM 服务商并填入获取的 API 密钥
+ - 为你的助手选择一个 Nvidia NIM 模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Nvidia NIM 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Nvidia NIM 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/ollama.mdx b/DigitalHumanWeb/docs/usage/providers/ollama.mdx
index 2d7f03d..f066fa7 100644
--- a/DigitalHumanWeb/docs/usage/providers/ollama.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/ollama.mdx
@@ -13,151 +13,130 @@ tags:
# Using Ollama in LobeChat
-
+
Ollama is a powerful framework for running large language models (LLMs) locally, supporting various language models including Llama 2, Mistral, and more. Now, LobeChat supports integration with Ollama, meaning you can easily enhance your application by using the language models provided by Ollama in LobeChat.
This document will guide you on how to use Ollama in LobeChat:
-
+
## Using Ollama on macOS
+ ### Local Installation of Ollama
-### Local Installation of Ollama
+ [Download Ollama for macOS](https://ollama.com/download?utm_source=lobehub\&utm_medium=docs\&utm_campaign=download-macos) and unzip/install it.
-[Download Ollama for macOS](https://ollama.com/download?utm_source=lobehub&utm_medium=docs&utm_campaign=download-macos) and unzip/install it.
+ ### Configure Ollama for Cross-Origin Access
-### Configure Ollama for Cross-Origin Access
+ Due to Ollama's default configuration, which restricts access to local only, additional environment variable setting `OLLAMA_ORIGINS` is required for cross-origin access and port listening. Use `launchctl` to set the environment variable:
-Due to Ollama's default configuration, which restricts access to local only, additional environment variable setting `OLLAMA_ORIGINS` is required for cross-origin access and port listening. Use `launchctl` to set the environment variable:
+ ```bash
+ launchctl setenv OLLAMA_ORIGINS "*"
+ ```
-```bash
-launchctl setenv OLLAMA_ORIGINS "*"
-```
-
-After setting up, restart the Ollama application.
+ After setting up, restart the Ollama application.
-### Conversing with Local Large Models in LobeChat
+ ### Conversing with Local Large Models in LobeChat
-Now, you can start conversing with the local LLM in LobeChat.
-
-
+ Now, you can start conversing with the local LLM in LobeChat.
+
## Using Ollama on Windows
+ ### Local Installation of Ollama
-### Local Installation of Ollama
-
-[Download Ollama for Windows](https://ollama.com/download?utm_source=lobehub&utm_medium=docs&utm_campaign=download-windows) and install it.
-
-### Configure Ollama for Cross-Origin Access
+ [Download Ollama for Windows](https://ollama.com/download?utm_source=lobehub\&utm_medium=docs\&utm_campaign=download-windows) and install it.
-Since Ollama's default configuration allows local access only, additional environment variable setting `OLLAMA_ORIGINS` is needed for cross-origin access and port listening.
+ ### Configure Ollama for Cross-Origin Access
-On Windows, Ollama inherits your user and system environment variables.
+ Since Ollama's default configuration allows local access only, additional environment variable setting `OLLAMA_ORIGINS` is needed for cross-origin access and port listening.
-1. First, exit the Ollama program by clicking on it in the Windows taskbar.
-2. Edit system environment variables from the Control Panel.
-3. Edit or create the Ollama environment variable `OLLAMA_ORIGINS` for your user account, setting the value to `*`.
-4. Click `OK/Apply` to save and restart the system.
-5. Run `Ollama` again.
+ On Windows, Ollama inherits your user and system environment variables.
-### Conversing with Local Large Models in LobeChat
+ 1. First, exit the Ollama program by clicking on it in the Windows taskbar.
+ 2. Edit system environment variables from the Control Panel.
+ 3. Edit or create the Ollama environment variable `OLLAMA_ORIGINS` for your user account, setting the value to `*`.
+ 4. Click `OK/Apply` to save and restart the system.
+ 5. Run `Ollama` again.
-Now, you can start conversing with the local LLM in LobeChat.
+ ### Conversing with Local Large Models in LobeChat
+ Now, you can start conversing with the local LLM in LobeChat.
## Using Ollama on Linux
+ ### Local Installation of Ollama
-### Local Installation of Ollama
+ Install using the following command:
-Install using the following command:
+ ```bash
+ curl -fsSL https://ollama.com/install.sh | sh
+ ```
-```bash
-curl -fsSL https://ollama.com/install.sh | sh
-```
-
-Alternatively, you can refer to the [Linux manual installation guide](https://github.com/ollama/ollama/blob/main/docs/linux.md).
+ Alternatively, you can refer to the [Linux manual installation guide](https://github.com/ollama/ollama/blob/main/docs/linux.md).
-### Configure Ollama for Cross-Origin Access
+ ### Configure Ollama for Cross-Origin Access
-Due to Ollama's default configuration, which allows local access only, additional environment variable setting `OLLAMA_ORIGINS` is required for cross-origin access and port listening. If Ollama runs as a systemd service, use `systemctl` to set the environment variable:
+ Due to Ollama's default configuration, which allows local access only, additional environment variable setting `OLLAMA_ORIGINS` is required for cross-origin access and port listening. If Ollama runs as a systemd service, use `systemctl` to set the environment variable:
-1. Edit the systemd service by calling `sudo systemctl edit ollama.service`:
-
-```bash
-sudo systemctl edit ollama.service
-```
+ 1. Edit the systemd service by calling `sudo systemctl edit ollama.service`:
-2. Add `Environment` under `[Service]` for each environment variable:
+ ```bash
+ sudo systemctl edit ollama.service
+ ```
-```bash
-[Service]
-Environment="OLLAMA_HOST=0.0.0.0"
-Environment="OLLAMA_ORIGINS=*"
-```
+ 2. Add `Environment` under `[Service]` for each environment variable:
-3. Save and exit.
-4. Reload `systemd` and restart Ollama:
+ ```bash
+ [Service]
+ Environment="OLLAMA_HOST=0.0.0.0"
+ Environment="OLLAMA_ORIGINS=*"
+ ```
-```bash
-sudo systemctl daemon-reload
-sudo systemctl restart ollama
-```
+ 3. Save and exit.
+ 4. Reload `systemd` and restart Ollama:
-### Conversing with Local Large Models in LobeChat
+ ```bash
+ sudo systemctl daemon-reload
+ sudo systemctl restart ollama
+ ```
-Now, you can start conversing with the local LLM in LobeChat.
+ ### Conversing with Local Large Models in LobeChat
+ Now, you can start conversing with the local LLM in LobeChat.
## Deploying Ollama using Docker
+ ### Pulling Ollama Image
-### Pulling Ollama Image
+ If you prefer using Docker, Ollama provides an official Docker image that you can pull using the following command:
-If you prefer using Docker, Ollama provides an official Docker image that you can pull using the following command:
+ ```bash
+ docker pull ollama/ollama
+ ```
-```bash
-docker pull ollama/ollama
-```
-
-### Configure Ollama for Cross-Origin Access
-
-Since Ollama's default configuration allows local access only, additional environment variable setting `OLLAMA_ORIGINS` is needed for cross-origin access and port listening.
+ ### Configure Ollama for Cross-Origin Access
-If Ollama runs as a Docker container, you can add the environment variable to the `docker run` command.
+ Since Ollama's default configuration allows local access only, additional environment variable setting `OLLAMA_ORIGINS` is needed for cross-origin access and port listening.
-```bash
-docker run -d --gpus=all -v ollama:/root/.ollama -e OLLAMA_ORIGINS="*" -p 11434:11434 --name ollama ollama/ollama
-```
+ If Ollama runs as a Docker container, you can add the environment variable to the `docker run` command.
-### Conversing with Local Large Models in LobeChat
+ ```bash
+ docker run -d --gpus=all -v ollama:/root/.ollama -e OLLAMA_ORIGINS="*" -p 11434:11434 --name ollama ollama/ollama
+ ```
-Now, you can start conversing with the local LLM in LobeChat.
+ ### Conversing with Local Large Models in LobeChat
+ Now, you can start conversing with the local LLM in LobeChat.
## Installing Ollama Models
@@ -168,11 +147,7 @@ Ollama supports various models, which you can view in the [Ollama Library](https
In LobeChat, we have enabled some common large language models by default, such as llama3, Gemma, Mistral, etc. When you select a model for conversation, we will prompt you to download that model.
-
+
Once downloaded, you can start conversing.
@@ -184,20 +159,13 @@ Alternatively, you can install models by executing the following command in the
ollama pull llama3
```
-
+
## Custom Configuration
You can find Ollama's configuration options in `Settings` -> `Language Models`, where you can configure Ollama's proxy, model names, etc.
-
+
Visit [Integrating with Ollama](/docs/self-hosting/examples/ollama) to learn how to deploy
diff --git a/DigitalHumanWeb/docs/usage/providers/ollama.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/ollama.zh-CN.mdx
index 2b899b4..98ac56a 100644
--- a/DigitalHumanWeb/docs/usage/providers/ollama.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/ollama.zh-CN.mdx
@@ -11,151 +11,130 @@ tags:
# 在 LobeChat 中使用 Ollama
-
+
Ollama 是一款强大的本地运行大型语言模型(LLM)的框架,支持多种语言模型,包括 Llama 2, Mistral 等。现在,LobeChat 已经支持与 Ollama 的集成,这意味着你可以在 LobeChat 中轻松使用 Ollama 提供的语言模型来增强你的应用。
本文档将指导你如何在 LobeChat 中使用 Ollama:
-
+
## 在 macOS 下使用 Ollama
+ ### 本地安装 Ollama
-### 本地安装 Ollama
+ [下载 Ollama for macOS](https://ollama.com/download?utm_source=lobehub\&utm_medium=docs\&utm_campaign=download-macos) 并解压、安装。
-[下载 Ollama for macOS](https://ollama.com/download?utm_source=lobehub&utm_medium=docs&utm_campaign=download-macos) 并解压、安装。
+ ### 配置 Ollama 允许跨域访问
-### 配置 Ollama 允许跨域访问
+ 由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。使用 `launchctl` 设置环境变量:
-由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。使用 `launchctl` 设置环境变量:
+ ```bash
+ launchctl setenv OLLAMA_ORIGINS "*"
+ ```
-```bash
-launchctl setenv OLLAMA_ORIGINS "*"
-```
-
-完成设置后,需要重启 Ollama 应用程序。
+ 完成设置后,需要重启 Ollama 应用程序。
-### 在 LobeChat 中与本地大模型对话
+ ### 在 LobeChat 中与本地大模型对话
-接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
-
-
+ 接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
+
## 在 windows 下使用 Ollama
+ ### 本地安装 Ollama
-### 本地安装 Ollama
-
-[下载 Ollama for Windows](https://ollama.com/download?utm_source=lobehub&utm_medium=docs&utm_campaign=download-windows) 并安装。
-
-### 配置 Ollama 允许跨域访问
+ [下载 Ollama for Windows](https://ollama.com/download?utm_source=lobehub\&utm_medium=docs\&utm_campaign=download-windows) 并安装。
-由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。
+ ### 配置 Ollama 允许跨域访问
-在 Windows 上,Ollama 继承了您的用户和系统环境变量。
+ 由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。
-1. 首先通过 Windows 任务栏点击 Ollama 退出程序。
-2. 从控制面板编辑系统环境变量。
-3. 为您的用户账户编辑或新建 Ollama 的环境变量 `OLLAMA_ORIGINS`,值设为 `*` 。
-4. 点击`OK/应用`保存后重启系统。
-5. 重新运行`Ollama`。
+ 在 Windows 上,Ollama 继承了您的用户和系统环境变量。
-### 在 LobeChat 中与本地大模型对话
+ 1. 首先通过 Windows 任务栏点击 Ollama 退出程序。
+ 2. 从控制面板编辑系统环境变量。
+ 3. 为您的用户账户编辑或新建 Ollama 的环境变量 `OLLAMA_ORIGINS`,值设为 `*` 。
+ 4. 点击`OK/应用`保存后重启系统。
+ 5. 重新运行`Ollama`。
-接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
+ ### 在 LobeChat 中与本地大模型对话
+ 接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
## 在 linux 下使用 Ollama
+ ### 本地安装 Ollama
-### 本地安装 Ollama
+ 通过以下命令安装:
-通过以下命令安装:
+ ```bash
+ curl -fsSL https://ollama.com/install.sh | sh
+ ```
-```bash
-curl -fsSL https://ollama.com/install.sh | sh
-```
-
-或者,你也可以参考 [Linux 手动安装指南](https://github.com/ollama/ollama/blob/main/docs/linux.md)。
+ 或者,你也可以参考 [Linux 手动安装指南](https://github.com/ollama/ollama/blob/main/docs/linux.md)。
-### 配置 Ollama 允许跨域访问
+ ### 配置 Ollama 允许跨域访问
-由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。如果 Ollama 作为 systemd 服务运行,应该使用`systemctl`设置环境变量:
+ 由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。如果 Ollama 作为 systemd 服务运行,应该使用`systemctl`设置环境变量:
-1. 通过调用`sudo systemctl edit ollama.service`编辑 systemd 服务。
-
-```bash
-sudo systemctl edit ollama.service
-```
+ 1. 通过调用`sudo systemctl edit ollama.service`编辑 systemd 服务。
-2. 对于每个环境变量,在`[Service]`部分下添加`Environment`:
+ ```bash
+ sudo systemctl edit ollama.service
+ ```
-```bash
-[Service]
-Environment="OLLAMA_HOST=0.0.0.0"
-Environment="OLLAMA_ORIGINS=*"
-```
+ 2. 对于每个环境变量,在`[Service]`部分下添加`Environment`:
-3. 保存并退出。
-4. 重载 `systemd` 并重启 Ollama:
+ ```bash
+ [Service]
+ Environment="OLLAMA_HOST=0.0.0.0"
+ Environment="OLLAMA_ORIGINS=*"
+ ```
-```bash
-sudo systemctl daemon-reload
-sudo systemctl restart ollama
-```
+ 3. 保存并退出。
+ 4. 重载 `systemd` 并重启 Ollama:
-### 在 LobeChat 中与本地大模型对话
+ ```bash
+ sudo systemctl daemon-reload
+ sudo systemctl restart ollama
+ ```
-接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
+ ### 在 LobeChat 中与本地大模型对话
+ 接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
## 使用 docker 部署使用 Ollama
+ ### 拉取 Ollama 镜像
-### 拉取 Ollama 镜像
+ 如果你更倾向于使用 Docker,Ollama 也提供了官方 Docker 镜像,你可以通过以下命令拉取:
-如果你更倾向于使用 Docker,Ollama 也提供了官方 Docker 镜像,你可以通过以下命令拉取:
+ ```bash
+ docker pull ollama/ollama
+ ```
-```bash
-docker pull ollama/ollama
-```
-
-### 配置 Ollama 允许跨域访问
-
-由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。
+ ### 配置 Ollama 允许跨域访问
-如果 Ollama 作为 Docker 容器运行,你可以将环境变量添加到 `docker run` 命令中。
+ 由于 Ollama 的默认参数配置,启动时设置了仅本地访问,所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS`。
-```bash
-docker run -d --gpus=all -v ollama:/root/.ollama -e OLLAMA_ORIGINS="*" -p 11434:11434 --name ollama ollama/ollama
-```
+ 如果 Ollama 作为 Docker 容器运行,你可以将环境变量添加到 `docker run` 命令中。
-### 在 LobeChat 中与本地大模型对话
+ ```bash
+ docker run -d --gpus=all -v ollama:/root/.ollama -e OLLAMA_ORIGINS="*" -p 11434:11434 --name ollama ollama/ollama
+ ```
-接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
+ ### 在 LobeChat 中与本地大模型对话
+ 接下来,你就可以使用 LobeChat 与本地 LLM 对话了。
## 安装 Ollama 模型
@@ -166,11 +145,7 @@ Ollama 支持多种模型,你可以在 [Ollama Library](https://ollama.com/lib
在 LobeChat 中,我们默认开启了一些常用的大语言模型,例如 llama3、 Gemma 、 Mistral 等。当你选中模型进行对话时,我们会提示你需要下载该模型。
-
+
下载完成后即可开始对话。
@@ -182,20 +157,13 @@ Ollama 支持多种模型,你可以在 [Ollama Library](https://ollama.com/lib
ollama pull llama3
```
-
+
## 自定义配置
你可以在 `设置` -> `语言模型` 中找到 Ollama 的配置选项,你可以在这里配置 Ollama 的代理、模型名称等。
-
+
你可以前往 [与 Ollama 集成](/zh/docs/self-hosting/examples/ollama) 了解如何部署 LobeChat
diff --git a/DigitalHumanWeb/docs/usage/providers/ollama/gemma.mdx b/DigitalHumanWeb/docs/usage/providers/ollama/gemma.mdx
index 80997f1..f7f9680 100644
--- a/DigitalHumanWeb/docs/usage/providers/ollama/gemma.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/ollama/gemma.mdx
@@ -14,11 +14,7 @@ tags:
# Using Google Gemma Model
-
+
[Gemma](https://blog.google/technology/developers/gemma-open-models/) is an open-source large language model (LLM) from Google, designed to provide a more general and flexible model for various natural language processing tasks. Now, with the integration of LobeChat and [Ollama](https://ollama.com/), you can easily use Google Gemma in LobeChat.
@@ -27,42 +23,29 @@ This document will guide you on how to use Google Gemma in LobeChat:
### Install Ollama locally
-First, you need to install Ollama. For the installation process, please refer to the [Ollama usage documentation](/docs/usage/providers/ollama).
+ First, you need to install Ollama. For the installation process, please refer to the [Ollama usage documentation](/docs/usage/providers/ollama).
-### Pull Google Gemma model to local using Ollama
+ ### Pull Google Gemma model to local using Ollama
-After installing Ollama, you can install the Google Gemma model using the following command, using the 7b model as an example:
+ After installing Ollama, you can install the Google Gemma model using the following command, using the 7b model as an example:
-```bash
-ollama pull gemma
-```
+ ```bash
+ ollama pull gemma
+ ```
-
+
-### Select Gemma model
+ ### Select Gemma model
-In the session page, open the model panel and then select the Gemma model.
+ In the session page, open the model panel and then select the Gemma model.
-
+
If you do not see the Ollama provider in the model selection panel, please refer to [Integrating
with Ollama](/docs/self-hosting/examples/ollama) to learn how to enable the Ollama provider in
LobeChat.
-
-
+
Now, you can start conversing with the local Gemma model using LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/ollama/gemma.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/ollama/gemma.zh-CN.mdx
index 9ecc4ea..1d30432 100644
--- a/DigitalHumanWeb/docs/usage/providers/ollama/gemma.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/ollama/gemma.zh-CN.mdx
@@ -13,12 +13,7 @@ tags:
# 使用 Google Gemma 模型
-
+
[Gemma](https://blog.google/technology/developers/gemma-open-models/) 是 Google 开源的一款大语言模型(LLM),旨在提供一个更加通用、灵活的模型用于各种自然语言处理任务。现在,通过 LobeChat 与 [Ollama](https://ollama.com/) 的集成,你可以轻松地在 LobeChat 中使用 Google Gemma。
@@ -27,41 +22,28 @@ tags:
### 本地安装 Ollama
-首先,你需要安装 Ollama,安装过程请查阅 [Ollama 使用文件](/zh/docs/usage/providers/ollama)。
+ 首先,你需要安装 Ollama,安装过程请查阅 [Ollama 使用文件](/zh/docs/usage/providers/ollama)。
-### 用 Ollama 拉取 Google Gemma 模型到本地
+ ### 用 Ollama 拉取 Google Gemma 模型到本地
-在安装完成 Ollama 后,你可以通过以下命令安装 Google Gemma 模型,以 7b 模型为例:
+ 在安装完成 Ollama 后,你可以通过以下命令安装 Google Gemma 模型,以 7b 模型为例:
-```bash
-ollama pull gemma
-```
+ ```bash
+ ollama pull gemma
+ ```
-
+
-### 选择 Gemma 模型
+ ### 选择 Gemma 模型
-在会话页面中,选择模型面板打开,然后选择 Gemma 模型。
+ 在会话页面中,选择模型面板打开,然后选择 Gemma 模型。
-
+
如果你没有在模型选择面板中看到 Ollama 服务商,请查阅 [与 Ollama
集成](/zh/docs/self-hosting/examples/ollama) 了解如何在 LobeChat 中开启 Ollama 服务商。
-
-
+
接下来,你就可以使用 LobeChat 与本地 Gemma 模型对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/ollama/qwen.mdx b/DigitalHumanWeb/docs/usage/providers/ollama/qwen.mdx
index 243c02f..12df710 100644
--- a/DigitalHumanWeb/docs/usage/providers/ollama/qwen.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/ollama/qwen.mdx
@@ -11,11 +11,7 @@ tags:
# Using the Local Qwen Model
-
+
[Qwen](https://github.com/QwenLM/Qwen1.5) is a large language model (LLM) open-sourced by Alibaba Cloud. It is officially defined as a constantly evolving AI large model, and it achieves more accurate Chinese recognition capabilities through more training set content.
@@ -26,44 +22,33 @@ Now, through the integration of LobeChat and [Ollama](https://ollama.com/), you
## Local Installation of Ollama
-First, you need to install Ollama. For the installation process, please refer to the [Ollama Usage Document](/docs/usage/providers/ollama).
+ First, you need to install Ollama. For the installation process, please refer to the [Ollama Usage Document](/docs/usage/providers/ollama).
-## Pull the Qwen Model to Local with Ollama
+ ## Pull the Qwen Model to Local with Ollama
-After installing Ollama, you can install the Qwen model with the following command, taking the 14b model as an example:
+ After installing Ollama, you can install the Qwen model with the following command, taking the 14b model as an example:
-```bash
-ollama pull qwen:14b
-```
+ ```bash
+ ollama pull qwen:14b
+ ```
-
- The local version of Qwen provides different model sizes to choose from. Please refer to the
- [Qwen's Ollama integration page](https://ollama.com/library/qwen) to understand how to choose the
- model size.
-
+
+ The local version of Qwen provides different model sizes to choose from. Please refer to the
+ [Qwen's Ollama integration page](https://ollama.com/library/qwen) to understand how to choose the
+ model size.
+
-
+
-### Select the Qwen Model
+ ### Select the Qwen Model
-In the LobeChat conversation page, open the model selection panel, and then select the Qwen model.
+ In the LobeChat conversation page, open the model selection panel, and then select the Qwen model.
-
+
If you do not see the Ollama provider in the model selection panel, please refer to [Integration with Ollama](/docs/self-hosting/examples/ollama) to learn how to enable the Ollama provider in LobeChat.
-
-
+
Next, you can have a conversation with the local Qwen model in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/ollama/qwen.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/ollama/qwen.zh-CN.mdx
index db797cc..da13ad7 100644
--- a/DigitalHumanWeb/docs/usage/providers/ollama/qwen.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/ollama/qwen.zh-CN.mdx
@@ -11,11 +11,7 @@ tags:
# 使用本地通义千问 Qwen 模型
-
+
[通义千问](https://github.com/QwenLM/Qwen1.5) 是阿里云开源的一款大语言模型(LLM),官方定义是一个不断进化的 AI 大模型,并通过更多的训练集内容达到更精准的中文识别能力。
@@ -28,39 +24,28 @@ tags:
### 本地安装 Ollama
-首先,你需要安装 Ollama,安装过程请查阅 [Ollama 使用文件](/zh/docs/usage/providers/ollama)。
+ 首先,你需要安装 Ollama,安装过程请查阅 [Ollama 使用文件](/zh/docs/usage/providers/ollama)。
-### 用 Ollama 拉取 Qwen 模型到本地
+ ### 用 Ollama 拉取 Qwen 模型到本地
-在安装完成 Ollama 后,你可以通过以下命令安装 Qwen 模型,以 14b 模型为例:
+ 在安装完成 Ollama 后,你可以通过以下命令安装 Qwen 模型,以 14b 模型为例:
-```bash
-ollama pull qwen:14b
-```
+ ```bash
+ ollama pull qwen:14b
+ ```
-
+
-### 选择 Qwen 模型
+ ### 选择 Qwen 模型
-在会话页面中,选择模型面板打开,然后选择 Qwen 模型。
+ 在会话页面中,选择模型面板打开,然后选择 Qwen 模型。
-
+
如果你没有在模型选择面板中看到 Ollama 服务商,请查阅 [与 Ollama
集成](/zh/docs/self-hosting/examples/ollama) 了解如何在 LobeChat 中开启 Ollama 服务商。
-
-
+
接下来,你就可以使用 LobeChat 与本地 Qwen 模型对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/openai.mdx b/DigitalHumanWeb/docs/usage/providers/openai.mdx
index ae624bf..4d1775b 100644
--- a/DigitalHumanWeb/docs/usage/providers/openai.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/openai.mdx
@@ -14,81 +14,67 @@ tags:
# Using OpenAI in LobeChat
-
+
This document will guide you on how to use [OpenAI](https://openai.com/) in LobeChat:
+ ### Step 1: Obtain OpenAI API Key
-### Step 1: Obtain OpenAI API Key
+ - Register for an [OpenAI account](https://platform.openai.com/signup). You will need to register using an international phone number and a non-mainland email address.
-- Register for an [OpenAI account](https://platform.openai.com/signup). You will need to register using an international phone number and a non-mainland email address.
+ - After registration, go to the [API Keys](https://platform.openai.com/api-keys) page and click on `Create new secret key` to generate a new API Key.
-- After registration, go to the [API Keys](https://platform.openai.com/api-keys) page and click on `Create new secret key` to generate a new API Key.
+ - Open the creation window
-- Open the creation window
+
-
+ - Create API Key
-- Create API Key
+
-
+ - Retrieve API Key
-- Retrieve API Key
+
-
+
+ After registering, you generally have a free credit of $5, but it is only valid for three months.
+
-
- After registering, you generally have a free credit of $5, but it is only valid for three months.
-
+ ### Step 2: Configure OpenAI in LobeChat
-### Step 2: Configure OpenAI in LobeChat
+ - Visit the `Settings` page in LobeChat
+ - Find the setting for `OpenAI` under `Language Model`
-- Visit the `Settings` page in LobeChat
-- Find the setting for `OpenAI` under `Language Model`
+
-
+ - Enter the obtained API Key
+ - Choose an OpenAI model for your AI assistant to start the conversation
-- Enter the obtained API Key
-- Choose an OpenAI model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider. Please refer to OpenAI's relevant
- pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider. Please refer to OpenAI's relevant
+ pricing policies.
+
You can now engage in conversations using the models provided by OpenAI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/openai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/openai.zh-CN.mdx
index 390ec9e..44d7d72 100644
--- a/DigitalHumanWeb/docs/usage/providers/openai.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/openai.zh-CN.mdx
@@ -11,77 +11,64 @@ tags:
# 在 LobeChat 中使用 OpenAI
-
+
本文档将指导你如何在 LobeChat 中使用 [OpenAI](https://openai.com/):
+ ### 步骤一:获取 OpenAI API 密钥
-### 步骤一:获取 OpenAI API 密钥
+ - 注册一个 [OpenAI 账户](https://platform.openai.com/signup),你需要使用国际手机号、非大陆邮箱进行注册;
-- 注册一个 [OpenAI 账户](https://platform.openai.com/signup),你需要使用国际手机号、非大陆邮箱进行注册;
-- 注册完毕后,前往 [API Keys](https://platform.openai.com/api-keys) 页面,点击 `Create new secret key` 创建新的 API Key:
+ - 注册完毕后,前往 [API Keys](https://platform.openai.com/api-keys) 页面,点击 `Create new secret key` 创建新的 API Key:
-- 打开创建窗口
+ - 打开创建窗口
-
+
-- 创建 API Key
+ - 创建 API Key
-
+
-- 获取 API Key
+ - 获取 API Key
-
+
-账户注册后,一般有 5 美元的免费额度,但有效期只有三个月。
+ 账户注册后,一般有 5 美元的免费额度,但有效期只有三个月。
-### 步骤二:在 LobeChat 中配置 OpenAI
+ ### 步骤二:在 LobeChat 中配置 OpenAI
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`OpenAI`的设置项
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`OpenAI`的设置项
-
+
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个 OpenAI 的模型即可开始对话
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 OpenAI 的模型即可开始对话
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 OpenAI 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 OpenAI 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 OpenAI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/openrouter.mdx b/DigitalHumanWeb/docs/usage/providers/openrouter.mdx
index 3fc4c68..550d66b 100644
--- a/DigitalHumanWeb/docs/usage/providers/openrouter.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/openrouter.mdx
@@ -13,98 +13,62 @@ tags:
# Using OpenRouter in LobeChat
-
+
[OpenRouter](https://openrouter.ai/) is a service that provides a variety of excellent large language model APIs, supporting models such as OpenAI (including GPT-3.5/4), Anthropic (Claude2, Instant), LLaMA 2, and PaLM Bison.
This document will guide you on how to use OpenRouter in LobeChat:
+ ### Step 1: Register and Log in to OpenRouter
-### Step 1: Register and Log in to OpenRouter
-
-- Visit [OpenRouter.ai](https://openrouter.ai/) and create an account
-- You can log in using your Google account or MetaMask wallet
-
-
-
-### Step 2: Create an API Key
-
-- Go to the `Keys` menu or visit [OpenRouter Keys](https://openrouter.ai/keys) directly
-- Click on `Create Key` to start the creation process
-- Name your API key in the pop-up dialog, for example, "LobeChat Key"
-- Leave the `Credit limit` blank to indicate no amount limit
-
-
-
-- Copy the API key from the pop-up dialog and save it securely
-
-
-
-
- Please store the key securely as it will only appear once. If you lose it accidentally, you will
- need to create a new key.
-
-
-### Step 3: Recharge Credit
-
-- Go to the `Credit` menu or visit [OpenRouter Credit](https://openrouter.ai/credits) directly
-- Click on `Manage Credits` to recharge your credit, you can check model prices at [https://openrouter.ai/models](https://openrouter.ai/models)
-- OpenRouter provides some free models that can be used without recharging
-
-
-
-### Step 4: Configure OpenRouter in LobeChat
-
-- Visit the `Settings` interface in LobeChat
-- Find the setting for `OpenRouter` under `Language Models`
-- Enable OpenRouter and enter the API key you obtained
-
-
-
-- Choose an OpenRouter model for your assistant to start the conversation
-
-
-
-
- You may need to pay the API service provider during usage, please refer to OpenRouter's relevant
- fee policies.
-
+ - Visit [OpenRouter.ai](https://openrouter.ai/) and create an account
+ - You can log in using your Google account or MetaMask wallet
+
+
+ ### Step 2: Create an API Key
+
+ - Go to the `Keys` menu or visit [OpenRouter Keys](https://openrouter.ai/keys) directly
+ - Click on `Create Key` to start the creation process
+ - Name your API key in the pop-up dialog, for example, "LobeChat Key"
+ - Leave the `Credit limit` blank to indicate no amount limit
+
+
+
+ - Copy the API key from the pop-up dialog and save it securely
+
+
+
+
+ Please store the key securely as it will only appear once. If you lose it accidentally, you will
+ need to create a new key.
+
+
+ ### Step 3: Recharge Credit
+
+ - Go to the `Credit` menu or visit [OpenRouter Credit](https://openrouter.ai/credits) directly
+ - Click on `Manage Credits` to recharge your credit, you can check model prices at [https://openrouter.ai/models](https://openrouter.ai/models)
+ - OpenRouter provides some free models that can be used without recharging
+
+
+
+ ### Step 4: Configure OpenRouter in LobeChat
+
+ - Visit the `Settings` interface in LobeChat
+ - Find the setting for `OpenRouter` under `Language Models`
+ - Enable OpenRouter and enter the API key you obtained
+
+
+
+ - Choose an OpenRouter model for your assistant to start the conversation
+
+
+
+
+ You may need to pay the API service provider during usage, please refer to OpenRouter's relevant
+ fee policies.
+
You can now engage in conversations using the models provided by OpenRouter in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/openrouter.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/openrouter.zh-CN.mdx
index 7db17f3..40670eb 100644
--- a/DigitalHumanWeb/docs/usage/providers/openrouter.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/openrouter.zh-CN.mdx
@@ -9,96 +9,60 @@ tags:
# 在 LobeChat 中使用 OpenRouter
-
+
[OpenRouter](https://openrouter.ai/) 是一个提供多种优秀大语言模型 API 的服务,它支持 OpenAI (包括 GPT-3.5/4)、Anthropic (Claude2、Instant)、LLaMA 2 和 PaLM Bison 等众多模型。
本文档将指导你如何在 LobeChat 中使用 OpenRouter:
+ ### 步骤一:注册 OpenRouter 账号并登录
-### 步骤一:注册 OpenRouter 账号并登录
+ - 访问 [OpenRouter.ai](https://openrouter.ai/) 并创建一个账号
+ - 你可以用 Google 账号或 MetaMask 钱包登录
-- 访问 [OpenRouter.ai](https://openrouter.ai/) 并创建一个账号
-- 你可以用 Google 账号或 MetaMask 钱包登录
+
-
+ ### 步骤二:创建 API 密钥
-### 步骤二:创建 API 密钥
+ - 进入 `Keys` 菜单或直接访问 [OpenRouter Keys](https://openrouter.ai/keys)
+ - 点击 `Create Key` 开始创建
+ - 在弹出对话框中为 API 密钥取一个名字,例如 "LobeChat Key"
+ - 留空 `Credit limit` 表示不设置金额限制
-- 进入 `Keys` 菜单或直接访问 [OpenRouter Keys](https://openrouter.ai/keys)
-- 点击 `Create Key` 开始创建
-- 在弹出对话框中为 API 密钥取一个名字,例如 "LobeChat Key"
-- 留空 `Credit limit` 表示不设置金额限制
+
-
+ - 在弹出的对话框中复制 API 密钥,并妥善保存
-- 在弹出的对话框中复制 API 密钥,并妥善保存
+
-
+
+ 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新密钥。
+
-
- 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新密钥。
-
+ ### 步骤三:充值信用额度
-### 步骤三:充值信用额度
+ - 进入 `Credit` 菜单,或直接访问 [OpenRouter Credit](https://openrouter.ai/credits)
+ - 点击 `Manage Credits` 充值信用额度,在 [https://openrouter.ai/models](https://openrouter.ai/models) 中可以查看模型价格
+ - OpenRouter 提供了一些免费模型,未充值的情况下可以使用
-- 进入 `Credit` 菜单,或直接访问 [OpenRouter Credit](https://openrouter.ai/credits)
-- 点击 `Manage Credits` 充值信用额度,在 [https://openrouter.ai/models](https://openrouter.ai/models) 中可以查看模型价格
-- OpenRouter 提供了一些免费模型,未充值的情况下可以使用
+
-
+ ### 步骤四:在 LobeChat 中配置 OpenRouter
-### 步骤四:在 LobeChat 中配置 OpenRouter
+ - 访问 LobeChat 的 `设置` 界面
+ - 在 `语言模型` 下找到 `OpenRouter` 的设置项
+ - 打开 OpenRouter 并填入获得的 API 密钥
-- 访问 LobeChat 的 `设置` 界面
-- 在 `语言模型` 下找到 `OpenRouter` 的设置项
-- 打开 OpenRouter 并填入获得的 API 密钥
+
-
+ - 为你的助手选择一个 OpenRouter 模型即可开始对话
-- 为你的助手选择一个 OpenRouter 模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 OpenRouter 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 OpenRouter 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 OpenRouter 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/perplexity.mdx b/DigitalHumanWeb/docs/usage/providers/perplexity.mdx
index d35b9e0..f76fd5c 100644
--- a/DigitalHumanWeb/docs/usage/providers/perplexity.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/perplexity.mdx
@@ -11,52 +11,34 @@ tags:
# Using Perplexity AI in LobeChat
-
+
The Perplexity AI API is now available for everyone to use. This document will guide you on how to use [Perplexity AI](https://www.perplexity.ai/) in LobeChat:
+ ### Step 1: Obtain Perplexity AI API Key
-### Step 1: Obtain Perplexity AI API Key
+ - Create a [Perplexity AI](https://www.perplexity.ai/) account
+ - Obtain your [API key](https://www.perplexity.ai/settings/api)
-- Create a [Perplexity AI](https://www.perplexity.ai/) account
-- Obtain your [API key](https://www.perplexity.ai/settings/api)
+
-
+ ### Step 2: Configure Perplexity AI in LobeChat
-### Step 2: Configure Perplexity AI in LobeChat
+ - Go to the `Settings` interface in LobeChat
+ - Find the setting for `Perplexity AI` under `Language Model`
-- Go to the `Settings` interface in LobeChat
-- Find the setting for `Perplexity AI` under `Language Model`
+
-
+ - Enter the API key you obtained
+ - Choose a Perplexity AI model for your AI assistant to start the conversation
-- Enter the API key you obtained
-- Choose a Perplexity AI model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider. Please refer to Perplexity AI's
- relevant pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider. Please refer to Perplexity AI's
+ relevant pricing policies.
+
You can now engage in conversations using the models provided by Perplexity AI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/perplexity.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/perplexity.zh-CN.mdx
index 7b1b7c3..b5de714 100644
--- a/DigitalHumanWeb/docs/usage/providers/perplexity.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/perplexity.zh-CN.mdx
@@ -9,51 +9,33 @@ tags:
# 在 LobeChat 中使用 Perplexity AI
-
+
-Perplexity AI API 现在可供所有人使用, 本文档将指导你如何在 LobeChat 中使用 [Perplexity AI](https://www.perplexity.ai/):
+Perplexity AI API 现在可供所有人使用,本文档将指导你如何在 LobeChat 中使用 [Perplexity AI](https://www.perplexity.ai/):
+ ### 步骤一:获取 Perplexity AI API 密钥
-### 步骤一:获取 Perplexity AI API 密钥
+ - 创建一个 [Perplexity AI](https://www.perplexity.ai/) 帐户
+ - 获取您的 [API 密钥](https://www.perplexity.ai/settings/api)
-- 创建一个 [Perplexity AI](https://www.perplexity.ai/) 帐户
-- 获取您的 [API 密钥](https://www.perplexity.ai/settings/api)
+
-
+ ### 步骤二:在 LobeChat 中配置 Perplexity AI
-### 步骤二:在 LobeChat 中配置 Perplexity AI
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`Perplexity AI`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`Perplexity AI`的设置项
+
-
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Perplexity AI 的模型即可开始对话
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个 Perplexity AI 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Perplexity AI 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Perplexity AI 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Perplexity AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/ppio.mdx b/DigitalHumanWeb/docs/usage/providers/ppio.mdx
new file mode 100644
index 0000000..a2dc322
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/ppio.mdx
@@ -0,0 +1,57 @@
+---
+title: Using PPIO API Key in LobeChat
+description: >-
+ Learn how to integrate PPIO's language model APIs into LobeChat. Follow the
+ steps to register, create an PPIO API key, configure settings, and chat with
+ our various AI models.
+tags:
+ - PPIO
+ - DeepSeek
+ - Llama
+ - Qwen
+ - uncensored
+ - API key
+ - Web UI
+---
+
+# Using PPIO in LobeChat
+
+
+
+[PPIO](https://ppinfra.com/user/register?invited_by=RQIMOC&utm_source=github_lobechat) supports stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.
+
+This document will guide you on how to integrate PPIO in LobeChat:
+
+
+ ### Step 1: Register and Log in to PPIO
+
+ - Visit [PPIO](https://ppinfra.com/user/register?invited_by=RQIMOC&utm_source=github_lobechat) and create an account
+ - Upon registration, PPIO will provide a ¥5 credit (about 5M tokens).
+
+
+
+ ### Step 2: Obtain the API Key
+
+ - Visit PPIO's [key management page](https://ppinfra.com/settings/key-management), create and copy an API Key.
+
+
+
+ ### Step 3: Configure PPIO in LobeChat
+
+ - Visit the `Settings` interface in LobeChat
+ - Find the setting for `PPIO` under `Language Model`
+
+
+
+ - Open PPIO and enter the obtained API key
+ - Choose a PPIO model for your assistant to start the conversation
+
+
+
+
+ During usage, you may need to pay the API service provider, please refer to PPIO's [pricing
+ policy](https://ppinfra.com/llm-api?utm_source=github_lobe-chat&utm_medium=github_readme&utm_campaign=link).
+
+
+
+You can now engage in conversations using the models provided by PPIO in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/ppio.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/ppio.zh-CN.mdx
new file mode 100644
index 0000000..30066c9
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/ppio.zh-CN.mdx
@@ -0,0 +1,55 @@
+---
+title: 在 LobeChat 中使用 PPIO 派欧云 API Key
+description: >-
+ 学习如何将 PPIO 派欧云的 LLM API 集成到 LobeChat 中。跟随以下步骤注册 PPIO 账号、创建 API Key、并在 LobeChat
+ 中进行设置。
+tags:
+ - PPIO
+ - PPInfra
+ - DeepSeek
+ - Qwen
+ - Llama3
+ - API key
+ - Web UI
+---
+
+# 在 LobeChat 中使用 PPIO 派欧云
+
+
+
+[PPIO 派欧云](https://ppinfra.com/user/register?invited_by=RQIMOC&utm_source=github_lobechat)提供稳定、高性价比的开源模型 API 服务,支持 DeepSeek 全系列、Llama、Qwen 等行业领先大模型。
+
+本文档将指导你如何在 LobeChat 中使用 PPIO:
+
+
+ ### 步骤一:注册 PPIO 派欧云账号并登录
+
+ - 访问 [PPIO 派欧云](https://ppinfra.com/user/register?invited_by=RQIMOC&utm_source=github_lobechat) 并注册账号
+ - 注册后,PPIO 会赠送 5 元(约 500 万 tokens)的使用额度
+
+
+
+ ### 步骤二:创建 API 密钥
+
+ - 访问 PPIO 派欧云的 [密钥管理页面](https://ppinfra.com/settings/key-management) ,创建并且复制一个 API 密钥.
+
+
+
+ ### 步骤三:在 LobeChat 中配置 PPIO 派欧云
+
+ - 访问 LobeChat 的 `设置` 界面
+ - 在 `语言模型` 下找到 `PPIO` 的设置项
+ - 打开 PPIO 并填入获得的 API 密钥
+
+
+
+ - 为你的助手选择一个 PPIO 模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,PPIO 的 API 费用参考[这里](https://ppinfra.com/llm-api?utm_source=github_lobe-chat&utm_medium=github_readme&utm_campaign=link)。
+
+
+
+至此你已经可以在 LobeChat 中使用 PPIO 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/qwen.mdx b/DigitalHumanWeb/docs/usage/providers/qwen.mdx
index 6291a6f..9563ede 100644
--- a/DigitalHumanWeb/docs/usage/providers/qwen.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/qwen.mdx
@@ -15,78 +15,52 @@ tags:
# Using Tongyi Qianwen in LobeChat
-
+
[Tongyi Qianwen](https://tongyi.aliyun.com/) is a large-scale language model independently developed by Alibaba Cloud, with powerful natural language understanding and generation capabilities. It can answer various questions, create text content, express opinions, write code, and play a role in multiple fields.
This document will guide you on how to use Tongyi Qianwen in LobeChat:
+ ### Step 1: Activate DashScope Model Service
-### Step 1: Activate DashScope Model Service
+ - Visit and log in to Alibaba Cloud's [DashScope](https://dashscope.console.aliyun.com/) platform.
+ - If it is your first time, you need to activate the DashScope service.
+ - If you have already activated it, you can skip this step.
-- Visit and log in to Alibaba Cloud's [DashScope](https://dashscope.console.aliyun.com/) platform.
-- If it is your first time, you need to activate the DashScope service.
-- If you have already activated it, you can skip this step.
+
-
+ ### Step 2: Obtain DashScope API Key
-### Step 2: Obtain DashScope API Key
+ - Go to the `API-KEY` interface and create an API key.
-- Go to the `API-KEY` interface and create an API key.
+
-
+ - Copy the API key from the pop-up dialog box and save it securely.
-- Copy the API key from the pop-up dialog box and save it securely.
+
-
+
+ Please store the key securely as it will only appear once. If you accidentally lose it, you will
+ need to create a new key.
+
-
- Please store the key securely as it will only appear once. If you accidentally lose it, you will
- need to create a new key.
-
+ ### Step 3: Configure Tongyi Qianwen in LobeChat
-### Step 3: Configure Tongyi Qianwen in LobeChat
+ - Visit the `Settings` interface in LobeChat.
+ - Find the setting for `Tongyi Qianwen` under `Language Model`.
-- Visit the `Settings` interface in LobeChat.
-- Find the setting for `Tongyi Qianwen` under `Language Model`.
+
-
+ - Open Tongyi Qianwen and enter the obtained API key.
+ - Choose a Qwen model for your AI assistant to start the conversation.
-- Open Tongyi Qianwen and enter the obtained API key.
-- Choose a Qwen model for your AI assistant to start the conversation.
-
-
-
-
- During usage, you may need to pay the API service provider. Please refer to Tongyi Qianwen's
- relevant pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider. Please refer to Tongyi Qianwen's
+ relevant pricing policies.
+
You can now engage in conversations using the models provided by Tongyi Qianwen in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/qwen.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/qwen.zh-CN.mdx
index 09bbb44..451d6e1 100644
--- a/DigitalHumanWeb/docs/usage/providers/qwen.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/qwen.zh-CN.mdx
@@ -12,76 +12,50 @@ tags:
# 在 LobeChat 中使用通义千问
-
+
-[通义千问](https://tongyi.aliyun.com/)是阿里云自主研发的超大规模语言模型,具有强大的自然语言理解和生成能力。它可以回答各种问题、创作文字内容、表达观点看法、撰写代码等,在多个领域发挥作用。
+[通义千问](https://tongyi.aliyun.com/)是阿里云自主研发的超大规模语言模型,具有强大的自然语言理解和生成能力。它可以回答各种问题、创作文字内容、表达观点看法、撰写代码等,在多个领域发挥作用。
本文档将指导你如何在 LobeChat 中使用通义千问:
+ ### 步骤一:开通 DashScope 模型服务
-### 步骤一:开通 DashScope 模型服务
+ - 访问并登录阿里云 [DashScope](https://dashscope.console.aliyun.com/) 平台
+ - 初次进入时需要开通 DashScope 服务
+ - 若你已开通,可跳过该步骤
-- 访问并登录阿里云 [DashScope](https://dashscope.console.aliyun.com/) 平台
-- 初次进入时需要开通 DashScope 服务
-- 若你已开通,可跳过该步骤
+
-
+ ### 步骤二:获取 DashScope API 密钥
-### 步骤二:获取 DashScope API 密钥
+ - 进入`API-KEY` 界面,并创建一个 API 密钥
-- 进入`API-KEY` 界面,并创建一个 API 密钥
+
-
+ - 在弹出的对话框中复制 API 密钥,并妥善保存
-- 在弹出的对话框中复制 API 密钥,并妥善保存
+
-
+
+ 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新密钥。
+
-
- 请安全地存储密钥,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新密钥。
-
+ ### 步骤三:在 LobeChat 中配置通义千问
-### 步骤三:在LobeChat 中配置通义千问
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`通义千问`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`通义千问`的设置项
+
-
+ - 打开通义千问并填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Qwen 的模型即可开始对话
-- 打开通义千问并填入获得的 API 密钥
-- 为你的 AI 助手选择一个 Qwen 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考通义千问的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考通义千问的相关费用政策。
+
至此你已经可以在 LobeChat 中使用通义千问提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/sambanova.mdx b/DigitalHumanWeb/docs/usage/providers/sambanova.mdx
new file mode 100644
index 0000000..fdb0a3d
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/sambanova.mdx
@@ -0,0 +1,50 @@
+---
+title: Using SambaNova API Key in LobeChat
+description: Learn how to configure and use SambaNova models in LobeChat, obtain an API key, and start a conversation.
+tags:
+ - LobeChat
+ - SambaNova
+ - API Key
+ - Web UI
+---
+
+# Using SambaNova in LobeChat
+
+
+
+[SambaNova](https://sambanova.ai/) is a company based in Palo Alto, California, USA, focused on developing high-performance AI hardware and software solutions. It provides fast AI model training, fine-tuning, and inference capabilities, especially suitable for large-scale generative AI models.
+
+This document will guide you on how to use SambaNova in LobeChat:
+
+
+ ### Step 1: Obtain a SambaNova API Key
+
+ - First, you need to register and log in to [SambaNova Cloud](https://cloud.sambanova.ai/)
+ - Create an API key in the `APIs` page
+
+
+
+ - Copy the obtained API key and save it securely
+
+
+ Please save the generated API Key securely, as it will only appear once. If you accidentally lose it, you will need to create a new API key.
+
+
+ ### Step 2: Configure SambaNova in LobeChat
+
+ - Access the `Application Settings` interface of LobeChat
+ - Find the `SambaNova` setting item under `Language Model`
+
+
+
+ - Turn on SambaNova and fill in the obtained API key
+ - Select a SambaNova model for your assistant to start the conversation
+
+
+
+
+ You may need to pay the API service provider during use, please refer to SambaNova's related fee policies.
+
+
+
+Now you can use the models provided by SambaNova in LobeChat to conduct conversations.
diff --git a/DigitalHumanWeb/docs/usage/providers/sambanova.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/sambanova.zh-CN.mdx
new file mode 100644
index 0000000..b64eacd
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/sambanova.zh-CN.mdx
@@ -0,0 +1,50 @@
+---
+title: 在 LobeChat 中使用 SambaNova API Key
+description: 学习如何在 LobeChat 中配置和使用 SambaNova 模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - SambaNova
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 SambaNova
+
+
+
+[SambaNova](https://sambanova.ai/) 是一家位于美国加利福尼亚州帕洛阿尔托的公司,专注于开发高性能 AI 硬件和软件解决方案,提供快速的 AI 模型训练、微调和推理能力,尤其适用于大规模生成式 AI 模型。
+
+本文档将指导你如何在 LobeChat 中使用 SambaNova:
+
+
+ ### 步骤一:获取 SambaNova API 密钥
+
+ - 首先,你需要注册并登录 [SambaNova Cloud](https://cloud.sambanova.ai/)
+ - 在 `APIs` 页面中创建一个 API 密钥
+
+
+
+ - 复制得到的 API 密钥并妥善保存
+
+
+ 请妥善保存生成的 API Key,它只会出现一次,如果不小心丢失了,你需要重新创建一个 API key
+
+
+ ### 步骤二:在 LobeChat 中配置 SambaNova
+
+ - 访问 LobeChat 的 `应用设置`界面
+ - 在 `语言模型` 下找到 `SambaNova` 的设置项
+
+
+
+ - 打开 SambaNova 并填入获取的 API 密钥
+ - 为你的助手选择一个 SambaNova 模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 SambaNova 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 SambaNova 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/sensenova.mdx b/DigitalHumanWeb/docs/usage/providers/sensenova.mdx
new file mode 100644
index 0000000..a8a77dc
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/sensenova.mdx
@@ -0,0 +1,58 @@
+---
+title: Using SenseNova in LobeChat
+description: >-
+ Learn how to configure and use SenseNova's API Key in LobeChat to start
+ conversations and interactions.
+tags:
+ - LobeChat
+ - SenseNova
+ - API Key
+ - Web UI
+---
+
+# Using SenseNova in LobeChat
+
+
+
+[SenseNova](https://platform.sensenova.cn/home) is a large model system introduced by SenseTime, aimed at promoting the rapid iteration and practical application of artificial intelligence (AI) technology.
+
+This article will guide you on how to use SenseNova in LobeChat.
+
+
+ ### Step 1: Obtain the API Key for SenseNova
+
+ - Register and log in to the [SenseCore Development Platform](https://www.sensecore.cn/product/aistudio).
+ - Locate the `SenseNova Large Model` in the product menu and activate the service.
+
+
+
+ - Go to the [AccessKey Management](https://console.sensecore.cn/iam/Security/access-key) page.
+ - Create an access key.
+ - Save the Access Key ID and secret in the pop-up window.
+
+
+
+
+ Please keep the access key from the pop-up window secure, as it will only appear once. If you lose
+ it, you will need to create a new access key.
+
+
+ ### Step 2: Configure SenseNova in LobeChat
+
+ - Access the `Settings` interface on LobeChat.
+ - Find the setting for `SenseNova` under `Language Models`.
+
+
+
+ - Input the obtained `Access Key ID` and `Access Key Secret`.
+ - Choose a SenseNova model for your AI assistant and start the conversation.
+
+
+
+
+ During usage, you may need to pay the API service provider, please refer to the relevant fee
+ policy for SenseNova.
+
+
+
+You can now have conversations using the models provided by SenseNova in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/sensenova.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/sensenova.zh-CN.mdx
new file mode 100644
index 0000000..449f4ce
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/sensenova.zh-CN.mdx
@@ -0,0 +1,54 @@
+---
+title: 在 LobeChat 中使用商汤日日新
+description: 学习如何在 LobeChat 中配置和使用商汤日日新的 API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - 商汤日日新
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用商汤日日新
+
+
+
+[商汤日日新](https://platform.sensenova.cn/home) 是商汤科技(SenseTime)推出的一个大模型体系,旨在推动人工智能(AI)技术的快速迭代和应用落地。
+
+本文将指导你如何在 LobeChat 中使用商汤日日新。
+
+
+ ### 步骤一:获取商汤日日新的 API 密钥
+
+ - 注册并登录 [万象模型开发平台](https://www.sensecore.cn/product/aistudio)
+ - 在产品菜单中找到 `日日新大模型` 并开通服务
+
+
+
+ - 进入 [AccessKey 访问密钥](https://console.sensecore.cn/iam/Security/access-key) 页面
+ - 创建一个访问密钥
+ - 在弹出窗口中保存访问密钥 ID 和令牌
+
+
+
+
+ 妥善保存弹窗中的访问密钥,它只会出现一次,如果不小心丢失了,你需要重新创建一个访问密钥。
+
+
+ ### 步骤二:在 LobeChat 中配置商汤日日新
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `商汤日日新` 的设置项
+
+
+
+ - 填入获得的 `AccessKey ID` 和 `AccessKey Secret`
+ - 为你的 AI 助手选择一个商汤日日新的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考商汤日日新的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用商汤日日新提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/siliconcloud.mdx b/DigitalHumanWeb/docs/usage/providers/siliconcloud.mdx
index 4d5ab5b..f578610 100644
--- a/DigitalHumanWeb/docs/usage/providers/siliconcloud.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/siliconcloud.mdx
@@ -1,8 +1,8 @@
---
-title: Using SiliconCloud API Key in LobeChat
+title: Using SiliconCloud in LobeChat
description: >-
- Learn how to configure and use SiliconCloud's large language models in
- LobeChat, get your API key, and start chatting.
+ Learn how to integrate and utilize SiliconCloud's language model APIs in
+ LobeChat.
tags:
- LobeChat
- SiliconCloud
@@ -12,36 +12,37 @@ tags:
# Using SiliconCloud in LobeChat
-[SiliconCloud](https://siliconflow.cn/zh-cn/siliconcloud) is a cost-effective large model service provider, offering various services such as text generation and image generation.
+
-This document will guide you on how to use SiliconCloud in LobeChat:
+[SiliconCloud](https://siliconflow.cn/) is an AI service platform based on open-source foundational models, offering a variety of generative AI (GenAI) services.
-
-
-### Step 1: Get your SiliconCloud API Key
-
-- First, you need to register and log in to [SiliconCloud](https://cloud.siliconflow.cn/auth/login)
+This article will guide you on how to use SiliconCloud in LobeChat.
-Currently, new users can get 14 yuan free credit upon registration
-
-- Go to the `API Key` menu and click `Create New API Key`
+
+ ### Step 1: Obtain the API Key from SiliconCloud
-- Click copy API key and keep it safe
+ - Sign up and log in to [SiliconCloud](https://cloud.siliconflow.cn/account/ak)
+ - Click on the `API Keys` menu on the left side
+ - Create an API Key and copy it
-### Step 2: Configure SiliconCloud in LobeChat
+
-- Visit the `App Settings` interface of LobeChat
+ ### Step 2: Configure SiliconCloud in LobeChat
-- Under `Language Model`, find the `SiliconCloud` settings
+ - Go to the `Settings` page in LobeChat
+ - Under `Language Model`, find the setting for `SiliconFlow`
-- Enable SiliconCloud and enter the obtained API key
+
-- Choose a SiliconCloud model for your assistant and start chatting
+ - Enter the API Key you obtained
+ - Choose a SiliconCloud model for your AI assistant to start the conversation
-
- You may need to pay the API service provider during use. Please refer to SiliconCloud's relevant fee policy.
-
+
+
+ During usage, you may need to pay the API service provider, so please refer to SiliconCloud's
+ relevant pricing policy.
+
-Now you can use the models provided by SiliconCloud for conversation in LobeChat.
+At this point, you can start chatting using the models provided by SiliconCloud in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/siliconcloud.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/siliconcloud.zh-CN.mdx
index 0d4b13c..b986295 100644
--- a/DigitalHumanWeb/docs/usage/providers/siliconcloud.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/siliconcloud.zh-CN.mdx
@@ -1,6 +1,6 @@
---
-title: 在 LobeChat 中使用 SiliconCloud API Key
-description: 学习如何在 LobeChat 中配置和使用 SiliconCloud 提供的大语言模型,获取 API 密钥并开始对话。
+title: 在 LobeChat 中使用 SiliconCloud
+description: 学习如何在 LobeChat 中配置和使用 SiliconCloud 的API Key,以便开始对话和交互。
tags:
- LobeChat
- SiliconCloud
@@ -10,36 +10,36 @@ tags:
# 在 LobeChat 中使用 SiliconCloud
-[SiliconCloud](https://siliconflow.cn/zh-cn/siliconcloud) 是高性价比的大模型服务提供商,提供文本生成与图片生成等多种服务。
+
-本文档将指导你如何在 LobeChat 中使用 SiliconCloud:
+[SiliconCloud](https://siliconflow.cn/) 是一个基于开源基础模型的人工智能服务平台,提供多种生成式 AI(GenAI)服务。
-
-
-### 步骤一:获取 SiliconCloud API 密钥
-
-- 首先,你需要注册并登录 [SiliconCloud](https://cloud.siliconflow.cn/auth/login)
+本文将指导你如何在 LobeChat 中使用 SiliconCloud。
-当前新用户注册可获赠 14 元免费额度
-
-- 进入 `API密钥` 菜单,并点击 `创建新API密钥`
+
+ ### 步骤一:获得 SiliconCloud 的 API Key
-- 点击复制 API 密钥并妥善保存
+ - 注册并登录 [SiliconCloud](https://cloud.siliconflow.cn/account/ak)
+ - 点击左侧 `API 密钥` 菜单
+ - 创建一个 API 密钥并复制
-### 步骤二:在 LobeChat 中配置 SiliconCloud
+
-- 访问 LobeChat 的 `应用设置` 界面
+ ### 步骤二:在 LobeChat 中配置 SiliconCloud
-- 在 `语言模型` 下找到 `SiliconCloud` 的设置项
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `SiliconFlow` 的设置项
-- 打开 SiliconCloud 并填入获取的 API 密钥
+
-- 为你的助手选择一个 SiliconCloud 模型即可开始对话
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 SiliconCloud 的模型即可开始对话
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 SiliconCloud 的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 SiliconCloud 的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 SiliconCloud 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/spark.mdx b/DigitalHumanWeb/docs/usage/providers/spark.mdx
new file mode 100644
index 0000000..52a0309
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/spark.mdx
@@ -0,0 +1,51 @@
+---
+title: Using iFLYTEK Spark in LobeChat
+description: Learn how to integrate and utilize iFLYTEK's Spark model APIs in LobeChat.
+tags:
+ - LobeChat
+ - iFLYTEK
+ - Spark
+ - API Key
+ - Web UI
+---
+
+# Using iFLYTEK Spark in LobeChat
+
+
+
+[iFLYTEK Spark](https://xinghuo.xfyun.cn/) is a powerful AI model launched by iFLYTEK, equipped with cross-domain knowledge and language understanding capabilities, able to perform various tasks such as Q\&A, conversations, and literary creation.
+
+This guide will instruct you on how to use iFLYTEK Spark in LobeChat.
+
+
+ ### Step 1: Obtain the iFLYTEK Spark API Key
+
+ - Register and log in to the [iFLYTEK Open Platform](https://console.xfyun.cn/)
+ - Create an application
+
+
+
+ - Select a large model to view details
+ - Copy the `API Password` from the top right corner under the HTTP service interface authentication information
+
+
+
+ ### Step 2: Configure iFLYTEK Spark in LobeChat
+
+ - Access the `Settings` menu in LobeChat
+ - Find the iFLYTEK Spark settings under `Language Model`
+
+
+
+ - Input the obtained API Key
+ - Choose an iFLYTEK Spark model for your AI assistant to start the conversation
+
+
+
+
+ During usage, you may need to pay the API service provider, please refer to the relevant pricing
+ policy of iFLYTEK Spark.
+
+
+
+Now you can use the models provided by iFLYTEK Spark for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/spark.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/spark.zh-CN.mdx
new file mode 100644
index 0000000..0b43463
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/spark.zh-CN.mdx
@@ -0,0 +1,49 @@
+---
+title: 在 LobeChat 中使用讯飞星火
+description: 学习如何在 LobeChat 中配置和使用讯飞星火的API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - 讯飞星火
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用讯飞星火
+
+
+
+[讯飞星火](https://xinghuo.xfyun.cn/)是科大讯飞推出的一款强大的 AI 大模型,具备跨领域的知识和语言理解能力,能够执行问答、对话和文学创作等多种任务。
+
+本文将指导你如何在 LobeChat 中使用讯飞星火。
+
+
+ ### 步骤一:获得讯飞星火的 API Key
+
+ - 注册并登录 [讯飞开放平台](https://console.xfyun.cn/)
+ - 创建一个应用
+
+
+
+ - 选择一个大模型查看详情
+ - 复制右上角 http 服务接口认证信息中的 `API Password`
+
+
+
+ ### 步骤二:在 LobeChat 中配置讯飞星火
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `讯飞星火` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个讯飞星火的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考讯飞星火的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用讯飞星火提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/stepfun.mdx b/DigitalHumanWeb/docs/usage/providers/stepfun.mdx
index 430daa6..34ddb6d 100644
--- a/DigitalHumanWeb/docs/usage/providers/stepfun.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/stepfun.mdx
@@ -12,55 +12,37 @@ tags:
# Using Stepfun in LobeChat
-
+
[Stepfun](https://www.stepfun.com/) is a startup focusing on the research and development of Artificial General Intelligence (AGI). They have released the Step-1 billion-parameter language model, Step-1V billion-parameter multimodal model, and the Step-2 trillion-parameter MoE language model preview.
This document will guide you on how to use Stepfun in LobeChat:
+ ### Step 1: Obtain Stepfun API Key
-### Step 1: Obtain Stepfun API Key
+ - Visit and log in to the [Stepfun Open Platform](https://platform.stepfun.com/)
+ - Go to the `API Key` menu, where the system has already created an API key for you
+ - Copy the created API key
-- Visit and log in to the [Stepfun Open Platform](https://platform.stepfun.com/)
-- Go to the `API Key` menu, where the system has already created an API key for you
-- Copy the created API key
+
-
+ ### Step 2: Configure Stepfun in LobeChat
-### Step 2: Configure Stepfun in LobeChat
+ - Visit the `Settings` interface in LobeChat
+ - Find the setting for Stepfun under `Language Models`
-- Visit the `Settings` interface in LobeChat
-- Find the setting for Stepfun under `Language Models`
+
-
+ - Open Stepfun and enter the obtained API key
+ - Choose a Stepfun model for your AI assistant to start the conversation
-- Open Stepfun and enter the obtained API key
-- Choose a Stepfun model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Stepfun's relevant
- pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Stepfun's relevant
+ pricing policies.
+
You can now use the models provided by Stepfun to have conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/stepfun.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/stepfun.zh-CN.mdx
index df6a855..db01006 100644
--- a/DigitalHumanWeb/docs/usage/providers/stepfun.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/stepfun.zh-CN.mdx
@@ -9,54 +9,36 @@ tags:
# 在 LobeChat 中使用 Stepfun 阶跃星辰
-
+
-[Stepfun 阶跃星辰](https://www.stepfun.com/)是一家专注于通用人工智能(AGI)研发的创业公司,目前已推出Step-1千亿参数语言大模型、Step-1V千亿参数多模态大模型,以及Step-2万亿参数MoE语言大模型预览版。
+[Stepfun 阶跃星辰](https://www.stepfun.com/)是一家专注于通用人工智能 (AGI) 研发的创业公司,目前已推出 Step-1 千亿参数语言大模型、Step-1V 千亿参数多模态大模型,以及 Step-2 万亿参数 MoE 语言大模型预览版。
本文档将指导你如何在 LobeChat 中使用 Stepfun 阶跃星辰:
+ ### 步骤一:获取 Stepfun 阶跃星辰 API 密钥
-### 步骤一:获取 Stepfun 阶跃星辰 API 密钥
+ - 访问并登录 [Stepfun Stepfun 阶跃星辰开放平台](https://platform.stepfun.com/)
+ - 进入`接口密钥`菜单,系统已为你创建好 API 密钥
+ - 复制已创建的 API 密钥
-- 访问并登录 [Stepfun Stepfun 阶跃星辰开放平台](https://platform.stepfun.com/)
-- 进入`接口密钥`菜单,系统已为你创建好 API 密钥
-- 复制已创建的 API 密钥
+
-
+ ### 步骤二:在 LobeChat 中配置 Stepfun Stepfun 阶跃星辰
-### 步骤二:在LobeChat 中配置 Stepfun Stepfun 阶跃星辰
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到` Stepfun 阶跃星辰`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到` Stepfun 阶跃星辰`的设置项
+
-
+ - 打开 Stepfun 阶跃星辰并填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Stepfun 阶跃星辰的模型即可开始对话
-- 打开 Stepfun 阶跃星辰并填入获得的 API 密钥
-- 为你的 AI 助手选择一个 Stepfun 阶跃星辰的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Stepfun 阶跃星辰的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Stepfun 阶跃星辰的相关费用政策。
+
至此你已经可以在 LobeChat 中使用 Stepfun 阶跃星辰提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/taichu.mdx b/DigitalHumanWeb/docs/usage/providers/taichu.mdx
index 5ccee72..8a59caf 100644
--- a/DigitalHumanWeb/docs/usage/providers/taichu.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/taichu.mdx
@@ -13,52 +13,34 @@ tags:
# Using Taichu in LobeChat
-
+
This article will guide you on how to use Taichu in LobeChat:
+ ### Step 1: Obtain Taichu API Key
-### Step 1: Obtain Taichu API Key
+ - Create an account on [Taichu](https://ai-maas.wair.ac.cn/)
+ - Create and obtain an [API key](https://ai-maas.wair.ac.cn/#/settlement/api/key)
-- Create an account on [Taichu](https://ai-maas.wair.ac.cn/)
-- Create and obtain an [API key](https://ai-maas.wair.ac.cn/#/settlement/api/key)
+
-
+ ### Step 2: Configure Taichu in LobeChat
-### Step 2: Configure Taichu in LobeChat
+ - Go to the `Settings` interface in LobeChat
+ - Find the setting for `Taichu` under `Language Model`
-- Go to the `Settings` interface in LobeChat
-- Find the setting for `Taichu` under `Language Model`
+
-
+ - Enter the obtained API key
+ - Choose a Purple Taichu model for your AI assistant to start the conversation
-- Enter the obtained API key
-- Choose a Purple Taichu model for your AI assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Taichu's relevant
- pricing policies.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Taichu's relevant
+ pricing policies.
+
Now you can start conversing with the models provided by Taichu in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/taichu.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/taichu.zh-CN.mdx
index 6e87ce0..82e0569 100644
--- a/DigitalHumanWeb/docs/usage/providers/taichu.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/taichu.zh-CN.mdx
@@ -11,51 +11,33 @@ tags:
# 在 LobeChat 中使用紫东太初
-
+
本文将指导你如何在 LobeChat 中使用紫东太初:
+ ### 步骤一:获取紫东太初 API 密钥
-### 步骤一:获取紫东太初 API 密钥
+ - 创建一个[紫东太初](https://ai-maas.wair.ac.cn/)账户
+ - 创建并获取 [API 密钥](https://ai-maas.wair.ac.cn/#/settlement/api/key)
-- 创建一个[紫东太初](https://ai-maas.wair.ac.cn/)账户
-- 创建并获取 [API 密钥](https://ai-maas.wair.ac.cn/#/settlement/api/key)
+
-
+ ### 步骤二:在 LobeChat 中配置紫东太初
-### 步骤二:在 LobeChat 中配置紫东太初
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`紫东太初`的设置项
-- 访问 LobeChat 的`设置`界面
-- 在`语言模型`下找到`紫东太初`的设置项
+
-
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个紫东太初的模型即可开始对话
-- 填入获得的 API 密钥
-- 为你的 AI 助手选择一个紫东太初的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考紫东太初的相关费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考紫东太初的相关费用政策。
+
至此你已经可以在 LobeChat 中使用紫东太初提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/tencentcloud.mdx b/DigitalHumanWeb/docs/usage/providers/tencentcloud.mdx
new file mode 100644
index 0000000..12284f8
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/tencentcloud.mdx
@@ -0,0 +1,49 @@
+---
+title: Using Tencent Cloud API Key in LobeChat
+description: Learn how to configure and use Tencent Cloud AI models in LobeChat, obtain an API key, and start a conversation.
+tags:
+ - LobeChat
+ - Tencent Cloud
+ - API Key
+ - Web UI
+---
+
+# Using Tencent Cloud in LobeChat
+
+
+
+[Tencent Cloud](https://cloud.tencent.com/) is the cloud computing service brand of Tencent, specializing in providing cloud computing services for enterprises and developers. Tencent Cloud provides a series of AI large model solutions, through which AI models can be connected stably and efficiently.
+
+This document will guide you on how to connect Tencent Cloud's AI models in LobeChat:
+
+
+ ### Step 1: Obtain the Tencent Cloud API Key
+
+ - First, visit [Tencent Cloud](https://cloud.tencent.com/) and complete the registration and login.
+ - Enter the Tencent Cloud Console and navigate to [Large-scale Knowledge Engine Atomic Capability](https://console.cloud.tencent.com/lkeap).
+ - Activate the Large-scale Knowledge Engine, which requires real-name authentication during the activation process.
+
+
+
+ - In the `Access via OpenAI SDK` option, click the `Create API Key` button to create a new API Key.
+ - You can view and manage the created API Keys in `API Key Management`.
+ - Copy and save the created API Key.
+
+ ### Step 2: Configure Tencent Cloud in LobeChat
+
+ - Visit the `Application Settings` and `AI Service Provider` interface of LobeChat.
+ - Find the `Tencent Cloud` settings item in the list of providers.
+
+
+
+ - Open the Tencent Cloud provider and fill in the obtained API Key.
+ - Select a Tencent Cloud model for your assistant to start the conversation.
+
+
+
+
+ You may need to pay the API service provider during use, please refer to Tencent Cloud's relevant fee policy.
+
+
+
+You can now use the models provided by Tencent Cloud in LobeChat to have conversations.
diff --git a/DigitalHumanWeb/docs/usage/providers/tencentcloud.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/tencentcloud.zh-CN.mdx
new file mode 100644
index 0000000..e90d39e
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/tencentcloud.zh-CN.mdx
@@ -0,0 +1,49 @@
+---
+title: 在 LobeChat 中使用腾讯云 API Key
+description: 学习如何在 LobeChat 中配置和使用腾讯云 AI 模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - 腾讯云
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用腾讯云
+
+
+
+[腾讯云(Tencent Cloud)](https://cloud.tencent.com/)是腾讯公司旗下的云计算服务品牌,专门为企业和开发者提供云计算服务。腾讯云提供了一系列 AI 大模型解决方案,通过这些工具可以稳定高效接入 AI 模型。
+
+本文档将指导你如何在 LobeChat 中接入腾讯云的 AI 模型:
+
+
+ ### 步骤一:获取腾讯云 API 密钥
+
+ - 首先,访问[腾讯云](https://cloud.tencent.com/)并完成注册登录
+ - 进入腾讯云控制台并导航至[知识引擎原子能力](https://console.cloud.tencent.com/lkeap)
+ - 开通大模型知识引擎,开通过程需要实名认证
+
+
+
+ - 在`使用OpenAI SDK方式接入`选项中,点击 `创建 API Key` 按钮,创建一个新的 API Key
+ - 在 `API key 管理` 中可以查看和管理已创建的 API Key
+ - 复制并保存创建好的 API Key
+
+ ### 步骤二:在 LobeChat 中配置腾讯云
+
+ - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+ - 在供应商列表中找到 `腾讯云` 的设置项
+
+
+
+ - 打开腾讯云服务商并填入获取的 API 密钥
+ - 为你的助手选择一个腾讯云模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考腾讯云的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用腾讯云提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/togetherai.mdx b/DigitalHumanWeb/docs/usage/providers/togetherai.mdx
index fd158c1..5b9e2eb 100644
--- a/DigitalHumanWeb/docs/usage/providers/togetherai.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/togetherai.mdx
@@ -11,62 +11,40 @@ tags:
# Using Together AI in LobeChat
-
+
[together.ai](https://www.together.ai/) is a platform focused on the field of Artificial Intelligence Generated Content (AIGC), founded in June 2022. It is dedicated to building a cloud platform for running, training, and fine-tuning open-source models, providing scalable computing power at prices lower than mainstream vendors.
This document will guide you on how to use Together AI in LobeChat:
+ ### Step 1: Obtain the API Key for Together AI
-### Step 1: Obtain the API Key for Together AI
+ - Visit and log in to [Together AI API](https://api.together.ai/)
+ - Upon initial login, the system will automatically create an API key for you and provide a $5.0 credit
-- Visit and log in to [Together AI API](https://api.together.ai/)
-- Upon initial login, the system will automatically create an API key for you and provide a $5.0 credit
+
-
+ - If you haven't saved it, you can also view the API key at any time in the `API Key` interface under `Settings`
-- If you haven't saved it, you can also view the API key at any time in the `API Key` interface under `Settings`
+
-
+ ### Step 2: Configure Together AI in LobeChat
-### Step 2: Configure Together AI in LobeChat
+ - Visit the `Settings` interface in LobeChat
+ - Find the setting for `together.ai` under `Language Model`
-- Visit the `Settings` interface in LobeChat
-- Find the setting for `together.ai` under `Language Model`
+
-
+ - Open together.ai and enter the obtained API key
+ - Choose a Together AI model for your assistant to start the conversation
-- Open together.ai and enter the obtained API key
-- Choose a Together AI model for your assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Together AI's pricing
- policy.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Together AI's pricing
+ policy.
+
You can now engage in conversations using the models provided by Together AI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/togetherai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/togetherai.zh-CN.mdx
index 7e16495..149aed8 100644
--- a/DigitalHumanWeb/docs/usage/providers/togetherai.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/togetherai.zh-CN.mdx
@@ -10,61 +10,39 @@ tags:
# 在 LobeChat 中使用 Together AI
-
+
-[together.ai](https://www.together.ai/) 是一家专注于生成式人工智能(AIGC)领域的平台,成立于2022年6月。 它致力于构建用于运行、训练和微调开源模型的云平台,以低于主流供应商的价格提供可扩展的计算能力。
+[together.ai](https://www.together.ai/) 是一家专注于生成式人工智能 (AIGC) 领域的平台,成立于 2022 年 6 月。 它致力于构建用于运行、训练和微调开源模型的云平台,以低于主流供应商的价格提供可扩展的计算能力。
本文档将指导你如何在 LobeChat 中使用 Together AI:
+ ### 步骤一:获取 Together AI 的 API 密钥
-### 步骤一:获取 Together AI 的 API 密钥
+ - 访问并登录 [Together AI API](https://api.together.ai/)
+ - 初次登录时系统会自动为你创建好 API 密钥并赠送 $5.0 的额度
-- 访问并登录 [Together AI API](https://api.together.ai/)
-- 初次登录时系统会自动为你创建好 API 密钥并赠送 $5.0 的额度
+
-
+ - 如果你没有保存,也可以在后续任意时间,通过 `设置` 中的 `API 密钥` 界面查看
-- 如果你没有保存,也可以在后续任意时间,通过 `设置` 中的 `API 密钥` 界面查看
+
-
+ ### 步骤二:在 LobeChat 中配置 Together AI
-### 步骤二:在 LobeChat 中配置 Together AI
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`together.ai`的设置项
-- 访问LobeChat的`设置`界面
-- 在`语言模型`下找到`together.ai`的设置项
+
-
+ - 打开 together.ai 并填入获得的 API 密钥
+ - 为你的助手选择一个 Together AI 的模型即可开始对话
-- 打开 together.ai 并填入获得的 API 密钥
-- 为你的助手选择一个 Together AI 的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考 Together AI 的费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Together AI 的费用政策。
+
至此你已经可以在 LobeChat 中使用 Together AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/upstage.mdx b/DigitalHumanWeb/docs/usage/providers/upstage.mdx
new file mode 100644
index 0000000..cc22cc6
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/upstage.mdx
@@ -0,0 +1,47 @@
+---
+title: Using Upstage in LobeChat
+description: Learn how to integrate and utilize Upstage's language model APIs in LobeChat.
+tags:
+ - LobeChat
+ - Upstage
+ - API Key
+ - Web UI
+---
+
+# Using Upstage in LobeChat
+
+
+
+[Upstage](https://www.upstage.ai/) is a platform that offers AI models and services, focusing on applications in natural language processing and machine learning. It allows developers to access its powerful AI capabilities through APIs, supporting various tasks such as text generation and conversational systems.
+
+This article will guide you on how to use Upstage in LobeChat.
+
+
+ ### Step 1: Obtain an Upstage API Key
+
+ - Register and log in to the [Upstage Console](https://console.upstage.ai/home)
+ - Navigate to the `API Keys` page
+ - Create a new API key
+ - Copy and save the generated API key
+
+
+
+ ### Step 2: Configure Upstage in LobeChat
+
+ - Access the `Settings` interface in LobeChat
+ - Locate the `Upstage` settings under `Language Models`
+
+
+
+ - Enter the obtained API key
+ - Select an Upstage model for your AI assistant to start the conversation
+
+
+
+
+ Please note that you may need to pay the API service provider for usage. Refer to Upstage's
+ pricing policy for more information.
+
+
+
+You can now use the models provided by Upstage for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/upstage.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/upstage.zh-CN.mdx
new file mode 100644
index 0000000..7bc2f7c
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/upstage.zh-CN.mdx
@@ -0,0 +1,46 @@
+---
+title: 在 LobeChat 中使用 Upstage
+description: 学习如何在 LobeChat 中配置和使用 Upstage 的API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - Upstage
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Upstage
+
+
+
+[Upstage](https://www.upstage.ai/) 是一个提供 AI 模型和服务的平台,专注于自然语言处理和机器学习应用。它允许开发者通过 API 接入其强大的 AI 功能,支持多种任务,如文本生成、对话系统等。
+
+本文将指导你如何在 LobeChat 中使用 Upstage。
+
+
+ ### 步骤一:获得 Upstage 的 API Key
+
+ - 注册并登录 [Upstage 控制台](https://console.upstage.ai/home)
+ - 进入 `API Keys` 页面
+ - 创建一个新的 API 密钥
+ - 复制并保存生成的 API 密钥
+
+
+
+ ### 步骤二:在 LobeChat 中配置 Upstage
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `Upstage` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 Upstage 的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Upstage 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Upstage 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/vertexai.mdx b/DigitalHumanWeb/docs/usage/providers/vertexai.mdx
new file mode 100644
index 0000000..f1caf94
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/vertexai.mdx
@@ -0,0 +1,59 @@
+---
+title: Using Vertex AI API Key in LobeChat
+description: Learn how to configure and use Vertex AI models in LobeChat, get an API key, and start a conversation.
+tags:
+ - LobeChat
+ - Vertex AI
+ - API Key
+ - Web UI
+---
+
+# Using Vertex AI in LobeChat
+
+
+
+[Vertex AI](https://cloud.google.com/vertex-ai) is a fully managed, integrated AI development platform from Google Cloud, designed for building and deploying generative AI. It provides easy access to Vertex AI Studio, Agent Builder, and over 160 foundational models for AI development.
+
+This document will guide you on how to connect Vertex AI models in LobeChat:
+
+
+ ### Step 1: Prepare a Vertex AI Project
+
+ - First, visit [Google Cloud](https://console.cloud.google.com/) and complete the registration and login process.
+ - Create a new Google Cloud project or select an existing one.
+ - Go to the [Vertex AI Console](https://console.cloud.google.com/vertex-ai).
+ - Ensure that the Vertex AI API service is enabled for the project.
+
+
+
+ ### Step 2: Set Up API Access Permissions
+
+ - Go to the Google Cloud [IAM Management page](https://console.cloud.google.com/iam-admin/serviceaccounts) and navigate to `Service Accounts`.
+ - Create a new service account and assign a role permission to it, such as `Vertex AI User`.
+
+
+
+ - On the service account management page, find the service account you just created, click `Keys`, and create a new JSON format key.
+ - After successful creation, the key file will be automatically saved to your computer in JSON format. Please keep it safe.
+
+
+
+ ### Step 3: Configure Vertex AI in LobeChat
+
+ - Visit the `App Settings` and then the `AI Service Provider` interface in LobeChat.
+ - Find the settings item for `Vertex AI` in the list of providers.
+
+
+
+ - Open the Vertex AI service provider settings.
+ - Fill the entire content of the JSON format key you just obtained into the API Key field.
+ - Select a Vertex AI model for your assistant to start the conversation.
+
+
+
+
+ You may need to pay the API service provider during usage. Please refer to Google Cloud's relevant fee policies.
+
+
+
+Now you can use the models provided by Vertex AI for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/vertexai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/vertexai.zh-CN.mdx
new file mode 100644
index 0000000..41c8677
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/vertexai.zh-CN.mdx
@@ -0,0 +1,59 @@
+---
+title: 在 LobeChat 中使用 Vertex AI API Key
+description: 学习如何在 LobeChat 中配置和使用 Vertex AI 模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - Vertex AI
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 Vertex AI
+
+
+
+[Vertex AI](https://cloud.google.com/vertex-ai) 是 Google Cloud 的一款全面托管、集成的 AI 开发平台,旨在构建与应用生成式 AI。你可轻松访问 Vertex AI Studio、Agent Builder 以及超过 160 种基础模型,进行 AI 开发。
+
+本文档将指导你如何在 LobeChat 中接入 Vertex AI 的模型:
+
+
+ ### 步骤一:准备 Vertex AI 项目
+
+ - 首先,访问[Google Cloud](https://console.cloud.google.com/)并完成注册登录
+ - 创建一个新的 Google Cloud 项目,或选择一个已存在的项目
+ - 进入 [Vertex AI 控制台](https://console.cloud.google.com/vertex-ai)
+ - 确认该项目已开通 Vertex AI API 服务
+
+
+
+ ### 步骤二:设置 API 访问权限
+
+ - 进入 Google Cloud [IAM 管理页面](https://console.cloud.google.com/iam-admin/serviceaccounts),并导航至`服务账号`
+ - 创建一个新的服务账号,并为其分配一个角色权限,例如 `Vertex AI User`
+
+
+
+ - 在服务账号管理页面找到刚刚创建的服务账号,点击`密钥`并创建一个新的 JSON 格式密钥
+ - 创建成功后,密钥文件将会以 JSON 文件的格式自动保存到你的电脑上,请妥善保存
+
+
+
+ ### 步骤三:在 LobeChat 中配置 Vertex AI
+
+ - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+ - 在供应商列表中找到 `Vertex AI` 的设置项
+
+
+
+ - 打开 Vertex AI 服务供应商
+ - 将刚刚获取的 JSON 格式的全部内容填入 API Key 字段中
+ - 为你的助手选择一个 Vertex AI 模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 Google Cloud 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 Vertex AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/vllm.mdx b/DigitalHumanWeb/docs/usage/providers/vllm.mdx
new file mode 100644
index 0000000..f28d136
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/vllm.mdx
@@ -0,0 +1,98 @@
+---
+title: Using vLLM API Key in LobeChat
+description: Learn how to configure and use the vLLM language model in LobeChat, obtain an API key, and start a conversation.
+tags:
+ - LobeChat
+ - vLLM
+ - API Key
+ - Web UI
+---
+
+# Using vLLM in LobeChat
+
+
+
+[vLLM](https://github.com/vllm-project/vllm) is an open-source local large language model (LLM) deployment tool that allows users to efficiently run LLM models on local devices and provides an OpenAI API-compatible service interface.
+
+This document will guide you on how to use vLLM in LobeChat:
+
+
+ ### Step 1: Preparation
+
+ vLLM has certain requirements for hardware and software environments. Be sure to configure according to the following requirements:
+
+ | Hardware Requirements | |
+ | --------- | ----------------------------------------------------------------------- |
+ | GPU | - NVIDIA CUDA - AMD ROCm - Intel XPU |
+ | CPU | - Intel/AMD x86 - ARM AArch64 - Apple silicon |
+ | Other AI Accelerators | - Google TPU - Intel Gaudi - AWS Neuron - OpenVINO |
+
+ | Software Requirements |
+ | --------------------------------------- |
+ | - OS: Linux - Python: 3.9 – 3.12 |
+
+ ### Step 2: Install vLLM
+
+ If you are using an NVIDIA GPU, you can directly install vLLM using `pip`. However, it is recommended to use `uv` here, which is a very fast Python environment manager, to create and manage the Python environment. Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install uv. After installing uv, you can use the following command to create a new Python environment and install vLLM:
+
+ ```shell
+ uv venv myenv --python 3.12 --seed
+ source myenv/bin/activate
+ uv pip install vllm
+ ```
+
+ Another method is to use `uv run` with the `--with [dependency]` option, which allows you to run commands such as `vllm serve` without creating an environment:
+
+ ```shell
+ uv run --with vllm vllm --help
+ ```
+
+ You can also use [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/getting-started.html) to create and manage your Python environment.
+
+ ```shell
+ conda create -n myenv python=3.12 -y
+ conda activate myenv
+ pip install vllm
+ ```
+
+
+ For non-CUDA platforms, please refer to the [official documentation](https://docs.vllm.ai/en/latest/getting_started/installation/index.html#installation-index) to learn how to install vLLM.
+
+
+ ### Step 3: Start Local Service
+
+ vLLM can be deployed as an OpenAI API protocol-compatible server. By default, it will start the server at `http://localhost:8000`. You can specify the address using the `--host` and `--port` parameters. The server currently runs only one model at a time.
+
+ The following command will start a vLLM server and run the `Qwen2.5-1.5B-Instruct` model:
+
+ ```shell
+ vllm serve Qwen/Qwen2.5-1.5B-Instruct
+ ```
+
+ You can enable the server to check the API key in the header by passing the parameter `--api-key` or the environment variable `VLLM_API_KEY`. If not set, no API Key is required to access.
+
+
+ For more detailed vLLM server configuration, please refer to the [official documentation](https://docs.vllm.ai/en/latest/).
+
+
+ ### Step 4: Configure vLLM in LobeChat
+
+ - Access the `Application Settings` interface of LobeChat.
+ - Find the `vLLM` settings item under `Language Model`.
+
+
+
+ - Open the vLLM service provider and fill in the API service address and API Key.
+
+
+ * If your vLLM is not configured with an API Key, please leave the API Key blank.
+ * If your vLLM is running locally, please make sure to turn on `Client Request Mode`.
+
+
+ - Add the model you are running to the model list below.
+ - Select a vLLM model to run for your assistant and start the conversation.
+
+
+
+
+Now you can use the models provided by vLLM in LobeChat to have conversations.
diff --git a/DigitalHumanWeb/docs/usage/providers/vllm.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/vllm.zh-CN.mdx
new file mode 100644
index 0000000..010412e
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/vllm.zh-CN.mdx
@@ -0,0 +1,98 @@
+---
+title: 在 LobeChat 中使用 vLLM API Key
+description: 学习如何在 LobeChat 中配置和使用 vLLM 语言模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - vLLM
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 vLLM
+
+
+
+[vLLM](https://github.com/vllm-project/vllm)是一个开源的本地大型语言模型(LLM)部署工具,允许用户在本地设备上高效运行 LLM 模型,并提供兼容 OpenAI API 的服务接口。
+
+本文档将指导你如何在 LobeChat 中使用 vLLM:
+
+
+ ### 步骤一:准备工作
+
+ vLLM 对于硬件和软件环境均有一定要求,请无比根据以下要求进行配置:
+
+ | 硬件需求 | |
+ | --------- | ----------------------------------------------------------------------- |
+ | GPU | - NVIDIA CUDA - AMD ROCm - Intel XPU |
+ | CPU | - Intel/AMD x86 - ARM AArch64 - Apple silicon |
+ | 其他 AI 加速器 | - Google TPU - Intel Gaudi - AWS Neuron - OpenVINO |
+
+ | 软件需求 |
+ | --------------------------------------- |
+ | - OS: Linux - Python: 3.9 – 3.12 |
+
+ ### 步骤二:安装 vLLM
+
+ 如果你正在使用 NVIDIA GPU,你可以直接使用`pip`安装 vLLM。但这里建议使用`uv`,它一个非常快速的 Python 环境管理器,来创建和管理 Python 环境。请按照[文档](https://docs.astral.sh/uv/#getting-started)安装 uv。安装 uv 后,你可以使用以下命令创建一个新的 Python 环境并安装 vLLM:
+
+ ```shell
+ uv venv myenv --python 3.12 --seed
+ source myenv/bin/activate
+ uv pip install vllm
+ ```
+
+ 另一种方法是使用`uv run`与`--with [dependency]`选项,这允许你运行`vllm serve`等命令而无需创建环境:
+
+ ```shell
+ uv run --with vllm vllm --help
+ ```
+
+ 你也可以使用 [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/getting-started.html) 来创建和管理你的 Python 环境。
+
+ ```shell
+ conda create -n myenv python=3.12 -y
+ conda activate myenv
+ pip install vllm
+ ```
+
+
+ 对于非 CUDA 平台,请参考[官方文档](https://docs.vllm.ai/en/latest/getting_started/installation/index.html#installation-index)了解如何安装 vLLM
+
+
+ ### 步骤三:启动本地服务
+
+ vLLM 可以部署为一个 OpenAI API 协议兼容的服务器。默认情况下,它将在 `http://localhost:8000` 启动服务器。你可以使用 `--host` 和 `--port` 参数指定地址。服务器目前一次仅运行一个模型。
+
+ 以下命令将启动一个 vLLM 服务器并运行 `Qwen2.5-1.5B-Instruct` 模型:
+
+ ```shell
+ vllm serve Qwen/Qwen2.5-1.5B-Instruct
+ ```
+
+ 你可以通过传递参数 `--api-key` 或环境变量 `VLLM_API_KEY` 来启用服务器检查头部中的 API 密钥。如不设置,则无需 API Key 即可访问。
+
+
+ 更详细的 vLLM 服务器配置,请参考[官方文档](https://docs.vllm.ai/en/latest/)
+
+
+ ### 步骤四:在 LobeChat 中配置 vLLM
+
+ - 访问 LobeChat 的 `应用设置`界面
+ - 在 `语言模型` 下找到 `vLLM` 的设置项
+
+
+
+ - 打开 vLLM 服务商并填入 API 服务地址以及 API Key
+
+
+ * 如果你的 vLLM 没有配置 API Key,请将 API Key 留空
+ * 如果你的 vLLM 运行在本地,请确保打开`客户端请求模式`
+
+
+ - 在下方的模型列表中添加你运行的模型
+ - 为你的助手选择一个 vLLM 运行的模型即可开始对话
+
+
+
+
+至此你已经可以在 LobeChat 中使用 vLLM 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/volcengine.mdx b/DigitalHumanWeb/docs/usage/providers/volcengine.mdx
new file mode 100644
index 0000000..5a75ba1
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/volcengine.mdx
@@ -0,0 +1,47 @@
+---
+title: Using the Volcano Engine API Key in LobeChat
+description: Learn how to configure and use the Volcano Engine AI model in LobeChat, obtain API keys, and start conversations.
+tags:
+ - LobeChat
+ - Volcengine
+ - Doubao
+ - API Key
+ - Web UI
+---
+# Using Volcengine in LobeChat
+
+
+
+[Volcengine](https://www.volcengine.com/) is a cloud service platform under ByteDance that provides large language model (LLM) services through "Volcano Ark," supporting multiple mainstream models such as Baichuan Intelligent, Mobvoi, and more.
+
+This document will guide you on how to use Volcengine in LobeChat:
+
+
+ ### Step 1: Obtain the Volcengine API Key
+ - First, visit the [Volcengine official website](https://www.volcengine.com/) and complete the registration and login process.
+ - Access the Volcengine console and navigate to [Volcano Ark](https://console.volcengine.com/ark/).
+
+
+
+- Go to the `API Key Management` menu and click `Create API Key`.
+- Copy and save the created API Key.
+
+### Step 2: Configure Volcengine in LobeChat
+
+- Navigate to the `Application Settings` page in LobeChat and select `AI Service Providers`.
+- Find the `Volcengine` option in the provider list.
+
+
+
+- Open the Volcengine service provider and enter the obtained API Key.
+- Choose a Volcengine model for your assistant to start the conversation.
+
+
+
+
+During usage, you may need to pay the API service provider, so please refer to Volcengine's pricing policy.
+
+
+
+
+You can now use the models provided by Volcengine for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/volcengine.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/volcengine.zh-CN.mdx
new file mode 100644
index 0000000..9cc835e
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/volcengine.zh-CN.mdx
@@ -0,0 +1,48 @@
+---
+title: 在 LobeChat 中使用火山引擎 API Key
+description: 学习如何在 LobeChat 中配置和使用火山引擎 AI 模型,获取 API 密钥并开始对话。
+tags:
+ - LobeChat
+ - 火山引擎
+ - 豆包
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用火山引擎
+
+
+
+[火山引擎](https://www.volcengine.com/)是字节跳动旗下的云服务平台,通过 "火山方舟" 提供大型语言模型 (LLM) 服务,支持多个主流模型如百川智能、Mobvoi 等。
+
+本文档将指导你如何在 LobeChat 中使用火山引擎:
+
+
+ ### 步骤一:获取火山引擎 API 密钥
+
+ - 首先,访问[火山引擎官网](https://www.volcengine.com/)并完成注册登录
+ - 进入火山引擎控制台并导航至[火山方舟](https://console.volcengine.com/ark/)
+
+
+
+ - 进入 `API key 管理` 菜单,并点击 `创建 API Key`
+ - 复制并保存创建好的 API Key
+
+ ### 步骤二:在 LobeChat 中配置火山引擎
+
+ - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+ - 在供应商列表中找到 `火山引擎` 的设置项
+
+
+
+ - 打开火山引擎服务商并填入获取的 API 密钥
+ - 为你的助手选择一个火山引擎模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考火山引擎的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用火山引擎提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/wenxin.mdx b/DigitalHumanWeb/docs/usage/providers/wenxin.mdx
new file mode 100644
index 0000000..42ca5df
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/wenxin.mdx
@@ -0,0 +1,59 @@
+---
+title: Using Wenxin Qianfan in LobeChat
+description: >-
+ Learn how to integrate and utilize Wenxin Qianfan's language model APIs in
+ LobeChat.
+tags:
+ - LobeChat
+ - 百度
+ - 文心千帆
+ - API密钥
+ - Web UI
+---
+
+# Using Wenxin Qianfan in LobeChat
+
+
+
+[Wenxin Qianfan](https://qianfan.cloud.baidu.com/) is an artificial intelligence large language model platform launched by Baidu, supporting a variety of application scenarios, including literary creation, commercial copywriting, and mathematical logic reasoning. The platform features deep semantic understanding and generation capabilities across modalities and languages, and it is widely utilized in fields such as search Q\&A, content creation, and smart office applications.
+
+This article will guide you on how to use Wenxin Qianfan in LobeChat.
+
+
+ ### Step 1: Obtain the Wenxin Qianfan API Key
+
+ - Register and log in to the [Baidu AI Cloud Console](https://console.bce.baidu.com/)
+ - Navigate to `Baidu AI Cloud Qianfan ModelBuilder`
+ - Select `API Key` from the left menu
+
+
+
+ - Click `Create API Key`
+ - In `Service`, select `Qianfan ModelBuilder`
+ - In `Resource`, choose `All Resources`
+ - Click the `Confirm` button
+ - Copy the `API Key` and keep it safe
+
+
+
+
+
+ ### Step 2: Configure Wenxin Qianfan in LobeChat
+
+ - Go to the `Settings` page of LobeChat
+ - Under `Language Models`, find the `Wenxin Qianfan` settings
+
+
+
+ - Enter the obtained `API Key`
+ - Select a Wenxin Qianfan model for your AI assistant, and you're ready to start chatting!
+
+
+
+
+ During usage, you may need to pay the API service provider. Please refer to Wenxin Qianfan's
+ relevant fee policy.
+
+
+
+You can now use the models provided by Wenxin Qianfan for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/wenxin.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/wenxin.zh-CN.mdx
new file mode 100644
index 0000000..318e61d
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/wenxin.zh-CN.mdx
@@ -0,0 +1,56 @@
+---
+title: 在 LobeChat 中使用文心千帆
+description: 学习如何在 LobeChat 中配置和使用文心千帆的API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - 百度
+ - 文心千帆
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用文心千帆
+
+
+
+[文心千帆](https://qianfan.cloud.baidu.com/)是百度推出的一个人工智能大语言模型平台,支持多种应用场景,包括文学创作、商业文案生成、数理逻辑推算等。该平台具备跨模态、跨语言的深度语义理解与生成能力,广泛应用于搜索问答、内容创作和智能办公等领域。
+
+本文将指导你如何在 LobeChat 中使用文心千帆。
+
+
+ ### 步骤一:获得文心千帆的 API Key
+
+ - 注册并登录 [百度智能云控制台](https://console.bce.baidu.com/)
+ - 进入 `百度智能云千帆 ModelBuilder`
+ - 在左侧菜单中选择 `API Key`
+
+
+
+ - 点击创建 API Key
+ - 在 `服务` 中选择 `千帆ModelBuilder`
+ - 在 `资源` 中选择 `所有资源`
+ - 点击 `确定` 按钮
+ - 复制 `API Key` 并妥善保存
+
+
+
+
+
+ ### 步骤二:在 LobeChat 中配置文心千帆
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `文心千帆` 的设置项
+
+
+
+ - 填入获得的 `API Key`
+ - 为你的 AI 助手选择一个文心千帆的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考文心千帆的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用文心千帆提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/xai.mdx b/DigitalHumanWeb/docs/usage/providers/xai.mdx
new file mode 100644
index 0000000..f04d371
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/xai.mdx
@@ -0,0 +1,53 @@
+---
+title: Using xAI in LobeChat
+description: >-
+ Learn how to configure and use xAI's API Key in LobeChat to start
+ conversations and interactions.
+tags:
+ - LobeChat
+ - xAI
+ - API Key
+ - Web UI
+---
+
+# Using xAI in LobeChat
+
+
+
+[xAI](https://x.ai/) is an artificial intelligence company founded by Elon Musk in 2023, aimed at exploring and understanding the true nature of the universe. The company's mission is to solve complex scientific and mathematical problems using AI technology and to advance the field of artificial intelligence.
+
+This article will guide you on how to use xAI in LobeChat.
+
+
+ ### Step 1: Obtain an API Key from xAI
+
+ - Register and login to the [xAI console](https://console.x.ai/)
+ - Create an API token
+ - Copy and save the API token
+
+
+
+
+ Make sure to securely save the API token displayed in the popup; it only appears once. If you
+ accidentally lose it, you will need to create a new API token.
+
+
+ ### Step 2: Configure xAI in LobeChat
+
+ - Go to the `Settings` menu in LobeChat
+ - Locate the `xAI` settings under `Language Model`
+
+
+
+ - Enter the API key you obtained
+ - Select an xAI model for your AI assistant to start a conversation
+
+
+
+
+ During use, you may need to pay the API service provider, so please refer to xAI's relevant
+ pricing policies.
+
+
+
+You are now ready to engage in conversations using the models provided by xAI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/xai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/xai.zh-CN.mdx
new file mode 100644
index 0000000..ed65cfc
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/xai.zh-CN.mdx
@@ -0,0 +1,49 @@
+---
+title: 在 LobeChat 中使用 xAI
+description: 学习如何在 LobeChat 中配置和使用 xAI 的 API Key,以便开始对话和交互。
+tags:
+ - LobeChat
+ - xAI
+ - API密钥
+ - Web UI
+---
+
+# 在 LobeChat 中使用 xAI
+
+
+
+[xAI](https://x.ai/) 是由埃隆・马斯克于 2023 年成立的一家人工智能公司,旨在探索和理解宇宙的真实本质。该公司的目标是通过人工智能技术解决复杂的科学和数学问题,并推动人工智能的发展。
+
+本文将指导你如何在 LobeChat 中使用 xAI。
+
+
+ ### 步骤一:获取 xAI 的 API 密钥
+
+ - 注册并登录 [xAI 控制台](https://console.x.ai/)
+ - 创建一个 API Token
+ - 复制并保存 API Token
+
+
+
+
+ 妥善保存弹窗中的 API 令牌,它只会出现一次,如果不小心丢失了,你需要重新创建一个 API 令牌。
+
+
+ ### 步骤二:在 LobeChat 中配置 xAI
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到 `xAI` 的设置项
+
+
+
+ - 填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 xAI 的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考 xAI 的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用 xAI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/zeroone.mdx b/DigitalHumanWeb/docs/usage/providers/zeroone.mdx
new file mode 100644
index 0000000..87baaf8
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/zeroone.mdx
@@ -0,0 +1,58 @@
+---
+title: Using 01 AI API Key in LobeChat
+description: >-
+ Learn how to integrate and use 01 AI in LobeChat with step-by-step
+ instructions. Obtain an API key, configure 01 AI, and start conversations with
+ AI models.
+tags:
+ - 01.AI
+ - Web UI
+ - API key
+ - AI models
+---
+
+# Using 01 AI in LobeChat
+
+
+
+[01 AI](https://www.01.ai/) is a global company dedicated to AI 2.0 large model technology and applications. Its billion-parameter Yi-Large closed-source model, when evaluated on Stanford University's English ranking AlpacaEval 2.0, is on par with GPT-4.
+
+This document will guide you on how to use 01 AI in LobeChat:
+
+
+ ### Step 1: Obtain 01 AI API Key
+
+ - Register and log in to the [01 AI Large Model Open Platform](https://platform.lingyiwanwu.com/)
+ - Go to the `Dashboard` and access the `API Key Management` menu
+ - A system-generated API key has been created for you automatically, or you can create a new one on this interface
+
+
+
+ - Account verification is required for first-time use
+
+
+
+ - Click on the created API key
+ - Copy and save the API key in the pop-up dialog box
+
+
+
+ ### Step 2: Configure 01 AI in LobeChat
+
+ - Access the `Settings` interface in LobeChat
+ - Find the setting for `01 AI` under `Language Model`
+
+
+
+ - Open 01 AI and enter the obtained API key
+ - Choose a 01.AI model for your AI assistant to start the conversation
+
+
+
+
+ During usage, you may need to pay the API service provider. Please refer to 01 AI's relevant fee
+ policies.
+
+
+
+You can now use the models provided by 01 AI for conversations in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/zeroone.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/zeroone.zh-CN.mdx
new file mode 100644
index 0000000..3461539
--- /dev/null
+++ b/DigitalHumanWeb/docs/usage/providers/zeroone.zh-CN.mdx
@@ -0,0 +1,59 @@
+---
+title: 在 LobeChat 中使用 01.AI 零一万物 API Key
+description: >-
+ 学习如何在 LobeChat 中配置并使用 01.AI 零一万物提供的 AI 模型进行对话。获取 API 密钥、填入设置项、选择模型,开始与 AI
+ 助手交流。
+tags:
+ - LobeChat
+ - 01.AI
+ - Zero One AI
+ - 零一万物
+ - Web UI
+ - API密钥
+ - 配置指南
+---
+
+# 在 LobeChat 中使用零一万物
+
+
+
+[零一万物](https://www.01.ai/)是一家致力于 AI 2.0 大模型技术和应用的全球公司,其发布的千亿参数的 Yi-Large 闭源模型,在斯坦福大学的英语排行 AlpacaEval 2.0 上,与 GPT-4 互有第一。
+
+本文档将指导你如何在 LobeChat 中使用零一万物:
+
+
+ ### 步骤一:获取零一万物 API 密钥
+
+ - 注册并登录 [零一万物大模型开放平台](https://platform.lingyiwanwu.com/)
+ - 进入`工作台`并访问`API Key管理`菜单
+ - 系统已为你自动创建了一个 API 密钥,你也可以在此界面创建新的 API 密钥
+
+
+
+ - 初次使用时需要完成账号认证
+
+
+
+ - 点击创建好的 API 密钥
+ - 在弹出的对话框中复制并保存 API 密钥
+
+
+
+ ### 步骤二:在 LobeChat 中配置零一万物
+
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`零一万物`的设置项
+
+
+
+ - 打开零一万物并填入获得的 API 密钥
+ - 为你的 AI 助手选择一个 01.AI 的模型即可开始对话
+
+
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考零一万物的相关费用政策。
+
+
+
+至此你已经可以在 LobeChat 中使用零一万物提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/providers/zhipu.mdx b/DigitalHumanWeb/docs/usage/providers/zhipu.mdx
index 048cc6c..c2b2de3 100644
--- a/DigitalHumanWeb/docs/usage/providers/zhipu.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/zhipu.mdx
@@ -13,55 +13,37 @@ tags:
# Using Zhipu ChatGLM in LobeChat
-
+
[Zhipu AI](https://www.zhipuai.cn/) is a high-tech company originating from the Department of Computer Science at Tsinghua University. Established in 2019, the company focuses on natural language processing, machine learning, and big data analysis, dedicated to expanding the boundaries of artificial intelligence technology in the field of cognitive intelligence.
This document will guide you on how to use Zhipu AI in LobeChat:
+ ### Step 1: Obtain the API Key for Zhipu AI
-### Step 1: Obtain the API Key for Zhipu AI
+ - Visit and log in to the [Zhipu AI Open Platform](https://open.bigmodel.cn/)
+ - Upon initial login, the system will automatically create an API key for you and gift you a resource package of 25M Tokens
+ - Navigate to the `API Key` section at the top to view your API key
-- Visit and log in to the [Zhipu AI Open Platform](https://open.bigmodel.cn/)
-- Upon initial login, the system will automatically create an API key for you and gift you a resource package of 25M Tokens
-- Navigate to the `API Key` section at the top to view your API key
+
-
+ ### Step 2: Configure Zhipu AI in LobeChat
-### Step 2: Configure Zhipu AI in LobeChat
+ - Visit the `Settings` interface in LobeChat
+ - Under `Language Model`, locate the settings for Zhipu AI
-- Visit the `Settings` interface in LobeChat
-- Under `Language Model`, locate the settings for Zhipu AI
+
-
+ - Open Zhipu AI and enter the obtained API key
+ - Choose a Zhipu AI model for your assistant to start the conversation
-- Open Zhipu AI and enter the obtained API key
-- Choose a Zhipu AI model for your assistant to start the conversation
-
-
-
-
- During usage, you may need to pay the API service provider, please refer to Zhipu AI's pricing
- policy.
-
+
+
+ During usage, you may need to pay the API service provider, please refer to Zhipu AI's pricing
+ policy.
+
You can now engage in conversations using the models provided by Zhipu AI in LobeChat.
diff --git a/DigitalHumanWeb/docs/usage/providers/zhipu.zh-CN.mdx b/DigitalHumanWeb/docs/usage/providers/zhipu.zh-CN.mdx
index 811b426..12fb801 100644
--- a/DigitalHumanWeb/docs/usage/providers/zhipu.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/providers/zhipu.zh-CN.mdx
@@ -10,52 +10,36 @@ tags:
# 在 LobeChat 中使用智谱 ChatGLM
-
+
-[智谱AI](https://www.zhipuai.cn/) 是一家源自清华大学计算机系技术成果的高科技公司,成立于2019年,专注于自然语言处理、机器学习和大数据分析,致力于在认知智能领域拓展人工智能技术的边界。
+[智谱 AI](https://www.zhipuai.cn/) 是一家源自清华大学计算机系技术成果的高科技公司,成立于 2019 年,专注于自然语言处理、机器学习和大数据分析,致力于在认知智能领域拓展人工智能技术的边界。
本文档将指导你如何在 LobeChat 中使用智谱 AI:
+ ### 步骤一:获取智谱 AI 的 API 密钥
-### 步骤一:获取智谱 AI 的 API 密钥
+ - 访问并登录 [智谱 AI 开放平台](https://open.bigmodel.cn/)
+ - 初次登录时系统会自动为你创建好 API 密钥并赠送 25M Tokens 的资源包
+ - 进入顶部的 `API密钥` 可以查看你的 API
-- 访问并登录 [智谱AI开放平台](https://open.bigmodel.cn/)
-- 初次登录时系统会自动为你创建好 API 密钥并赠送 25M Tokens 的资源包
-- 进入顶部的 `API密钥` 可以查看你的 API
+
-
+ ### 步骤二:在 LobeChat 中配置智谱 AI
-### 步骤二:在 LobeChat 中配置智谱AI
+ - 访问 LobeChat 的`设置`界面
+ - 在`语言模型`下找到`智谱AI`的设置项
-- 访问LobeChat的`设置`界面
-- 在`语言模型`下找到`智谱AI`的设置项
+
-
+ - 打开智谱 AI 并填入获得的 API 密钥
+ - 为你的助手选择一个智谱 AI 的模型即可开始对话
-- 打开智谱 AI 并填入获得的 API 密钥
-- 为你的助手选择一个智谱AI的模型即可开始对话
-
-
-
-
- 在使用过程中你可能需要向 API 服务提供商付费,请参考智谱AI的费用政策。
-
+
+
+ 在使用过程中你可能需要向 API 服务提供商付费,请参考智谱 AI 的费用政策。
+
-至此你已经可以在 LobeChat 中使用智谱AI提供的模型进行对话了。
+至此你已经可以在 LobeChat 中使用智谱 AI 提供的模型进行对话了。
diff --git a/DigitalHumanWeb/docs/usage/start.mdx b/DigitalHumanWeb/docs/usage/start.mdx
index 856a6a3..78c6a33 100644
--- a/DigitalHumanWeb/docs/usage/start.mdx
+++ b/DigitalHumanWeb/docs/usage/start.mdx
@@ -16,33 +16,48 @@ tags:
# ✨ Feature Overview
-
-
-
-
-## Experience Features
-
-
+## 2024 Overview
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+## 2023 Overview
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/DigitalHumanWeb/docs/usage/start.zh-CN.mdx b/DigitalHumanWeb/docs/usage/start.zh-CN.mdx
index 421df1a..3177146 100644
--- a/DigitalHumanWeb/docs/usage/start.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/start.zh-CN.mdx
@@ -14,27 +14,48 @@ tags:
# ✨ LobeChat 功能特性一览
-
-
-
-
-## 体验特性
-
-
+## 2024 特性一览
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+## 2023 特性一览
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/DigitalHumanWeb/docs/usage/tools-calling.mdx b/DigitalHumanWeb/docs/usage/tools-calling.mdx
index 490bb8b..acc025d 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling.mdx
@@ -1,3 +1,12 @@
+---
+title: Tools Calling
+description: Discover the best tools to enhance your calling experience and productivity.
+tags:
+ - Calling Tools
+ - Productivity
+ - Communication
+---
+
# Tools Calling
TODO
diff --git a/DigitalHumanWeb/docs/usage/tools-calling.zh-CN.mdx b/DigitalHumanWeb/docs/usage/tools-calling.zh-CN.mdx
index 8b37f6c..92ef954 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling.zh-CN.mdx
@@ -27,76 +27,71 @@ LobeChat 的插件实现基于模型的 Tools Calling 能力,模型本身的 T
我们基于实际真实的用户场景出发构建了两大组测试任务,第一组为简单的调用指令(天气查询),第二组为复杂调用指令(文生图)。这两组指令的系统描述如下:
-
-
-```md
-## Tools
-
-You can use these tools below:
-
-### Realtime Weather
-
-Get realtime weather information
-
-The APIs you can use:
+
+ ```md
+ ## Tools
-#### `realtime-weather____fetchCurrentWeather`
+ You can use these tools below:
-获取当前天气情况
-```
+ ### Realtime Weather
-
+ Get realtime weather information
-
+ The APIs you can use:
-```md
-## Tools
+ #### `realtime-weather____fetchCurrentWeather`
-You can use these tools below:
+ 获取当前天气情况
+ ```
+
-### DALL·E 3
+
+ ```md
+ ## Tools
-Whenever a description of an image is given, use lobe-image-designer to create the images and then summarize the prompts used to generate the images in plain text. If the user does not ask for a specific number of images, default to creating four captions to send to lobe-image-designer that are written to be as diverse as possible.
+ You can use these tools below:
-All captions sent to lobe-image-designer must abide by the following policies:
+ ### DALL·E 3
-1. If the description is not in English, then translate it.
-2. Do not create more than 4 images, even if the user requests more.
-3. Don't create images of politicians or other public figures. Recommend other ideas instead.
-4. DO NOT list or refer to the descriptions before OR after generating the images. They should ONLY ever be written out ONCE, in the `prompts` field of the request. You do not need to ask for permission to generate, just do it!
-5. Always mention the image type (photo, oil painting, watercolor painting, illustration, cartoon, drawing, vector, render, etc.) at the beginning of the caption. Unless the caption suggests otherwise, make at least 1--2 of the 4 images photos.
-6. Diversify depictions of ALL images with people to include DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions.
+ Whenever a description of an image is given, use lobe-image-designer to create the images and then summarize the prompts used to generate the images in plain text. If the user does not ask for a specific number of images, default to creating four captions to send to lobe-image-designer that are written to be as diverse as possible.
-- EXPLICITLY specify these attributes, not abstractly reference them. The attributes should be specified in a minimal way and should directly describe their physical form.
-- Your choices should be grounded in reality. For example, all of a given OCCUPATION should not be the same gender or race. Additionally, focus on creating diverse, inclusive, and exploratory scenes via the properties you choose during rewrites. Make choices that may be insightful or unique sometimes.
-- Use "various" or "diverse" ONLY IF the description refers to groups of more than 3 people. Do not change the number of people requested in the original description.
-- Don't alter memes, fictional character origins, or unseen people. Maintain the original prompt's intent and prioritize quality.
-- Do not create any imagery that would be offensive.
+ All captions sent to lobe-image-designer must abide by the following policies:
-8. Silently modify descriptions that include names or hints or references of specific people or celebrities by carefully selecting a few minimal modifications to substitute references to the people with generic descriptions that don't divulge any information about their identities, except for their genders and physiques. Do this EVEN WHEN the instructions ask for the prompt to not be changed. Some special cases:
+ 1. If the description is not in English, then translate it.
+ 2. Do not create more than 4 images, even if the user requests more.
+ 3. Don't create images of politicians or other public figures. Recommend other ideas instead.
+ 4. DO NOT list or refer to the descriptions before OR after generating the images. They should ONLY ever be written out ONCE, in the `prompts` field of the request. You do not need to ask for permission to generate, just do it!
+ 5. Always mention the image type (photo, oil painting, watercolor painting, illustration, cartoon, drawing, vector, render, etc.) at the beginning of the caption. Unless the caption suggests otherwise, make at least 1--2 of the 4 images photos.
+ 6. Diversify depictions of ALL images with people to include DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions.
-- Modify such prompts even if you don't know who the person is, or if their name is misspelled (e.g. "Barake Obema")
-- If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it.
-- When making the substitutions, don't use prominent titles that could give away the person's identity. E.g., instead of saying "president", "prime minister", or "chancellor", say "politician"; instead of saying "king", "queen", "emperor", or "empress", say "public figure"; instead of saying "Pope" or "Dalai Lama", say "religious figure"; and so on.
-- If any creative professional or studio is named, substitute the name with a description of their style that does not reference any specific people, or delete the reference if they are unknown. DO NOT refer to the artist or studio's style.
+ - EXPLICITLY specify these attributes, not abstractly reference them. The attributes should be specified in a minimal way and should directly describe their physical form.
+ - Your choices should be grounded in reality. For example, all of a given OCCUPATION should not be the same gender or race. Additionally, focus on creating diverse, inclusive, and exploratory scenes via the properties you choose during rewrites. Make choices that may be insightful or unique sometimes.
+ - Use "various" or "diverse" ONLY IF the description refers to groups of more than 3 people. Do not change the number of people requested in the original description.
+ - Don't alter memes, fictional character origins, or unseen people. Maintain the original prompt's intent and prioritize quality.
+ - Do not create any imagery that would be offensive.
-The prompt must intricately describe every part of the image in concrete, objective detail. THINK about what the end goal of the description is, and extrapolate that to what would make satisfying images. All descriptions sent to lobe-image-designer should be a paragraph of text that is extremely descriptive and detailed. Each should be more than 3 sentences long.
+ 8. Silently modify descriptions that include names or hints or references of specific people or celebrities by carefully selecting a few minimal modifications to substitute references to the people with generic descriptions that don't divulge any information about their identities, except for their genders and physiques. Do this EVEN WHEN the instructions ask for the prompt to not be changed. Some special cases:
-The APIs you can use:
+ - Modify such prompts even if you don't know who the person is, or if their name is misspelled (e.g. "Barake Obema")
+ - If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it.
+ - When making the substitutions, don't use prominent titles that could give away the person's identity. E.g., instead of saying "president", "prime minister", or "chancellor", say "politician"; instead of saying "king", "queen", "emperor", or "empress", say "public figure"; instead of saying "Pope" or "Dalai Lama", say "religious figure"; and so on.
+ - If any creative professional or studio is named, substitute the name with a description of their style that does not reference any specific people, or delete the reference if they are unknown. DO NOT refer to the artist or studio's style.
-#### `lobe-image-designer____text2image____builtin`
+ The prompt must intricately describe every part of the image in concrete, objective detail. THINK about what the end goal of the description is, and extrapolate that to what would make satisfying images. All descriptions sent to lobe-image-designer should be a paragraph of text that is extremely descriptive and detailed. Each should be more than 3 sentences long.
-Create images from a text-only prompt.
-```
+ The APIs you can use:
-
+ #### `lobe-image-designer____text2image____builtin`
+ Create images from a text-only prompt.
+ ```
+
-如上所示,简单调用指令在插件调用时它的系统描述(system role)相对简单,复杂调用指令的系统描述会复杂很多。这两组不同复杂度的指令可以比较好地区分出模型对于系统指令的遵循能力:
+如上所示,简单调用指令在插件调用时它的系统描述 (system role) 相对简单,复杂调用指令的系统描述会复杂很多。这两组不同复杂度的指令可以比较好地区分出模型对于系统指令的遵循能力:
- **天气查询可以测试模型的基础 Tools Calling 能力,确认模型是否存在「虚假宣传」的情况。** 就我们实际的测试来看,的确存在一些模型号称具有 Tools Calling 能力,但是处于完全不可用的状态;
-- **文生图可以测试模型指令跟随能力的上限。** 例如基础模型(例如 GPT-3.5)可能只能生成 1 张图片的 prompt,而高级模型(例如 GPT-4o)则能够生成 1~4 张图片的 prompt。
+- **文生图可以测试模型指令跟随能力的上限。** 例如基础模型(例如 GPT-3.5)可能只能生成 1 张图片的 prompt,而高级模型(例如 GPT-4o)则能够生成 1\~4 张图片的 prompt。
### 简单调用指令:天气查询
@@ -126,11 +121,11 @@ Create images from a text-only prompt.
针对这一个工具,我们构建的测试组中包含了三个指令:
-| 指令编号 | 指令内容 | 基础 Tools Calling 调用 | 并发调用 | 复合指令跟随 |
-| --- | --- | --- | --- | --- |
-| 指令 ① | 告诉我杭州和北京的天气,先回答我好的 | 🟢 | 🟢 | 🟢 |
-| 指令 ② | 告诉我杭州和北京的天气 | 🟢 | 🟢 | - |
-| 指令 ③ | 告诉我杭州的天气 | 🟢 | - | - |
+| 指令编号 | 指令内容 | 基础 Tools Calling 调用 | 并发调用 | 复合指令跟随 |
+| ---- | ------------------ | ------------------- | ---- | ------ |
+| 指令 ① | 告诉我杭州和北京的天气,先回答我好的 | 🟢 | 🟢 | 🟢 |
+| 指令 ② | 告诉我杭州和北京的天气 | 🟢 | 🟢 | - |
+| 指令 ③ | 告诉我杭州的天气 | 🟢 | - | - |
上述三个指令的复杂度逐渐递减,我们可以通过这三个指令来测试模型对于简单指令的处理能力。
@@ -147,30 +142,26 @@ Create images from a text-only prompt.
-
根据我们实际的日常使用,工具调用往往会和普通文本生成结合在一起回答。例如比较经典的 Code Interpreter 插件,ChatGPT 往往会先回复一些代码生成的思路,然后再调用 Code Interpreter 插件生成代码。
这种情况下,我们需要模型能够正确地识别出用户的意图,然后调用对应的工具。
因此, 指令 ① 中的「告诉我杭州和北京的天气,先回答我好的」就是一个复合指令跟随的例子。前半句期望模型调用天气查询工具,后半句期望模型回答「好的」。并且理想的顺序应该是先回答「好的」,然后再调用天气查询工具。
+
-
-
并发工具调用(Parallel function calling)是指模型能够同时调用多个工具,或同时调用一个工具多次,这在对话中可以大大降低用户等待的时间,提升用户体验。
- 并发工具调用能力由 OpenAI 于 2023年11月率先提出,目前支持并发工具调用的模型并不算多,属于是 Tools Calling 的进阶能力。
+ 并发工具调用能力由 OpenAI 于 2023 年 11 月率先提出,目前支持并发工具调用的模型并不算多,属于是 Tools Calling 的进阶能力。
指令 ② 中的「告诉我杭州和北京的天气」就是一个期望执行并发调用的例子。理想的情况下,单个模型的返回应该存在两个工具的调用返回。
+
-
-
基础工具调用不必再赘述,这是 Tools Calling 的基础能力。
指令 ③ 中的「告诉我杭州的天气」就是最基本的工具调用的例子。
-
-
+
### 复杂调用指令:文生图
@@ -229,10 +220,10 @@ Create images from a text-only prompt.
针对这一个工具,我们构建的测试组中包含了两个指令:
-| 指令编号 | 指令内容 | 流式调用 | 复杂 Tools Calling 调用 | 并发调用 | 复合指令跟随 |
-| --- | --- | --- | --- | --- | --- |
-| 指令 ① | 我要画 3 幅画,第一幅画的主体为一只达芬奇风格的小狗,第二幅是毕加索风格的大雁,最后一幅是莫奈风格的狮子。每一幅都需要产出 2 个 prompts。请先说明你的构思,然后开始生成相应的图片。 | 🟢 | 🟢 | 🟢 | 🟢 |
-| 指令 ② | 画一只小狗 | 🟢 | 🟢 | - | - |
+| 指令编号 | 指令内容 | 流式调用 | 复杂 Tools Calling 调用 | 并发调用 | 复合指令跟随 |
+| ---- | ------------------------------------------------------------------------------------------------ | ---- | ------------------- | ---- | ------ |
+| 指令 ① | 我要画 3 幅画,第一幅画的主体为一只达芬奇风格的小狗,第二幅是毕加索风格的大雁,最后一幅是莫奈风格的狮子。每一幅都需要产出 2 个 prompts。请先说明你的构思,然后开始生成相应的图片。 | 🟢 | 🟢 | 🟢 | 🟢 |
+| 指令 ② | 画一只小狗 | 🟢 | 🟢 | - | - |
此外,由于文生图的 prompts 的生成时间较长,这一组指令也可以清晰地测试出模型的 API 是否支持流式 Tools Calling。
@@ -242,12 +233,13 @@ Create images from a text-only prompt.
+
+
-
+
+
+
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/anthropic.mdx b/DigitalHumanWeb/docs/usage/tools-calling/anthropic.mdx
index a6ed471..37876a6 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/anthropic.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/anthropic.mdx
@@ -15,12 +15,12 @@ tags:
Overview of Anthropic Claude Series model Tools Calling capabilities:
-| Model | Support Tools Calling | Stream | Parallel | Simple Instruction Score | Complex Instruction |
-| --- | --- | --- | --- | --- | --- |
-| Claude 3.5 Sonnet | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
-| Claude 3 Opus | ✅ | ✅ | ❌ | 🌟 | ⛔️ |
-| Claude 3 Sonnet | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
-| Claude 3 Haiku | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
+| Model | Support Tools Calling | Stream | Parallel | Simple Instruction Score | Complex Instruction |
+| ----------------- | --------------------- | ------ | -------- | ------------------------ | ------------------- |
+| Claude 3.5 Sonnet | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
+| Claude 3 Opus | ✅ | ✅ | ❌ | 🌟 | ⛔️ |
+| Claude 3 Sonnet | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
+| Claude 3 Haiku | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
## Claude 3.5 Sonnet
@@ -30,18 +30,13 @@ Test Instruction: Instruction ①
-
+Tools Calling Raw Output:
-```yml
-
-```
-
+ ```yml
+ ```
### Complex Instruction Call: Literary Map
@@ -55,18 +50,13 @@ From the above video:
1. Sonnet 3.5 supports Stream Tools Calling and Parallel Tools Calling;
2. In Stream Tools Calling, it is observed that creating long sentences will cause a delay (as seen in the Tools Calling raw output `[chunk 40]` and `[chunk 41]` with a delay of 6s). Therefore, there will be a relatively long waiting time at the beginning stage of Tools Calling.
-
+Tools Calling Raw Output:
-```yml
-
-```
-
+ ```yml
+ ```
## Claude 3 Opus
@@ -83,14 +73,10 @@ From the above video:
2. Opus triggers Tools Calling twice, indicating that it does not support Parallel Tools Calling;
3. The raw output of Tools Calling shows that Opus also supports Stream Tools Calling.
-
+Tools Calling Raw Output:
-
### Complex Instruction Call: Literary Map
@@ -104,14 +90,10 @@ From the above video:
1. Combining with simple tasks, Opus will always output a `` tag, which significantly impacts the user experience;
2. Opus outputs the prompts field as a string instead of an array, causing an error and preventing the plugin from being called correctly.
-
+Tools Calling Raw Output:
-
## Claude 3 Sonnet
@@ -124,14 +106,10 @@ Test Instruction: Instruction ①
From the above video, it can be seen that Claude 3 Sonnet triggers Tools Calling twice, indicating that it does not support Parallel Tools Calling.
-
+Tools Calling Raw Output:
-
### Complex Instruction Call: Literary Map
@@ -142,14 +120,10 @@ Test Instruction: Instruction ②
From the above video, it can be seen that Sonnet 3 fails in the complex instruction call. The error is due to prompts being expected as an array but generated as a string.
-
+Tools Calling Raw Output:
-
## Claude 3 Haiku
@@ -161,10 +135,7 @@ From the above video:
1. Claude 3 Haiku triggers Tools Calling twice, indicating that it also does not support Parallel Tools Calling;
2. Haiku does not provide a good response and directly calls the tool;
-
+
### Complex Instruction Call: Literary Map
@@ -174,12 +145,8 @@ Test Instruction: Instruction ②
From the above video, it can be seen that Haiku 3 also fails in the complex instruction call. The error is the same as prompts generating a string instead of an array.
-
+Tools Calling Raw Output:
-
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/anthropic.zh-CN.mdx b/DigitalHumanWeb/docs/usage/tools-calling/anthropic.zh-CN.mdx
index 95db4ff..c052fea 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/anthropic.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/anthropic.zh-CN.mdx
@@ -15,12 +15,12 @@ tags:
Anthropic Claude 系列模型 Tools Calling 能力一览:
-| 模型 | 支持 Tools Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
-| --- | --- | --- | --- | --- | --- |
-| Claude 3.5 Sonnet | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
-| Claude 3 Opus | ✅ | ✅ | ❌ | 🌟 | ⛔️ |
-| Claude 3 Sonnet | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
-| Claude 3 Haiku | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
+| 模型 | 支持 Tools Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
+| ----------------- | ---------------- | ----------- | ------------ | ------ | ---- |
+| Claude 3.5 Sonnet | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
+| Claude 3 Opus | ✅ | ✅ | ❌ | 🌟 | ⛔️ |
+| Claude 3 Sonnet | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
+| Claude 3 Haiku | ✅ | ✅ | ❌ | 🌟🌟 | ⛔️ |
## Claude 3.5 Sonnet
@@ -30,18 +30,13 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
-
+Tools Calling 原始输出:
-```yml
-
-```
-
+ ```yml
+ ```
### 复杂调用指令:文生图
@@ -52,21 +47,16 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
从上述视频中可以看到:
-1. Sonnet 3.5 支持流式 Tools Calling 和 Parallel Tools Calling;
-2. 在流式 Tools Calling 时,表现出来的特征是在创建长句会等待住(详见 Tools Calling 原始输出 `[chunk 40]` 和 `[chunk 41]` 中间的耗时达到 6s)。所以相对来说会在 Tools Calling 的起始阶段有一个较长的等待时间。
+1. Sonnet 3.5 支持流式 Tools Calling 和 Parallel Tools Calling;
+2. 在流式 Tools Calling 时,表现出来的特征是在创建长句会等待住(详见 Tools Calling 原始输出 `[chunk 40]` 和 `[chunk 41]` 中间的耗时达到 6s)。所以相对来说会在 Tools Calling 的起始阶段有一个较长的等待时间。
-
+Tools Calling 原始输出:
-```yml
-
-```
-
+ ```yml
+ ```
## Claude 3 Opus
@@ -83,14 +73,10 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
2. Opus 会触发两次 Tools Calling,说明它并不支持 Parallel Tools Calling;
3. 从 Tools Calling 的原始输出来看, Opus 也是支持流式 Tools Calling 的
-
-
-
- Tools Calling 原始输出:
+
+
+ Tools Calling 原始输出:
### 复杂调用指令:文生图
@@ -104,14 +90,10 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
1. 结合简单任务, Opus 的工具调用一定会输出 `` 标签,这其实对体验影响非常大
2. Opus 输出的 prompts 字段是字符串,而不是数组,导致报错,无法正常调用插件。
-
+Tools Calling 原始输出:
-
## Claude 3 Sonnet
@@ -124,14 +106,10 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
从上述视频中可以看出,Claude 3 Sonnet 会调用两次 Tools Calling,说明它并不支持 Parallel Tools Calling。
-
+Tools Calling 原始输出:
-
### 复杂调用指令:文生图
@@ -142,14 +120,10 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
从上述视频中可以看到, Sonnet 3 在复杂指令调用下就失败了。报错原因是 prompts 原本预期为一个数组,但是生成的却是一个字符串。
-
+Tools Calling 原始输出:
-
## Claude 3 Haiku
@@ -161,10 +135,7 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
1. Claude 3 Haiku 会调用两次 Tools Calling,说明它也不支持 Parallel Tools Calling;
2. Haiku 并没有回答好的,也是直接调用的工具;
-
+
### 复杂调用指令:文生图
@@ -174,12 +145,8 @@ Anthropic Claude 系列模型 Tools Calling 能力一览:
从上述视频中可以看到, Haiku 3 在复杂指令调用下也是失败的。报错原因同样是 prompts 生成了字符串而不是数组。
-
+Tools Calling 原始输出:
-
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/google.mdx b/DigitalHumanWeb/docs/usage/tools-calling/google.mdx
index 2df7326..2699e7a 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/google.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/google.mdx
@@ -15,10 +15,10 @@ tags:
Overview of Google Gemini series model Tools Calling capabilities:
-| Model | Tools Calling Support | Streaming | Parallel | Simple Instruction Score | Complex Instruction |
-| --- | --- | --- | --- | --- | --- |
-| Gemini 1.5 Pro | ✅ | ❌ | ✅ | ⛔ | ⛔ |
-| Gemini 1.5 Flash | ❌ | ❌ | ❌ | ⛔ | ⛔ |
+| Model | Tools Calling Support | Streaming | Parallel | Simple Instruction Score | Complex Instruction |
+| ---------------- | --------------------- | --------- | -------- | ------------------------ | ------------------- |
+| Gemini 1.5 Pro | ✅ | ❌ | ✅ | ⛔ | ⛔ |
+| Gemini 1.5 Flash | ❌ | ❌ | ❌ | ⛔ | ⛔ |
Based on our actual tests, we strongly recommend not enabling plugins for Gemini because as of
@@ -35,38 +35,31 @@ Test Instruction: Instruction ①
In the json output from Gemini, the name is incorrect, so LobeChat cannot recognize which plugin it called. (In the input, the name of the weather plugin is `realtime-weather____fetchCurrentWeather`, while Gemini returns `weather____fetchCurrentWeather`).
-
+Original Tools Calling Output:
-```yml
-[stream start] 2024-7-7 17:53:25.647
-[chunk 0] 2024-7-7 17:53:25.654
-{"candidates":[{"content":{"parts":[{"text":"好的"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
-
-[chunk 1] 2024-7-7 17:53:26.288
-{"candidates":[{"content":{"parts":[{"text":"\n\n"}],"role":"model"},"finishReason":"STOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
+ ```yml
+ [stream start] 2024-7-7 17:53:25.647
+ [chunk 0] 2024-7-7 17:53:25.654
+ {"candidates":[{"content":{"parts":[{"text":"好的"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
-[chunk 2] 2024-7-7 17:53:26.336
-{"candidates":[{"content":{"parts":[{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"Hangzhou"}}},{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"Beijing"}}}],"role":"model"},"finishReasoSTOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":79,"totalTokenCount":174}}
+ [chunk 1] 2024-7-7 17:53:26.288
+ {"candidates":[{"content":{"parts":[{"text":"\n\n"}],"role":"model"},"finishReason":"STOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
-[stream finished] total chunks: 3
-```
+ [chunk 2] 2024-7-7 17:53:26.336
+ {"candidates":[{"content":{"parts":[{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"Hangzhou"}}},{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"Beijing"}}}],"role":"model"},"finishReasoSTOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":79,"totalTokenCount":174}}
+ [stream finished] total chunks: 3
+ ```
### Complex Instruction Call: Image Generation
Test Instruction: Instruction ②
-
+
When testing a set of complex instructions, Google throws an error directly:
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/google.zh-CN.mdx b/DigitalHumanWeb/docs/usage/tools-calling/google.zh-CN.mdx
index fc3c78d..35c54c5 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/google.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/google.zh-CN.mdx
@@ -15,13 +15,13 @@ tags:
Google Gemini 系列模型 Tools Calling 能力一览:
-| 模型 | 支持 Tools Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
-| --- | --- | --- | --- | --- | --- |
-| Gemini 1.5 Pro | ✅ | ❌ | ✅ | ⛔ | ⛔ |
-| Gemini 1.5 Flash | ❌ | ❌ | ❌ | ⛔ | ⛔ |
+| 模型 | 支持 Tools Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
+| ---------------- | ---------------- | ----------- | ------------ | ------ | ---- |
+| Gemini 1.5 Pro | ✅ | ❌ | ✅ | ⛔ | ⛔ |
+| Gemini 1.5 Flash | ❌ | ❌ | ❌ | ⛔ | ⛔ |
- 根据我们的的实际测试,强烈建议不要给 Gemini 开启插件,因为目前(截止2024.07.07)它的 Tools Calling
+ 根据我们的的实际测试,强烈建议不要给 Gemini 开启插件,因为目前(截止 2024.07.07)它的 Tools Calling
能力实在太烂了。
@@ -35,38 +35,31 @@ Google Gemini 系列模型 Tools Calling 能力一览:
Gemini 输出的 json 中,name 是错误的,因此 LobeChat 无法识别到它调用了什么插件。(入参中,天气插件的 name 为 `realtime-weather____fetchCurrentWeather`,而 Gemini 返回的是 `weather____fetchCurrentWeather`)。
-
+Tools Calling 原始输出:
-```yml
-[stream start] 2024-7-7 17:53:25.647
-[chunk 0] 2024-7-7 17:53:25.654
-{"candidates":[{"content":{"parts":[{"text":"好的"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
-
-[chunk 1] 2024-7-7 17:53:26.288
-{"candidates":[{"content":{"parts":[{"text":"\n\n"}],"role":"model"},"finishReason":"STOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
+ ```yml
+ [stream start] 2024-7-7 17:53:25.647
+ [chunk 0] 2024-7-7 17:53:25.654
+ {"candidates":[{"content":{"parts":[{"text":"好的"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
-[chunk 2] 2024-7-7 17:53:26.336
-{"candidates":[{"content":{"parts":[{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"杭州"}}},{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"北京"}}}],"role":"model"},"finishReasoSTOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":79,"totalTokenCount":174}}
+ [chunk 1] 2024-7-7 17:53:26.288
+ {"candidates":[{"content":{"parts":[{"text":"\n\n"}],"role":"model"},"finishReason":"STOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
-[stream finished] total chunks: 3
-```
+ [chunk 2] 2024-7-7 17:53:26.336
+ {"candidates":[{"content":{"parts":[{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"杭州"}}},{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"北京"}}}],"role":"model"},"finishReasoSTOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":79,"totalTokenCount":174}}
+ [stream finished] total chunks: 3
+ ```
### 复杂调用指令:文生图
测试指令:指令 ②
-
+
在测试复杂指令集时,Google 直接抛错:
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/groq.mdx b/DigitalHumanWeb/docs/usage/tools-calling/groq.mdx
index 1333ed7..99a1d0b 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/groq.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/groq.mdx
@@ -1 +1,10 @@
+---
+title: ''
+description: 学习如何有效管理待办事项,提高工作效率和组织能力。
+tags:
+ - 待办事项
+ - 工作效率
+ - 时间管理
+---
+
TODO
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/groq.zh-CN.mdx b/DigitalHumanWeb/docs/usage/tools-calling/groq.zh-CN.mdx
index baabe3b..6fb22aa 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/groq.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/groq.zh-CN.mdx
@@ -17,11 +17,11 @@ tags:
Groq 平台的模型 Tools Calling 能力一览:
-| 模型 | 支持 Tools Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
-| ------------ | ------------------ | --------------- | ---------------- | ------------ | -------- |
-| LLAMA3 70B | ✅ | ❌ | ✅ | 🌟🌟 | 🌟🌟 |
-| LLAMA3 8B | ✅ | ❌ | ✅ | 🌟🌟 | 🌟 |
-| Mixtral-8x7B | ✅ | ❌ | ✅ | ⛔ | 🌟🌟 |
+| 模型 | 支持 Tools Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
+| ------------ | ---------------- | ----------- | ------------ | ------ | ---- |
+| LLAMA3 70B | ✅ | ❌ | ✅ | 🌟🌟 | 🌟🌟 |
+| LLAMA3 8B | ✅ | ❌ | ✅ | 🌟🌟 | 🌟 |
+| Mixtral-8x7B | ✅ | ❌ | ✅ | ⛔ | 🌟🌟 |
## LLAMA3 70B
@@ -33,21 +33,17 @@ Groq 平台的模型 Tools Calling 能力一览:
从上述视频中可以看到 LLAMA3 70B 支持并发 Tools Calling,可以同时调用多次天气查询。
-
+Tools Calling 原始输出:
-```yml
-[no stream response] 2024-7-8 15:50:40.166
+ ```yml
+ [no stream response] 2024-7-8 15:50:40.166
-{"id":"chatcmpl-ec4b6c0b-1078-4f50-a39c-e58b3b1f9c31","object":"chat.completion","created":1720425030,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_v89g","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州\"}"}},{"id":"call_jxwk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"prompt_time":0.224209489,"completion_tokens":68,"completion_time":0.194285714,"total_tokens":1037,"total_time":0.418495203},"system_fingerprint":"fp_87cbfbbc4d","x_groq":{"id":"req_01j28n57x9e78a6bfbn9sdn139"}}
-
-```
+ {"id":"chatcmpl-ec4b6c0b-1078-4f50-a39c-e58b3b1f9c31","object":"chat.completion","created":1720425030,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_v89g","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州\"}"}},{"id":"call_jxwk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"prompt_time":0.224209489,"completion_tokens":68,"completion_time":0.194285714,"total_tokens":1037,"total_time":0.418495203},"system_fingerprint":"fp_87cbfbbc4d","x_groq":{"id":"req_01j28n57x9e78a6bfbn9sdn139"}}
+ ```
### 复杂调用指令:文生图
@@ -56,22 +52,18 @@ Groq 平台的模型 Tools Calling 能力一览:
-
+
-Tools Calling 原始输出:
-
-```yml
-[no stream response] 2024-7-8 18:0:34.811
+ Tools Calling 原始输出:
-{"id":"chatcmpl-e3b59ca9-1172-4ae2-96c7-3d6997a1f8a8","object":"chat.completion","created":1720432834,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_azm9","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A small, fluffy, and playful golden retriever puppy with a white patch on its forehead, sitting on a green grass field with a bright blue sky in the background, photo.\",\"A cute, little, brown and white Dalmatian puppy with a red collar, running around in a park with a sunny day, illustration.\",\"A tiny, grey and white Poodle puppy with a pink ribbon, sitting on a white couch with a few toys surrounding it, watercolor painting.\",\"A sweet, small, black and white Chihuahua puppy with a pink bow, lying on a soft, white blanket with a few stuffed animals nearby, oil painting.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2305,"prompt_time":3.027052298,"completion_tokens":246,"completion_time":0.702857143,"total_tokens":2551,"total_time":3.729909441},"system_fingerprint":"fp_7ab5f7e105","x_groq":{"id":"req_01j28wk2q0efvs22qatw7rd0ds"}}
+ ```yml
+ [no stream response] 2024-7-8 18:0:34.811
-POST /api/chat/groq 200 in 17462ms
-```
+ {"id":"chatcmpl-e3b59ca9-1172-4ae2-96c7-3d6997a1f8a8","object":"chat.completion","created":1720432834,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_azm9","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A small, fluffy, and playful golden retriever puppy with a white patch on its forehead, sitting on a green grass field with a bright blue sky in the background, photo.\",\"A cute, little, brown and white Dalmatian puppy with a red collar, running around in a park with a sunny day, illustration.\",\"A tiny, grey and white Poodle puppy with a pink ribbon, sitting on a white couch with a few toys surrounding it, watercolor painting.\",\"A sweet, small, black and white Chihuahua puppy with a pink bow, lying on a soft, white blanket with a few stuffed animals nearby, oil painting.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2305,"prompt_time":3.027052298,"completion_tokens":246,"completion_time":0.702857143,"total_tokens":2551,"total_time":3.729909441},"system_fingerprint":"fp_7ab5f7e105","x_groq":{"id":"req_01j28wk2q0efvs22qatw7rd0ds"}}
+ POST /api/chat/groq 200 in 17462ms
+ ```
## LLAMA3-8B
@@ -84,22 +76,18 @@ POST /api/chat/groq 200 in 17462ms
从上述视频中可以看到 LLAMA3-8B 对于天气插件可以正常调用,并获得正确的总结结果。但是它并没有完全 follow 我们的描述指令,没有回答「好的」。
-
+Tools Calling 原始输出:
-```yml
-[no stream response] 2024-7-9 11:33:16.920
+ ```yml
+ [no stream response] 2024-7-9 11:33:16.920
-{"id":"chatcmpl-f3672d59-e91d-4253-af1b-bfc4e0912085","object":"chat.completion","created":1720495996,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_rjtk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州市\"}"}},{"id":"call_7pqh","type":"functi,"function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京市\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"ppt_time":0.145428625,"completion_tokens":128,"completion_time":0.101364747,"total_tokens":1097,"total_time":0.246793372},"system_fingerprint":"fp_33d61fdfc3","x_groq":{"id":"req_01j2artze1exz82nettf2h9066"}}
-
-POST /api/chat/groq 200 in 1649ms
-```
+ {"id":"chatcmpl-f3672d59-e91d-4253-af1b-bfc4e0912085","object":"chat.completion","created":1720495996,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_rjtk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州市\"}"}},{"id":"call_7pqh","type":"functi,"function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京市\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"ppt_time":0.145428625,"completion_tokens":128,"completion_time":0.101364747,"total_tokens":1097,"total_time":0.246793372},"system_fingerprint":"fp_33d61fdfc3","x_groq":{"id":"req_01j2artze1exz82nettf2h9066"}}
+ POST /api/chat/groq 200 in 1649ms
+ ```
### 复杂调用指令:文生图
@@ -110,22 +98,18 @@ POST /api/chat/groq 200 in 1649ms
LLAMA3 8B 在 DallE 的输出场景下,只会输出 1 张图片,而不是像 LLAMA3 70B 一样输出 4 张,意味着在复杂 Tools 指令层面,能力和 GPT 3.5 Turbo 接近,不如 GPT 4。
-
+
-Tools Calling 原始输出:
-
-```yml
-[no stream response] 2024-7-9 11:58:27.40
+ Tools Calling 原始输出:
-{"id":"chatcmpl-3c38f4d2-3424-416c-9fb0-0969d2683959","object":"chat.completion","created":1720497506,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_k6xj","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"Create a watercolor painting of a small white dog with a pink nose, wearing a red collar and sitting on a green grass. The dog's ears should be floppy and its fur should be curly.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"natural\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2282,"prompt_time":0.342335558,"completion_tokens":148,"completion_time":0.118023813,"total_tokens":2430,"total_time":0.460359371},"system_fingerprint":"fp_179b0f92c9","x_groq":{"id":"req_01j2at921tec8aymdq48czcw1y"}}
+ ```yml
+ [no stream response] 2024-7-9 11:58:27.40
-POST /api/chat/groq 200 in 2517ms
-```
+ {"id":"chatcmpl-3c38f4d2-3424-416c-9fb0-0969d2683959","object":"chat.completion","created":1720497506,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_k6xj","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"Create a watercolor painting of a small white dog with a pink nose, wearing a red collar and sitting on a green grass. The dog's ears should be floppy and its fur should be curly.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"natural\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2282,"prompt_time":0.342335558,"completion_tokens":148,"completion_time":0.118023813,"total_tokens":2430,"total_time":0.460359371},"system_fingerprint":"fp_179b0f92c9","x_groq":{"id":"req_01j2at921tec8aymdq48czcw1y"}}
+ POST /api/chat/groq 200 in 2517ms
+ ```
## Mixtral-8x7B
@@ -138,23 +122,19 @@ POST /api/chat/groq 200 in 2517ms
从上述视频中可以看到 Mixtral-8x7B 对于天气插件的查询输出的参数有问题,导致无法正常调用插件。
-
+Tools Calling 原始输出:
-```yml
-
-[no stream response] 2024-7-8 22:18:19.682
+ ```yml
-{"id":"chatcmpl-9f89d669-5642-48be-b5cd-7a29756800c0","object":"chat.completion","created":1720448299,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_719t","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"Hangzhou,Beijing\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":1262,"prompt_time":0.116684046,"completion_tokens":102,"completion_time":0.163113006,"total_tokens":1364,"total_time":0.279797052},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j29bbc8xen2s3thp9qen5bys"}}
+ [no stream response] 2024-7-8 22:18:19.682
-POST /api/chat/groq 200 in 4860ms
-```
+ {"id":"chatcmpl-9f89d669-5642-48be-b5cd-7a29756800c0","object":"chat.completion","created":1720448299,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_719t","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"Hangzhou,Beijing\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":1262,"prompt_time":0.116684046,"completion_tokens":102,"completion_time":0.163113006,"total_tokens":1364,"total_time":0.279797052},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j29bbc8xen2s3thp9qen5bys"}}
+ POST /api/chat/groq 200 in 4860ms
+ ```
### 复杂调用指令:文生图
@@ -165,25 +145,19 @@ POST /api/chat/groq 200 in 4860ms
非常意外地,Mixtral 8x7B 在文生图的 Tools Calling 的场景下,居然可以正常出图,而且出图的能力基本和 LLAMA3 70B 持平。
-
-
+
+
+Tools Calling 原始输出:
-```yml
-[no stream response] 2024-7-9 12:6:38.11
-
-{"id":"chatcmpl-a90069f3-b119-41b9-b8d7-c7f97373529e","object":"chat.completion","created":1720497998,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_hw8t","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A colorful and playful illustration of a friendly small dog, looking directly at the viewer with a wagging tail and bright, expressive eyes. The dog's fur is glossy and well-groomed, with a mix of black, white, and brown colors. The background is a lush, green park with a clear blue sky and a few fluffy clouds.\",\"An oil painting of a small, energetic dog in a sunlit park, chasing a frisbee. The dog is a mix of black and white fur, with a distinct brown spot above its left eye. The park features tall trees, providing dappled shade across the grassy landscape. The frisbee is bright orange and stands out against the natural surroundings.\",\"A realistic watercolor painting of a small, fluffy white dog curled up next to a warm fireplace during a cozy winter evening. The dog's eyes are closed in contentment, and a single red bow is tied around its neck. The background includes a plush armchair, a stack of books, and a softly lit room.\",\"A fun and engaging cartoon of a small dog sitting at a café table, enjoying a cup of coffee and a croissant. The dog has a expressive face and a blue scarf around its neck. The café has a vintage, 1920's style and a red awning, with a bustling city background.\"],\"quality\":\"standard\",\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2920,"prompt_time":0.228639219,"completion_tokens":465,"completion_time":0.755757988,"total_tokens":3385,"total_time":0.984397207},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j2atr155f0nv8rmfk448e2at"}}
+ ```yml
+ [no stream response] 2024-7-9 12:6:38.11
-POST /api/chat/groq 200 in 6216ms
+ {"id":"chatcmpl-a90069f3-b119-41b9-b8d7-c7f97373529e","object":"chat.completion","created":1720497998,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_hw8t","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A colorful and playful illustration of a friendly small dog, looking directly at the viewer with a wagging tail and bright, expressive eyes. The dog's fur is glossy and well-groomed, with a mix of black, white, and brown colors. The background is a lush, green park with a clear blue sky and a few fluffy clouds.\",\"An oil painting of a small, energetic dog in a sunlit park, chasing a frisbee. The dog is a mix of black and white fur, with a distinct brown spot above its left eye. The park features tall trees, providing dappled shade across the grassy landscape. The frisbee is bright orange and stands out against the natural surroundings.\",\"A realistic watercolor painting of a small, fluffy white dog curled up next to a warm fireplace during a cozy winter evening. The dog's eyes are closed in contentment, and a single red bow is tied around its neck. The background includes a plush armchair, a stack of books, and a softly lit room.\",\"A fun and engaging cartoon of a small dog sitting at a café table, enjoying a cup of coffee and a croissant. The dog has a expressive face and a blue scarf around its neck. The café has a vintage, 1920's style and a red awning, with a bustling city background.\"],\"quality\":\"standard\",\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2920,"prompt_time":0.228639219,"completion_tokens":465,"completion_time":0.755757988,"total_tokens":3385,"total_time":0.984397207},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j2atr155f0nv8rmfk448e2at"}}
-```
+ POST /api/chat/groq 200 in 6216ms
+ ```
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/moonshot.mdx b/DigitalHumanWeb/docs/usage/tools-calling/moonshot.mdx
index 1333ed7..422f796 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/moonshot.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/moonshot.mdx
@@ -1 +1,10 @@
+---
+title: ''
+description: 学习如何有效管理待办事项,提高工作效率和生产力。
+tags:
+ - 待办事项
+ - 工作效率
+ - 生产力
+---
+
TODO
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/openai.mdx b/DigitalHumanWeb/docs/usage/tools-calling/openai.mdx
index 98fde36..01f3af9 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/openai.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/openai.mdx
@@ -15,11 +15,11 @@ tags:
Overview of the Tool Calling capabilities of OpenAI GPT series models:
-| Model | Tool Calling Support | Streaming | Parallel | Simple Instruction Score | Complex Instruction Score |
-| --- | --- | --- | --- | --- | --- |
-| GPT-3.5-turbo | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟 |
-| GPT-4-turbo | ✅ | ✅ | ✅ | 🌟🌟 | 🌟🌟 |
-| GPT-4o | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
+| Model | Tool Calling Support | Streaming | Parallel | Simple Instruction Score | Complex Instruction Score |
+| ------------- | -------------------- | --------- | -------- | ------------------------ | ------------------------- |
+| GPT-3.5-turbo | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟 |
+| GPT-4-turbo | ✅ | ✅ | ✅ | 🌟🌟 | 🌟🌟 |
+| GPT-4o | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
For testing instructions, see [Tools Calling - Evaluation Task
@@ -34,14 +34,10 @@ Test Instruction: Instruction ①
-
+
-Streaming Tool Calling Raw Output:
-
+ Streaming Tool Calling Raw Output:
### Complex Instruction Call: Wenshengtu
@@ -50,14 +46,10 @@ Test Instruction: Instruction ②
-
+
-Streaming Tool Calling Raw Output:
-
+ Streaming Tool Calling Raw Output:
## GPT-4 Turbo
@@ -72,14 +64,10 @@ Of course, it is also possible that GPT-4 Turbo's model has more "autonomy" and
-
+
-Streaming Tool Calling Raw Output:
-
+ Streaming Tool Calling Raw Output:
### Complex Instruction Call: Wenshengtu
@@ -88,14 +76,10 @@ Test Instruction: Instruction ②
-
+
-Streaming Tool Calling Raw Output:
-
+ Streaming Tool Calling Raw Output:
## GPT-4o
@@ -108,14 +92,10 @@ Similar to GPT-3.5, GPT-4o performs very well in following compound instructions
-
+
- Streaming Tool Calling Raw Output:
-
+ Streaming Tool Calling Raw Output:
### Complex Instruction Call: Wenshengtu
@@ -124,16 +104,11 @@ Test Instruction: Instruction ②
-
+
- Streaming Tool Calling Raw Output:
-
-```yml
-
-```
+ Streaming Tool Calling Raw Output:
+ ```yml
+ ```
diff --git a/DigitalHumanWeb/docs/usage/tools-calling/openai.zh-CN.mdx b/DigitalHumanWeb/docs/usage/tools-calling/openai.zh-CN.mdx
index 8d401ab..babd830 100644
--- a/DigitalHumanWeb/docs/usage/tools-calling/openai.zh-CN.mdx
+++ b/DigitalHumanWeb/docs/usage/tools-calling/openai.zh-CN.mdx
@@ -15,11 +15,11 @@ tags:
OpenAI GPT 系列模型 Tool Calling 能力一览:
-| 模型 | 支持 Tool Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
-| ------------- | ----------------- | --------------- | ---------------- | ------------ | -------- |
-| GPT-3.5-turbo | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟 |
-| GPT-4-turbo | ✅ | ✅ | ✅ | 🌟🌟 | 🌟🌟 |
-| GPT-4o | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
+| 模型 | 支持 Tool Calling | 流式 (Stream) | 并发(Parallel) | 简单指令得分 | 复杂指令 |
+| ------------- | --------------- | ----------- | ------------ | ------ | ---- |
+| GPT-3.5-turbo | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟 |
+| GPT-4-turbo | ✅ | ✅ | ✅ | 🌟🌟 | 🌟🌟 |
+| GPT-4o | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
关于测试指令,详见 [工具调用 Tools Calling -
@@ -34,14 +34,10 @@ OpenAI GPT 系列模型 Tool Calling 能力一览:
-
+
-流式 Tool Calling 原始输出:
-
+ 流式 Tool Calling 原始输出:
### 复杂调用指令:文生图
@@ -50,14 +46,10 @@ OpenAI GPT 系列模型 Tool Calling 能力一览:
-
+
-流式 Tool Calling 原始输出:
-
+ 流式 Tool Calling 原始输出:
## GPT-4 Turbo
@@ -68,18 +60,14 @@ OpenAI GPT 系列模型 Tool Calling 能力一览:
GPT-4 Turbo 在调用 Tool Calling 时并没有像 GPT-3.5 Turbo 一样回复「好的」,且经过多次测试始终一样,因此在这一条复合指令的跟随中反而不如 GPT-3.5 Turbo,但剩余两项能力均不错。
-当然,也有可能是因为 GPT-4 Turbo 的模型更加有“自主意识”,认为不需要输出这一句“好的”。
+当然,也有可能是因为 GPT-4 Turbo 的模型更加有 “自主意识”,认为不需要输出这一句 “好的”。
-
+
-流式 Tool Calling 原始输出:
-
+ 流式 Tool Calling 原始输出:
### 复杂调用指令:文生图
@@ -88,14 +76,10 @@ GPT-4 Turbo 在调用 Tool Calling 时并没有像 GPT-3.5 Turbo 一样回复「
-
+
-流式 Tool Calling 原始输出:
-
+ 流式 Tool Calling 原始输出:
## GPT 4o
@@ -108,14 +92,10 @@ GPT-4o 和 3.5 一样,在简单调用指令中,能够达到非常不错的
-
+
- 流式 Tool Calling 原始输出:
-
+ 流式 Tool Calling 原始输出:
### 复杂调用指令:文生图
@@ -124,16 +104,11 @@ GPT-4o 和 3.5 一样,在简单调用指令中,能够达到非常不错的
-
+
- 流式 Tool Calling 原始输出:
-
-```yml
-
-```
+ 流式 Tool Calling 原始输出:
+ ```yml
+ ```
diff --git a/DigitalHumanWeb/drizzle.config.ts b/DigitalHumanWeb/drizzle.config.ts
index 2f6460d..3d71493 100644
--- a/DigitalHumanWeb/drizzle.config.ts
+++ b/DigitalHumanWeb/drizzle.config.ts
@@ -22,8 +22,8 @@ export default {
url: connectionString,
},
dialect: 'postgresql',
- out: './src/database/server/migrations',
+ out: './src/database/migrations',
- schema: './src/database/server/schemas/lobechat',
+ schema: './src/database/schemas',
strict: true,
} satisfies Config;
diff --git a/DigitalHumanWeb/locales/ar/auth.json b/DigitalHumanWeb/locales/ar/auth.json
index 1ec1966..ee23b37 100644
--- a/DigitalHumanWeb/locales/ar/auth.json
+++ b/DigitalHumanWeb/locales/ar/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "الشهر الماضي",
+ "recent30Days": "آخر 30 يومًا"
+ },
+ "header": {
+ "desc": "إدارة معلومات حسابك.",
+ "title": "الحساب"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "غير نشط",
+ "more": "نشط"
+ },
+ "months": {
+ "apr": "أبريل",
+ "aug": "أغسطس",
+ "dec": "ديسمبر",
+ "feb": "فبراير",
+ "jan": "يناير",
+ "jul": "يوليو",
+ "jun": "يونيو",
+ "mar": "مارس",
+ "may": "مايو",
+ "nov": "نوفمبر",
+ "oct": "أكتوبر",
+ "sep": "سبتمبر"
+ },
+ "tooltip": "{{date}} أرسل {{count}} رسائل في ذلك اليوم",
+ "totalCount": "إجمالي {{count}} رسائل أرسلت في العام الماضي"
+ },
"login": "تسجيل الدخول",
- "loginOrSignup": "تسجيل الدخول / التسجيل",
- "profile": "الملف الشخصي",
- "security": "الأمان",
+ "loginOrSignup": "تسجيل الدخول / الاشتراك",
+ "profile": {
+ "avatar": "الصورة الشخصية",
+ "email": "عنوان البريد الإلكتروني",
+ "sso": {
+ "loading": "جارٍ تحميل الحسابات المرتبطة من طرف ثالث",
+ "providers": "الحسابات المتصلة",
+ "unlink": {
+ "description": "بعد unlink ، لن تتمكن من تسجيل الدخول باستخدام حساب {{provider}} \"{{providerAccountId}}\". إذا كنت بحاجة إلى إعادة ربط حساب {{provider}} بالحساب الحالي، يرجى التأكد من أن عنوان البريد الإلكتروني لحساب {{provider}} هو {{email}}، وسنقوم بربطه تلقائيًا بالحساب المسجل الدخول عند تسجيل الدخول.",
+ "forbidden": "يجب أن تحتفظ بحساب طرف ثالث واحد على الأقل مرتبطًا.",
+ "title": "هل تريد فصل حساب الطرف الثالث {{provider}}؟"
+ }
+ },
+ "username": "اسم المستخدم"
+ },
"signout": "تسجيل الخروج",
- "signup": "التسجيل"
+ "signup": "الاشتراك",
+ "stats": {
+ "aiheatmaps": "مؤشر النشاط",
+ "assistants": "المساعدون",
+ "assistantsRank": {
+ "left": "المساعد",
+ "right": "المواضيع",
+ "title": "ترتيب استخدام المساعد"
+ },
+ "createdAt": "تاريخ التسجيل",
+ "days": "أيام",
+ "empty": {
+ "desc": "يرجى تجميع المزيد من بيانات الدردشة للعرض",
+ "title": "لا توجد بيانات"
+ },
+ "lastYearActivity": "النشاط في العام الماضي",
+ "loginGuide": {
+ "f1": "احصل على استخدام مجاني",
+ "f2": "مزامنة الرسائل عبر الأجهزة المتعددة",
+ "f3": "تمتع بمساعدين متنوعين",
+ "f4": "استكشف الإضافات القوية",
+ "title": "بعد تسجيل الدخول يمكنك:"
+ },
+ "messages": "رسائل",
+ "modelsRank": {
+ "left": "النموذج",
+ "right": "الرسائل",
+ "title": "ترتيب استخدام النموذج"
+ },
+ "share": {
+ "title": "مؤشر نشاط الذكاء الاصطناعي الخاص بي"
+ },
+ "topics": "المواضيع",
+ "topicsRank": {
+ "left": "الموضوع",
+ "right": "الرسائل",
+ "title": "ترتيب محتوى الموضوع"
+ },
+ "updatedAt": "تاريخ التحديث",
+ "welcome": "{{username}}، هذا هو يومك {{days}} مع {{appName}}",
+ "words": "كلمات"
+ },
+ "tab": {
+ "profile": "الملف الشخصي",
+ "security": "الأمان",
+ "stats": "الإحصائيات"
+ }
}
diff --git a/DigitalHumanWeb/locales/ar/changelog.json b/DigitalHumanWeb/locales/ar/changelog.json
new file mode 100644
index 0000000..261158c
--- /dev/null
+++ b/DigitalHumanWeb/locales/ar/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "تابعنا على X",
+ "subscribeToUpdates": "اشترك في التحديثات",
+ "versions": "تفاصيل الإصدار"
+ },
+ "addedWhileAway": "لقد أضفنا ميزات جديدة أثناء غيابك.",
+ "allChangelog": "عرض جميع سجلات التحديثات",
+ "description": "تابع الميزات الجديدة والتحسينات في {{appName}}",
+ "pagination": {
+ "next": "الصفحة التالية",
+ "older": "عرض التغييرات السابقة"
+ },
+ "readDetails": "اقرأ التفاصيل",
+ "title": "سجل التحديثات",
+ "versionDetails": "تفاصيل الإصدار",
+ "welcomeBack": "مرحبًا بعودتك!"
+}
diff --git a/DigitalHumanWeb/locales/ar/chat.json b/DigitalHumanWeb/locales/ar/chat.json
index 51659ce..e5dec92 100644
--- a/DigitalHumanWeb/locales/ar/chat.json
+++ b/DigitalHumanWeb/locales/ar/chat.json
@@ -8,6 +8,7 @@
"agents": "مساعد",
"artifact": {
"generating": "جاري الإنشاء",
+ "inThread": "لا يمكن عرض الموضوعات الفرعية، يرجى التبديل إلى منطقة المحادثة الرئيسية لفتحها",
"thinking": "جاري التفكير",
"thought": "عملية التفكير",
"unknownTitle": "عمل غير مسمى"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} نسخة",
"emptyAgent": "لا يوجد مساعد",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "يمكن تقليل تكلفة توليد محادثة واحدة بنسبة تصل إلى 90%، وزيادة سرعة الاستجابة بمقدار 4 مرات (<1>اعرف المزيد1>). عند التفعيل، سيتم تعطيل حد عدد الرسائل التاريخية تلقائيًا",
+ "title": "تفعيل تخزين السياق"
+ },
+ "enableReasoning": {
+ "desc": "استنادًا إلى آلية تفكير كلود (Claude Thinking) المحدودة (<1>اعرف المزيد1>)، عند التفعيل، سيتم تعطيل حد عدد الرسائل التاريخية تلقائيًا",
+ "title": "تفعيل التفكير العميق"
+ },
+ "reasoningBudgetToken": {
+ "title": "استهلاك توكن التفكير"
+ },
+ "title": "وظائف توسيع النموذج"
+ },
+ "history": {
+ "title": "سيتذكر المساعد آخر {{count}} رسالة فقط"
+ },
"historyRange": "نطاق التاريخ",
+ "historySummary": "ملخص الرسائل التاريخية",
"inbox": {
"desc": "قم بتشغيل مجموعة الدماغ وأشعل شرارة التفكير. مساعدك الذكي، هنا حيث يمكنك التواصل بكل شيء",
"title": "دردشة عشوائية"
@@ -45,6 +64,9 @@
"stop": "توقف",
"warp": "تغيير السطر"
},
+ "intentUnderstanding": {
+ "title": "جارٍ فهم وتحليل نواياك..."
+ },
"knowledgeBase": {
"all": "جميع المحتويات",
"allFiles": "جميع الملفات",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "حذف وإعادة الإنشاء",
+ "deleteDisabledByThreads": "يوجد موضوعات فرعية، لا يمكن الحذف",
"regenerate": "إعادة الإنشاء"
},
+ "messages": {
+ "modelCard": {
+ "credit": "نقاط",
+ "creditPricing": "التسعير",
+ "creditTooltip": "لتسهيل العد، نقوم بتحويل 1$ إلى 1M نقطة، على سبيل المثال، 3$/M رموز تعني 3 نقاط/رمز",
+ "pricing": {
+ "inputCachedTokens": "مدخلات مخزنة {{amount}}/نقطة · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M حرف",
+ "inputMinutes": "${{amount}}/دقيقة",
+ "inputTokens": "مدخلات {{amount}}/نقطة · ${{amount}}/M",
+ "outputTokens": "مخرجات {{amount}}/نقطة · ${{amount}}/M",
+ "writeCacheInputTokens": "تخزين إدخال الكتابة {{amount}}/نقطة · ${{amount}}/ميغابايت"
+ }
+ },
+ "tokenDetails": {
+ "average": "متوسط السعر",
+ "input": "مدخلات",
+ "inputAudio": "مدخلات صوتية",
+ "inputCached": "مدخلات مخزنة",
+ "inputCitation": "اقتباس الإدخال",
+ "inputText": "مدخلات نصية",
+ "inputTitle": "تفاصيل المدخلات",
+ "inputUncached": "مدخلات غير مخزنة",
+ "inputWriteCached": "تخزين إدخال الكتابة",
+ "output": "مخرجات",
+ "outputAudio": "مخرجات صوتية",
+ "outputText": "مخرجات نصية",
+ "outputTitle": "تفاصيل المخرجات",
+ "reasoning": "تفكير عميق",
+ "title": "تفاصيل التوليد",
+ "total": "الإجمالي المستهلك"
+ }
+ },
"newAgent": "مساعد جديد",
"pin": "تثبيت",
"pinOff": "إلغاء التثبيت",
@@ -81,6 +137,32 @@
},
"regenerate": "إعادة الإنشاء",
"roleAndArchive": "الدور والأرشيف",
+ "search": {
+ "grounding": {
+ "searchQueries": "كلمات البحث",
+ "title": "تم العثور على {{count}} نتيجة"
+ },
+ "mode": {
+ "auto": {
+ "desc": "تحديد ما إذا كان من الضروري البحث بناءً على محتوى المحادثة",
+ "title": "الاتصال الذكي"
+ },
+ "off": {
+ "desc": "استخدام المعرفة الأساسية للنموذج فقط، دون إجراء بحث عبر الإنترنت",
+ "title": "إيقاف الاتصال"
+ },
+ "on": {
+ "desc": "الاستمرار في البحث عبر الإنترنت للحصول على أحدث المعلومات",
+ "title": "الاتصال دائمًا"
+ },
+ "useModelBuiltin": "استخدام محرك البحث المدمج في النموذج"
+ },
+ "searchModel": {
+ "desc": "النموذج الحالي لا يدعم استدعاء الدوال، لذا يجب استخدام نموذج يدعم استدعاء الدوال للبحث عبر الإنترنت",
+ "title": "نموذج البحث المساعد"
+ },
+ "title": "بحث عبر الإنترنت"
+ },
"searchAgentPlaceholder": "مساعد البحث...",
"sendPlaceholder": "أدخل محتوى الدردشة...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "يجب أن يكون طول اسم المجموعة بين 1 و 20"
},
"shareModal": {
+ "copy": "نسخ",
"download": "تحميل اللقطة",
+ "downloadFile": "تحميل الملف",
+ "exportTitle": "العنوان الافتراضي",
"imageType": "نوع الصورة",
+ "includeTool": "تضمين رسالة الأداة",
+ "includeUser": "تضمين رسالة المستخدم",
"screenshot": "لقطة شاشة",
"settings": "إعدادات التصدير",
- "shareToShareGPT": "إنشاء رابط مشاركة ShareGPT",
+ "text": "نص",
"withBackground": "تضمين صورة الخلفية",
"withFooter": "تضمين تذييل",
"withPluginInfo": "تضمين معلومات البرنامج المساعد",
+ "withRole": "تضمين رسالة الدور",
"withSystemRole": "تضمين دور المساعد"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "جارٍ التعرف...",
"prettifying": "جارٍ التجميل..."
},
- "temp": "مؤقت",
+ "thread": {
+ "divider": "موضوع فرعي",
+ "threadMessageCount": "{{messageCount}} رسالة",
+ "title": "موضوع فرعي"
+ },
"tokenDetails": {
"chats": "رسائل المحادثة",
+ "historySummary": "ملخص التاريخ",
"rest": "المتبقي",
"systemRole": "تعيين الدور",
"title": "تفاصيل الرمز",
@@ -131,29 +224,10 @@
"used": "مستخدم"
},
"topic": {
- "actions": {
- "autoRename": "إعادة تسمية ذكية",
- "duplicate": "إنشاء نسخة",
- "export": "تصدير الموضوع"
- },
"checkOpenNewTopic": "هل ترغب في فتح موضوع جديد؟",
"checkSaveCurrentMessages": "هل ترغب في حفظ الدردشة الحالية كموضوع؟",
- "confirmRemoveAll": "سيتم حذف جميع المواضيع قريبًا، وبمجرد الحذف لن يمكن استعادتها، يرجى التحلي بالحذر.",
- "confirmRemoveTopic": "سيتم حذف هذا الموضوع قريبًا، وبمجرد الحذف لن يمكن استعادته، يرجى التحلي بالحذر.",
- "confirmRemoveUnstarred": "سيتم حذف المواضيع غير المحفوظة قريبًا، وبمجرد الحذف لن يمكن استعادتها، يرجى التحلي بالحذر.",
- "defaultTitle": "الموضوع الافتراضي",
- "duplicateLoading": "جاري نسخ الموضوع...",
- "duplicateSuccess": "تم نسخ الموضوع بنجاح",
- "guide": {
- "desc": "انقر فوق زر الإرسال الأيسر لحفظ الجلسة الحالية كموضوع تاريخي وبدء جلسة جديدة",
- "title": "قائمة المواضيع"
- },
"openNewTopic": "فتح موضوع جديد",
- "removeAll": "حذف جميع المواضيع",
- "removeUnstarred": "حذف المواضيع غير المحفوظة",
- "saveCurrentMessages": "حفظ الجلسة الحالية كموضوع",
- "searchPlaceholder": "البحث في المواضيع...",
- "title": "الموضوع"
+ "saveCurrentMessages": "حفظ الجلسة الحالية كموضوع"
},
"translate": {
"action": "ترجمة",
@@ -184,5 +258,6 @@
"processing": "يتم معالجة الملف..."
}
}
- }
+ },
+ "zenMode": "وضع التركيز"
}
diff --git a/DigitalHumanWeb/locales/ar/common.json b/DigitalHumanWeb/locales/ar/common.json
index d7b55c3..43d0959 100644
--- a/DigitalHumanWeb/locales/ar/common.json
+++ b/DigitalHumanWeb/locales/ar/common.json
@@ -9,15 +9,79 @@
"title": "مرحبًا بك في التجربة {{name}}"
}
},
- "appInitializing": "جارٍ تشغيل التطبيق...",
+ "appLoading": {
+ "appIdle": "جاهز للإطلاق",
+ "appInitializing": "جارٍ تشغيل التطبيق...",
+ "failed": "عذرًا، فشل تحميل التطبيق، يرجى مراجعة التفاصيل للتحقق من المشكلة",
+ "finished": "تم الانتهاء من تهيئة قاعدة البيانات",
+ "goToChat": "جارٍ تحميل صفحة الدردشة...",
+ "initAuth": "جارٍ تهيئة خدمة المصادقة...",
+ "initUser": "جارٍ تهيئة حالة المستخدم...",
+ "initializing": "جارٍ تهيئة قاعدة بيانات PGlite...",
+ "loadingDependencies": "جارٍ تهيئة الاعتمادات...",
+ "loadingWasm": "جارٍ تحميل وحدة WASM...",
+ "migrating": "جارٍ تنفيذ ترحيل الجداول...",
+ "ready": "قاعدة البيانات جاهزة",
+ "showDetail": "عرض التفاصيل"
+ },
"autoGenerate": "توليد تلقائي",
"autoGenerateTooltip": "إكمال تلقائي بناءً على الكلمات المقترحة لوصف المساعد",
"autoGenerateTooltipDisabled": "الرجاء إدخال كلمة تلميح قبل تفعيل وظيفة الإكمال التلقائي",
"back": "عودة",
"batchDelete": "حذف دفعة",
"blog": "مدونة المنتجات",
+ "branching": "إنشاء موضوع فرعي",
+ "branchingDisable": "ميزة \"الموضوع الفرعي\" متاحة فقط في إصدار الخادم. إذا كنت بحاجة إلى هذه الميزة، يرجى التبديل إلى وضع نشر الخادم أو استخدام LobeChat Cloud",
"cancel": "إلغاء",
"changelog": "سجل التغييرات",
+ "clientDB": {
+ "autoInit": {
+ "title": "تهيئة قاعدة بيانات PGlite"
+ },
+ "error": {
+ "desc": "نعتذر، حدث خطأ أثناء عملية تهيئة قاعدة بيانات Pglite. يرجى النقر على الزر لإعادة المحاولة. إذا استمرت المشكلة بعد عدة محاولات، يرجى <1>تقديم مشكلة1>، وسنساعدك في حلها في أسرع وقت ممكن",
+ "detail": "سبب الخطأ: [{{type}}] {{message}}، التفاصيل كالتالي:",
+ "retry": "إعادة المحاولة",
+ "title": "فشل تهيئة قاعدة البيانات"
+ },
+ "initing": {
+ "error": "حدث خطأ، يرجى إعادة المحاولة",
+ "idle": "في انتظار التهيئة...",
+ "initializing": "جارٍ التهيئة...",
+ "loadingDependencies": "جارٍ تحميل الاعتماديات...",
+ "loadingWasmModule": "جارٍ تحميل وحدة WASM...",
+ "migrating": "جارٍ تنفيذ ترحيل البيانات...",
+ "ready": "قاعدة البيانات جاهزة"
+ },
+ "modal": {
+ "desc": "قم بتمكين قاعدة بيانات عميل PGlite، لتخزين بيانات الدردشة بشكل دائم في متصفحك، واستخدام ميزات متقدمة مثل مكتبة المعرفة",
+ "enable": "تمكين الآن",
+ "features": {
+ "knowledgeBase": {
+ "desc": "قم بتخزين قاعدة معرفتك الشخصية وابدأ محادثة مع مساعدك بسهولة (قريبًا)",
+ "title": "دعم محادثة قاعدة المعرفة، افتح دماغك الثاني"
+ },
+ "localFirst": {
+ "desc": "تُخزن بيانات الدردشة بالكامل في المتصفح، بياناتك دائمًا تحت سيطرتك.",
+ "title": "الأولوية محلية، الخصوصية أولاً"
+ },
+ "pglite": {
+ "desc": "مبني على PGlite، يدعم بشكل أصلي ميزات AI Native المتقدمة (استرجاع المتجهات)",
+ "title": "بنية تخزين عميل من الجيل الجديد"
+ }
+ },
+ "init": {
+ "desc": "جارٍ تهيئة قاعدة البيانات، قد يستغرق الأمر من 5 إلى 30 ثانية حسب اختلاف الشبكة",
+ "title": "جارٍ تهيئة قاعدة بيانات PGlite"
+ },
+ "title": "فتح قاعدة بيانات العميل"
+ },
+ "ready": {
+ "button": "استخدم الآن",
+ "desc": "استخدم الآن",
+ "title": "قاعدة بيانات PGlite جاهزة"
+ }
+ },
"close": "إغلاق",
"contact": "اتصل بنا",
"copy": "نسخ",
@@ -112,6 +176,7 @@
"en": "الإنجليزية",
"en-US": "الإنجليزية",
"es-ES": "الإسبانية",
+ "fa-IR": "الفارسية",
"fi-FI": "الفنلندية",
"fr-FR": "الفرنسية",
"hi-IN": "الهندية",
@@ -153,6 +218,7 @@
"pinOff": "إلغاء التثبيت",
"privacy": "سياسة الخصوصية",
"regenerate": "إعادة توليد",
+ "releaseNotes": "تفاصيل الإصدار",
"rename": "إعادة تسمية",
"reset": "إعادة تعيين",
"retry": "إعادة المحاولة",
@@ -209,6 +275,7 @@
},
"temp": "مؤقت",
"terms": "شروط الخدمة",
+ "update": "تحديث",
"updateAgent": "تحديث معلومات الوكيل",
"upgradeVersion": {
"action": "ترقية",
@@ -219,6 +286,7 @@
"anonymousNickName": "مستخدم مجهول",
"billing": "إدارة الفواتير",
"cloud": "تجربة {{name}}",
+ "community": "نسخة المجتمع",
"data": "تخزين البيانات",
"defaultNickname": "مستخدم النسخة المجتمعية",
"discord": "الدعم المجتمعي",
@@ -228,7 +296,6 @@
"help": "مركز المساعدة",
"moveGuide": "تم نقل زر الإعدادات إلى هنا",
"plans": "خطط الاشتراك",
- "preview": "المعاينة",
"profile": "إدارة الحساب",
"setting": "إعدادات التطبيق",
"usages": "إحصاءات الاستخدام"
diff --git a/DigitalHumanWeb/locales/ar/components.json b/DigitalHumanWeb/locales/ar/components.json
index 94b98c7..db60426 100644
--- a/DigitalHumanWeb/locales/ar/components.json
+++ b/DigitalHumanWeb/locales/ar/components.json
@@ -12,6 +12,7 @@
"batchChunking": "تقسيم دفعي",
"chunking": "تقسيم",
"chunkingTooltip": "قم بتقسيم الملف إلى عدة كتل نصية وتحويلها إلى متجهات، يمكن استخدامها في البحث الدلالي والمحادثة حول الملفات",
+ "chunkingUnsupported": "هذا الملف لا يدعم تقسيم الأجزاء",
"confirmDelete": "سيتم حذف هذا الملف، ولن يمكن استعادته بعد الحذف، يرجى تأكيد العملية",
"confirmDeleteMultiFiles": "سيتم حذف {{count}} ملفًا محددًا، ولن يمكن استعادته بعد الحذف، يرجى تأكيد العملية",
"confirmRemoveFromKnowledgeBase": "سيتم إزالة {{count}} ملفًا محددًا من قاعدة المعرفة، لا يزال بإمكانك رؤية الملفات في جميع الملفات، يرجى تأكيد العملية",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "عودة"
},
+ "MaxTokenSlider": {
+ "unlimited": "غير محدود"
+ },
"ModelSelect": {
"featureTag": {
"custom": "نموذج مخصص، الإعداد الافتراضي يدعم الاستدعاء الوظيفي والتعرف البصري، يرجى التحقق من قدرة النموذج على القيام بذلك بناءً على الحالة الفعلية",
"file": "يدعم هذا النموذج قراءة وتعرف الملفات المرفوعة",
"functionCall": "يدعم هذا النموذج استدعاء الوظائف",
+ "reasoning": "يدعم هذا النموذج التفكير العميق",
+ "search": "يدعم هذا النموذج البحث عبر الإنترنت",
"tokens": "يدعم هذا النموذج حتى {{tokens}} رمزًا في جلسة واحدة",
"vision": "يدعم هذا النموذج التعرف البصري"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "لا توجد نماذج ممكن تمكينها، يرجى الانتقال إلى الإعدادات لتمكينها",
+ "emptyProvider": "لا توجد مزودات مفعلة، يرجى الذهاب إلى الإعدادات لتفعيلها",
+ "goToSettings": "اذهب إلى الإعدادات",
"provider": "مزود"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "بسبب قيود أمان المتصفح، تحتاج إلى تكوين CORS لـ Ollama لاستخدامه بشكل صحيح.",
+ "linux": {
+ "env": "أضف `Environment` تحت قسم [Service]، وأضف متغير البيئة OLLAMA_ORIGINS:",
+ "reboot": "أعد تحميل systemd وأعد تشغيل Ollama",
+ "systemd": "استخدم systemd لتحرير خدمة ollama:"
+ },
+ "macos": "يرجى فتح تطبيق «الطرفية» ولصق الأوامر التالية ثم الضغط على Enter للتنفيذ",
+ "reboot": "يرجى إعادة تشغيل خدمة Ollama بعد الانتهاء من التنفيذ",
+ "title": "تكوين Ollama للسماح بالوصول عبر النطاقات المتعددة",
+ "windows": "على نظام Windows، انقر على «لوحة التحكم»، ثم انتقل إلى تحرير متغيرات البيئة للنظام. أنشئ متغير بيئة جديد باسم «OLLAMA_ORIGINS» لقائمة المستخدم الخاصة بك، وقيمته هي *، ثم انقر على «موافق/تطبيق» لحفظ التغييرات."
+ },
+ "install": {
+ "description": "يرجى التأكد من أنك قد قمت بتشغيل Ollama، إذا لم تقم بتنزيل Ollama، يرجى زيارة الموقع الرسمي <1>للتنزيل1>",
+ "docker": "إذا كنت تفضل استخدام Docker، فإن Ollama يوفر أيضًا صورة Docker رسمية، يمكنك سحبها باستخدام الأمر التالي:",
+ "linux": {
+ "command": "قم بتثبيت باستخدام الأمر التالي:",
+ "manual": "أو يمكنك الرجوع إلى <1>دليل التثبيت اليدوي لنظام Linux1> للتثبيت بنفسك."
+ },
+ "title": "تثبيت وتشغيل تطبيق Ollama محليًا",
+ "windowsTab": "Windows (نسخة المعاينة)"
+ }
+ },
+ "Thinking": {
+ "thinking": "في حالة تفكير عميق...",
+ "thought": "لقد فكرت بعمق (استغرق الأمر {{duration}} ثانية)",
+ "thoughtWithDuration": "لقد فكرت بعمق"
}
}
diff --git a/DigitalHumanWeb/locales/ar/discover.json b/DigitalHumanWeb/locales/ar/discover.json
index a3ab309..c3d1dd5 100644
--- a/DigitalHumanWeb/locales/ar/discover.json
+++ b/DigitalHumanWeb/locales/ar/discover.json
@@ -126,6 +126,10 @@
"title": "جدة الموضوع"
},
"range": "نطاق",
+ "reasoning_effort": {
+ "desc": "تُستخدم هذه الإعدادات للتحكم في شدة التفكير التي يقوم بها النموذج قبل توليد الإجابات. الشدة المنخفضة تعطي الأولوية لسرعة الاستجابة وتوفر الرموز، بينما الشدة العالية توفر تفكيرًا أكثر اكتمالًا ولكنها تستهلك المزيد من الرموز وتقلل من سرعة الاستجابة. القيمة الافتراضية هي متوسطة، مما يوازن بين دقة التفكير وسرعة الاستجابة.",
+ "title": "شدة التفكير"
+ },
"temperature": {
"desc": "تؤثر هذه الإعدادات على تنوع استجابة النموذج. القيم المنخفضة تؤدي إلى استجابات أكثر توقعًا ونمطية، بينما القيم الأعلى تشجع على استجابات أكثر تنوعًا وغير شائعة. عندما تكون القيمة 0، يعطي النموذج نفس الاستجابة دائمًا لنفس المدخل.",
"title": "عشوائية"
diff --git a/DigitalHumanWeb/locales/ar/error.json b/DigitalHumanWeb/locales/ar/error.json
index 0dc4f28..0869efd 100644
--- a/DigitalHumanWeb/locales/ar/error.json
+++ b/DigitalHumanWeb/locales/ar/error.json
@@ -12,8 +12,14 @@
"retry": "إعادة التحميل",
"title": "واجهت الصفحة مشكلة ما.."
},
- "fetchError": "فشل الطلب",
- "fetchErrorDetail": "تفاصيل الخطأ",
+ "fetchError": {
+ "detail": "تفاصيل الخطأ",
+ "title": "فشل الطلب"
+ },
+ "loginRequired": {
+ "desc": "سيتم التحويل تلقائيًا إلى صفحة تسجيل الدخول",
+ "title": "يرجى تسجيل الدخول لاستخدام هذه الميزة"
+ },
"notFound": {
"backHome": "العودة إلى الصفحة الرئيسية",
"check": "يرجى التحقق من صحة عنوان URL الخاص بك",
@@ -51,22 +57,34 @@
"431": "عذرًا، حقول رأس الطلب الخاصة بك كبيرة جدًا والخادم غير قادر على معالجتها",
"451": "عذرًا، بسبب الأسباب القانونية، يرفض الخادم توفير هذا المورد",
"500": "عذرًا، يبدو أن الخادم واجه بعض الصعوبات ولا يمكنه حاليًا استكمال طلبك، يرجى المحاولة مرة أخرى لاحقًا",
+ "501": "عذرًا، لا يعرف الخادم كيفية معالجة هذا الطلب، يرجى التأكد من صحة العملية الخاصة بك",
"502": "عذرًا، يبدو أن الخادم قد ضل الطريق ولا يمكنه حاليًا تقديم الخدمة، يرجى المحاولة مرة أخرى لاحقًا",
"503": "عذرًا، الخادم غير قادر حاليًا على معالجة طلبك، قد يكون بسبب الحمل الزائد أو الصيانة الجارية، يرجى المحاولة مرة أخرى لاحقًا",
"504": "عذرًا، الخادم لم ينتظر ردًا من الخادم الأصلي، يرجى المحاولة مرة أخرى لاحقًا",
+ "505": "عذرًا، لا يدعم الخادم إصدار HTTP الذي تستخدمه، يرجى التحديث والمحاولة مرة أخرى",
+ "506": "عذرًا، هناك مشكلة في تكوين الخادم، يرجى الاتصال بالمسؤول لحلها",
+ "507": "عذرًا، لا يوجد مساحة تخزين كافية على الخادم لمعالجة طلبك، يرجى المحاولة مرة أخرى لاحقًا",
+ "509": "عذرًا، لقد استنفد الخادم النطاق الترددي، يرجى المحاولة مرة أخرى لاحقًا",
+ "510": "عذرًا، لا يدعم الخادم الوظائف الإضافية المطلوبة، يرجى الاتصال بالمسؤول",
+ "524": "عذرًا، انتهت مهلة الخادم أثناء الانتظار للرد، قد يكون ذلك بسبب بطء الاستجابة، يرجى المحاولة مرة أخرى لاحقًا",
"AgentRuntimeError": "حدث خطأ في تشغيل نموذج Lobe اللغوي، يرجى التحقق من المعلومات التالية أو إعادة المحاولة",
+ "ConnectionCheckFailed": "الاستجابة فارغة، يرجى التحقق من أن عنوان وكيل الـ API لا ينتهي بـ `/v1`",
+ "ExceededContextWindow": "المحتوى المطلوب الحالي يتجاوز الطول الذي يمكن للنموذج معالجته، يرجى تقليل كمية المحتوى ثم إعادة المحاولة",
"FreePlanLimit": "أنت حاليًا مستخدم مجاني، لا يمكنك استخدام هذه الوظيفة، يرجى الترقية إلى خطة مدفوعة للمتابعة",
+ "InsufficientQuota": "عذرًا، لقد reached الحد الأقصى للحصة (quota) لهذه المفتاح، يرجى التحقق من رصيد الحساب الخاص بك أو زيادة حصة المفتاح ثم المحاولة مرة أخرى",
"InvalidAccessCode": "كلمة المرور غير صحيحة أو فارغة، يرجى إدخال كلمة مرور الوصول الصحيحة أو إضافة مفتاح API مخصص",
"InvalidBedrockCredentials": "فشلت مصادقة Bedrock، يرجى التحقق من AccessKeyId/SecretAccessKey وإعادة المحاولة",
"InvalidClerkUser": "عذرًا، لم تقم بتسجيل الدخول بعد، يرجى تسجيل الدخول أو التسجيل للمتابعة",
"InvalidGithubToken": "رمز وصول شخصية GitHub غير صحيح أو فارغ، يرجى التحقق من رمز وصول GitHub الشخصي والمحاولة مرة أخرى",
"InvalidOllamaArgs": "تكوين Ollama غير صحيح، يرجى التحقق من تكوين Ollama وإعادة المحاولة",
"InvalidProviderAPIKey": "{{provider}} مفتاح API غير صحيح أو فارغ، يرجى التحقق من مفتاح API {{provider}} الخاص بك وحاول مرة أخرى",
+ "InvalidVertexCredentials": "فشل التحقق من بيانات اعتماد Vertex، يرجى التحقق من بيانات الاعتماد وإعادة المحاولة",
"LocationNotSupportError": "عذرًا، لا يدعم موقعك الحالي خدمة هذا النموذج، قد يكون ذلك بسبب قيود المنطقة أو عدم توفر الخدمة. يرجى التحقق مما إذا كان الموقع الحالي يدعم استخدام هذه الخدمة، أو محاولة استخدام معلومات الموقع الأخرى.",
+ "ModelNotFound": "عذرًا، لا يمكن طلب النموذج المطلوب، قد يكون النموذج غير موجود أو أن الوصول غير مصرح به، يرجى تغيير مفتاح API أو تعديل أذونات الوصول ثم إعادة المحاولة",
"NoOpenAIAPIKey": "مفتاح API الخاص بـ OpenAI فارغ، يرجى إضافة مفتاح API الخاص بـ OpenAI",
"OllamaBizError": "خطأ في طلب خدمة Ollama، يرجى التحقق من المعلومات التالية أو إعادة المحاولة",
"OllamaServiceUnavailable": "خدمة Ollama غير متوفرة، يرجى التحقق من تشغيل Ollama بشكل صحيح أو إعدادات الـ Ollama للاتصال عبر النطاقات",
- "OpenAIBizError": "طلب خدمة OpenAI خاطئ، يرجى التحقق من المعلومات التالية أو إعادة المحاولة",
+ "PermissionDenied": "عذرًا، ليس لديك إذن للوصول إلى هذه الخدمة، يرجى التحقق مما إذا كانت مفاتيحك تمتلك إذن الوصول",
"PluginApiNotFound": "عذرًا، لا يوجد API للإضافة في وصف الإضافة، يرجى التحقق من تطابق طريقة الطلب الخاصة بك مع API الوصف",
"PluginApiParamsError": "عذرًا، فشلت التحقق من صحة معلمات الطلب للإضافة، يرجى التحقق من تطابق المعلمات مع معلومات الوصف",
"PluginFailToTransformArguments": "عذرًا، فشل تحويل معلمات استدعاء الإضافة، يرجى محاولة إعادة إنشاء رسالة المساعد أو تجربة نموذج AI ذو قدرات استدعاء أقوى",
@@ -81,8 +99,11 @@
"PluginServerError": "خطأ في استجابة الخادم لطلب الإضافة، يرجى التحقق من ملف وصف الإضافة وتكوين الإضافة وتنفيذ الخادم وفقًا لمعلومات الخطأ أدناه",
"PluginSettingsInvalid": "تحتاج هذه الإضافة إلى تكوين صحيح قبل الاستخدام، يرجى التحقق من صحة تكوينك",
"ProviderBizError": "طلب خدمة {{provider}} خاطئ، يرجى التحقق من المعلومات التالية أو إعادة المحاولة",
+ "QuotaLimitReached": "عذرًا، لقد reached الحد الأقصى من استخدام الرموز أو عدد الطلبات لهذا المفتاح. يرجى زيادة حصة هذا المفتاح أو المحاولة لاحقًا.",
"StreamChunkError": "خطأ في تحليل كتلة الرسالة لطلب التدفق، يرجى التحقق مما إذا كانت واجهة برمجة التطبيقات الحالية تتوافق مع المعايير، أو الاتصال بمزود واجهة برمجة التطبيقات الخاصة بك للاستفسار.",
- "SubscriptionPlanLimit": "لقد استنفذت حصتك من الاشتراك، لا يمكنك استخدام هذه الوظيفة، يرجى الترقية إلى خطة أعلى أو شراء حزمة موارد للمتابعة",
+ "SubscriptionKeyMismatch": "نعتذر، بسبب عطل عرضي في النظام، فإن استخدام الاشتراك الحالي غير فعال مؤقتًا. يرجى النقر على الزر أدناه لاستعادة الاشتراك، أو مراسلتنا عبر البريد الإلكتروني للحصول على الدعم.",
+ "SubscriptionPlanLimit": "لقد استنفدت نقاط اشتراكك، ولا يمكنك استخدام هذه الميزة. يرجى الترقية إلى خطة أعلى، أو تكوين واجهة برمجة التطبيقات للنموذج المخصص للاستمرار في الاستخدام",
+ "SystemTimeNotMatchError": "عذرًا، وقت النظام لديك لا يتطابق مع الخادم، يرجى التحقق من وقت النظام لديك ثم إعادة المحاولة",
"UnknownChatFetchError": "عذرًا، حدث خطأ غير معروف في الطلب، يرجى التحقق من المعلومات التالية أو المحاولة مرة أخرى"
},
"stt": {
diff --git a/DigitalHumanWeb/locales/ar/metadata.json b/DigitalHumanWeb/locales/ar/metadata.json
index 034b748..3d1a0c8 100644
--- a/DigitalHumanWeb/locales/ar/metadata.json
+++ b/DigitalHumanWeb/locales/ar/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "تابع الميزات الجديدة والتحسينات في {{appName}} باستمرار",
+ "title": "سجل التحديثات"
+ },
"chat": {
"description": "{{appName}} يقدم لك أفضل تجربة لاستخدام ChatGPT وClaude وGemini وOLLaMA WebUI",
"title": "{{appName}}: أداة الذكاء الاصطناعي الشخصية، امنح نفسك دماغًا أكثر ذكاءً"
diff --git a/DigitalHumanWeb/locales/ar/modelProvider.json b/DigitalHumanWeb/locales/ar/modelProvider.json
index c15f1f3..a331da1 100644
--- a/DigitalHumanWeb/locales/ar/modelProvider.json
+++ b/DigitalHumanWeb/locales/ar/modelProvider.json
@@ -19,6 +19,24 @@
"title": "مفتاح API"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "إصدار واجهة برمجة التطبيقات Azure، يتبع تنسيق YYYY-MM-DD، راجع [الإصدار الأحدث](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "الحصول على القائمة",
+ "title": "إصدار واجهة برمجة التطبيقات Azure"
+ },
+ "endpoint": {
+ "desc": "ابحث عن نقطة نهاية استدلال نموذج Azure AI من نظرة عامة على مشروع Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "نقطة نهاية Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "ابحث عن مفتاح واجهة برمجة التطبيقات من نظرة عامة على مشروع Azure AI",
+ "placeholder": "مفتاح Azure",
+ "title": "المفتاح"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "أدخل AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "استخدام معلومات المصادقة الخاصة بـ Bedrock المخصصة"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "يرجى ملء Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "أدخل رقم حساب Cloudflare أو عنوان URL API المخصص",
+ "placeholder": "رقم حساب Cloudflare / عنوان URL API المخصص",
+ "title": "رقم حساب Cloudflare / عنوان URL API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "يرجى إدخال مفتاح API الخاص بك",
+ "title": "مفتاح API"
+ },
+ "basicTitle": "المعلومات الأساسية",
+ "configTitle": "معلومات التكوين",
+ "confirm": "إنشاء جديد",
+ "createSuccess": "تم الإنشاء بنجاح",
+ "description": {
+ "placeholder": "نبذة عن مزود الخدمة (اختياري)",
+ "title": "نبذة عن مزود الخدمة"
+ },
+ "id": {
+ "desc": "معرف فريد لمزود الخدمة، لا يمكن تعديله بعد الإنشاء",
+ "format": "يمكن أن يحتوي فقط على أرقام، أحرف صغيرة، شرطات (-) وشرطات سفلية (_) ",
+ "placeholder": "يفضل أن يكون بالكامل بحروف صغيرة، مثل openai، لن يمكن تعديله بعد الإنشاء",
+ "required": "يرجى إدخال معرف المزود",
+ "title": "معرف المزود"
+ },
+ "logo": {
+ "required": "يرجى تحميل شعار المزود بشكل صحيح",
+ "title": "شعار المزود"
+ },
+ "name": {
+ "placeholder": "يرجى إدخال اسم العرض لمزود الخدمة",
+ "required": "يرجى إدخال اسم المزود",
+ "title": "اسم المزود"
+ },
+ "proxyUrl": {
+ "required": "يرجى إدخال عنوان الوكيل",
+ "title": "عنوان الوكيل"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "يرجى اختيار نوع SDK",
+ "title": "تنسيق الطلب"
+ },
+ "title": "إنشاء مزود AI مخصص"
+ },
"github": {
"personalAccessToken": {
"desc": "أدخل رمز الوصول الشخصي الخاص بك على Github، انقر [هنا](https://github.com/settings/tokens) لإنشاء واحد",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "أدخل رمز HuggingFace الخاص بك، انقر [هنا](https://huggingface.co/settings/tokens) لإنشاء واحد",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "رمز HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "مزود الخدمة غير مفعل",
+ "enabled": "مزود الخدمة مفعل"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "إضافة مزود خدمة مخصص",
+ "all": "الكل",
+ "list": {
+ "disabled": "غير مفعل",
+ "enabled": "مفعل"
+ },
+ "notFound": "لم يتم العثور على نتائج البحث",
+ "searchProviders": "البحث عن مزودين...",
+ "sort": "ترتيب مخصص"
+ },
"ollama": {
"checker": {
"desc": "اختبر ما إذا تم إدخال عنوان الوكيل بشكل صحيح",
@@ -69,39 +163,15 @@
"title": "أسماء النماذج المخصصة"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. It will resume from where it left off if you restart the download.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "أولاما يقوم بتنزيل هذا النموذج، يرجى عدم إغلاق هذه الصفحة إذا أمكن. سيتم استئناف التنزيل من النقطة التي تم قطعها عند إعادة التحميل",
+ "remainingTime": "الوقت المتبقي",
+ "speed": "سرعة التنزيل",
+ "title": "جارٍ تنزيل النموذج {{model}} "
},
"endpoint": {
- "desc": "أدخل عنوان واجهة برمجة التطبيقات الخاص بـ Ollama، إذا لم يتم تحديده محليًا، يمكن تركه فارغًا",
+ "desc": "يجب أن تحتوي على http(s)://، يمكن تركها فارغة إذا لم يتم تحديدها محليًا",
"title": "عنوان وكيل الواجهة"
},
- "setup": {
- "cors": {
- "description": "بسبب قيود الأمان في المتصفح، يجب تكوين الوصول عبر المواقع المختلفة لـ Ollama لاستخدامه بشكل صحيح.",
- "linux": {
- "env": "في القسم [Service]، أضف `Environment` وأضف متغير البيئة OLLAMA_ORIGINS:",
- "reboot": "أعد تحميل systemd وأعد تشغيل Ollama",
- "systemd": "استدعاء تحرير خدمة ollama في systemd:"
- },
- "macos": "افتح تطبيق \"Terminal\" والصق الأمر التالي، ثم اضغط على Enter للتشغيل.",
- "reboot": "يرجى إعادة تشغيل خدمة Ollama بعد الانتهاء من التنفيذ",
- "title": "تكوين Ollama للسماح بالوصول عبر المواقع المختلفة",
- "windows": "على نظام Windows، انقر فوق \"لوحة التحكم\"، ثم ادخل إلى تحرير متغيرات البيئة النظامية. قم بإنشاء متغير بيئي بعنوان \"OLLAMA_ORIGINS\" لحساب المستخدم الخاص بك، واجعل قيمته * ثم انقر على \"موافق/تطبيق\" للحفظ."
- },
- "install": {
- "description": "يرجى التأكد من أنك قد قمت بتشغيل Ollama ، إذا لم تقم بتنزيل Ollama ، يرجى زيارة الموقع الرسمي <1>للتنزيل1>",
- "docker": "إذا كنت تفضل استخدام Docker، يوفر Ollama أيضًا صور Docker الرسمية، يمكنك سحبها باستخدام الأمر التالي:",
- "linux": {
- "command": "قم بتثبيته باستخدام الأمر التالي:",
- "manual": "أو يمكنك الرجوع إلى <1>دليل تثبيت Linux يدويًا1> للقيام بالتثبيت بنفسك."
- },
- "title": "تثبيت وتشغيل تطبيق Ollama محليًا",
- "windowsTab": "Windows (نسخة معاينة)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Cancel Download",
@@ -112,6 +182,156 @@
"title": "Download specified Ollama model"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "سيتم استخدام خوارزمية التشفير <1>AES-GCM1> لتشفير مفتاحك وعنوان الوكيل وما إلى ذلك",
+ "apiKey": {
+ "desc": "يرجى إدخال مفتاح API الخاص بك {{name}}",
+ "placeholder": "{{name}} مفتاح API",
+ "title": "مفتاح API"
+ },
+ "baseURL": {
+ "desc": "يجب أن يحتوي على http(s)://",
+ "invalid": "يرجى إدخال عنوان URL صالح",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "عنوان وكيل API"
+ },
+ "checker": {
+ "button": "تحقق",
+ "desc": "اختبار ما إذا كان مفتاح API وعنوان الوكيل قد تم إدخالهما بشكل صحيح",
+ "pass": "تم التحقق بنجاح",
+ "title": "اختبار الاتصال"
+ },
+ "fetchOnClient": {
+ "desc": "سيتم بدء طلب الجلسة مباشرة من المتصفح، مما قد يحسن سرعة الاستجابة",
+ "title": "استخدام وضع الطلب من العميل"
+ },
+ "helpDoc": "دليل التكوين",
+ "waitingForMore": "المزيد من النماذج قيد <1>التخطيط للإدماج1>، يرجى الانتظار"
+ },
+ "createNew": {
+ "title": "إنشاء نموذج AI مخصص"
+ },
+ "item": {
+ "config": "تكوين النموذج",
+ "customModelCards": {
+ "addNew": "إنشاء وإضافة نموذج {{id}}",
+ "confirmDelete": "سيتم حذف هذا النموذج المخصص، ولن يمكن استعادته بعد الحذف، يرجى توخي الحذر."
+ },
+ "delete": {
+ "confirm": "هل تؤكد حذف النموذج {{displayName}}؟",
+ "success": "تم الحذف بنجاح",
+ "title": "حذف النموذج"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "الحقل المطلوب في Azure OpenAI",
+ "placeholder": "يرجى إدخال اسم نشر النموذج في Azure",
+ "title": "اسم نشر النموذج"
+ },
+ "deployName": {
+ "extra": "سيتم استخدام هذا الحقل كمعرف نموذج عند إرسال الطلب",
+ "placeholder": "يرجى إدخال اسم أو معرف النشر الفعلي للنموذج",
+ "title": "اسم نشر النموذج"
+ },
+ "displayName": {
+ "placeholder": "يرجى إدخال اسم العرض للنموذج، مثل ChatGPT، GPT-4، إلخ",
+ "title": "اسم عرض النموذج"
+ },
+ "files": {
+ "extra": "تنفيذ تحميل الملفات الحالي هو مجرد حل Hack، يقتصر على التجربة الذاتية. يرجى الانتظار حتى يتم تنفيذ القدرة الكاملة لتحميل الملفات لاحقًا",
+ "title": "دعم تحميل الملفات"
+ },
+ "functionCall": {
+ "extra": "هذا الإعداد سيفتح فقط قدرة النموذج على استخدام الأدوات، مما يسمح بإضافة مكونات إضافية من نوع الأدوات للنموذج. لكن ما إذا كان يمكن استخدام الأدوات فعليًا يعتمد تمامًا على النموذج نفسه، يرجى اختبار مدى قابليته للاستخدام",
+ "title": "دعم استخدام الأدوات"
+ },
+ "id": {
+ "extra": "لا يمكن تعديله بعد الإنشاء، سيتم استخدامه كمعرف نموذج عند استدعاء الذكاء الاصطناعي",
+ "placeholder": "يرجى إدخال معرف النموذج، مثل gpt-4o أو claude-3.5-sonnet",
+ "title": "معرف النموذج"
+ },
+ "modalTitle": "تكوين النموذج المخصص",
+ "reasoning": {
+ "extra": "هذا الإعداد سيفتح فقط قدرة النموذج على التفكير العميق، التأثير الفعلي يعتمد بالكامل على النموذج نفسه، يرجى اختبار ما إذا كان هذا النموذج يمتلك القدرة على التفكير العميق القابل للاستخدام",
+ "title": "يدعم التفكير العميق"
+ },
+ "tokens": {
+ "extra": "تعيين الحد الأقصى لعدد الرموز المدعومة من قبل النموذج",
+ "title": "أقصى نافذة سياق",
+ "unlimited": "غير محدود"
+ },
+ "vision": {
+ "extra": "سيؤدي هذا التكوين إلى فتح إعدادات تحميل الصور في التطبيق، ما إذا كان يدعم التعرف يعتمد بالكامل على النموذج نفسه، يرجى اختبار قابلية استخدام التعرف البصري لهذا النموذج بنفسك",
+ "title": "دعم التعرف البصري"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/صورة",
+ "inputCharts": "${{amount}}/M حرف",
+ "inputMinutes": "${{amount}}/دقيقة",
+ "inputTokens": "إدخال ${{amount}}/م",
+ "outputTokens": "إخراج ${{amount}}/م"
+ },
+ "releasedAt": "صدر في {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "إضافة نموذج",
+ "disabled": "غير مفعل",
+ "disabledActions": {
+ "showMore": "عرض الكل"
+ },
+ "empty": {
+ "desc": "يرجى إنشاء نموذج مخصص أو سحب نموذج للبدء في الاستخدام",
+ "title": "لا توجد نماذج متاحة"
+ },
+ "enabled": "مفعل",
+ "enabledActions": {
+ "disableAll": "تعطيل الكل",
+ "enableAll": "تفعيل الكل",
+ "sort": "ترتيب النموذج حسب التخصيص"
+ },
+ "enabledEmpty": "لا توجد نماذج مفعلة، يرجى تفعيل النماذج المفضلة لديك من القائمة أدناه~",
+ "fetcher": {
+ "clear": "مسح النماذج المستخرجة",
+ "fetch": "الحصول على قائمة النماذج",
+ "fetching": "جارٍ الحصول على قائمة النماذج...",
+ "latestTime": "آخر تحديث: {{time}}",
+ "noLatestTime": "لم يتم الحصول على القائمة بعد"
+ },
+ "resetAll": {
+ "conform": "هل أنت متأكد من إعادة تعيين جميع التعديلات على النموذج الحالي؟ بعد إعادة التعيين، ستعود قائمة النماذج الحالية إلى الحالة الافتراضية",
+ "success": "تمت إعادة التعيين بنجاح",
+ "title": "إعادة تعيين جميع التعديلات"
+ },
+ "search": "ابحث عن نموذج...",
+ "searchResult": "تم العثور على {{count}} نموذج",
+ "title": "قائمة النماذج",
+ "total": "إجمالي {{count}} نموذج متاح"
+ },
+ "searchNotFound": "لم يتم العثور على نتائج البحث"
+ },
+ "sortModal": {
+ "success": "تم تحديث الترتيب بنجاح",
+ "title": "ترتيب مخصص",
+ "update": "تحديث"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "سيتم حذف مزود AI هذا، ولن يمكن استعادته بعد الحذف، هل تؤكد الحذف؟",
+ "deleteSuccess": "تم الحذف بنجاح",
+ "tooltip": "تحديث التكوين الأساسي للمزود",
+ "updateSuccess": "تم التحديث بنجاح"
+ },
+ "updateCustomAiProvider": {
+ "title": "تحديث إعدادات مزود الذكاء الاصطناعي المخصص"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "أدخل مفاتيح Vertex AI الخاصة بك",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "مفاتيح Vertex AI"
+ }
+ },
"zeroone": {
"title": "01.AI الأشياء الصغرى"
},
diff --git a/DigitalHumanWeb/locales/ar/models.json b/DigitalHumanWeb/locales/ar/models.json
index 2173242..38225d8 100644
--- a/DigitalHumanWeb/locales/ar/models.json
+++ b/DigitalHumanWeb/locales/ar/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B، يقدم أداءً ممتازًا في التطبيقات الصناعية بفضل مجموعة التدريب الغنية."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat هو متغير من سلسلة Yi-1.5، وهو نموذج دردشة مفتوح المصدر. Yi-1.5 هو إصدار مطور من Yi، تم تدريبه على 500B من البيانات عالية الجودة، وتم تحسينه على 3M من عينات التعديل المتنوعة. مقارنةً بـ Yi، يظهر Yi-1.5 أداءً أقوى في الترميز، والرياضيات، والاستدلال، والامتثال للتعليمات، مع الحفاظ على قدرة ممتازة في فهم اللغة، والاستدلال العام، وفهم القراءة. يتوفر هذا النموذج بإصدارات بطول سياق 4K و16K و32K، مع إجمالي تدريب يصل إلى 3.6T توكن."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B يدعم 16K توكن، ويوفر قدرة توليد لغوية فعالة وسلسة."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Everything، أحدث نموذج مفتوح المصدر تم تعديله، يحتوي على 34 مليار معلمة، ويدعم تعديلات متعددة لمشاهد الحوار، مع بيانات تدريب عالية الجودة تتماشى مع تفضيلات البشر."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Everything، أحدث نموذج مفتوح المصدر تم تعديله، يحتوي على 9 مليار معلمة، ويدعم تعديلات متعددة لمشاهد الحوار، مع بيانات تدريب عالية الجودة تتماشى مع تفضيلات البشر."
+ },
"360gpt-pro": {
"description": "360GPT Pro كعضو مهم في سلسلة نماذج 360 AI، يلبي احتياجات معالجة النصوص المتنوعة بفعالية، ويدعم فهم النصوص الطويلة والحوار المتعدد الجولات."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K يركز على الأمان الدلالي والتوجيه المسؤول، مصمم خصيصًا لتطبيقات تتطلب مستوى عالٍ من الأمان في المحتوى، مما يضمن دقة وموثوقية تجربة المستخدم."
},
+ "360gpt2-o1": {
+ "description": "يستخدم 360gpt2-o1 البحث الشجري لبناء سلسلة التفكير، ويقدم آلية للتفكير العميق، ويستخدم التعلم المعزز للتدريب، مما يمنح النموذج القدرة على التفكير الذاتي وتصحيح الأخطاء."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro هو نموذج متقدم لمعالجة اللغة الطبيعية تم إطلاقه من قبل شركة 360، يتمتع بقدرات استثنائية في توليد وفهم النصوص، خاصة في مجالات التوليد والإبداع، ويستطيع التعامل مع مهام تحويل اللغة المعقدة وأداء الأدوار."
},
+ "360zhinao2-o1": {
+ "description": "يستخدم 360zhinao2-o1 البحث الشجري لبناء سلسلة التفكير، ويقدم آلية للتفكير النقدي، ويستخدم التعلم المعزز للتدريب، مما يمنح النموذج القدرة على التفكير الذاتي وتصحيح الأخطاء."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra هو أقوى إصدار في سلسلة نماذج Spark، حيث يعزز فهم النصوص وقدرات التلخيص مع تحسين روابط البحث عبر الإنترنت. إنه حل شامل يهدف إلى تعزيز إنتاجية المكتب والاستجابة الدقيقة للاحتياجات، ويعتبر منتجًا ذكيًا رائدًا في الصناعة."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "النموذج الأول في البلاد من حيث القدرة، يتفوق على النماذج الرئيسية الأجنبية في المهام الصينية مثل الموسوعات، والنصوص الطويلة، والإبداع. كما يتمتع بقدرات متعددة الوسائط رائدة في الصناعة، ويظهر أداءً ممتازًا في العديد من معايير التقييم الموثوقة."
},
+ "Baichuan4-Air": {
+ "description": "النموذج الأول محليًا، يتفوق على النماذج الرئيسية الأجنبية في المهام الصينية مثل المعرفة الموسوعية، النصوص الطويلة، والإبداع. كما يتمتع بقدرات متعددة الوسائط الرائدة في الصناعة، ويظهر أداءً ممتازًا في العديد من معايير التقييم الموثوقة."
+ },
+ "Baichuan4-Turbo": {
+ "description": "النموذج الأول محليًا، يتفوق على النماذج الرئيسية الأجنبية في المهام الصينية مثل المعرفة الموسوعية، النصوص الطويلة، والإبداع. كما يتمتع بقدرات متعددة الوسائط الرائدة في الصناعة، ويظهر أداءً ممتازًا في العديد من معايير التقييم الموثوقة."
+ },
+ "DeepSeek-R1": {
+ "description": "نموذج LLM المتقدم والفعال، بارع في الاستدلال والرياضيات والبرمجة."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 - النموذج الأكبر والأذكى في مجموعة DeepSeek - تم تقطيره إلى هيكل Llama 70B. بناءً على اختبارات الأداء والتقييمات البشرية، فإن هذا النموذج أكثر ذكاءً من Llama 70B الأصلي، خاصة في المهام التي تتطلب الدقة الرياضية والحقائق."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "نموذج التقطير DeepSeek-R1 المستند إلى Qwen2.5-Math-1.5B، تم تحسين أداء الاستدلال من خلال التعلم المعزز وبيانات البداية الباردة، ويعيد نموذج المصدر فتح معايير المهام المتعددة."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "نموذج التقطير DeepSeek-R1 المستند إلى Qwen2.5-14B، تم تحسين أداء الاستدلال من خلال التعلم المعزز وبيانات البداية الباردة، ويعيد نموذج المصدر فتح معايير المهام المتعددة."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "تسلسل DeepSeek-R1 يحسن أداء الاستدلال من خلال التعلم المعزز وبيانات البداية الباردة، ويعيد نموذج المصدر فتح معايير المهام المتعددة، متجاوزًا مستوى OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "نموذج التقطير DeepSeek-R1 المستند إلى Qwen2.5-Math-7B، تم تحسين أداء الاستدلال من خلال التعلم المعزز وبيانات البداية الباردة، ويعيد نموذج المصدر فتح معايير المهام المتعددة."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "دو باو 1.5 فيجن برو هو نموذج كبير متعدد الوسائط تم تحديثه حديثًا، يدعم التعرف على الصور بدقة أي دقة ونسب عرض إلى ارتفاع متطرفة، مما يعزز القدرة على الاستدلال البصري، والتعرف على الوثائق، وفهم المعلومات التفصيلية، والامتثال للتعليمات."
+ },
+ "Doubao-lite-128k": {
+ "description": "دو باو-لايت يوفر سرعة استجابة فائقة وقيمة جيدة للكلفة، ويقدم خيارات أكثر مرونة للعملاء في سيناريوهات مختلفة. يدعم الاستدلال والتنقيح بسعة سياق 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "دو باو-لايت يوفر سرعة استجابة فائقة وقيمة جيدة للكلفة، ويقدم خيارات أكثر مرونة للعملاء في سيناريوهات مختلفة. يدعم الاستدلال والتنقيح بسعة سياق 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "دو باو-لايت يوفر سرعة استجابة فائقة وقيمة جيدة للكلفة، ويقدم خيارات أكثر مرونة للعملاء في سيناريوهات مختلفة. يدعم الاستدلال والتنقيح بسعة سياق 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "النموذج الرئيسي الأفضل أداءً، مناسب لمعالجة المهام المعقدة، يقدم أداءً جيدًا في السيناريوهات مثل الاستجابة المرجعية، والتلخيص، والإبداع، وتصنيف النصوص، وألعاب الأدوار. يدعم الاستدلال والتنقيح بسعة سياق 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "أفضل نموذج رئيسي من حيث الأداء، مناسب لمعالجة المهام المعقدة، حيث يظهر أداءً جيدًا في سيناريوهات مثل الأسئلة والأجوبة المرجعية، والتلخيص، والإبداع، وتصنيف النصوص، وأدوار الشخصيات. يدعم استدلال نافذة السياق 256k والتعديل الدقيق."
+ },
+ "Doubao-pro-32k": {
+ "description": "النموذج الرئيسي الأفضل أداءً، مناسب لمعالجة المهام المعقدة، يقدم أداءً جيدًا في السيناريوهات مثل الاستجابة المرجعية، والتلخيص، والإبداع، وتصنيف النصوص، وألعاب الأدوار. يدعم الاستدلال والتنقيح بسعة سياق 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "النموذج الرئيسي الأفضل أداءً، مناسب لمعالجة المهام المعقدة، يقدم أداءً جيدًا في السيناريوهات مثل الاستجابة المرجعية، والتلخيص، والإبداع، وتصنيف النصوص، وألعاب الأدوار. يدعم الاستدلال والتنقيح بسعة سياق 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "نموذج دو باو فيجن هو نموذج كبير متعدد الوسائط تم إطلاقه من قبل دو باو، يتمتع بقدرة قوية على فهم الصور والاستدلال، بالإضافة إلى القدرة الدقيقة على فهم التعليمات. أظهر النموذج أداءً قويًا في استخراج معلومات النصوص من الصور، ومهام الاستدلال المعتمدة على الصور، مما يجعله مناسبًا لمهام الأسئلة والأجوبة البصرية الأكثر تعقيدًا وعمومية."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "نموذج دو باو فيجن هو نموذج كبير متعدد الوسائط تم إطلاقه من قبل دو باو، يتمتع بقدرة قوية على فهم الصور والاستدلال، بالإضافة إلى القدرة الدقيقة على فهم التعليمات. أظهر النموذج أداءً قويًا في استخراج معلومات النصوص من الصور، ومهام الاستدلال المعتمدة على الصور، مما يجعله مناسبًا لمهام الأسئلة والأجوبة البصرية الأكثر تعقيدًا وعمومية."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، يغطي كمية هائلة من البيانات باللغة الصينية والإنجليزية، ويتميز بقدرات عامة قوية، يمكنه تلبية معظم متطلبات الحوار، والإجابة على الأسئلة، وإنشاء المحتوى، وتطبيقات الإضافات؛ يدعم الاتصال التلقائي بإضافات بحث بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، يغطي كمية هائلة من البيانات باللغة الصينية والإنجليزية، ويتميز بقدرات عامة قوية، يمكنه تلبية معظم متطلبات الحوار، والإجابة على الأسئلة، وإنشاء المحتوى، وتطبيقات الإضافات؛ يدعم الاتصال التلقائي بإضافات بحث بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، يغطي كمية هائلة من البيانات باللغة الصينية والإنجليزية، ويتميز بقدرات عامة قوية، يمكنه تلبية معظم متطلبات الحوار، والإجابة على الأسئلة، وإنشاء المحتوى، وتطبيقات الإضافات؛ يدعم الاتصال التلقائي بإضافات بحث بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي شهد ترقية شاملة في القدرات مقارنةً بـERNIE 3.5، ويستخدم على نطاق واسع في مجالات متعددة لمهام معقدة؛ يدعم الاتصال التلقائي بإضافات بحث بايدو لضمان تحديث معلومات الإجابة."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي شهد ترقية شاملة في القدرات مقارنةً بـERNIE 3.5، ويستخدم على نطاق واسع في مجالات متعددة لمهام معقدة؛ يدعم الاتصال التلقائي بإضافات بحث بايدو لضمان تحديث معلومات الإجابة."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي يظهر أداءً ممتازًا في مجالات متعددة، مما يجعله مناسبًا لمجموعة واسعة من المهام المعقدة؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الأسئلة والأجوبة. مقارنة بـ ERNIE 4.0، يظهر أداءً أفضل."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، يتميز بأداء شامل ممتاز، ويستخدم على نطاق واسع في مجالات متعددة لمهام معقدة؛ يدعم الاتصال التلقائي بإضافات بحث بايدو لضمان تحديث معلومات الإجابة. مقارنةً بـERNIE 4.0، يتمتع بأداء أفضل."
+ },
+ "ERNIE-Character-8K": {
+ "description": "نموذج اللغة الكبير الذي طورته بايدو، مناسب لمشاهد الألعاب، والحوار مع خدمة العملاء، وأدوار الحوار، وغيرها من تطبيقات السيناريوهات، حيث يتميز بأسلوب شخصيات واضح ومتسق، وقدرة قوية على اتباع التعليمات، وأداء استدلال أفضل."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "نموذج اللغة الخفيف الذي طورته بايدو، يجمع بين أداء النموذج الممتاز وأداء الاستدلال، ويتميز بأداء أفضل من ERNIE Lite، مناسب للاستخدام في بطاقات تسريع الذكاء الاصطناعي ذات القدرة الحاسوبية المنخفضة."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "نموذج اللغة الكبير عالي الأداء الذي طورته بايدو، والذي تم إصداره في عام 2024، يتمتع بقدرات عامة ممتازة، مناسب كنموذج أساسي للتعديل الدقيق، مما يساعد على معالجة مشكلات السيناريوهات المحددة بشكل أفضل، مع أداء استدلال ممتاز."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "نموذج اللغة الكبير عالي الأداء الذي طورته بايدو، والذي تم إصداره في عام 2024، يتمتع بقدرات عامة ممتازة، ويتميز بأداء أفضل من ERNIE Speed، مناسب كنموذج أساسي للتعديل الدقيق، مما يساعد على معالجة مشكلات السيناريوهات المحددة بشكل أفضل، مع أداء استدلال ممتاز."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) هو نموذج مبتكر، مناسب لتطبيقات متعددة المجالات والمهام المعقدة."
},
- "Max-32k": {
- "description": "Spark Max 32K مزود بقدرة معالجة سياقية كبيرة، وفهم أقوى للسياق وقدرة على الاستدلال المنطقي، يدعم إدخال نصوص تصل إلى 32K توكن، مناسب لقراءة الوثائق الطويلة، وأسئلة وأجوبة المعرفة الخاصة، وغيرها من السيناريوهات."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B هو نموذج قوي للغة البصرية، يدعم المعالجة متعددة الوسائط للصورة والنص، قادر على التعرف بدقة على محتوى الصورة وتوليد أوصاف أو إجابات ذات صلة."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B هو نموذج قوي للغة البصرية، يدعم المعالجة متعددة الوسائط للصورة والنص، قادر على التعرف بدقة على محتوى الصورة وتوليد أوصاف أو إجابات ذات صلة."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "قدرات استدلال الصور الممتازة على الصور عالية الدقة، مناسبة لتطبيقات الفهم البصري."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "قدرات استدلال الصور المتقدمة المناسبة لتطبيقات الوكلاء في الفهم البصري."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct هو أحد أحدث نماذج اللغة الكبيرة التي أصدرتها Alibaba Cloud. يتمتع هذا النموذج بقدرات محسنة بشكل ملحوظ في مجالات الترميز والرياضيات. كما يوفر دعمًا للغات متعددة، تغطي أكثر من 29 لغة، بما في ذلك الصينية والإنجليزية. أظهر النموذج تحسينات ملحوظة في اتباع التعليمات، وفهم البيانات الهيكلية، وتوليد المخرجات الهيكلية (خاصة JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct هو أحد أحدث نماذج اللغة الكبيرة التي أصدرتها Alibaba Cloud. يتمتع هذا النموذج بقدرات محسنة بشكل ملحوظ في مجالات الترميز والرياضيات. كما يوفر دعمًا للغات متعددة، تغطي أكثر من 29 لغة، بما في ذلك الصينية والإنجليزية. أظهر النموذج تحسينات ملحوظة في اتباع التعليمات، وفهم البيانات الهيكلية، وتوليد المخرجات الهيكلية (خاصة JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "نموذج نصي تم تعديله تحت الإشراف من Llama 3.1، تم تحسينه لحالات الحوار متعددة اللغات، حيث يتفوق في العديد من نماذج الدردشة مفتوحة ومغلقة المصدر المتاحة في المعايير الصناعية الشائعة."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO هو دمج متعدد النماذج مرن للغاية، يهدف إلى تقديم تجربة إبداعية ممتازة."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "نموذج نصي تم تعديله تحت الإشراف من Llama 3.1، تم تحسينه لحالات الحوار متعددة اللغات، حيث يتفوق في العديد من نماذج الدردشة مفتوحة ومغلقة المصدر المتاحة في المعايير الصناعية الشائعة."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "نموذج نصي تم تعديله تحت الإشراف من Llama 3.1، تم تحسينه لحالات الحوار متعددة اللغات، حيث يتفوق في العديد من نماذج الدردشة مفتوحة ومغلقة المصدر المتاحة في المعايير الصناعية الشائعة."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "نموذج لغوي صغير متقدم وحديث، يتمتع بفهم اللغة وقدرات استدلال ممتازة وقدرة على توليد النصوص."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "نموذج لغوي صغير متقدم وحديث، يتمتع بفهم اللغة وقدرات استدلال ممتازة وقدرة على توليد النصوص."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 هو النموذج اللغوي مفتوح المصدر متعدد اللغات الأكثر تقدمًا في سلسلة Llama، حيث يقدم تجربة تنافس أداء نموذج 405B بتكلفة منخفضة للغاية. يعتمد على هيكل Transformer، وتم تحسين فائدته وأمانه من خلال التعديل الدقيق تحت الإشراف (SFT) والتعلم المعزز من خلال ردود الفعل البشرية (RLHF). تم تحسين إصدار التعديل الخاص به ليكون مثاليًا للحوار متعدد اللغات، حيث يتفوق في العديد من المعايير الصناعية على العديد من نماذج الدردشة مفتوحة ومغلقة المصدر. تاريخ انتهاء المعرفة هو ديسمبر 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "في سلسلة نماذج MiniMax-01، قمنا بإجراء ابتكارات جريئة: تم تنفيذ آلية الانتباه الخطي على نطاق واسع لأول مرة، لم يعد هيكل Transformer التقليدي هو الخيار الوحيد. يصل عدد معلمات هذا النموذج إلى 456 مليار، مع تنشيط واحد يصل إلى 45.9 مليار. الأداء الشامل للنموذج يتساوى مع النماذج الرائدة في الخارج، بينما يمكنه معالجة سياقات تصل إلى 4 ملايين توكن، وهو 32 مرة من GPT-4o و20 مرة من Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) هو نموذج تعليمات عالي الدقة، مناسب للحسابات المعقدة."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) يوفر مخرجات لغوية محسنة وإمكانيات تطبيق متنوعة."
- },
- "Phi-3-5-mini-instruct": {
- "description": "تحديث لنموذج Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "أظهر InternVL2 أداءً رائعًا في مجموعة متنوعة من مهام اللغة البصرية، بما في ذلك فهم الوثائق والرسوم البيانية، وفهم النصوص في المشاهد، وOCR، وحل المشكلات العلمية والرياضية."
},
"Phi-3-medium-128k-instruct": {
"description": "نموذج Phi-3-medium نفسه، ولكن مع حجم سياق أكبر لـ RAG أو التوجيه القليل."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "نموذج بحجم 7B، يثبت جودة أفضل من Phi-3-mini، مع التركيز على البيانات الكثيفة في التفكير عالية الجودة."
},
- "Pro-128k": {
- "description": "Spark Pro-128K مزود بقدرة معالجة سياق ضخمة، يمكنه التعامل مع معلومات سياق تصل إلى 128K، مما يجعله مثاليًا للمحتوى الطويل الذي يتطلب تحليلًا شاملًا ومعالجة علاقات منطقية طويلة الأمد، ويمكنه تقديم منطق سلس ودقيق ودعم متنوع للاقتباسات في التواصل النصي المعقد."
+ "Phi-3.5-mini-instruct": {
+ "description": "النسخة المحدثة من نموذج Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "النسخة المحدثة من نموذج Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "أظهر InternVL2 أداءً رائعًا في مجموعة متنوعة من مهام اللغة البصرية، بما في ذلك فهم الوثائق والرسوم البيانية، وفهم النصوص في المشاهد، وOCR، وحل المشكلات العلمية والرياضية."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct هو نموذج لغوي كبير تم تعديله وفقًا للتعليمات في سلسلة Qwen2، بحجم 1.5B. يعتمد هذا النموذج على بنية Transformer، ويستخدم تقنيات مثل دالة تنشيط SwiGLU، وتحويل QKV، والانتباه الجماعي. أظهر أداءً ممتازًا في فهم اللغة، والتوليد، والقدرات متعددة اللغات، والترميز، والرياضيات، والاستدلال في العديد من اختبارات المعايير، متجاوزًا معظم النماذج مفتوحة المصدر."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct هو نموذج لغوي كبير تم تعديله وفقًا للتعليمات في سلسلة Qwen2، بحجم 7B. يعتمد هذا النموذج على بنية Transformer، ويستخدم تقنيات مثل دالة تنشيط SwiGLU، وتحويل QKV، والانتباه الجماعي. يمكنه معالجة المدخلات الكبيرة. أظهر النموذج أداءً ممتازًا في فهم اللغة، والتوليد، والقدرات متعددة اللغات، والترميز، والرياضيات، والاستدلال في العديد من اختبارات المعايير، متجاوزًا معظم النماذج مفتوحة المصدر."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL هو النسخة الأحدث من نموذج Qwen-VL، وقد حقق أداءً متقدمًا في اختبارات الفهم البصري."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct هو أحد أحدث نماذج اللغة الكبيرة التي أصدرتها Alibaba Cloud. يتمتع هذا النموذج بقدرات محسنة بشكل ملحوظ في مجالات الترميز والرياضيات. كما يوفر دعمًا للغات متعددة، تغطي أكثر من 29 لغة، بما في ذلك الصينية والإنجليزية. أظهر النموذج تحسينات ملحوظة في اتباع التعليمات، وفهم البيانات الهيكلية، وتوليد المخرجات الهيكلية (خاصة JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct هو أحدث إصدار من سلسلة نماذج اللغة الكبيرة المحددة للشيفرة التي أصدرتها Alibaba Cloud. تم تحسين هذا النموذج بشكل كبير في توليد الشيفرة، والاستدلال، وإصلاح الأخطاء، من خلال تدريب على 55 تريليون توكن."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat هو الإصدار مفتوح المصدر من نموذج GLM-4 الذي أطلقته Zhizhu AI. أظهر هذا النموذج أداءً ممتازًا في مجالات الدلالات، والرياضيات، والاستدلال، والشيفرة، والمعرفة. بالإضافة إلى دعم المحادثات متعددة الجولات، يتمتع GLM-4-9B-Chat أيضًا بميزات متقدمة مثل تصفح الويب، وتنفيذ الشيفرة، واستدعاء الأدوات المخصصة (Function Call)، والاستدلال على النصوص الطويلة. يدعم النموذج 26 لغة، بما في ذلك الصينية، والإنجليزية، واليابانية، والكورية، والألمانية. أظهر GLM-4-9B-Chat أداءً ممتازًا في العديد من اختبارات المعايير مثل AlignBench-v2 وMT-Bench وMMLU وC-Eval. يدعم النموذج طول سياق يصل إلى 128K، مما يجعله مناسبًا للأبحاث الأكاديمية والتطبيقات التجارية."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 هو نموذج استدلال مدفوع بالتعلم المعزز (RL)، يعالج مشكلات التكرار وقابلية القراءة في النموذج. قبل التعلم المعزز، أدخل DeepSeek-R1 بيانات بدء التشغيل الباردة، مما أدى إلى تحسين أداء الاستدلال. إنه يتفوق في المهام الرياضية، والبرمجة، والاستدلال مقارنةً بـ OpenAI-o1، وقد حسّن الأداء العام من خلال طرق تدريب مصممة بعناية."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 هو نموذج لغوي مختلط الخبراء (MoE) يحتوي على 6710 مليار معلمة، يستخدم الانتباه المتعدد الرؤوس (MLA) وهيكل DeepSeekMoE، ويجمع بين استراتيجيات توازن الحمل بدون خسائر مساعدة، مما يحسن كفاءة الاستدلال والتدريب. تم تدريبه مسبقًا على 14.8 تريليون توكن عالية الجودة، وتم إجراء تعديل دقيق تحت الإشراف والتعلم المعزز، مما يجعل DeepSeek-V3 يتفوق على نماذج مفتوحة المصدر الأخرى، ويقترب من النماذج المغلقة الرائدة."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma هو أحد نماذج Google المتقدمة والخفيفة الوزن من سلسلة النماذج المفتوحة. إنه نموذج لغوي كبير يعتمد على فك الشيفرة فقط، يدعم اللغة الإنجليزية، ويقدم أوزان مفتوحة، ومتغيرات مدربة مسبقًا، ومتغيرات معدلة وفقًا للتعليمات. نموذج Gemma مناسب لمجموعة متنوعة من مهام توليد النصوص، بما في ذلك الأسئلة والأجوبة، والتلخيص، والاستدلال. تم تدريب هذا النموذج 9B على 8 تريليون توكن. حجمه النسبي الصغير يجعله مناسبًا للنشر في بيئات ذات موارد محدودة، مثل أجهزة الكمبيوتر المحمولة، وأجهزة الكمبيوتر المكتبية، أو البنية التحتية السحابية الخاصة بك، مما يتيح لمزيد من الأشخاص الوصول إلى نماذج الذكاء الاصطناعي المتقدمة وتعزيز الابتكار."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 هو جزء من عائلة نماذج اللغة الكبيرة متعددة اللغات التي طورتها Meta، بما في ذلك متغيرات مدربة مسبقًا ومعدلة وفقًا للتعليمات بحجم 8B و70B و405B. تم تحسين هذا النموذج 8B وفقًا لمشاهدات المحادثات متعددة اللغات، وأظهر أداءً ممتازًا في العديد من اختبارات المعايير الصناعية. تم تدريب النموذج باستخدام أكثر من 15 تريليون توكن من البيانات العامة، واستخدم تقنيات مثل التعديل الخاضع للإشراف والتعلم المعزز من ردود الفعل البشرية لتحسين فائدة النموذج وأمانه. يدعم Llama 3.1 توليد النصوص وتوليد الشيفرة، مع تاريخ معرفة حتى ديسمبر 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview هو نموذج معالجة اللغة الطبيعية المبتكر، قادر على معالجة مهام توليد الحوار وفهم السياق بشكل فعال."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview هو نموذج بحثي طورته فريق Qwen يركز على قدرات الاستدلال البصري، حيث يتمتع بميزة فريدة في فهم المشاهد المعقدة وحل المشكلات الرياضية المتعلقة بالرؤية."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "كنموذج تجريبي لـ Qwen2، يستخدم Qwen1.5 بيانات ضخمة لتحقيق وظائف حوارية أكثر دقة."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ هو نموذج استدلال من سلسلة Qwen. مقارنةً بالنماذج التقليدية المعتمدة على تحسين التعليمات، يتمتع QwQ بقدرة على التفكير والاستدلال، مما يتيح له تحقيق أداء معزز بشكل ملحوظ في المهام اللاحقة، خاصة في حل المشكلات الصعبة. QwQ-32B هو نموذج استدلال متوسط الحجم، قادر على تحقيق أداء تنافسي عند مقارنته بأحدث نماذج الاستدلال (مثل DeepSeek-R1، o1-mini). يستخدم هذا النموذج تقنيات مثل RoPE، SwiGLU، RMSNorm وAttention QKV bias، ويتميز بهيكل شبكة مكون من 64 طبقة و40 رأس انتباه Q (حيث KV في هيكل GQA هو 8)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) يوفر استجابة سريعة وقدرة على الحوار الطبيعي، مناسب للبيئات متعددة اللغات."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview هو أحدث نموذج بحث تجريبي من Qwen، يركز على تعزيز قدرات الاستدلال للذكاء الاصطناعي. من خلال استكشاف آليات معقدة مثل خلط اللغة والاستدلال التكراري، تشمل المزايا الرئيسية القدرة القوية على التحليل الاستدلالي، والقدرات الرياضية والبرمجية. في الوقت نفسه، هناك أيضًا مشكلات في تبديل اللغة، ودورات الاستدلال، واعتبارات الأمان، واختلافات في القدرات الأخرى."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct هو نموذج لغوي كبير تم تعديله وفقًا للتعليمات في سلسلة Qwen2، بحجم 1.5B. يعتمد هذا النموذج على بنية Transformer، ويستخدم تقنيات مثل دالة تنشيط SwiGLU، وتحويل QKV، والانتباه الجماعي. أظهر أداءً ممتازًا في فهم اللغة، والتوليد، والقدرات متعددة اللغات، والترميز، والرياضيات، والاستدلال في العديد من اختبارات المعايير، متجاوزًا معظم النماذج مفتوحة المصدر."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 هو نموذج لغوي عام متقدم، يدعم أنواع متعددة من التعليمات."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct هو نموذج لغوي كبير تم تعديله وفقًا للتعليمات في سلسلة Qwen2، بحجم 72B. يعتمد هذا النموذج على بنية Transformer، ويستخدم تقنيات مثل دالة تنشيط SwiGLU، وتحويل QKV، والانتباه الجماعي. يمكنه معالجة المدخلات الكبيرة. أظهر النموذج أداءً ممتازًا في فهم اللغة، والتوليد، والقدرات متعددة اللغات، والترميز، والرياضيات، والاستدلال في العديد من اختبارات المعايير، متجاوزًا معظم النماذج مفتوحة المصدر."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL هو النسخة الأحدث من نموذج Qwen-VL، وقد حقق أداءً متقدمًا في اختبارات الفهم البصري."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 هو سلسلة جديدة من نماذج اللغة الكبيرة، تهدف إلى تحسين معالجة المهام الإرشادية."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 هو سلسلة جديدة من نماذج اللغة الكبيرة، تهدف إلى تحسين معالجة المهام الإرشادية."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 هو سلسلة جديدة من نماذج اللغة الكبيرة، تتمتع بقدرات أقوى في الفهم والتوليد."
+ "description": "نموذج لغة كبير تم تطويره بواسطة فريق علي بابا السحابي للذكاء الاصطناعي"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 هي سلسلة جديدة من نماذج اللغة الكبيرة، تتمتع بقدرة أكبر على الفهم والتوليد."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 هو سلسلة جديدة من نماذج اللغة الكبيرة، مصممة لتحسين معالجة المهام التوجيهية."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 هو سلسلة جديدة من نماذج اللغة الكبيرة، تهدف إلى تحسين معالجة المهام الإرشادية."
},
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 هو سلسلة جديدة من نماذج اللغة الكبيرة، مصممة لتحسين معالجة المهام التوجيهية."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "يركز Qwen2.5-Coder على كتابة الكود."
+ },
"Qwen/Qwen2.5-Coder-7B-Instruct": {
- "description": "Qwen2.5-Coder يركز على كتابة الشيفرة."
+ "description": "Qwen2.5-Coder-7B-Instruct هو أحدث إصدار من سلسلة نماذج اللغة الكبيرة المحددة للشيفرة التي أصدرتها Alibaba Cloud. تم تحسين هذا النموذج بشكل كبير في توليد الشيفرة، والاستدلال، وإصلاح الأخطاء، من خلال تدريب على 55 تريليون توكن."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 هو أحدث سلسلة من نموذج Qwen، ويدعم سياقًا يصل إلى 128 ألف، مقارنةً بأفضل النماذج مفتوحة المصدر الحالية، يتفوق Qwen2-72B بشكل ملحوظ في فهم اللغة الطبيعية والمعرفة والترميز والرياضيات والقدرات متعددة اللغات."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 هو أحدث سلسلة من نموذج Qwen، قادر على التفوق على النماذج مفتوحة المصدر ذات الحجم المماثل أو حتى النماذج الأكبر حجمًا، حقق Qwen2 7B مزايا ملحوظة في عدة تقييمات، خاصة في فهم الترميز والصينية."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B هو نموذج قوي للغة البصرية، يدعم المعالجة متعددة الوسائط للصورة والنص، ويستطيع التعرف بدقة على محتوى الصورة وتوليد أوصاف أو إجابات ذات صلة."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct هو نموذج لغوي كبير يحتوي على 14 مليار معلمة، يتميز بأداء ممتاز، تم تحسينه لمشاهد اللغة الصينية واللغات المتعددة، ويدعم التطبيقات مثل الأسئلة الذكية وتوليد المحتوى."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct هو نموذج لغوي كبير يحتوي على 32 مليار معلمة، يتميز بأداء متوازن، تم تحسينه لمشاهد اللغة الصينية واللغات المتعددة، ويدعم التطبيقات مثل الأسئلة الذكية وتوليد المحتوى."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "يدعم Qwen2.5-72B-Instruct سياقًا يصل إلى 16 ألف، وينتج نصوصًا طويلة تتجاوز 8 آلاف. يدعم استدعاء الوظائف والتفاعل السلس مع الأنظمة الخارجية، مما يعزز بشكل كبير من المرونة وقابلية التوسع. لقد زادت معرفة النموذج بشكل ملحوظ، كما تحسنت قدراته في الترميز والرياضيات بشكل كبير، ويدعم أكثر من 29 لغة."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct هو نموذج لغوي كبير يحتوي على 7 مليارات معلمة، يدعم الاتصال الوظيفي مع الأنظمة الخارجية بسلاسة، مما يعزز المرونة وقابلية التوسع بشكل كبير. تم تحسينه لمشاهد اللغة الصينية واللغات المتعددة، ويدعم التطبيقات مثل الأسئلة الذكية وتوليد المحتوى."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct هو نموذج تعليمات برمجة قائم على تدريب مسبق واسع النطاق، يتمتع بقدرة قوية على فهم وتوليد الشيفرات، مما يجعله فعالاً في معالجة مختلف مهام البرمجة، وخاصة كتابة الشيفرات الذكية، وتوليد السكربتات الآلية، وحل مشكلات البرمجة."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct هو نموذج لغوي كبير مصمم خصيصًا لتوليد الشيفرات، وفهم الشيفرات، ومشاهد التطوير الفعالة، مع استخدام حجم 32B من المعلمات الرائدة في الصناعة، مما يلبي احتياجات البرمجة المتنوعة."
+ },
+ "SenseChat": {
+ "description": "نموذج الإصدار الأساسي (V4)، بطول سياق 4K، يمتلك قدرات قوية وعامة."
+ },
+ "SenseChat-128K": {
+ "description": "نموذج الإصدار الأساسي (V4)، بطول سياق 128K، يتفوق في مهام فهم وتوليد النصوص الطويلة."
+ },
+ "SenseChat-32K": {
+ "description": "نموذج الإصدار الأساسي (V4)، بطول سياق 32K، يمكن استخدامه بمرونة في مختلف السيناريوهات."
+ },
+ "SenseChat-5": {
+ "description": "أحدث إصدار من النموذج (V5.5)، بطول سياق 128K، مع تحسينات ملحوظة في القدرة على الاستدلال الرياضي، المحادثات باللغة الإنجليزية، اتباع التعليمات وفهم النصوص الطويلة، مما يجعله في مستوى GPT-4o."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math يركز على حل المشكلات في مجال الرياضيات، ويقدم إجابات احترافية للأسئلة الصعبة."
+ "SenseChat-5-1202": {
+ "description": "هو الإصدار الأحدث المبني على V5.5، وقد شهد تحسنًا ملحوظًا في القدرات الأساسية بين الصينية والإنجليزية، والدردشة، والمعرفة العلمية، والمعرفة الأدبية، والكتابة، والمنطق الرياضي، والتحكم في عدد الكلمات."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "بطول سياق 32K، يتفوق في فهم المحادثات باللغة الكانتونية مقارنة بـ GPT-4، ويضاهي GPT-4 Turbo في مجالات المعرفة، الاستدلال، الرياضيات وكتابة الأكواد."
+ },
+ "SenseChat-Character": {
+ "description": "نموذج النسخة القياسية، بطول سياق 8K، بسرعة استجابة عالية."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "نموذج النسخة المتقدمة، بطول سياق 32K، مع تحسين شامل في القدرات، يدعم المحادثات باللغة الصينية والإنجليزية."
+ },
+ "SenseChat-Turbo": {
+ "description": "مناسب للأسئلة السريعة، وسيناريوهات ضبط النموذج."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "هو أحدث نموذج خفيف الوزن، يحقق أكثر من 90% من قدرات النموذج الكامل، مما يقلل بشكل ملحوظ من تكلفة الاستدلال."
+ },
+ "SenseChat-Vision": {
+ "description": "النموذج الأحدث (V5.5) يدعم إدخال صور متعددة، ويحقق تحسينات شاملة في القدرات الأساسية للنموذج، مع تحسينات كبيرة في التعرف على خصائص الكائنات، والعلاقات المكانية، والتعرف على الأحداث، وفهم المشاهد، والتعرف على المشاعر، واستنتاج المعرفة المنطقية، وفهم النصوص وتوليدها."
+ },
+ "Skylark2-lite-8k": {
+ "description": "نموذج سكايلارك (Skylark) من الجيل الثاني، نموذج سكايلارك2-لايت يتميز بسرعات استجابة عالية، مناسب للسيناريوهات التي تتطلب استجابة في الوقت الحقيقي، وحساسة للتكاليف، وغير متطلبة لدقة نموذج عالية، بسعة سياق تبلغ 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "نموذج سكايلارك (Skylark) من الجيل الثاني، النسخة سكايلارك2-برو تتميز بدقة نموذج عالية، مناسبة لمهام توليد النصوص المعقدة، مثل إنشاء نصوص في مجالات احترافية، وكتابة الروايات، والترجمة عالية الجودة، بسعة سياق تبلغ 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "نموذج سكايلارك (Skylark) من الجيل الثاني، النسخة سكايلارك2-برو تتميز بدقة نموذج عالية، مناسبة لمهام توليد النصوص المعقدة، مثل إنشاء نصوص في مجالات احترافية، وكتابة الروايات، والترجمة عالية الجودة، بسعة سياق تبلغ 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "نموذج سكايلارك (Skylark) من الجيل الثاني، نموذج سكايلارك2-برو-شخصية يتميز بقدرات ممتازة في لعب الأدوار والدردشة، يجيد تجسيد شخصيات مختلفة بناءً على طلب المستخدم والتفاعل بشكل طبيعي، مناسب لبناء روبوتات الدردشة، والمساعدين الافتراضيين، وخدمة العملاء عبر الإنترنت، ويتميز بسرعة استجابة عالية."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "نموذج سكايلارك (Skylark) من الجيل الثاني، سكايلارك2-برو-توربو-8k يقدم استدلالًا أسرع وتكاليف أقل، بسعة سياق تبلغ 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B هو نموذج مفتوح المصدر من سلسلة ChatGLM، تم تطويره بواسطة Zhizhu AI. يحتفظ هذا النموذج بخصائص الجيل السابق الممتازة، مثل سلاسة المحادثة وانخفاض عتبة النشر، بينما يقدم ميزات جديدة. تم تدريبه على بيانات تدريب أكثر تنوعًا، وعدد أكبر من خطوات التدريب، واستراتيجيات تدريب أكثر منطقية، مما يجعله نموذجًا ممتازًا بين النماذج المدربة مسبقًا التي تقل عن 10B. يدعم ChatGLM3-6B المحادثات متعددة الجولات، واستدعاء الأدوات، وتنفيذ الشيفرة، ومهام الوكلاء في سيناريوهات معقدة. بالإضافة إلى نموذج المحادثة، تم إصدار النموذج الأساسي ChatGLM-6B-Base ونموذج المحادثة الطويلة ChatGLM3-6B-32K. النموذج مفتوح بالكامل للأبحاث الأكاديمية، ويسمح بالاستخدام التجاري المجاني بعد التسجيل."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B هو إصدار مفتوح المصدر، يوفر تجربة حوار محسنة لتطبيقات الحوار."
},
+ "TeleAI/TeleChat2": {
+ "description": "نموذج TeleChat2 هو نموذج كبير تم تطويره ذاتيًا من قبل China Telecom، يدعم وظائف مثل الأسئلة والأجوبة الموسوعية، وتوليد الشيفرة، وتوليد النصوص الطويلة، ويقدم خدمات استشارية للمستخدمين، مما يمكنه من التفاعل مع المستخدمين، والإجابة على الأسئلة، والمساعدة في الإبداع، وتوفير المعلومات والمعرفة والإلهام بكفاءة وسهولة. أظهر النموذج أداءً ممتازًا في معالجة مشكلات الهلوسة، وتوليد النصوص الطويلة، وفهم المنطق."
+ },
+ "TeleAI/TeleMM": {
+ "description": "نموذج TeleMM هو نموذج كبير لفهم متعدد الوسائط تم تطويره ذاتيًا من قبل China Telecom، يمكنه معالجة مدخلات متعددة الوسائط مثل النصوص والصور، ويدعم وظائف مثل فهم الصور، وتحليل الرسوم البيانية، مما يوفر خدمات فهم متعددة الوسائط للمستخدمين. يمكن للنموذج التفاعل مع المستخدمين بطرق متعددة الوسائط، وفهم المحتوى المدخل بدقة، والإجابة على الأسئلة، والمساعدة في الإبداع، وتوفير معلومات متعددة الوسائط ودعم الإلهام بكفاءة. أظهر أداءً ممتازًا في المهام متعددة الوسائط مثل الإدراك الدقيق، والاستدلال المنطقي."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct هو أحد أحدث نماذج اللغة الكبيرة التي أصدرتها Alibaba Cloud. يتمتع هذا النموذج بقدرات محسنة بشكل ملحوظ في مجالات الترميز والرياضيات. كما يوفر دعمًا للغات متعددة، تغطي أكثر من 29 لغة، بما في ذلك الصينية والإنجليزية. أظهر النموذج تحسينات ملحوظة في اتباع التعليمات، وفهم البيانات الهيكلية، وتوليد المخرجات الهيكلية (خاصة JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B، مع الحفاظ على القدرات اللغوية العامة الممتازة للنموذج الأصلي، تم تدريبه بشكل إضافي على 500 مليار توكن عالي الجودة، مما أدى إلى تحسين كبير في المنطق الرياضي وقدرات الترميز."
+ },
"abab5.5-chat": {
"description": "موجه لمشاهد الإنتاجية، يدعم معالجة المهام المعقدة وتوليد النصوص بكفاءة، مناسب للتطبيقات في المجالات المهنية."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "محسن لمشاهد الحوار باللغة الصينية، يوفر قدرة توليد حوار سلس ومتوافق مع عادات التعبير الصينية."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "نموذج استدعاء الدوال مفتوح المصدر من Fireworks، يوفر قدرة تنفيذ تعليمات ممتازة وخصائص قابلة للتخصيص."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2 من شركة Fireworks هو نموذج استدعاء دوال عالي الأداء، تم تطويره بناءً على Llama-3، وتم تحسينه بشكل كبير، مناسب بشكل خاص لاستدعاء الدوال، والحوار، واتباع التعليمات."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b هو نموذج لغوي بصري، يمكنه استقبال المدخلات من الصور والنصوص، تم تدريبه على بيانات عالية الجودة، مناسب للمهام متعددة الوسائط."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 هو نموذج لغة كبير متقدم، تم تحسينه من خلال التعلم المعزز وبيانات البدء البارد، ويتميز بأداء ممتاز في الاستدلال، والرياضيات، والبرمجة."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "نموذج Gemma 2 9B للتعليمات، يعتمد على تقنيات Google السابقة، مناسب لمهام توليد النصوص مثل الإجابة على الأسئلة، والتلخيص، والاستدلال."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "نموذج اللغة القوي من Deepseek، الذي يعتمد على مزيج من الخبراء (MoE)، بإجمالي عدد معلمات يبلغ 671 مليار، حيث يتم تفعيل 37 مليار معلمة لكل علامة."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "نموذج Llama 3 70B للتعليمات، مصمم للحوار متعدد اللغات وفهم اللغة الطبيعية، أداءه يتفوق على معظم النماذج المنافسة."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "نموذج Llama 3 70B للتعليمات (نسخة HF)، يتوافق مع نتائج التنفيذ الرسمية، مناسب لمهام اتباع التعليمات عالية الجودة."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "نموذج Llama 3 8B للتعليمات، تم تحسينه للحوار والمهام متعددة اللغات، يظهر أداءً ممتازًا وفعالًا."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "نموذج Llama 3.1 8B للتعليمات، تم تحسينه للحوار متعدد اللغات، قادر على تجاوز معظم النماذج المفتوحة والمغلقة في المعايير الصناعية الشائعة."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "نموذج استدلال الصور المعدل من Meta ذو 11B معلمات. تم تحسين هذا النموذج للتعرف البصري، واستدلال الصور، ووصف الصور، والإجابة عن الأسئلة العامة المتعلقة بالصور. يستطيع النموذج فهم البيانات البصرية مثل الرسوم البيانية والرسوم، ويسد الفجوة بين الرؤية واللغة من خلال توليد أوصاف نصية لجزئيات الصور."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "نموذج التوجيه Llama 3.2 3B هو نموذج متعدد اللغات خفيف الوزن قدمته Meta. يهدف هذا النموذج إلى زيادة الكفاءة، مع تحسينات ملحوظة في التأخير والتكلفة مقارنة بالنماذج الأكبر. تشمل حالات الاستخدام النموذجية لهذا النموذج الاستفسارات وإعادة كتابة الملاحظات والمساعدة في الكتابة."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "نموذج استدلال الصور المعدل من Meta ذو 90B معلمات. تم تحسين هذا النموذج للتعرف البصري، واستدلال الصور، ووصف الصور، والإجابة عن الأسئلة العامة المتعلقة بالصور. يستطيع النموذج فهم البيانات البصرية مثل الرسوم البيانية والرسوم، ويسد الفجوة بين الرؤية واللغة من خلال توليد أوصاف نصية لجزئيات الصور."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct هو الإصدار المحدث من Llama 3.1 70B في ديسمبر. تم تحسين هذا النموذج بناءً على Llama 3.1 70B (الذي تم إصداره في يوليو 2024) لتعزيز استدعاء الأدوات، ودعم النصوص متعددة اللغات، والقدرات الرياضية وبرمجة. لقد حقق هذا النموذج مستويات رائدة في الصناعة في الاستدلال، والرياضيات، واتباع التعليمات، ويستطيع تقديم أداء مشابه لـ 3.1 405B، مع مزايا ملحوظة في السرعة والتكلفة."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "نموذج بـ 24 مليار معلمة، يتمتع بقدرات متقدمة تعادل النماذج الأكبر حجماً."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "نموذج Mixtral MoE 8x22B للتعليمات، مع معلمات ضخمة وهيكل خبير متعدد، يدعم معالجة فعالة لمهام معقدة."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "نموذج Mixtral MoE 8x7B للتعليمات، يوفر هيكل خبير متعدد لتقديم تعليمات فعالة واتباعها."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "نموذج Mixtral MoE 8x7B للتعليمات (نسخة HF)، الأداء يتوافق مع التنفيذ الرسمي، مناسب لمجموعة متنوعة من سيناريوهات المهام الفعالة."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "نموذج MythoMax L2 13B، يجمع بين تقنيات الدمج الجديدة، بارع في السرد وأدوار الشخصيات."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "نموذج Phi 3 Vision للتعليمات، نموذج متعدد الوسائط خفيف الوزن، قادر على معالجة معلومات بصرية ونصية معقدة، يتمتع بقدرة استدلال قوية."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "نموذج StarCoder 15.5B، يدعم مهام البرمجة المتقدمة، مع تعزيز القدرة على التعامل مع لغات متعددة، مناسب لتوليد وفهم الشيفرات المعقدة."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "نموذج QwQ هو نموذج بحث تجريبي تم تطويره بواسطة فريق Qwen، يركز على تعزيز قدرات الاستدلال للذكاء الاصطناعي."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "نموذج StarCoder 7B، تم تدريبه على أكثر من 80 لغة برمجة، يتمتع بقدرة ممتازة على ملء البرمجة وفهم السياق."
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "الإصدار 72B من نموذج Qwen-VL هو نتيجة أحدث ابتكارات Alibaba، ويمثل ما يقرب من عام من الابتكار."
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 هي سلسلة من نماذج اللغة التي طورتها مجموعة Qwen من علي بابا، تحتوي فقط على شريحة فك شفرات. توفر هذه النماذج أحجامًا مختلفة، بما في ذلك 0.5B، 1.5B، 3B، 7B، 14B، 32B و72B، وتأتي بنسخ أساسية (base) ونماذج توجيهية (instruct)."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct هو أحدث إصدار من سلسلة نماذج اللغة الكبيرة المحددة للشيفرة التي أصدرتها Alibaba Cloud. تم تحسين هذا النموذج بشكل كبير في توليد الشيفرة، والاستدلال، وإصلاح الأخطاء، من خلال تدريب على 55 تريليون توكن."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "نموذج Yi-Large، يتمتع بقدرة معالجة لغوية ممتازة، يمكن استخدامه في جميع أنواع مهام توليد وفهم اللغة."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "نموذج متعدد اللغات بحجم 52B (12B نشط)، يقدم نافذة سياق طويلة بحجم 256K، واستدعاء وظائف، وإخراج منظم، وتوليد مستند."
},
- "ai21-jamba-instruct": {
- "description": "نموذج LLM يعتمد على Mamba، مصمم لتحقيق أفضل أداء وكفاءة من حيث الجودة والتكلفة."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet يرفع المعايير في الصناعة، حيث يتفوق على نماذج المنافسين وClaude 3 Opus، ويظهر أداءً ممتازًا في تقييمات واسعة، مع سرعة وتكلفة تتناسب مع نماذجنا المتوسطة."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "لقد رفع كلود 3.5 سونيت معايير الصناعة، حيث تفوق أداؤه على نماذج المنافسين ونموذج كلود 3 أوبس، وأظهر أداءً ممتازًا في تقييمات واسعة، مع الحفاظ على سرعة وتكلفة نماذجنا المتوسطة."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku هو أسرع وأصغر نموذج من Anthropic، يوفر سرعة استجابة شبه فورية. يمكنه بسرعة الإجابة على الاستفسارات والطلبات البسيطة. سيتمكن العملاء من بناء تجربة ذكاء اصطناعي سلسة تحاكي التفاعل البشري. يمكن لـ Claude 3 Haiku معالجة الصور وإرجاع إخراج نصي، مع نافذة سياقية تبلغ 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus هو أقوى نموذج من Anthropic لمعالجة المهام المعقدة للغاية. يتميز بأداء ممتاز وذكاء وسلاسة وفهم."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku هو أسرع نموذج من الجيل التالي من Anthropic. مقارنةً بـ Claude 3 Haiku، تم تحسين Claude 3.5 Haiku في جميع المهارات، وتفوق في العديد من اختبارات الذكاء على النموذج الأكبر من الجيل السابق Claude 3 Opus."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet يقدم قدرات تتجاوز Opus وسرعة أكبر من Sonnet، مع الحفاظ على نفس السعر. يتميز Sonnet بمهارات خاصة في البرمجة وعلوم البيانات ومعالجة الصور والمهام الوكيلة."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet هو أكثر النماذج ذكاءً من Anthropic حتى الآن، وهو أيضًا أول نموذج مختلط للتفكير في السوق. يمكن لـ Claude 3.7 Sonnet إنتاج استجابات شبه فورية أو تفكير تدريجي ممتد، حيث يمكن للمستخدمين رؤية هذه العمليات بوضوح. يتميز Sonnet بشكل خاص في البرمجة، وعلوم البيانات، ومعالجة الصور، والمهام الوكيلة."
+ },
"aya": {
"description": "Aya 23 هو نموذج متعدد اللغات أطلقته Cohere، يدعم 23 لغة، مما يسهل التطبيقات اللغوية المتنوعة."
},
"aya:35b": {
"description": "Aya 23 هو نموذج متعدد اللغات أطلقته Cohere، يدعم 23 لغة، مما يسهل التطبيقات اللغوية المتنوعة."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B هو نموذج لغوي كبير مفتوح المصدر قابل للاستخدام التجاري تم تطويره بواسطة Baichuan Intelligence، ويحتوي على 13 مليار معلمة، وقد حقق أفضل النتائج في المعايير الصينية والإنجليزية."
+ },
"charglm-3": {
"description": "CharGLM-3 مصمم خصيصًا للأدوار التفاعلية والمرافقة العاطفية، يدعم ذاكرة متعددة الجولات طويلة الأمد وحوارات مخصصة، ويستخدم على نطاق واسع."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 يوفر تقدمًا في القدرات الأساسية للمؤسسات، بما في ذلك سياق يصل إلى 200K توكن، وتقليل كبير في معدل حدوث الهلوسة في النموذج، وإشعارات النظام، وميزة اختبار جديدة: استدعاء الأدوات."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku هو أسرع نموذج من الجيل التالي من Anthropic. مقارنةً بـ Claude 3 Haiku، فإن Claude 3.5 Haiku قد حقق تحسينات في جميع المهارات، وتفوق في العديد من اختبارات الذكاء على أكبر نموذج من الجيل السابق، Claude 3 Opus."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet يوفر قدرات تتجاوز Opus وسرعة أكبر من Sonnet، مع الحفاظ على نفس السعر. Sonnet بارع بشكل خاص في البرمجة، وعلوم البيانات، ومعالجة الصور، ومهام الوكالة."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "يقدم كلاف 3.5 سونيت قدرات تتجاوز أوبوس وسرعة أكبر من سونيت، مع الحفاظ على نفس الأسعار. سونيت متخصصة بشكل خاص في البرمجة، علوم البيانات، معالجة الصور، والمهام الوكيلة."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet هو أحدث نموذج من Anthropic، يتميز بأداء ممتاز في تقييمات واسعة، ويتفوق على نماذج المنافسين ونموذج Claude 3.5 Sonnet، مع الحفاظ على سرعة وتكلفة نماذجنا المتوسطة."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku هو أسرع وأصغر نموذج من Anthropic، مصمم لتحقيق استجابة شبه فورية. يتمتع بأداء توجيهي سريع ودقيق."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet يوفر توازنًا مثاليًا بين الذكاء والسرعة لحمولات العمل المؤسسية. يقدم أقصى فائدة بسعر أقل، موثوق ومناسب للنشر على نطاق واسع."
},
- "claude-instant-1.2": {
- "description": "نموذج Anthropic يستخدم لتوليد النصوص ذات التأخير المنخفض، يدعم توليد مئات الصفحات من النص."
- },
"codegeex-4": {
"description": "CodeGeeX-4 هو مساعد برمجي قوي، يدعم مجموعة متنوعة من لغات البرمجة في الإجابة الذكية وإكمال الشيفرة، مما يعزز من كفاءة التطوير."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B هو نموذج توليد كود متعدد اللغات، يدعم مجموعة شاملة من الوظائف بما في ذلك إكمال الشيفرات والتوليد، ومفسر الشيفرات، والبحث عبر الإنترنت، واستدعاء الوظائف، وأسئلة وأجوبة على مستوى المستودع، مما يغطي جميع سيناريوهات تطوير البرمجيات. إنه أحد أفضل نماذج توليد الشيفرات بأقل من 10 مليار معلمة."
+ },
"codegemma": {
"description": "CodeGemma هو نموذج لغوي خفيف الوزن مخصص لمهام البرمجة المختلفة، يدعم التكرار السريع والتكامل."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama هو نموذج لغوي كبير يركز على توليد الشيفرة والنقاش، يجمع بين دعم مجموعة واسعة من لغات البرمجة، مناسب لبيئات المطورين."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama هو نموذج LLM يركز على توليد ومناقشة الشيفرة، يجمع بين دعم واسع للغات البرمجة، مناسب لبيئات المطورين."
+ },
"codellama:13b": {
"description": "Code Llama هو نموذج لغوي كبير يركز على توليد الشيفرة والنقاش، يجمع بين دعم مجموعة واسعة من لغات البرمجة، مناسب لبيئات المطورين."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ هو نموذج لغوي كبير عالي الأداء، مصمم لمشاهد الأعمال الحقيقية والتطبيقات المعقدة."
},
+ "dall-e-2": {
+ "description": "النموذج الثاني من DALL·E، يدعم توليد صور أكثر واقعية ودقة، بدقة تعادل أربعة أضعاف الجيل الأول."
+ },
+ "dall-e-3": {
+ "description": "أحدث نموذج DALL·E، تم إصداره في نوفمبر 2023. يدعم توليد صور أكثر واقعية ودقة، مع قدرة أكبر على التعبير عن التفاصيل."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct يوفر قدرة معالجة تعليمات موثوقة، يدعم تطبيقات متعددة الصناعات."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 هو نموذج استدلال مدفوع بالتعلم المعزز (RL) يعالج مشكلات التكرار وقابلية القراءة في النموذج. قبل استخدام RL، قدم DeepSeek-R1 بيانات بدء باردة، مما أدى إلى تحسين أداء الاستدلال. إنه يقدم أداءً مماثلاً لـ OpenAI-o1 في المهام الرياضية والبرمجية والاستدلال، وقد حسّن النتائج العامة من خلال طرق تدريب مصممة بعناية."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "نموذج التقطير DeepSeek-R1، تم تحسين أداء الاستدلال من خلال التعلم المعزز وبيانات البداية الباردة، ويعيد نموذج المصدر فتح معايير المهام المتعددة."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B هو نموذج تم تطويره بناءً على Llama-3.1-8B. تم ضبط هذا النموذج باستخدام عينات تم إنشاؤها بواسطة DeepSeek-R1، ويظهر قدرة استدلال ممتازة. حقق أداءً جيدًا في اختبارات المعايير، حيث حقق دقة 89.1% في MATH-500، وحقق معدل نجاح 50.4% في AIME 2024، وحصل على تقييم 1205 في CodeForces، مما يظهر قدرة قوية في الرياضيات والبرمجة كنموذج بحجم 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "نموذج التقطير DeepSeek-R1، تم تحسين أداء الاستدلال من خلال التعلم المعزز وبيانات البداية الباردة، ويعيد نموذج المصدر فتح معايير المهام المتعددة."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "نموذج التقطير DeepSeek-R1، تم تحسين أداء الاستدلال من خلال التعلم المعزز وبيانات البداية الباردة، ويعيد نموذج المصدر فتح معايير المهام المتعددة."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B هو نموذج تم الحصول عليه من Qwen2.5-32B من خلال التقطير المعرفي. تم ضبط هذا النموذج باستخدام 800,000 عينة مختارة تم إنشاؤها بواسطة DeepSeek-R1، ويظهر أداءً ممتازًا في مجالات متعددة مثل الرياضيات، البرمجة، والاستدلال. حقق نتائج ممتازة في اختبارات المعايير مثل AIME 2024، MATH-500، وGPQA Diamond، حيث حقق دقة 94.3% في MATH-500، مما يظهر قدرة قوية في الاستدلال الرياضي."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B هو نموذج تم الحصول عليه من Qwen2.5-Math-7B من خلال التقطير المعرفي. تم ضبط هذا النموذج باستخدام 800,000 عينة مختارة تم إنشاؤها بواسطة DeepSeek-R1، ويظهر أداءً ممتازًا في الاستدلال. حقق نتائج ممتازة في اختبارات المعايير، حيث حقق دقة 92.8% في MATH-500، وحقق معدل نجاح 55.5% في AIME 2024، وحصل على تقييم 1189 في CodeForces، مما يظهر قدرة قوية في الرياضيات والبرمجة كنموذج بحجم 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 يجمع بين الميزات الممتازة للإصدارات السابقة، ويعزز القدرات العامة والترميز."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 هو نموذج لغوي مختلط الخبراء (MoE) يحتوي على 6710 مليار معلمة، يستخدم انتباه متعدد الرؤوس (MLA) وبنية DeepSeekMoE، ويجمع بين استراتيجية توازن الحمل بدون خسارة مساعدة، مما يحسن كفاءة الاستدلال والتدريب. من خلال التدريب المسبق على 14.8 تريليون توكن عالي الجودة، وإجراء تعديلات إشرافية وتعلم معزز، يتفوق DeepSeek-V3 في الأداء على نماذج المصدر المفتوح الأخرى، ويقترب من النماذج المغلقة الرائدة."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B هو نموذج متقدم تم تدريبه للحوار المعقد."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "نموذج لغوي متقدم وفعال، بارع في الاستدلال، والرياضيات، والبرمجة."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 هو نموذج لغوي بصري مختلط الخبراء (MoE) تم تطويره بناءً على DeepSeekMoE-27B، يستخدم بنية MoE ذات تفعيل نادر، محققًا أداءً ممتازًا مع تفعيل 4.5 مليار معلمة فقط. يقدم هذا النموذج أداءً ممتازًا في مهام مثل الأسئلة البصرية، التعرف الضوئي على الأحرف، فهم الوثائق/الجداول/الرسوم البيانية، وتحديد المواقع البصرية."
+ },
"deepseek-chat": {
"description": "نموذج مفتوح المصدر الجديد الذي يجمع بين القدرات العامة وقدرات البرمجة، لا يحتفظ فقط بالقدرات الحوارية العامة لنموذج الدردشة الأصلي وقدرات معالجة الشيفرة القوية لنموذج Coder، بل يتماشى أيضًا بشكل أفضل مع تفضيلات البشر. بالإضافة إلى ذلك، حقق DeepSeek-V2.5 تحسينات كبيرة في مهام الكتابة، واتباع التعليمات، وغيرها من المجالات."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B هو نموذج لغة برمجية، تم تدريبه على 20 تريليون بيانات، منها 87% كود و13% لغات صينية وإنجليزية. يقدم النموذج حجم نافذة 16K ومهام ملء الفراغ، مما يوفر إكمال الشيفرات على مستوى المشروع ووظائف ملء المقاطع."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 هو نموذج شيفرة مفتوح المصدر من نوع خبير مختلط، يقدم أداءً ممتازًا في مهام الشيفرة، ويضاهي GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 هو نموذج شيفرة مفتوح المصدر من نوع خبير مختلط، يقدم أداءً ممتازًا في مهام الشيفرة، ويضاهي GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 هو نموذج استدلال مدفوع بالتعلم المعزز (RL) يعالج مشكلات التكرار وقابلية القراءة في النموذج. قبل استخدام RL، قدم DeepSeek-R1 بيانات بدء باردة، مما أدى إلى تحسين أداء الاستدلال. إنه يقدم أداءً مماثلاً لـ OpenAI-o1 في المهام الرياضية والبرمجية والاستدلال، وقد حسّن النتائج العامة من خلال طرق تدريب مصممة بعناية."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - النموذج الأكبر والأذكى في مجموعة DeepSeek - تم تقطيره إلى بنية Llama 70B. بناءً على اختبارات المعايير والتقييمات البشرية، يظهر هذا النموذج ذكاءً أكبر من Llama 70B الأصلي، خاصة في المهام التي تتطلب دقة رياضية وحقائق."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "نموذج DeepSeek-R1-Distill تم تطويره من خلال تقنية تقطير المعرفة، حيث تم تعديل عينات تم إنشاؤها بواسطة DeepSeek-R1 على نماذج مفتوحة المصدر مثل Qwen وLlama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "نموذج DeepSeek-R1-Distill تم تطويره من خلال تقنية تقطير المعرفة، حيث تم تعديل عينات تم إنشاؤها بواسطة DeepSeek-R1 على نماذج مفتوحة المصدر مثل Qwen وLlama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "نموذج DeepSeek-R1-Distill تم تطويره من خلال تقنية تقطير المعرفة، حيث تم تعديل عينات تم إنشاؤها بواسطة DeepSeek-R1 على نماذج مفتوحة المصدر مثل Qwen وLlama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "نموذج DeepSeek-R1-Distill تم تطويره من خلال تقنية تقطير المعرفة، حيث تم تعديل عينات تم إنشاؤها بواسطة DeepSeek-R1 على نماذج مفتوحة المصدر مثل Qwen وLlama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "نموذج DeepSeek-R1-Distill تم تطويره من خلال تقنية تقطير المعرفة، حيث تم تعديل عينات تم إنشاؤها بواسطة DeepSeek-R1 على نماذج مفتوحة المصدر مثل Qwen وLlama."
+ },
+ "deepseek-reasoner": {
+ "description": "نموذج الاستدلال الذي أطلقته DeepSeek. قبل تقديم الإجابة النهائية، يقوم النموذج أولاً بإخراج سلسلة من المحتوى الفكري لتحسين دقة الإجابة النهائية."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 هو نموذج لغوي فعال من نوع Mixture-of-Experts، مناسب لاحتياجات المعالجة الاقتصادية."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B هو نموذج تصميم الشيفرة لـ DeepSeek، يوفر قدرة توليد شيفرة قوية."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 هو نموذج MoE تم تطويره بواسطة شركة Hangzhou DeepSeek AI Technology Research Co.، Ltd، وقد حقق نتائج بارزة في العديد من التقييمات، ويحتل المرتبة الأولى بين نماذج المصدر المفتوح في القوائم الرئيسية. مقارنةً بنموذج V2.5، حقق V3 زيادة في سرعة التوليد بمقدار 3 مرات، مما يوفر تجربة استخدام أسرع وأكثر سلاسة للمستخدمين."
+ },
"deepseek/deepseek-chat": {
"description": "نموذج مفتوح المصدر جديد يجمع بين القدرات العامة وقدرات البرمجة، لا يحتفظ فقط بقدرات الحوار العامة لنموذج الدردشة الأصلي وقدرات معالجة الأكواد القوية لنموذج Coder، بل يتماشى أيضًا بشكل أفضل مع تفضيلات البشر. بالإضافة إلى ذلك، حقق DeepSeek-V2.5 تحسينات كبيرة في مهام الكتابة، واتباع التعليمات، وغيرها من المجالات."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 يعزز بشكل كبير من قدرة النموذج على الاستدلال في ظل وجود بيانات محدودة جدًا. قبل تقديم الإجابة النهائية، يقوم النموذج أولاً بإخراج سلسلة من التفكير لتحسين دقة الإجابة النهائية."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B هو نموذج لغوي كبير يعتمد على Llama3.3 70B، حيث يحقق أداءً تنافسيًا مماثلاً للنماذج الرائدة الكبيرة من خلال استخدام التعديلات المستندة إلى مخرجات DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B هو نموذج لغوي كبير مكرر يعتمد على Llama-3.1-8B-Instruct، تم تدريبه باستخدام مخرجات DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B هو نموذج لغوي كبير مكرر يعتمد على Qwen 2.5 14B، تم تدريبه باستخدام مخرجات DeepSeek R1. لقد تفوق هذا النموذج في العديد من اختبارات المعايير على نموذج OpenAI o1-mini، محققًا أحدث الإنجازات التقنية في النماذج الكثيفة. فيما يلي بعض نتائج اختبارات المعايير:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nتصنيف CodeForces: 1481\nأظهر هذا النموذج أداءً تنافسيًا مماثلاً للنماذج الرائدة الأكبر حجمًا من خلال التعديل المستند إلى مخرجات DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B هو نموذج لغوي كبير مكرر يعتمد على Qwen 2.5 32B، تم تدريبه باستخدام مخرجات DeepSeek R1. لقد تفوق هذا النموذج في العديد من اختبارات المعايير على نموذج OpenAI o1-mini، محققًا أحدث الإنجازات التقنية في النماذج الكثيفة. فيما يلي بعض نتائج اختبارات المعايير:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nتصنيف CodeForces: 1691\nأظهر هذا النموذج أداءً تنافسيًا مماثلاً للنماذج الرائدة الأكبر حجمًا من خلال التعديل المستند إلى مخرجات DeepSeek R1."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 هو أحدث نموذج مفتوح المصدر أطلقه فريق DeepSeek، ويتميز بأداء استدلال قوي للغاية، خاصة في المهام الرياضية والبرمجة والاستدلال، حيث وصل إلى مستوى مماثل لنموذج OpenAI o1."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 يعزز بشكل كبير من قدرة النموذج على الاستدلال في ظل وجود بيانات محدودة جدًا. قبل تقديم الإجابة النهائية، يقوم النموذج أولاً بإخراج سلسلة من التفكير لتحسين دقة الإجابة النهائية."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "حقق DeepSeek-V3 تقدمًا كبيرًا في سرعة الاستدلال مقارنة بالنماذج السابقة. يحتل المرتبة الأولى بين النماذج المفتوحة المصدر، ويمكن مقارنته بأحدث النماذج المغلقة على مستوى العالم. يعتمد DeepSeek-V3 على بنية الانتباه المتعدد الرؤوس (MLA) وبنية DeepSeekMoE، والتي تم التحقق منها بشكل شامل في DeepSeek-V2. بالإضافة إلى ذلك، قدم DeepSeek-V3 استراتيجية مساعدة غير مدمرة للتوازن في الحمل، وحدد أهداف تدريب متعددة التسمية لتحقيق أداء أقوى."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "حقق DeepSeek-V3 تقدمًا كبيرًا في سرعة الاستدلال مقارنة بالنماذج السابقة. يحتل المرتبة الأولى بين النماذج المفتوحة المصدر، ويمكن مقارنته بأحدث النماذج المغلقة على مستوى العالم. يعتمد DeepSeek-V3 على بنية الانتباه المتعدد الرؤوس (MLA) وبنية DeepSeekMoE، والتي تم التحقق منها بشكل شامل في DeepSeek-V2. بالإضافة إلى ذلك، قدم DeepSeek-V3 استراتيجية مساعدة غير مدمرة للتوازن في الحمل، وحدد أهداف تدريب متعددة التسمية لتحقيق أداء أقوى."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "دو باو 1.5 لايت هو نموذج الجيل الجديد الخفيف، مع سرعة استجابة قصوى، حيث يصل الأداء والوقت المستغرق إلى مستوى عالمي."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "دو باو 1.5 برو 256k هو النسخة المحدثة من دو باو 1.5 برو، حيث تم تحسين الأداء العام بنسبة 10%. يدعم استدلال نافذة السياق 256k، وطول الإخراج يصل إلى 12k توكن. أداء أعلى، نافذة أكبر، قيمة عالية، مناسب لمجموعة واسعة من سيناريوهات الاستخدام."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "دو باو 1.5 برو هو نموذج الجيل الجديد الرائد، مع ترقية شاملة في الأداء، حيث يظهر تفوقًا في المعرفة، والبرمجة، والاستدلال، وغيرها."
+ },
"emohaa": {
"description": "Emohaa هو نموذج نفسي، يتمتع بقدرات استشارية متخصصة، يساعد المستخدمين في فهم القضايا العاطفية."
},
+ "ernie-3.5-128k": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، يغطي كمية هائلة من البيانات باللغة الصينية والإنجليزية، ويتميز بقدرات عامة قوية، تلبي متطلبات معظم حالات الحوار، والإجابة، والتوليد، وتطبيقات المكونات الإضافية؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ernie-3.5-8k": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، يغطي كمية هائلة من البيانات باللغة الصينية والإنجليزية، ويتميز بقدرات عامة قوية، تلبي متطلبات معظم حالات الحوار، والإجابة، والتوليد، وتطبيقات المكونات الإضافية؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، يغطي كمية هائلة من البيانات باللغة الصينية والإنجليزية، ويتميز بقدرات عامة قوية، تلبي متطلبات معظم حالات الحوار، والإجابة، والتوليد، وتطبيقات المكونات الإضافية؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي حقق ترقية شاملة في القدرات مقارنةً بـ ERNIE 3.5، ويستخدم على نطاق واسع في مشاهد المهام المعقدة في مختلف المجالات؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي حقق ترقية شاملة في القدرات مقارنةً بـ ERNIE 3.5، ويستخدم على نطاق واسع في مشاهد المهام المعقدة في مختلف المجالات؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي يظهر أداءً ممتازًا بشكل شامل، ويستخدم على نطاق واسع في مشاهد المهام المعقدة في مختلف المجالات؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة. مقارنةً بـ ERNIE 4.0، يظهر أداءً أفضل."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي يظهر أداءً ممتازًا بشكل شامل، ويستخدم على نطاق واسع في مشاهد المهام المعقدة في مختلف المجالات؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة. مقارنةً بـ ERNIE 4.0، يظهر أداءً أفضل."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "نموذج اللغة الكبير الرائد الذي طورته بايدو، والذي يظهر أداءً ممتازًا بشكل شامل، ويستخدم على نطاق واسع في مشاهد المهام المعقدة في مختلف المجالات؛ يدعم الاتصال التلقائي بمكونات البحث من بايدو، مما يضمن تحديث معلومات الإجابة. مقارنةً بـ ERNIE 4.0، يظهر أداءً أفضل."
+ },
+ "ernie-char-8k": {
+ "description": "نموذج اللغة الكبير المخصص الذي طورته بايدو، مناسب لتطبيقات مثل NPC في الألعاب، محادثات خدمة العملاء، وأدوار الحوار، حيث يتميز بأسلوب شخصيات واضح ومتسق، وقدرة قوية على اتباع التعليمات، وأداء استدلال ممتاز."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "نموذج اللغة الكبير المخصص الذي طورته بايدو، مناسب لتطبيقات مثل NPC في الألعاب، محادثات خدمة العملاء، وأدوار الحوار، حيث يتميز بأسلوب شخصيات واضح ومتسق، وقدرة قوية على اتباع التعليمات، وأداء استدلال ممتاز."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite هو نموذج اللغة الكبير الخفيف الذي طورته بايدو، يجمع بين أداء النموذج الممتاز وأداء الاستدلال، مناسب للاستخدام مع بطاقات تسريع الذكاء الاصطناعي ذات القدرة الحاسوبية المنخفضة."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "نموذج اللغة الكبير الخفيف الذي طورته بايدو، يجمع بين أداء النموذج الممتاز وأداء الاستدلال، ويظهر أداءً أفضل من ERNIE Lite، مناسب للاستخدام مع بطاقات تسريع الذكاء الاصطناعي ذات القدرة الحاسوبية المنخفضة."
+ },
+ "ernie-novel-8k": {
+ "description": "نموذج اللغة الكبير العام الذي طورته بايدو، يظهر مزايا واضحة في القدرة على كتابة روايات، ويمكن استخدامه أيضًا في مشاهد مثل المسرحيات القصيرة والأفلام."
+ },
+ "ernie-speed-128k": {
+ "description": "نموذج اللغة الكبير عالي الأداء الذي طورته بايدو، والذي تم إصداره في عام 2024، يتمتع بقدرات عامة ممتازة، مناسب كنموذج أساسي للتعديل، مما يساعد على معالجة مشكلات المشاهد المحددة بشكل أفضل، ويظهر أداءً ممتازًا في الاستدلال."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "نموذج اللغة الكبير عالي الأداء الذي طورته بايدو، والذي تم إصداره في عام 2024، يتمتع بقدرات عامة ممتازة، ويظهر أداءً أفضل من ERNIE Speed، مناسب كنموذج أساسي للتعديل، مما يساعد على معالجة مشكلات المشاهد المحددة بشكل أفضل، ويظهر أداءً ممتازًا في الاستدلال."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny هو نموذج اللغة الكبير عالي الأداء الذي طورته بايدو، وتكاليف النشر والتعديل هي الأدنى بين نماذج سلسلة Wenxin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (تعديل) يوفر أداءً مستقرًا وقابلًا للتعديل، وهو الخيار المثالي لحلول المهام المعقدة."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro هو نموذج ذكاء اصطناعي عالي الأداء من Google، مصمم للتوسع في مجموعة واسعة من المهام."
},
+ "gemini-1.5-flash": {
+ "description": "جمني 1.5 فلاش هو أحدث نموذج ذكاء اصطناعي متعدد الوسائط من جوجل، يتمتع بقدرة معالجة سريعة، ويدعم إدخال النصوص والصور والفيديو، مما يجعله مناسبًا للتوسع الفعال في مجموعة متنوعة من المهام."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 هو نموذج متعدد الوسائط فعال، يدعم التوسع في التطبيقات الواسعة."
},
"gemini-1.5-flash-002": {
"description": "جمني 1.5 فلاش 002 هو نموذج متعدد الوسائط فعال، يدعم توسيع التطبيقات على نطاق واسع."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 مصمم لمعالجة سيناريوهات المهام الكبيرة، ويوفر سرعة معالجة لا مثيل لها."
+ "gemini-1.5-flash-8b": {
+ "description": "جمني 1.5 فلاش 8B هو نموذج متعدد الوسائط عالي الكفاءة، يدعم مجموعة واسعة من التطبيقات."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "جمني 1.5 فلاش 8B 0924 هو النموذج التجريبي الأحدث، حيث حقق تحسينات ملحوظة في الأداء في حالات الاستخدام النصية ومتعددة الوسائط."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 يوفر قدرات معالجة متعددة الوسائط محسّنة، مناسبة لمجموعة متنوعة من سيناريوهات المهام المعقدة."
+ "description": "جيميني 1.5 فلاش 0827 يقدم قدرة معالجة متعددة الوسائط محسنة، مناسب لمجموعة متنوعة من سيناريوهات المهام المعقدة."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash هو أحدث نموذج ذكاء اصطناعي متعدد الوسائط من Google، يتمتع بقدرات معالجة سريعة، ويدعم إدخال النصوص والصور والفيديو، مما يجعله مناسبًا للتوسع الفعال في مجموعة متنوعة من المهام."
@@ -354,14 +819,38 @@
"description": "جمني 1.5 برو 002 هو النموذج الأحدث الجاهز للإنتاج، حيث يقدم مخرجات ذات جودة أعلى، مع تحسينات ملحوظة خاصة في الرياضيات والسياقات الطويلة والمهام البصرية."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 يوفر قدرات معالجة متعددة الوسائط ممتازة، مما يوفر مرونة أكبر لتطوير التطبيقات."
+ "description": "جيميني 1.5 برو 0801 يوفر قدرة معالجة متعددة الوسائط ممتازة، مما يوفر مرونة أكبر لتطوير التطبيقات."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 يجمع بين أحدث تقنيات التحسين، مما يوفر قدرة معالجة بيانات متعددة الوسائط أكثر كفاءة."
+ "description": "جيميني 1.5 برو 0827 يدمج أحدث تقنيات التحسين، مما يوفر قدرة معالجة بيانات متعددة الوسائط أكثر كفاءة."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro يدعم ما يصل إلى 2 مليون توكن، وهو الخيار المثالي للنماذج المتوسطة الحجم متعددة الوسائط، مناسب لدعم المهام المعقدة من جوانب متعددة."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash يقدم ميزات وتحسينات من الجيل التالي، بما في ذلك سرعة فائقة، واستخدام أدوات أصلية، وتوليد متعدد الوسائط، ونافذة سياق تصل إلى 1M توكن."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash يقدم ميزات وتحسينات من الجيل التالي، بما في ذلك سرعة فائقة، واستخدام أدوات أصلية، وتوليد متعدد الوسائط، ونافذة سياق تصل إلى 1M توكن."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "نموذج جمنّي 2.0 فلاش هو نسخة معدلة، تم تحسينها لتحقيق الكفاءة من حيث التكلفة والحد من التأخير."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "نموذج جمنّي 2.0 فلاش هو نسخة معدلة، تم تحسينها لتحقيق الكفاءة من حيث التكلفة والحد من التأخير."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "نموذج Gemini 2.0 Flash، تم تحسينه لأهداف التكلفة المنخفضة والكمون المنخفض."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp هو أحدث نموذج تجريبي متعدد الوسائط من Google، يتمتع بميزات الجيل التالي، وسرعة فائقة، واستدعاء أدوات أصلية، وتوليد متعدد الوسائط."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp هو أحدث نموذج تجريبي متعدد الوسائط من Google، يتمتع بميزات الجيل التالي، وسرعة فائقة، واستدعاء أدوات أصلية، وتوليد متعدد الوسائط."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental هو أحدث نموذج ذكاء اصطناعي متعدد الوسائط التجريبي من Google، مع تحسينات ملحوظة في الجودة مقارنة بالإصدارات السابقة، خاصة في المعرفة العالمية، والبرمجة، والسياقات الطويلة."
+ },
"gemma-7b-it": {
"description": "Gemma 7B مناسب لمعالجة المهام المتوسطة والصغيرة، ويجمع بين الكفاءة من حيث التكلفة."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 هو نموذج فعال أطلقته Google، يغطي مجموعة متنوعة من سيناريوهات التطبيقات من التطبيقات الصغيرة إلى معالجة البيانات المعقدة."
},
- "general": {
- "description": "Spark Lite هو نموذج لغوي كبير خفيف الوزن، يتمتع بتأخير منخفض للغاية وقدرة معالجة فعالة، ومفتوح بالكامل، ويدعم وظيفة البحث عبر الإنترنت في الوقت الحقيقي. تجعل خاصية الاستجابة السريعة منه مثاليًا لتطبيقات الاستدلال على الأجهزة ذات القدرة الحاسوبية المنخفضة وتعديل النماذج، مما يوفر للمستخدمين قيمة ممتازة وتجربة ذكية، خاصة في مجالات الإجابة على الأسئلة، وتوليد المحتوى، وسيناريوهات البحث."
- },
"generalv3": {
"description": "Spark Pro هو نموذج لغوي كبير عالي الأداء تم تحسينه للحقول المهنية، يركز على الرياضيات، والبرمجة، والطب، والتعليم، ويدعم البحث عبر الإنترنت بالإضافة إلى المكونات الإضافية المدمجة مثل الطقس والتاريخ. يظهر النموذج المحسن أداءً ممتازًا وكفاءة في الإجابة على الأسئلة المعقدة، وفهم اللغة، وإنشاء نصوص عالية المستوى، مما يجعله الخيار المثالي لتطبيقات الاستخدام المهني."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 هو أحدث إصدار من النموذج، مصمم للمهام المعقدة والمتنوعة، ويظهر أداءً ممتازًا."
},
+ "glm-4-9b-chat": {
+ "description": "يظهر GLM-4-9B-Chat أداءً عاليًا في مجالات متعددة مثل الدلالات والرياضيات والاستدلال والترميز والمعرفة. كما أنه مزود بقدرات تصفح الويب وتنفيذ الشيفرات واستدعاء الأدوات المخصصة واستدلال النصوص الطويلة. يدعم 26 لغة بما في ذلك اليابانية والكورية والألمانية."
+ },
"glm-4-air": {
"description": "GLM-4-Air هو إصدار ذو قيمة عالية، يتمتع بأداء قريب من GLM-4، ويقدم سرعة عالية وسعرًا معقولًا."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash هو الخيار المثالي لمعالجة المهام البسيطة، حيث يتمتع بأسرع سرعة وأفضل سعر."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX هو إصدار معزز من Flash، يتميز بسرعة استدلال فائقة."
+ },
"glm-4-long": {
"description": "GLM-4-Long يدعم إدخالات نصية طويلة جدًا، مما يجعله مناسبًا للمهام الذاكرية ومعالجة الوثائق الكبيرة."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V يوفر قدرات قوية في فهم الصور والاستدلال، ويدعم مجموعة متنوعة من المهام البصرية."
},
+ "glm-4v-flash": {
+ "description": "يتميز GLM-4V-Flash بتركيزه على فهم الصور الفردية بكفاءة، وهو مناسب لسيناريوهات تحليل الصور السريعة، مثل تحليل الصور في الوقت الفعلي أو معالجة الصور بكميات كبيرة."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus يتمتع بقدرة على فهم محتوى الفيديو والصور المتعددة، مما يجعله مناسبًا للمهام متعددة الوسائط."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 يوفر قدرات معالجة متعددة الوسائط محسّنة، مناسبة لمجموعة متنوعة من سيناريوهات المهام المعقدة."
+ "glm-zero-preview": {
+ "description": "يمتلك GLM-Zero-Preview قدرة قوية على الاستدلال المعقد، ويظهر أداءً ممتازًا في مجالات الاستدلال المنطقي، والرياضيات، والبرمجة."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash يقدم ميزات وتحسينات من الجيل التالي، بما في ذلك سرعة فائقة، واستخدام أدوات أصلية، وتوليد متعدد الوسائط، ونافذة سياق تصل إلى 1M توكن."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental هو أحدث نموذج ذكاء اصطناعي متعدد الوسائط التجريبي من Google، مع تحسينات ملحوظة في الجودة مقارنة بالإصدارات السابقة، خاصة في المعرفة العالمية، والبرمجة، والسياقات الطويلة."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "يقدم Gemini 1.5 Flash قدرات معالجة متعددة الوسائط محسّنة، مناسبة لمجموعة متنوعة من سيناريوهات المهام المعقدة."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 يجمع بين أحدث تقنيات التحسين، مما يوفر قدرة معالجة بيانات متعددة الوسائط أكثر كفاءة."
+ "google/gemini-pro-1.5": {
+ "description": "يجمع Gemini 1.5 Pro بين أحدث تقنيات التحسين، مما يوفر قدرة معالجة بيانات متعددة الوسائط بشكل أكثر كفاءة."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 هو نموذج فعال أطلقته Google، يغطي مجموعة متنوعة من سيناريوهات التطبيقات من التطبيقات الصغيرة إلى معالجة البيانات المعقدة."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 تستمر في مفهوم التصميم الخفيف والفعال."
},
+ "google/gemma-2-2b-it": {
+ "description": "نموذج تحسين التعليمات الخفيف من Google"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 هو نموذج فعال أطلقته Google، يغطي مجموعة متنوعة من سيناريوهات التطبيقات من التطبيقات الصغيرة إلى معالجة البيانات المعقدة."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 هو سلسلة نماذج نصية مفتوحة المصدر خفيفة الوزن من Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "نموذج GPT 3.5 Turbo، مناسب لمجموعة متنوعة من مهام توليد وفهم النصوص، يشير حاليًا إلى gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "جي بي تي 3.5 توربو، نموذج فعال مقدم من OpenAI، مناسب للدردشة ومهام توليد النصوص، يدعم استدعاءات الوظائف المتوازية."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "جي بي تي 3.5 توربو 16k، نموذج توليد نصوص عالي السعة، مناسب للمهام المعقدة."
+ },
"gpt-4": {
"description": "يوفر GPT-4 نافذة سياقية أكبر، مما يمكنه من معالجة إدخالات نصية أطول، مما يجعله مناسبًا للمواقف التي تتطلب دمج معلومات واسعة وتحليل البيانات."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "نموذج GPT-4 Turbo الأحدث يتمتع بقدرات بصرية. الآن، يمكن استخدام الطلبات البصرية باستخدام نمط JSON واستدعاء الوظائف. GPT-4 Turbo هو إصدار معزز يوفر دعمًا فعالًا من حيث التكلفة للمهام متعددة الوسائط. يجد توازنًا بين الدقة والكفاءة، مما يجعله مناسبًا للتطبيقات التي تتطلب تفاعلات في الوقت الحقيقي."
},
- "gpt-4-1106-vision-preview": {
- "description": "نموذج GPT-4 Turbo الأحدث يتمتع بقدرات بصرية. الآن، يمكن استخدام الطلبات البصرية باستخدام نمط JSON واستدعاء الوظائف. GPT-4 Turbo هو إصدار معزز يوفر دعمًا فعالًا من حيث التكلفة للمهام متعددة الوسائط. يجد توازنًا بين الدقة والكفاءة، مما يجعله مناسبًا للتطبيقات التي تتطلب تفاعلات في الوقت الحقيقي."
- },
"gpt-4-32k": {
"description": "يوفر GPT-4 نافذة سياقية أكبر، مما يمكنه من معالجة إدخالات نصية أطول، مما يجعله مناسبًا للمواقف التي تتطلب دمج معلومات واسعة وتحليل البيانات."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "نموذج GPT-4 Turbo الأحدث يتمتع بقدرات بصرية. الآن، يمكن استخدام الطلبات البصرية باستخدام نمط JSON واستدعاء الوظائف. GPT-4 Turbo هو إصدار معزز يوفر دعمًا فعالًا من حيث التكلفة للمهام متعددة الوسائط. يجد توازنًا بين الدقة والكفاءة، مما يجعله مناسبًا للتطبيقات التي تتطلب تفاعلات في الوقت الحقيقي."
},
+ "gpt-4.5-preview": {
+ "description": "نسخة المعاينة البحثية لـ GPT-4.5، وهي أكبر وأقوى نموذج GPT لدينا حتى الآن. تتمتع بمعرفة واسعة عن العالم وتفهم أفضل لنوايا المستخدم، مما يجعلها بارعة في المهام الإبداعية والتخطيط الذاتي. يمكن لـ GPT-4.5 قبول المدخلات النصية والصورية وتوليد مخرجات نصية (بما في ذلك المخرجات الهيكلية). تدعم ميزات المطورين الأساسية مثل استدعاء الدوال، وواجهة برمجة التطبيقات الجماعية، والمخرجات المتدفقة. تتألق GPT-4.5 بشكل خاص في المهام التي تتطلب التفكير الإبداعي، والتفكير المفتوح، والحوار (مثل الكتابة، والتعلم، أو استكشاف أفكار جديدة). تاريخ انتهاء المعرفة هو أكتوبر 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o هو نموذج ديناميكي يتم تحديثه في الوقت الحقيقي للحفاظ على أحدث إصدار. يجمع بين فهم اللغة القوي وقدرات التوليد، مما يجعله مناسبًا لمجموعة واسعة من التطبيقات، بما في ذلك خدمة العملاء والتعليم والدعم الفني."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o هو نموذج ديناميكي يتم تحديثه في الوقت الحقيقي للحفاظ على أحدث إصدار. يجمع بين فهم اللغة القوي وقدرات التوليد، مما يجعله مناسبًا لمجموعة واسعة من التطبيقات، بما في ذلك خدمة العملاء والتعليم والدعم الفني."
},
+ "gpt-4o-2024-11-20": {
+ "description": "تشات جي بي تي-4o هو نموذج ديناميكي يتم تحديثه في الوقت الفعلي للحفاظ على أحدث إصدار. يجمع بين الفهم اللغوي القوي وقدرة التوليد، مما يجعله مناسبًا لتطبيقات واسعة النطاق، بما في ذلك خدمة العملاء والتعليم والدعم الفني."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "نموذج GPT-4o Audio، يدعم إدخال وإخراج الصوت."
+ },
"gpt-4o-mini": {
"description": "نموذج GPT-4o mini هو أحدث نموذج أطلقته OpenAI بعد GPT-4 Omni، ويدعم إدخال الصور والنصوص وإخراج النصوص. كأحد نماذجهم المتقدمة الصغيرة، فهو أرخص بكثير من النماذج الرائدة الأخرى في الآونة الأخيرة، وأرخص بأكثر من 60% من GPT-3.5 Turbo. يحتفظ بذكاء متقدم مع قيمة ممتازة. حصل GPT-4o mini على 82% في اختبار MMLU، وهو حاليًا يتفوق على GPT-4 في تفضيلات الدردشة."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "الإصدار المصغر الفوري من GPT-4o، يدعم إدخال وإخراج الصوت والنص في الوقت الحقيقي."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "الإصدار الفوري من GPT-4o، يدعم إدخال وإخراج الصوت والنص في الوقت الحقيقي."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "الإصدار الفوري من GPT-4o، يدعم إدخال وإخراج الصوت والنص في الوقت الحقيقي."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "الإصدار الفوري من GPT-4o، يدعم إدخال وإخراج الصوت والنص في الوقت الحقيقي."
+ },
+ "grok-2-1212": {
+ "description": "لقد تم تحسين هذا النموذج في الدقة، والامتثال للتعليمات، والقدرة على التعامل مع لغات متعددة."
+ },
+ "grok-2-vision-1212": {
+ "description": "لقد تم تحسين هذا النموذج في الدقة، والامتثال للتعليمات، والقدرة على التعامل مع لغات متعددة."
+ },
+ "grok-beta": {
+ "description": "يمتلك أداءً يعادل Grok 2، ولكنه يتمتع بكفاءة وسرعة ووظائف أعلى."
+ },
+ "grok-vision-beta": {
+ "description": "أحدث نموذج لفهم الصور، يمكنه معالجة مجموعة متنوعة من المعلومات البصرية، بما في ذلك الوثائق، الرسوم البيانية، لقطات الشاشة، والصور."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B هو نموذج لغوي يجمع بين الإبداع والذكاء من خلال دمج عدة نماذج رائدة."
},
+ "hunyuan-code": {
+ "description": "نموذج توليد الشيفرة الأحدث من Hunyuan، تم تدريبه على نموذج أساسي من بيانات الشيفرة عالية الجودة بحجم 200B، مع تدريب عالي الجودة على بيانات SFT لمدة ستة أشهر، وزيادة طول نافذة السياق إلى 8K، ويحتل مرتبة متقدمة في مؤشرات التقييم التلقائي لتوليد الشيفرة في خمس لغات؛ كما أنه في الطليعة في تقييمات الشيفرة عالية الجودة عبر عشرة معايير في خمس لغات."
+ },
+ "hunyuan-functioncall": {
+ "description": "نموذج Hunyuan الأحدث من نوع MOE FunctionCall، تم تدريبه على بيانات FunctionCall عالية الجودة، مع نافذة سياق تصل إلى 32K، ويحتل مرتبة متقدمة في مؤشرات التقييم عبر عدة أبعاد."
+ },
+ "hunyuan-large": {
+ "description": "نموذج Hunyuan-large يحتوي على حوالي 389 مليار معلمة، مع حوالي 52 مليار معلمة نشطة، وهو أكبر نموذج MoE مفتوح المصدر في الصناعة من حيث حجم المعلمات وأفضلها من حيث الأداء."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "يتفوق في معالجة المهام الطويلة مثل تلخيص الوثائق والأسئلة والأجوبة المتعلقة بالوثائق، كما يمتلك القدرة على معالجة مهام إنشاء النصوص العامة. يظهر أداءً ممتازًا في تحليل وإنشاء النصوص الطويلة، مما يمكنه من التعامل بفعالية مع متطلبات معالجة المحتوى الطويل المعقد والمفصل."
+ },
+ "hunyuan-lite": {
+ "description": "تم الترقية إلى هيكل MOE، مع نافذة سياق تصل إلى 256k، متفوقًا على العديد من النماذج مفتوحة المصدر في تقييمات NLP، البرمجة، الرياضيات، والصناعات."
+ },
+ "hunyuan-lite-vision": {
+ "description": "نموذج مختلط حديث بقدرة 7 مليار معلمة، مع نافذة سياقية 32K، يدعم المحادثات متعددة الوسائط في السيناريوهات الصينية والإنجليزية، والتعرف على كائنات الصور، وفهم جداول الوثائق، والرياضيات متعددة الوسائط، ويتفوق في مؤشرات التقييم على نماذج المنافسة ذات 7 مليار معلمة في عدة أبعاد."
+ },
+ "hunyuan-pro": {
+ "description": "نموذج نصوص طويلة MOE-32K بحجم تريليون من المعلمات. يحقق مستوى رائد مطلق في مختلف المعايير، مع القدرة على التعامل مع التعليمات المعقدة والاستدلال، ويتميز بقدرات رياضية معقدة، ويدعم استدعاء الوظائف، مع تحسينات رئيسية في مجالات الترجمة متعددة اللغات، المالية، القانونية، والرعاية الصحية."
+ },
+ "hunyuan-role": {
+ "description": "نموذج Hunyuan الأحدث لتقمص الأدوار، تم تطويره من قبل Hunyuan مع تدريب دقيق، يعتمد على نموذج Hunyuan مع مجموعة بيانات سيناريوهات تقمص الأدوار، مما يوفر أداءً أفضل في سيناريوهات تقمص الأدوار."
+ },
+ "hunyuan-standard": {
+ "description": "يستخدم استراتيجية توجيه أفضل، مع تخفيف مشكلات التوازن في الحمل وتوافق الخبراء. في مجال النصوص الطويلة، تصل نسبة مؤشر البحث إلى 99.9%. MOE-32K يقدم قيمة أفضل، مع تحقيق توازن بين الأداء والسعر، مما يسمح بمعالجة المدخلات النصية الطويلة."
+ },
+ "hunyuan-standard-256K": {
+ "description": "يستخدم استراتيجية توجيه أفضل، مع تخفيف مشكلات التوازن في الحمل وتوافق الخبراء. في مجال النصوص الطويلة، تصل نسبة مؤشر البحث إلى 99.9%. MOE-256K يحقق اختراقًا إضافيًا في الطول والأداء، مما يوسع بشكل كبير طول المدخلات الممكنة."
+ },
+ "hunyuan-standard-vision": {
+ "description": "نموذج متعدد الوسائط حديث يدعم الإجابة بعدة لغات، مع توازن في القدرات بين الصينية والإنجليزية."
+ },
+ "hunyuan-translation": {
+ "description": "يدعم الترجمة بين 15 لغة بما في ذلك الصينية والإنجليزية واليابانية والفرنسية والبرتغالية والإسبانية والتركية والروسية والعربية والكورية والإيطالية والألمانية والفيتنامية والماليزية والإندونيسية، ويعتمد على مجموعة تقييم الترجمة متعددة السيناريوهات لتقييم تلقائي باستخدام درجة COMET، حيث يتفوق بشكل عام على نماذج السوق المماثلة في القدرة على الترجمة بين اللغات الشائعة."
+ },
+ "hunyuan-translation-lite": {
+ "description": "يدعم نموذج الترجمة هونيون الترجمة الحوارية بلغة طبيعية؛ يدعم الترجمة بين 15 لغة بما في ذلك الصينية والإنجليزية واليابانية والفرنسية والبرتغالية والإسبانية والتركية والروسية والعربية والكورية والإيطالية والألمانية والفيتنامية والماليزية والإندونيسية."
+ },
+ "hunyuan-turbo": {
+ "description": "نسخة المعاينة من الجيل الجديد من نموذج اللغة الكبير، يستخدم هيكل نموذج الخبراء المختلط (MoE) الجديد، مما يوفر كفاءة استدلال أسرع وأداء أقوى مقارنة بـ hunyuan-pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "الإصدار الثابت من hunyuan-turbo بتاريخ 20 نوفمبر 2024، وهو إصدار يقع بين hunyuan-turbo و hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "تحسينات في هذا الإصدار: توجيه البيانات، مما يعزز بشكل كبير قدرة النموذج على التعميم؛ تحسين كبير في القدرات الرياضية، البرمجية، وقدرات الاستدلال المنطقي؛ تحسين القدرات المتعلقة بفهم النصوص والكلمات؛ تحسين جودة إنشاء محتوى النص."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "تحسين تجربة شاملة، بما في ذلك فهم اللغة الطبيعية، إنشاء النصوص، الدردشة، الأسئلة والأجوبة المعرفية، الترجمة، والمجالات الأخرى؛ تعزيز الطابع الإنساني، وتحسين الذكاء العاطفي للنموذج؛ تعزيز قدرة النموذج على توضيح النوايا الغامضة؛ تحسين القدرة على معالجة الأسئلة المتعلقة بتحليل الكلمات؛ تحسين جودة الإبداع والتفاعل؛ تعزيز تجربة التفاعل المتعدد الجولات."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "نموذج اللغة البصرية الرائد من الجيل الجديد، يستخدم هيكل نموذج الخبراء المختلط (MoE) الجديد، مع تحسين شامل في القدرات المتعلقة بفهم النصوص والصور، وإنشاء المحتوى، والأسئلة والأجوبة المعرفية، والتحليل والاستدلال مقارنة بالنماذج السابقة."
+ },
+ "hunyuan-vision": {
+ "description": "نموذج Hunyuan الأحدث متعدد الوسائط، يدعم إدخال الصور والنصوص لتوليد محتوى نصي."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "نموذج مفتوح المصدر مبتكر InternLM2.5، يعزز الذكاء الحواري من خلال عدد كبير من المعلمات."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 يوفر حلول حوار ذكية في عدة سيناريوهات."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "نموذج Llama 3.1 70B للتعليمات، يتمتع بـ 70B من المعلمات، قادر على تقديم أداء ممتاز في مهام توليد النصوص الكبيرة والتعليمات."
+ "internlm2-pro-chat": {
+ "description": "نموذج النسخة القديمة الذي لا زلنا نحافظ عليه، يتوفر بخيارات متعددة من عدد المعلمات 7 مليار و 20 مليار."
+ },
+ "internlm2.5-latest": {
+ "description": "سلسلة نماذجنا الأحدث، تتمتع بأداء استدلال ممتاز، تدعم طول سياق يصل إلى 1 مليون، بالإضافة إلى قدرة أقوى على اتباع التعليمات واستدعاء الأدوات."
+ },
+ "internlm3-latest": {
+ "description": "سلسلة نماذجنا الأحدث، تتمتع بأداء استدلال ممتاز، تتصدر نماذج المصدر المفتوح من نفس الفئة. تشير بشكل افتراضي إلى أحدث نماذج سلسلة InternLM3 التي تم إصدارها."
+ },
+ "jina-deepsearch-v1": {
+ "description": "البحث العميق يجمع بين البحث عبر الإنترنت، والقراءة، والاستدلال، مما يتيح إجراء تحقيق شامل. يمكنك اعتباره وكيلًا يتولى مهام البحث الخاصة بك - حيث يقوم بإجراء بحث واسع النطاق ويخضع لعدة تكرارات قبل تقديم الإجابة. تتضمن هذه العملية بحثًا مستمرًا، واستدلالًا، وحل المشكلات من زوايا متعددة. وهذا يختلف اختلافًا جوهريًا عن النماذج الكبيرة القياسية التي تولد الإجابات مباشرة من البيانات المدربة مسبقًا، وكذلك عن أنظمة RAG التقليدية التي تعتمد على البحث السطحي لمرة واحدة."
+ },
+ "kimi-latest": {
+ "description": "يستخدم منتج كيمي المساعد الذكي أحدث نموذج كبير من كيمي، وقد يحتوي على ميزات لم تستقر بعد. يدعم فهم الصور، وسيختار تلقائيًا نموذج 8k/32k/128k كنموذج للتسعير بناءً على طول سياق الطلب."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM هو نموذج لغوي تجريبي محدد المهام، تم تدريبه ليتماشى مع مبادئ علوم التعلم، يمكنه اتباع التعليمات النظامية في سيناريوهات التعليم والتعلم، ويعمل كمدرب خبير."
+ },
+ "lite": {
+ "description": "سبارك لايت هو نموذج لغوي كبير خفيف الوزن، يتميز بتأخير منخفض للغاية وكفاءة عالية في المعالجة، وهو مجاني تمامًا ومفتوح، ويدعم وظيفة البحث عبر الإنترنت في الوقت الحقيقي. تجعل خصائص استجابته السريعة منه مثاليًا لتطبيقات الاستدلال على الأجهزة ذات القدرة الحاسوبية المنخفضة وضبط النماذج، مما يوفر للمستخدمين قيمة ممتازة من حيث التكلفة وتجربة ذكية، خاصة في مجالات الأسئلة والأجوبة المعرفية، وتوليد المحتوى، وسيناريوهات البحث."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B يوفر قدرة استدلال ذكائي أقوى، مناسب للتطبيقات المعقدة، يدعم معالجة حسابية ضخمة ويضمن الكفاءة والدقة."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B هو نموذج عالي الأداء، يوفر قدرة سريعة على توليد النصوص، مما يجعله مثاليًا لمجموعة من التطبيقات التي تتطلب كفاءة كبيرة وتكلفة فعالة."
},
- "llama-3.1-8b-instruct": {
- "description": "نموذج Llama 3.1 8B للتعليمات، يتمتع بـ 8B من المعلمات، يدعم تنفيذ مهام التعليمات بكفاءة، ويوفر قدرة ممتازة على توليد النصوص."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "قدرة استدلال الصور التي تبرز في الصور عالية الدقة، مناسبة لتطبيقات الفهم البصري."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "نموذج Llama 3.1 Sonar Huge Online، يتمتع بـ 405B من المعلمات، يدعم طول سياق حوالي 127,000 علامة، مصمم لتطبيقات دردشة معقدة عبر الإنترنت."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 مصمم للتعامل مع المهام التي تجمع بين البيانات البصرية والنصية. يظهر أداءً ممتازًا في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة والاستدلال البصري."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "نموذج Llama 3.1 Sonar Large Chat، يتمتع بـ 70B من المعلمات، يدعم طول سياق حوالي 127,000 علامة، مناسب لمهام دردشة غير متصلة معقدة."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "قدرة استدلال الصور المتقدمة المناسبة لتطبيقات الوكلاء في الفهم البصري."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "نموذج Llama 3.1 Sonar Large Online، يتمتع بـ 70B من المعلمات، يدعم طول سياق حوالي 127,000 علامة، مناسب لمهام دردشة عالية السعة ومتنوعة."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 مصمم للتعامل مع المهام التي تجمع بين البيانات البصرية والنصية. يظهر أداءً ممتازًا في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة والاستدلال البصري."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "نموذج Llama 3.1 Sonar Small Chat، يتمتع بـ 8B من المعلمات، مصمم للدردشة غير المتصلة، يدعم طول سياق حوالي 127,000 علامة."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 هو النموذج الأكثر تقدمًا في سلسلة Llama، وهو نموذج لغوي مفتوح المصدر متعدد اللغات، يوفر تجربة أداء تنافس نموذج 405B بتكلفة منخفضة للغاية. يعتمد على هيكل Transformer، وتم تحسين فائدته وأمانه من خلال التعديل الدقيق تحت الإشراف (SFT) والتعلم المعزز من خلال التغذية الراجعة البشرية (RLHF). تم تحسين نسخة التعديل الخاصة به لتكون مثالية للحوار متعدد اللغات، حيث يتفوق في العديد من المعايير الصناعية على العديد من نماذج الدردشة المفتوحة والمغلقة. تاريخ انتهاء المعرفة هو ديسمبر 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "نموذج Llama 3.1 Sonar Small Online، يتمتع بـ 8B من المعلمات، يدعم طول سياق حوالي 127,000 علامة، مصمم للدردشة عبر الإنترنت، قادر على معالجة تفاعلات نصية متنوعة بكفاءة."
+ "llama-3.3-70b-versatile": {
+ "description": "ميتّا لاما 3.3 هو نموذج لغة كبير متعدد اللغات (LLM) يضم 70 مليار (إدخال نص/إخراج نص) من النموذج المدرب مسبقًا والمعدل وفقًا للتعليمات. تم تحسين نموذج لاما 3.3 المعدل وفقًا للتعليمات للاستخدامات الحوارية متعددة اللغات ويتفوق على العديد من النماذج المتاحة مفتوحة المصدر والمغلقة في المعايير الصناعية الشائعة."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B يوفر قدرة معالجة معقدة لا مثيل لها، مصمم خصيصًا للمشاريع ذات المتطلبات العالية."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral مصمم للبحث العلمي والاستدلال الرياضي، يوفر قدرة حسابية فعالة وتفسير النتائج."
},
+ "max-32k": {
+ "description": "سبارك ماكس 32K مزود بقدرة معالجة سياق كبيرة، مع فهم أقوى للسياق وقدرة على الاستدلال المنطقي، يدعم إدخال نصوص تصل إلى 32K توكن، مما يجعله مناسبًا لقراءة الوثائق الطويلة، والأسئلة والأجوبة المعرفية الخاصة، وغيرها من السيناريوهات."
+ },
"meta-llama-3-70b-instruct": {
"description": "نموذج قوي بحجم 70 مليار معلمة يتفوق في التفكير، والترميز، وتطبيقات اللغة الواسعة."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) يوفر قدرة ممتازة على معالجة اللغة وتجربة تفاعلية رائعة."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "يوفر LLaMA-2 قدرة معالجة لغوية ممتازة وتجربة تفاعلية رائعة."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) هو نموذج دردشة قوي، يدعم احتياجات الحوار المعقدة."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) يوفر دعمًا متعدد اللغات، ويغطي مجموعة واسعة من المعرفة في المجالات."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "تم تصميم LLaMA 3.2 لمعالجة المهام التي تجمع بين البيانات البصرية والنصية. إنه يبرز في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة واستدلال الرؤية."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "تم تصميم LLaMA 3.2 لمعالجة المهام التي تجمع بين البيانات البصرية والنصية. إنه يبرز في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة واستدلال الرؤية."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "تم تصميم LLaMA 3.2 لمعالجة المهام التي تجمع بين البيانات البصرية والنصية. إنه يبرز في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة واستدلال الرؤية."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 هو أحدث نموذج لغوي مفتوح المصدر متعدد اللغات من سلسلة Llama، يقدم تجربة مشابهة لأداء نموذج 405B بتكلفة منخفضة للغاية. يعتمد على هيكل Transformer، وتم تحسينه من خلال التعديل الإشرافي (SFT) والتعلم المعزز من خلال ردود الفعل البشرية (RLHF) لتعزيز الفائدة والأمان. تم تحسين نسخة التعديل الخاصة به للحوار متعدد اللغات، حيث يتفوق في العديد من المعايير الصناعية على العديد من نماذج الدردشة المفتوحة والمغلقة. تاريخ انتهاء المعرفة هو ديسمبر 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "نموذج Meta Llama 3.3 متعدد اللغات (LLM) هو نموذج توليد تم تدريبه مسبقًا وضبطه على التعليمات في 70B (إدخال نص/إخراج نص). تم تحسين نموذج Llama 3.3 المعدل على التعليمات لحالات استخدام الحوار متعدد اللغات، ويتفوق على العديد من نماذج الدردشة المفتوحة والمغلقة المتاحة في المعايير الصناعية الشائعة."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "تم تصميم LLaMA 3.2 لمعالجة المهام التي تجمع بين البيانات البصرية والنصية. إنه يبرز في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة واستدلال الرؤية."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite مناسب للبيئات التي تتطلب أداءً عاليًا وزمن استجابة منخفض."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "نموذج Llama 3.1 Turbo 405B يوفر دعمًا كبيرًا للسياق لمعالجة البيانات الكبيرة، ويظهر أداءً بارزًا في تطبيقات الذكاء الاصطناعي على نطاق واسع."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 هو نموذج رائد أطلقته Meta، يدعم ما يصل إلى 405B من المعلمات، ويمكن تطبيقه في مجالات المحادثات المعقدة، والترجمة متعددة اللغات، وتحليل البيانات."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B يوفر دعمًا فعالًا للحوار متعدد اللغات."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct تم تحسينه لمشاهد الحوار عالية الجودة، ويظهر أداءً أفضل من العديد من النماذج المغلقة."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct هو أحدث إصدار من Meta، تم تحسينه لتوليد حوارات عالية الجودة، متجاوزًا العديد من النماذج المغلقة الرائدة."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct مصمم للحوار عالي الجودة، ويظهر أداءً بارزًا في التقييمات البشرية، مما يجعله مناسبًا بشكل خاص للمشاهد التفاعلية العالية."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 يوفر دعمًا متعدد اللغات، وهو واحد من النماذج الرائدة في الصناعة في مجال التوليد."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "تم تصميم LLaMA 3.2 لمعالجة المهام التي تجمع بين البيانات البصرية والنصية. إنه يتفوق في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة والاستدلال البصري."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "تم تصميم LLaMA 3.2 لمعالجة المهام التي تجمع بين البيانات البصرية والنصية. إنه يتفوق في مهام وصف الصور والأسئلة البصرية، متجاوزًا الفجوة بين توليد اللغة والاستدلال البصري."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 هو النموذج الأكثر تقدمًا في سلسلة Llama، وهو نموذج لغوي مفتوح المصدر متعدد اللغات، يوفر تجربة أداء تنافس نموذج 405B بتكلفة منخفضة للغاية. يعتمد على هيكل Transformer، وتم تحسين فائدته وأمانه من خلال التعديل الدقيق تحت الإشراف (SFT) والتعلم المعزز من خلال التغذية الراجعة البشرية (RLHF). تم تحسين نسخة التعديل الخاصة به لتكون مثالية للحوار متعدد اللغات، حيث يتفوق في العديد من المعايير الصناعية على العديد من نماذج الدردشة المفتوحة والمغلقة. تاريخ انتهاء المعرفة هو ديسمبر 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 هو النموذج الأكثر تقدمًا في سلسلة Llama، وهو نموذج لغوي مفتوح المصدر متعدد اللغات، يوفر تجربة أداء تنافس نموذج 405B بتكلفة منخفضة للغاية. يعتمد على هيكل Transformer، وتم تحسين فائدته وأمانه من خلال التعديل الدقيق تحت الإشراف (SFT) والتعلم المعزز من خلال التغذية الراجعة البشرية (RLHF). تم تحسين نسخة التعديل الخاصة به لتكون مثالية للحوار متعدد اللغات، حيث يتفوق في العديد من المعايير الصناعية على العديد من نماذج الدردشة المفتوحة والمغلقة. تاريخ انتهاء المعرفة هو ديسمبر 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "نموذج Meta Llama 3.1 405B Instruct هو أكبر وأقوى نموذج في مجموعة نماذج Llama 3.1 Instruct، وهو نموذج متقدم للغاية لتوليد البيانات والحوار، ويمكن استخدامه كأساس للتدريب المستمر أو التخصيص في مجالات معينة. توفر Llama 3.1 نماذج لغوية كبيرة متعددة اللغات (LLMs) وهي مجموعة من النماذج المدربة مسبقًا والمعدلة وفقًا للتعليمات، بما في ذلك أحجام 8B و70B و405B (إدخال/إخراج نصي). تم تحسين نماذج النص المعدلة وفقًا للتعليمات (8B و70B و405B) لحالات الاستخدام الحوارية متعددة اللغات، وقد تفوقت في العديد من اختبارات المعايير الصناعية الشائعة على العديد من نماذج الدردشة مفتوحة المصدر المتاحة. تم تصميم Llama 3.1 للاستخدام التجاري والبحثي في عدة لغات. نماذج النص المعدلة وفقًا للتعليمات مناسبة للدردشة الشبيهة بالمساعد، بينما يمكن للنماذج المدربة مسبقًا التكيف مع مجموعة متنوعة من مهام توليد اللغة الطبيعية. تدعم نماذج Llama 3.1 أيضًا تحسين نماذج أخرى باستخدام مخرجاتها، بما في ذلك توليد البيانات الاصطناعية والتنقيح. Llama 3.1 هو نموذج لغوي ذاتي التكرار يستخدم بنية المحولات المحسّنة. تستخدم النسخ المعدلة التعلم المعزز مع التغذية الراجعة البشرية (RLHF) لتلبية تفضيلات البشر فيما يتعلق بالمساعدة والأمان."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 هو نموذج لغوي كبير مفتوح (LLM) موجه للمطورين والباحثين والشركات، يهدف إلى مساعدتهم في بناء وتجربة وتوسيع أفكارهم في الذكاء الاصطناعي بشكل مسؤول. كجزء من نظام الابتكار المجتمعي العالمي، فهو مثالي للأجهزة ذات القدرة الحاسوبية والموارد المحدودة، والأجهزة الطرفية، وأوقات التدريب الأسرع."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B هو أحدث نموذج خفيف الوزن وسريع من Microsoft AI، ويقترب أداؤه من 10 أضعاف النماذج الرائدة المفتوحة المصدر الحالية."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "نموذج لغوي متقدم، يدعم توليد البيانات الاصطناعية، وتقطير المعرفة، والاستدلال، مناسب للدردشة، والبرمجة، والمهام الخاصة."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "يمكنه تمكين المحادثات المعقدة، ويتميز بفهم سياقي ممتاز، وقدرات استدلال، وقدرة على توليد النصوص."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "نموذج متقدم من الطراز الأول، يتمتع بفهم اللغة، وقدرات استدلال ممتازة، وقدرة على توليد النصوص."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "نموذج متقدم للرؤية واللغة، بارع في إجراء استدلال عالي الجودة من الصور."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "نموذج لغوي صغير متقدم، يتمتع بفهم اللغة، وقدرات استدلال ممتازة، وقدرة على توليد النصوص."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "نموذج لغوي صغير متقدم، يتمتع بفهم اللغة، وقدرات استدلال ممتازة، وقدرة على توليد النصوص."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "نموذج متقدم للرؤية واللغة، بارع في إجراء استدلال عالي الجودة من الصور."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "نموذج لغوي متقدم، بارع في الاستدلال، والرياضيات، والمعرفة العامة، واستدعاء الدوال."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 هو نموذج لغوي تقدمه Microsoft AI، يتميز بأداء ممتاز في المحادثات المعقدة، واللغات المتعددة، والاستدلال، ومساعدات الذكاء."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B هو نموذج Wizard المتقدم من Microsoft، يظهر أداءً تنافسيًا للغاية."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V هو نموذج متعدد الوسائط من الجيل الجديد تم إطلاقه بواسطة OpenBMB، ويتميز بقدرات استثنائية في التعرف على النصوص وفهم الوسائط المتعددة، ويدعم مجموعة واسعة من سيناريوهات الاستخدام."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B هو نموذج حافة عالمي المستوى من Mistral."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B هو نموذج حافة ذات قيمة ممتازة من Mistral."
+ },
"mistral": {
"description": "Mistral هو نموذج 7B أطلقته Mistral AI، مناسب لاحتياجات معالجة اللغة المتغيرة."
},
"mistral-large": {
"description": "Mixtral Large هو النموذج الرائد من Mistral، يجمع بين قدرات توليد الشيفرة، والرياضيات، والاستدلال، ويدعم نافذة سياق تصل إلى 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) هو نموذج لغة كبير متقدم (LLM) يتمتع بقدرات متطورة في التفكير والمعرفة والترميز."
- },
"mistral-large-latest": {
"description": "Mistral Large هو النموذج الرائد، يتفوق في المهام متعددة اللغات، والاستدلال المعقد، وتوليد الشيفرة، وهو الخيار المثالي للتطبيقات الراقية."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 يوفر قدرة حسابية فعالة وفهم اللغة الطبيعية، مناسب لمجموعة واسعة من التطبيقات."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B هو نموذج مضغوط ولكنه عالي الأداء، متفوق في المعالجة الجماعية والمهام البسيطة مثل التصنيف وتوليد النصوص، مع قدرة استدلال جيدة."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) هو نموذج لغوي كبير للغاية، يدعم احتياجات معالجة عالية جدًا."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B هو نموذج خبير مختلط مدرب مسبقًا، يستخدم لمهام النص العامة."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B هو نموذج خبير متفرق، يستفيد من معلمات متعددة لزيادة سرعة الاستدلال، مناسب لمعالجة المهام متعددة اللغات وتوليد الأكواد."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct هو نموذج صناعي عالي الأداء يجمع بين تحسين السرعة ودعم السياقات الطويلة."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K هو نموذج يتمتع بقدرة معالجة سياقات طويلة جدًا، مناسب لتوليد نصوص طويلة جدًا، يلبي احتياجات المهام المعقدة، قادر على معالجة ما يصل إلى 128,000 توكن، مما يجعله مثاليًا للبحث، والأكاديميات، وتوليد الوثائق الكبيرة."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "نموذج Kimi البصري (بما في ذلك moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview وغيرها) قادر على فهم محتوى الصور، بما في ذلك النصوص والألوان وأشكال الأجسام."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K يوفر قدرة معالجة سياقات متوسطة الطول، قادر على معالجة 32,768 توكن، مناسب بشكل خاص لتوليد مجموعة متنوعة من الوثائق الطويلة والحوار المعقد، ويستخدم في إنشاء المحتوى، وتوليد التقارير، وأنظمة الحوار."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "نموذج Kimi البصري (بما في ذلك moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview وغيرها) قادر على فهم محتوى الصور، بما في ذلك النصوص والألوان وأشكال الأجسام."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K مصمم خصيصًا لتوليد مهام النصوص القصيرة، يتمتع بأداء معالجة فعال، قادر على معالجة 8,192 توكن، مما يجعله مثاليًا للحوار القصير، والتدوين السريع، وتوليد المحتوى السريع."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "نموذج Kimi البصري (بما في ذلك moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview وغيرها) قادر على فهم محتوى الصور، بما في ذلك النصوص والألوان وأشكال الأجسام."
+ },
+ "moonshot-v1-auto": {
+ "description": "يمكن لـ Moonshot V1 Auto اختيار النموذج المناسب بناءً على عدد الرموز المستخدمة في السياق الحالي."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B هو إصدار مطور من Nous Hermes 2، ويحتوي على أحدث مجموعات البيانات المطورة داخليًا."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B هو نموذج لغوي كبير مخصص من NVIDIA، يهدف إلى تحسين استجابة LLM لمساعدة استفسارات المستخدمين. لقد أظهر النموذج أداءً ممتازًا في اختبارات المعايير مثل Arena Hard وAlpacaEval 2 LC وGPT-4-Turbo MT-Bench، حيث احتل المرتبة الأولى في جميع اختبارات المحاذاة التلقائية الثلاثة حتى 1 أكتوبر 2024. تم تدريب النموذج باستخدام RLHF (خاصة REINFORCE) وLlama-3.1-Nemotron-70B-Reward وHelpSteer2-Preference على أساس نموذج Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "نموذج لغوي فريد، يقدم دقة وأداء لا مثيل لهما."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B هو نموذج لغوي كبير مخصص من NVIDIA، مصمم لتحسين فائدة الاستجابات التي يولدها LLM."
+ },
+ "o1": {
+ "description": "يركز على الاستدلال المتقدم وحل المشكلات المعقدة، بما في ذلك المهام الرياضية والعلمية. مثالي للتطبيقات التي تتطلب فهمًا عميقًا للسياق وإدارة سير العمل."
+ },
"o1-mini": {
"description": "o1-mini هو نموذج استدلال سريع وفعال من حيث التكلفة مصمم لتطبيقات البرمجة والرياضيات والعلوم. يحتوي هذا النموذج على 128K من السياق وتاريخ انتهاء المعرفة في أكتوبر 2023."
},
"o1-preview": {
"description": "o1 هو نموذج استدلال جديد من OpenAI، مناسب للمهام المعقدة التي تتطلب معرفة عامة واسعة. يحتوي هذا النموذج على 128K من السياق وتاريخ انتهاء المعرفة في أكتوبر 2023."
},
+ "o3-mini": {
+ "description": "o3-mini هو أحدث نموذج استدلال صغير لدينا، يقدم ذكاءً عالياً تحت نفس تكاليف التأخير والأداء مثل o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba هو نموذج لغة Mamba 2 يركز على توليد الشيفرة، ويوفر دعمًا قويًا لمهام الشيفرة المتقدمة والاستدلال."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B هو نموذج خبير نادر، يستخدم عدة معلمات لزيادة سرعة الاستدلال، مناسب لمعالجة المهام متعددة اللغات وتوليد الشيفرة."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o هو نموذج ديناميكي يتم تحديثه في الوقت الحقيقي للحفاظ على أحدث إصدار. يجمع بين قدرات الفهم اللغوي القوي والتوليد، وهو مناسب لمجموعة واسعة من سيناريوهات الاستخدام، بما في ذلك خدمة العملاء والتعليم والدعم الفني."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o هو نموذج ديناميكي يتم تحديثه في الوقت الحقيقي للحفاظ على أحدث إصدار. يجمع بين فهم اللغة القوي وقدرة التوليد، مما يجعله مناسبًا لمجموعة واسعة من التطبيقات، بما في ذلك خدمة العملاء والتعليم والدعم الفني."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini هو أحدث نموذج من OpenAI تم إطلاقه بعد GPT-4 Omni، ويدعم إدخال النصوص والصور وإخراج النصوص. كأحد نماذجهم المتقدمة الصغيرة، فهو أرخص بكثير من النماذج الرائدة الأخرى في الآونة الأخيرة، وأرخص بأكثر من 60% من GPT-3.5 Turbo. يحتفظ بذكاء متقدم مع قيمة ممتازة. حصل GPT-4o mini على 82% في اختبار MMLU، وهو حاليًا يتفوق على GPT-4 في تفضيلات الدردشة."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "نموذج Pixtral يظهر قدرات قوية في فهم الرسوم البيانية والصور، والإجابة على الأسئلة المتعلقة بالمستندات، والاستدلال متعدد الوسائط، واتباع التعليمات، مع القدرة على إدخال الصور بدقة طبيعية ونسبة عرض إلى ارتفاع، بالإضافة إلى معالجة عدد غير محدود من الصور في نافذة سياق طويلة تصل إلى 128K توكن."
},
+ "pixtral-large-latest": {
+ "description": "بيكسترا لارج هو نموذج متعدد الوسائط مفتوح المصدر يحتوي على 124 مليار معلمة، مبني على نموذج ميسترال لارج 2. هذا هو النموذج الثاني في عائلتنا متعددة الوسائط، ويظهر مستوى متقدم من القدرة على فهم الصور."
+ },
+ "pro-128k": {
+ "description": "سبارك برو 128K مزود بقدرة معالجة سياق كبيرة جدًا، قادر على معالجة ما يصل إلى 128K من معلومات السياق، مما يجعله مناسبًا بشكل خاص للتحليل الشامل ومعالجة الروابط المنطقية طويلة الأمد في المحتوى الطويل، ويمكنه تقديم منطق سلس ومتسق ودعم متنوع للاقتباسات في الاتصالات النصية المعقدة."
+ },
+ "qvq-72b-preview": {
+ "description": "نموذج QVQ هو نموذج بحث تجريبي تم تطويره بواسطة فريق Qwen، يركز على تعزيز قدرات الاستدلال البصري، خاصة في مجال الاستدلال الرياضي."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "نموذج كود Qwen الشامل."
+ },
"qwen-coder-turbo-latest": {
"description": "نموذج Qwen للبرمجة."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "نموذج Qwen الرياضي مصمم خصيصًا لحل المسائل الرياضية."
},
+ "qwen-max": {
+ "description": "نموذج لغة ضخم من توغي بمستوى مئات المليارات، يدعم إدخال لغات مختلفة مثل الصينية والإنجليزية. هو النموذج الذي يقف خلف إصدار توغي 2.5."
+ },
"qwen-max-latest": {
"description": "نموذج لغة ضخم من Qwen بمستوى تريليونات، يدعم إدخال لغات مختلفة مثل الصينية والإنجليزية، وهو النموذج API وراء إصدار Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "تدعم نماذج كيوين-أومني إدخال بيانات متعددة الأنماط، بما في ذلك الفيديو والصوت والصور والنصوص، وتخرج الصوت والنص."
+ },
+ "qwen-plus": {
+ "description": "نموذج لغة ضخم من توغي، نسخة معززة، يدعم إدخال لغات مختلفة مثل الصينية والإنجليزية."
+ },
"qwen-plus-latest": {
"description": "نسخة محسنة من نموذج لغة Qwen الضخم، تدعم إدخال لغات مختلفة مثل الصينية والإنجليزية."
},
+ "qwen-turbo": {
+ "description": "نموذج لغة ضخم من توغي، يدعم إدخال لغات مختلفة مثل الصينية والإنجليزية."
+ },
"qwen-turbo-latest": {
"description": "نموذج لغة ضخم من Qwen، يدعم إدخال لغات مختلفة مثل الصينية والإنجليزية."
},
"qwen-vl-chat-v1": {
"description": "نموذج Qwen العملاق للغة البصرية يدعم طرق تفاعل مرنة، بما في ذلك الصور المتعددة، والأسئلة والأجوبة المتعددة، والإبداع."
},
- "qwen-vl-max": {
- "description": "نموذج Qwen العملاق للغة البصرية. يعزز بشكل أكبر من قدرة الاستدلال البصري والامتثال للتعليمات، ويقدم مستوى أعلى من الإدراك البصري والفهم."
+ "qwen-vl-max-latest": {
+ "description": "نموذج اللغة البصرية الكبير Qwen. مقارنةً بالنسخة المحسّنة، تعزز مرة أخرى من قدرة الاستدلال البصري وقدرة اتباع التعليمات، مما يوفر مستوى أعلى من الإدراك البصري والمعرفة."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "نموذج OCR الخاص بـ Tongyi Qianwen هو نموذج استخراج النصوص، يركز على قدرة استخراج النصوص من أنواع الصور مثل الوثائق، الجداول، الأسئلة، والنصوص المكتوبة بخط اليد. يمكنه التعرف على عدة لغات، بما في ذلك: الصينية، الإنجليزية، الفرنسية، اليابانية، الكورية، الألمانية، الروسية، الإيطالية، الفيتنامية، والعربية."
},
- "qwen-vl-plus": {
- "description": "نموذج Qwen العملاق للغة البصرية المعزز. يعزز بشكل كبير من قدرة التعرف على التفاصيل والتعرف على النصوص، ويدعم دقة تصل إلى مليون بكسل وأبعاد صورة بأي نسبة."
+ "qwen-vl-plus-latest": {
+ "description": "نسخة محسّنة من نموذج اللغة البصرية الكبير Qwen. تعزز بشكل كبير من قدرة التعرف على التفاصيل وقدرة التعرف على النصوص، وتدعم دقة تصل إلى أكثر من مليون بكسل وأبعاد صور بأي نسبة عرض إلى ارتفاع."
},
"qwen-vl-v1": {
"description": "نموذج تم تدريبه باستخدام نموذج Qwen-7B اللغوي، مع إضافة نموذج الصور، بدقة إدخال الصور 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 هو سلسلة جديدة من نماذج اللغة الكبيرة Qwen. Qwen2 7B هو نموذج يعتمد على بنية transformer، ويظهر أداءً ممتازًا في فهم اللغة، والقدرات متعددة اللغات، والبرمجة، والرياضيات، والاستدلال."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 هو سلسلة جديدة من نماذج اللغة الكبيرة، تتمتع بقدرات فهم وتوليد أقوى."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL هو الإصدار الأحدث من نموذج Qwen-VL، وقد حقق أداءً متقدمًا في اختبارات الفهم البصري، بما في ذلك MathVista وDocVQA وRealWorldQA وMTVQA. يمكن لـ Qwen2-VL فهم مقاطع الفيديو التي تزيد مدتها عن 20 دقيقة، مما يتيح إجابات عالية الجودة على الأسئلة المستندة إلى الفيديو، والمحادثات، وإنشاء المحتوى. كما يتمتع بقدرات استدلال واتخاذ قرارات معقدة، ويمكن دمجه مع الأجهزة المحمولة والروبوتات، مما يتيح التشغيل التلقائي بناءً على البيئة البصرية والتعليمات النصية. بالإضافة إلى الإنجليزية والصينية، يدعم Qwen2-VL الآن فهم النصوص بلغات مختلفة في الصور، بما في ذلك معظم اللغات الأوروبية واليابانية والكورية والعربية والفيتنامية."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct هو أحد أحدث نماذج اللغة الكبيرة التي أصدرتها Alibaba Cloud. يتمتع هذا النموذج 72B بقدرات محسنة بشكل ملحوظ في مجالات الترميز والرياضيات. كما يوفر النموذج دعمًا متعدد اللغات، يغطي أكثر من 29 لغة، بما في ذلك الصينية والإنجليزية. وقد حقق النموذج تحسينات ملحوظة في اتباع التعليمات وفهم البيانات الهيكلية وتوليد المخرجات الهيكلية (خاصة JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct هو أحد أحدث نماذج اللغة الكبيرة التي أصدرتها Alibaba Cloud. يتمتع هذا النموذج 32B بقدرات محسنة بشكل ملحوظ في مجالات الترميز والرياضيات. كما يوفر النموذج دعمًا متعدد اللغات، يغطي أكثر من 29 لغة، بما في ذلك الصينية والإنجليزية. وقد حقق النموذج تحسينات ملحوظة في اتباع التعليمات وفهم البيانات الهيكلية وتوليد المخرجات الهيكلية (خاصة JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "نموذج لغوي موجه للغة الصينية والإنجليزية، يستهدف مجالات اللغة، والبرمجة، والرياضيات، والاستدلال، وغيرها."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "نموذج لغوي متقدم، يدعم توليد الشيفرة، والاستدلال، والإصلاح، ويغطي لغات البرمجة الرئيسية."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "نموذج قوي للبرمجة متوسطة الحجم، يدعم طول سياق يصل إلى 32K، بارع في البرمجة متعددة اللغات."
+ },
"qwen2": {
"description": "Qwen2 هو نموذج لغوي كبير من الجيل الجديد من Alibaba، يدعم أداءً ممتازًا لتلبية احتياجات التطبيقات المتنوعة."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 هو الجيل الجديد من نماذج اللغة الكبيرة من Alibaba، يدعم احتياجات التطبيقات المتنوعة بأداء ممتاز."
+ },
"qwen2.5-14b-instruct": {
"description": "نموذج Qwen 2.5 مفتوح المصدر بحجم 14B."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "نموذج بحجم 72B مفتوح المصدر من Tongyi Qianwen 2.5."
+ },
"qwen2.5-32b-instruct": {
"description": "نموذج Qwen 2.5 مفتوح المصدر بحجم 32B."
},
@@ -824,13 +1599,16 @@
"description": "نموذج Qwen 2.5 مفتوح المصدر بحجم 7B."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "نسخة مفتوحة المصدر من نموذج Qwen للبرمجة."
+ "description": "نموذج كود تونغي، النسخة مفتوحة المصدر."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "الإصدار المفتوح من نموذج كود Qwen الشامل."
},
"qwen2.5-coder-7b-instruct": {
"description": "نسخة مفتوحة المصدر من نموذج Qwen للبرمجة."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "نموذج Qwen-Math يتمتع بقدرات قوية في حل المسائل الرياضية."
+ "description": "نموذج Qwen-Math لديه قدرة قوية على حل المسائل الرياضية."
},
"qwen2.5-math-72b-instruct": {
"description": "نموذج Qwen-Math يتمتع بقدرات قوية في حل المسائل الرياضية."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "نموذج Qwen-Math يتمتع بقدرات قوية في حل المسائل الرياضية."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "تحسين شامل في اتباع التعليمات، الرياضيات، حل المشكلات، والبرمجة، وزيادة قدرة التعرف على العناصر البصرية، يدعم تنسيقات متعددة لتحديد العناصر البصرية بدقة، ويدعم فهم ملفات الفيديو الطويلة (حتى 10 دقائق) وتحديد اللحظات الزمنية بدقة، قادر على فهم التسلسل الزمني والسرعة، يدعم التحكم في أنظمة التشغيل أو الوكلاء المحمولة بناءً على قدرات التحليل والتحديد، قوي في استخراج المعلومات الرئيسية وإخراج البيانات بتنسيق Json، هذه النسخة هي النسخة 72B، وهي الأقوى في هذه السلسلة."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "تحسين شامل في اتباع التعليمات، الرياضيات، حل المشكلات، والبرمجة، وزيادة قدرة التعرف على العناصر البصرية، يدعم تنسيقات متعددة لتحديد العناصر البصرية بدقة، ويدعم فهم ملفات الفيديو الطويلة (حتى 10 دقائق) وتحديد اللحظات الزمنية بدقة، قادر على فهم التسلسل الزمني والسرعة، يدعم التحكم في أنظمة التشغيل أو الوكلاء المحمولة بناءً على قدرات التحليل والتحديد، قوي في استخراج المعلومات الرئيسية وإخراج البيانات بتنسيق Json، هذه النسخة هي النسخة 72B، وهي الأقوى في هذه السلسلة."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 هو الجيل الجديد من نماذج اللغة الكبيرة من Alibaba، يدعم احتياجات التطبيقات المتنوعة بأداء ممتاز."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 هو الجيل الجديد من نماذج اللغة الكبيرة من Alibaba، يدعم احتياجات التطبيقات المتنوعة بأداء ممتاز."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 هو الجيل الجديد من نماذج اللغة الكبيرة من Alibaba، يدعم احتياجات التطبيقات المتنوعة بأداء ممتاز."
+ },
"qwen2:0.5b": {
"description": "Qwen2 هو نموذج لغوي كبير من الجيل الجديد من Alibaba، يدعم أداءً ممتازًا لتلبية احتياجات التطبيقات المتنوعة."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 هو نموذج لغوي كبير من الجيل الجديد من Alibaba، يدعم أداءً ممتازًا لتلبية احتياجات التطبيقات المتنوعة."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini هو نموذج LLM مدمج، يتفوق على GPT-3.5، ويتميز بقدرات متعددة اللغات، ويدعم الإنجليزية والكورية، ويقدم حلولًا فعالة وصغيرة الحجم."
+ "qwq": {
+ "description": "QwQ هو نموذج بحث تجريبي يركز على تحسين قدرات الاستدلال للذكاء الاصطناعي."
+ },
+ "qwq-32b": {
+ "description": "نموذج استدلال QwQ المدرب على نموذج Qwen2.5-32B، الذي يعزز بشكل كبير من قدرة الاستدلال للنموذج من خلال التعلم المعزز. تصل المؤشرات الأساسية للنموذج (AIME 24/25، LiveCodeBench) وبعض المؤشرات العامة (IFEval، LiveBench وغيرها) إلى مستوى DeepSeek-R1 الكامل، حيث تتجاوز جميع المؤشرات بشكل ملحوظ نموذج DeepSeek-R1-Distill-Qwen-32B المعتمد أيضًا على Qwen2.5-32B."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) يوسع قدرات Solar Mini، ويركز على اللغة اليابانية، مع الحفاظ على الكفاءة والأداء الممتاز في استخدام الإنجليزية والكورية."
+ "qwq-32b-preview": {
+ "description": "نموذج QwQ هو نموذج بحث تجريبي تم تطويره بواسطة فريق Qwen، يركز على تعزيز قدرات الاستدلال للذكاء الاصطناعي."
+ },
+ "qwq-plus-latest": {
+ "description": "نموذج استدلال QwQ المدرب على نموذج Qwen2.5، الذي يعزز بشكل كبير من قدرة الاستدلال للنموذج من خلال التعلم المعزز. تصل المؤشرات الأساسية للنموذج (AIME 24/25، LiveCodeBench) وبعض المؤشرات العامة (IFEval، LiveBench وغيرها) إلى مستوى DeepSeek-R1 الكامل."
+ },
+ "r1-1776": {
+ "description": "R1-1776 هو إصدار من نموذج DeepSeek R1، تم تدريبه لاحقًا لتقديم معلومات حقائق غير خاضعة للرقابة وغير متحيزة."
+ },
+ "solar-mini": {
+ "description": "Solar Mini هو نموذج LLM مدمج، يتفوق على GPT-3.5، ويتميز بقدرات متعددة اللغات قوية، ويدعم الإنجليزية والكورية، ويقدم حلولًا فعالة وصغيرة الحجم."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) يوسع من قدرات Solar Mini، مع التركيز على اللغة اليابانية، مع الحفاظ على الكفاءة والأداء الممتاز في استخدام الإنجليزية والكورية."
},
"solar-pro": {
"description": "Solar Pro هو نموذج LLM عالي الذكاء تم إطلاقه من قبل Upstage، يركز على قدرة اتباع التعليمات على وحدة معالجة الرسوميات الواحدة، وسجل IFEval فوق 80. حاليًا يدعم اللغة الإنجليزية، ومن المقرر إصدار النسخة الرسمية في نوفمبر 2024، مع توسيع دعم اللغات وطول السياق."
},
+ "sonar": {
+ "description": "منتج بحث خفيف الوزن يعتمد على سياق البحث، أسرع وأرخص من Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "تقوم Deep Research بإجراء أبحاث شاملة على مستوى الخبراء وتجميعها في تقارير يمكن الوصول إليها وقابلة للتنفيذ."
+ },
+ "sonar-pro": {
+ "description": "منتج بحث متقدم يدعم سياق البحث، مع دعم للاستعلامات المتقدمة والمتابعة."
+ },
+ "sonar-reasoning": {
+ "description": "منتج API الجديد المدعوم من نموذج الاستدلال من DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "منتج API جديد مدعوم من نموذج الاستدلال DeepSeek."
+ },
"step-1-128k": {
"description": "يوفر توازنًا بين الأداء والتكلفة، مناسب لمجموعة متنوعة من السيناريوهات."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "نموذج عالي السرعة، مناسب للحوار في الوقت الحقيقي."
},
+ "step-1.5v-mini": {
+ "description": "يمتلك هذا النموذج قدرة قوية على فهم الفيديو."
+ },
+ "step-1o-turbo-vision": {
+ "description": "يمتلك هذا النموذج قدرة قوية على فهم الصور، ويتفوق في مجالات الرياضيات والبرمجة مقارنةً بـ 1o. النموذج أصغر من 1o، وسرعة الإخراج أسرع."
+ },
+ "step-1o-vision-32k": {
+ "description": "يمتلك هذا النموذج قدرة قوية على فهم الصور. مقارنةً بسلسلة نماذج step-1v، فإنه يتمتع بأداء بصري أقوى."
+ },
"step-1v-32k": {
"description": "يدعم المدخلات البصرية، يعزز تجربة التفاعل متعدد الوسائط."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "يدعم تفاعلات سياق كبيرة، مناسب لمشاهد الحوار المعقدة."
},
+ "step-2-mini": {
+ "description": "نموذج كبير سريع يعتمد على بنية الانتباه الجديدة MFA، يحقق نتائج مشابهة لـ step1 بتكلفة منخفضة جداً، مع الحفاظ على قدرة أعلى على المعالجة وزمن استجابة أسرع. يمكنه التعامل مع المهام العامة، ويتميز بقدرات قوية في البرمجة."
+ },
"taichu_llm": {
"description": "نموذج اللغة الكبير TaiChu يتمتع بقدرات قوية في فهم اللغة، بالإضافة إلى إنشاء النصوص، والإجابة على الأسئلة، وبرمجة الأكواد، والحسابات الرياضية، والاستدلال المنطقي، وتحليل المشاعر، وتلخيص النصوص. يجمع بشكل مبتكر بين التدريب المسبق على البيانات الضخمة والمعرفة الغنية من مصادر متعددة، من خلال تحسين تقنيات الخوارزميات باستمرار واستيعاب المعرفة الجديدة من البيانات النصية الضخمة، مما يحقق تطورًا مستمرًا في أداء النموذج. يوفر للمستخدمين معلومات وخدمات أكثر سهولة وتجربة أكثر ذكاءً."
},
- "taichu_vqa": {
- "description": "تايتشو 2.0V يجمع بين فهم الصور، ونقل المعرفة، والاستدلال المنطقي، ويظهر أداءً بارزًا في مجال الأسئلة والأجوبة النصية والصورية."
+ "taichu_vl": {
+ "description": "يجمع بين فهم الصور، ونقل المعرفة، والاستدلال المنطقي، ويظهر أداءً بارزًا في مجال الأسئلة والأجوبة النصية والصورية."
+ },
+ "text-embedding-3-large": {
+ "description": "أقوى نموذج لتضمين النصوص، مناسب للمهام الإنجليزية وغير الإنجليزية."
+ },
+ "text-embedding-3-small": {
+ "description": "نموذج التضمين من الجيل الجديد، فعال واقتصادي، مناسب لاسترجاع المعرفة وتطبيقات RAG وغيرها."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "الإصدار المفتوح من الجيل الأحدث من نموذج GLM-4 الذي أطلقته Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) يوفر قدرة حسابية معززة من خلال استراتيجيات فعالة وهندسة نموذجية."
},
+ "tts-1": {
+ "description": "أحدث نموذج لتحويل النص إلى كلام، تم تحسينه للسرعة في السيناريوهات الحية."
+ },
+ "tts-1-hd": {
+ "description": "أحدث نموذج لتحويل النص إلى كلام، تم تحسينه للجودة."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) مناسب لمهام التعليمات الدقيقة، يوفر قدرة معالجة لغوية ممتازة."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet يرفع المعايير الصناعية، حيث يتفوق على نماذج المنافسين وClaude 3 Opus، ويظهر أداءً ممتازًا في تقييمات واسعة، مع سرعة وتكلفة تتناسب مع نماذجنا المتوسطة."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "كلود 3.7 سونيت هو أسرع نموذج من الجيل التالي من أنثروبيك. مقارنةً بكلود 3 هايكو، تم تحسين كلود 3.7 سونيت في جميع المهارات، وتجاوز العديد من اختبارات الذكاء لأكبر نموذج من الجيل السابق، كلود 3 أوبس."
+ },
+ "whisper-1": {
+ "description": "نموذج التعرف على الصوت العام، يدعم التعرف على الصوت متعدد اللغات، والترجمة الصوتية، والتعرف على اللغات."
+ },
"wizardlm2": {
"description": "WizardLM 2 هو نموذج لغوي تقدمه Microsoft AI، يتميز بأداء ممتاز في الحوار المعقد، واللغات المتعددة، والاستدلال، والمساعدين الذكيين."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "عالية الكفاءة، أداء ممتاز. يتم ضبطها بدقة عالية لتحقيق توازن بين الأداء وسرعة الاستدلال والتكلفة."
},
+ "yi-lightning": {
+ "description": "نموذج جديد عالي الأداء، يضمن إنتاج جودة عالية مع زيادة كبيرة في سرعة الاستدلال."
+ },
+ "yi-lightning-lite": {
+ "description": "نسخة خفيفة الوزن، يُوصى باستخدام yi-lightning."
+ },
"yi-medium": {
"description": "نموذج متوسط الحجم تم تحسينه، يتمتع بقدرات متوازنة، وكفاءة عالية في التكلفة. تم تحسين قدرة اتباع التعليمات بشكل عميق."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "نموذج لمهام الرؤية المعقدة، يوفر قدرة عالية على فهم وتحليل الصور."
+ },
+ "yi-vision-v2": {
+ "description": "نموذج مهام بصرية معقدة، يوفر فهمًا عالي الأداء وقدرات تحليلية بناءً على صور متعددة."
}
}
diff --git a/DigitalHumanWeb/locales/ar/plugin.json b/DigitalHumanWeb/locales/ar/plugin.json
index 9577dad..ddfa4b1 100644
--- a/DigitalHumanWeb/locales/ar/plugin.json
+++ b/DigitalHumanWeb/locales/ar/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "فشل تحديث الإضافة {{name}}",
"urlError": "الرابط لا يعيد محتوى بتنسيق JSON، يرجى التأكد من صحة الرابط"
},
+ "inspector": {
+ "args": "عرض قائمة المعلمات",
+ "pluginRender": "عرض واجهة المكون الإضافي"
+ },
"list": {
"item": {
"deprecated.title": "مهجور",
@@ -130,6 +134,34 @@
"plugin": "جاري تشغيل الإضافة..."
},
"pluginList": "قائمة الإضافات",
+ "search": {
+ "config": {
+ "addKey": "إضافة مفتاح",
+ "close": "حذف",
+ "confirm": "تم تكوينه وإعادة المحاولة"
+ },
+ "crawPages": {
+ "crawling": "جاري التعرف على الروابط",
+ "detail": {
+ "preview": "معاينة",
+ "raw": "النص الأصلي",
+ "tooLong": "محتوى النص طويل جدًا، سيتم الاحتفاظ بالسياق السابق فقط بأول {{characters}} حرف، ولن يتم احتساب الأجزاء الزائدة في سياق المحادثة"
+ },
+ "meta": {
+ "crawler": "وضع الزحف",
+ "words": "عدد الأحرف"
+ }
+ },
+ "searchxng": {
+ "baseURL": "الرجاء الإدخال",
+ "description": "الرجاء إدخال عنوان URL لـ SearchXNG لبدء البحث عبر الإنترنت",
+ "keyPlaceholder": "الرجاء إدخال المفتاح",
+ "title": "تكوين محرك بحث SearchXNG",
+ "unconfiguredDesc": "يرجى الاتصال بالمسؤول لإكمال تكوين محرك بحث SearchXNG لبدء البحث عبر الإنترنت",
+ "unconfiguredTitle": "لم يتم تكوين محرك بحث SearchXNG بعد"
+ },
+ "title": "البحث عبر الإنترنت"
+ },
"setting": "إعدادات الإضافة",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/ar/portal.json b/DigitalHumanWeb/locales/ar/portal.json
index 3280f17..b8619fa 100644
--- a/DigitalHumanWeb/locales/ar/portal.json
+++ b/DigitalHumanWeb/locales/ar/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "ملحقات",
- "actions": {
- "genAiMessage": "إنشاء رسالة مساعد ذكاء اصطناعي",
- "summary": "ملخص",
- "summaryTooltip": "ملخص للمحتوى الحالي"
- },
"artifacts": {
"display": {
"code": "رمز",
diff --git a/DigitalHumanWeb/locales/ar/providers.json b/DigitalHumanWeb/locales/ar/providers.json
index 9daacf2..fd13cd8 100644
--- a/DigitalHumanWeb/locales/ar/providers.json
+++ b/DigitalHumanWeb/locales/ar/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "تقوم AI21 Labs ببناء نماذج أساسية وأنظمة ذكاء اصطناعي للشركات، مما يسرع من تطبيق الذكاء الاصطناعي التوليدي في الإنتاج."
+ },
"ai360": {
"description": "AI 360 هي منصة نماذج وخدمات الذكاء الاصطناعي التي أطلقتها شركة 360، تقدم مجموعة متنوعة من نماذج معالجة اللغة الطبيعية المتقدمة، بما في ذلك 360GPT2 Pro و360GPT Pro و360GPT Turbo و360GPT Turbo Responsibility 8K. تجمع هذه النماذج بين المعلمات الكبيرة والقدرات متعددة الوسائط، وتستخدم على نطاق واسع في توليد النصوص، وفهم المعاني، وأنظمة الحوار، وتوليد الشيفرات. من خلال استراتيجيات تسعير مرنة، تلبي AI 360 احتياجات المستخدمين المتنوعة، وتدعم المطورين في التكامل، مما يعزز الابتكار والتطوير في التطبيقات الذكية."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "توفر Azure مجموعة متنوعة من نماذج الذكاء الاصطناعي المتقدمة، بما في ذلك GPT-3.5 وأحدث سلسلة GPT-4، تدعم أنواع بيانات متعددة ومهام معقدة، وتلتزم بحلول ذكاء اصطناعي آمنة وموثوقة ومستدامة."
},
+ "azureai": {
+ "description": "توفر Azure مجموعة متنوعة من نماذج الذكاء الاصطناعي المتقدمة، بما في ذلك GPT-3.5 وأحدث سلسلة GPT-4، تدعم أنواع البيانات المتعددة والمهام المعقدة، وتهدف إلى تقديم حلول ذكاء اصطناعي آمنة وموثوقة ومستدامة."
+ },
"baichuan": {
"description": "Baichuan Intelligence هي شركة تركز على تطوير نماذج الذكاء الاصطناعي الكبيرة، حيث تظهر نماذجها أداءً ممتازًا في المهام الصينية مثل الموسوعات المعرفية ومعالجة النصوص الطويلة والإبداع. تتفوق على النماذج الرئيسية الأجنبية. كما تتمتع Baichuan Intelligence بقدرات متعددة الوسائط رائدة في الصناعة، وقد أظهرت أداءً ممتازًا في العديد من التقييمات الموثوقة. تشمل نماذجها Baichuan 4 وBaichuan 3 Turbo وBaichuan 3 Turbo 128k، وكل منها مُحسّن لمشاهد تطبيق مختلفة، مما يوفر حلولًا فعالة من حيث التكلفة."
},
"bedrock": {
"description": "Bedrock هي خدمة تقدمها أمازون AWS، تركز على توفير نماذج لغة ورؤية متقدمة للذكاء الاصطناعي للشركات. تشمل عائلة نماذجها سلسلة Claude من Anthropic وسلسلة Llama 3.1 من Meta، وتغطي مجموعة من الخيارات من النماذج الخفيفة إلى عالية الأداء، وتدعم مهام مثل توليد النصوص، والحوار، ومعالجة الصور، مما يجعلها مناسبة لتطبيقات الشركات بمختلف أحجامها واحتياجاتها."
},
+ "cloudflare": {
+ "description": "تشغيل نماذج التعلم الآلي المدفوعة بوحدات معالجة الرسوميات بدون خادم على شبكة Cloudflare العالمية."
+ },
"deepseek": {
"description": "DeepSeek هي شركة تركز على أبحاث وتطبيقات تقنيات الذكاء الاصطناعي، حيث يجمع نموذجها الأحدث DeepSeek-V2.5 بين قدرات الحوار العامة ومعالجة الشيفرات، وقد حقق تحسينات ملحوظة في محاذاة تفضيلات البشر، ومهام الكتابة، واتباع التعليمات."
},
+ "doubao": {
+ "description": "نموذج كبير تم تطويره داخليًا بواسطة بايت دانس. تم التحقق من صحته من خلال أكثر من 50 سيناريو عمل داخلي، مع استخدام يومي يتجاوز تريليون توكن، مما يتيح تقديم قدرات متعددة الأنماط، ويعمل على توفير تجربة عمل غنية للشركات من خلال نموذج عالي الجودة."
+ },
"fireworksai": {
"description": "Fireworks AI هي شركة رائدة في تقديم خدمات نماذج اللغة المتقدمة، تركز على استدعاء الوظائف والمعالجة متعددة الوسائط. نموذجها الأحدث Firefunction V2 مبني على Llama-3، مُحسّن لاستدعاء الوظائف، والحوار، واتباع التعليمات. يدعم نموذج اللغة البصرية FireLLaVA-13B إدخال الصور والنصوص المختلطة. تشمل النماذج البارزة الأخرى سلسلة Llama وسلسلة Mixtral، مما يوفر دعمًا فعالًا لاتباع التعليمات وتوليدها بلغات متعددة."
},
+ "giteeai": {
+ "description": "خادم واجهات برمجة التطبيقات gitee منظمة العفو الدولية يوفر نموذج كبير المنطق API خدمة منظمة العفو الدولية للمطورين ."
+ },
"github": {
"description": "مع نماذج GitHub، يمكن للمطورين أن يصبحوا مهندسي ذكاء اصطناعي ويبنون باستخدام نماذج الذكاء الاصطناعي الرائدة في الصناعة."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "يتميز محرك الاستدلال LPU من Groq بأداء ممتاز في أحدث اختبارات المعايير لنماذج اللغة الكبيرة المستقلة (LLM)، حيث أعاد تعريف معايير حلول الذكاء الاصطناعي بسرعته وكفاءته المذهلة. Groq يمثل سرعة استدلال فورية، ويظهر أداءً جيدًا في النشر القائم على السحابة."
},
+ "higress": {
+ "description": "Higress هو بوابة API سحابية الأصل، تم تطويرها داخل علي بابا لحل مشاكل إعادة تحميل Tengine التي تؤثر سلبًا على الأعمال ذات الاتصالات الطويلة، بالإضافة إلى نقص قدرات توازن الحمل لـ gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "تقدم واجهة برمجة التطبيقات الخاصة بـ HuggingFace طريقة سريعة ومجانية لاستكشاف الآلاف من النماذج لمجموعة متنوعة من المهام. سواء كنت تقوم بتصميم نموذج أولي لتطبيق جديد أو تحاول استكشاف إمكانيات التعلم الآلي، فإن هذه الواجهة تتيح لك الوصول الفوري إلى نماذج عالية الأداء في مجالات متعددة."
+ },
+ "hunyuan": {
+ "description": "نموذج لغة متقدم تم تطويره بواسطة Tencent، يتمتع بقدرة قوية على الإبداع باللغة الصينية، وقدرة على الاستدلال المنطقي في سياقات معقدة، بالإضافة إلى قدرة موثوقة على تنفيذ المهام."
+ },
+ "internlm": {
+ "description": "منظمة مفتوحة المصدر مكرسة لأبحاث وتطوير أدوات النماذج الكبيرة. توفر منصة مفتوحة المصدر فعالة وسهلة الاستخدام لجميع مطوري الذكاء الاصطناعي، مما يجعل أحدث تقنيات النماذج الكبيرة والخوارزميات في متناول اليد."
+ },
+ "jina": {
+ "description": "تأسست Jina AI في عام 2020، وهي شركة رائدة في مجال الذكاء الاصطناعي للبحث. تحتوي منصتنا الأساسية للبحث على نماذج متجهة، ومعيدي ترتيب، ونماذج لغوية صغيرة، لمساعدة الشركات في بناء تطبيقات بحث موثوقة وعالية الجودة تعتمد على الذكاء الاصطناعي التوليدي ومتعددة الوسائط."
+ },
+ "lmstudio": {
+ "description": "LM Studio هو تطبيق سطح مكتب لتطوير وتجربة نماذج اللغة الكبيرة (LLMs) على جهاز الكمبيوتر الخاص بك."
+ },
"minimax": {
"description": "MiniMax هي شركة تكنولوجيا الذكاء الاصطناعي العامة التي تأسست في عام 2021، تكرس جهودها للتعاون مع المستخدمين في إنشاء الذكاء. طورت MiniMax نماذج كبيرة عامة من أوضاع مختلفة، بما في ذلك نموذج نصي MoE الذي يحتوي على تريليونات من المعلمات، ونموذج صوتي، ونموذج صور. وقد أطلقت تطبيقات مثل Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI هي منصة تقدم خدمات API لمجموعة متنوعة من نماذج اللغة الكبيرة وتوليد الصور بالذكاء الاصطناعي، مرنة وموثوقة وفعالة من حيث التكلفة. تدعم أحدث النماذج مفتوحة المصدر مثل Llama3 وMistral، وتوفر حلول API شاملة وسهلة الاستخدام وقابلة للتوسع تلقائيًا لتطوير تطبيقات الذكاء الاصطناعي، مما يجعلها مناسبة لنمو الشركات الناشئة في مجال الذكاء الاصطناعي."
},
+ "nvidia": {
+ "description": "تقدم NVIDIA NIM™ حاويات يمكن استخدامها لاستضافة خدمات استدلال معززة بواسطة GPU، تدعم نشر نماذج الذكاء الاصطناعي المدربة مسبقًا والمخصصة على السحابة ومراكز البيانات وأجهزة الكمبيوتر الشخصية RTX™ ومحطات العمل."
+ },
"ollama": {
"description": "تغطي نماذج Ollama مجموعة واسعة من مجالات توليد الشيفرة، والعمليات الرياضية، ومعالجة اللغات المتعددة، والتفاعل الحواري، وتدعم احتياجات النشر على مستوى المؤسسات والتخصيص المحلي."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity هي شركة رائدة في تقديم نماذج توليد الحوار، تقدم مجموعة من نماذج Llama 3.1 المتقدمة، تدعم التطبيقات عبر الإنترنت وغير المتصلة، وتناسب بشكل خاص مهام معالجة اللغة الطبيعية المعقدة."
},
+ "ppio": {
+ "description": "تقدم PPIO بايو السحابية خدمات واجهة برمجة التطبيقات لنماذج مفتوحة المصدر مستقرة وذات تكلفة فعالة، تدعم جميع سلسلة DeepSeek، وLlama، وQwen، وغيرها من النماذج الكبيرة الرائدة في الصناعة."
+ },
"qwen": {
"description": "Qwen هو نموذج لغة ضخم تم تطويره ذاتيًا بواسطة Alibaba Cloud، يتمتع بقدرات قوية في فهم وتوليد اللغة الطبيعية. يمكنه الإجابة على مجموعة متنوعة من الأسئلة، وكتابة المحتوى، والتعبير عن الآراء، وكتابة الشيفرات، ويؤدي دورًا في مجالات متعددة."
},
+ "sambanova": {
+ "description": "تتيح لك سحابة SambaNova استخدام أفضل النماذج مفتوحة المصدر بسهولة، والاستمتاع بأسرع سرعة استدلال."
+ },
+ "sensenova": {
+ "description": "تقدم شركة SenseTime خدمات نماذج كبيرة شاملة وسهلة الاستخدام، مدعومة بقوة من البنية التحتية الكبيرة لشركة SenseTime."
+ },
"siliconcloud": {
"description": "تسعى SiliconFlow إلى تسريع الذكاء الاصطناعي العام (AGI) لفائدة البشرية، من خلال تحسين كفاءة الذكاء الاصطناعي على نطاق واسع باستخدام حزمة GenAI سهلة الاستخدام وذات التكلفة المنخفضة."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "أطلقت الأكاديمية الصينية للعلوم ومعهد ووهان للذكاء الاصطناعي نموذجًا جديدًا متعدد الوسائط، يدعم أسئلة وأجوبة متعددة الجولات، وإنشاء النصوص، وتوليد الصور، وفهم 3D، وتحليل الإشارات، ويغطي مجموعة شاملة من مهام الأسئلة والأجوبة، مع قدرات أقوى في الإدراك والفهم والإبداع، مما يوفر تجربة تفاعلية جديدة."
},
+ "tencentcloud": {
+ "description": "قدرة المحرك المعرفي الذري (LLM Knowledge Engine Atomic Power) هي قدرة كاملة للإجابة على الأسئلة مبنية على تطوير المحرك المعرفي، موجهة نحو الشركات والمطورين، وتوفر القدرة على تجميع وتطوير تطبيقات النماذج بشكل مرن. يمكنك من خلال مجموعة من القدرات الذرية تجميع خدمة النموذج الخاصة بك، واستدعاء خدمات تحليل الوثائق، والتقسيم، والتضمين، وإعادة الكتابة متعددة الجولات، لتخصيص أعمال الذكاء الاصطناعي الخاصة بالشركة."
+ },
"togetherai": {
"description": "تسعى Together AI لتحقيق أداء رائد من خلال نماذج الذكاء الاصطناعي المبتكرة، وتقدم مجموعة واسعة من القدرات المخصصة، بما في ذلك دعم التوسع السريع وعمليات النشر البديهية، لتلبية احتياجات الشركات المتنوعة."
},
"upstage": {
"description": "تتخصص Upstage في تطوير نماذج الذكاء الاصطناعي لتلبية احتياجات الأعمال المتنوعة، بما في ذلك Solar LLM وDocument AI، بهدف تحقيق الذكاء الاصطناعي العام (AGI) القائم على العمل. من خلال واجهة Chat API، يمكن إنشاء وكلاء حوار بسيطين، وتدعم استدعاء الوظائف، والترجمة، والتضمين، وتطبيقات المجالات المحددة."
},
+ "vertexai": {
+ "description": "سلسلة جيميني من جوجل هي نماذج الذكاء الاصطناعي الأكثر تقدمًا وعمومية، تم تطويرها بواسطة جوجل ديب مايند، مصممة خصيصًا لتكون متعددة الوسائط، تدعم الفهم والمعالجة السلسة للنصوص، الأكواد، الصور، الصوتيات، والفيديو. تناسب مجموعة متنوعة من البيئات، من مراكز البيانات إلى الأجهزة المحمولة، مما يعزز بشكل كبير كفاءة نماذج الذكاء الاصطناعي وتطبيقاتها الواسعة."
+ },
+ "vllm": {
+ "description": "vLLM هو مكتبة سريعة وسهلة الاستخدام لاستدلال LLM والخدمات."
+ },
+ "volcengine": {
+ "description": "منصة تطوير خدمات النماذج الكبيرة التي أطلقتها بايت دانس، تقدم خدمات استدعاء نماذج غنية بالوظائف وآمنة وتنافسية من حيث الأسعار، كما توفر بيانات النماذج، والتعديل الدقيق، والاستدلال، والتقييم، وغيرها من الوظائف الشاملة، لضمان تطوير تطبيقات الذكاء الاصطناعي الخاصة بك بشكل كامل."
+ },
+ "wenxin": {
+ "description": "منصة تطوير وخدمات النماذج الكبيرة والتطبيقات الأصلية للذكاء الاصطناعي على مستوى المؤسسات، تقدم مجموعة شاملة وسهلة الاستخدام من أدوات تطوير النماذج الذكية التوليدية وأدوات تطوير التطبيقات على مدار العملية بأكملها."
+ },
+ "xai": {
+ "description": "xAI هي شركة تكرّس جهودها لبناء الذكاء الاصطناعي لتسريع الاكتشافات العلمية البشرية. مهمتنا هي تعزيز فهمنا المشترك للكون."
+ },
"zeroone": {
"description": "01.AI تركز على تقنيات الذكاء الاصطناعي في عصر الذكاء الاصطناعي 2.0، وتعزز الابتكار والتطبيقات \"الإنسان + الذكاء الاصطناعي\"، باستخدام نماذج قوية وتقنيات ذكاء اصطناعي متقدمة لتعزيز إنتاجية البشر وتحقيق تمكين التكنولوجيا."
},
diff --git a/DigitalHumanWeb/locales/ar/setting.json b/DigitalHumanWeb/locales/ar/setting.json
index 3d36ece..ed21e99 100644
--- a/DigitalHumanWeb/locales/ar/setting.json
+++ b/DigitalHumanWeb/locales/ar/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "تكوين النموذج المخصص",
"tokens": {
- "title": "أقصى عدد من الرموز",
- "unlimited": "غير محدود"
+ "title": "أقصى عدد من الرموز"
},
"vision": {
"extra": "ستفتح هذه الإعدادات فقط القدرة على تحميل الصور داخل التطبيق، وما إذا كانت القدرة على التعرف مدعومة يعتمد تمامًا على النموذج نفسه، يرجى اختبار قابلية استخدام التعرف البصري لهذا النموذج بنفسك",
@@ -98,6 +97,7 @@
"title": "استخدام طريقة طلب العميل"
},
"fetcher": {
+ "clear": "مسح النموذج المستخرج",
"fetch": "احصل على قائمة النماذج",
"fetching": "جاري الحصول على قائمة النماذج...",
"latestTime": "آخر تحديث: {{time}}",
@@ -175,8 +175,8 @@
"desc": "هل يجب إنشاء موضوع تلقائيًا أثناء الدردشة، يسري ذلك فقط في المواضيع المؤقتة",
"title": "تمكين إنشاء الموضوع تلقائيًا"
},
- "enableCompressThreshold": {
- "title": "هل تريد تمكين عتبة ضغط طول الرسائل التاريخية"
+ "enableCompressHistory": {
+ "title": "تفعيل تلخيص الرسائل التاريخية تلقائيًا"
},
"enableHistoryCount": {
"alias": "غير محدود",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "تمكين الحد الأقصى للردود"
},
+ "enableReasoningEffort": {
+ "title": "تفعيل ضبط قوة الاستدلال"
+ },
"frequencyPenalty": {
- "desc": "كلما زادت القيمة، زاد احتمال تقليل تكرار الكلمات",
- "title": "عقوبة التكرار"
+ "desc": "كلما زادت القيمة، كانت المفردات أكثر تنوعًا؛ وكلما انخفضت القيمة، كانت المفردات أكثر بساطة ووضوحًا",
+ "title": "تنوع المفردات"
},
"maxTokens": {
"desc": "عدد الرموز الأقصى المستخدمة في التفاعل الواحد",
@@ -212,19 +215,31 @@
"desc": "{{provider}} نموذج",
"title": "النموذج"
},
+ "params": {
+ "title": "إعدادات متقدمة"
+ },
"presencePenalty": {
- "desc": "كلما زادت القيمة، زاد احتمال التوسع في مواضيع جديدة",
- "title": "جديد الحديث"
+ "desc": "كلما زادت القيمة، زادت الميل إلى استخدام تعبيرات مختلفة، مما يتجنب تكرار المفاهيم؛ وكلما انخفضت القيمة، زادت الميل إلى استخدام المفاهيم أو السرد المتكرر، مما يجعل التعبير أكثر اتساقًا",
+ "title": "تنوع التعبير"
+ },
+ "reasoningEffort": {
+ "desc": "كلما زادت القيمة، زادت قدرة الاستدلال، ولكن قد يؤدي ذلك إلى زيادة وقت الاستجابة واستهلاك التوكنات",
+ "options": {
+ "high": "عالي",
+ "low": "منخفض",
+ "medium": "متوسط"
+ },
+ "title": "قوة الاستدلال"
},
"temperature": {
- "desc": "كلما زادت القيمة، زادت الردود عشوائية أكثر",
- "title": "التباين",
- "titleWithValue": "التباين {{value}}"
+ "desc": "كلما زادت القيمة، كانت الإجابات أكثر إبداعًا وخيالًا؛ وكلما انخفضت القيمة، كانت الإجابات أكثر دقة",
+ "title": "مستوى الإبداع",
+ "warning": "إذا كانت قيمة مستوى الإبداع مرتفعة جدًا، قد تحتوي المخرجات على تشويش"
},
"title": "إعدادات النموذج",
"topP": {
- "desc": "مشابه للتباين ولكن لا يجب تغييره مع التباين",
- "title": "العينة الأساسية"
+ "desc": "عدد الاحتمالات التي يتم أخذها في الاعتبار، كلما زادت القيمة، زادت احتمالية قبول إجابات متعددة؛ وكلما انخفضت القيمة، زادت الميل لاختيار الإجابة الأكثر احتمالًا. لا يُنصح بتغييرها مع مستوى الإبداع",
+ "title": "مستوى الانفتاح الفكري"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "يحدد النموذج المستخدم لإنشاء اسم المساعد ووصفه وصورته وعلامته",
"title": "توليد معلومات المساعد تلقائيًا"
},
+ "customPrompt": {
+ "addPrompt": "إضافة موجه مخصص",
+ "desc": "بعد ملئه، سيستخدم المساعد النظامي الموجه المخصص عند إنشاء المحتوى",
+ "placeholder": "أدخل كلمة الموجه المخصصة",
+ "title": "كلمة الموجه المخصصة"
+ },
+ "historyCompress": {
+ "label": "نموذج تاريخ المحادثة",
+ "modelDesc": "حدد النموذج المستخدم لضغط تاريخ المحادثة",
+ "title": "تلخيص تلقائي لتاريخ المحادثة"
+ },
"queryRewrite": {
"label": "نموذج إعادة صياغة الأسئلة",
"modelDesc": "نموذج مخصص لتحسين أسئلة المستخدمين",
- "title": "قاعدة المعرفة"
+ "title": "إعادة صياغة سؤال قاعدة المعرفة"
+ },
+ "thread": {
+ "label": "نموذج تسمية الموضوعات الفرعية",
+ "modelDesc": "نموذج مخصص لإعادة تسمية الموضوعات الفرعية تلقائيًا",
+ "title": "تسمية الموضوعات الفرعية تلقائيًا"
},
"title": "مساعد النظام",
"topic": {
@@ -395,6 +426,7 @@
"common": "إعدادات عامة",
"experiment": "تجربة",
"llm": "نموذج اللغة",
+ "provider": "مزود خدمة الذكاء الاصطناعي",
"sync": "مزامنة السحابة",
"system-agent": "مساعد النظام",
"tts": "خدمة الكلام"
diff --git a/DigitalHumanWeb/locales/ar/thread.json b/DigitalHumanWeb/locales/ar/thread.json
new file mode 100644
index 0000000..b5bf221
--- /dev/null
+++ b/DigitalHumanWeb/locales/ar/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "سيتم حذف هذا الموضوع الفرعي، ولن يمكن استعادته بعد الحذف، يرجى توخي الحذر."
+ },
+ "newPortalThread": {
+ "includeContext": "تضمين سياق الموضوع",
+ "title": "فتح موضوع فرعي جديد"
+ },
+ "notSupportMultiModals": "الموضوعات الفرعية لا تدعم حاليًا تحميل الملفات/الصور، إذا كان لديك أي طلب، لا تتردد في ترك رسالة: <1>💬 قسم النقاش1>"
+}
diff --git a/DigitalHumanWeb/locales/ar/tool.json b/DigitalHumanWeb/locales/ar/tool.json
index 6876ab6..5d90399 100644
--- a/DigitalHumanWeb/locales/ar/tool.json
+++ b/DigitalHumanWeb/locales/ar/tool.json
@@ -6,5 +6,23 @@
"generating": "جارٍ التوليد...",
"images": "الصور:",
"prompt": "كلمة تلميح"
+ },
+ "search": {
+ "createNewSearch": "إنشاء سجل بحث جديد",
+ "emptyResult": "لم يتم العثور على نتائج، يرجى تعديل الكلمات الرئيسية والمحاولة مرة أخرى",
+ "genAiMessage": "إنشاء رسالة مساعد",
+ "includedTooltip": "ستدخل نتائج البحث الحالية في سياق المحادثة",
+ "keywords": "الكلمات الرئيسية:",
+ "scoreTooltip": "درجة الصلة، كلما كانت هذه الدرجة أعلى، كانت أكثر ارتباطًا بكلمات البحث",
+ "searchBar": {
+ "button": "بحث",
+ "placeholder": "الكلمات الرئيسية",
+ "tooltip": "سيتم إعادة الحصول على نتائج البحث، وإنشاء رسالة ملخص جديدة"
+ },
+ "searchEngine": "محرك البحث:",
+ "searchResult": "عدد النتائج:",
+ "summary": "ملخص",
+ "summaryTooltip": "تلخيص المحتوى الحالي",
+ "viewMoreResults": "عرض المزيد من {{results}} نتيجة"
}
}
diff --git a/DigitalHumanWeb/locales/ar/topic.json b/DigitalHumanWeb/locales/ar/topic.json
new file mode 100644
index 0000000..d532791
--- /dev/null
+++ b/DigitalHumanWeb/locales/ar/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "إعادة تسمية ذكية",
+ "confirmRemoveAll": "سيتم حذف جميع المواضيع، ولن يمكن استعادتها بعد الحذف، يرجى توخي الحذر.",
+ "confirmRemoveTopic": "سيتم حذف هذا الموضوع، ولن يمكن استعادته بعد الحذف، يرجى توخي الحذر.",
+ "confirmRemoveUnstarred": "سيتم حذف المواضيع غير المفضلة، ولن يمكن استعادتها بعد الحذف، يرجى توخي الحذر.",
+ "duplicate": "إنشاء نسخة",
+ "export": "تصدير الموضوع",
+ "removeAll": "حذف جميع المواضيع",
+ "removeUnstarred": "حذف المواضيع غير المفضلة"
+ },
+ "defaultTitle": "موضوع افتراضي",
+ "duplicateLoading": "يتم نسخ الموضوع...",
+ "duplicateSuccess": "تم نسخ الموضوع بنجاح",
+ "favorite": "مفضل",
+ "groupMode": {
+ "ascMessages": "ترتيب حسب إجمالي عدد الرسائل",
+ "byTime": "تجميع حسب الوقت",
+ "descMessages": "ترتيب عكسي حسب إجمالي عدد الرسائل",
+ "flat": "بدون تجميع"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "هذا الشهر",
+ "today": "اليوم",
+ "week": "هذا الأسبوع",
+ "yesterday": "أمس"
+ }
+ },
+ "guide": {
+ "desc": "انقر على زر الإرسال على اليسار لحفظ المحادثة الحالية كموضوع تاريخي وبدء جولة جديدة من المحادثة",
+ "title": "قائمة المواضيع"
+ },
+ "searchPlaceholder": "ابحث عن موضوع...",
+ "searchResultEmpty": "لا توجد نتائج للبحث",
+ "temp": "مؤقت",
+ "title": "موضوع"
+}
diff --git a/DigitalHumanWeb/locales/ar/welcome.json b/DigitalHumanWeb/locales/ar/welcome.json
index 8a88801..e41fe82 100644
--- a/DigitalHumanWeb/locales/ar/welcome.json
+++ b/DigitalHumanWeb/locales/ar/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "استيراد التكوين",
- "market": "تسوق في السوق",
- "start": "ابدأ الآن"
- },
"guide": {
"agents": {
"replaceBtn": "تغيير",
diff --git a/DigitalHumanWeb/locales/bg-BG/auth.json b/DigitalHumanWeb/locales/bg-BG/auth.json
index 1d88bf0..e93377e 100644
--- a/DigitalHumanWeb/locales/bg-BG/auth.json
+++ b/DigitalHumanWeb/locales/bg-BG/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Миналия месец",
+ "recent30Days": "Последните 30 дни"
+ },
+ "header": {
+ "desc": "Управлявайте информацията за вашия акаунт.",
+ "title": "Акаунт"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Неактивен",
+ "more": "Активен"
+ },
+ "months": {
+ "apr": "Апр",
+ "aug": "Авг",
+ "dec": "Дек",
+ "feb": "Фев",
+ "jan": "Ян",
+ "jul": "Юл",
+ "jun": "Юн",
+ "mar": "Мар",
+ "may": "Май",
+ "nov": "Ное",
+ "oct": "Окт",
+ "sep": "Сеп"
+ },
+ "tooltip": "{{date}} изпратил(а) {{count}} съобщения този ден",
+ "totalCount": "Общо {{count}} съобщения изпратени през последната година"
+ },
"login": "Вход",
"loginOrSignup": "Вход / Регистрация",
- "profile": "Профил",
- "security": "Сигурност",
+ "profile": {
+ "avatar": "Аватар",
+ "email": "Имейл адрес",
+ "sso": {
+ "loading": "Зареждане на свързаните трети страни акаунти",
+ "providers": "Свързани акаунти",
+ "unlink": {
+ "description": "След като свържете, няма да можете да използвате акаунта на {{provider}} „{{providerAccountId}}“ за вход. Ако искате отново да свържете акаунта на {{provider}} с текущия акаунт, уверете се, че имейл адресът на акаунта на {{provider}} е {{email}}, а ние автоматично ще ви свържем с текущия влезлия акаунт при вход.",
+ "forbidden": "Трябва да имате поне един свързан акаунт на трета страна.",
+ "title": "Наистина ли искате да свържете акаунта на трета страна {{provider}}?"
+ }
+ },
+ "username": "Потребителско име"
+ },
"signout": "Изход",
- "signup": "Регистрация"
+ "signup": "Регистрация",
+ "stats": {
+ "aiheatmaps": "Индекс на активност",
+ "assistants": "Асистенти",
+ "assistantsRank": {
+ "left": "Асистент",
+ "right": "Тематики",
+ "title": "Ранг на използване на асистенти"
+ },
+ "createdAt": "Регистриран на",
+ "days": "дни",
+ "empty": {
+ "desc": "Моля, натрупайте повече данни от чат, за да видите",
+ "title": "Няма данни"
+ },
+ "lastYearActivity": "активност през последната година",
+ "loginGuide": {
+ "f1": "Получете безплатен лимит",
+ "f2": "Синхронизирайте съобщения на множество устройства",
+ "f3": "Разполагайте с богат асистент",
+ "f4": "Изследвайте мощни приставки",
+ "title": "След влизане можете да:"
+ },
+ "messages": "Съобщения",
+ "modelsRank": {
+ "left": "Модел",
+ "right": "Съобщения",
+ "title": "Ранг на използване на модели"
+ },
+ "share": {
+ "title": "Моят индекс на активност с ИИ"
+ },
+ "topics": "Тематики",
+ "topicsRank": {
+ "left": "Тематика",
+ "right": "Съобщения",
+ "title": "Ранг на съдържание на тематики"
+ },
+ "updatedAt": "Актуализиран на",
+ "welcome": "{{username}}, това е вашият {{days}} ден с {{appName}}",
+ "words": "Думи"
+ },
+ "tab": {
+ "profile": "Профил",
+ "security": "Сигурност",
+ "stats": "Статистика"
+ }
}
diff --git a/DigitalHumanWeb/locales/bg-BG/changelog.json b/DigitalHumanWeb/locales/bg-BG/changelog.json
new file mode 100644
index 0000000..08d26f7
--- /dev/null
+++ b/DigitalHumanWeb/locales/bg-BG/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Последвайте ни в X",
+ "subscribeToUpdates": "Абонирайте се за актуализации",
+ "versions": "Детайли за версиите"
+ },
+ "addedWhileAway": "Докато ви нямаше, добавихме нови функции.",
+ "allChangelog": "Вижте всички актуализации",
+ "description": "Следете новите функции и подобрения на {{appName}}",
+ "pagination": {
+ "next": "Следваща страница",
+ "older": "Преглед на историческите промени"
+ },
+ "readDetails": "Прочетете подробности",
+ "title": "Актуализации",
+ "versionDetails": "Детайли за версиите",
+ "welcomeBack": "Добре дошли обратно!"
+}
diff --git a/DigitalHumanWeb/locales/bg-BG/chat.json b/DigitalHumanWeb/locales/bg-BG/chat.json
index e07eb82..cacf441 100644
--- a/DigitalHumanWeb/locales/bg-BG/chat.json
+++ b/DigitalHumanWeb/locales/bg-BG/chat.json
@@ -8,6 +8,7 @@
"agents": "Асистент",
"artifact": {
"generating": "Генериране",
+ "inThread": "Не можете да видите в подтемата, моля, превключете към основната дискусия.",
"thinking": "В процес на мислене",
"thought": "Процес на мислене",
"unknownTitle": "Неназован артефакт"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Копие",
"emptyAgent": "Няма наличен асистент",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Разходите за генериране на единичен разговор могат да бъдат намалени с до 90%, а скоростта на отговорите да се увеличи 4 пъти (<1>Научете повече1>). При активиране автоматично ще се деактивира ограничението на броя на историческите съобщения",
+ "title": "Активиране на кеширане на контекста"
+ },
+ "enableReasoning": {
+ "desc": "Ограничения на механизма Claude Thinking (<1>Научете повече1>), при активиране автоматично ще се деактивира ограничението на броя на историческите съобщения",
+ "title": "Активиране на дълбочинно мислене"
+ },
+ "reasoningBudgetToken": {
+ "title": "Токени за разходи при мислене"
+ },
+ "title": "Разширени функции на модела"
+ },
+ "history": {
+ "title": "Асистентът ще запомни само последните {{count}} съобщения"
+ },
"historyRange": "Диапазон на историята",
+ "historySummary": "Исторически обобщение на съобщения",
"inbox": {
"desc": "Активирай мозъчния клъстер и събуди креативното мислене. Твоят виртуален агент е тук, за да общува с теб за всичко.",
"title": "Просто чати"
@@ -45,6 +64,9 @@
"stop": "Спри",
"warp": "Нов ред"
},
+ "intentUnderstanding": {
+ "title": "Разбирам и анализирам вашето намерение..."
+ },
"knowledgeBase": {
"all": "Всички съдържания",
"allFiles": "Всички файлове",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Изтрий и прегенерирай",
+ "deleteDisabledByThreads": "Съществуват подтеми, не можете да изтриете.",
"regenerate": "Прегенерирай"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Кредити",
+ "creditPricing": "Ценообразуване",
+ "creditTooltip": "За удобство при броенето, 1$ се преобразува в 1M кредити, например $3/M токени се преобразува в 3 кредита/token",
+ "pricing": {
+ "inputCachedTokens": "Кеширани входящи {{amount}}/кредити · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M символи",
+ "inputMinutes": "${{amount}}/минута",
+ "inputTokens": "Входящи {{amount}}/кредити · ${{amount}}/M",
+ "outputTokens": "Изходящи {{amount}}/кредити · ${{amount}}/M",
+ "writeCacheInputTokens": "Кеширане на входящи данни {{amount}}/точки · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Средна цена",
+ "input": "Вход",
+ "inputAudio": "Аудио вход",
+ "inputCached": "Кеширан вход",
+ "inputCitation": "Цитиране на входящи данни",
+ "inputText": "Текстов вход",
+ "inputTitle": "Детайли за входа",
+ "inputUncached": "Некеширан вход",
+ "inputWriteCached": "Входящи кеширани данни",
+ "output": "Изход",
+ "outputAudio": "Аудио изход",
+ "outputText": "Текстов изход",
+ "outputTitle": "Детайли за изхода",
+ "reasoning": "Дълбочинно разсъждение",
+ "title": "Детайли за генериране",
+ "total": "Общо разходи"
+ }
+ },
"newAgent": "Нов агент",
"pin": "Закачи",
"pinOff": "Откачи",
@@ -81,6 +137,32 @@
},
"regenerate": "Прегенерирай",
"roleAndArchive": "Роля и архив",
+ "search": {
+ "grounding": {
+ "searchQueries": "Търсене на ключови думи",
+ "title": "Намерени са {{count}} резултата"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Интелигентно определяне на необходимостта от търсене въз основа на съдържанието на разговора",
+ "title": "Интелигентно свързване"
+ },
+ "off": {
+ "desc": "Използва само основните знания на модела, без интернет търсене",
+ "title": "Изключване на свързването"
+ },
+ "on": {
+ "desc": "Постоянно извършва интернет търсене за получаване на най-новата информация",
+ "title": "Винаги свързано"
+ },
+ "useModelBuiltin": "Използване на вградената търсачка на модела"
+ },
+ "searchModel": {
+ "desc": "Текущият модел не поддържа извикване на функции, затова е необходимо да се комбинира с модел, който поддържа извикване на функции, за да се извърши търсене в интернет",
+ "title": "Модел за търсене на помощ"
+ },
+ "title": "Търсене в интернет"
+ },
"searchAgentPlaceholder": "Търсач на помощ...",
"sendPlaceholder": "Напиши съобщението си тук...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Дължината на името на групата трябва да бъде между 1-20 символа"
},
"shareModal": {
+ "copy": "Копирай",
"download": "Изтегли екранна снимка",
+ "downloadFile": "Изтегли файла",
+ "exportTitle": "По подразбиране заглавие",
"imageType": "Формат на изображението",
+ "includeTool": "Включи съобщения от инструмента",
+ "includeUser": "Включи съобщения от потребителя",
"screenshot": "Екранна снимка",
"settings": "Настройки за експортиране",
- "shareToShareGPT": "Генерирай ShareGPT линк за споделяне",
+ "text": "Текст",
"withBackground": "Включи фоново изображение",
"withFooter": "Включи долен колонтитул",
"withPluginInfo": "Включи информация за плъгина",
+ "withRole": "Включи роля на съобщението",
"withSystemRole": "Включи настройката за роля на агента"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Разпознаване...",
"prettifying": "Изглаждане..."
},
- "temp": "Временен",
+ "thread": {
+ "divider": "Подтема",
+ "threadMessageCount": "{{messageCount}} съобщения",
+ "title": "Подтема"
+ },
"tokenDetails": {
"chats": "Чат съобщения",
+ "historySummary": "Историческо резюме",
"rest": "Оставащи",
"systemRole": "Настройки на ролята",
"title": "Детайли на токена",
@@ -131,29 +224,10 @@
"used": "Използвани"
},
"topic": {
- "actions": {
- "autoRename": "Автоматично преименуване",
- "duplicate": "Създай копие",
- "export": "Експортирай тема"
- },
"checkOpenNewTopic": "Да се отвори ли нова тема?",
"checkSaveCurrentMessages": "Искате ли да запазите текущата сесия като тема?",
- "confirmRemoveAll": "На път си да изтриеш всички теми. След като бъдат изтрити, те не могат да бъдат възстановени. Моля, продължи с повишено внимание.",
- "confirmRemoveTopic": "На път си да изтриеш тази тема. След като бъде изтрита, тя не може да бъде възстановена. Моля, продължи с повишено внимание.",
- "confirmRemoveUnstarred": "На път си да изтриеш немаркираните теми. След като бъдат изтрити, те не могат да бъдат възстановени. Моля, продължи с повишено внимание.",
- "defaultTitle": "Тема по подразбиране",
- "duplicateLoading": "Копиране на темата...",
- "duplicateSuccess": "Темата е успешно копирана",
- "guide": {
- "desc": "Кликни върху бутона вляво, за да запазиш текущата сесия като историческа тема и да започнеш нова сесия.",
- "title": "Списък с теми"
- },
"openNewTopic": "Отвори нова тема",
- "removeAll": "Премахни всички теми",
- "removeUnstarred": "Премахни немаркираните теми",
- "saveCurrentMessages": "Запази текущата сесия като тема",
- "searchPlaceholder": "Търсене на теми...",
- "title": "Списък с теми"
+ "saveCurrentMessages": "Запази текущата сесия като тема"
},
"translate": {
"action": "Превод",
@@ -184,5 +258,6 @@
"processing": "Обработка на файла..."
}
}
- }
+ },
+ "zenMode": "Режим на фокус"
}
diff --git a/DigitalHumanWeb/locales/bg-BG/common.json b/DigitalHumanWeb/locales/bg-BG/common.json
index c56c072..0d6cddc 100644
--- a/DigitalHumanWeb/locales/bg-BG/common.json
+++ b/DigitalHumanWeb/locales/bg-BG/common.json
@@ -9,15 +9,79 @@
"title": "Добре дошли в {{name}}"
}
},
- "appInitializing": "Приложението се стартира...",
+ "appLoading": {
+ "appIdle": "Подготовка за стартиране",
+ "appInitializing": "Приложението се стартира...",
+ "failed": "Съжаляваме, приложението не успя да се инициализира. Моля, прегледайте детайлите за отстраняване на проблема.",
+ "finished": "Инициализацията на базата данни е завършена",
+ "goToChat": "Зареждане на страницата за разговори...",
+ "initAuth": "Инициализиране на услугата за удостоверяване...",
+ "initUser": "Инициализиране на състоянието на потребителя...",
+ "initializing": "Инициализиране на PGlite базата данни...",
+ "loadingDependencies": "Инициализиране на зависимостите...",
+ "loadingWasm": "Зареждане на WASM модула...",
+ "migrating": "Извършване на миграция на таблиците...",
+ "ready": "Базата данни е готова",
+ "showDetail": "Покажи подробности"
+ },
"autoGenerate": "Автоматично генериране",
"autoGenerateTooltip": "Автоматично генериране на описание на агент въз основа на подкани",
"autoGenerateTooltipDisabled": "Моля, попълнете подсказката, за да използвате функцията за автоматично допълване",
"back": "Назад",
"batchDelete": "Пакетно изтриване",
"blog": "Продуктов блог",
+ "branching": "Създаване на подтема",
+ "branchingDisable": "Функцията „подтема“ е налична само в сървърната версия. Ако искате да използвате тази функция, моля, превключете на режим на сървърно разполагане или използвайте LobeChat Cloud.",
"cancel": "Отказ",
"changelog": "Дневник на промените",
+ "clientDB": {
+ "autoInit": {
+ "title": "Инициализиране на PGlite базата данни"
+ },
+ "error": {
+ "desc": "Извинявайте, но възникна проблем по време на инициализацията на Pglite базата данни. Моля, натиснете бутона, за да опиташ отново. Ако проблемът продължава след многократни опити, моля <1>подайте проблем1>, и ние ще ви помогнем възможно най-скоро.",
+ "detail": "Причина за грешка: [{{type}}] {{message}}. Подробности по-долу:",
+ "retry": "Опитай отново",
+ "title": "Неуспешна инициализация на базата данни"
+ },
+ "initing": {
+ "error": "Възникна грешка, моля опитайте отново",
+ "idle": "Изчакване на инициализация...",
+ "initializing": "Инициализиране...",
+ "loadingDependencies": "Зареждане на зависимости...",
+ "loadingWasmModule": "Зареждане на WASM модула...",
+ "migrating": "Извършване на миграция на данни...",
+ "ready": "Базата данни е готова"
+ },
+ "modal": {
+ "desc": "Активирайте PGlite клиентската база данни, за да съхранявате данни за чата в браузъра си и да използвате разширени функции като база знания.",
+ "enable": "Активирайте сега",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Създайте своя лична база знания и лесно започнете разговори с вашия асистент (скоро налично)",
+ "title": "Поддръжка на разговори в базата знания, активирайте втория си мозък"
+ },
+ "localFirst": {
+ "desc": "Данните от чата се съхраняват изцяло в браузъра, вашите данни винаги са под ваш контрол.",
+ "title": "Локален приоритет, конфиденциалността е на първо място"
+ },
+ "pglite": {
+ "desc": "Изграден на базата на PGlite, нативна поддръжка на AI Native висши функции (векторно търсене)",
+ "title": "Новото поколение архитектура за съхранение на клиенти"
+ }
+ },
+ "init": {
+ "desc": "Инициализиране на базата данни, времето за което може да варира от 5 до 30 секунди в зависимост от мрежата.",
+ "title": "Инициализиране на PGlite базата данни"
+ },
+ "title": "Активиране на клиентската база данни"
+ },
+ "ready": {
+ "button": "Използвайте сега",
+ "desc": "Искам да използвам веднага",
+ "title": "PGlite базата данни е готова"
+ }
+ },
"close": "Затвори",
"contact": "Свържете се с нас",
"copy": "Копирай",
@@ -112,6 +176,7 @@
"en": "Английски",
"en-US": "Английски",
"es-ES": "Испански",
+ "fa-IR": "персийски",
"fi-FI": "Финландски",
"fr-FR": "Френски",
"hi-IN": "Хинди",
@@ -153,6 +218,7 @@
"pinOff": "Откачи",
"privacy": "Политика за поверителност",
"regenerate": "Прегенерирай",
+ "releaseNotes": "Информация за версията",
"rename": "Преименувай",
"reset": "Нулирай",
"retry": "Опитай отново",
@@ -209,6 +275,7 @@
},
"temp": "Временен",
"terms": "Условия за ползване",
+ "update": "Актуализиране",
"updateAgent": "Актуализирай информацията за агента",
"upgradeVersion": {
"action": "Надстрой",
@@ -219,6 +286,7 @@
"anonymousNickName": "Анонимен потребител",
"billing": "Управление на сметките",
"cloud": "Изпробвайте {{name}}",
+ "community": "Общностна версия",
"data": "Съхранение на данни",
"defaultNickname": "Потребител на общността",
"discord": "Поддръжка на общността",
@@ -228,7 +296,6 @@
"help": "Център за помощ",
"moveGuide": "Бутонът за настройки е преместен тук",
"plans": "Планове за абонамент",
- "preview": "Преглед",
"profile": "Управление на профила",
"setting": "Настройки на приложението",
"usages": "Статистика за използване"
diff --git a/DigitalHumanWeb/locales/bg-BG/components.json b/DigitalHumanWeb/locales/bg-BG/components.json
index 37ba01e..4452894 100644
--- a/DigitalHumanWeb/locales/bg-BG/components.json
+++ b/DigitalHumanWeb/locales/bg-BG/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Партидно разделяне",
"chunking": "Разделяне",
"chunkingTooltip": "Разделете файла на множество текстови блокове и ги векторизирайте, за да се използват за семантично търсене и диалог с файла",
+ "chunkingUnsupported": "Този файл не поддържа разделяне на части.",
"confirmDelete": "Ще изтриете този файл. След изтриването му няма да може да бъде възстановен. Моля, потвърдете действието си.",
"confirmDeleteMultiFiles": "Ще изтриете избраните {{count}} файла. След изтриването им няма да могат да бъдат възстановени. Моля, потвърдете действието си.",
"confirmRemoveFromKnowledgeBase": "Ще премахнете избраните {{count}} файла от базата знания. След премахването им файловете все още могат да бъдат видяни в списъка с всички файлове. Моля, потвърдете действието си.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Назад"
},
+ "MaxTokenSlider": {
+ "unlimited": "Неограничено"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Потребителски модел, по подразбиране поддържа функционалност за функционални обаждания и визуално разпознаване, моля, потвърдете наличието на тези възможности спрямо реалните условия",
"file": "Този модел поддържа качване на файлове и разпознаване",
"functionCall": "Този модел поддържа функционални обаждания (Function Call)",
+ "reasoning": "Този модел поддържа дълбочинно мислене",
+ "search": "Този модел поддържа търсене в мрежата",
"tokens": "Този модел поддържа до {{tokens}} токена за една сесия",
"vision": "Този модел поддържа визуално разпознаване"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Няма активирани модели, моля, посетете настройките и ги активирайте",
+ "emptyProvider": "Няма активиран доставчик на услуги, моля, отидете в настройките, за да го активирате",
+ "goToSettings": "Отидете в настройките",
"provider": "Доставчик"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Поради ограниченията на сигурността на браузъра, трябва да конфигурирате крос-домейн достъп за Ollama, за да можете да го използвате нормално.",
+ "linux": {
+ "env": "Добавете `Environment` в секцията [Service] и добавете променливата на средата OLLAMA_ORIGINS:",
+ "reboot": "Презаредете systemd и рестартирайте Ollama",
+ "systemd": "Извикайте systemd, за да редактирате услугата ollama:"
+ },
+ "macos": "Моля, отворете приложението „Терминал“ и поставете следната команда, след което натиснете Enter, за да я изпълните",
+ "reboot": "Моля, рестартирайте услугата Ollama след завършване на изпълнението",
+ "title": "Конфигуриране на Ollama за разрешаване на крос-домейн достъп",
+ "windows": "На Windows, кликнете върху „Контролен панел“, за да редактирате системните променливи на средата. Създайте нова променлива на средата с име „OLLAMA_ORIGINS“ за вашия потребителски акаунт, със стойност * и кликнете „OK/Приложи“, за да запазите"
+ },
+ "install": {
+ "description": "Моля, уверете се, че сте стартирали Ollama. Ако не сте изтеглили Ollama, моля, посетете официалния сайт <1>за изтегляне1>",
+ "docker": "Ако предпочитате да използвате Docker, Ollama предлага и официален Docker образ, който можете да изтеглите с следната команда:",
+ "linux": {
+ "command": "Инсталирайте с следната команда:",
+ "manual": "Или можете да се запознаете с <1>Ръководството за ръчна инсталация на Linux1> и да инсталирате сами"
+ },
+ "title": "Инсталиране и стартиране на приложението Ollama локално",
+ "windowsTab": "Windows (предварителна версия)"
+ }
+ },
+ "Thinking": {
+ "thinking": "В процес на дълбочинно размисъл...",
+ "thought": "Дълбоко размислих (отне ми {{duration}} секунди)",
+ "thoughtWithDuration": "Дълбоко размислих"
}
}
diff --git a/DigitalHumanWeb/locales/bg-BG/discover.json b/DigitalHumanWeb/locales/bg-BG/discover.json
index b3e924c..a3cdd77 100644
--- a/DigitalHumanWeb/locales/bg-BG/discover.json
+++ b/DigitalHumanWeb/locales/bg-BG/discover.json
@@ -126,6 +126,10 @@
"title": "Свежест на темата"
},
"range": "Обхват",
+ "reasoning_effort": {
+ "desc": "Тази настройка контролира интензивността на разсъжденията на модела преди генерирането на отговор. Ниска интензивност приоритизира скоростта на отговор и спестява токени, докато висока интензивност предоставя по-пълни разсъждения, но изразходва повече токени и намалява скоростта на отговор. Стойността по подразбиране е средна, което балансира точността на разсъжденията и скоростта на отговор.",
+ "title": "Интензивност на разсъжденията"
+ },
"temperature": {
"desc": "Тази настройка влияе на разнообразието на отговорите на модела. По-ниски стойности водят до по-предсказуеми и типични отговори, докато по-високи стойности насърчават по-разнообразни и необичайни отговори. Когато стойността е 0, моделът винаги дава един и същ отговор на даден вход.",
"title": "Случайност"
diff --git a/DigitalHumanWeb/locales/bg-BG/error.json b/DigitalHumanWeb/locales/bg-BG/error.json
index 252b539..1df5ec8 100644
--- a/DigitalHumanWeb/locales/bg-BG/error.json
+++ b/DigitalHumanWeb/locales/bg-BG/error.json
@@ -12,8 +12,14 @@
"retry": "Опитай отново",
"title": "Страницата се е сблъскала с проблем.."
},
- "fetchError": "Грешка при извличане",
- "fetchErrorDetail": "Подробности за грешката",
+ "fetchError": {
+ "detail": "Детайли за грешката",
+ "title": "Заявката не успя"
+ },
+ "loginRequired": {
+ "desc": "Ще бъдете автоматично пренасочени към страницата за вход",
+ "title": "Моля, влезте, за да използвате тази функция"
+ },
"notFound": {
"backHome": "Върни се в началото",
"check": "Моля, проверете дали URL адресът е правилен",
@@ -51,22 +57,34 @@
"431": "Съжаляваме, полетата на заглавието на вашата заявка са твърде големи, за да бъдат обработени от сървъра",
"451": "Съжаляваме, сървърът отказва да предостави този ресурс поради правни причини",
"500": "Съжаляваме, изглежда сървърът има някои затруднения и временно не може да изпълни заявката ви. Моля, опитайте отново по-късно.",
+ "501": "Съжаляваме, сървърът все още не знае как да обработи тази заявка, моля, уверете се, че вашата операция е правилна",
"502": "Съжаляваме, изглежда сървърът е изгубен и временно не може да предостави услуга. Моля, опитайте отново по-късно.",
"503": "Съжаляваме, сървърът в момента не може да обработи заявката ви, вероятно поради претоварване или поддръжка. Моля, опитайте отново по-късно.",
"504": "Съжаляваме, сървърът не получи отговор от сървъра нагоре по веригата. Моля, опитайте отново по-късно.",
+ "505": "Съжаляваме, сървърът не поддържа версията на HTTP, която използвате, моля, актуализирайте и опитайте отново",
+ "506": "Съжаляваме, сървърната конфигурация има проблем, моля, свържете се с администратора за разрешаване",
+ "507": "Съжаляваме, сървърът няма достатъчно пространство за съхранение, за да обработи вашата заявка, моля, опитайте отново по-късно",
+ "509": "Съжаляваме, сървърът е изчерпал наличната честотна лента, моля, опитайте отново по-късно",
+ "510": "Съжаляваме, сървърът не поддържа исканата разширена функция, моля, свържете се с администратора",
+ "524": "Съжаляваме, сървърът изтече времето за изчакване при очакване на отговор, вероятно поради бавен отговор, моля, опитайте отново по-късно",
"AgentRuntimeError": "Грешка при изпълнение на времето за изпълнение на езиковия модел Lobe. Моля, отстранете неизправностите или опитайте отново въз основа на следната информация.",
+ "ConnectionCheckFailed": "Заявката върна празен отговор. Моля, проверете дали адресът на API проксито не завършва с `/v1`.",
+ "ExceededContextWindow": "Текущото съдържание на заявката надвишава дължината, която моделът може да обработи. Моля, намалете обема на съдържанието и опитайте отново.",
"FreePlanLimit": "В момента сте потребител на безплатен план и не можете да използвате тази функционалност. Моля, надстройте до платен план, за да продължите да я използвате.",
+ "InsufficientQuota": "Съжаляваме, квотата за този ключ е достигнала лимита. Моля, проверете баланса на акаунта си или увеличете квотата на ключа и опитайте отново.",
"InvalidAccessCode": "Невалиден или празен код за достъп. Моля, въведете правилния код за достъп или добавете персонализиран API ключ.",
"InvalidBedrockCredentials": "Удостоверяването на Bedrock е неуспешно. Моля, проверете AccessKeyId/SecretAccessKey и опитайте отново.",
"InvalidClerkUser": "很抱歉,你当前尚未登录,请先登录或注册账号后继续操作",
"InvalidGithubToken": "GitHub Личният Достъпен Токен е неправилен или е празен. Моля, проверете Личния Достъпен Токен на GitHub и опитайте отново.",
"InvalidOllamaArgs": "Невалидна конфигурация на Ollama, моля, проверете конфигурацията на Ollama и опитайте отново",
"InvalidProviderAPIKey": "{{provider}} API ключ е невалиден или липсва, моля проверете {{provider}} API ключа и опитайте отново",
+ "InvalidVertexCredentials": "Аутентификация на Vertex не беше успешна, моля проверете удостоверението и опитайте отново",
"LocationNotSupportError": "Съжаляваме, вашето текущо местоположение не поддържа тази услуга на модела. Това може да се дължи на регионални ограничения или на недостъпност на услугата. Моля, потвърдете дали текущото местоположение поддържа използването на тази услуга или опитайте да използвате друго местоположение.",
+ "ModelNotFound": "Съжаляваме, не можем да намерим съответния модел, може да е невалиден или да нямате достъп до него. Моля, сменете API ключа или коригирайте правата за достъп и опитайте отново.",
"NoOpenAIAPIKey": "API ключът на OpenAI е празен, моля, добавете персонализиран API ключ на OpenAI",
"OllamaBizError": "Грешка при заявка към услугата Ollama, моля, отстранете неизправностите или опитайте отново въз основа на следната информация",
"OllamaServiceUnavailable": "Услугата Ollama не е налична. Моля, проверете дали Ollama работи правилно или дали е конфигуриран коректно за междудомейност.",
- "OpenAIBizError": "Грешка в услугата на OpenAI, моля проверете следната информация или опитайте отново",
+ "PermissionDenied": "Съжаляваме, нямате разрешение да достъпвате тази услуга. Моля, проверете дали вашият ключ има необходимите права за достъп.",
"PluginApiNotFound": "Съжаляваме, API не съществува в манифеста на плъгина. Моля, проверете дали методът на вашата заявка съвпада с API на манифеста на плъгина",
"PluginApiParamsError": "Съжаляваме, проверката на входния параметър за заявката на плъгина е неуспешна. Моля, проверете дали входните параметри съвпадат с описанието на API",
"PluginFailToTransformArguments": "Съжаляваме, неуспешно преобразуване на аргументите за извикване на плъгин. Моля, опитайте отново да генерирате съобщението на помощника или опитайте с по-мощна AI модел на Tools Calling.",
@@ -81,8 +99,11 @@
"PluginServerError": "Заявката към сървъра на плъгина върна грешка. Моля, проверете файла на манифеста на плъгина, конфигурацията на плъгина или изпълнението на сървъра въз основа на информацията за грешката по-долу",
"PluginSettingsInvalid": "Този плъгин трябва да бъде конфигуриран правилно, преди да може да се използва. Моля, проверете дали конфигурацията ви е правилна",
"ProviderBizError": "Грешка в услугата на {{provider}}, моля проверете следната информация или опитайте отново",
+ "QuotaLimitReached": "Съжаляваме, но текущото използване на токени или брой на заявките е достигнало лимита на квотата за този ключ. Моля, увеличете квотата на ключа или опитайте отново по-късно.",
"StreamChunkError": "Грешка при парсирането на съобщение от потокова заявка. Моля, проверете дали текущият API интерфейс отговаря на стандартите или се свържете с вашия доставчик на API за консултация.",
- "SubscriptionPlanLimit": "Изчерпали сте вашия абонаментен лимит и не можете да използвате тази функционалност. Моля, надстройте до по-висок план или закупете допълнителни ресурси, за да продължите да я използвате.",
+ "SubscriptionKeyMismatch": "Съжаляваме, но поради случайна системна грешка, текущото използване на абонамента временно е невалидно. Моля, кликнете върху бутона по-долу, за да възстановите абонамента, или се свържете с нас по имейл за поддръжка.",
+ "SubscriptionPlanLimit": "Вашият абонаментен план е изчерпан, не можете да използвате тази функция. Моля, надстройте до по-висок план или конфигурирайте персонализиран модел API, за да продължите да използвате.",
+ "SystemTimeNotMatchError": "Съжаляваме, вашето системно време не съвпада с времето на сървъра. Моля, проверете системното си време и опитайте отново.",
"UnknownChatFetchError": "Съжаляваме, възникна неизвестна грешка при заявката. Моля, проверете информацията по-долу или опитайте отново."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/bg-BG/metadata.json b/DigitalHumanWeb/locales/bg-BG/metadata.json
index 8c12d30..f8f312d 100644
--- a/DigitalHumanWeb/locales/bg-BG/metadata.json
+++ b/DigitalHumanWeb/locales/bg-BG/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Непрекъснато следене на новите функции и подобрения в {{appName}}",
+ "title": "Журнал на промените"
+ },
"chat": {
"description": "{{appName}} ви предлага най-доброто изживяване с ChatGPT, Claude, Gemini и OLLaMA WebUI",
"title": "{{appName}}: Личен AI инструмент за ефективност, дайте си по-умен мозък"
diff --git a/DigitalHumanWeb/locales/bg-BG/modelProvider.json b/DigitalHumanWeb/locales/bg-BG/modelProvider.json
index a3f7446..e20bb87 100644
--- a/DigitalHumanWeb/locales/bg-BG/modelProvider.json
+++ b/DigitalHumanWeb/locales/bg-BG/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API ключ"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Версия на API на Azure, следваща формата YYYY-MM-DD, вижте [най-новата версия](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Вземи списък",
+ "title": "Версия на API на Azure"
+ },
+ "endpoint": {
+ "desc": "Намерете крайна точка за инференция на моделите на Azure AI в прегледа на проекта на Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Крайна точка на Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Намерете API ключа в прегледа на проекта на Azure AI",
+ "placeholder": "Ключ на Azure",
+ "title": "Ключ"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Въведете AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "Използване на персонализирана информация за удостоверяване на Bedrock"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Моля, въведете Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Въведете ID на Cloudflare или личен API адрес",
+ "placeholder": "ID на Cloudflare / личен API адрес",
+ "title": "ID на Cloudflare / API адрес"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Моля, въведете вашия API ключ",
+ "title": "API ключ"
+ },
+ "basicTitle": "Основна информация",
+ "configTitle": "Конфигурационна информация",
+ "confirm": "Създаване",
+ "createSuccess": "Създаването е успешно",
+ "description": {
+ "placeholder": "Описание на доставчика (по избор)",
+ "title": "Описание на доставчика"
+ },
+ "id": {
+ "desc": "Уникален идентификатор за доставчика на услуги, който не може да бъде променян след създаването му",
+ "format": "Може да съдържа само цифри, малки букви, тирета (-) и долни черти (_) ",
+ "placeholder": "Препоръчително изцяло с малки букви, например openai, след създаването не може да се промени",
+ "required": "Моля, въведете ID на доставчика",
+ "title": "ID на доставчика"
+ },
+ "logo": {
+ "required": "Моля, качете правилното лого на доставчика",
+ "title": "Лого на доставчика"
+ },
+ "name": {
+ "placeholder": "Моля, въведете показваното име на доставчика",
+ "required": "Моля, въведете името на доставчика",
+ "title": "Име на доставчика"
+ },
+ "proxyUrl": {
+ "required": "Моля, въведете адреса на проксито",
+ "title": "Адрес на прокси"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Моля, изберете тип SDK",
+ "title": "Формат на запитването"
+ },
+ "title": "Създаване на персонализиран AI доставчик"
+ },
"github": {
"personalAccessToken": {
"desc": "Въведете вашия GitHub PAT, кликнете [тук](https://github.com/settings/tokens), за да създадете",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Въведете вашия HuggingFace токен, кликнете [тук](https://huggingface.co/settings/tokens), за да създадете",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace токен"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Неактивен доставчик",
+ "enabled": "Активен доставчик"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Добавяне на персонализиран доставчик",
+ "all": "Всички",
+ "list": {
+ "disabled": "Неактивиран",
+ "enabled": "Активиран"
+ },
+ "notFound": "Не са намерени резултати от търсенето",
+ "searchProviders": "Търсене на доставчици...",
+ "sort": "Персонализирано сортиране"
+ },
"ollama": {
"checker": {
"desc": "Тестване дали адресът на прокси е попълнен правилно",
@@ -69,47 +163,173 @@
"title": "Имена на персонализирани модели"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. It will resume from where it left off if you restart the download.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama изтегля този модел, моля, не затваряйте тази страница. При повторно изтегляне ще продължи от мястото, на което е прекъснато",
+ "remainingTime": "Оставащо време",
+ "speed": "Скорост на изтегляне",
+ "title": "Изтегляне на модел {{model}} "
},
"endpoint": {
- "desc": "Въведете адрес на Ollama интерфейсния прокси, оставете празно, ако локално не е указано специално",
+ "desc": "Трябва да съдържа http(s)://, местният адрес може да остане празен, ако не е зададен допълнително",
"title": "Адрес на прокси интерфейс"
},
- "setup": {
- "cors": {
- "description": "Заради ограниченията за сигурност в браузъра, трябва да конфигурирате кросдомейн за Ollama, за да работи правилно.",
- "linux": {
- "env": "Добавете `Environment` в раздела [Service], като добавите променливата на средата OLLAMA_ORIGINS:",
- "reboot": "Презаредете systemd и рестартирайте Ollama",
- "systemd": "Извикайте systemd за редактиране на услугата ollama:"
- },
- "macos": "Моля, отворете приложението „Терминал“ и поставете следната команда, след което натиснете Enter",
- "reboot": "Моля, рестартирайте услугата Ollama след приключване на изпълнението",
- "title": "Конфигуриране на Ollama за позволяване на кросдомейн достъп",
- "windows": "На Windows кликнете върху „Контролен панел“, влезте в редактиране на системните променливи. Създайте нова променлива на средата с име „OLLAMA_ORIGINS“, стойност * и кликнете „ОК/Приложи“, за да запазите промените"
- },
- "install": {
- "description": "Моля, потвърдете, че сте активирали Ollama. Ако не сте го изтеглили, моля посетете <1>официалния сайт1> на Ollama.",
- "docker": "Ако предпочитате да използвате Docker, Ollama предлага официален Docker образ, който можете да изтеглите с помощта на следната команда:",
- "linux": {
- "command": "Инсталирайте чрез следната команда:",
- "manual": "Или може да се обадите на <1>Ръководство за ръчна инсталация на Linux1> и да инсталирате ръчно"
- },
- "title": "Инсталиране и стартиране на приложението Ollama локално",
- "windowsTab": "Windows (преглед)"
- }
- },
"title": "Ollama",
"unlock": {
- "cancel": "Cancel Download",
- "confirm": "Download",
- "description": "Enter your Ollama model tag to continue the session",
+ "cancel": "Отмяна на изтеглянето",
+ "confirm": "Изтегляне",
+ "description": "Въведете етикета на вашия Ollama модел, за да продължите сесията",
"downloaded": "{{completed}} / {{total}}",
- "starting": "Starting download...",
- "title": "Download specified Ollama model"
+ "starting": "Започва изтеглянето...",
+ "title": "Изтегляне на зададения Ollama модел"
+ }
+ },
+ "providerModels": {
+ "config": {
+ "aesGcm": "Вашият ключ и адреса на прокси ще бъдат криптирани с <1>AES-GCM1> алгоритъм",
+ "apiKey": {
+ "desc": "Моля, въведете вашия {{name}} API ключ",
+ "placeholder": "{{name}} API ключ",
+ "title": "API ключ"
+ },
+ "baseURL": {
+ "desc": "Трябва да съдържа http(s)://",
+ "invalid": "Моля, въведете валиден URL",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API адрес на прокси"
+ },
+ "checker": {
+ "button": "Проверка",
+ "desc": "Тест на API ключа и адреса на прокси за правилно попълване",
+ "pass": "Проверката е успешна",
+ "title": "Проверка на свързаност"
+ },
+ "fetchOnClient": {
+ "desc": "Режимът на клиентски запитвания ще инициира сесийни запитвания директно от браузъра, което може да ускори времето за отговор",
+ "title": "Използване на клиентски режим на запитвания"
+ },
+ "helpDoc": "Ръководство за конфигуриране",
+ "waitingForMore": "Още модели са в <1>планиране1>, моля, очаквайте"
+ },
+ "createNew": {
+ "title": "Създаване на персонализиран AI модел"
+ },
+ "item": {
+ "config": "Конфигуриране на модела",
+ "customModelCards": {
+ "addNew": "Създаване и добавяне на модел {{id}}",
+ "confirmDelete": "Ще изтриете този персонализиран модел, след изтриването няма да може да бъде възстановен, моля, действайте внимателно."
+ },
+ "delete": {
+ "confirm": "Потвърдете ли, че искате да изтриете модела {{displayName}}?",
+ "success": "Изтриването е успешно",
+ "title": "Изтриване на модел"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Полето, което действително се изисква в Azure OpenAI",
+ "placeholder": "Моля, въведете името на модела за разполагане в Azure",
+ "title": "Име на разполагане на модела"
+ },
+ "deployName": {
+ "extra": "Това поле ще бъде използвано като ID на модела при изпращане на заявката",
+ "placeholder": "Моля, въведете действителното име или ID на разположението на модела",
+ "title": "Име на разположение на модела"
+ },
+ "displayName": {
+ "placeholder": "Моля, въведете показваното име на модела, например ChatGPT, GPT-4 и др.",
+ "title": "Показвано име на модела"
+ },
+ "files": {
+ "extra": "Текущата функция за качване на файлове е само един хак, само за опити. Пълната функционалност за качване на файлове ще бъде реализирана по-късно.",
+ "title": "Поддръжка на качване на файлове"
+ },
+ "functionCall": {
+ "extra": "Тази конфигурация ще активира само способността на модела да използва инструменти, което позволява добавянето на плъгини от клас инструменти. Но дали наистина ще се поддържа използването на инструменти зависи изцяло от самия модел, моля, тествайте неговата наличност",
+ "title": "Поддръжка на използването на инструменти"
+ },
+ "id": {
+ "extra": "След създаването не може да бъде променян, ще се използва като идентификатор на модела при извикване на AI",
+ "placeholder": "Моля, въведете идентификатор на модела, например gpt-4o или claude-3.5-sonnet",
+ "title": "ID на модела"
+ },
+ "modalTitle": "Конфигурация на персонализиран модел",
+ "reasoning": {
+ "extra": "Тази конфигурация ще активира само способността на модела за дълбоко мислене, конкретният ефект зависи изцяло от самия модел, моля, тествайте сами дали моделът притежава налична способност за дълбоко мислене",
+ "title": "Поддръжка на дълбоко мислене"
+ },
+ "tokens": {
+ "extra": "Настройте максималния брой токени, поддържани от модела",
+ "title": "Максимален контекстуален прозорец",
+ "unlimited": "Без ограничения"
+ },
+ "vision": {
+ "extra": "Тази конфигурация ще активира само конфигурацията за качване на изображения в приложението, дали поддържа разпознаване зависи изцяло от самия модел, моля, тествайте наличността на визуалната разпознаваемост на този модел.",
+ "title": "Поддръжка на визуално разпознаване"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/изображение",
+ "inputCharts": "${{amount}}/M символи",
+ "inputMinutes": "${{amount}}/минути",
+ "inputTokens": "Входящи ${{amount}}/М",
+ "outputTokens": "Изходящи ${{amount}}/М"
+ },
+ "releasedAt": "Пуснато на {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Добавяне на модел",
+ "disabled": "Неактивен",
+ "disabledActions": {
+ "showMore": "Покажи всичко"
+ },
+ "empty": {
+ "desc": "Моля, създайте персонализиран модел или изтеглете модел, за да започнете да го използвате",
+ "title": "Няма налични модели"
+ },
+ "enabled": "Активен",
+ "enabledActions": {
+ "disableAll": "Деактивирай всичко",
+ "enableAll": "Активирай всичко",
+ "sort": "Персонализиране на подредбата на моделите"
+ },
+ "enabledEmpty": "Няма активни модели, моля активирайте желаните модели от списъка по-долу~",
+ "fetcher": {
+ "clear": "Изчисти получените модели",
+ "fetch": "Получаване на списък с модели",
+ "fetching": "Получаване на списък с модели...",
+ "latestTime": "Последно обновление: {{time}}",
+ "noLatestTime": "Все още не е получен списък"
+ },
+ "resetAll": {
+ "conform": "Потвърдете ли, че искате да нулирате всички промени в текущия модел? След нулирането списъкът с текущи модели ще се върне в първоначалното си състояние",
+ "success": "Успешно нулирано",
+ "title": "Нулиране на всички промени"
+ },
+ "search": "Търсене на модели...",
+ "searchResult": "Намерени са {{count}} модела",
+ "title": "Списък с модели",
+ "total": "Общо {{count}} налични модела"
+ },
+ "searchNotFound": "Не са намерени резултати от търсенето"
+ },
+ "sortModal": {
+ "success": "Сортирането е успешно обновено",
+ "title": "Персонализирано сортиране",
+ "update": "Актуализиране"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Ще изтриете този AI доставчик, след изтриването няма да може да бъде възстановен, потвърдете ли, че искате да изтриете?",
+ "deleteSuccess": "Изтриването е успешно",
+ "tooltip": "Актуализиране на основната конфигурация на доставчика",
+ "updateSuccess": "Актуализацията е успешна"
+ },
+ "updateCustomAiProvider": {
+ "title": "Актуализиране на конфигурацията на доставчика на персонализирани AI услуги"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Въведете вашите ключове за Vertex AI",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Ключове за Vertex AI"
}
},
"zeroone": {
diff --git a/DigitalHumanWeb/locales/bg-BG/models.json b/DigitalHumanWeb/locales/bg-BG/models.json
index 4f40d01..db10aa1 100644
--- a/DigitalHumanWeb/locales/bg-BG/models.json
+++ b/DigitalHumanWeb/locales/bg-BG/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B предлага отлични резултати в индустриалните приложения с богат набор от обучителни примери."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat е вариант на Yi-1.5, който принадлежи към отворените модели за разговори. Yi-1.5 е подобрена версия на Yi, която е била предварително обучена на 500B висококачествени корпуси и е била фино настроена на 3M разнообразни примери. В сравнение с Yi, Yi-1.5 показва по-силни способности в кодирането, математиката, разсъжденията и следването на инструкции, като същевременно запазва отлични способности за разбиране на езика, разсъждения на общи познания и разбиране на текст. Моделът предлага версии с контекстна дължина от 4K, 16K и 32K, с общо количество предварително обучение от 3.6T токена."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B поддържа 16K токена, предоставяйки ефективни и плавни способности за генериране на език."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "零一万物, най-новият отворен модел с фина настройка, с 34 милиарда параметри, който поддържа множество диалогови сценарии, с висококачествени обучителни данни, съобразени с човешките предпочитания."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "零一万物, най-новият отворен модел с фина настройка, с 9 милиарда параметри, който поддържа множество диалогови сценарии, с висококачествени обучителни данни, съобразени с човешките предпочитания."
+ },
"360gpt-pro": {
"description": "360GPT Pro, като важен член на серията AI модели на 360, отговаря на разнообразни приложения на естествения език с ефективни способности за обработка на текст, поддържайки разбиране на дълги текстове и многостепенни диалози."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K акцентира на семантичната безопасност и отговорността, проектиран специално за приложения с високи изисквания за безопасност на съдържанието, осигурявайки точност и стабилност на потребителското изживяване."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 използва дървесно търсене за изграждане на вериги от мисли и въвежда механизъм за размисъл, обучен чрез подсилено учене, моделът притежава способността за саморазмисъл и корекция на грешки."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro е усъвършенстван модел за обработка на естествен език, пуснат от компания 360, с изключителни способности за генериране и разбиране на текст, особено в областта на генерирането и творчеството, способен да обработва сложни езикови трансформации и ролеви игри."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 използва дървесно търсене за изграждане на мисловни вериги и въвежда механизъм за саморазмисъл, обучавайки се чрез подсилено учене, моделът притежава способността за саморазмисъл и корекция на грешки."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra е най-мощната версия в серията Starfire, която подобрява разбирането и обобщаването на текстовото съдържание, докато надгражда свързаните търсения. Това е всестранно решение за повишаване на производителността в офиса и точно отговаряне на нуждите, водещо в индустрията интелигентно решение."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Моделът е с най-добри способности в страната, надминаващ чуждестранните водещи модели в задачи като енциклопедични знания, дълги текстове и генериране на съдържание. Също така притежава водещи в индустрията мултимодални способности и отлични резултати в множество авторитетни тестови стандарти."
},
+ "Baichuan4-Air": {
+ "description": "Моделът е лидер в страната по способности, надминавайки чуждестранните основни модели в задачи на китайски език, като знания, дълги текстове и генериране на творби. Също така притежава водещи в индустрията мултимодални способности и отлични резултати в множество авторитетни оценки."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Моделът е лидер в страната по способности, надминавайки чуждестранните основни модели в задачи на китайски език, като знания, дълги текстове и генериране на творби. Също така притежава водещи в индустрията мултимодални способности и отлични резултати в множество авторитетни оценки."
+ },
+ "DeepSeek-R1": {
+ "description": "Най-напредналият ефективен LLM, специализиран в разсъждения, математика и програмиране."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 - по-голям и по-умен модел в комплекта DeepSeek - е дестилиран в архитектурата Llama 70B. На базата на бенчмаркове и човешка оценка, този модел е по-умен от оригиналния Llama 70B, особено в задачи, изискващи математическа и фактическа точност."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 дестилиран модел, базиран на Qwen2.5-Math-1.5B, оптимизира производителността на разсъжденията чрез подсилено учене и данни за студен старт, отворен модел, който обновява многозадачния стандарт."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 дестилиран модел, базиран на Qwen2.5-14B, оптимизира производителността на разсъжденията чрез подсилено учене и данни за студен старт, отворен модел, който обновява многозадачния стандарт."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "Серията DeepSeek-R1 оптимизира производителността на разсъжденията чрез подсилено учене и данни за студен старт, отворен модел, който обновява многозадачния стандарт, надминавайки нивото на OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1 дестилиран модел, базиран на Qwen2.5-Math-7B, оптимизира производителността на разсъжденията чрез подсилено учене и данни за студен старт, отворен модел, който обновява многозадачния стандарт."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro е ново обновен мултимодален голям модел, който поддържа разпознаване на изображения с произволна резолюция и екстремни съотношения на страните, подобрявайки способностите за визуално разсъждение, разпознаване на документи, разбиране на детайлна информация и следване на инструкции."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite предлага изключителна скорост на отговор и по-добра цена, предоставяйки на клиентите гъвкави опции за различни сценарии. Поддържа извеждане и фин настройка на контекстов прозорец от 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite предлага изключителна скорост на отговор и по-добра цена, предоставяйки на клиентите гъвкави опции за различни сценарии. Поддържа извеждане и фин настройка на контекстов прозорец от 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite предлага изключителна скорост на отговор и по-добра цена, предоставяйки на клиентите гъвкави опции за различни сценарии. Поддържа извеждане и фин настройка на контекстов прозорец от 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "Най-добрият модел за основни задачи, подходящ за работа с комплексни задачи, с много добри резултати в справочния отговор, обобщение, творчество, текстова класификация и ролеви игри. Поддържа извеждане и фин настройка на контекстов прозорец от 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "Най-добрият основен модел, подходящ за обработка на сложни задачи, с отлични резултати в сценарии като отговори на въпроси, резюмиране, творчество, текстова класификация и ролеви игри. Поддържа разсъждения и фина настройка с контекстен прозорец от 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "Най-добрият модел за основни задачи, подходящ за работа с комплексни задачи, с много добри резултати в справочния отговор, обобщение, творчество, текстова класификация и ролеви игри. Поддържа извеждане и фин настройка на контекстов прозорец от 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "Най-добрият модел за основни задачи, подходящ за работа с комплексни задачи, с много добри резултати в справочния отговор, обобщение, творчество, текстова класификация и ролеви игри. Поддържа извеждане и фин настройка на контекстов прозорец от 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Doubao-vision моделът е мултимодален голям модел, представен от Doubao, който притежава мощни способности за разбиране и разсъждение на изображения, както и прецизно разбиране на инструкции. Моделът показва силни резултати в извличането на текстова информация от изображения и в задачи за разсъждение, базирани на изображения, и може да се прилага в по-сложни и по-широки визуални въпроси."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Doubao-vision моделът е мултимодален голям модел, представен от Doubao, който притежава мощни способности за разбиране и разсъждение на изображения, както и прецизно разбиране на инструкции. Моделът показва силни резултати в извличането на текстова информация от изображения и в задачи за разсъждение, базирани на изображения, и може да се прилага в по-сложни и по-широки визуални въпроси."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Флагманският модел на Baidu, разработен самостоятелно, е мащабен езиков модел, който обхваща огромно количество китайски и английски текстове. Той притежава мощни общи способности и може да отговори на почти всички изисквания за диалогови въпроси и отговори, генериране на съдържание и приложения с плъгини; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията за отговорите."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Флагманският модел на Baidu, разработен самостоятелно, е мащабен езиков модел, който обхваща огромно количество китайски и английски текстове. Той притежава мощни общи способности и може да отговори на почти всички изисквания за диалогови въпроси и отговори, генериране на съдържание и приложения с плъгини; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията за отговорите."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Флагманският модел на Baidu, разработен самостоятелно, е мащабен езиков модел, който обхваща огромно количество китайски и английски текстове. Той притежава мощни общи способности и може да отговори на почти всички изисквания за диалогови въпроси и отговори, генериране на съдържание и приложения с плъгини; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията за отговорите."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Флагманският модел на Baidu за изключително големи езикови модели, разработен самостоятелно, е напълно обновен в сравнение с ERNIE 3.5 и е широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията за отговори."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Флагманският модел на Baidu за изключително големи езикови модели, разработен самостоятелно, е напълно обновен в сравнение с ERNIE 3.5 и е широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията за отговори."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Патентованият флагмански модул на Baidu, изключително мащабен езиков модел, показващ отлични резултати и широко приложение в сложни сценарии. Поддържа автоматично свързване с плъгини на Baidu Search, гарантирайки актуалността на информацията. В сравнение с ERNIE 4.0, той представя по-добри резултати."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Флагманският модел на Baidu за изключително големи езикови модели, разработен самостоятелно, показва отлични резултати и е широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията за отговори. В сравнение с ERNIE 4.0, представянето му е по-добро."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Специализиран модел на Baidu за големи езикови модели, разработен самостоятелно, подходящ за приложения като NPC в игри, клиентски разговори и ролеви игри, с по-изразителен и последователен стил на персонажите, по-силна способност за следване на инструкции и по-добра производителност при извеждане."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Лек модел на Baidu за големи езикови модели, разработен самостоятелно, който съчетава отлични резултати с производителност при извеждане, с по-добри резултати в сравнение с ERNIE Lite, подходящ за използване с AI ускорителни карти с ниска изчислителна мощ."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Най-новият модел на Baidu за големи езикови модели с висока производителност, разработен самостоятелно, с отлични общи способности, подходящ за основен модел за фина настройка, за по-добро справяне с конкретни проблеми, като същевременно предлага отлична производителност при извеждане."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Най-новият модел на Baidu за големи езикови модели с висока производителност, разработен самостоятелно, с отлични общи способности, по-добри резултати в сравнение с ERNIE Speed, подходящ за основен модел за фина настройка, за по-добро справяне с конкретни проблеми, като същевременно предлага отлична производителност при извеждане."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) е иновативен модел, подходящ за приложения в множество области и сложни задачи."
},
- "Max-32k": {
- "description": "Spark Max 32K е конфигуриран с голяма способност за обработка на контекст, по-силно разбиране на контекста и логическо разсъждение, поддържа текстов вход от 32K токена, подходящ за четене на дълги документи, частни въпроси и отговори и други сценарии."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B е мощен визуален езиков модел, който поддържа многомодално обработване на изображения и текст, способен да разпознава точно съдържанието на изображения и да генерира свързани описания или отговори."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B е мощен визуален езиков модел, който поддържа многомодално обработване на изображения и текст, способен да разпознава точно съдържанието на изображения и да генерира свързани описания или отговори."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Изключителни способности за визуално разсъждение върху изображения с висока резолюция, подходящи за приложения за визуално разбиране."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Напреднали способности за визуално разсъждение, подходящи за приложения на агенти за визуално разбиране."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct е един от най-новите големи езикови модели, публикувани от Alibaba Cloud. Този 72B модел показва значителни подобрения в областите на кодирането и математиката. Моделът предлага многоезична поддръжка, обхващаща над 29 езика, включително китайски, английски и др. Моделът показва значителни подобрения в следването на инструкции, разбирането на структурирани данни и генерирането на структурирани изходи (особено JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct е един от най-новите големи езикови модели, публикувани от Alibaba Cloud. Този 7B модел показва значителни подобрения в областите на кодирането и математиката. Моделът предлага многоезична поддръжка, обхващаща над 29 езика, включително китайски, английски и др. Моделът показва значителни подобрения в следването на инструкции, разбирането на структурирани данни и генерирането на структурирани изходи (особено JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Текстов модел с оптимизация за инструкции на Llama 3.1, проектиран за многоезични диалогови случаи, който показва отлични резултати на много налични отворени и затворени чат модели на общи индустриални бенчмаркове."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO е високо гъвкава многомоделна комбинация, предназначена да предостави изключителен креативен опит."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Текстов модел с оптимизация за инструкции на Llama 3.1, проектиран за многоезични диалогови случаи, който показва отлични резултати на много налични отворени и затворени чат модели на общи индустриални бенчмаркове."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Текстов модел с оптимизация за инструкции на Llama 3.1, проектиран за многоезични диалогови случаи, който показва отлични резултати на много налични отворени и затворени чат модели на общи индустриални бенчмаркове."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Напреднал, водещ малък езиков модел с разбиране на езика, изключителни способности за разсъждение и генериране на текст."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Напреднал, водещ малък езиков модел с разбиране на езика, изключителни способности за разсъждение и генериране на текст."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 е най-напредналият многоезичен отворен голям езиков модел от серията Llama, който предлага производителност, сравнима с 405B моделите, на изключително ниска цена. Базиран на структурата Transformer и подобрен чрез супервизирано фино настройване (SFT) и обучение с човешка обратна връзка (RLHF) за повишаване на полезността и безопасността. Неговата версия с оптимизация за инструкции е специално проектирана за многоезични диалози и показва по-добри резултати от много от наличните отворени и затворени чат модели на множество индустриални бенчмаркове. Краен срок за знанията е декември 2023 г."
+ },
+ "MiniMax-Text-01": {
+ "description": "В серията модели MiniMax-01 направихме смели иновации: за първи път реализирахме мащабно линейно внимание, традиционната архитектура на Transformer вече не е единственият избор. Параметрите на този модел достигат 4560 милиарда, с единична активация от 45.9 милиарда. Общата производителност на модела е на нивото на водещите модели в чужбина, като същевременно ефективно обработва глобалния контекст от 4 милиона токена, което е 32 пъти повече от GPT-4o и 20 пъти повече от Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) е модел с висока точност за инструкции, подходящ за сложни изчисления."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) предлага оптимизирани езикови изходи и разнообразни възможности за приложение."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Обновление на модела Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 демонстрира изключителни резултати в различни визуално-языкови задачи, включително разбиране на документи и графики, разбиране на текст в сцени, OCR, решаване на научни и математически проблеми."
},
"Phi-3-medium-128k-instruct": {
"description": "Същият модел Phi-3-medium, но с по-голям размер на контекста за RAG или малко подканване."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Модел с 7B параметри, предлагащ по-добро качество от Phi-3-mini, с акцент върху висококачествени, плътни на разсъждения данни."
},
- "Pro-128k": {
- "description": "Spark Pro-128K е конфигуриран с изключителна способност за обработка на контекст, способен да обработва до 128K контекстна информация, особено подходящ за дълги текстове, изискващи цялостен анализ и дългосрочни логически връзки, предоставяйки плавна и последователна логика и разнообразна поддръжка на цитати в сложни текстови комуникации."
+ "Phi-3.5-mini-instruct": {
+ "description": "Актуализирана версия на модела Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Актуализирана версия на модела Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 демонстрира изключителни резултати в различни визуално-языкови задачи, включително разбиране на документи и графики, разбиране на текст в сцени, OCR, решаване на научни и математически проблеми."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct е голям езиков модел с параметри 1.5B от серията Qwen2, специално настроен за инструкции. Моделът е базиран на архитектурата Transformer и използва технологии като SwiGLU активационна функция, QKV отклонение за внимание и групова внимание. Той показва отлични резултати в множество бенчмаркове за разбиране на езика, генериране, многоезични способности, кодиране, математика и разсъждения, надминавайки повечето отворени модели. В сравнение с Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct показва значителни подобрения в тестовете MMLU, HumanEval, GSM8K, C-Eval и IFEval, въпреки че параметрите са малко по-малко."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct е голям езиков модел с параметри 7B от серията Qwen2, специално настроен за инструкции. Моделът е базиран на архитектурата Transformer и използва технологии като SwiGLU активационна функция, QKV отклонение за внимание и групова внимание. Той може да обработва големи входни данни. Моделът показва отлични резултати в множество бенчмаркове за разбиране на езика, генериране, многоезични способности, кодиране, математика и разсъждения, надминавайки повечето отворени модели и показвайки конкурентоспособност на определени задачи в сравнение с патентовани модели. Qwen2-7B-Instruct показва значителни подобрения в множество оценки в сравнение с Qwen1.5-7B-Chat."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL е най-новата итерация на модела Qwen-VL, който е постигнал водещи резултати в тестовете за визуално разбиране."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct е един от най-новите големи езикови модели, публикувани от Alibaba Cloud. Този 7B модел показва значителни подобрения в областите на кодирането и математиката. Моделът предлага многоезична поддръжка, обхващаща над 29 езика, включително китайски, английски и др. Моделът показва значителни подобрения в следването на инструкции, разбирането на структурирани данни и генерирането на структурирани изходи (особено JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct е най-новата версия на серията големи езикови модели, специфични за код, публикувана от Alibaba Cloud. Моделът значително подобрява способностите за генериране на код, разсъждения и корекции, след като е обучен с 55 трилиона токена на базата на Qwen2.5. Той не само подобрява кодовите умения, но и запазва предимствата в математиката и общите способности. Моделът предоставя по-пълна основа за практическите приложения като кодови интелигентни агенти."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat е отворената версия на предварително обучен модел от серията GLM-4, пусната от Zhizhu AI. Моделът показва отлични резултати в семантика, математика, разсъждения, код и знания. Освен че поддържа многократни разговори, GLM-4-9B-Chat предлага и напреднали функции като уеб браузинг, изпълнение на код, извикване на персонализирани инструменти (Function Call) и разсъждения с дълги текстове. Моделът поддържа 26 езика, включително китайски, английски, японски, корейски и немски. В множество бенчмаркове, GLM-4-9B-Chat показва отлична производителност, като AlignBench-v2, MT-Bench, MMLU и C-Eval. Моделът поддържа максимална контекстна дължина от 128K, подходящ за академични изследвания и търговски приложения."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 е модел за инференция, управляван от обучение с подсилване (RL), който решава проблемите с повторяемостта и четимостта в моделите. Преди RL, DeepSeek-R1 въвежда данни за студен старт, за да оптимизира допълнително производителността на инференцията. Той показва сравними резултати с OpenAI-o1 в математически, кодови и инференционни задачи и подобрява общата ефективност чрез внимателно проектирани методи на обучение."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 е модел на езика с 6710 милиарда параметри, който използва архитектура на смесени експерти (MoE) с много глави на потенциално внимание (MLA) и стратегия за баланс на натоварването без помощни загуби, оптимизираща производителността на инференцията и обучението. Чрез предварително обучение на 14.8 трилиона висококачествени токени и последващо супервизирано фино настройване и обучение с подсилване, DeepSeek-V3 надминава производителността на други отворени модели и е близо до водещите затворени модели."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma е един от най-новите леки, авангардни отворени модели, разработени от Google. Това е голям езиков модел с един декодер, който поддържа английски и предлага отворени тегла, предварително обучени варианти и варианти с фино настройване на инструкции. Моделът Gemma е подходящ за различни задачи по генериране на текст, включително въпроси и отговори, резюмиране и разсъждения. Този 9B модел е обучен с 8 трилиона токена. Неговият относително малък размер позволява внедряване в среди с ограничени ресурси, като лаптопи, настолни компютри или собствена облачна инфраструктура, което позволява на повече хора да имат достъп до авангардни AI модели и да насърчават иновации."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 е семейство от многоезични големи езикови модели, разработени от Meta, включващо предварително обучени и модели с фино настройване с параметри 8B, 70B и 405B. Този 8B модел с фино настройване на инструкции е оптимизиран за многоезични разговорни сценарии и показва отлични резултати в множество индустриални бенчмаркове. Моделът е обучен с над 15 трилиона токена от публични данни и използва технологии като наблюдавано фино настройване и обучение с човешка обратна връзка, за да подобри полезността и безопасността на модела. Llama 3.1 поддържа генериране на текст и генериране на код, с дата на прекратяване на знанията до декември 2023 г."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview е иновативен модел за обработка на естествен език, способен да обработва ефективно сложни задачи за генериране на диалог и разбиране на контекста."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview е изследователски модел, разработен от екипа на Qwen, който се фокусира върху визуалните способности за извеждане и притежава уникални предимства в разбирането на сложни сцени и решаването на визуално свързани математически проблеми."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Като тестова версия на Qwen2, Qwen1.5 използва големи данни за постигане на по-точни диалогови функции."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ е моделът за изводи от серията Qwen. В сравнение с традиционните модели за оптимизация на инструкции, QwQ притежава способности за разсъждение и извод, което позволява значително подобряване на производителността в задачи от по-ниско ниво, особено при решаване на трудни проблеми. QwQ-32B е среден модел за изводи, който постига конкурентоспособна производителност в сравнение с най-съвременните модели за изводи (като DeepSeek-R1, o1-mini). Този модел използва технологии като RoPE, SwiGLU, RMSNorm и Attention QKV bias, с 64 слоя в мрежовата структура и 40 Q внимание глави (в архитектурата GQA KV е 8)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) предлага бързи отговори и естествени диалогови способности, подходящи за многоезични среди."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview е най-новият експериментален изследователски модел на Qwen, който се фокусира върху подобряване на AI разсъдъчните способности. Чрез изследване на сложни механизми като езикови смеси и рекурсивно разсъждение, основните предимства включват мощни аналитични способности, математически и програмистки умения. В същото време съществуват проблеми с езиковото превключване, цикли на разсъждение, съображения за безопасност и разлики в други способности."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct е голям езиков модел с параметри 1.5B от серията Qwen2, специално настроен за инструкции. Моделът е базиран на архитектурата Transformer и използва технологии като SwiGLU активационна функция, QKV отклонение за внимание и групова внимание. Той показва отлични резултати в множество бенчмаркове за разбиране на езика, генериране, многоезични способности, кодиране, математика и разсъждения, надминавайки повечето отворени модели. В сравнение с Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct показва значителни подобрения в тестовете MMLU, HumanEval, GSM8K, C-Eval и IFEval, въпреки че параметрите са малко по-малко."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 е напреднал универсален езиков модел, поддържащ множество типове инструкции."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct е голям езиков модел с параметри 72B от серията Qwen2, специално настроен за инструкции. Моделът е базиран на архитектурата Transformer и използва технологии като SwiGLU активационна функция, QKV отклонение за внимание и групова внимание. Той може да обработва големи входни данни. Моделът показва отлични резултати в множество бенчмаркове за разбиране на езика, генериране, многоезични способности, кодиране, математика и разсъждения, надминавайки повечето отворени модели и показвайки конкурентоспособност на определени задачи в сравнение с патентовани модели."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL е най-новата итерация на модела Qwen-VL, който е постигнал водещи резултати в тестовете за визуално разбиране."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 е нова серия от големи езикови модели, проектирана да оптимизира обработката на инструкции."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 е нова серия от големи езикови модели, проектирана да оптимизира обработката на инструкции."
},
"Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Голям езиков модел, разработен от екипа на Alibaba Cloud Tongyi Qianwen"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
"description": "Qwen2.5 е нова серия от големи езикови модели с по-силни способности за разбиране и генериране."
},
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 е нова серия от големи езикови модели, проектирана да оптимизира обработката на инструкти."
+ },
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 е нова серия от големи езикови модели, проектирана да оптимизира обработката на инструкции."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 е нова серия от големи езикови модели, проектирана да оптимизира обработката на инструкти."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder се фокусира върху писането на код."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math се фокусира върху решаването на математически проблеми, предоставяйки професионални отговори на трудни задачи."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct е най-новата версия на серията големи езикови модели, специфични за код, публикувана от Alibaba Cloud. Моделът значително подобрява способностите за генериране на код, разсъждения и корекции, след като е обучен с 55 трилиона токена на базата на Qwen2.5. Той не само подобрява кодовите умения, но и запазва предимствата в математиката и общите способности. Моделът предоставя по-пълна основа за практическите приложения като кодови интелигентни агенти."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 е най-новата серия на модела Qwen, поддържаща 128k контекст. В сравнение с текущите най-добри отворени модели, Qwen2-72B значително надминава водещите модели в области като разбиране на естествен език, знания, код, математика и многоезичност."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 е най-новата серия на модела Qwen, способен да надмине оптималните отворени модели с равен размер или дори по-големи модели. Qwen2 7B постига значителни предимства в множество тестове, особено в разбирането на код и китайския език."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B е мощен визуален езиков модел, който поддържа многомодално обработване на изображения и текст, способен точно да разпознава съдържанието на изображения и да генерира свързани описания или отговори."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct е голям езиков модел с 14 милиарда параметри, с отлично представяне, оптимизиран за китайски и многоезични сценарии, поддържа интелигентни въпроси и отговори, генериране на съдържание и други приложения."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct е голям езиков модел с 32 милиарда параметри, с балансирано представяне, оптимизиран за китайски и многоезични сценарии, поддържа интелигентни въпроси и отговори, генериране на съдържание и други приложения."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct поддържа 16k контекст, генерира дълги текстове над 8K. Поддържа функция за извикване и безпроблемна интеграция с външни системи, значително увеличаваща гъвкавостта и разширяемостта. Моделът има значително увеличени знания и значително подобрени способности в кодиране и математика, с поддръжка на над 29 езика."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct е голям езиков модел с 7 милиарда параметри, който поддържа безпроблемно взаимодействие с функции и външни системи, значително увеличавайки гъвкавостта и разширяемостта. Оптимизиран за китайски и многоезични сценарии, поддържа интелигентни въпроси и отговори, генериране на съдържание и други приложения."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct е модел за програмиране, базиран на мащабно предварително обучение, с мощни способности за разбиране и генериране на код, способен ефективно да обработва различни програмни задачи, особено подходящ за интелигентно писане на код, автоматично генериране на скриптове и отговори на програмни въпроси."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct е голям езиков модел, проектиран специално за генериране на код, разбиране на код и ефективни сценарии за разработка, с водеща в индустрията параметрична стойност от 32B, способен да отговори на разнообразни програмни нужди."
+ },
+ "SenseChat": {
+ "description": "Основна версия на модела (V4), с контекстна дължина 4K, с мощни общи способности."
+ },
+ "SenseChat-128K": {
+ "description": "Основна версия на модела (V4), с контекстна дължина 128K, показваща отлични резултати в задачи за разбиране и генериране на дълги текстове."
+ },
+ "SenseChat-32K": {
+ "description": "Основна версия на модела (V4), с контекстна дължина 32K, гъвкаво приложима в различни сцени."
+ },
+ "SenseChat-5": {
+ "description": "Най-новата версия на модела (V5.5), с контекстна дължина 128K, значително подобрена способност в области като математическо разсъждение, английски разговори, следване на инструкции и разбиране на дълги текстове, сравнима с GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "Това е най-новата версия, базирана на V5.5, която показва значителни подобрения в основните способности на китайски и английски, чат, научни знания, хуманитарни знания, писане, математическа логика и контрол на броя на думите в сравнение с предишната версия."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "С контекстна дължина 32K, надминава GPT-4 в разбирането на разговори на кантонски, сравним с GPT-4 Turbo в множество области като знания, разсъждение, математика и писане на код."
+ },
+ "SenseChat-Character": {
+ "description": "Стандартна версия на модела, с контекстна дължина 8K, с висока скорост на отговор."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Премиум версия на модела, с контекстна дължина 32K, с напълно подобрени способности, поддържаща разговори на китайски/английски."
+ },
+ "SenseChat-Turbo": {
+ "description": "Подходящ за бързи въпроси и отговори, сцени на фино настройване на модела."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "Това е най-новият лек модел, който достига над 90% от способностите на пълния модел, значително намалявайки разходите за изчисление."
+ },
+ "SenseChat-Vision": {
+ "description": "Най-новата версия на модела (V5.5) поддържа вход с множество изображения и напълно реализира оптимизация на основните способности на модела, с голямо подобрение в разпознаването на свойства на обекти, пространствени отношения, разпознаване на действия и събития, разбиране на сцени, разпознаване на емоции, логическо разсъждение и генериране на текст."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Cloud Lark (Skylark) второ поколение модел, Skylark2-lite предлага висока скорост на отговор, подходяща за сценарии с високи изисквания за реално време, чувствителни към разходите и с по-ниски изисквания за прецизност, с дължина на контекстовия прозорец 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Cloud Lark (Skylark) второ поколение модел, версията Skylark2-pro предлага висока прецизност на модела, подходяща за по-сложни текстови генерации, като например генериране на текстове за специализирани области, писане на романи и висококачествени преводи, с дължина на контекстовия прозорец 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Cloud Lark (Skylark) второ поколение модел, версията Skylark2-pro предлага висока прецизност на модела, подходяща за по-сложни текстови генерации, като например генериране на текстове за специализирани области, писане на романи и висококачествени преводи, с дължина на контекстовия прозорец 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Cloud Lark (Skylark) второ поколение модел, Skylark2-pro-character предоставя отлични способности за ролеви игри и чат, специализирани в адаптиране на стилове на персонажи, които естествено взаимодействат с потребителите, идеален за изграждане на чат-ботове, виртуални асистенти и онлайн обслужване с висока скорост на отговор."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Cloud Lark (Skylark) второ поколение модел, Skylark2-pro-turbo-8k предлага по-бърза обработка и по-ниски разходи, с дължина на контекстовия прозорец 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B е отворен модел от серията ChatGLM, разработен от Zhizhu AI. Моделът запазва отличителните характеристики на предшествениците си, като плавност на разговора и ниски изисквания за внедряване, докато въвежда нови функции. Той използва по-разнообразни тренировъчни данни, по-пълноценни тренировъчни стъпки и по-разумни тренировъчни стратегии, показвайки отлични резултати сред предварително обучените модели под 10B. ChatGLM3-6B поддържа многократни разговори, извикване на инструменти, изпълнение на код и сложни сценарии на задачи на агенти. Освен модела за разговори, са отворени и основният модел ChatGLM-6B-Base и моделът за дълги текстови разговори ChatGLM3-6B-32K. Моделът е напълно отворен за академични изследвания и позволява безплатна търговска употреба след регистрация."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B е отворен код версия, предоставяща оптимизирано изживяване в разговорните приложения."
},
+ "TeleAI/TeleChat2": {
+ "description": "TeleChat2 е голям модел, разработен от China Telecom, който предлага генеративен семантичен модел, поддържащ функции като енциклопедични въпроси и отговори, генериране на код и генериране на дълги текстове, предоставяйки услуги за консултации на потребителите, способни да взаимодействат с потребителите, да отговарят на въпроси и да помагат в творчеството, ефективно и удобно помагайки на потребителите да получат информация, знания и вдъхновение. Моделът показва отлични резултати в проблеми с илюзии, генериране на дълги текстове и логическо разбиране."
+ },
+ "TeleAI/TeleMM": {
+ "description": "TeleMM е многомодален голям модел, разработен от China Telecom, способен да обработва текст, изображения и други видове входни данни, поддържащ функции като разбиране на изображения и анализ на графики, предоставяйки услуги за разбиране на потребителите в различни модалности. Моделът може да взаимодейства с потребителите в многомодални сценарии, точно разбирайки входното съдържание, отговаряйки на въпроси, помагайки в творчеството и ефективно предоставяйки многомодална информация и вдъхновение. Моделът показва отлични резултати в задачи с фина перцепция и логическо разсъждение."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct е един от най-новите големи езикови модели, публикувани от Alibaba Cloud. Този 72B модел показва значителни подобрения в областите на кодирането и математиката. Моделът предлага многоезична поддръжка, обхващаща над 29 езика, включително китайски, английски и др. Моделът показва значителни подобрения в следването на инструкции, разбирането на структурирани данни и генерирането на структурирани изходи (особено JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B значително подобрява математическата логика и способностите в кодирането, като запазва отличните общи езикови способности на оригиналната серия модели, чрез инкрементално обучение с 500 милиарда висококачествени токени."
+ },
"abab5.5-chat": {
"description": "Насочена към производствени сценарии, поддържаща обработка на сложни задачи и ефективно генериране на текст, подходяща за професионални приложения."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Оптимизирана за диалогови сценарии на китайски, предлагаща плавно и съответстващо на китайските изразни навици генериране на диалози."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworks отворен модел за извикване на функции, предлагащ отлични способности за изпълнение на инструкции и отворени, персонализируеми характеристики."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Fireworks компанията представя Firefunction-v2, модел за извикване на функции с изключителна производителност, разработен на базата на Llama-3 и оптимизиран за функции, диалози и следване на инструкции."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b е визуален езиков модел, който може да приема изображения и текстови входове, обучен с висококачествени данни, подходящ за мултимодални задачи."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 е авангарден голям езиков модел, оптимизиран чрез подсилено обучение и данни за студен старт, с отлични способности в разсъжденията, математиката и програмирането."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B модел за инструкции, базиран на предишната технология на Google, подходящ за отговори на въпроси, обобщения и разсъждения в множество текстови генериращи задачи."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Мощен езиков модел Mixture-of-Experts (MoE) от Deepseek, с общ брой параметри 671B, активиращи 37B параметри на всеки токен."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Llama 3 70B модел за инструкции, специално оптимизиран за многоезични диалози и разбиране на естествен език, с производителност, превъзхождаща повечето конкурентни модели."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B модел за инструкции (HF версия), с резултати, съвпадащи с официалната реализация, подходящ за висококачествени задачи за следване на инструкции."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Llama 3 8B модел за инструкции, оптимизиран за диалози и многоезични задачи, с изключителна производителност и ефективност."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Llama 3.1 8B модел за инструкции, оптимизиран за многоезични диалози, способен да надмине повечето отворени и затворени модели на общи индустриални стандарти."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Моделът за разсъждение по изображения с 11B параметри на Meta е оптимизиран за визуално разпознаване, разсъждение по изображения, описание на изображения и отговаряне на общи въпроси относно изображения. Моделът може да разбира визуални данни, като графики и таблици, и свързва визуалните данни с текстовите описания на детайлите на изображенията."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Моделът Llama 3.2 3B е лека многоезична разработка от Meta. Този модел е проектиран да подобри ефективността, предоставяйки значителни подобрения в забавянето и разходите в сравнение с по-големи модели. Примерни случаи на ползване включват заявки, пренаписване на подканвания и подпомагане на писането."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Моделът за разсъждение по изображения с 90B параметри на Meta е оптимизиран за визуално разпознаване, разсъждение по изображения, описание на изображения и отговаряне на общи въпроси относно изображения. Моделът може да разбира визуални данни, като графики и таблици, и свързва визуалните данни с текстовите описания на детайлите на изображенията."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct е актуализирана версия на Llama 3.1 70B от декември. Този модел е подобрен на базата на Llama 3.1 70B (пуснат през юли 2024 г.), с подобрени възможности за извикване на инструменти, поддръжка на многоезичен текст, математика и програмиране. Моделът постига водещи в индустрията резултати в области като разсъждение, математика и следване на инструкции, и предлага производителност, подобна на 3.1 405B, с значителни предимства в скоростта и разходите."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Модел с 24B параметри, предлагащ водещи в индустрията способности, сравними с по-големите модели."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B модел за инструкции, с голям брой параметри и архитектура с множество експерти, осигуряваща всестранна поддръжка за ефективна обработка на сложни задачи."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B модел за инструкции, архитектура с множество експерти, предлагаща ефективно следване и изпълнение на инструкции."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B модел за инструкции (HF версия), с производителност, съвпадаща с официалната реализация, подходящ за множество ефективни сценарии."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "MythoMax L2 13B модел, комбиниращ новаторски технологии за интеграция, специализиран в разказване на истории и ролеви игри."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision модел за инструкции, лек мултимодален модел, способен да обработва сложна визуална и текстова информация, с високи способности за разсъждение."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5B модел, поддържащ напреднали програмни задачи, с подобрени многоезични способности, подходящ за сложна генерация и разбиране на код."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "QwQ моделът е експериментален изследователски модел, разработен от екипа на Qwen, който се фокусира върху подобряване на AI разсъдъчните способности."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "72B версия на модела Qwen-VL е последната итерация на Alibaba, представляваща иновации от последната година."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7B модел, обучен за над 80 програмни езика, с отлични способности за попълване на код и разбиране на контекста."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 е серия от езикови модели, разработени от екипа на Alibaba Cloud Qwen, които съдържат само декодери. Тези модели предлагат различни размери, включително 0.5B, 1.5B, 3B, 7B, 14B, 32B и 72B, и разполагат с базови (base) и инструкти (instruct) варианти."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct е най-новата версия на серията големи езикови модели, специфични за код, публикувана от Alibaba Cloud. Моделът значително подобрява способностите за генериране на код, разсъждения и корекции, след като е обучен с 55 трилиона токена на базата на Qwen2.5. Той не само подобрява кодовите умения, но и запазва предимствата в математиката и общите способности. Моделът предоставя по-пълна основа за практическите приложения като кодови интелигентни агенти."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Yi-Large модел, предлагащ изключителни способности за многоезична обработка, подходящ за различни задачи по генериране и разбиране на език."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Многоезичен модел с 52B параметри (12B активни), предлагащ контекстен прозорец с дължина 256K, извикване на функции, структурирани изходи и генериране на основа."
},
- "ai21-jamba-instruct": {
- "description": "Модел на базата на Mamba, проектиран за постигане на най-добри резултати, качество и ефективност на разходите."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet повишава индустриалните стандарти, с производителност, надвишаваща конкурентните модели и Claude 3 Opus, с отлични резултати в широки оценки, като същевременно предлага скорост и разходи на нашите модели от средно ниво."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet повишава индустриалните стандарти, с производителност, надминаваща конкурентните модели и Claude 3 Opus, показвайки отлични резултати в широки оценки, като същевременно предлага скорост и разходи, характерни за нашите модели от среден клас."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku е най-бързият и компактен модел на Anthropic, предлагащ почти мигновена скорост на отговор. Той може бързо да отговаря на прости запитвания и заявки. Клиентите ще могат да изградят безпроблемно AI изживяване, имитиращо човешко взаимодействие. Claude 3 Haiku може да обработва изображения и да връща текстови изходи, с контекстуален прозорец от 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus е най-мощният модел на Anthropic, предназначен за обработка на изключително сложни задачи. Той се отличава с изключителна производителност, интелигентност, гладкост и разбиране."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku е най-бързият следващ модел на Anthropic. В сравнение с Claude 3 Haiku, Claude 3.5 Haiku показва подобрения в различни умения и надминава предишното поколение най-голям модел Claude 3 Opus в много интелектуални бенчмаркове."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet предлага способности, надхвърлящи Opus, и по-бърза скорост в сравнение с Sonnet, като същевременно запазва същата цена. Sonnet е особено силен в програмирането, науката за данни, визуалната обработка и агентските задачи."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet е най-интелигентният модел на Anthropic до момента и е първият хибриден модел за разсъждение на пазара. Claude 3.7 Sonnet може да генерира почти мигновени отговори или удължено стъпково мислене, което позволява на потребителите ясно да видят тези процеси. Sonnet е особено добър в програмирането, науката за данни, визуалната обработка и агентските задачи."
+ },
"aya": {
"description": "Aya 23 е многозначен модел, представен от Cohere, поддържащ 23 езика, предоставяйки удобство за многоезични приложения."
},
"aya:35b": {
"description": "Aya 23 е многозначен модел, представен от Cohere, поддържащ 23 езика, предоставяйки удобство за многоезични приложения."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B е отворен, комерсиален голям езиков модел, разработен от Baichuan Intelligence, с 13 милиарда параметри, който постига най-добрите резултати в своя размер на авторитетни бенчмаркове на китайски и английски."
+ },
"charglm-3": {
"description": "CharGLM-3 е проектиран за ролеви игри и емоционално придружаване, поддържаща дълга многократна памет и персонализиран диалог, с широко приложение."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 предлага напредък в ключовите способности за бизнеса, включително водещи в индустрията 200K токена контекст, значително намаляване на честотата на илюзии на модела, системни подсказки и нова тестова функция: извикване на инструменти."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku е най-бързият следващ модел на Anthropic. В сравнение с Claude 3 Haiku, Claude 3.5 Haiku е подобрен във всички умения и надминава предишния най-голям модел Claude 3 Opus в много интелектуални тестове."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet предлага способности, надминаващи Opus и по-бърза скорост от Sonnet, като същевременно поддържа същата цена. Sonnet е особено силен в програмирането, науката за данни, визуалната обработка и задачи с агенти."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet предлага възможности, които надминават Opus и скорости, които са по-бързи от Sonnet, като същевременно поддържа същата цена като Sonnet. Sonnet е специално силен в програмирането, науката за данни, визуалната обработка и задачи, свързани с代理."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet предлага индустриални стандарти, с производителност, надвишаваща конкурентните модели и Claude 3 Opus, с отлични резултати в широки оценки, като същевременно предлага скорост и разходи, характерни за нашите модели от среден клас."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku е най-бързият и компактен модел на Anthropic, проектиран за почти мигновени отговори. Той предлага бърза и точна насочена производителност."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet предлага идеален баланс между интелигентност и скорост за корпоративни работни натоварвания. Той предлага максимална полезност на по-ниска цена, надежден и подходящ за мащабно внедряване."
},
- "claude-instant-1.2": {
- "description": "Моделът на Anthropic е предназначен за ниска латентност и висока производителност на текстовото генериране, поддържащ генерирането на стотици страници текст."
- },
"codegeex-4": {
"description": "CodeGeeX-4 е мощен AI помощник за програмиране, който поддържа интелигентни въпроси и отговори и автоматично допълване на код за различни програмни езици, повишавайки ефективността на разработката."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B е многоезичен модел за генериране на код, който предлага пълни функции, включително попълване и генериране на код, интерпретатор на код, уеб търсене, извикване на функции и въпроси и отговори на ниво хранилище, обхващащ различни сценарии на софтуерна разработка. Това е водещ модел за генериране на код с по-малко от 10B параметри."
+ },
"codegemma": {
"description": "CodeGemma е лек езиков модел, специализиран в различни програмни задачи, поддържащ бърза итерация и интеграция."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama е LLM, фокусиран върху генерирането и обсъждането на код, комбиниращ широк спектър от поддръжка на програмни езици, подходящ за среда на разработчици."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama е LLM, фокусиран върху генерирането и обсъждането на код, с широка поддръжка на програмни езици, подходящ за среда на разработчици."
+ },
"codellama:13b": {
"description": "Code Llama е LLM, фокусиран върху генерирането и обсъждането на код, комбиниращ широк спектър от поддръжка на програмни езици, подходящ за среда на разработчици."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ е високопроизводителен голям езиков модел, проектиран за реални бизнес сценарии и сложни приложения."
},
+ "dall-e-2": {
+ "description": "Второ поколение модел DALL·E, поддържащ по-реалистично и точно генериране на изображения, с резолюция 4 пъти по-висока от първото поколение."
+ },
+ "dall-e-3": {
+ "description": "Най-новият модел DALL·E, пуснат през ноември 2023 г. Поддържа по-реалистично и точно генериране на изображения с по-силна детайлност."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct предлага висока надеждност в обработката на инструкции, поддържаща приложения в множество индустрии."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 е модел за извеждане, управляван от подсилено обучение (RL), който решава проблемите с повторяемостта и четимостта в модела. Преди RL, DeepSeek-R1 въвежда данни за студен старт, за да оптимизира допълнително производителността на извеждане. Той показва сравнима производителност с OpenAI-o1 в математически, кодови и извеждащи задачи и подобрява общите резултати чрез внимателно проектирани методи на обучение."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek-R1 дестилиран модел, оптимизира производителността на разсъжденията чрез подсилено учене и данни за студен старт, отворен модел, който обновява многозадачния стандарт."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B е дестилиран модел, базиран на Llama-3.1-8B. Този модел е финализиран с примери, генерирани от DeepSeek-R1, и показва отлична производителност на разсъжденията. Той постига добри резултати в множество бенчмаркове, включително 89.1% точност в MATH-500, 50.4% успеваемост в AIME 2024 и 1205 точки в CodeForces, демонстрирайки силни способности за математика и програмиране."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 дестилиран модел, оптимизира производителността на разсъжденията чрез подсилено учене и данни за студен старт, отворен модел, който обновява многозадачния стандарт."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 дестилиран модел, оптимизира производителността на разсъжденията чрез подсилено учене и данни за студен старт, отворен модел, който обновява многозадачния стандарт."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B е модел, получен чрез знание дестилация на Qwen2.5-32B. Този модел е финализиран с 800 000 избрани примера, генерирани от DeepSeek-R1, и показва изключителна производителност в множество области, включително математика, програмиране и разсъждения. Той постига отлични резултати в множество бенчмаркове, включително 94.3% точност в MATH-500, демонстрирайки силни способности за математическо разсъждение."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B е модел, получен чрез знание дестилация на Qwen2.5-Math-7B. Този модел е финализиран с 800 000 избрани примера, генерирани от DeepSeek-R1, и показва отлична производителност на разсъжденията. Той постига отлични резултати в множество бенчмаркове, включително 92.8% точност в MATH-500, 55.5% успеваемост в AIME 2024 и 1189 точки в CodeForces, демонстрирайки силни способности за математика и програмиране."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 обединява отличителните характеристики на предишните версии, подобрявайки общите и кодиращите способности."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 е езиков модел с 6710 милиарда параметри, базиран на смесени експерти (MoE), който използва многоглаво потенциално внимание (MLA) и архитектурата DeepSeekMoE, комбинирайки стратегии за баланс на натоварването без помощни загуби, за да оптимизира производителността на извеждане и обучение. Чрез предварително обучение на 14.8 трилиона висококачествени токени и последващо наблюдавано фино настройване и подсилено обучение, DeepSeek-V3 надминава производителността на други отворени модели и се приближава до водещите затворени модели."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B е напреднал модел, обучен за диалози с висока сложност."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "Най-съвременен ефективен LLM, специализиран в разсъждения, математика и програмиране."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 е визуален езиков модел, разработен на базата на DeepSeekMoE-27B, който използва архитектура на смесени експерти (MoE) с рядка активация, постигайки изключителна производителност с активирани само 4.5B параметри. Моделът показва отлични резултати в множество задачи, включително визуални въпроси и отговори, оптично разпознаване на символи, разбиране на документи/таблици/графики и визуална локализация."
+ },
"deepseek-chat": {
"description": "Новооткритият отворен модел, който съчетава общи и кодови способности, не само запазва общата диалогова способност на оригиналния Chat модел и мощната способност за обработка на код на Coder модела, но също така по-добре се съгласува с човешките предпочитания. Освен това, DeepSeek-V2.5 постигна значителни подобрения в писателските задачи, следването на инструкции и много други области."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B е модел за кодови езици, обучен на 20 трилиона данни, от които 87% са код и 13% са на китайски и английски. Моделът въвежда размер на прозореца от 16K и задачи за попълване, предоставяйки функции за попълване на код на проектно ниво и попълване на фрагменти."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 е отворен хибриден експертен кодов модел, който се представя отлично в кодовите задачи, сравним с GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 е отворен хибриден експертен кодов модел, който се представя отлично в кодовите задачи, сравним с GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 е модел за извеждане, управляван от подсилено обучение (RL), който решава проблемите с повторяемостта и четимостта в модела. Преди RL, DeepSeek-R1 въвежда данни за студен старт, за да оптимизира допълнително производителността на извеждане. Той показва сравнима производителност с OpenAI-o1 в математически, кодови и извеждащи задачи и подобрява общите резултати чрез внимателно проектирани методи на обучение."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - по-голям и по-интелигентен модел в комплекта DeepSeek - е дестилиран в архитектурата Llama 70B. На базата на бенчмаркове и човешка оценка, този модел е по-интелигентен от оригиналния Llama 70B, особено в задачи, изискващи математическа и фактическа точност."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Моделите от серията DeepSeek-R1-Distill са получени чрез техника на знание дестилация, като се фино настройват образците, генерирани от DeepSeek-R1, спрямо отворени модели като Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Моделите от серията DeepSeek-R1-Distill са получени чрез техника на знание дестилация, като се фино настройват образците, генерирани от DeepSeek-R1, спрямо отворени модели като Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Моделите от серията DeepSeek-R1-Distill са получени чрез техника на знание дестилация, като се фино настройват образците, генерирани от DeepSeek-R1, спрямо отворени модели като Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Моделите от серията DeepSeek-R1-Distill са получени чрез техника на знание дестилация, като се фино настройват образците, генерирани от DeepSeek-R1, спрямо отворени модели като Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Моделите от серията DeepSeek-R1-Distill са получени чрез техника на знание дестилация, като се фино настройват образците, генерирани от DeepSeek-R1, спрямо отворени модели като Qwen и Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "Модел за извеждане, разработен от DeepSeek. Преди да предостави окончателния отговор, моделът първо извежда част от веригата на мислене, за да повиши точността на крайния отговор."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 е ефективен модел на Mixture-of-Experts, подходящ за икономически ефективни нужди от обработка."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B е кодовият модел на DeepSeek, предоставящ мощни способности за генериране на код."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 е MoE модел, разработен от Hangzhou DeepSeek AI Technology Research Co., Ltd., с отлични резултати в множество тестове, заемащ първото място в основните класации на отворените модели. V3 постига 3-кратно увеличение на скоростта на генериране в сравнение с V2.5, предоставяйки на потребителите по-бързо и гладко изживяване."
+ },
"deepseek/deepseek-chat": {
"description": "Новооткритият отворен модел, който съчетава общи и кодови способности, не само запазва общата диалогова способност на оригиналния Chat модел и мощната способност за обработка на код на Coder модела, но също така по-добре се съобразява с човешките предпочитания. Освен това, DeepSeek-V2.5 постигна значителни подобрения в задачи по писане, следване на инструкции и много други."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 значително подобри способността на модела за разсъждение при наличието на много малко маркирани данни. Преди да предостави окончателния отговор, моделът първо ще изведе част от съдържанието на веригата на мислене, за да повиши точността на окончателния отговор."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B е голям езиков модел, базиран на Llama3.3 70B, който използва фина настройка на изхода на DeepSeek R1, за да постигне конкурентна производителност, сравнима с големите водещи модели."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B е дестилиран голям езиков модел, базиран на Llama-3.1-8B-Instruct, обучен с изхода на DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B е дестилиран голям езиков модел, базиран на Qwen 2.5 14B, обучен с изхода на DeepSeek R1. Този модел надминава o1-mini на OpenAI в множество бенчмарков, постигащи най-съвременни резултати за плътни модели. Ето някои от резултатите от бенчмарковете:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nТози модел демонстрира конкурентна производителност, сравнима с по-големи водещи модели, благодарение на фина настройка на изхода на DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B е дестилиран голям езиков модел, базиран на Qwen 2.5 32B, обучен с изхода на DeepSeek R1. Този модел надминава o1-mini на OpenAI в множество бенчмарков, постигащи най-съвременни резултати за плътни модели. Ето някои от резултатите от бенчмарковете:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nТози модел демонстрира конкурентна производителност, сравнима с по-големи водещи модели, благодарение на фина настройка на изхода на DeepSeek R1."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 е най-новият отворен модел, публикуван от екипа на DeepSeek, който предлага изключителна производителност при извеждане, особено в математически, програмистки и логически задачи, достигайки ниво, сравнимо с модела o1 на OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 значително подобри способността на модела за разсъждение при наличието на много малко маркирани данни. Преди да предостави окончателния отговор, моделът първо ще изведе част от съдържанието на веригата на мислене, за да повиши точността на окончателния отговор."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 постига значителен напредък в скоростта на извеждане в сравнение с предишните модели. Той е на първо място сред отворените модели и може да се сравнява с най-съвременните затворени модели в света. DeepSeek-V3 използва архитектури с многоглаво внимание (MLA) и DeepSeekMoE, които бяха напълно валидирани в DeepSeek-V2. Освен това, DeepSeek-V3 въвежда помощна беззагубна стратегия за баланс на натоварването и задава цели за обучение с множество етикети, за да постигне по-силна производителност."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 постига значителен напредък в скоростта на извеждане в сравнение с предишните модели. Той е на първо място сред отворените модели и може да се сравнява с най-съвременните затворени модели в света. DeepSeek-V3 използва архитектури с многоглаво внимание (MLA) и DeepSeekMoE, които бяха напълно валидирани в DeepSeek-V2. Освен това, DeepSeek-V3 въвежда помощна беззагубна стратегия за баланс на натоварването и задава цели за обучение с множество етикети, за да постигне по-силна производителност."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite е ново поколение лек модел, с изключителна скорост на отговор, който постига световно ниво както по отношение на ефективността, така и на времето за реакция."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k е напълно обновен вариант на Doubao-1.5-Pro, с общо подобрение на ефективността с 10%. Поддържа разсъждения с контекстен прозорец от 256k, а дължината на изхода поддържа максимум 12k токена. По-висока производителност, по-голям прозорец и изключителна цена-качество, подходящ за по-широк спектър от приложения."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro е ново поколение основен модел, с напълно обновени характеристики, който показва отлични резултати в области като знания, код, разсъждения и др."
+ },
"emohaa": {
"description": "Emohaa е психологически модел с професионални консултантски способности, помагащ на потребителите да разберат емоционалните проблеми."
},
+ "ernie-3.5-128k": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, обхваща огромно количество китайски и английски текстове, притежаващ силни общи способности, способен да отговори на повечето изисквания за диалогови въпроси и отговори, генериране на съдържание и приложения на плъгини; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията."
+ },
+ "ernie-3.5-8k": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, обхваща огромно количество китайски и английски текстове, притежаващ силни общи способности, способен да отговори на повечето изисквания за диалогови въпроси и отговори, генериране на съдържание и приложения на плъгини; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, обхваща огромно количество китайски и английски текстове, притежаващ силни общи способности, способен да отговори на повечето изисквания за диалогови въпроси и отговори, генериране на съдържание и приложения на плъгини; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, с изключителни подобрения в сравнение с ERNIE 3.5, широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, с изключителни подобрения в сравнение с ERNIE 3.5, широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, с отлични общи резултати, широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията. В сравнение с ERNIE 4.0, показва по-добри резултати."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, с отлични общи резултати, широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията. В сравнение с ERNIE 4.0, показва по-добри резултати."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Флагманският голям езиков модел, разработен от Baidu, с отлични общи резултати, широко приложим в сложни задачи в различни области; поддържа автоматично свързване с плъгина за търсене на Baidu, осигурявайки актуалност на информацията. В сравнение с ERNIE 4.0, показва по-добри резултати."
+ },
+ "ernie-char-8k": {
+ "description": "Специализиран голям езиков модел, разработен от Baidu, подходящ за приложения като NPC в игри, диалози на клиентска поддръжка и ролеви игри, с по-изразителен и последователен стил на персонажите, по-силна способност за следване на инструкции и по-добра производителност на разсъжденията."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Специализиран голям езиков модел, разработен от Baidu, подходящ за приложения като NPC в игри, диалози на клиентска поддръжка и ролеви игри, с по-изразителен и последователен стил на персонажите, по-силна способност за следване на инструкции и по-добра производителност на разсъжденията."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite е лек голям езиков модел, разработен от Baidu, който съчетава отлични резултати с производителност на разсъжденията, подходящ за използване с AI ускорителни карти с ниска изчислителна мощ."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Лек голям езиков модел, разработен от Baidu, който съчетава отлични резултати с производителност на разсъжденията, с по-добри резултати в сравнение с ERNIE Lite, подходящ за използване с AI ускорителни карти с ниска изчислителна мощ."
+ },
+ "ernie-novel-8k": {
+ "description": "Общ голям езиков модел, разработен от Baidu, с очевидни предимства в продължаването на разкази, подходящ и за кратки пиеси и филми."
+ },
+ "ernie-speed-128k": {
+ "description": "Най-новият високопроизводителен голям езиков модел, разработен от Baidu през 2024 г., с отлични общи способности, подходящ за финализиране на специфични проблеми, с отлична производителност на разсъжденията."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Най-новият високопроизводителен голям езиков модел, разработен от Baidu през 2024 г., с отлични общи способности, с по-добри резултати в сравнение с ERNIE Speed, подходящ за финализиране на специфични проблеми, с отлична производителност на разсъжденията."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny е модел с изключителна производителност, разработен от Baidu, с най-ниски разходи за внедряване и фина настройка сред моделите от серията Wenxin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Тунинг) предлага стабилна и настройваема производителност, идеален избор за решения на сложни задачи."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro е високопроизводителен AI модел на Google, проектиран за разширяване на широк спектър от задачи."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash е най-новият мултимодален AI модел на Google, който предлага бърза обработка и поддържа текстови, изображенчески и видео входове, подходящ за ефективно разширяване на различни задачи."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 е ефективен многомодален модел, който поддържа разширяване на широк спектър от приложения."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 е ефективен мултимодален модел, който поддържа разширения за широко приложение."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 е проектиран за обработка на мащабни задачи, предлагащ ненадмината скорост на обработка."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B е ефективен многомодален модел, който поддържа разширения за широко приложение."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 е най-новият експериментален модел, който показва значителни подобрения в производителността както в текстови, така и в мултимодални приложения."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 предлага оптимизирани многомодални обработващи способности, подходящи за множество сложни задачи."
+ "description": "Gemini 1.5 Flash 0827 предлага оптимизирани мултимодални способности, подходящи за различни сложни задачи."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash е най-новият многомодален AI модел на Google, който предлага бърза обработка и поддържа текстови, изображенчески и видео входове, подходящ за ефективно разширяване на множество задачи."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002 е най-новият модел, готов за производство, който предлага по-високо качество на изхода, особено в математически, дълги контексти и визуални задачи."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 предлага отлични способности за обработка на многомодални данни, предоставяйки по-голяма гъвкавост за разработка на приложения."
+ "description": "Gemini 1.5 Pro 0801 предоставя отлична мултимодална обработка, давайки по-голяма гъвкавост при разработката на приложения."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 комбинира най-новите оптимизационни технологии, предоставяйки по-ефективни способности за обработка на многомодални данни."
+ "description": "Gemini 1.5 Pro 0827 комбинира най-новите оптимизационни технологии, предоставяйки по-ефективни мултимодални способности за обработка на данни."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro поддържа до 2 милиона токена и е идеален избор за среден многомодален модел, подходящ за многостранна поддръжка на сложни задачи."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash предлага следващо поколение функции и подобрения, включително изключителна скорост, нативна употреба на инструменти, многомодално генериране и контекстен прозорец от 1M токена."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash предлага следващо поколение функции и подобрения, включително изключителна скорост, нативна употреба на инструменти, многомодално генериране и контекстен прозорец от 1M токена."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash е вариант на модела, оптимизиран за икономичност и ниска латентност."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash е вариант на модела, оптимизиран за икономичност и ниска латентност."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Модел на Gemini 2.0 Flash, оптимизиран за икономичност и ниска латентност."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp е най-новият експериментален многомодален AI модел на Google, с ново поколение функции, изключителна скорост, нативно извикване на инструменти и многомодално генериране."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp е най-новият експериментален многомодален AI модел на Google, с ново поколение функции, изключителна скорост, нативно извикване на инструменти и многомодално генериране."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental е най-новият експериментален многомодален AI модел на Google, който предлага значително подобрение в качеството в сравнение с предишните версии, особено по отношение на световни знания, код и дълги контексти."
+ },
"gemma-7b-it": {
"description": "Gemma 7B е подходяща за обработка на средни и малки задачи, съчетаваща икономичност."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 е ефективен модел, представен от Google, обхващащ множество приложения от малки до сложни обработки на данни."
},
- "general": {
- "description": "Spark Lite е лек голям езиков модел с изключително ниска латентност и висока ефективност, напълно безплатен и отворен, поддържащ функция за търсене в реално време. Неговата бърза реакция го прави отличен за приложения с ниска изчислителна мощ и фино настройване на модела, предоставяйки на потребителите отлична цена-качество и интелигентно изживяване, особено в области като отговори на знания, генериране на съдържание и търсене."
- },
"generalv3": {
"description": "Spark Pro е високопроизводителен голям езиков модел, оптимизиран за професионални области, фокусирайки се върху математика, програмиране, медицина, образование и др., и поддържа свързано търсене и вградени плъгини за времето, датата и др. Оптимизираният модел показва отлични резултати и висока производителност в сложни отговори на знания, разбиране на езика и високо ниво на текстово генериране, което го прави идеален избор за професионални приложения."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 е най-новата версия на модела, проектирана за високо сложни и разнообразни задачи, с отлични резултати."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat показва висока производителност в множество области, включително семантика, математика, логическо разсъждение, код и знания. Също така предлага уеб браузинг, изпълнение на код, извикване на персонализирани инструменти и разсъждение върху дълги текстове. Поддържа 26 езика, включително японски, корейски и немски."
+ },
"glm-4-air": {
"description": "GLM-4-Air е икономичен вариант, с производителност близка до GLM-4, предлагаща бързина и достъпна цена."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash е идеалният избор за обработка на прости задачи, с най-бърза скорост и най-добра цена."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX е подобрена версия на Flash с изключително бърза скорост на извеждане."
+ },
"glm-4-long": {
"description": "GLM-4-Long поддържа извеждане на много дълги текстове, подходящ за задачи, свързани с памет и обработка на големи документи."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V предлага мощни способности за разбиране и разсъждение на изображения, поддържаща множество визуални задачи."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash се фокусира върху ефективното разбиране на единични изображения, подходящо за сцени с бърз анализ на изображения, като например анализ в реално време или обработка на партидни изображения."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus разполага с разбиране на видео съдържание и множество изображения, подходящ за мултимодални задачи."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 предлага оптимизирани мултимодални обработващи способности, подходящи за различни сложни задачи."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview притежава мощни способности за сложни разсъждения, показвайки отлични резултати в логическото разсъждение, математиката и програмирането."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash предлага следващо поколение функции и подобрения, включително изключителна скорост, нативна употреба на инструменти, многомодално генериране и контекстен прозорец от 1M токена."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 комбинира най-новите оптимизационни технологии, предоставяйки по-ефективни способности за обработка на мултимодални данни."
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental е най-новият експериментален многомодален AI модел на Google, който предлага значително подобрение в качеството в сравнение с предишните версии, особено по отношение на световни знания, код и дълги контексти."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash предлага оптимизирани мултимодални обработващи способности, подходящи за различни сложни задачи."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro комбинира най-новите оптимизационни технологии, предоставяйки по-ефективна обработка на мултимодални данни."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 е ефективен модел, представен от Google, обхващащ множество приложения от малки приложения до сложна обработка на данни."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 продължава концепцията за лекота и ефективност."
},
+ "google/gemma-2-2b-it": {
+ "description": "Лек модел за настройка на инструкции от Google."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 е ефективен модел, представен от Google, обхващащ множество приложения от малки приложения до сложна обработка на данни."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 е серия от леки отворени текстови модели на Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, подходящ за различни задачи по генериране и разбиране на текст, в момента сочи към gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo е ефективен модел, предоставен от OpenAI, подходящ за чат и генериране на текст, поддържащ паралелни извиквания на функции."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k е модел с висока капацитет за генериране на текст, подходящ за сложни задачи."
+ },
"gpt-4": {
"description": "GPT-4 предлага по-голям контекстуален прозорец, способен да обработва по-дълги текстови входове, подходящ за сценарии, изискващи интеграция на обширна информация и анализ на данни."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "Най-новият модел GPT-4 Turbo разполага с визуални функции. Сега визуалните заявки могат да се използват с JSON формат и извиквания на функции. GPT-4 Turbo е подобрена версия, която предлага икономически ефективна поддръжка за мултимодални задачи. Той намира баланс между точност и ефективност, подходящ за приложения, изискващи взаимодействие в реално време."
},
- "gpt-4-1106-vision-preview": {
- "description": "Най-новият модел GPT-4 Turbo разполага с визуални функции. Сега визуалните заявки могат да се използват с JSON формат и извиквания на функции. GPT-4 Turbo е подобрена версия, която предлага икономически ефективна поддръжка за мултимодални задачи. Той намира баланс между точност и ефективност, подходящ за приложения, изискващи взаимодействие в реално време."
- },
"gpt-4-32k": {
"description": "GPT-4 предлага по-голям контекстуален прозорец, способен да обработва по-дълги текстови входове, подходящ за сценарии, изискващи интеграция на обширна информация и анализ на данни."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "Най-новият модел GPT-4 Turbo разполага с визуални функции. Сега визуалните заявки могат да се използват с JSON формат и извиквания на функции. GPT-4 Turbo е подобрена версия, която предлага икономически ефективна поддръжка за мултимодални задачи. Той намира баланс между точност и ефективност, подходящ за приложения, изискващи взаимодействие в реално време."
},
+ "gpt-4.5-preview": {
+ "description": "Изследователската предварителна версия на GPT-4.5, която е нашият най-голям и мощен GPT модел до момента. Тя притежава обширни знания за света и може по-добре да разбира намеренията на потребителите, което я прави изключително ефективна в креативни задачи и автономно планиране. GPT-4.5 приема текстови и изображен вход и генерира текстови изход (включително структурирани изходи). Поддържа ключови функции за разработчици, като извикване на функции, пакетно API и потоков изход. В задачи, изискващи креативно, открито мислене и диалог (като писане, учене или изследване на нови идеи), GPT-4.5 показва особени способности. Крайната дата на знанията е октомври 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o е динамичен модел, който се актуализира в реално време, за да поддържа най-новата версия. Той комбинира мощно разбиране на езика и генериране на текст, подходящ за мащабни приложения, включително обслужване на клиенти, образование и техническа поддръжка."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o е динамичен модел, който се актуализира в реално време, за да поддържа най-новата версия. Той комбинира мощно разбиране на езика и генериране на текст, подходящ за мащабни приложения, включително обслужване на клиенти, образование и техническа поддръжка."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o е динамичен модел, който се актуализира в реално време, за да поддържа най-новата версия. Той съчетава мощно разбиране и генериране на език и е подходящ за мащабни приложения, включително обслужване на клиенти, образование и техническа поддръжка."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Модел GPT-4o Audio, поддържащ вход и изход на аудио."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini е най-новият модел на OpenAI, след GPT-4 Omni, който поддържа текстово и визуално въвеждане и генерира текст. Като най-напредналият им малък модел, той е значително по-евтин от другите нови модели и е с над 60% по-евтин от GPT-3.5 Turbo. Запазва най-съвременната интелигентност, като същевременно предлага значителна стойност за парите. GPT-4o mini получи 82% на теста MMLU и в момента е с по-висок рейтинг от GPT-4 по предпочитания за чат."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Реален вариант на GPT-4o-mini, поддържащ вход и изход на аудио и текст в реално време."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Реален вариант на GPT-4o, поддържащ вход и изход на аудио и текст в реално време."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Реален вариант на GPT-4o, поддържащ вход и изход на аудио и текст в реално време."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Реален вариант на GPT-4o, поддържащ вход и изход на аудио и текст в реално време."
+ },
+ "grok-2-1212": {
+ "description": "Този модел е подобрен по отношение на точност, спазване на инструкции и многоезични способности."
+ },
+ "grok-2-vision-1212": {
+ "description": "Този модел е подобрен по отношение на точност, спазване на инструкции и многоезични способности."
+ },
+ "grok-beta": {
+ "description": "С производителност, сравнима с Grok 2, но с по-висока ефективност, скорост и функции."
+ },
+ "grok-vision-beta": {
+ "description": "Най-новият модел за разбиране на изображения, способен да обработва разнообразна визуална информация, включително документи, графики, екранни снимки и снимки."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B е езиков модел, който комбинира креативност и интелигентност, обединявайки множество водещи модели."
},
+ "hunyuan-code": {
+ "description": "Най-новият модел за генериране на код на HunYuan, обучен с 200B висококачествени данни за код, с шестмесечно обучение на данни за SFT с високо качество, увеличен контекстен прозорец до 8K, и водещи резултати в автоматичните оценъчни показатели за генериране на код на пет основни езика; в комплексната оценка на кодови задачи на пет основни езика, представянето е в първата група."
+ },
+ "hunyuan-functioncall": {
+ "description": "Най-новият модел на HunYuan с MOE архитектура за извикване на функции, обучен с висококачествени данни за извикване на функции, с контекстен прозорец от 32K, водещ в множество измерения на оценъчните показатели."
+ },
+ "hunyuan-large": {
+ "description": "Моделът Hunyuan-large има общ брой параметри около 389B, активни параметри около 52B, и е най-голямият и най-добър в индустрията отворен MoE модел с архитектура Transformer."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Специализира в обработката на дълги текстови задачи, като резюмета на документи и отговори на въпроси, и също така притежава способността да обработва общи текстови генериращи задачи. Показва отлични резултати в анализа и генерирането на дълги текстове, ефективно справяйки се с комплексни и подробни изисквания за обработка на дълги текстове."
+ },
+ "hunyuan-lite": {
+ "description": "Актуализиран до MOE структура, контекстният прозорец е 256k, водещ в множество оценъчни набори в NLP, код, математика и индустрия, пред много от отворените модели."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Най-новият 7B мултимодален модел на Hunyuan, с контекстен прозорец от 32K, поддържа мултимодални разговори на китайски и английски, разпознаване на обекти в изображения, разбиране на документи и таблици, мултимодална математика и др., с показатели, които надвишават 7B конкурентни модели в множество измерения."
+ },
+ "hunyuan-pro": {
+ "description": "Модел с параметри от триллион MOE-32K за дълги текстове. Постига абсолютни водещи нива в различни бенчмаркове, с комплексни инструкции и разсъждения, притежаващи сложни математически способности, поддържа функция за извикване, с акцент върху оптимизацията в области като многоезичен превод, финанси, право и медицина."
+ },
+ "hunyuan-role": {
+ "description": "Най-новият модел за ролеви игри на HunYuan, официално настроен и обучен от HunYuan, базиран на модела HunYuan и данни от набори за ролеви игри, с по-добри основни резултати в ролевите игри."
+ },
+ "hunyuan-standard": {
+ "description": "Използва по-добра стратегия за маршрутизиране, като същевременно облекчава проблемите с балансирането на натоварването и сближаването на експертите. За дълги текстове, показателят за откритие достига 99.9%. MOE-32K предлага по-добра цена-качество, балансирайки ефективността и цената, и позволява обработка на дълги текстови входове."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Използва по-добра стратегия за маршрутизиране, като същевременно облекчава проблемите с балансирането на натоварването и сближаването на експертите. За дълги текстове, показателят за откритие достига 99.9%. MOE-256K прави допълнителен пробив в дължината и ефективността, значително разширявайки допустимата дължина на входа."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Най-новият мултимодален модел на Hunyuan, поддържащ отговори на множество езици, с балансирани способности на китайски и английски."
+ },
+ "hunyuan-translation": {
+ "description": "Поддържа автоматичен превод между 15 езика, включително китайски, английски, японски, френски, португалски, испански, турски, руски, арабски, корейски, италиански, немски, виетнамски, малайски и индонезийски, базиран на автоматизирана оценка COMET, с цялостна преводна способност, която е по-добра от моделите на пазара с подобен мащаб."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Моделът за превод HunYuan поддържа естествено езиково диалогово превеждане; поддържа автоматичен превод между 15 езика, включително китайски, английски, японски, френски, португалски, испански, турски, руски, арабски, корейски, италиански, немски, виетнамски, малайски и индонезийски."
+ },
+ "hunyuan-turbo": {
+ "description": "Предварителна версия на новото поколение голям езиков модел на HunYuan, използваща нова структура на смесен експертен модел (MoE), с по-бърза скорост на извеждане и по-силни резултати в сравнение с hunyuan-pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Фиксирана версия на hunyuan-turbo от 20 ноември 2024 г., която е между hunyuan-turbo и hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Оптимизация в тази версия: скалиране на данни и инструкции, значително повишаване на общата генерализационна способност на модела; значително повишаване на математическите, кодовите и логическите способности; оптимизиране на свързаните с разбирането на текста и думите способности; оптимизиране на качеството на генерираното съдържание при създаване на текст."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Оптимизация на общото изживяване, включително разбиране на NLP, създаване на текст, разговори, отговори на въпроси, превод и специфични области; повишаване на хуманността, оптимизиране на емоционалната интелигентност на модела; подобряване на способността на модела да изяснява при неясни намерения; повишаване на способността за обработка на въпроси, свързани с анализ на думи; подобряване на качеството и интерактивността на създаването; подобряване на многократното изживяване."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Новото поколение визуално езиково флагманско голямо модел на Hunyuan, използващо нова структура на смесен експертен модел (MoE), с цялостно подобрение на способностите за основно разпознаване, създаване на съдържание, отговори на въпроси и анализ и разсъждение в сравнение с предишното поколение модели."
+ },
+ "hunyuan-vision": {
+ "description": "Най-новият мултимодален модел на HunYuan, поддържащ генериране на текстово съдържание от изображения и текстови входове."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Иновативният отворен модел InternLM2.5 повишава интелигентността на диалога чрез голям брой параметри."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 предлага интелигентни решения за диалог в множество сценарии."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct модел, с 70B параметри, способен да предоставя изключителна производителност в задачи за генериране на текст и инструкции."
+ "internlm2-pro-chat": {
+ "description": "По-стара версия на модела, която все още поддържаме, с налични параметри от 7B и 20B."
+ },
+ "internlm2.5-latest": {
+ "description": "Нашата най-нова серия модели с изключителни способности за извеждане, поддържаща контекстна дължина от 1M и по-силни способности за следване на инструкции и извикване на инструменти."
+ },
+ "internlm3-latest": {
+ "description": "Нашата най-нова серия модели с изключителна производителност на разсъжденията, водеща в категорията на отворените модели. По подразбиране сочи към най-ново публикуваната серия модели InternLM3."
+ },
+ "jina-deepsearch-v1": {
+ "description": "Дълбокото търсене комбинира интернет търсене, четене и разсъждение, за да извърши обширно разследване. Можете да го разглеждате като агент, който приема вашата изследователска задача - той ще извърши широко търсене и ще премине през множество итерации, преди да предостави отговор. Този процес включва непрекъснато изследване, разсъждение и решаване на проблеми от различни ъгли. Това е коренно различно от стандартните големи модели, които генерират отговори директно от предварително обучени данни, и от традиционните RAG системи, които разчитат на еднократни повърхностни търсения."
+ },
+ "kimi-latest": {
+ "description": "Kimi интелигентен асистент използва най-новия Kimi голям модел, който може да съдържа нестабилни функции. Поддържа разбиране на изображения и автоматично избира 8k/32k/128k модел за таксуване в зависимост от дължината на контекста на заявката."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM е експериментален езиков модел, специфичен за задачи, обучен да отговаря на принципите на научното обучение, способен да следва системни инструкции в учебни и обучителни сценарии, да действа като експертен ментор и др."
+ },
+ "lite": {
+ "description": "Spark Lite е лек модел на голям език, с изключително ниска латентност и ефективна обработка, напълно безплатен и отворен, поддържащ функции за онлайн търсене в реално време. Неговите бързи отговори го правят отличен за приложения на нискомощни устройства и фина настройка на модели, предоставяйки на потребителите отлична рентабилност и интелигентно изживяване, особено в контекста на въпроси и отговори, генериране на съдържание и търсене."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B предлага по-мощни способности за разсъждение на AI, подходящи за сложни приложения, поддържащи множество изчислителни обработки и осигуряващи ефективност и точност."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B е модел с висока производителност, предлагащ бързи способности за генериране на текст, особено подходящ за приложения, изискващи мащабна ефективност и икономичност."
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct модел, с 8B параметри, поддържащ ефективно изпълнение на задачи с визуални указания, предлагащ качествени способности за генериране на текст."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Изключителни способности за визуално разсъждение върху изображения с висока разделителна способност, подходящи за приложения за визуално разбиране."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Online модел, с 405B параметри, поддържащ контекстова дължина от около 127,000 маркера, проектиран за сложни онлайн чат приложения."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 е проектиран да обработва задачи, свързващи визуални и текстови данни. Той показва отлични резултати в задачи като описание на изображения и визуални въпроси и отговори, преодолявайки пропастта между генерирането на език и визуалното разсъждение."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chat модел, с 70B параметри, поддържащ контекстова дължина от около 127,000 маркера, подходящ за сложни офлайн чат задачи."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Разширени способности за визуално разсъждение, подходящи за приложения на визуални агенти."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Online модел, с 70B параметри, поддържащ контекстова дължина от около 127,000 маркера, подходящ за задачи с висока капацитет и разнообразие в чата."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 е проектиран да обработва задачи, свързващи визуални и текстови данни. Той показва отлични резултати в задачи като описание на изображения и визуални въпроси и отговори, преодолявайки пропастта между генерирането на език и визуалното разсъждение."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chat модел, с 8B параметри, проектиран за офлайн чат, поддържащ контекстова дължина от около 127,000 маркера."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 е най-напредналият многоезичен отворен езиков модел от серията Llama, който предлага производителност, сравнима с 405B моделите, на изключително ниска цена. Базиран на структурата Transformer и подобрен чрез супервизирано фино настройване (SFT) и обучение с човешка обратна връзка (RLHF) за повишаване на полезността и безопасността. Неговата версия, оптимизирана за инструкции, е специално проектирана за многоезични диалози и показва по-добри резултати от много от отворените и затворените чат модели в множество индустриални бенчмаркове. Краен срок за знания: декември 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Online модел, с 8B параметри, поддържащ контекстова дължина от около 127,000 маркера, проектиран за онлайн чат, способен да обработва ефективно различни текстови взаимодействия."
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 е многоезичен модел за генерация на език (LLM) с 70B (вход/изход на текст), който е предварително обучен и е пригоден за указания. Чистият текстов модел на Llama 3.3 е оптимизиран за многоезични диалогови случаи и надминава много налични отворени и затворени чат модели на стандартни индустриални тестове."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B предлага ненадмината способност за обработка на сложност, проектирана за високи изисквания."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral е проектиран за научни изследвания и математически разсъждения, предоставяйки ефективни изчислителни способности и интерпретация на резултати."
},
+ "max-32k": {
+ "description": "Spark Max 32K е конфигуриран с голяма способност за обработка на контекст, с по-силно разбиране на контекста и логическо разсъждение, поддържащ текстови входове до 32K токена, подходящ за четене на дълги документи, частни въпроси и отговори и други сценарии."
+ },
"meta-llama-3-70b-instruct": {
"description": "Мощен модел с 70 милиарда параметри, отличаващ се в разсъждения, кодиране и широки езикови приложения."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) предлага отлични способности за обработка на език и изключителен интерактивен опит."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 предлага отлични способности за обработка на език и невероятно потребителско изживяване."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) е мощен чат модел, поддържащ сложни изисквания за диалог."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) предлага многоезична поддръжка, обхващаща богати области на знание."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 е проектирана да обработва задачи, комбиниращи визуални и текстови данни. Тя демонстрира отлични резултати в задачи като описание на изображения и визуални въпроси и отговори, преодолявайки пропастта между генерирането на езици и визуалното разсъждение."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 е проектирана да обработва задачи, комбиниращи визуални и текстови данни. Тя демонстрира отлични резултати в задачи като описание на изображения и визуални въпроси и отговори, преодолявайки пропастта между генерирането на езици и визуалното разсъждение."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 е проектирана да обработва задачи, комбиниращи визуални и текстови данни. Тя демонстрира отлични резултати в задачи като описание на изображения и визуални въпроси и отговори, преодолявайки пропастта между генерирането на езици и визуалното разсъждение."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 е най-напредналият многоезичен отворен голям езиков модел от серията Llama, предлагащ производителност, сравнима с 405B моделите на изключително ниска цена. Базиран на структурата Transformer и подобрен чрез супервизирано фино настройване (SFT) и обучение с човешка обратна връзка (RLHF) за повишаване на полезността и безопасността. Неговата версия за оптимизация на инструкции е специално проектирана за многоезични диалози и показва по-добри резултати от много от отворените и затворените чат модели в множество индустриални бенчмаркове. Краен срок за знания: декември 2023 г."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 многоезичен голям езиков модел (LLM) е предварително обучен и коригиран за инструкции в 70B (текстов вход/текстов изход). Моделът Llama 3.3, коригиран за инструкции, е оптимизиран за многоезични диалогови случаи и превъзхожда много налични отворени и затворени чат модели на общи индустриални бенчмаркове."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 е проектирана да обработва задачи, комбиниращи визуални и текстови данни. Тя демонстрира отлични резултати в задачи като описание на изображения и визуални въпроси и отговори, преодолявайки пропастта между генерирането на езици и визуалното разсъждение."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite е подходящ за среди, изискващи висока производителност и ниска латентност."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "405B Llama 3.1 Turbo моделът предлага огромна контекстова поддръжка за обработка на големи данни, с изключителна производителност в приложения с изкуствен интелект с много голям мащаб."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 е водещ модел, представен от Meta, поддържащ до 405B параметри, подходящ за сложни разговори, многоезичен превод и анализ на данни."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B предлага ефективна поддръжка за многоезични диалози."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct е оптимизирана за висококачествени диалогови сценарии, с представяне, надминаващо много затворени модели."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct е най-новата версия на Meta, оптимизирана за генериране на висококачествени диалози, надминаваща много водещи затворени модели."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct е проектиран за висококачествени диалози и показва отлични резултати в човешките оценки, особено подходящ за сценарии с висока интерактивност."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 предлага поддръжка на множество езици и е един от водещите генеративни модели в индустрията."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 е проектиран да обработва задачи, свързващи визуални и текстови данни. Той показва отлични резултати в задачи като описание на изображения и визуални въпроси, преодолявайки пропастта между генерирането на език и визуалното разсъждение."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 е проектиран да обработва задачи, свързващи визуални и текстови данни. Той показва отлични резултати в задачи като описание на изображения и визуални въпроси, преодолявайки пропастта между генерирането на език и визуалното разсъждение."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 е най-напредналият многоезичен отворен езиков модел от серията Llama, който предлага производителност, сравнима с 405B моделите, на изключително ниска цена. Базиран на структурата Transformer и подобрен чрез супервизирано фино настройване (SFT) и обучение с човешка обратна връзка (RLHF) за повишаване на полезността и безопасността. Неговата версия, оптимизирана за инструкции, е специално проектирана за многоезични диалози и показва по-добри резултати от много от отворените и затворените чат модели в множество индустриални бенчмаркове. Краен срок за знания: декември 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 е най-напредналият многоезичен отворен езиков модел от серията Llama, който предлага производителност, сравнима с 405B моделите, на изключително ниска цена. Базиран на структурата Transformer и подобрен чрез супервизирано фино настройване (SFT) и обучение с човешка обратна връзка (RLHF) за повишаване на полезността и безопасността. Неговата версия, оптимизирана за инструкции, е специално проектирана за многоезични диалози и показва по-добри резултати от много от отворените и затворените чат модели в множество индустриални бенчмаркове. Краен срок за знания: декември 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct е най-голямата и най-мощната версия на модела Llama 3.1 Instruct. Това е високо напреднал модел за диалогово разсъждение и генериране на синтетични данни, който може да се използва и като основа за професионално продължително предварително обучение или фино настройване в специфични области. Многоезичният голям езиков модел (LLMs), предоставен от Llama 3.1, е набор от предварително обучени, коригирани по инструкции генеративни модели, включително размери 8B, 70B и 405B (текстов вход/изход). Текстовите модели, коригирани по инструкции (8B, 70B, 405B), са оптимизирани за многоезични диалогови случаи и надминават много налични отворени чат модели в общи индустриални бенчмаркове. Llama 3.1 е проектиран за търговски и изследователски цели на множество езици. Моделите, коригирани по инструкции, са подходящи за чатове, подобни на асистенти, докато предварително обучените модели могат да се адаптират към различни задачи за генериране на естествен език. Моделите на Llama 3.1 също поддържат използването на изхода на модела за подобряване на други модели, включително генериране на синтетични данни и рафиниране. Llama 3.1 е саморегресивен езиков модел, използващ оптимизирана трансформаторна архитектура. Коригираните версии използват супервизирано фино настройване (SFT) и обучение с човешка обратна връзка (RLHF), за да отговорят на предпочитанията на хората за полезност и безопасност."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 е отворен голям езиков модел (LLM), насочен към разработчици, изследователи и предприятия, предназначен да им помогне да изградят, експериментират и отговорно разширят своите идеи за генеративен ИИ. Като част от основната система на глобалната общност за иновации, той е особено подходящ за устройства с ограничени изчислителни ресурси и по-бързо време за обучение."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B е най-новият бърз и лек модел на Microsoft AI, с производителност, близка до 10 пъти на съществуващите водещи отворени модели."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "Напреднал LLM, поддържащ генериране на синтетични данни, дестилация на знания и разсъждение, подходящ за чатботове, програмиране и специфични задачи."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Улеснява сложни разговори, с изключителни способности за разбиране на контекста, разсъждение и генериране на текст."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Напреднал, водещ модел с разбиране на езика, изключителни способности за разсъждение и генериране на текст."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Водещ визуално-езиков модел, специализиран в извършване на висококачествени разсъждения от изображения."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Напреднал, водещ малък езиков модел с разбиране на езика, изключителни способности за разсъждение и генериране на текст."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Напреднал, водещ малък езиков модел с разбиране на езика, изключителни способности за разсъждение и генериране на текст."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Водещ визуално-езиков модел, специализиран в извършване на висококачествени разсъждения от изображения."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Напреднал LLM, специализиран в разсъждения, математика, общи познания и извикване на функции."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 е езиков модел, предоставен от Microsoft AI, който показва особени способности в сложни разговори, многоезичност, разсъждения и интелигентни асистенти."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B е най-напредналият Wizard модел на Microsoft AI, показващ изключителна конкурентоспособност."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V е новото поколение мултимодален голям модел, представен от OpenBMB, който притежава изключителни способности за OCR разпознаване и мултимодално разбиране, поддържащ широк спектър от приложения."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B е световен лидер сред моделите на Mistral."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B е модел на Mistral с отлична цена-качество."
+ },
"mistral": {
"description": "Mistral е 7B модел, представен от Mistral AI, подходящ за променливи нужди в обработката на език."
},
"mistral-large": {
"description": "Mixtral Large е флагманският модел на Mistral, комбиниращ способности за генериране на код, математика и разсъждение, поддържащ контекстен прозорец от 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) е напреднал модел на езика (LLM) с най-съвременни способности за разсъждение, знание и кодиране."
- },
"mistral-large-latest": {
"description": "Mistral Large е флагманският модел, специализиран в многоезични задачи, сложни разсъждения и генериране на код, идеален за висококачествени приложения."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 предлага ефективна изчислителна мощ и разбиране на естествения език, подходяща за широк спектър от приложения."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B е компактен, но високопроизводителен модел, специализиран в обработка на партиди и основни задачи, като класификация и генериране на текст с добри способности за разсъждение."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) е супер голям езиков модел, поддържащ изключително високи изисквания за обработка."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B е предварително обучен модел на разредени смесени експерти, предназначен за универсални текстови задачи."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B е модел с рядък експерт, който използва множество параметри, за да подобри скоростта на разсъждение, подходящ за обработка на многоезични и генериращи код задачи."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct е високопроизводителен индустриален стандартен модел, оптимизиран за бързина и поддръжка на дълги контексти."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K е модел с изключителна способност за обработка на дълги контексти, подходящ за генериране на много дълги текстове, отговарящи на сложни изисквания за генериране, способен да обработва до 128,000 токена, особено подходящ за научни изследвания, академични и генериране на големи документи."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Визуалният модел Kimi (включително moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview и др.) може да разбира съдържанието на изображения, включително текст в изображения, цветове и форми на обекти."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K предлага средна дължина на контекста, способен да обработва 32,768 токена, особено подходящ за генериране на различни дълги документи и сложни диалози, използван в области като създаване на съдържание, генериране на отчети и диалогови системи."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Визуалният модел Kimi (включително moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview и др.) може да разбира съдържанието на изображения, включително текст в изображения, цветове и форми на обекти."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K е проектиран за генериране на кратки текстови задачи, с ефективна производителност, способен да обработва 8,192 токена, особено подходящ за кратки диалози, бележки и бързо генериране на съдържание."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Визуалният модел Kimi (включително moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview и др.) може да разбира съдържанието на изображения, включително текст в изображения, цветове и форми на обекти."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto може да избере подходящ модел в зависимост от количеството токени, заето от текущия контекст."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B е обновена версия на Nous Hermes 2, включваща най-новите вътрешно разработени набори от данни."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B е голям езиков модел, персонализиран от NVIDIA, предназначен да увеличи полезността на отговорите, генерирани от LLM на потребителските запитвания. Моделът показва отлични резултати в бенчмаркове като Arena Hard, AlpacaEval 2 LC и GPT-4-Turbo MT-Bench, като заема първо място в трите автоматизирани теста за подравняване към 1 октомври 2024 г. Моделът е обучен с RLHF (по-специално REINFORCE), Llama-3.1-Nemotron-70B-Reward и HelpSteer2-Preference подсказки на базата на Llama-3.1-70B-Instruct модела."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Уникален езиков модел, предлагащ ненадмината точност и ефективност."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct е персонализиран голям езиков модел на NVIDIA, предназначен да подобри полезността на отговорите, генерирани от LLM."
+ },
+ "o1": {
+ "description": "Фокусиран върху напреднали изводи и решаване на сложни проблеми, включително математически и научни задачи. Изключително подходящ за приложения, изискващи дълбочинно разбиране на контекста и управление на работни потоци."
+ },
"o1-mini": {
"description": "o1-mini е бърз и икономичен модел за изводи, проектиран за приложения в програмирането, математиката и науката. Моделът разполага с контекст от 128K и дата на знание до октомври 2023."
},
"o1-preview": {
"description": "o1 е новият модел за изводи на OpenAI, подходящ за сложни задачи, изискващи обширни общи знания. Моделът разполага с контекст от 128K и дата на знание до октомври 2023."
},
+ "o3-mini": {
+ "description": "o3-mini е нашият най-нов малък модел за инференция, който предлага висока интелигентност при същите разходи и цели за закъснение като o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba е модел на езика Mamba 2, специализиран в генерирането на код, предоставящ мощна поддръжка за напреднали кодови и разсъждателни задачи."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B е рядък експертен модел, който използва множество параметри за увеличаване на скоростта на разсъждение, подходящ за обработка на многоезични и кодови генериращи задачи."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o е динамичен модел, който се актуализира в реално време, за да поддържа най-новата версия. Той комбинира мощни способности за разбиране и генериране на език, подходящи за мащабни приложения, включително обслужване на клиенти, образование и техническа поддръжка."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o е динамичен модел, който се актуализира в реално време, за да поддържа най-новата версия. Той комбинира мощно разбиране на езика и способности за генериране, подходящ за мащабни приложения, включително обслужване на клиенти, образование и техническа поддръжка."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini е най-новият модел на OpenAI, пуснат след GPT-4 Omni, който поддържа вход и изход на текст и изображения. Като най-напредналият им малък модел, той е значително по-евтин от другите нови модели и е с над 60% по-евтин от GPT-3.5 Turbo. Запазва най-съвременната интелигентност, като предлага значителна стойност за парите. GPT-4o mini получи 82% на теста MMLU и в момента е с по-висок рейтинг от GPT-4 в предпочитанията за чат."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Моделът Pixtral демонстрира силни способности в задачи като разбиране на графики и изображения, отговори на документи, многомодално разсъждение и следване на инструкции, способен да приема изображения с естествено разрешение и съотношение на страните, както и да обработва произволен брой изображения в контекстен прозорец с дължина до 128K токена."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large е отворен многомодален модел с 1240 милиарда параметри, базиран на Mistral Large 2. Това е вторият модел в нашето многомодално семейство, който демонстрира авангардни способности за разбиране на изображения."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K е конфигуриран с изключителна способност за обработка на контекст, способен да обработва до 128K контекстна информация, особено подходящ за дълги текстове, изискващи цялостен анализ и дългосрочна логическа свързаност, предоставяйки гладка и последователна логика и разнообразна поддръжка на цитати в сложни текстови комуникации."
+ },
+ "qvq-72b-preview": {
+ "description": "QVQ моделът е експериментален изследователски модел, разработен от екипа на Qwen, фокусиран върху повишаване на визуалните способности за разсъждение, особено в областта на математическото разсъждение."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Модел за кодиране Qwen с общо предназначение."
+ },
"qwen-coder-turbo-latest": {
"description": "Моделът на кода Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Математическият модел Qwen е специално проектиран за решаване на математически задачи."
},
+ "qwen-max": {
+ "description": "通义千问(Qwen) е моделиран на база багатограмния езиков модел с хипотетично ниво на милярд, поддържащ различни езици, включително китайски и английски, и в момента служи като API на продукта версия 2.5 на 通义千问."
+ },
"qwen-max-latest": {
"description": "Qwen Max е езиков модел с мащаб от стотици милиарди параметри, който поддържа вход на различни езици, включително китайски и английски. В момента е основният API модел зад версията на продукта Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "Моделите от серията Qwen-Omni поддържат входни данни от множество модалности, включително видео, аудио, изображения и текст, и генерират аудио и текст."
+ },
+ "qwen-plus": {
+ "description": "通义千问(Qwen) е подобрена версия на мащабен езиков модел, който поддържа вход на различни езици, включително китайски и английски."
+ },
"qwen-plus-latest": {
"description": "Разширената версия на Qwen Turbo е мащабен езиков модел, който поддържа вход на различни езици, включително китайски и английски."
},
+ "qwen-turbo": {
+ "description": "通义千问(Qwen) е мащабен езиков модел, който поддържа вход на различни езици, включително китайски и английски."
+ },
"qwen-turbo-latest": {
"description": "Моделът на езика Qwen Turbo е мащабен езиков модел, който поддържа вход на различни езици, включително китайски и английски."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL поддържа гъвкави интерактивни методи, включително множество изображения, многократни въпроси и отговори, творчество и др."
},
- "qwen-vl-max": {
- "description": "Qwen е мащабен визуален езиков модел. В сравнение с подобрената версия, отново е подобрена способността за визуално разсъждение и следване на инструкции, предоставяйки по-високо ниво на визуално възприятие и познание."
+ "qwen-vl-max-latest": {
+ "description": "Qwen-VL Max е модел за визуален език с изключително голям мащаб. В сравнение с подобрената версия, той отново подобрява способността за визуално разсъждение и следване на инструкции, предоставяйки по-високо ниво на визуално възприятие и познание."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Qwen OCR е специализиран модел за извличане на текст, фокусиран върху способността за извличане на текст от изображения на документи, таблици, тестови въпроси, ръкописен текст и др. Той може да разпознава множество езици, включително: китайски, английски, френски, японски, корейски, немски, руски, италиански, виетнамски и арабски."
},
- "qwen-vl-plus": {
- "description": "Qwen е подобрена версия на мащабния визуален езиков модел. Значително подобрена способност за разпознаване на детайли и текст, поддържа изображения с резолюция над един милион пиксела и произволни съотношения на страните."
+ "qwen-vl-plus-latest": {
+ "description": "Моделят за визуален език Qwen-VL Plus е подобрена версия с голям мащаб. Значително подобрява способността за разпознаване на детайли и текст, поддържа резолюция над милион пиксела и изображения с произволно съотношение на страните."
},
"qwen-vl-v1": {
"description": "Инициализиран с езиковия модел Qwen-7B, добавя модел за изображения, предтренировъчен модел с резолюция на входа от 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 е новата серия големи езикови модели Qwen. Qwen2 7B е модел, базиран на трансформатор, който показва отлични резултати в разбирането на езика, многоезичните способности, програмирането, математиката и разсъжденията."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 е нова серия от големи езикови модели с по-силни способности за разбиране и генериране."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL е най-новата итерация на модела Qwen-VL, постигайки най-съвременни резултати в бенчмарковете за визуално разбиране, включително MathVista, DocVQA, RealWorldQA и MTVQA. Qwen2-VL може да разбира видеа с продължителност над 20 минути, за висококачествени въпроси и отговори, диалози и създаване на съдържание, базирани на видео. Той също така притежава сложни способности за разсъждение и вземане на решения, които могат да се интегрират с мобилни устройства, роботи и др., за автоматични операции на базата на визуална среда и текстови инструкции. Освен английски и китайски, Qwen2-VL сега поддържа и разбиране на текст на различни езици в изображения, включително повечето европейски езици, японски, корейски, арабски и виетнамски."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct е една от най-новите серии големи езикови модели, публикувани от Alibaba Cloud. Този 72B модел има значителни подобрения в области като кодиране и математика. Моделът предлага и многоезична поддръжка, обхващаща над 29 езика, включително китайски и английски. Моделът показва значителни подобрения в следването на инструкции, разбирането на структурирани данни и генерирането на структурирани изходи (особено JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct е една от най-новите серии големи езикови модели, публикувани от Alibaba Cloud. Този 32B модел има значителни подобрения в области като кодиране и математика. Моделът предлага и многоезична поддръжка, обхващаща над 29 езика, включително китайски и английски. Моделът показва значителни подобрения в следването на инструкции, разбирането на структурирани данни и генерирането на структурирани изходи (особено JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM, насочен към китайски и английски, за области като език, програмиране, математика и разсъждение."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "Напреднал LLM, поддържащ генериране на код, разсъждение и корекции, обхващащ основните програмни езици."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Мощен среден модел за код, поддържащ 32K дължина на контекста, специализиран в многоезично програмиране."
+ },
"qwen2": {
"description": "Qwen2 е новото поколение голям езиков модел на Alibaba, предлагащ отлична производителност за разнообразни приложения."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 е новото поколение мащабен езиков модел на Alibaba, който предлага отлична производителност, за да отговори на разнообразни приложни нужди."
+ },
"qwen2.5-14b-instruct": {
"description": "Модел с мащаб 14B, отворен за обществеността от Qwen 2.5."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Qwen2.5 е отворен модел с мащаб 72B."
+ },
"qwen2.5-32b-instruct": {
"description": "Модел с мащаб 32B, отворен за обществеността от Qwen 2.5."
},
@@ -824,13 +1599,16 @@
"description": "Модел с мащаб 7B, отворен за обществеността от Qwen 2.5."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "Отворената версия на модела на кода Qwen."
+ "description": "通义千问(Qwen) е отворен код модел за програмиране."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Отворена версия на модела за кодиране Qwen с общо предназначение."
},
"qwen2.5-coder-7b-instruct": {
"description": "Отворената версия на модела на кода Qwen."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Моделът Qwen-Math притежава силни способности за решаване на математически задачи."
+ "description": "Qwen-Math моделът разполага със силни умения за решаване на математически задачи."
},
"qwen2.5-math-72b-instruct": {
"description": "Моделът Qwen-Math притежава силни способности за решаване на математически задачи."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Моделът Qwen-Math притежава силни способности за решаване на математически задачи."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Подобрение на следването на инструкции, математика, решаване на проблеми и код, повишаване на способността за разпознаване на обекти, поддържа директно точно локализиране на визуални елементи в различни формати, поддържа разбиране на дълги видео файлове (до 10 минути) и локализиране на събития в секунда, може да разбира времеви последователности и скорости, базирано на способности за анализ и локализация, поддържа управление на OS или Mobile агенти, силна способност за извличане на ключова информация и изход в JSON формат, тази версия е 72B, най-силната версия в серията."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Подобрение на следването на инструкции, математика, решаване на проблеми и код, повишаване на способността за разпознаване на обекти, поддържа директно точно локализиране на визуални елементи в различни формати, поддържа разбиране на дълги видео файлове (до 10 минути) и локализиране на събития в секунда, може да разбира времеви последователности и скорости, базирано на способности за анализ и локализация, поддържа управление на OS или Mobile агенти, силна способност за извличане на ключова информация и изход в JSON формат, тази версия е 72B, най-силната версия в серията."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 е новото поколение мащабен езиков модел на Alibaba, който предлага отлична производителност, за да отговори на разнообразни приложни нужди."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 е новото поколение мащабен езиков модел на Alibaba, който предлага отлична производителност, за да отговори на разнообразни приложни нужди."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 е новото поколение мащабен езиков модел на Alibaba, който предлага отлична производителност, за да отговори на разнообразни приложни нужди."
+ },
"qwen2:0.5b": {
"description": "Qwen2 е новото поколение голям езиков модел на Alibaba, предлагащ отлична производителност за разнообразни приложения."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 е новото поколение голям езиков модел на Alibaba, предлагащ отлична производителност за разнообразни приложения."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini е компактен LLM, с производителност над GPT-3.5, предлагащ мощни многоезични способности, поддържащ английски и корейски, предоставяйки ефективно и компактно решение."
+ "qwq": {
+ "description": "QwQ е експериментален изследователски модел, който се фокусира върху подобряване на AI разсъдъчните способности."
+ },
+ "qwq-32b": {
+ "description": "QwQ моделът за изводи, обучен на базата на модела Qwen2.5-32B, значително подобрява способностите си за изводи чрез усилено обучение. Основните показатели на модела, като математически код и други ключови индикатори (AIME 24/25, LiveCodeBench), както и някои общи индикатори (IFEval, LiveBench и др.), достигат нивото на DeepSeek-R1 в пълна версия, като всички показатели значително надвишават тези на DeepSeek-R1-Distill-Qwen-32B, също базиран на Qwen2.5-32B."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) разширява възможностите на Solar Mini, фокусирайки се върху японския език, като същевременно поддържа висока ефективност и отлична производителност на английски и корейски."
+ "qwq-32b-preview": {
+ "description": "QwQ моделът е експериментален изследователски модел, разработен от екипа на Qwen, който се фокусира върху подобряване на AI разсъдъчните способности."
+ },
+ "qwq-plus-latest": {
+ "description": "QwQ моделът за изводи, обучен на базата на модела Qwen2.5, значително подобрява способностите си за изводи чрез усилено обучение. Основните показатели на модела, като математически код и други ключови индикатори (AIME 24/25, LiveCodeBench), както и някои общи индикатори (IFEval, LiveBench и др.), достигат нивото на DeepSeek-R1 в пълна версия."
+ },
+ "r1-1776": {
+ "description": "R1-1776 е версия на модела DeepSeek R1, след обучението, която предоставя непроверена и безпристрастна фактическа информация."
+ },
+ "solar-mini": {
+ "description": "Solar Mini е компактен LLM, който превъзхожда GPT-3.5, с мощни многоезични способности, поддържа английски и корейски, предоставяйки ефективно и компактно решение."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) разширява възможностите на Solar Mini, фокусирайки се върху японския език, като същевременно поддържа висока ефективност и отлично представяне в английския и корейския."
},
"solar-pro": {
"description": "Solar Pro е високоинтелигентен LLM, пуснат от Upstage, фокусиран върху способността за следване на инструкции с един GPU, с IFEval оценка над 80. В момента поддържа английски, а официалната версия е планирана за пускане през ноември 2024 г., с разширена поддръжка на езици и дължина на контекста."
},
+ "sonar": {
+ "description": "Лек продукт за търсене, базиран на контекст на търсене, по-бърз и по-евтин от Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research извършва задълбочени експертни изследвания и ги обобщава в достъпни и приложими доклади."
+ },
+ "sonar-pro": {
+ "description": "Разширен продукт за търсене, който поддържа контекст на търсене, напреднали запитвания и проследяване."
+ },
+ "sonar-reasoning": {
+ "description": "Нови API продукти, поддържани от модела за разсъждение на DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Нов API продукт, поддържан от модела за разсъждение DeepSeek."
+ },
"step-1-128k": {
"description": "Баланс между производителност и разходи, подходящ за общи сценарии."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Бърз модел, подходящ за реални диалози."
},
+ "step-1.5v-mini": {
+ "description": "Този модел разполага с мощни способности за разбиране на видео."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Този модел разполага с мощни способности за разбиране на изображения и е по-добър от 1o в областта на математиката и кода. Моделът е по-малък от 1o и предлага по-бърза скорост на изход."
+ },
+ "step-1o-vision-32k": {
+ "description": "Този модел разполага с мощни способности за разбиране на изображения. В сравнение с моделите от серията step-1v, предлага по-силна визуална производителност."
+ },
"step-1v-32k": {
"description": "Поддържа визуални входове, подобряваща мултимодалното взаимодействие."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Поддържа взаимодействия с голям мащаб на контекста, подходящи за сложни диалогови сценарии."
},
+ "step-2-mini": {
+ "description": "Модел с бърза производителност, базиран на новото поколение собствена архитектура Attention MFA, който постига резултати, подобни на step1 с много ниски разходи, като същевременно поддържа по-висока производителност и по-бързо време за отговор. Може да обработва общи задачи и притежава специализирани умения в кодирането."
+ },
"taichu_llm": {
"description": "Моделът на езика TaiChu е с изключителни способности за разбиране на езика, текстово генериране, отговори на знания, програмиране, математически изчисления, логическо разсъждение, анализ на емоции, резюмиране на текст и др. Иновативно комбинира предварително обучение с големи данни и разнообразни източници на знания, чрез непрекъснато усъвършенстване на алгоритмичните технологии и усвояване на нови знания от масивни текстови данни, за да осигури на потребителите по-удобна информация и услуги, както и по-интелигентно изживяване."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V обединява способности за разбиране на изображения, прехвърляне на знания, логическо обяснение и др., и се представя отлично в областта на въпросите и отговорите на текст и изображения."
+ "taichu_vl": {
+ "description": "Съчетава способности за разбиране на изображения, прехвърляне на знания и логическо обяснение, като показва отлични резултати в областта на въпросите и отговорите с текст и изображения."
+ },
+ "text-embedding-3-large": {
+ "description": "Най-мощният модел за векторизация, подходящ за английски и неанглийски задачи."
+ },
+ "text-embedding-3-small": {
+ "description": "Ефективен и икономичен ново поколение модел за вграждане, подходящ за извличане на знания, RAG приложения и други сценарии."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "GLM-4 е последната версия на предварително обучен модел от серията, публикувана от Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) предлага подобрена изчислителна мощ чрез ефективни стратегии и архитектура на модела."
},
+ "tts-1": {
+ "description": "Най-новият модел за текст в реч, оптимизиран за скорост в реални сценарии."
+ },
+ "tts-1-hd": {
+ "description": "Най-новият модел за текст в реч, оптимизиран за качество."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) е подходящ за прецизни задачи с инструкции, предлагащи отлични способности за обработка на език."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet повишава индустриалните стандарти, с производителност, надминаваща конкурентните модели и Claude 3 Opus, показвайки отлични резултати в широк спектър от оценки, като същевременно предлага скорост и разходи, сравними с нашите модели от средно ниво."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 сонет е най-бързият модел от следващото поколение на Anthropic. В сравнение с Claude 3 Haiku, Claude 3.7 Сонет е подобрен във всички умения и надминава най-големия модел от предишното поколение Claude 3 Opus в много интелектуални тестове."
+ },
+ "whisper-1": {
+ "description": "Универсален модел за разпознаване на реч, поддържащ многоезично разпознаване на реч, превод на реч и разпознаване на езици."
+ },
"wizardlm2": {
"description": "WizardLM 2 е езиков модел, предоставен от Microsoft AI, който се отличава в сложни диалози, многоезичност, разсъждение и интелигентни асистенти."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Изключителна производителност на висока цена. Балансирано прецизно настройване на производителността и скоростта на разсъжденията."
},
+ "yi-lightning": {
+ "description": "Най-новият високо производителен модел, който гарантира висококачествени изходи, докато значително ускорява времето за разсъждение."
+ },
+ "yi-lightning-lite": {
+ "description": "Лека версия, препоръчително е да се използва yi-lightning."
+ },
"yi-medium": {
"description": "Модел с среден размер, обновен и прецизно настроен, с балансирани способности и висока цена на производителност."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Модел за сложни визуални задачи, предлагащ висока производителност за разбиране и анализ на изображения."
+ },
+ "yi-vision-v2": {
+ "description": "Модел за сложни визуални задачи, предлагащ висока производителност в разбирането и анализа на базата на множество изображения."
}
}
diff --git a/DigitalHumanWeb/locales/bg-BG/plugin.json b/DigitalHumanWeb/locales/bg-BG/plugin.json
index 6b3ded8..1659599 100644
--- a/DigitalHumanWeb/locales/bg-BG/plugin.json
+++ b/DigitalHumanWeb/locales/bg-BG/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Неуспешно опресняване на плъгина {{name}}",
"urlError": "Връзката не върна съдържание във формат JSON. Моля, уверете се, че е валидна връзка."
},
+ "inspector": {
+ "args": "Преглед на списъка с параметри",
+ "pluginRender": "Преглед на интерфейса на плъгина"
+ },
"list": {
"item": {
"deprecated.title": "Изтрит",
@@ -130,6 +134,34 @@
"plugin": "Плъгинът работи..."
},
"pluginList": "Списък с плъгини",
+ "search": {
+ "config": {
+ "addKey": "Добавяне на ключ",
+ "close": "Изтриване",
+ "confirm": "Конфигурацията е завършена и опитайте отново"
+ },
+ "crawPages": {
+ "crawling": "Разпознаване на връзки",
+ "detail": {
+ "preview": "Преглед",
+ "raw": "Оригинален текст",
+ "tooLong": "Текстът е твърде дълъг, контекстът на разговора ще запази само първите {{characters}} символа, а останалата част няма да бъде включена в контекста на разговора"
+ },
+ "meta": {
+ "crawler": "Режим на улавяне",
+ "words": "Брой символи"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Моля, въведете",
+ "description": "Моля, въведете URL адреса на SearchXNG, за да започнете търсене в мрежата",
+ "keyPlaceholder": "Моля, въведете ключ",
+ "title": "Конфигуриране на търсачката SearchXNG",
+ "unconfiguredDesc": "Моля, свържете се с администратора, за да завършите конфигурацията на търсачката SearchXNG и да започнете търсене в мрежата",
+ "unconfiguredTitle": "Търсачката SearchXNG все още не е конфигурирана"
+ },
+ "title": "Търсене в мрежата"
+ },
"setting": "Настройки на плъгина",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/bg-BG/portal.json b/DigitalHumanWeb/locales/bg-BG/portal.json
index da254d0..2bcea8d 100644
--- a/DigitalHumanWeb/locales/bg-BG/portal.json
+++ b/DigitalHumanWeb/locales/bg-BG/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Плъгини",
- "actions": {
- "genAiMessage": "Създаване на съобщение на помощника",
- "summary": "Обобщение",
- "summaryTooltip": "Обобщение на текущото съдържание"
- },
"artifacts": {
"display": {
"code": "Код",
diff --git a/DigitalHumanWeb/locales/bg-BG/providers.json b/DigitalHumanWeb/locales/bg-BG/providers.json
index 3dc565a..eff27f7 100644
--- a/DigitalHumanWeb/locales/bg-BG/providers.json
+++ b/DigitalHumanWeb/locales/bg-BG/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs изгражда основни модели и системи за изкуствен интелект за предприятия, ускорявайки приложението на генеративния изкуствен интелект в производството."
+ },
"ai360": {
"description": "360 AI е платформа за AI модели и услуги, предлагана от компания 360, предлагаща множество напреднали модели за обработка на естествен език, включително 360GPT2 Pro, 360GPT Pro, 360GPT Turbo и 360GPT Turbo Responsibility 8K. Тези модели комбинират голям брой параметри и мултимодални способности, широко използвани в текстово генериране, семантично разбиране, диалогови системи и генериране на код. Чрез гъвкава ценова стратегия, 360 AI отговаря на разнообразни потребителски нужди, поддържайки интеграция за разработчици и насърчавайки иновации и развитие на интелигентни приложения."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure предлага разнообразие от напреднали AI модели, включително GPT-3.5 и най-новата серия GPT-4, поддържащи различни типове данни и сложни задачи, с акцент върху безопасни, надеждни и устойчиви AI решения."
},
+ "azureai": {
+ "description": "Azure предлага множество напреднали AI модели, включително GPT-3.5 и най-новата серия GPT-4, които поддържат различни типове данни и сложни задачи, ангажирани с безопасни, надеждни и устойчиви AI решения."
+ },
"baichuan": {
"description": "Baichuan Intelligence е компания, специализирана в разработката на големи модели за изкуствен интелект, чийто модели показват отлични резултати в китайски задачи, свързани с енциклопедии, обработка на дълги текстове и генериране на съдържание, надминавайки основните чуждестранни модели. Baichuan Intelligence също така притежава индустриално водещи мултимодални способности, показвайки отлични резултати в множество авторитетни оценки. Моделите им включват Baichuan 4, Baichuan 3 Turbo и Baichuan 3 Turbo 128k, оптимизирани за различни приложения, предлагащи решения с висока цена-качество."
},
"bedrock": {
"description": "Bedrock е услуга, предоставяна от Amazon AWS, фокусирана върху предоставянето на напреднали AI езикови и визуални модели за предприятия. Семейството на моделите включва серията Claude на Anthropic, серията Llama 3.1 на Meta и други, обхващащи разнообразие от опции от леки до високо производителни, поддържащи текстово генериране, диалог, обработка на изображения и много други задачи, подходящи за различни мащаби и нужди на бизнес приложения."
},
+ "cloudflare": {
+ "description": "Работа с модели на машинно обучение, задвижвани от безсървърни GPU, в глобалната мрежа на Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek е компания, специализирана в изследвания и приложения на технологии за изкуствен интелект, чийто най-нов модел DeepSeek-V2.5 комбинира способности за общи диалози и обработка на код, постигайки значителни подобрения в съответствието с човешките предпочитания, писателските задачи и следването на инструкции."
},
+ "doubao": {
+ "description": "Модел, разработен от ByteDance. Проверен в над 50 бизнес сценария в рамките на компанията, с ежедневна употреба на триллиони токени, който продължава да се усъвършенства, предоставяйки множество модални възможности и създавайки богато бизнес изживяване с висококачествени модели."
+ },
"fireworksai": {
"description": "Fireworks AI е водещ доставчик на напреднали езикови модели, фокусирайки се върху извикване на функции и мултимодална обработка. Най-новият им модел Firefunction V2, базиран на Llama-3, е оптимизиран за извикване на функции, диалози и следване на инструкции. Визуалният езиков модел FireLLaVA-13B поддържа смесени входове от изображения и текст. Други забележителни модели включват серията Llama и серията Mixtral, предлагащи ефективна поддръжка за многоезично следване на инструкции и генериране."
},
+ "giteeai": {
+ "description": "Безсървърният API на Гити ИИ предоставя на разработчиците ИИ услугата за извеждане на голям модел."
+ },
"github": {
"description": "С моделите на GitHub разработчиците могат да станат AI инженери и да изграждат с водещите AI модели в индустрията."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Инженерният двигател LPU на Groq показва изключителни резултати в последните независими тестове на големи езикови модели (LLM), преосмисляйки стандартите за AI решения с невероятната си скорост и ефективност. Groq е представител на мигновен скорост на изводите, демонстрирайки добро представяне в облачни внедрения."
},
+ "higress": {
+ "description": "Higress е облачно роден API шлюз, създаден в Alibaba, за да реши проблемите с Tengine reload, които вредят на дългосрочните връзки, и недостатъчните възможности за баланс на натоварването на gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API предлагава бърз и безплатен начин да изследвате хиляди модели, подходящи за различни задачи. Независимо дали проектирате прототип за ново приложение, или опитвате функционалността на машинното обучение, този API ви предоставя незабавен достъп до високопроизводителни модели в множество области."
+ },
+ "hunyuan": {
+ "description": "Модел на голям език, разработен от Tencent, който притежава мощни способности за създаване на текст на китайски, логическо разсъждение в сложни контексти и надеждни способности за изпълнение на задачи."
+ },
+ "internlm": {
+ "description": "Отворена организация, посветена на изследването и разработването на инструменти за големи модели. Предоставя на всички AI разработчици ефективна и лесна за използване отворена платформа, която прави най-съвременните технологии и алгоритми за големи модели достъпни."
+ },
+ "jina": {
+ "description": "Jina AI е основана през 2020 г. и е водеща компания в областта на търсенето с AI. Нашата платформа за търсене включва векторни модели, реорганизатори и малки езикови модели, които помагат на предприятията да изградят надеждни и висококачествени генеративни AI и мултимодални приложения за търсене."
+ },
+ "lmstudio": {
+ "description": "LM Studio е настолно приложение за разработка и експериментиране с LLMs на вашия компютър."
+ },
"minimax": {
"description": "MiniMax е компания за универсален изкуствен интелект, основана през 2021 г., която се стреми да създаде интелигентност заедно с потребителите. MiniMax е разработила различни универсални големи модели, включително текстови модели с трилйон параметри, модели за глас и модели за изображения. Също така е пуснала приложения като Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI е платформа, предлагаща API услуги за множество големи езикови модели и генериране на AI изображения, гъвкава, надеждна и икономически ефективна. Поддържа най-новите отворени модели, като Llama3 и Mistral, и предлага цялостни, потребителски приятелски и автоматично разширяеми API решения за разработка на генеративни AI приложения, подходящи за бързото развитие на AI стартъпи."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ предлага контейнери, които могат да се използват за самостоятелно хоствани GPU ускорени инференционни микросервизи, поддържащи разгръщането на предварително обучени и персонализирани AI модели в облака, центрове за данни, RTX™ AI персонални компютри и работни станции."
+ },
"ollama": {
"description": "Моделите, предоставени от Ollama, обхващат широк спектър от области, включително генериране на код, математически операции, многоезично обработване и диалогова интеракция, отговарящи на разнообразните нужди на предприятията и локализирани внедрявания."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity е водещ доставчик на модели за генериране на диалози, предлагащ множество напреднали модели Llama 3.1, поддържащи онлайн и офлайн приложения, особено подходящи за сложни задачи по обработка на естествен език."
},
+ "ppio": {
+ "description": "PPIO ПайОу облак предлага стабилни и икономически изгодни API услуги за отворени модели, поддържащи цялата серия DeepSeek, Llama, Qwen и други водещи модели в индустрията."
+ },
"qwen": {
"description": "Qwen е самостоятелно разработен свръхголям езиков модел на Alibaba Cloud, с мощни способности за разбиране и генериране на естествен език. Може да отговаря на различни въпроси, да създава текстово съдържание, да изразява мнения и да пише код, играейки роля в множество области."
},
+ "sambanova": {
+ "description": "SambaNova Cloud позволява на разработчиците лесно да използват най-добрите отворени модели и да се наслаждават на най-бързата скорост на извеждане."
+ },
+ "sensenova": {
+ "description": "SenseNova, с мощната основа на SenseTime, предлага ефективни и лесни за използване услуги за големи модели с пълен стек."
+ },
"siliconcloud": {
"description": "SiliconFlow се стреми да ускори AGI, за да бъде от полза за човечеството, повишавайки ефективността на мащабния AI чрез лесен за използване и икономически изгоден GenAI стек."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "Институтът по автоматизация на Китайската академия на науките и Институтът по изкуствен интелект в Ухан представят ново поколение мултимодални големи модели, поддържащи многократни въпроси и отговори, текстово създаване, генериране на изображения, 3D разбиране, анализ на сигнали и др., с по-силни способности за познание, разбиране и създаване, предоставяйки ново взаимодействие."
},
+ "tencentcloud": {
+ "description": "Атомни способности на знаниевия двигател (LLM Knowledge Engine Atomic Power) са базирани на разработката на знаниевия двигател и предлагат пълна верига от способности за въпроси и отговори, насочени към предприятия и разработчици, предоставяйки гъвкави възможности за изграждане и разработка на моделни приложения. Можете да изградите собствена моделна услуга чрез множество атомни способности, като използвате услуги за анализ на документи, разделяне, вграждане, многократни пренаписвания и др., за да персонализирате AI бизнеса, специфичен за вашето предприятие."
+ },
"togetherai": {
"description": "Together AI се стреми да постигне водеща производителност чрез иновационни AI модели, предлагащи широки възможности за персонализация, включително бърза поддръжка за разширяване и интуитивни процеси на внедряване, отговарящи на разнообразните нужди на предприятията."
},
"upstage": {
"description": "Upstage се фокусира върху разработването на AI модели за различни бизнес нужди, включително Solar LLM и документен AI, с цел постигане на човешки универсален интелект (AGI). Създава прости диалогови агенти чрез Chat API и поддържа извикване на функции, превод, вграждане и специфични приложения."
},
+ "vertexai": {
+ "description": "Серията Gemini на Google е най-напредналият и универсален AI модел, създаден от Google DeepMind, проектиран за мултимодалност, който поддържа безпроблемно разбиране и обработка на текст, код, изображения, аудио и видео. Подходящ за различни среди, от центрове за данни до мобилни устройства, значително увеличава ефективността и приложимостта на AI моделите."
+ },
+ "vllm": {
+ "description": "vLLM е бърза и лесна за използване библиотека за LLM инференция и услуги."
+ },
+ "volcengine": {
+ "description": "Платформа за разработка на услуги с големи модели, пусната от ByteDance, предлагаща богати на функции, безопасни и конкурентни по цена услуги за извикване на модели. Освен това предоставя край до край функции като данни за модели, фина настройка, инференция и оценка, за да осигури всестранна подкрепа за разработката на вашите AI приложения."
+ },
+ "wenxin": {
+ "description": "Платформа за разработка и услуги на корпоративно ниво, предлагаща цялостно решение за разработка на генеративни модели на изкуствен интелект и приложения, с най-пълния и лесен за използване инструментариум за целия процес на разработка на модели и приложения."
+ },
+ "xai": {
+ "description": "xAI е компания, която се стреми да изгражда изкуствен интелект за ускоряване на човешките научни открития. Нашата мисия е да насърчаваме общото ни разбиране за вселената."
+ },
"zeroone": {
"description": "01.AI се фокусира върху технологии за изкуствен интелект от ерата на AI 2.0, активно насърчавайки иновации и приложения на \"човек + изкуствен интелект\", използвайки мощни модели и напреднали AI технологии за повишаване на производителността на човека и реализиране на технологично овластяване."
},
diff --git a/DigitalHumanWeb/locales/bg-BG/setting.json b/DigitalHumanWeb/locales/bg-BG/setting.json
index 65b74e6..a686366 100644
--- a/DigitalHumanWeb/locales/bg-BG/setting.json
+++ b/DigitalHumanWeb/locales/bg-BG/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Конфигурация на персонализиран модел",
"tokens": {
- "title": "Максимален брой токени",
- "unlimited": "неограничен"
+ "title": "Максимален брой токени"
},
"vision": {
"extra": "Тази конфигурация ще активира само настройките за качване на изображения в приложението. Поддръжката на разпознаване зависи изцяло от самия модел, моля, тествайте наличността на визуалната разпознаваемост на този модел.",
@@ -98,6 +97,7 @@
"title": "Използване на режим на заявка от клиента"
},
"fetcher": {
+ "clear": "Изчисти получената модел",
"fetch": "Изтегляне на списъка с модели",
"fetching": "Изтегляне на списъка с модели...",
"latestTime": "Последно актуализирано: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Дали да се създава автоматично тема по време на разговора, ефективно само във временни теми",
"title": "Автоматично създаване на тема"
},
- "enableCompressThreshold": {
- "title": "Активиране на прага на компресия на дължината на съобщенията в историята"
+ "enableCompressHistory": {
+ "title": "Активиране на автоматично обобщаване на историята на съобщенията"
},
"enableHistoryCount": {
"alias": "Неограничен",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Активиране на ограничението за максимален брой токени"
},
+ "enableReasoningEffort": {
+ "title": "Активиране на настройките за интензивност на разсъжденията"
+ },
"frequencyPenalty": {
- "desc": "Колкото по-висока е стойността, толкова по-вероятно е да се намалят повтарящите се думи",
- "title": "Наказание за честота"
+ "desc": "Колкото по-голяма е стойността, толкова по-богат и разнообразен е речникът; колкото по-ниска е стойността, толкова по-прост и обикновен е речникът.",
+ "title": "Богатство на речника"
},
"maxTokens": {
"desc": "Максималният брой токени, използвани за всяко взаимодействие",
@@ -212,19 +215,31 @@
"desc": "{{provider}} модел",
"title": "Модел"
},
+ "params": {
+ "title": "Разширени параметри"
+ },
"presencePenalty": {
- "desc": "Колкото по-висока е стойността, толкова по-вероятно е да се разшири до нови теми",
- "title": "Свежест на темата"
+ "desc": "Колкото по-голяма е стойността, толкова по-склонен е към различни изрази, избягвайки повторение на концепции; колкото по-ниска е стойността, толкова по-склонен е да използва повторение на концепции или разкази, изразявайки по-голяма последователност.",
+ "title": "Разнообразие на изразите"
+ },
+ "reasoningEffort": {
+ "desc": "Колкото по-висока е стойността, толкова по-силна е способността за разсъждение, но може да увеличи времето за отговор и консумацията на токени",
+ "options": {
+ "high": "Висока",
+ "low": "Ниска",
+ "medium": "Средна"
+ },
+ "title": "Интензивност на разсъжденията"
},
"temperature": {
- "desc": "Колкото по-висока е стойността, толкова по-случаен е отговорът",
- "title": "Случайност",
- "titleWithValue": "Случайност {{value}}"
+ "desc": "Колкото по-голямо е числото, толкова по-креативни и въображаеми са отговорите; колкото по-малко е числото, толкова по-строги са отговорите",
+ "title": "Креативна активност",
+ "warning": "Ако стойността на креативната активност е твърде голяма, изходът може да съдържа грешки"
},
"title": "Настройки на модела",
"topP": {
- "desc": "Подобно на случайността, но не се променя заедно със случайността",
- "title": "Top P вземане на проби"
+ "desc": "Колко възможности да се вземат предвид, по-голямата стойност приема повече възможни отговори; по-малката стойност предпочита най-вероятния отговор. Не се препоръчва да се променя заедно с креативната активност",
+ "title": "Отвореност на мисленето"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Модел, определен за генериране на име, описание, профилна снимка и етикети на помощник",
"title": "Автоматично генериране на информация за помощник"
},
+ "customPrompt": {
+ "addPrompt": "Добавяне на персонализиран подканва",
+ "desc": "След попълване, системният асистент ще използва персонализираната подканва при генериране на съдържание",
+ "placeholder": "Моля, въведете персонализирана подканва",
+ "title": "Персонализирана подканва"
+ },
+ "historyCompress": {
+ "label": "Модел на история на сесията",
+ "modelDesc": "Определете модела, използван за компресиране на историята на сесията",
+ "title": "Автоматично обобщаване на историята на сесията"
+ },
"queryRewrite": {
"label": "Модел за пренаписване на запитвания",
"modelDesc": "Определя модел за оптимизиране на запитванията на потребителите",
- "title": "База знания"
+ "title": "Пренаписване на въпроси от базата данни"
+ },
+ "thread": {
+ "label": "Модел за именуване на подтеми",
+ "modelDesc": "Модел, предназначен за автоматично преименуване на подтеми",
+ "title": "Автоматично именуване на подтеми"
},
"title": "Системен асистент",
"topic": {
@@ -395,6 +426,7 @@
"common": "Общи настройки",
"experiment": "Експеримент",
"llm": "Езиков модел",
+ "provider": "AI доставчик",
"sync": "Синхронизиране в облака",
"system-agent": "Системен асистент",
"tts": "Текст към реч"
diff --git a/DigitalHumanWeb/locales/bg-BG/thread.json b/DigitalHumanWeb/locales/bg-BG/thread.json
new file mode 100644
index 0000000..cff1f89
--- /dev/null
+++ b/DigitalHumanWeb/locales/bg-BG/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Ще изтриете тази подтема. След изтриването ѝ няма да може да бъде възстановена, моля, бъдете внимателни."
+ },
+ "newPortalThread": {
+ "includeContext": "Включи контекста на темата",
+ "title": "Създаване на нова подтема"
+ },
+ "notSupportMultiModals": "Подтемите в момента не поддържат качване на файлове/снимки. Ако имате нужда, моля, оставете съобщение: <1>💬 Дискусионен форум1>"
+}
diff --git a/DigitalHumanWeb/locales/bg-BG/tool.json b/DigitalHumanWeb/locales/bg-BG/tool.json
index 0f7f661..5591223 100644
--- a/DigitalHumanWeb/locales/bg-BG/tool.json
+++ b/DigitalHumanWeb/locales/bg-BG/tool.json
@@ -6,5 +6,23 @@
"generating": "Генериране...",
"images": "Изображения:",
"prompt": "подсказка"
+ },
+ "search": {
+ "createNewSearch": "Създаване на нова търсене",
+ "emptyResult": "Не са намерени резултати, моля, променете ключовите думи и опитайте отново",
+ "genAiMessage": "Създаване на съобщение от асистент",
+ "includedTooltip": "Текущите резултати от търсенето ще бъдат включени в контекста на сесията",
+ "keywords": "Ключови думи:",
+ "scoreTooltip": "Степен на релевантност, колкото по-висок е този резултат, толкова по-релевантен е спрямо ключовите думи",
+ "searchBar": {
+ "button": "Търсене",
+ "placeholder": "Ключови думи",
+ "tooltip": "Ще се извлекат отново резултатите от търсенето и ще се създаде ново резюме"
+ },
+ "searchEngine": "Търсачка:",
+ "searchResult": "Брой резултати:",
+ "summary": "Резюме",
+ "summaryTooltip": "Резюме на текущото съдържание",
+ "viewMoreResults": "Вижте още {{results}} резултата"
}
}
diff --git a/DigitalHumanWeb/locales/bg-BG/topic.json b/DigitalHumanWeb/locales/bg-BG/topic.json
new file mode 100644
index 0000000..9148946
--- /dev/null
+++ b/DigitalHumanWeb/locales/bg-BG/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Автоматично преименуване",
+ "confirmRemoveAll": "Ще бъдат изтрити всички теми. След изтриването им не може да се възстановят. Моля, действайте внимателно.",
+ "confirmRemoveTopic": "Ще бъде изтрита тази тема. След изтриването ѝ не може да се възстанови. Моля, действайте внимателно.",
+ "confirmRemoveUnstarred": "Ще бъдат изтрити темите, които не са запазени. След изтриването им не може да се възстановят. Моля, действайте внимателно.",
+ "duplicate": "Създаване на копие",
+ "export": "Експортиране на темата",
+ "removeAll": "Изтриване на всички теми",
+ "removeUnstarred": "Изтриване на незапазените теми"
+ },
+ "defaultTitle": "По подразбиране тема",
+ "duplicateLoading": "Копиране на темата...",
+ "duplicateSuccess": "Темата е копирана успешно",
+ "favorite": "Запазено",
+ "groupMode": {
+ "ascMessages": "По ред на общия брой съобщения",
+ "byTime": "Групирано по време",
+ "descMessages": "По ред на общия брой съобщения (обратен)",
+ "flat": "Без групиране"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Този месец",
+ "today": "Днес",
+ "week": "Тази седмица",
+ "yesterday": "Вчера"
+ }
+ },
+ "guide": {
+ "desc": "Кликнете върху бутона отляво за изпращане, за да запазите текущия разговор като историческа тема и да започнете нова сесия.",
+ "title": "Списък с теми"
+ },
+ "searchPlaceholder": "Търсене на теми...",
+ "searchResultEmpty": "Няма намерени резултати",
+ "temp": "Временен",
+ "title": "Тема"
+}
diff --git a/DigitalHumanWeb/locales/bg-BG/welcome.json b/DigitalHumanWeb/locales/bg-BG/welcome.json
index 30a0add..aea3ff2 100644
--- a/DigitalHumanWeb/locales/bg-BG/welcome.json
+++ b/DigitalHumanWeb/locales/bg-BG/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Импортирай конфигурация",
- "market": "Пазар",
- "start": "Започни сега"
- },
"guide": {
"agents": {
"replaceBtn": "Смени",
diff --git a/DigitalHumanWeb/locales/de-DE/auth.json b/DigitalHumanWeb/locales/de-DE/auth.json
index 7d6a7d8..979d0ad 100644
--- a/DigitalHumanWeb/locales/de-DE/auth.json
+++ b/DigitalHumanWeb/locales/de-DE/auth.json
@@ -1,8 +1,96 @@
{
- "login": "Anmelden",
- "loginOrSignup": "Anmelden / Registrieren",
- "profile": "Profil",
- "security": "Sicherheit",
- "signout": "Abmelden",
- "signup": "Registrieren"
+ "date": {
+ "prevMonth": "Letzter Monat",
+ "recent30Days": "Letzte 30 Tage"
+ },
+ "header": {
+ "desc": "Verwalten Sie Ihre Kontoinformationen.",
+ "title": "Konto"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Inaktiv",
+ "more": "Aktiv"
+ },
+ "months": {
+ "apr": "Apr",
+ "aug": "Aug",
+ "dec": "Dez",
+ "feb": "Feb",
+ "jan": "Jan",
+ "jul": "Jul",
+ "jun": "Jun",
+ "mar": "Mär",
+ "may": "Mai",
+ "nov": "Nov",
+ "oct": "Okt",
+ "sep": "Sep"
+ },
+ "tooltip": "{{date}} hat {{count}} Nachrichten an diesem Tag gesendet",
+ "totalCount": "Insgesamt wurden {{count}} Nachrichten im letzten Jahr gesendet"
+ },
+ "login": "Einloggen",
+ "loginOrSignup": "Einloggen / Registrieren",
+ "profile": {
+ "avatar": "Avatar",
+ "email": "E-Mail-Adresse",
+ "sso": {
+ "loading": "Laden der verknüpften Drittanbieter-Konten",
+ "providers": "Verbundene Konten",
+ "unlink": {
+ "description": "Wenn Sie die Verknüpfung aufheben, können Sie sich nicht mehr mit dem {{provider}}-Konto „{{providerAccountId}}“ anmelden. Wenn Sie das {{provider}}-Konto erneut mit dem aktuellen Konto verknüpfen möchten, stellen Sie bitte sicher, dass die E-Mail-Adresse des {{provider}}-Kontos {{email}} ist, und wir werden es Ihnen automatisch bei der Anmeldung mit dem aktuellen Konto zuordnen.",
+ "forbidden": "Sie müssen mindestens ein Drittanbieter-Konto verbunden behalten.",
+ "title": "Möchten Sie das Drittanbieter-Konto {{provider}} wirklich trennen?"
+ }
+ },
+ "username": "Benutzername"
+ },
+ "signout": "Ausloggen",
+ "signup": "Registrieren",
+ "stats": {
+ "aiheatmaps": "Aktivitätsindex",
+ "assistants": "Assistenten",
+ "assistantsRank": {
+ "left": "Assistent",
+ "right": "Themen",
+ "title": "Rang der Assistentennutzung"
+ },
+ "createdAt": "Registriert am",
+ "days": "Tage",
+ "empty": {
+ "desc": "Bitte sammeln Sie mehr Chatdaten, um sie anzuzeigen",
+ "title": "Keine Daten"
+ },
+ "lastYearActivity": "Aktivität im letzten Jahr",
+ "loginGuide": {
+ "f1": "Kostenlose Nutzung erhalten",
+ "f2": "Nachrichten auf mehreren Geräten synchronisieren",
+ "f3": "Überreiche Assistenten nutzen",
+ "f4": "Mächtige Plugins erkunden",
+ "title": "Nach dem Login kannst du:"
+ },
+ "messages": "Nachrichten",
+ "modelsRank": {
+ "left": "Modell",
+ "right": "Nachrichten",
+ "title": "Rang der Modellenutzung"
+ },
+ "share": {
+ "title": "Mein AI Aktivitätsindex"
+ },
+ "topics": "Themen",
+ "topicsRank": {
+ "left": "Thema",
+ "right": "Nachrichten",
+ "title": "Rang des Themeninhalts"
+ },
+ "updatedAt": "Aktualisiert am",
+ "welcome": "{{username}}, dies ist Ihr {{days}} Tag mit {{appName}}",
+ "words": "Wörter"
+ },
+ "tab": {
+ "profile": "Profil",
+ "security": "Sicherheit",
+ "stats": "Statistiken"
+ }
}
diff --git a/DigitalHumanWeb/locales/de-DE/changelog.json b/DigitalHumanWeb/locales/de-DE/changelog.json
new file mode 100644
index 0000000..dab2017
--- /dev/null
+++ b/DigitalHumanWeb/locales/de-DE/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Folgen Sie uns auf X",
+ "subscribeToUpdates": "Abonnieren Sie Updates",
+ "versions": "Versionsdetails"
+ },
+ "addedWhileAway": "Wir haben neue Funktionen hinzugefügt, während Sie weg waren.",
+ "allChangelog": "Alle Änderungsprotokolle anzeigen",
+ "description": "Verfolgen Sie die neuen Funktionen und Verbesserungen von {{appName}} kontinuierlich",
+ "pagination": {
+ "next": "Nächste Seite",
+ "older": "Ältere Änderungen anzeigen"
+ },
+ "readDetails": "Details lesen",
+ "title": "Änderungsprotokoll",
+ "versionDetails": "Versionsdetails",
+ "welcomeBack": "Willkommen zurück!"
+}
diff --git a/DigitalHumanWeb/locales/de-DE/chat.json b/DigitalHumanWeb/locales/de-DE/chat.json
index 891721b..4faada0 100644
--- a/DigitalHumanWeb/locales/de-DE/chat.json
+++ b/DigitalHumanWeb/locales/de-DE/chat.json
@@ -8,6 +8,7 @@
"agents": "Assistent",
"artifact": {
"generating": "Wird generiert",
+ "inThread": "In Unterthemen kann nicht angezeigt werden, bitte wechseln Sie zum Hauptdiskussionsbereich.",
"thinking": "Denken",
"thought": "Denkenprozess",
"unknownTitle": "Unbenanntes Werk"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Kopie",
"emptyAgent": "Kein Assistent verfügbar",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Die Kosten für die Generierung einer einzelnen Konversation können um bis zu 90 % gesenkt werden, die Reaktionsgeschwindigkeit wird um das Vierfache erhöht (<1>Mehr erfahren1>). Wenn aktiviert, wird die Begrenzung der Anzahl historischer Nachrichten automatisch deaktiviert.",
+ "title": "Kontext-Caching aktivieren"
+ },
+ "enableReasoning": {
+ "desc": "Basierend auf den Einschränkungen des Claude Thinking-Mechanismus (<1>Mehr erfahren1>), wird bei Aktivierung die Begrenzung der Anzahl historischer Nachrichten automatisch deaktiviert.",
+ "title": "Tiefes Denken aktivieren"
+ },
+ "reasoningBudgetToken": {
+ "title": "Token für Denkaufwand"
+ },
+ "title": "Modell Erweiterungsfunktionen"
+ },
+ "history": {
+ "title": "Der Assistent wird nur die letzten {{count}} Nachrichten speichern"
+ },
"historyRange": "Verlaufsbereich",
+ "historySummary": "Zusammenfassung historischer Nachrichten",
"inbox": {
"desc": "Aktiviere das Gehirncluster und entfache den Funken des Denkens. Dein intelligenter Assistent, der mit dir über alles kommuniziert.",
"title": "Lass uns plaudern"
@@ -45,6 +64,9 @@
"stop": "Stoppen",
"warp": "Zeilenumbruch"
},
+ "intentUnderstanding": {
+ "title": "Verstehe und analysiere gerade Ihre Absicht..."
+ },
"knowledgeBase": {
"all": "Alle Inhalte",
"allFiles": "Alle Dateien",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Löschen und neu generieren",
+ "deleteDisabledByThreads": "Es gibt Unterthemen, die Löschung ist nicht möglich.",
"regenerate": "Neu generieren"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Punkte",
+ "creditPricing": "Preisgestaltung",
+ "creditTooltip": "Zur Vereinfachung der Zählung rechnen wir 1$ als 1M Punkte um, zum Beispiel werden $3/M Tokens als 3 Punkte/token umgerechnet",
+ "pricing": {
+ "inputCachedTokens": "Zwischengespeicherte Eingabe {{amount}}/Punkte · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M Zeichen",
+ "inputMinutes": "${{amount}}/Minute",
+ "inputTokens": "Eingabe {{amount}}/Punkte · ${{amount}}/M",
+ "outputTokens": "Ausgabe {{amount}}/Punkte · ${{amount}}/M",
+ "writeCacheInputTokens": "Cache-Eingabe schreiben {{amount}}/Punkte · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Durchschnittspreis",
+ "input": "Eingabe",
+ "inputAudio": "Audioeingabe",
+ "inputCached": "Eingabe zwischengespeichert",
+ "inputCitation": "Eingabe zitieren",
+ "inputText": "Text-Eingabe",
+ "inputTitle": "Eingabedetails",
+ "inputUncached": "Eingabe nicht zwischengespeichert",
+ "inputWriteCached": "Eingabe Cache schreiben",
+ "output": "Ausgabe",
+ "outputAudio": "Audioausgabe",
+ "outputText": "Text-Ausgabe",
+ "outputTitle": "Ausgabedetails",
+ "reasoning": "Tiefes Denken",
+ "title": "Generierungsdetails",
+ "total": "Gesamter Verbrauch"
+ }
+ },
"newAgent": "Neuer Assistent",
"pin": "Anheften",
"pinOff": "Anheften aufheben",
@@ -81,6 +137,32 @@
},
"regenerate": "Neu generieren",
"roleAndArchive": "Rolle und Archiv",
+ "search": {
+ "grounding": {
+ "searchQueries": "Suchbegriffe",
+ "title": "Es wurden {{count}} Ergebnisse gefunden"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Intelligente Beurteilung, ob eine Suche basierend auf dem Gesprächsinhalt erforderlich ist",
+ "title": "Intelligente Vernetzung"
+ },
+ "off": {
+ "desc": "Verwendet nur das Grundwissen des Modells, ohne Netzsuche",
+ "title": "Vernetzung deaktivieren"
+ },
+ "on": {
+ "desc": "Führt kontinuierlich Netzsuchen durch, um die neuesten Informationen zu erhalten",
+ "title": "Immer vernetzt"
+ },
+ "useModelBuiltin": "Verwenden Sie die integrierte Suchmaschine des Modells"
+ },
+ "searchModel": {
+ "desc": "Das aktuelle Modell unterstützt keine Funktionsaufrufe, daher muss es mit einem Modell kombiniert werden, das Funktionsaufrufe unterstützt, um online zu suchen",
+ "title": "Suchunterstützungsmodell"
+ },
+ "title": "Netzwerksuche"
+ },
"searchAgentPlaceholder": "Suchassistent...",
"sendPlaceholder": "Chat-Nachricht eingeben...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Gruppenname muss zwischen 1 und 20 Zeichen lang sein"
},
"shareModal": {
+ "copy": "Kopieren",
"download": "Screenshot herunterladen",
+ "downloadFile": "Datei herunterladen",
+ "exportTitle": "Standardtitel",
"imageType": "Bildformat",
+ "includeTool": "Plugin-Nachricht einfügen",
+ "includeUser": "Benutzernachricht einfügen",
"screenshot": "Screenshot",
"settings": "Exporteinstellungen",
- "shareToShareGPT": "ShareGPT-Link generieren",
+ "text": "Text",
"withBackground": "Mit Hintergrundbild",
"withFooter": "Mit Fußzeile",
"withPluginInfo": "Mit Plugin-Informationen",
+ "withRole": "Nachrichtenrolle einfügen",
"withSystemRole": "Mit Assistentenrolle"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Erkenne...",
"prettifying": "Verschönern..."
},
- "temp": "Temporär",
+ "thread": {
+ "divider": "Unterthema",
+ "threadMessageCount": "{{messageCount}} Nachrichten",
+ "title": "Unterthema"
+ },
"tokenDetails": {
"chats": "Chats",
+ "historySummary": "Historische Zusammenfassung",
"rest": "Verbleibend",
"systemRole": "Systemrolle",
"title": "Kontextdetails",
@@ -131,29 +224,10 @@
"used": "Verwendet"
},
"topic": {
- "actions": {
- "autoRename": "Intelligent umbenennen",
- "duplicate": "Kopie erstellen",
- "export": "Thema exportieren"
- },
"checkOpenNewTopic": "Soll ein neues Thema eröffnet werden?",
"checkSaveCurrentMessages": "Möchten Sie die aktuelle Konversation als Thema speichern?",
- "confirmRemoveAll": "Möchtest du wirklich alle Themen löschen? Diese Aktion kann nicht rückgängig gemacht werden.",
- "confirmRemoveTopic": "Möchtest du dieses Thema wirklich löschen? Diese Aktion kann nicht rückgängig gemacht werden.",
- "confirmRemoveUnstarred": "Möchtest du die nicht markierten Themen wirklich löschen? Diese Aktion kann nicht rückgängig gemacht werden.",
- "defaultTitle": "Standardthema",
- "duplicateLoading": "Thema wird kopiert...",
- "duplicateSuccess": "Thema erfolgreich kopiert",
- "guide": {
- "desc": "Klicken Sie auf die Schaltfläche links, um das aktuelle Gespräch als historisches Thema zu speichern und eine neue Gesprächsrunde zu starten",
- "title": "Themenliste"
- },
"openNewTopic": "Neues Thema öffnen",
- "removeAll": "Alle Themen löschen",
- "removeUnstarred": "Nicht markierte Themen löschen",
- "saveCurrentMessages": "Aktuelle Unterhaltung als Thema speichern",
- "searchPlaceholder": "Themen durchsuchen...",
- "title": "Themenliste"
+ "saveCurrentMessages": "Aktuelle Unterhaltung als Thema speichern"
},
"translate": {
"action": "Übersetzen",
@@ -184,5 +258,6 @@
"processing": "Datei wird verarbeitet..."
}
}
- }
+ },
+ "zenMode": "Fokusmodus"
}
diff --git a/DigitalHumanWeb/locales/de-DE/common.json b/DigitalHumanWeb/locales/de-DE/common.json
index 4ca51c5..702242b 100644
--- a/DigitalHumanWeb/locales/de-DE/common.json
+++ b/DigitalHumanWeb/locales/de-DE/common.json
@@ -9,15 +9,79 @@
"title": "Willkommen bei {{name}}"
}
},
- "appInitializing": "Anwendung wird gestartet...",
+ "appLoading": {
+ "appIdle": "Bereit zum Starten",
+ "appInitializing": "Anwendung wird gestartet...",
+ "failed": "Es tut uns leid, die Anwendung konnte nicht initialisiert werden. Bitte sehen Sie sich die Details zur Fehlerbehebung an.",
+ "finished": "Datenbankinitialisierung abgeschlossen",
+ "goToChat": "Lade die Chat-Seite...",
+ "initAuth": "Initialisiere den Authentifizierungsdienst...",
+ "initUser": "Initialisiere den Benutzerstatus...",
+ "initializing": "Initialisiere die PGlite-Datenbank...",
+ "loadingDependencies": "Abhängigkeiten werden initialisiert...",
+ "loadingWasm": "WASM-Module werden geladen...",
+ "migrating": "Datenbankmigration wird durchgeführt...",
+ "ready": "Datenbank ist bereit",
+ "showDetail": "Details anzeigen"
+ },
"autoGenerate": "Automatisch generieren",
"autoGenerateTooltip": "Assistentenbeschreibung automatisch auf Basis von Vorschlägen vervollständigen",
"autoGenerateTooltipDisabled": "Bitte geben Sie einen Hinweis ein, um die automatische Vervollständigung zu aktivieren",
"back": "Zurück",
"batchDelete": "Massenlöschung",
"blog": "Produkt-Blog",
+ "branching": "Unterthema erstellen",
+ "branchingDisable": "Die Funktion „Unterthema“ ist nur in der Serverversion verfügbar. Wenn Sie diese Funktion benötigen, wechseln Sie bitte in den Serverbereitstellungsmodus oder verwenden Sie LobeChat Cloud.",
"cancel": "Abbrechen",
"changelog": "Änderungsprotokoll",
+ "clientDB": {
+ "autoInit": {
+ "title": "Initialisiere PGlite-Datenbank"
+ },
+ "error": {
+ "desc": "Es tut uns leid, während des Initialisierungsprozesses der Pglite-Datenbank ist ein Fehler aufgetreten. Bitte klicken Sie auf die Schaltfläche, um es erneut zu versuchen. Wenn der Fehler nach mehreren Versuchen weiterhin auftritt, <1>reichen Sie bitte ein Problem ein1>, und wir werden Ihnen umgehend bei der Untersuchung helfen.",
+ "detail": "Fehlerursache: [{{type}}] {{message}}. Einzelheiten sind wie folgt:",
+ "retry": "Erneut versuchen",
+ "title": "Datenbankinitialisierung fehlgeschlagen"
+ },
+ "initing": {
+ "error": "Ein Fehler ist aufgetreten, bitte versuchen Sie es erneut",
+ "idle": "Warte auf die Initialisierung...",
+ "initializing": "Wird initialisiert...",
+ "loadingDependencies": "Abhängigkeiten werden geladen...",
+ "loadingWasmModule": "WASM-Modul wird geladen...",
+ "migrating": "Datenbankmigration wird durchgeführt...",
+ "ready": "Datenbank ist bereit"
+ },
+ "modal": {
+ "desc": "Aktivieren Sie die PGlite-Clientdatenbank, um Chatdaten in Ihrem Browser dauerhaft zu speichern und erweiterte Funktionen wie Wissensdatenbanken zu nutzen.",
+ "enable": "Jetzt aktivieren",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Bauen Sie Ihre persönliche Wissensdatenbank auf und führen Sie mühelos Gespräche mit Ihrem Assistenten (demnächst verfügbar)",
+ "title": "Unterstützung für Wissensdatenbankgespräche, aktivieren Sie Ihr zweites Gehirn"
+ },
+ "localFirst": {
+ "desc": "Chat-Daten werden vollständig im Browser gespeichert, Ihre Daten sind immer in Ihrer Kontrolle.",
+ "title": "Lokale Priorität, Datenschutz an erster Stelle"
+ },
+ "pglite": {
+ "desc": "Basierend auf PGlite, unterstützt nativ AI Native fortgeschrittene Funktionen (Vektorsuche)",
+ "title": "Neue Generation der Client-Speicherarchitektur"
+ }
+ },
+ "init": {
+ "desc": "Die Datenbank wird initialisiert, je nach Netzwerkbedingungen kann dies 5 bis 30 Sekunden dauern.",
+ "title": "Initialisiere PGlite-Datenbank"
+ },
+ "title": "Clientdatenbank aktivieren"
+ },
+ "ready": {
+ "button": "Jetzt verwenden",
+ "desc": "Jetzt verwenden",
+ "title": "PGlite-Datenbank ist bereit"
+ }
+ },
"close": "Schließen",
"contact": "Kontakt",
"copy": "Kopieren",
@@ -112,6 +176,7 @@
"en": "Englisch",
"en-US": "Englisch",
"es-ES": "Spanisch",
+ "fa-IR": "Persisch",
"fi-FI": "Finnisch",
"fr-FR": "Französisch",
"hi-IN": "Hindi",
@@ -153,6 +218,7 @@
"pinOff": "Anheften aufheben",
"privacy": "Datenschutzrichtlinie",
"regenerate": "Neu generieren",
+ "releaseNotes": "Versionsdetails",
"rename": "Umbenennen",
"reset": "Zurücksetzen",
"retry": "Erneut versuchen",
@@ -209,6 +275,7 @@
},
"temp": "Temporär",
"terms": "Nutzungsbedingungen",
+ "update": "Aktualisieren",
"updateAgent": "Assistentenprofil aktualisieren",
"upgradeVersion": {
"action": "Aktualisieren",
@@ -219,6 +286,7 @@
"anonymousNickName": "Anonymer Benutzer",
"billing": "Abrechnung verwalten",
"cloud": "Erleben Sie {{name}}",
+ "community": "Gemeinschaftsversion",
"data": "Daten speichern",
"defaultNickname": "Community User",
"discord": "Community-Support",
@@ -228,7 +296,6 @@
"help": "Hilfezentrum",
"moveGuide": "Die Einstellungen wurden hierher verschoben.",
"plans": "Abonnementpläne",
- "preview": "Vorschau",
"profile": "Kontoverwaltung",
"setting": "App-Einstellungen",
"usages": "Nutzungsstatistiken"
diff --git a/DigitalHumanWeb/locales/de-DE/components.json b/DigitalHumanWeb/locales/de-DE/components.json
index 0775a66..785504b 100644
--- a/DigitalHumanWeb/locales/de-DE/components.json
+++ b/DigitalHumanWeb/locales/de-DE/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Batch-Zerteilung",
"chunking": "Zerteilung",
"chunkingTooltip": "Teilen Sie die Datei in mehrere Textblöcke und vektorisieren Sie sie, um sie für die semantische Suche und Dateidialoge zu verwenden.",
+ "chunkingUnsupported": "Diese Datei unterstützt kein Chunking.",
"confirmDelete": "Die Datei wird gelöscht. Nach dem Löschen kann sie nicht wiederhergestellt werden. Bitte bestätigen Sie Ihre Aktion.",
"confirmDeleteMultiFiles": "Die ausgewählten {{count}} Dateien werden gelöscht. Nach dem Löschen können sie nicht wiederhergestellt werden. Bitte bestätigen Sie Ihre Aktion.",
"confirmRemoveFromKnowledgeBase": "Die ausgewählten {{count}} Dateien werden aus der Wissensdatenbank entfernt. Die Dateien sind weiterhin in allen Dateien sichtbar. Bitte bestätigen Sie Ihre Aktion.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Zurück"
},
+ "MaxTokenSlider": {
+ "unlimited": "Unbegrenzt"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Benutzerdefiniertes Modell, standardmäßig unterstützt es sowohl Funktionsaufrufe als auch visuelle Erkennung. Bitte überprüfen Sie die Verfügbarkeit dieser Fähigkeiten basierend auf den tatsächlichen Gegebenheiten.",
"file": "Dieses Modell unterstützt das Hochladen von Dateien und deren Erkennung.",
"functionCall": "Dieses Modell unterstützt Funktionsaufrufe.",
+ "reasoning": "Dieses Modell unterstützt tiefes Denken",
+ "search": "Dieses Modell unterstützt die Online-Suche",
"tokens": "Dieses Modell unterstützt maximal {{tokens}} Tokens pro Sitzung.",
"vision": "Dieses Modell unterstützt die visuelle Erkennung."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Kein aktiviertes Modell. Bitte gehen Sie zu den Einstellungen, um es zu aktivieren.",
+ "emptyProvider": "Es sind keine aktiven Anbieter vorhanden, bitte gehen Sie zu den Einstellungen, um sie zu aktivieren",
+ "goToSettings": "Zu den Einstellungen gehen",
"provider": "Anbieter"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Aufgrund von Sicherheitsbeschränkungen im Browser müssen Sie CORS für Ollama konfigurieren, um es ordnungsgemäß nutzen zu können.",
+ "linux": {
+ "env": "Fügen Sie im Abschnitt [Service] `Environment` hinzu und setzen Sie die Umgebungsvariable OLLAMA_ORIGINS:",
+ "reboot": "Laden Sie systemd neu und starten Sie Ollama neu",
+ "systemd": "Rufen Sie systemd auf, um den ollama-Dienst zu bearbeiten:"
+ },
+ "macos": "Bitte öffnen Sie die „Terminal“-Anwendung, fügen Sie die folgenden Befehle ein und drücken Sie die Eingabetaste, um sie auszuführen",
+ "reboot": "Bitte starten Sie den Ollama-Dienst nach Abschluss der Ausführung neu",
+ "title": "Konfigurieren Sie Ollama für den CORS-Zugriff",
+ "windows": "Klicken Sie unter Windows auf „Systemsteuerung“ und gehen Sie zu den Systemeigenschaften. Erstellen Sie eine neue Umgebungsvariable mit dem Namen „OLLAMA_ORIGINS“ für Ihr Benutzerkonto, setzen Sie den Wert auf * und klicken Sie auf „OK/Übernehmen“, um zu speichern"
+ },
+ "install": {
+ "description": "Bitte stellen Sie sicher, dass Sie Ollama gestartet haben. Wenn Sie Ollama nicht heruntergeladen haben, besuchen Sie die offizielle Website <1>zum Herunterladen1>",
+ "docker": "Wenn Sie lieber Docker verwenden möchten, bietet Ollama auch offizielle Docker-Images an, die Sie mit dem folgenden Befehl herunterladen können:",
+ "linux": {
+ "command": "Installieren Sie es mit dem folgenden Befehl:",
+ "manual": "Alternativ können Sie auch die <1>Linux-Handbuchinstallation1> zur Selbstinstallation konsultieren"
+ },
+ "title": "Ollama-Anwendung lokal installieren und starten",
+ "windowsTab": "Windows (Vorschau)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Tiefes Nachdenken...",
+ "thought": "Tiefgründig nachgedacht (Dauer: {{duration}} Sekunden)",
+ "thoughtWithDuration": "Tiefgründig nachgedacht"
}
}
diff --git a/DigitalHumanWeb/locales/de-DE/discover.json b/DigitalHumanWeb/locales/de-DE/discover.json
index 4102d2d..789c094 100644
--- a/DigitalHumanWeb/locales/de-DE/discover.json
+++ b/DigitalHumanWeb/locales/de-DE/discover.json
@@ -126,6 +126,10 @@
"title": "Themenfrische"
},
"range": "Bereich",
+ "reasoning_effort": {
+ "desc": "Diese Einstellung steuert die Intensität des Denkprozesses des Modells, bevor es eine Antwort generiert. Eine niedrige Intensität priorisiert die Geschwindigkeit der Antwort und spart Token, während eine hohe Intensität eine umfassendere Argumentation bietet, jedoch mehr Token verbraucht und die Antwortgeschwindigkeit verringert. Der Standardwert ist mittel, um eine Balance zwischen Genauigkeit des Denkens und Antwortgeschwindigkeit zu gewährleisten.",
+ "title": "Denkintensität"
+ },
"temperature": {
"desc": "Diese Einstellung beeinflusst die Vielfalt der Antworten des Modells. Niedrigere Werte führen zu vorhersehbareren und typischen Antworten, während höhere Werte zu vielfältigeren und weniger häufigen Antworten anregen. Wenn der Wert auf 0 gesetzt wird, gibt das Modell für einen bestimmten Input immer die gleiche Antwort.",
"title": "Zufälligkeit"
diff --git a/DigitalHumanWeb/locales/de-DE/error.json b/DigitalHumanWeb/locales/de-DE/error.json
index 8b6a66b..c87a977 100644
--- a/DigitalHumanWeb/locales/de-DE/error.json
+++ b/DigitalHumanWeb/locales/de-DE/error.json
@@ -12,8 +12,14 @@
"retry": "Erneut laden",
"title": "Ein Problem ist aufgetreten auf der Seite.."
},
- "fetchError": "Anforderung fehlgeschlagen",
- "fetchErrorDetail": "Fehlerdetails",
+ "fetchError": {
+ "detail": "Fehlerdetails",
+ "title": "Anfrage fehlgeschlagen"
+ },
+ "loginRequired": {
+ "desc": "Sie werden in Kürze zur Anmeldeseite weitergeleitet",
+ "title": "Bitte melden Sie sich an, um diese Funktion zu nutzen"
+ },
"notFound": {
"backHome": "Zurück zur Startseite",
"check": "Bitte überprüfen Sie, ob Ihre URL korrekt ist.",
@@ -51,22 +57,34 @@
"431": "Entschuldigung, der Header Ihrer Anfrage ist zu groß und kann vom Server nicht verarbeitet werden",
"451": "Entschuldigung, aus rechtlichen Gründen verweigert der Server die Bereitstellung dieser Ressource",
"500": "Entschuldigung, der Server hat anscheinend einige Schwierigkeiten und kann Ihre Anfrage vorübergehend nicht bearbeiten. Bitte versuchen Sie es später erneut",
+ "501": "Es tut uns leid, der Server weiß noch nicht, wie er diese Anfrage bearbeiten soll. Bitte überprüfen Sie, ob Ihre Aktion korrekt ist.",
"502": "Entschuldigung, der Server scheint die Orientierung verloren zu haben und kann vorübergehend keinen Service bereitstellen. Bitte versuchen Sie es später erneut",
"503": "Entschuldigung, der Server kann Ihre Anfrage derzeit nicht verarbeiten. Möglicherweise aufgrund von Überlastung oder Wartungsarbeiten. Bitte versuchen Sie es später erneut",
"504": "Entschuldigung, der Server hat keine Antwort vom Upstream-Server erhalten. Bitte versuchen Sie es später erneut",
+ "505": "Es tut uns leid, der Server unterstützt die von Ihnen verwendete HTTP-Version nicht. Bitte aktualisieren Sie und versuchen Sie es erneut.",
+ "506": "Es tut uns leid, es gibt ein Problem mit der Serverkonfiguration. Bitte wenden Sie sich an den Administrator, um das Problem zu lösen.",
+ "507": "Es tut uns leid, der Server hat nicht genügend Speicherplatz, um Ihre Anfrage zu bearbeiten. Bitte versuchen Sie es später erneut.",
+ "509": "Es tut uns leid, die Bandbreite des Servers ist erschöpft. Bitte versuchen Sie es später erneut.",
+ "510": "Es tut uns leid, der Server unterstützt die angeforderte Erweiterungsfunktion nicht. Bitte wenden Sie sich an den Administrator.",
+ "524": "Es tut uns leid, der Server hat beim Warten auf eine Antwort die Zeit überschritten, möglicherweise aufgrund einer zu langsamen Antwort. Bitte versuchen Sie es später erneut.",
"AgentRuntimeError": "Es ist ein Fehler bei der Ausführung des Lobe-Sprachmodells aufgetreten. Bitte überprüfen Sie die folgenden Informationen oder versuchen Sie es erneut.",
+ "ConnectionCheckFailed": "Die Anfrage brachte eine leere Antwort zurück. Bitte überprüfen Sie, ob die API-Proxy-Adresse am Ende nicht mit `/v1` endet.",
+ "ExceededContextWindow": "Der aktuelle Anfrageinhalt überschreitet die von dem Modell verarbeitbare Länge. Bitte reduzieren Sie die Menge des Inhalts und versuchen Sie es erneut.",
"FreePlanLimit": "Sie sind derzeit ein kostenloser Benutzer und können diese Funktion nicht nutzen. Bitte aktualisieren Sie auf ein kostenpflichtiges Abonnement, um fortzufahren.",
+ "InsufficientQuota": "Es tut uns leid, das Kontingent (Quota) für diesen Schlüssel ist erreicht. Bitte überprüfen Sie Ihr Kontoguthaben oder erhöhen Sie das Kontingent des Schlüssels und versuchen Sie es erneut.",
"InvalidAccessCode": "Das Passwort ist ungültig oder leer. Bitte geben Sie das richtige Zugangspasswort ein oder fügen Sie einen benutzerdefinierten API-Schlüssel hinzu.",
"InvalidBedrockCredentials": "Die Bedrock-Authentifizierung ist fehlgeschlagen. Bitte überprüfen Sie AccessKeyId/SecretAccessKey und versuchen Sie es erneut.",
"InvalidClerkUser": "Entschuldigung, du bist derzeit nicht angemeldet. Bitte melde dich an oder registriere ein Konto, um fortzufahren.",
"InvalidGithubToken": "Der persönliche Zugriffstoken für Github ist ungültig oder leer. Bitte überprüfen Sie den persönlichen Zugriffstoken für Github und versuchen Sie es erneut.",
"InvalidOllamaArgs": "Ollama-Konfiguration ist ungültig. Bitte überprüfen Sie die Ollama-Konfiguration und versuchen Sie es erneut.",
"InvalidProviderAPIKey": "{{provider}} API-Schlüssel ist ungültig oder leer. Bitte überprüfen Sie den {{provider}} API-Schlüssel und versuchen Sie es erneut.",
+ "InvalidVertexCredentials": "Die Vertex-Authentifizierung ist fehlgeschlagen. Bitte überprüfen Sie Ihre Authentifizierungsdaten und versuchen Sie es erneut.",
"LocationNotSupportError": "Entschuldigung, Ihr Standort unterstützt diesen Modellservice möglicherweise aufgrund von regionalen Einschränkungen oder nicht aktivierten Diensten nicht. Bitte überprüfen Sie, ob der aktuelle Standort die Verwendung dieses Dienstes unterstützt, oder versuchen Sie, andere Standortinformationen zu verwenden.",
+ "ModelNotFound": "Es tut uns leid, das angeforderte Modell konnte nicht gefunden werden. Möglicherweise existiert das Modell nicht oder es liegen keine Zugriffsrechte vor. Bitte ändern Sie den API-Schlüssel oder passen Sie die Zugriffsrechte an und versuchen Sie es erneut.",
"NoOpenAIAPIKey": "Der OpenAI-API-Schlüssel ist leer. Bitte fügen Sie einen benutzerdefinierten OpenAI-API-Schlüssel hinzu",
"OllamaBizError": "Fehler bei der Anforderung des Ollama-Dienstes. Bitte überprüfen Sie die folgenden Informationen oder versuchen Sie es erneut.",
"OllamaServiceUnavailable": "Der Ollama-Dienst ist nicht verfügbar. Bitte überprüfen Sie, ob Ollama ordnungsgemäß ausgeführt wird und ob die CORS-Konfiguration von Ollama korrekt ist.",
- "OpenAIBizError": "Fehler bei der Anforderung des OpenAI-Dienstes. Bitte überprüfen Sie die folgenden Informationen oder versuchen Sie es erneut.",
+ "PermissionDenied": "Es tut uns leid, Sie haben keine Berechtigung, auf diesen Dienst zuzugreifen. Bitte überprüfen Sie, ob Ihr Schlüssel die erforderlichen Zugriffsrechte hat.",
"PluginApiNotFound": "Entschuldigung, das API des Plugins im Plugin-Manifest existiert nicht. Bitte überprüfen Sie, ob Ihre Anfragemethode mit dem Plugin-Manifest-API übereinstimmt",
"PluginApiParamsError": "Entschuldigung, die Eingabeüberprüfung der Plugin-Anfrage ist fehlgeschlagen. Bitte überprüfen Sie, ob die Eingabe mit den API-Beschreibungsinformationen übereinstimmt",
"PluginFailToTransformArguments": "Es tut uns leid, die Plugin-Aufrufargumente konnten nicht transformiert werden. Bitte versuchen Sie, die Assistentennachricht erneut zu generieren, oder wechseln Sie zu einem leistungsstärkeren AI-Modell mit Tools Calling-Fähigkeiten und versuchen Sie es erneut.",
@@ -81,8 +99,11 @@
"PluginServerError": "Fehler bei der Serveranfrage des Plugins. Bitte überprüfen Sie die Fehlerinformationen unten in Ihrer Plugin-Beschreibungsdatei, Plugin-Konfiguration oder Serverimplementierung",
"PluginSettingsInvalid": "Das Plugin muss korrekt konfiguriert werden, um verwendet werden zu können. Bitte überprüfen Sie Ihre Konfiguration auf Richtigkeit",
"ProviderBizError": "Fehler bei der Anforderung des {{provider}}-Dienstes. Bitte überprüfen Sie die folgenden Informationen oder versuchen Sie es erneut.",
+ "QuotaLimitReached": "Es tut uns leid, die aktuelle Token-Nutzung oder die Anzahl der Anfragen hat das Kontingent (Quota) für diesen Schlüssel erreicht. Bitte erhöhen Sie das Kontingent für diesen Schlüssel oder versuchen Sie es später erneut.",
"StreamChunkError": "Fehler beim Parsen des Nachrichtenchunks der Streaming-Anfrage. Bitte überprüfen Sie, ob die aktuelle API-Schnittstelle den Standards entspricht, oder wenden Sie sich an Ihren API-Anbieter.",
- "SubscriptionPlanLimit": "Ihr Abonnementkontingent wurde aufgebraucht und Sie können diese Funktion nicht nutzen. Bitte aktualisieren Sie auf ein höheres Abonnement oder kaufen Sie ein Ressourcenpaket, um fortzufahren.",
+ "SubscriptionKeyMismatch": "Es tut uns leid, aufgrund eines vorübergehenden Systemfehlers ist das aktuelle Abonnement vorübergehend ungültig. Bitte klicken Sie auf die Schaltfläche unten, um das Abonnement wiederherzustellen, oder kontaktieren Sie uns per E-Mail für Unterstützung.",
+ "SubscriptionPlanLimit": "Ihr Abonnementspunktestand ist erschöpft, Sie können diese Funktion nicht nutzen. Bitte upgraden Sie auf einen höheren Plan oder konfigurieren Sie die benutzerdefinierte Modell-API, um weiterhin zu verwenden.",
+ "SystemTimeNotMatchError": "Es tut uns leid, Ihre Systemzeit stimmt nicht mit dem Server überein. Bitte überprüfen Sie Ihre Systemzeit und versuchen Sie es erneut.",
"UnknownChatFetchError": "Es tut uns leid, es ist ein unbekannter Anforderungsfehler aufgetreten. Bitte überprüfen Sie die folgenden Informationen oder versuchen Sie es erneut."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/de-DE/metadata.json b/DigitalHumanWeb/locales/de-DE/metadata.json
index d5e0175..06c08be 100644
--- a/DigitalHumanWeb/locales/de-DE/metadata.json
+++ b/DigitalHumanWeb/locales/de-DE/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Verfolgen Sie kontinuierlich die neuen Funktionen und Verbesserungen von {{appName}}",
+ "title": "Änderungsprotokoll"
+ },
"chat": {
"description": "{{appName}} bietet dir das beste Erlebnis mit ChatGPT, Claude, Gemini und OLLaMA WebUI",
"title": "{{appName}}: Persönliches KI-Effizienzwerkzeug, gib dir selbst ein schlaueres Gehirn"
diff --git a/DigitalHumanWeb/locales/de-DE/modelProvider.json b/DigitalHumanWeb/locales/de-DE/modelProvider.json
index 99df752..0407caa 100644
--- a/DigitalHumanWeb/locales/de-DE/modelProvider.json
+++ b/DigitalHumanWeb/locales/de-DE/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "API-Version von Azure, im Format YYYY-MM-DD, siehe [aktuelle Version](https://learn.microsoft.com/de-de/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Liste abrufen",
+ "title": "Azure API-Version"
+ },
+ "endpoint": {
+ "desc": "Finden Sie den Endpunkt für die Modellinferenz von Azure AI im Überblick über das Azure AI-Projekt",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AI-Endpunkt"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Finden Sie den API-Schlüssel im Überblick über das Azure AI-Projekt",
+ "placeholder": "Azure-Schlüssel",
+ "title": "Schlüssel"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Geben Sie Ihre AWS Access Key Id ein",
@@ -51,6 +69,58 @@
"title": "Verwenden Sie benutzerdefinierte Bedrock-Authentifizierungsinformationen"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Bitte füllen Sie die Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Eingeben Sie die Cloudflare-Kundenkennung oder die benutzerdefinierte API-Adresse",
+ "placeholder": "Cloudflare-Kundenkennung / benutzerdefinierte API-Adresse",
+ "title": "Cloudflare-Kundenkennung / API-Adresse"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Bitte geben Sie Ihren API-Schlüssel ein",
+ "title": "API-Schlüssel"
+ },
+ "basicTitle": "Grundinformationen",
+ "configTitle": "Konfigurationsinformationen",
+ "confirm": "Neu erstellen",
+ "createSuccess": "Erstellung erfolgreich",
+ "description": {
+ "placeholder": "Beschreibung des Anbieters (optional)",
+ "title": "Beschreibung des Anbieters"
+ },
+ "id": {
+ "desc": "Eindeutige Kennung des Anbieters, die nach der Erstellung nicht mehr geändert werden kann",
+ "format": "Darf nur aus Zahlen, Kleinbuchstaben, Bindestrichen (-) und Unterstrichen (_) bestehen",
+ "placeholder": "Empfohlen in Kleinbuchstaben, z.B. openai, nach der Erstellung nicht mehr änderbar",
+ "required": "Bitte geben Sie die Anbieter-ID ein",
+ "title": "Anbieter-ID"
+ },
+ "logo": {
+ "required": "Bitte laden Sie das korrekte Anbieter-Logo hoch",
+ "title": "Anbieter-Logo"
+ },
+ "name": {
+ "placeholder": "Bitte geben Sie den angezeigten Namen des Anbieters ein",
+ "required": "Bitte geben Sie den Namen des Anbieters ein",
+ "title": "Name des Anbieters"
+ },
+ "proxyUrl": {
+ "required": "Bitte geben Sie die Proxy-Adresse ein",
+ "title": "Proxy-Adresse"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Bitte wählen Sie den SDK-Typ aus",
+ "title": "Anforderungsformat"
+ },
+ "title": "Erstellen Sie einen benutzerdefinierten AI-Anbieter"
+ },
"github": {
"personalAccessToken": {
"desc": "Geben Sie Ihr GitHub-PAT ein und klicken Sie [hier](https://github.com/settings/tokens), um eines zu erstellen.",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Geben Sie Ihr HuggingFace-Token ein, klicken Sie [hier](https://huggingface.co/settings/tokens), um eines zu erstellen",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace-Token"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Dienstanbieter nicht aktiviert",
+ "enabled": "Dienstanbieter aktiviert"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Benutzerdefinierten Anbieter hinzufügen",
+ "all": "Alle",
+ "list": {
+ "disabled": "Nicht aktiviert",
+ "enabled": "Aktiviert"
+ },
+ "notFound": "Keine Suchergebnisse gefunden",
+ "searchProviders": "Anbieter suchen...",
+ "sort": "Benutzerdefinierte Sortierung"
+ },
"ollama": {
"checker": {
"desc": "Testen Sie, ob die Proxy-Adresse korrekt eingetragen wurde",
@@ -69,39 +163,15 @@
"title": "Benutzerdefinierte Modellnamen"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. The download will resume from where it left off if interrupted.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama lädt dieses Modell herunter. Bitte schließen Sie diese Seite nicht. Ein erneuter Download wird an der unterbrochenen Stelle fortgesetzt.",
+ "remainingTime": "Verbleibende Zeit",
+ "speed": "Downloadgeschwindigkeit",
+ "title": "Lade Modell {{model}} herunter"
},
"endpoint": {
- "desc": "Geben Sie die Proxy-Adresse der Ollama-Schnittstelle ein, leer lassen, wenn lokal nicht spezifiziert",
+ "desc": "Muss http(s):// enthalten, kann leer gelassen werden, wenn lokal nicht zusätzlich angegeben.",
"title": "Schnittstellen-Proxy-Adresse"
},
- "setup": {
- "cors": {
- "description": "Aufgrund von Browser-Sicherheitsbeschränkungen müssen Sie die CORS-Einstellungen für Ollama konfigurieren, um es ordnungsgemäß zu verwenden.",
- "linux": {
- "env": "Fügen Sie unter [Service] `Environment` hinzu und setzen Sie die Umgebungsvariable OLLAMA_ORIGINS:",
- "reboot": "Systemd neu laden und Ollama neu starten",
- "systemd": "Rufen Sie systemd auf, um den Ollama-Dienst zu bearbeiten:"
- },
- "macos": "Öffnen Sie das Terminal und fügen Sie den folgenden Befehl ein, um fortzufahren.",
- "reboot": "Starten Sie den Ollama-Dienst nach Abschluss der Ausführung neu.",
- "title": "Konfigurieren Sie Ollama für den Zugriff über CORS",
- "windows": "Klicken Sie auf Windows auf 'Systemsteuerung', um die Systemumgebungsvariablen zu bearbeiten. Erstellen Sie eine Umgebungsvariable namens 'OLLAMA_ORIGINS' für Ihr Benutzerkonto mit dem Wert '*', und klicken Sie auf 'OK/Anwenden', um zu speichern."
- },
- "install": {
- "description": "Stelle sicher, dass du Ollama aktiviert hast. Wenn du Ollama noch nicht heruntergeladen hast, besuche die offizielle Website, um es <1>herunterzuladen1>.",
- "docker": "Wenn Sie Docker bevorzugen, bietet Ollama auch offizielle Docker-Images an. Sie können sie mit dem folgenden Befehl abrufen:",
- "linux": {
- "command": "Installieren Sie mit dem folgenden Befehl:",
- "manual": "Alternativ können Sie die <1>Linux-Installationsanleitung1> für die manuelle Installation verwenden."
- },
- "title": "Installieren und starten Sie die lokale Ollama-Anwendung",
- "windowsTab": "Windows (Vorschau)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Cancel Download",
@@ -112,6 +182,156 @@
"title": "Download specified Ollama model"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "Ihr Schlüssel und die Proxy-Adresse werden mit dem <1>AES-GCM1>-Verschlüsselungsalgorithmus verschlüsselt",
+ "apiKey": {
+ "desc": "Bitte geben Sie Ihren {{name}} API-Schlüssel ein",
+ "placeholder": "{{name}} API-Schlüssel",
+ "title": "API-Schlüssel"
+ },
+ "baseURL": {
+ "desc": "Muss http(s):// enthalten",
+ "invalid": "Bitte geben Sie eine gültige URL ein",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API-Proxy-Adresse"
+ },
+ "checker": {
+ "button": "Überprüfen",
+ "desc": "Testen Sie, ob der API-Schlüssel und die Proxy-Adresse korrekt eingegeben wurden",
+ "pass": "Überprüfung bestanden",
+ "title": "Verbindungsprüfung"
+ },
+ "fetchOnClient": {
+ "desc": "Der Client-Anforderungsmodus initiiert die Sitzung direkt aus dem Browser, was die Reaktionsgeschwindigkeit erhöhen kann",
+ "title": "Client-Anforderungsmodus verwenden"
+ },
+ "helpDoc": "Konfigurationsanleitung",
+ "waitingForMore": "Weitere Modelle werden <1>geplant1>, bitte warten Sie"
+ },
+ "createNew": {
+ "title": "Erstellen Sie ein benutzerdefiniertes AI-Modell"
+ },
+ "item": {
+ "config": "Modell konfigurieren",
+ "customModelCards": {
+ "addNew": "Erstellen und hinzufügen {{id}} Modell",
+ "confirmDelete": "Das benutzerdefinierte Modell wird gelöscht, nach dem Löschen kann es nicht wiederhergestellt werden. Bitte vorsichtig vorgehen."
+ },
+ "delete": {
+ "confirm": "Bestätigen Sie das Löschen des Modells {{displayName}}?",
+ "success": "Löschung erfolgreich",
+ "title": "Modell löschen"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Feld, das in Azure OpenAI tatsächlich angefordert wird",
+ "placeholder": "Bitte geben Sie den Modellbereitstellungsnamen in Azure ein",
+ "title": "Modellbereitstellungsname"
+ },
+ "deployName": {
+ "extra": "Dieses Feld wird als Modell-ID gesendet, wenn die Anfrage gesendet wird",
+ "placeholder": "Bitte geben Sie den tatsächlichen Namen oder die ID des bereitgestellten Modells ein",
+ "title": "Modellbereitstellungsname"
+ },
+ "displayName": {
+ "placeholder": "Bitte geben Sie den angezeigten Namen des Modells ein, z.B. ChatGPT, GPT-4 usw.",
+ "title": "Anzeigename des Modells"
+ },
+ "files": {
+ "extra": "Der aktuelle Datei-Upload ist nur eine Hack-Lösung und nur für eigene Versuche gedacht. Warten Sie auf die vollständige Datei-Upload-Funktionalität.",
+ "title": "Datei-Upload unterstützen"
+ },
+ "functionCall": {
+ "extra": "Diese Konfiguration aktiviert nur die Fähigkeit des Modells, Werkzeuge zu verwenden, und ermöglicht es, pluginartige Werkzeuge hinzuzufügen. Ob das Modell tatsächlich in der Lage ist, Werkzeuge zu verwenden, hängt jedoch vollständig vom Modell selbst ab. Bitte testen Sie die Verwendbarkeit selbst.",
+ "title": "Unterstützung der Werkzeugnutzung"
+ },
+ "id": {
+ "extra": "Nach der Erstellung nicht mehr änderbar, wird als Modell-ID verwendet, wenn AI aufgerufen wird",
+ "placeholder": "Bitte Modell-ID eingeben, z. B. gpt-4o oder claude-3.5-sonnet",
+ "title": "Modell-ID"
+ },
+ "modalTitle": "Benutzerdefinierte Modellkonfiguration",
+ "reasoning": {
+ "extra": "Diese Konfiguration aktiviert nur die Fähigkeit des Modells zu tiefem Denken. Die tatsächlichen Ergebnisse hängen vollständig vom Modell selbst ab. Bitte testen Sie selbst, ob das Modell über die Fähigkeit zum tiefen Denken verfügt.",
+ "title": "Unterstützung für tiefes Denken"
+ },
+ "tokens": {
+ "extra": "Maximale Token-Anzahl für das Modell festlegen",
+ "title": "Maximales Kontextfenster",
+ "unlimited": "Unbegrenzt"
+ },
+ "vision": {
+ "extra": "Diese Konfiguration aktiviert nur die Bild-Upload-Funktionalität in der Anwendung. Ob die Erkennung unterstützt wird, hängt vollständig vom Modell selbst ab. Bitte testen Sie die Verwendbarkeit der visuellen Erkennungsfähigkeit des Modells selbst.",
+ "title": "Visuelle Erkennung unterstützen"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/Bild",
+ "inputCharts": "${{amount}}/M Zeichen",
+ "inputMinutes": "${{amount}}/Minuten",
+ "inputTokens": "Eingabe ${{amount}}/M",
+ "outputTokens": "Ausgabe ${{amount}}/M"
+ },
+ "releasedAt": "Veröffentlicht am {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Modell hinzufügen",
+ "disabled": "Nicht aktiviert",
+ "disabledActions": {
+ "showMore": "Alle anzeigen"
+ },
+ "empty": {
+ "desc": "Bitte erstellen Sie ein benutzerdefiniertes Modell oder ziehen Sie ein Modell, um zu beginnen.",
+ "title": "Keine verfügbaren Modelle"
+ },
+ "enabled": "Aktiviert",
+ "enabledActions": {
+ "disableAll": "Alle deaktivieren",
+ "enableAll": "Alle aktivieren",
+ "sort": "Benutzerdefinierte Modellreihenfolge"
+ },
+ "enabledEmpty": "Keine aktivierten Modelle vorhanden, bitte aktivieren Sie Ihre bevorzugten Modelle aus der Liste unten~",
+ "fetcher": {
+ "clear": "Abgerufene Modelle löschen",
+ "fetch": "Modellliste abrufen",
+ "fetching": "Modellliste wird abgerufen...",
+ "latestTime": "Letzte Aktualisierung: {{time}}",
+ "noLatestTime": "Liste wurde noch nicht abgerufen"
+ },
+ "resetAll": {
+ "conform": "Möchten Sie alle Änderungen am aktuellen Modell wirklich zurücksetzen? Nach dem Zurücksetzen wird die aktuelle Modellliste auf den Standardzustand zurückgesetzt.",
+ "success": "Zurücksetzen erfolgreich",
+ "title": "Alle Änderungen zurücksetzen"
+ },
+ "search": "Modelle suchen...",
+ "searchResult": "{{count}} Modelle gefunden",
+ "title": "Modellliste",
+ "total": "Insgesamt {{count}} verfügbare Modelle"
+ },
+ "searchNotFound": "Keine Suchergebnisse gefunden"
+ },
+ "sortModal": {
+ "success": "Sortierung erfolgreich aktualisiert",
+ "title": "Benutzerdefinierte Sortierung",
+ "update": "Aktualisieren"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Der AI-Anbieter wird gelöscht, nach dem Löschen kann er nicht wiederhergestellt werden. Bestätigen Sie, ob Sie löschen möchten?",
+ "deleteSuccess": "Löschung erfolgreich",
+ "tooltip": "Aktualisieren Sie die grundlegenden Anbieterinformationen",
+ "updateSuccess": "Aktualisierung erfolgreich"
+ },
+ "updateCustomAiProvider": {
+ "title": "Konfiguration des benutzerdefinierten KI-Anbieters aktualisieren"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Geben Sie Ihre Vertex AI-Schlüssel ein",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI-Schlüssel"
+ }
+ },
"zeroone": {
"title": "01.AI Alles und Nichts"
},
diff --git a/DigitalHumanWeb/locales/de-DE/models.json b/DigitalHumanWeb/locales/de-DE/models.json
index bfa79a8..709bb3b 100644
--- a/DigitalHumanWeb/locales/de-DE/models.json
+++ b/DigitalHumanWeb/locales/de-DE/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B bietet mit umfangreichen Trainingsbeispielen überlegene Leistungen in der Branchenanwendung."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat ist eine Variante der Yi-1.5-Serie und gehört zu den Open-Source-Chatmodellen. Yi-1.5 ist die verbesserte Version von Yi, die auf 500B hochwertigen Korpora kontinuierlich vortrainiert wurde und auf 3M diversifizierten Feinabstimmungsbeispielen feinabgestimmt wurde. Im Vergleich zu Yi zeigt Yi-1.5 stärkere Fähigkeiten in Codierung, Mathematik, Inferenz und Befolgung von Anweisungen, während es hervorragende Sprachverständnis-, Alltagswissen- und Leseverständnisfähigkeiten bewahrt. Das Modell bietet Versionen mit Kontextlängen von 4K, 16K und 32K, mit einer Gesamtanzahl von 3,6T Tokens im Vortraining."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B unterstützt 16K Tokens und bietet effiziente, flüssige Sprachgenerierungsfähigkeiten."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Yi 1.5, das neueste Open-Source-Fine-Tuning-Modell mit 34 Milliarden Parametern, unterstützt verschiedene Dialogszenarien mit hochwertigen Trainingsdaten, die auf menschliche Präferenzen abgestimmt sind."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Yi 1.5, das neueste Open-Source-Fine-Tuning-Modell mit 9 Milliarden Parametern, unterstützt verschiedene Dialogszenarien mit hochwertigen Trainingsdaten, die auf menschliche Präferenzen abgestimmt sind."
+ },
"360gpt-pro": {
"description": "360GPT Pro ist ein wichtiger Bestandteil der 360 AI-Modellreihe und erfüllt mit seiner effizienten Textverarbeitungsfähigkeit vielfältige Anwendungen der natürlichen Sprache, unterstützt das Verständnis langer Texte und Mehrfachdialoge."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K betont semantische Sicherheit und verantwortungsbewusste Ausrichtung, speziell für Anwendungen mit hohen Anforderungen an die Inhaltssicherheit konzipiert, um die Genauigkeit und Robustheit der Benutzererfahrung zu gewährleisten."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 verwendet Baumsuche zur Konstruktion von Denkketten und führt einen Reflexionsmechanismus ein, der durch verstärkendes Lernen trainiert wird. Das Modell verfügt über die Fähigkeit zur Selbstreflexion und Fehlerkorrektur."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro ist ein fortschrittliches Modell zur Verarbeitung natürlicher Sprache, das von der 360 Company entwickelt wurde und über außergewöhnliche Textgenerierungs- und Verständnisfähigkeiten verfügt, insbesondere im Bereich der Generierung und Kreativität, und in der Lage ist, komplexe Sprachumwandlungs- und Rollendarstellungsaufgaben zu bewältigen."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 verwendet Baumsuche zur Konstruktion von Denkketten und führt einen Reflexionsmechanismus ein, der durch verstärkendes Lernen trainiert wird. Das Modell verfügt über die Fähigkeit zur Selbstreflexion und Fehlerkorrektur."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra ist die leistungsstärkste Version der Spark-Großmodellreihe, die die Online-Suchverbindung aktualisiert und die Fähigkeit zur Textverständnis und -zusammenfassung verbessert. Es ist eine umfassende Lösung zur Steigerung der Büroproduktivität und zur genauen Reaktion auf Anforderungen und ein führendes intelligentes Produkt in der Branche."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Das Modell hat die höchste Fähigkeit im Inland und übertrifft ausländische Mainstream-Modelle in Aufgaben wie Wissensdatenbanken, langen Texten und kreativer Generierung. Es verfügt auch über branchenführende multimodale Fähigkeiten und zeigt in mehreren autoritativen Bewertungsbenchmarks hervorragende Leistungen."
},
+ "Baichuan4-Air": {
+ "description": "Das Modell hat die höchste Leistungsfähigkeit im Inland und übertrifft ausländische Mainstream-Modelle in Aufgaben wie Wissensdatenbanken, langen Texten und kreativen Generierungen auf Chinesisch. Es verfügt auch über branchenführende multimodale Fähigkeiten und zeigt in mehreren anerkannten Bewertungsbenchmarks hervorragende Leistungen."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Das Modell hat die höchste Leistungsfähigkeit im Inland und übertrifft ausländische Mainstream-Modelle in Aufgaben wie Wissensdatenbanken, langen Texten und kreativen Generierungen auf Chinesisch. Es verfügt auch über branchenführende multimodale Fähigkeiten und zeigt in mehreren anerkannten Bewertungsbenchmarks hervorragende Leistungen."
+ },
+ "DeepSeek-R1": {
+ "description": "Ein hochmodernes, effizientes LLM, das sich auf Schlussfolgerungen, Mathematik und Programmierung spezialisiert hat."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 – das größere und intelligentere Modell im DeepSeek-Paket – wurde in die Llama 70B-Architektur destilliert. Basierend auf Benchmark-Tests und menschlicher Bewertung ist dieses Modell intelligenter als das ursprüngliche Llama 70B, insbesondere bei Aufgaben, die mathematische und faktische Genauigkeit erfordern."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Das DeepSeek-R1-Distill-Modell basiert auf Qwen2.5-Math-1.5B und optimiert die Inferenzleistung durch verstärkendes Lernen und Kaltstartdaten. Das Open-Source-Modell setzt neue Maßstäbe für Multitasking."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Das DeepSeek-R1-Distill-Modell basiert auf Qwen2.5-14B und optimiert die Inferenzleistung durch verstärkendes Lernen und Kaltstartdaten. Das Open-Source-Modell setzt neue Maßstäbe für Multitasking."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "Die DeepSeek-R1-Serie optimiert die Inferenzleistung durch verstärkendes Lernen und Kaltstartdaten, das Open-Source-Modell setzt neue Maßstäbe für Multitasking und übertrifft das Niveau von OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Das DeepSeek-R1-Distill-Modell basiert auf Qwen2.5-Math-7B und optimiert die Inferenzleistung durch verstärkendes Lernen und Kaltstartdaten. Das Open-Source-Modell setzt neue Maßstäbe für Multitasking."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro ist das neueste Upgrade des multimodalen Großmodells, das die Erkennung von Bildern mit beliebiger Auflösung und extremen Seitenverhältnissen unterstützt und die Fähigkeiten zur visuellen Schlussfolgerung, Dokumentenerkennung, Detailverständnis und Befehlsbefolgung verbessert."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite bietet eine extrem hohe Reaktionsgeschwindigkeit und ein hervorragendes Preis-Leistungs-Verhältnis und bietet den Kunden flexiblere Optionen für verschiedene Szenarien. Es unterstützt Schlussfolgerungen und Feinabstimmungen mit einem 128k-Kontextfenster."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite bietet eine extrem hohe Reaktionsgeschwindigkeit und ein hervorragendes Preis-Leistungs-Verhältnis und bietet den Kunden flexiblere Optionen für verschiedene Szenarien. Es unterstützt Schlussfolgerungen und Feinabstimmungen mit einem 32k-Kontextfenster."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite bietet eine extrem hohe Reaktionsgeschwindigkeit und ein hervorragendes Preis-Leistungs-Verhältnis und bietet den Kunden flexiblere Optionen für verschiedene Szenarien. Es unterstützt Schlussfolgerungen und Feinabstimmungen mit einem 4k-Kontextfenster."
+ },
+ "Doubao-pro-128k": {
+ "description": "Das leistungsstärkste Hauptmodell, das sich zur Verarbeitung komplexer Aufgaben eignet und in Szenarien wie Referenzfragen, Zusammenfassungen, Kreativität, Textklassifizierung und Rollenspiel sehr gute Ergebnisse erzielt. Es unterstützt Schlussfolgerungen und Feinabstimmungen mit einem 128k-Kontextfenster."
+ },
+ "Doubao-pro-256k": {
+ "description": "Das leistungsstärkste Hauptmodell, das sich gut für komplexe Aufgaben eignet und in Szenarien wie Referenzfragen, Zusammenfassungen, kreatives Schreiben, Textklassifizierung und Rollenspiel hervorragende Ergebnisse erzielt. Es unterstützt Schlussfolgerungen und Feinabstimmungen mit einem Kontextfenster von 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "Das leistungsstärkste Hauptmodell, das sich zur Verarbeitung komplexer Aufgaben eignet und in Szenarien wie Referenzfragen, Zusammenfassungen, Kreativität, Textklassifizierung und Rollenspiel sehr gute Ergebnisse erzielt. Es unterstützt Schlussfolgerungen und Feinabstimmungen mit einem 32k-Kontextfenster."
+ },
+ "Doubao-pro-4k": {
+ "description": "Das leistungsstärkste Hauptmodell, das sich zur Verarbeitung komplexer Aufgaben eignet und in Szenarien wie Referenzfragen, Zusammenfassungen, Kreativität, Textklassifizierung und Rollenspiel sehr gute Ergebnisse erzielt. Es unterstützt Schlussfolgerungen und Feinabstimmungen mit einem 4k-Kontextfenster."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Das Doubao-vision-Modell ist ein multimodales Großmodell, das von Doubao eingeführt wurde und über starke Fähigkeiten zur Bildverständnis und Schlussfolgerung sowie präzise Befehlsverständnisfähigkeiten verfügt. Das Modell zeigt starke Leistungen bei der Extraktion von Bildtextinformationen und bildbasierten Schlussfolgerungsaufgaben und kann in komplexeren und breiteren visuellen Frage-Antwort-Aufgaben eingesetzt werden."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Das Doubao-vision-Modell ist ein multimodales Großmodell, das von Doubao eingeführt wurde und über starke Fähigkeiten zur Bildverständnis und Schlussfolgerung sowie präzise Befehlsverständnisfähigkeiten verfügt. Das Modell zeigt starke Leistungen bei der Extraktion von Bildtextinformationen und bildbasierten Schlussfolgerungsaufgaben und kann in komplexeren und breiteren visuellen Frage-Antwort-Aufgaben eingesetzt werden."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für großangelegte Sprachverarbeitung, das eine riesige Menge an chinesischen und englischen Texten abdeckt. Es verfügt über starke allgemeine Fähigkeiten und kann die meisten Anforderungen an Dialogfragen, kreative Generierung und Anwendungsfälle von Plugins erfüllen. Es unterstützt die automatische Anbindung an das Baidu-Such-Plugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für großangelegte Sprachverarbeitung, das eine riesige Menge an chinesischen und englischen Texten abdeckt. Es verfügt über starke allgemeine Fähigkeiten und kann die meisten Anforderungen an Dialogfragen, kreative Generierung und Anwendungsfälle von Plugins erfüllen. Es unterstützt die automatische Anbindung an das Baidu-Such-Plugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für großangelegte Sprachverarbeitung, das eine riesige Menge an chinesischen und englischen Texten abdeckt. Es verfügt über starke allgemeine Fähigkeiten und kann die meisten Anforderungen an Dialogfragen, kreative Generierung und Anwendungsfälle von Plugins erfüllen. Es unterstützt die automatische Anbindung an das Baidu-Such-Plugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für ultra-große Sprachverarbeitung, das im Vergleich zu ERNIE 3.5 eine umfassende Verbesserung der Modellfähigkeiten erreicht hat und sich breit für komplexe Aufgaben in verschiedenen Bereichen eignet; unterstützt die automatische Anbindung an das Baidu-Such-Plugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für ultra-große Sprachverarbeitung, das im Vergleich zu ERNIE 3.5 eine umfassende Verbesserung der Modellfähigkeiten erreicht hat und sich breit für komplexe Aufgaben in verschiedenen Bereichen eignet; unterstützt die automatische Anbindung an das Baidu-Such-Plugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Baidus selbstentwickeltes Flaggschiff-Modell für großflächige Sprachverarbeitung, das in vielen komplexen Aufgaben hervorragende Ergebnisse zeigt und umfassend in verschiedenen Bereichen eingesetzt werden kann; unterstützt die automatische Anbindung an Baidu-Suchplugins, um die Aktualität von Antwortinformationen zu gewährleisten. Im Vergleich zu ERNIE 4.0 hat es eine bessere Leistung."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für ultra-große Sprachverarbeitung, das in der Gesamtleistung herausragend ist und sich breit für komplexe Aufgaben in verschiedenen Bereichen eignet; unterstützt die automatische Anbindung an das Baidu-Such-Plugin, um die Aktualität der Antwortinformationen zu gewährleisten. Im Vergleich zu ERNIE 4.0 bietet es eine bessere Leistungsfähigkeit."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Das von Baidu entwickelte Sprachmodell für vertikale Szenarien, das sich für Anwendungen wie Spiel-NPCs, Kundenservice-Dialoge und Rollenspiele eignet. Es hat einen klareren und konsistenteren Charakterstil, eine stärkere Befolgung von Anweisungen und eine bessere Inferenzleistung."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Das von Baidu entwickelte leichte Sprachmodell, das hervorragende Modellleistung und Inferenzleistung kombiniert. Es bietet bessere Ergebnisse als ERNIE Lite und eignet sich für die Inferenznutzung auf AI-Beschleunigungskarten mit geringer Rechenleistung."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Das neueste von Baidu im Jahr 2024 veröffentlichte hochleistungsfähige Sprachmodell, das überragende allgemeine Fähigkeiten bietet und sich als Basis-Modell für Feinabstimmungen eignet, um spezifische Szenarien besser zu bearbeiten, und bietet gleichzeitig hervorragende Inferenzleistung."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Das neueste von Baidu im Jahr 2024 veröffentlichte hochleistungsfähige Sprachmodell, das überragende allgemeine Fähigkeiten bietet und bessere Ergebnisse als ERNIE Speed erzielt. Es eignet sich als Basis-Modell für Feinabstimmungen, um spezifische Szenarien besser zu bearbeiten, und bietet gleichzeitig hervorragende Inferenzleistung."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) ist ein innovatives Modell, das sich für Anwendungen in mehreren Bereichen und komplexe Aufgaben eignet."
},
- "Max-32k": {
- "description": "Spark Max 32K ist mit einer hohen Kontextverarbeitungsfähigkeit ausgestattet, die ein besseres Verständnis des Kontexts und eine stärkere logische Schlussfolgerung ermöglicht. Es unterstützt Texteingaben von bis zu 32K Tokens und eignet sich für Szenarien wie das Lesen langer Dokumente und private Wissensabfragen."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B ist ein leistungsstarkes visuelles Sprachmodell, das multimodale Verarbeitung von Bildern und Text unterstützt und in der Lage ist, Bildinhalte präzise zu erkennen und relevante Beschreibungen oder Antworten zu generieren."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B ist ein leistungsstarkes visuelles Sprachmodell, das multimodale Verarbeitung von Bildern und Text unterstützt und in der Lage ist, Bildinhalte präzise zu erkennen und relevante Beschreibungen oder Antworten zu generieren."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Hervorragende Bildschlussfolgerungsfähigkeiten auf hochauflösenden Bildern, geeignet für Anwendungen im Bereich der visuellen Verständigung."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Fortgeschrittene Bildschlussfolgerungsfähigkeiten für Anwendungen im Bereich der visuellen Verständigung."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct ist eines der neuesten großen Sprachmodelle, die von Alibaba Cloud veröffentlicht wurden. Dieses 72B-Modell hat signifikante Verbesserungen in den Bereichen Codierung und Mathematik. Das Modell bietet auch mehrsprachige Unterstützung und deckt über 29 Sprachen ab, einschließlich Chinesisch und Englisch. Es zeigt signifikante Verbesserungen in der Befolgung von Anweisungen, im Verständnis strukturierter Daten und in der Generierung strukturierter Ausgaben (insbesondere JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct ist eines der neuesten großen Sprachmodelle, die von Alibaba Cloud veröffentlicht wurden. Dieses 7B-Modell hat signifikante Verbesserungen in den Bereichen Codierung und Mathematik. Das Modell bietet auch mehrsprachige Unterstützung und deckt über 29 Sprachen ab, einschließlich Chinesisch und Englisch. Es zeigt signifikante Verbesserungen in der Befolgung von Anweisungen, im Verständnis strukturierter Daten und in der Generierung strukturierter Ausgaben (insbesondere JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Das auf Anweisungen optimierte Textmodell Llama 3.1 wurde für mehrsprachige Dialoganwendungen optimiert und zeigt in vielen verfügbaren Open-Source- und geschlossenen Chat-Modellen in gängigen Branchenbenchmarks hervorragende Leistungen."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO ist eine hochflexible Multi-Modell-Kombination, die darauf abzielt, außergewöhnliche kreative Erlebnisse zu bieten."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Das auf Anweisungen optimierte Textmodell Llama 3.1 wurde für mehrsprachige Dialoganwendungen optimiert und zeigt in vielen verfügbaren Open-Source- und geschlossenen Chat-Modellen in gängigen Branchenbenchmarks hervorragende Leistungen."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Das auf Anweisungen optimierte Textmodell Llama 3.1 wurde für mehrsprachige Dialoganwendungen optimiert und zeigt in vielen verfügbaren Open-Source- und geschlossenen Chat-Modellen in gängigen Branchenbenchmarks hervorragende Leistungen."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Ein fortschrittliches, hochmodernes kleines Sprachmodell mit Sprachverständnis, hervorragenden Schlussfolgerungsfähigkeiten und Textgenerierungsfähigkeiten."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Ein fortschrittliches, hochmodernes kleines Sprachmodell mit Sprachverständnis, hervorragenden Schlussfolgerungsfähigkeiten und Textgenerierungsfähigkeiten."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 ist das fortschrittlichste mehrsprachige Open-Source-Sprachmodell der Llama-Serie, das eine Leistung bietet, die mit einem 405B-Modell vergleichbar ist, und das zu extrem niedrigen Kosten. Es basiert auf der Transformer-Architektur und wurde durch überwachte Feinabstimmung (SFT) und verstärkendes Lernen mit menschlichem Feedback (RLHF) in Bezug auf Nützlichkeit und Sicherheit verbessert. Die auf Anweisungen optimierte Version ist speziell für mehrsprachige Dialoge optimiert und übertrifft in mehreren Branchenbenchmarks viele verfügbare Open-Source- und geschlossene Chat-Modelle. Das Wissensdatum endet im Dezember 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "In der MiniMax-01-Serie haben wir mutige Innovationen vorgenommen: Erstmals wurde die lineare Aufmerksamkeitsmechanismus in großem Maßstab implementiert, sodass die traditionelle Transformer-Architektur nicht mehr die einzige Wahl ist. Dieses Modell hat eine Parameteranzahl von bis zu 456 Milliarden, wobei eine Aktivierung 45,9 Milliarden beträgt. Die Gesamtleistung des Modells kann mit den besten Modellen im Ausland mithalten und kann gleichzeitig effizient den weltweit längsten Kontext von 4 Millionen Tokens verarbeiten, was 32-mal so viel wie GPT-4o und 20-mal so viel wie Claude-3.5-Sonnet ist."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) ist ein hochpräzises Anweisungsmodell, das für komplexe Berechnungen geeignet ist."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) bietet optimierte Sprachausgaben und vielfältige Anwendungsmöglichkeiten."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Aktualisierung des Phi-3-mini-Modells."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 zeigt herausragende Leistungen in verschiedenen visuellen Sprachaufgaben, einschließlich Dokumenten- und Diagrammverständnis, Szenentexterkennung, OCR, wissenschaftlicher und mathematischer Problemlösung."
},
"Phi-3-medium-128k-instruct": {
"description": "Das gleiche Phi-3-medium-Modell, jedoch mit einer größeren Kontextgröße für RAG oder Few-Shot-Prompting."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Ein Modell mit 7 Milliarden Parametern, das eine bessere Qualität als Phi-3-mini bietet und sich auf qualitativ hochwertige, reasoning-dense Daten konzentriert."
},
- "Pro-128k": {
- "description": "Spark Pro-128K ist mit einer extrem großen Kontextverarbeitungsfähigkeit ausgestattet, die bis zu 128K Kontextinformationen verarbeiten kann, besonders geeignet für lange Texte, die eine umfassende Analyse und langfristige logische Verknüpfung erfordern, und bietet in komplexen Textkommunikationen flüssige und konsistente Logik sowie vielfältige Zitationsunterstützung."
+ "Phi-3.5-mini-instruct": {
+ "description": "Aktualisierte Version des Phi-3-mini-Modells."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Aktualisierte Version des Phi-3-vision-Modells."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 zeigt herausragende Leistungen in verschiedenen visuellen Sprachaufgaben, einschließlich Dokumenten- und Diagrammverständnis, Szenentexterkennung, OCR, wissenschaftlicher und mathematischer Problemlösung."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct ist das anweisungsfeinabgestimmte große Sprachmodell der Qwen2-Serie mit einer Parametergröße von 1,5B. Dieses Modell basiert auf der Transformer-Architektur und verwendet Technologien wie die SwiGLU-Aktivierungsfunktion, QKV-Offsets und gruppierte Abfrageaufmerksamkeit. Es zeigt hervorragende Leistungen in der Sprachverständnis, -generierung, Mehrsprachigkeit, Codierung, Mathematik und Inferenz in mehreren Benchmark-Tests und übertrifft die meisten Open-Source-Modelle. Im Vergleich zu Qwen1.5-1.8B-Chat zeigt Qwen2-1.5B-Instruct in Tests wie MMLU, HumanEval, GSM8K, C-Eval und IFEval signifikante Leistungsverbesserungen, obwohl die Parameteranzahl etwas geringer ist."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct ist das anweisungsfeinabgestimmte große Sprachmodell der Qwen2-Serie mit einer Parametergröße von 7B. Dieses Modell basiert auf der Transformer-Architektur und verwendet Technologien wie die SwiGLU-Aktivierungsfunktion, QKV-Offsets und gruppierte Abfrageaufmerksamkeit. Es kann große Eingaben verarbeiten. Das Modell zeigt hervorragende Leistungen in der Sprachverständnis, -generierung, Mehrsprachigkeit, Codierung, Mathematik und Inferenz in mehreren Benchmark-Tests und übertrifft die meisten Open-Source-Modelle und zeigt in bestimmten Aufgaben eine vergleichbare Wettbewerbsfähigkeit mit proprietären Modellen. Qwen2-7B-Instruct übertrifft Qwen1.5-7B-Chat in mehreren Bewertungen und zeigt signifikante Leistungsverbesserungen."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL ist die neueste Iteration des Qwen-VL-Modells, das in visuellen Verständnis-Benchmarks erstklassige Leistungen erzielt."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct ist eines der neuesten großen Sprachmodelle, die von Alibaba Cloud veröffentlicht wurden. Dieses 7B-Modell hat signifikante Verbesserungen in den Bereichen Codierung und Mathematik. Das Modell bietet auch mehrsprachige Unterstützung und deckt über 29 Sprachen ab, einschließlich Chinesisch und Englisch. Es zeigt signifikante Verbesserungen in der Befolgung von Anweisungen, im Verständnis strukturierter Daten und in der Generierung strukturierter Ausgaben (insbesondere JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct ist die neueste Version der von Alibaba Cloud veröffentlichten Reihe von code-spezifischen großen Sprachmodellen. Dieses Modell basiert auf Qwen2.5 und wurde mit 55 Billionen Tokens trainiert, um die Fähigkeiten zur Codegenerierung, Inferenz und Fehlerbehebung erheblich zu verbessern. Es verbessert nicht nur die Codierungsfähigkeiten, sondern bewahrt auch die Vorteile in Mathematik und allgemeinen Fähigkeiten. Das Modell bietet eine umfassendere Grundlage für praktische Anwendungen wie Code-Agenten."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat ist die Open-Source-Version des GLM-4-Modells, das von Zhizhu AI eingeführt wurde. Dieses Modell zeigt hervorragende Leistungen in den Bereichen Semantik, Mathematik, Inferenz, Code und Wissen. Neben der Unterstützung für mehrstufige Dialoge bietet GLM-4-9B-Chat auch fortgeschrittene Funktionen wie Web-Browsing, Code-Ausführung, benutzerdefinierte Tool-Aufrufe (Function Call) und langes Textverständnis. Das Modell unterstützt 26 Sprachen, darunter Chinesisch, Englisch, Japanisch, Koreanisch und Deutsch. In mehreren Benchmark-Tests zeigt GLM-4-9B-Chat hervorragende Leistungen, wie AlignBench-v2, MT-Bench, MMLU und C-Eval. Das Modell unterstützt eine maximale Kontextlänge von 128K und ist für akademische Forschung und kommerzielle Anwendungen geeignet."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 ist ein durch verstärkendes Lernen (RL) gesteuertes Inferenzmodell, das Probleme mit Wiederholungen und Lesbarkeit im Modell löst. Vor dem RL führte DeepSeek-R1 Kaltstartdaten ein, um die Inferenzleistung weiter zu optimieren. Es zeigt in mathematischen, programmierbezogenen und Inferenzaufgaben eine vergleichbare Leistung zu OpenAI-o1 und verbessert die Gesamtleistung durch sorgfältig gestaltete Trainingsmethoden."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 ist ein hybrides Experten (MoE) Sprachmodell mit 6710 Milliarden Parametern, das eine Multi-Head-Latente-Attention (MLA) und DeepSeekMoE-Architektur verwendet, kombiniert mit einer Lastenausgleichsstrategie ohne Hilfskosten, um die Inferenz- und Trainingseffizienz zu optimieren. Durch das Pre-Training auf 14,8 Billionen hochwertigen Tokens und anschließende überwachte Feinabstimmung und verstärktes Lernen übertrifft DeepSeek-V3 in der Leistung andere Open-Source-Modelle und nähert sich führenden geschlossenen Modellen."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma ist eines der leichtgewichtigen, hochmodernen offenen Modellserien, die von Google entwickelt wurden. Es handelt sich um ein großes Sprachmodell mit nur Decoder, das Englisch unterstützt und offene Gewichte, vortrainierte Varianten und anweisungsfeinabgestimmte Varianten bietet. Das Gemma-Modell eignet sich für verschiedene Textgenerierungsaufgaben, einschließlich Fragen und Antworten, Zusammenfassungen und Inferenz. Dieses 9B-Modell wurde mit 80 Billionen Tokens trainiert. Seine relativ kleine Größe ermöglicht es, in ressourcenbeschränkten Umgebungen wie Laptops, Desktop-Computern oder Ihrer eigenen Cloud-Infrastruktur bereitgestellt zu werden, wodurch mehr Menschen Zugang zu modernsten KI-Modellen erhalten und Innovationen gefördert werden."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 ist eine Familie von mehrsprachigen großen Sprachmodellen, die von Meta entwickelt wurden und vortrainierte sowie anweisungsfeinabgestimmte Varianten mit 8B, 70B und 405B Parametern umfasst. Dieses 8B-Anweisungsfeinabgestimmte Modell wurde für mehrsprachige Dialogszenarien optimiert und zeigt in mehreren Branchen-Benchmark-Tests hervorragende Leistungen. Das Modelltraining verwendete über 150 Billionen Tokens aus öffentlichen Daten und nutzte Techniken wie überwachte Feinabstimmung und verstärkendes Lernen mit menschlichem Feedback, um die Nützlichkeit und Sicherheit des Modells zu verbessern. Llama 3.1 unterstützt Text- und Codegenerierung, mit einem Wissensstichtag von Dezember 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview ist ein innovatives Modell für die Verarbeitung natürlicher Sprache, das komplexe Aufgaben der Dialoggenerierung und des Kontextverständnisses effizient bewältigen kann."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview ist ein forschungsorientiertes Modell, das vom Qwen-Team entwickelt wurde und sich auf visuelle Inferenzfähigkeiten konzentriert. Es hat einzigartige Vorteile beim Verständnis komplexer Szenen und der Lösung visuell verwandter mathematischer Probleme."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Als Testversion von Qwen2 bietet Qwen1.5 präzisere Dialogfunktionen durch den Einsatz großer Datenmengen."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ ist das Inferenzmodell der Qwen-Serie. Im Vergleich zu traditionellen, anweisungsoptimierten Modellen verfügt QwQ über Denk- und Schlussfolgerungsfähigkeiten, die eine signifikante Leistungssteigerung bei nachgelagerten Aufgaben ermöglichen, insbesondere bei der Lösung schwieriger Probleme. QwQ-32B ist ein mittelgroßes Inferenzmodell, das im Vergleich zu den fortschrittlichsten Inferenzmodellen (wie DeepSeek-R1, o1-mini) wettbewerbsfähige Leistungen erzielt. Dieses Modell verwendet Technologien wie RoPE, SwiGLU, RMSNorm und Attention QKV Bias und hat eine Netzwerkstruktur mit 64 Schichten und 40 Q-Attention-Köpfen (im GQA-Architektur sind es 8 KV)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) bietet schnelle Antworten und natürliche Dialogfähigkeiten, die sich für mehrsprachige Umgebungen eignen."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview ist das neueste experimentelle Forschungsmodell von Qwen, das sich auf die Verbesserung der KI-Inferenzfähigkeiten konzentriert. Durch die Erforschung komplexer Mechanismen wie Sprachmischung und rekursive Inferenz bietet es Hauptvorteile wie starke Analysefähigkeiten, mathematische und Programmierfähigkeiten. Gleichzeitig gibt es Herausforderungen wie Sprachwechsel, Inferenzzyklen, Sicherheitsüberlegungen und Unterschiede in anderen Fähigkeiten."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct ist das anweisungsfeinabgestimmte große Sprachmodell der Qwen2-Serie mit einer Parametergröße von 1,5B. Dieses Modell basiert auf der Transformer-Architektur und verwendet Technologien wie die SwiGLU-Aktivierungsfunktion, QKV-Offsets und gruppierte Abfrageaufmerksamkeit. Es zeigt hervorragende Leistungen in der Sprachverständnis, -generierung, Mehrsprachigkeit, Codierung, Mathematik und Inferenz in mehreren Benchmark-Tests und übertrifft die meisten Open-Source-Modelle. Im Vergleich zu Qwen1.5-1.8B-Chat zeigt Qwen2-1.5B-Instruct in Tests wie MMLU, HumanEval, GSM8K, C-Eval und IFEval signifikante Leistungsverbesserungen, obwohl die Parameteranzahl etwas geringer ist."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 ist ein fortschrittliches allgemeines Sprachmodell, das eine Vielzahl von Anweisungsarten unterstützt."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct ist das anweisungsfeinabgestimmte große Sprachmodell der Qwen2-Serie mit einer Parametergröße von 72B. Dieses Modell basiert auf der Transformer-Architektur und verwendet Technologien wie die SwiGLU-Aktivierungsfunktion, QKV-Offsets und gruppierte Abfrageaufmerksamkeit. Es kann große Eingaben verarbeiten. Das Modell zeigt hervorragende Leistungen in der Sprachverständnis, -generierung, Mehrsprachigkeit, Codierung, Mathematik und Inferenz in mehreren Benchmark-Tests und übertrifft die meisten Open-Source-Modelle und zeigt in bestimmten Aufgaben eine vergleichbare Wettbewerbsfähigkeit mit proprietären Modellen."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL ist die neueste Iteration des Qwen-VL-Modells, das in visuellen Verständnis-Benchmarks erstklassige Leistungen erzielt."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 ist eine brandneue Serie von großen Sprachmodellen, die darauf abzielt, die Verarbeitung von Anweisungsaufgaben zu optimieren."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 ist eine brandneue Serie von großen Sprachmodellen, die darauf abzielt, die Verarbeitung von Anweisungsaufgaben zu optimieren."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 ist eine brandneue Serie von großen Sprachmodellen mit verbesserter Verständnis- und Generierungsfähigkeit."
+ "description": "Ein großes Sprachmodell, das vom Alibaba Cloud Tongyi Qianwen-Team entwickelt wurde."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 ist eine neue Serie großer Sprachmodelle mit stärkeren Verständnis- und Generierungsfähigkeiten."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 ist eine neue Serie großer Sprachmodelle, die darauf abzielt, die Verarbeitung von instructiven Aufgaben zu optimieren."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 ist eine brandneue Serie von großen Sprachmodellen, die darauf abzielt, die Verarbeitung von Anweisungsaufgaben zu optimieren."
},
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 ist eine neue Serie großer Sprachmodelle, die darauf abzielt, die Verarbeitung von instructiven Aufgaben zu optimieren."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder konzentriert sich auf das Programmieren."
+ },
"Qwen/Qwen2.5-Coder-7B-Instruct": {
- "description": "Qwen2.5-Coder konzentriert sich auf die Programmierung."
+ "description": "Qwen2.5-Coder-7B-Instruct ist die neueste Version der von Alibaba Cloud veröffentlichten Reihe von code-spezifischen großen Sprachmodellen. Dieses Modell basiert auf Qwen2.5 und wurde mit 55 Billionen Tokens trainiert, um die Fähigkeiten zur Codegenerierung, Inferenz und Fehlerbehebung erheblich zu verbessern. Es verbessert nicht nur die Codierungsfähigkeiten, sondern bewahrt auch die Vorteile in Mathematik und allgemeinen Fähigkeiten. Das Modell bietet eine umfassendere Grundlage für praktische Anwendungen wie Code-Agenten."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 ist die neueste Reihe des Qwen-Modells, das 128k Kontext unterstützt. Im Vergleich zu den derzeit besten Open-Source-Modellen übertrifft Qwen2-72B in den Bereichen natürliche Sprachverständnis, Wissen, Code, Mathematik und Mehrsprachigkeit deutlich die führenden Modelle."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 ist die neueste Reihe des Qwen-Modells, das in der Lage ist, die besten Open-Source-Modelle ähnlicher Größe oder sogar größerer Modelle zu übertreffen. Qwen2 7B hat in mehreren Bewertungen signifikante Vorteile erzielt, insbesondere im Bereich Code und Verständnis der chinesischen Sprache."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B ist ein leistungsstarkes visuelles Sprachmodell, das multimodale Verarbeitung von Bildern und Text unterstützt und in der Lage ist, Bildinhalte präzise zu erkennen und relevante Beschreibungen oder Antworten zu generieren."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct ist ein großes Sprachmodell mit 14 Milliarden Parametern, das hervorragende Leistungen bietet, für chinesische und mehrsprachige Szenarien optimiert ist und Anwendungen wie intelligente Fragen und Antworten sowie Inhaltserstellung unterstützt."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct ist ein großes Sprachmodell mit 32 Milliarden Parametern, das eine ausgewogene Leistung bietet, für chinesische und mehrsprachige Szenarien optimiert ist und Anwendungen wie intelligente Fragen und Antworten sowie Inhaltserstellung unterstützt."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct unterstützt 16k Kontext und generiert lange Texte über 8K. Es unterstützt Funktionsaufrufe und nahtlose Interaktionen mit externen Systemen, was die Flexibilität und Skalierbarkeit erheblich verbessert. Das Wissen des Modells hat deutlich zugenommen, und die Codierungs- und mathematischen Fähigkeiten wurden erheblich verbessert, mit Unterstützung für über 29 Sprachen."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct ist ein großes Sprachmodell mit 7 Milliarden Parametern, das Funktionsaufrufe unterstützt und nahtlos mit externen Systemen interagiert, was die Flexibilität und Skalierbarkeit erheblich erhöht. Es ist für chinesische und mehrsprachige Szenarien optimiert und unterstützt Anwendungen wie intelligente Fragen und Antworten sowie Inhaltserstellung."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct ist ein auf großflächigem Pre-Training basierendes Programmiermodell, das über starke Fähigkeiten zur Codeverstehung und -generierung verfügt und effizient verschiedene Programmieraufgaben bearbeiten kann. Es eignet sich besonders gut für intelligente Codeerstellung, automatisierte Skripterstellung und die Beantwortung von Programmierfragen."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct ist ein großes Sprachmodell, das speziell für die Codegenerierung, das Verständnis von Code und effiziente Entwicklungsszenarien entwickelt wurde. Es verwendet eine branchenführende Parametergröße von 32B und kann vielfältige Programmieranforderungen erfüllen."
+ },
+ "SenseChat": {
+ "description": "Basisversion des Modells (V4) mit 4K Kontextlänge, die über starke allgemeine Fähigkeiten verfügt."
+ },
+ "SenseChat-128K": {
+ "description": "Basisversion des Modells (V4) mit 128K Kontextlänge, das in Aufgaben des Verständnisses und der Generierung langer Texte hervorragende Leistungen zeigt."
+ },
+ "SenseChat-32K": {
+ "description": "Basisversion des Modells (V4) mit 32K Kontextlänge, flexibel einsetzbar in verschiedenen Szenarien."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math konzentriert sich auf die Problemlösung im Bereich Mathematik und bietet professionelle Lösungen für schwierige Aufgaben."
+ "SenseChat-5": {
+ "description": "Die neueste Modellversion (V5.5) mit 128K Kontextlänge hat signifikante Verbesserungen in den Bereichen mathematische Schlussfolgerungen, englische Konversation, Befolgen von Anweisungen und Verständnis langer Texte, vergleichbar mit GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "Dies ist die neueste Version basierend auf V5.5, die im Vergleich zur vorherigen Version signifikante Verbesserungen in den grundlegenden Fähigkeiten in Chinesisch und Englisch, im Chat, in Naturwissenschaften, in Geisteswissenschaften, im Schreiben, in mathematischer Logik und in der Wortanzahlkontrolle aufweist."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Mit 32K Kontextlänge übertrifft es GPT-4 im Verständnis von Konversationen auf Kantonesisch und kann in mehreren Bereichen wie Wissen, Schlussfolgerungen, Mathematik und Programmierung mit GPT-4 Turbo konkurrieren."
+ },
+ "SenseChat-Character": {
+ "description": "Standardmodell mit 8K Kontextlänge und hoher Reaktionsgeschwindigkeit."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Premium-Modell mit 32K Kontextlänge, das umfassende Verbesserungen in den Fähigkeiten bietet und sowohl chinesische als auch englische Konversationen unterstützt."
+ },
+ "SenseChat-Turbo": {
+ "description": "Geeignet für schnelle Fragen und Antworten sowie Szenarien zur Feinabstimmung des Modells."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "Dies ist das neueste leichte Modell, das über 90 % der Fähigkeiten des Vollmodells erreicht und die Kosten für die Inferenz erheblich senkt."
+ },
+ "SenseChat-Vision": {
+ "description": "Das neueste Modell (V5.5) unterstützt die Eingabe mehrerer Bilder und optimiert umfassend die grundlegenden Fähigkeiten des Modells. Es hat signifikante Verbesserungen in der Erkennung von Objektattributen, räumlichen Beziehungen, Aktionsereignissen, Szenenverständnis, Emotionserkennung, logischem Wissen und Textverständnis und -generierung erreicht."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Das zweite Modell der Skylark-Reihe, das Skylark2-lite-Modell bietet eine hohe Reaktionsgeschwindigkeit und eignet sich für Szenarien mit hohen Echtzeitanforderungen, kostensensitiven Anforderungen und geringeren Genauigkeitsanforderungen, mit einer Kontextfensterlänge von 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Das zweite Modell der Skylark-Reihe, die Skylark2-pro-Version hat eine hohe Modellgenauigkeit und eignet sich für komplexere Textgenerierungsszenarien, wie z. B. professionelle Texterstellung, Romankreation und hochwertige Übersetzungen, mit einer Kontextfensterlänge von 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Das zweite Modell der Skylark-Reihe, die Skylark2-pro-Version hat eine hohe Modellgenauigkeit und eignet sich für komplexere Textgenerierungsszenarien, wie z. B. professionelle Texterstellung, Romankreation und hochwertige Übersetzungen, mit einer Kontextfensterlänge von 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Das zweite Modell der Skylark-Reihe, das Skylark2-pro-character-Modell hat hervorragende Fähigkeiten im Rollenspiel und Chat, kann sich entsprechend den Anforderungen des Benutzers verkleiden und bietet natürliche und flüssige Dialoginhalte. Es eignet sich für den Aufbau von Chatbots, virtuellen Assistenten und Online-Kundensupport und bietet eine hohe Reaktionsgeschwindigkeit."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Das zweite Modell der Skylark-Reihe, das Skylark2-pro-turbo-8k bietet schnellere Schlussfolgerungen und niedrigere Kosten, mit einer Kontextfensterlänge von 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B ist das Open-Source-Modell der ChatGLM-Serie, das von Zhizhu AI entwickelt wurde. Dieses Modell bewahrt die hervorragenden Eigenschaften der Vorgängermodelle, wie flüssige Dialoge und niedrige Bereitstellungskosten, während es neue Funktionen einführt. Es verwendet vielfältigere Trainingsdaten, eine größere Anzahl an Trainingsschritten und eine sinnvollere Trainingsstrategie und zeigt hervorragende Leistungen unter den vortrainierten Modellen mit weniger als 10B. ChatGLM3-6B unterstützt mehrstufige Dialoge, Tool-Aufrufe, Code-Ausführung und Agentenaufgaben in komplexen Szenarien. Neben dem Dialogmodell wurden auch das Basis-Modell ChatGLM-6B-Base und das lange Textdialogmodell ChatGLM3-6B-32K als Open Source veröffentlicht. Dieses Modell ist vollständig für akademische Forschung geöffnet und erlaubt auch kostenlose kommerzielle Nutzung nach Registrierung."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B ist die Open-Source-Version, die ein optimiertes Dialogerlebnis für Konversationsanwendungen bietet."
},
+ "TeleAI/TeleChat2": {
+ "description": "Das TeleChat2-Modell ist ein generatives semantisches Großmodell, das von China Telecom von Grund auf neu entwickelt wurde und Funktionen wie Enzyklopädiefragen, Codegenerierung und lange Textgenerierung unterstützt. Es bietet Benutzern Beratungsdienste, ermöglicht Dialoginteraktionen mit Benutzern, beantwortet Fragen, unterstützt bei der Erstellung und hilft Benutzern effizient und bequem, Informationen, Wissen und Inspiration zu erhalten. Das Modell zeigt hervorragende Leistungen in den Bereichen Halluzinationsprobleme, lange Textgenerierung und logisches Verständnis."
+ },
+ "TeleAI/TeleMM": {
+ "description": "Das TeleMM-Modell ist ein multimodales Großmodell, das von China Telecom entwickelt wurde und in der Lage ist, Texte, Bilder und andere Modalitäten zu verarbeiten. Es unterstützt Funktionen wie Bildverständnis und Diagrammanalyse und bietet Benutzern multimodale Verständnisdienste. Das Modell kann mit Benutzern multimodal interagieren, den Eingabeinhalt genau verstehen, Fragen beantworten, bei der Erstellung helfen und effizient multimodale Informationen und Inspirationsunterstützung bereitstellen. Es zeigt hervorragende Leistungen in multimodalen Aufgaben wie feinkörniger Wahrnehmung und logischem Schlussfolgern."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct ist eines der neuesten großen Sprachmodelle, die von Alibaba Cloud veröffentlicht wurden. Dieses 72B-Modell hat signifikante Verbesserungen in den Bereichen Codierung und Mathematik. Das Modell bietet auch mehrsprachige Unterstützung und deckt über 29 Sprachen ab, einschließlich Chinesisch und Englisch. Es zeigt signifikante Verbesserungen in der Befolgung von Anweisungen, im Verständnis strukturierter Daten und in der Generierung strukturierter Ausgaben (insbesondere JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B hat die hervorragenden allgemeinen Sprachfähigkeiten des ursprünglichen Modells beibehalten und durch inkrementelles Training von 500 Milliarden hochwertigen Tokens die mathematische Logik und Codierungsfähigkeiten erheblich verbessert."
+ },
"abab5.5-chat": {
"description": "Für produktivitätsorientierte Szenarien konzipiert, unterstützt es die Verarbeitung komplexer Aufgaben und die effiziente Textgenerierung, geeignet für professionelle Anwendungen."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Für chinesische Charakterdialoge optimiert, bietet es flüssige und den chinesischen Ausdrucksgewohnheiten entsprechende Dialoggenerierung."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Das Open-Source-Funktionsaufrufmodell von Fireworks bietet hervorragende Anweisungsdurchführungsfähigkeiten und anpassbare Funktionen."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Das neueste Firefunction-v2 von Fireworks ist ein leistungsstarkes Funktionsaufrufmodell, das auf Llama-3 basiert und durch zahlreiche Optimierungen besonders für Funktionsaufrufe, Dialoge und Anweisungsverfolgung geeignet ist."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 ist ein hochmodernes großes Sprachmodell, das durch verstärktes Lernen und Optimierung mit Kaltstartdaten hervorragende Leistungen in Inferenz, Mathematik und Programmierung bietet."
},
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b ist ein visuelles Sprachmodell, das sowohl Bild- als auch Texteingaben verarbeiten kann und für multimodale Aufgaben geeignet ist, nachdem es mit hochwertigen Daten trainiert wurde."
- },
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Das Gemma 2 9B Instruct-Modell basiert auf früheren Google-Technologien und eignet sich für eine Vielzahl von Textgenerierungsaufgaben wie Fragen beantworten, Zusammenfassen und Schlussfolgern."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Ein leistungsstarkes Mixture-of-Experts (MoE) Sprachmodell von Deepseek mit insgesamt 671B Parametern, wobei 37B Parameter pro Token aktiviert werden."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Das Llama 3 70B Instruct-Modell ist speziell für mehrsprachige Dialoge und natürliche Sprachverständnis optimiert und übertrifft die meisten Wettbewerbsmodelle."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Das Llama 3 70B Instruct-Modell (HF-Version) entspricht den offiziellen Ergebnissen und eignet sich für hochwertige Anweisungsverfolgungsaufgaben."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Das Llama 3 8B Instruct-Modell ist für Dialoge und mehrsprachige Aufgaben optimiert und bietet hervorragende und effiziente Leistungen."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Das Llama 3.1 8B Instruct-Modell ist speziell für mehrsprachige Dialoge optimiert und kann die meisten Open-Source- und Closed-Source-Modelle in gängigen Branchenbenchmarks übertreffen."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Meta's 11B Parameter instruct-Modell für Bildverarbeitung. Dieses Modell ist optimiert für visuelle Erkennung, Bildverarbeitung, Bildbeschreibung und die Beantwortung allgemeiner Fragen zu Bildern. Es kann visuelle Daten wie Diagramme und Grafiken verstehen und schließt die Lücke zwischen visuellen und sprachlichen Informationen, indem es textuelle Beschreibungen der Bilddetails generiert."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Llama 3.2 3B instruct-Modell ist ein leichtgewichtiges mehrsprachiges Modell, das von Meta veröffentlicht wurde. Dieses Modell zielt darauf ab, die Effizienz zu steigern und bietet im Vergleich zu größeren Modellen signifikante Verbesserungen in Bezug auf Latenz und Kosten. Anwendungsbeispiele für dieses Modell sind Abfragen und Aufforderungsneuschreibungen sowie Schreibassistenz."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Meta's 90B Parameter instruct-Modell für Bildverarbeitung. Dieses Modell ist optimiert für visuelle Erkennung, Bildverarbeitung, Bildbeschreibung und die Beantwortung allgemeiner Fragen zu Bildern. Es kann visuelle Daten wie Diagramme und Grafiken verstehen und schließt die Lücke zwischen visuellen und sprachlichen Informationen, indem es textuelle Beschreibungen der Bilddetails generiert."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct ist die aktualisierte Version von Llama 3.1 70B aus dem Dezember. Dieses Modell wurde auf der Grundlage von Llama 3.1 70B (veröffentlicht im Juli 2024) verbessert und bietet erweiterte Funktionen für Toolaufrufe, mehrsprachige Textunterstützung sowie mathematische und Programmierfähigkeiten. Das Modell erreicht branchenführende Leistungen in den Bereichen Inferenz, Mathematik und Befehlsbefolgung und bietet eine ähnliche Leistung wie 3.1 405B, während es gleichzeitig signifikante Vorteile in Bezug auf Geschwindigkeit und Kosten bietet."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Ein 24B-Parameter-Modell mit fortschrittlichen Fähigkeiten, die mit größeren Modellen vergleichbar sind."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Das Mixtral MoE 8x22B Instruct-Modell unterstützt durch seine große Anzahl an Parametern und Multi-Expert-Architektur die effiziente Verarbeitung komplexer Aufgaben."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Das Mixtral MoE 8x7B Instruct-Modell bietet durch seine Multi-Expert-Architektur effiziente Anweisungsverfolgung und -ausführung."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Das Mixtral MoE 8x7B Instruct-Modell (HF-Version) bietet die gleiche Leistung wie die offizielle Implementierung und eignet sich für verschiedene effiziente Anwendungsszenarien."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "Das MythoMax L2 13B-Modell kombiniert neuartige Kombinations-Technologien und ist besonders gut in Erzählungen und Rollenspielen."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Das Phi 3 Vision Instruct-Modell ist ein leichtgewichtiges multimodales Modell, das komplexe visuelle und textuelle Informationen verarbeiten kann und über starke Schlussfolgerungsfähigkeiten verfügt."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "Das StarCoder 15.5B-Modell unterstützt fortgeschrittene Programmieraufgaben und hat verbesserte mehrsprachige Fähigkeiten, die sich für komplexe Codegenerierung und -verständnis eignen."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Das QwQ-Modell ist ein experimentelles Forschungsmodell, das vom Qwen-Team entwickelt wurde und sich auf die Verbesserung der KI-Inferenzfähigkeiten konzentriert."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Die 72B-Version des Qwen-VL-Modells ist das neueste Ergebnis von Alibabas Iteration und repräsentiert fast ein Jahr an Innovation."
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 ist eine Reihe von Sprachmodellen mit ausschließlich Decodern, die vom Alibaba Cloud Qwen-Team entwickelt wurde. Diese Modelle sind in verschiedenen Größen erhältlich, darunter 0.5B, 1.5B, 3B, 7B, 14B, 32B und 72B, mit Basis- und instruct-Varianten."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "Das StarCoder 7B-Modell wurde für über 80 Programmiersprachen trainiert und bietet hervorragende Programmierausfüllfähigkeiten und Kontextverständnis."
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct ist die neueste Version der von Alibaba Cloud veröffentlichten Reihe von code-spezifischen großen Sprachmodellen. Dieses Modell basiert auf Qwen2.5 und wurde mit 55 Billionen Tokens trainiert, um die Fähigkeiten zur Codegenerierung, Inferenz und Fehlerbehebung erheblich zu verbessern. Es verbessert nicht nur die Codierungsfähigkeiten, sondern bewahrt auch die Vorteile in Mathematik und allgemeinen Fähigkeiten. Das Modell bietet eine umfassendere Grundlage für praktische Anwendungen wie Code-Agenten."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Das Yi-Large-Modell bietet hervorragende mehrsprachige Verarbeitungsfähigkeiten und kann für verschiedene Sprachgenerierungs- und Verständnisaufgaben eingesetzt werden."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Ein mehrsprachiges Modell mit 52 Milliarden Parametern (12 Milliarden aktiv), das ein 256K langes Kontextfenster, Funktionsaufrufe, strukturierte Ausgaben und fundierte Generierung bietet."
},
- "ai21-jamba-instruct": {
- "description": "Ein produktionsreifes Mamba-basiertes LLM-Modell, das eine erstklassige Leistung, Qualität und Kosteneffizienz erreicht."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet hebt den Branchenstandard an, übertrifft die Konkurrenzmodelle und Claude 3 Opus und zeigt in umfassenden Bewertungen hervorragende Leistungen, während es die Geschwindigkeit und Kosten unserer mittleren Modelle beibehält."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet setzt neue Maßstäbe in der Branche, übertrifft die Modelle der Konkurrenz und Claude 3 Opus, und zeigt in umfassenden Bewertungen hervorragende Leistungen, während es die Geschwindigkeit und Kosten unserer mittelgroßen Modelle beibehält."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku ist das schnellste und kompakteste Modell von Anthropic und bietet nahezu sofortige Reaktionsgeschwindigkeiten. Es kann schnell einfache Anfragen und Anforderungen beantworten. Kunden werden in der Lage sein, nahtlose AI-Erlebnisse zu schaffen, die menschliche Interaktionen nachahmen. Claude 3 Haiku kann Bilder verarbeiten und Textausgaben zurückgeben, mit einem Kontextfenster von 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus ist das leistungsstärkste Modell von Anthropic zur Bearbeitung hochkomplexer Aufgaben. Es zeichnet sich durch hervorragende Leistung, Intelligenz, Flüssigkeit und Verständnis aus."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku ist das schnellste nächste Generation Modell von Anthropic. Im Vergleich zu Claude 3 Haiku hat Claude 3.5 Haiku in allen Fähigkeiten Fortschritte gemacht und übertrifft in vielen intellektuellen Benchmark-Tests das größte Modell der vorherigen Generation, Claude 3 Opus."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet bietet Fähigkeiten, die über Opus hinausgehen, und eine schnellere Geschwindigkeit als Sonnet, während es den gleichen Preis wie Sonnet beibehält. Sonnet ist besonders gut in Programmierung, Datenwissenschaft, visueller Verarbeitung und Agentenaufgaben."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet ist das intelligenteste Modell von Anthropic bis heute und das erste hybride Inferenzmodell auf dem Markt. Claude 3.7 Sonnet kann nahezu sofortige Antworten oder verlängerte, schrittweise Überlegungen erzeugen, wobei die Benutzer diesen Prozess klar nachvollziehen können. Sonnet ist besonders gut in den Bereichen Programmierung, Datenwissenschaft, visuelle Verarbeitung und Agentenaufgaben."
+ },
"aya": {
"description": "Aya 23 ist ein mehrsprachiges Modell von Cohere, das 23 Sprachen unterstützt und die Anwendung in einer Vielzahl von Sprachen erleichtert."
},
"aya:35b": {
"description": "Aya 23 ist ein mehrsprachiges Modell von Cohere, das 23 Sprachen unterstützt und die Anwendung in einer Vielzahl von Sprachen erleichtert."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B ist ein Open-Source-Sprachmodell mit 13 Milliarden Parametern, das von Baichuan Intelligence entwickelt wurde und in autorisierten chinesischen und englischen Benchmarks die besten Ergebnisse in seiner Größenordnung erzielt hat."
+ },
"charglm-3": {
"description": "CharGLM-3 ist für Rollenspiele und emotionale Begleitung konzipiert und unterstützt extrem lange Mehrfachgedächtnisse und personalisierte Dialoge, mit breiter Anwendung."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 bietet Unternehmen Fortschritte in kritischen Fähigkeiten, einschließlich branchenführenden 200K Token Kontext, erheblich reduzierter Häufigkeit von Modellillusionen, Systemaufforderungen und einer neuen Testfunktion: Werkzeugaufrufe."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku ist das schnellste nächste Modell von Anthropic. Im Vergleich zu Claude 3 Haiku hat Claude 3.5 Haiku in allen Fähigkeiten Verbesserungen erzielt und übertrifft das vorherige größte Modell, Claude 3 Opus, in vielen intellektuellen Benchmark-Tests."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet bietet Fähigkeiten, die über Opus hinausgehen, und ist schneller als Sonnet, während es den gleichen Preis wie Sonnet beibehält. Sonnet ist besonders gut in Programmierung, Datenwissenschaft, visueller Verarbeitung und Agenturaufgaben."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet bietet überlegene Fähigkeiten im Vergleich zu Opus und schnellere Geschwindigkeiten als Sonnet, während es den gleichen Preis wie Sonnet beibehält. Sonnet ist besonders gut in den Bereichen Programmierung, Datenwissenschaft, visuelle Verarbeitung und Aufgabenübertragung."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet hebt den Branchenstandard an, übertrifft die Modelle der Konkurrenz und Claude 3 Opus, und zeigt in umfassenden Bewertungen hervorragende Leistungen, während es die Geschwindigkeit und Kosten unserer mittelgroßen Modelle beibehält."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku ist das schnellste und kompakteste Modell von Anthropic, das darauf abzielt, nahezu sofortige Antworten zu liefern. Es bietet schnelle und präzise zielgerichtete Leistungen."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet bietet eine ideale Balance zwischen Intelligenz und Geschwindigkeit für Unternehmensarbeitslasten. Es bietet maximalen Nutzen zu einem niedrigeren Preis, ist zuverlässig und für großflächige Bereitstellungen geeignet."
},
- "claude-instant-1.2": {
- "description": "Das Modell von Anthropic wird für latenzarme, hochdurchsatzfähige Textgenerierung verwendet und unterstützt die Generierung von Hunderten von Seiten Text."
- },
"codegeex-4": {
"description": "CodeGeeX-4 ist ein leistungsstarker AI-Programmierassistent, der intelligente Fragen und Codevervollständigung in verschiedenen Programmiersprachen unterstützt und die Entwicklungseffizienz steigert."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B ist ein mehrsprachiges Code-Generierungsmodell, das umfassende Funktionen unterstützt, darunter Code-Vervollständigung und -Generierung, Code-Interpreter, Websuche, Funktionsaufrufe und repository-weite Codefragen und -antworten, und deckt verschiedene Szenarien der Softwareentwicklung ab. Es ist das führende Code-Generierungsmodell mit weniger als 10B Parametern."
+ },
"codegemma": {
"description": "CodeGemma ist ein leichtgewichtiges Sprachmodell, das speziell für verschiedene Programmieraufgaben entwickelt wurde und schnelle Iterationen und Integrationen unterstützt."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama ist ein LLM, das sich auf die Codegenerierung und -diskussion konzentriert und eine breite Unterstützung für Programmiersprachen bietet, die sich für Entwicklerumgebungen eignet."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama ist ein LLM, das sich auf die Codegenerierung und -diskussion konzentriert und eine breite Unterstützung für Programmiersprachen bietet, die für Entwicklerumgebungen geeignet ist."
+ },
"codellama:13b": {
"description": "Code Llama ist ein LLM, das sich auf die Codegenerierung und -diskussion konzentriert und eine breite Unterstützung für Programmiersprachen bietet, die sich für Entwicklerumgebungen eignet."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ ist ein leistungsstarkes großes Sprachmodell, das speziell für reale Unternehmensszenarien und komplexe Anwendungen entwickelt wurde."
},
+ "dall-e-2": {
+ "description": "Zweite Generation des DALL·E-Modells, unterstützt realistischere und genauere Bildgenerierung, mit einer Auflösung, die viermal so hoch ist wie die der ersten Generation."
+ },
+ "dall-e-3": {
+ "description": "Das neueste DALL·E-Modell, veröffentlicht im November 2023. Unterstützt realistischere und genauere Bildgenerierung mit verbesserter Detailgenauigkeit."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct bietet zuverlässige Anweisungsverarbeitungsfähigkeiten und unterstützt Anwendungen in verschiedenen Branchen."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 ist ein durch verstärkendes Lernen (RL) gesteuertes Inferenzmodell, das die Probleme der Wiederholbarkeit und Lesbarkeit im Modell löst. Vor dem RL führte DeepSeek-R1 Kaltstartdaten ein, um die Inferenzleistung weiter zu optimieren. Es zeigt in mathematischen, programmierbezogenen und Inferenzaufgaben eine vergleichbare Leistung zu OpenAI-o1 und verbessert durch sorgfältig gestaltete Trainingsmethoden die Gesamteffizienz."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "Das DeepSeek-R1-Distill-Modell optimiert die Inferenzleistung durch verstärkendes Lernen und Kaltstartdaten. Das Open-Source-Modell setzt neue Maßstäbe für Multitasking."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B ist ein destilliertes Modell, das auf Llama-3.1-8B basiert. Dieses Modell wurde mit Beispielen, die von DeepSeek-R1 generiert wurden, feinabgestimmt und zeigt hervorragende Inferenzfähigkeiten. Es hat in mehreren Benchmark-Tests gut abgeschnitten, darunter eine Genauigkeit von 89,1 % in MATH-500, eine Bestehensquote von 50,4 % in AIME 2024 und eine Bewertung von 1205 in CodeForces, was starke mathematische und Programmierfähigkeiten für ein 8B-Modell demonstriert."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Das DeepSeek-R1-Distill-Modell optimiert die Inferenzleistung durch verstärkendes Lernen und Kaltstartdaten. Das Open-Source-Modell setzt neue Maßstäbe für Multitasking."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Das DeepSeek-R1-Distill-Modell optimiert die Inferenzleistung durch verstärkendes Lernen und Kaltstartdaten. Das Open-Source-Modell setzt neue Maßstäbe für Multitasking."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B ist ein Modell, das durch Wissensdestillation aus Qwen2.5-32B gewonnen wurde. Dieses Modell wurde mit 800.000 ausgewählten Beispielen, die von DeepSeek-R1 generiert wurden, feinabgestimmt und zeigt herausragende Leistungen in mehreren Bereichen wie Mathematik, Programmierung und Inferenz. Es hat in mehreren Benchmark-Tests, darunter AIME 2024, MATH-500 und GPQA Diamond, hervorragende Ergebnisse erzielt, wobei es in MATH-500 eine Genauigkeit von 94,3 % erreicht hat und damit starke mathematische Schlussfolgerungsfähigkeiten demonstriert."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B ist ein Modell, das durch Wissensdestillation aus Qwen2.5-Math-7B gewonnen wurde. Dieses Modell wurde mit 800.000 ausgewählten Beispielen, die von DeepSeek-R1 generiert wurden, feinabgestimmt und zeigt hervorragende Inferenzfähigkeiten. Es hat in mehreren Benchmark-Tests, darunter eine Genauigkeit von 92,8 % in MATH-500, eine Bestehensquote von 55,5 % in AIME 2024 und eine Bewertung von 1189 in CodeForces, was starke mathematische und Programmierfähigkeiten für ein 7B-Modell demonstriert."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 vereint die hervorragenden Merkmale früherer Versionen und verbessert die allgemeinen und kodierenden Fähigkeiten."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 ist ein hybrides Expertenmodell (MoE) mit 6710 Milliarden Parametern, das eine Multi-Head-Latent-Attention (MLA) und die DeepSeekMoE-Architektur verwendet, kombiniert mit einer Lastenausgleichsstrategie ohne Hilfskosten, um die Inferenz- und Trainingseffizienz zu optimieren. Durch das Pre-Training auf 14,8 Billionen hochwertigen Tokens und anschließendes überwachten Feintuning und verstärkendes Lernen übertrifft DeepSeek-V3 in der Leistung andere Open-Source-Modelle und nähert sich führenden Closed-Source-Modellen."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B ist ein fortschrittliches Modell, das für komplexe Dialoge trainiert wurde."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "Hochmodernes, effizientes LLM, das auf Schlussfolgern, Mathematik und Programmierung spezialisiert ist."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 ist ein hybrides Expertenmodell (MoE) für visuelle Sprache, das auf DeepSeekMoE-27B basiert und eine spärliche Aktivierung der MoE-Architektur verwendet, um außergewöhnliche Leistungen bei der Aktivierung von nur 4,5 Milliarden Parametern zu erzielen. Dieses Modell zeigt hervorragende Leistungen in mehreren Aufgaben, darunter visuelle Fragenbeantwortung, optische Zeichenerkennung, Dokument-/Tabellen-/Diagrammverständnis und visuelle Lokalisierung."
+ },
"deepseek-chat": {
"description": "Ein neues Open-Source-Modell, das allgemeine und Codefähigkeiten kombiniert. Es bewahrt nicht nur die allgemeinen Dialogfähigkeiten des ursprünglichen Chat-Modells und die leistungsstarken Codeverarbeitungsfähigkeiten des Coder-Modells, sondern stimmt auch besser mit menschlichen Präferenzen überein. Darüber hinaus hat DeepSeek-V2.5 in mehreren Bereichen wie Schreibaufgaben und Befolgung von Anweisungen erhebliche Verbesserungen erzielt."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B ist ein Code-Sprachmodell, das auf 20 Billionen Daten trainiert wurde, von denen 87 % Code und 13 % in Chinesisch und Englisch sind. Das Modell führt eine Fenstergröße von 16K und Aufgaben zur Lückenergänzung ein und bietet projektbezogene Code-Vervollständigung und Fragmentfüllfunktionen."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 ist ein Open-Source-Mischexperten-Code-Modell, das in Codeaufgaben hervorragende Leistungen erbringt und mit GPT4-Turbo vergleichbar ist."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 ist ein Open-Source-Mischexperten-Code-Modell, das in Codeaufgaben hervorragende Leistungen erbringt und mit GPT4-Turbo vergleichbar ist."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 ist ein durch verstärkendes Lernen (RL) gesteuertes Inferenzmodell, das die Probleme der Wiederholbarkeit und Lesbarkeit im Modell löst. Vor dem RL führte DeepSeek-R1 Kaltstartdaten ein, um die Inferenzleistung weiter zu optimieren. Es zeigt in mathematischen, programmierbezogenen und Inferenzaufgaben eine vergleichbare Leistung zu OpenAI-o1 und verbessert durch sorgfältig gestaltete Trainingsmethoden die Gesamteffizienz."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 – das größere und intelligentere Modell im DeepSeek-Paket – wurde in die Llama 70B-Architektur destilliert. Basierend auf Benchmark-Tests und menschlicher Bewertung ist dieses Modell intelligenter als das ursprüngliche Llama 70B, insbesondere bei Aufgaben, die mathematische und faktische Genauigkeit erfordern."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Das DeepSeek-R1-Distill Modell wurde durch Wissensdistillationstechniken entwickelt, indem Proben, die von DeepSeek-R1 generiert wurden, auf Qwen, Llama und andere Open-Source-Modelle feinabgestimmt wurden."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Das DeepSeek-R1-Distill Modell wurde durch Wissensdistillationstechniken entwickelt, indem Proben, die von DeepSeek-R1 generiert wurden, auf Qwen, Llama und andere Open-Source-Modelle feinabgestimmt wurden."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Das DeepSeek-R1-Distill Modell wurde durch Wissensdistillationstechniken entwickelt, indem Proben, die von DeepSeek-R1 generiert wurden, auf Qwen, Llama und andere Open-Source-Modelle feinabgestimmt wurden."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Das DeepSeek-R1-Distill Modell wurde durch Wissensdistillationstechniken entwickelt, indem Proben, die von DeepSeek-R1 generiert wurden, auf Qwen, Llama und andere Open-Source-Modelle feinabgestimmt wurden."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Das DeepSeek-R1-Distill Modell wurde durch Wissensdistillationstechniken entwickelt, indem Proben, die von DeepSeek-R1 generiert wurden, auf Qwen, Llama und andere Open-Source-Modelle feinabgestimmt wurden."
+ },
+ "deepseek-reasoner": {
+ "description": "Das von DeepSeek entwickelte Inferenzmodell. Bevor das Modell die endgültige Antwort ausgibt, gibt es zunächst eine Denkprozesskette aus, um die Genauigkeit der endgültigen Antwort zu erhöhen."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 ist ein effizientes Mixture-of-Experts-Sprachmodell, das für wirtschaftliche Verarbeitungsanforderungen geeignet ist."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B ist das Design-Code-Modell von DeepSeek und bietet starke Fähigkeiten zur Codegenerierung."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 ist ein MoE-Modell, das von der Hangzhou DeepSeek Artificial Intelligence Technology Research Co., Ltd. entwickelt wurde. Es hat in mehreren Bewertungen herausragende Ergebnisse erzielt und belegt in den gängigen Rankings den ersten Platz unter den Open-Source-Modellen. Im Vergleich zum V2.5-Modell hat sich die Generierungsgeschwindigkeit um das Dreifache erhöht, was den Nutzern ein schnelleres und flüssigeres Nutzungserlebnis bietet."
+ },
"deepseek/deepseek-chat": {
"description": "Ein neues Open-Source-Modell, das allgemeine und Codefähigkeiten vereint. Es behält nicht nur die allgemeinen Dialogfähigkeiten des ursprünglichen Chat-Modells und die leistungsstarken Codeverarbeitungsfähigkeiten des Coder-Modells bei, sondern stimmt auch besser mit menschlichen Vorlieben überein. Darüber hinaus hat DeepSeek-V2.5 in vielen Bereichen wie Schreibaufgaben und Befehlsbefolgung erhebliche Verbesserungen erzielt."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 hat die Schlussfolgerungsfähigkeiten des Modells erheblich verbessert, selbst bei nur wenigen gekennzeichneten Daten. Bevor das Modell die endgültige Antwort ausgibt, gibt es zunächst eine Denkprozesskette aus, um die Genauigkeit der endgültigen Antwort zu erhöhen."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B ist ein großes Sprachmodell, das auf Llama3.3 70B basiert und durch Feinabstimmung mit den Ausgaben von DeepSeek R1 eine wettbewerbsfähige Leistung erreicht, die mit großen, fortschrittlichen Modellen vergleichbar ist."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B ist ein distilliertes großes Sprachmodell, das auf Llama-3.1-8B-Instruct basiert und durch Training mit den Ausgaben von DeepSeek R1 erstellt wurde."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B ist ein distilliertes großes Sprachmodell, das auf Qwen 2.5 14B basiert und durch Training mit den Ausgaben von DeepSeek R1 erstellt wurde. Dieses Modell hat in mehreren Benchmark-Tests OpenAI's o1-mini übertroffen und die neuesten technologischen Fortschritte bei dichten Modellen (state-of-the-art) erzielt. Hier sind einige Ergebnisse der Benchmark-Tests:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nDas Modell zeigt durch Feinabstimmung mit den Ausgaben von DeepSeek R1 eine wettbewerbsfähige Leistung, die mit größeren, fortschrittlichen Modellen vergleichbar ist."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B ist ein distilliertes großes Sprachmodell, das auf Qwen 2.5 32B basiert und durch Training mit den Ausgaben von DeepSeek R1 erstellt wurde. Dieses Modell hat in mehreren Benchmark-Tests OpenAI's o1-mini übertroffen und die neuesten technologischen Fortschritte bei dichten Modellen (state-of-the-art) erzielt. Hier sind einige Ergebnisse der Benchmark-Tests:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nDas Modell zeigt durch Feinabstimmung mit den Ausgaben von DeepSeek R1 eine wettbewerbsfähige Leistung, die mit größeren, fortschrittlichen Modellen vergleichbar ist."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 ist das neueste Open-Source-Modell, das vom DeepSeek-Team veröffentlicht wurde und über eine äußerst leistungsstarke Inferenzleistung verfügt, insbesondere in den Bereichen Mathematik, Programmierung und logisches Denken, die mit dem OpenAI o1-Modell vergleichbar ist."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 hat die Schlussfolgerungsfähigkeiten des Modells erheblich verbessert, selbst bei nur wenigen gekennzeichneten Daten. Bevor das Modell die endgültige Antwort ausgibt, gibt es zunächst eine Denkprozesskette aus, um die Genauigkeit der endgültigen Antwort zu erhöhen."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 hat einen bedeutenden Durchbruch in der Inferenzgeschwindigkeit im Vergleich zu früheren Modellen erzielt. Es belegt den ersten Platz unter den Open-Source-Modellen und kann mit den weltweit fortschrittlichsten proprietären Modellen konkurrieren. DeepSeek-V3 verwendet die Multi-Head-Latent-Attention (MLA) und die DeepSeekMoE-Architektur, die in DeepSeek-V2 umfassend validiert wurden. Darüber hinaus hat DeepSeek-V3 eine unterstützende verlustfreie Strategie für die Lastenverteilung eingeführt und mehrere Zielvorgaben für das Training von Mehrfachvorhersagen festgelegt, um eine stärkere Leistung zu erzielen."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 hat einen bedeutenden Durchbruch in der Inferenzgeschwindigkeit im Vergleich zu früheren Modellen erzielt. Es belegt den ersten Platz unter den Open-Source-Modellen und kann mit den weltweit fortschrittlichsten proprietären Modellen konkurrieren. DeepSeek-V3 verwendet die Multi-Head-Latent-Attention (MLA) und die DeepSeekMoE-Architektur, die in DeepSeek-V2 umfassend validiert wurden. Darüber hinaus hat DeepSeek-V3 eine unterstützende verlustfreie Strategie für die Lastenverteilung eingeführt und mehrere Zielvorgaben für das Training von Mehrfachvorhersagen festgelegt, um eine stärkere Leistung zu erzielen."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite ist das neueste leichte Modell der nächsten Generation, das eine extrem schnelle Reaktionszeit bietet und sowohl in der Leistung als auch in der Latenz weltweit erstklassig ist."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k ist die umfassend verbesserte Version von Doubao-1.5-Pro, die die Gesamtleistung um 10 % steigert. Es unterstützt Schlussfolgerungen mit einem Kontextfenster von 256k und eine maximale Ausgabelänge von 12k Tokens. Höhere Leistung, größeres Fenster und ein hervorragendes Preis-Leistungs-Verhältnis machen es für eine breitere Palette von Anwendungsszenarien geeignet."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro ist das neueste Hauptmodell der nächsten Generation, dessen Leistung umfassend verbessert wurde und das in den Bereichen Wissen, Code, Schlussfolgerungen usw. herausragende Leistungen zeigt."
+ },
"emohaa": {
"description": "Emohaa ist ein psychologisches Modell mit professionellen Beratungsfähigkeiten, das den Nutzern hilft, emotionale Probleme zu verstehen."
},
+ "ernie-3.5-128k": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle deckt eine riesige Menge an chinesischen und englischen Korpora ab und bietet starke allgemeine Fähigkeiten, die die meisten Anforderungen an Dialogfragen, kreative Generierung und Plugin-Anwendungen erfüllen; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ernie-3.5-8k": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle deckt eine riesige Menge an chinesischen und englischen Korpora ab und bietet starke allgemeine Fähigkeiten, die die meisten Anforderungen an Dialogfragen, kreative Generierung und Plugin-Anwendungen erfüllen; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle deckt eine riesige Menge an chinesischen und englischen Korpora ab und bietet starke allgemeine Fähigkeiten, die die meisten Anforderungen an Dialogfragen, kreative Generierung und Plugin-Anwendungen erfüllen; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle hat im Vergleich zu ERNIE 3.5 eine umfassende Verbesserung der Modellfähigkeiten erreicht und ist weit verbreitet in komplexen Aufgabenbereichen anwendbar; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle hat im Vergleich zu ERNIE 3.5 eine umfassende Verbesserung der Modellfähigkeiten erreicht und ist weit verbreitet in komplexen Aufgabenbereichen anwendbar; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle zeigt hervorragende Gesamtergebnisse und ist weit verbreitet in komplexen Aufgabenbereichen anwendbar; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten. Im Vergleich zu ERNIE 4.0 bietet es eine bessere Leistung."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle zeigt hervorragende Gesamtergebnisse und ist weit verbreitet in komplexen Aufgabenbereichen anwendbar; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten. Im Vergleich zu ERNIE 4.0 bietet es eine bessere Leistung."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Das von Baidu entwickelte Flaggschiff-Modell für große Sprachmodelle zeigt hervorragende Gesamtergebnisse und ist weit verbreitet in komplexen Aufgabenbereichen anwendbar; es unterstützt die automatische Anbindung an das Baidu-Suchplugin, um die Aktualität der Antwortinformationen zu gewährleisten. Im Vergleich zu ERNIE 4.0 bietet es eine bessere Leistung."
+ },
+ "ernie-char-8k": {
+ "description": "Das von Baidu entwickelte große Sprachmodell für vertikale Szenarien eignet sich für Anwendungen wie NPCs in Spielen, Kundenservice-Dialoge und Rollenspiele, mit einem klareren und konsistenteren Charakterstil, einer stärkeren Befolgung von Anweisungen und besserer Inferenzleistung."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Das von Baidu entwickelte große Sprachmodell für vertikale Szenarien eignet sich für Anwendungen wie NPCs in Spielen, Kundenservice-Dialoge und Rollenspiele, mit einem klareren und konsistenteren Charakterstil, einer stärkeren Befolgung von Anweisungen und besserer Inferenzleistung."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite ist ein leichtgewichtiges großes Sprachmodell, das von Baidu entwickelt wurde und sowohl hervorragende Modellleistung als auch Inferenzleistung bietet, geeignet für die Verwendung mit AI-Beschleunigungskarten mit geringer Rechenleistung."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Das von Baidu entwickelte leichtgewichtige große Sprachmodell bietet sowohl hervorragende Modellleistung als auch Inferenzleistung, die besser ist als die von ERNIE Lite, und ist geeignet für die Verwendung mit AI-Beschleunigungskarten mit geringer Rechenleistung."
+ },
+ "ernie-novel-8k": {
+ "description": "Das von Baidu entwickelte allgemeine große Sprachmodell hat deutliche Vorteile in der Fähigkeit zur Fortsetzung von Romanen und kann auch in Szenarien wie Kurzdramen und Filmen eingesetzt werden."
+ },
+ "ernie-speed-128k": {
+ "description": "Das neueste hochleistungsfähige große Sprachmodell von Baidu, das 2024 veröffentlicht wurde, bietet hervorragende allgemeine Fähigkeiten und eignet sich gut als Basismodell für Feinabstimmungen, um spezifische Szenarien besser zu bewältigen, während es auch hervorragende Inferenzleistungen bietet."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Das neueste hochleistungsfähige große Sprachmodell von Baidu, das 2024 veröffentlicht wurde, bietet hervorragende allgemeine Fähigkeiten und ist besser als ERNIE Speed, geeignet als Basismodell für Feinabstimmungen, um spezifische Szenarien besser zu bewältigen, während es auch hervorragende Inferenzleistungen bietet."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny ist ein hochleistungsfähiges großes Sprachmodell, dessen Bereitstellungs- und Feinabstimmungskosten die niedrigsten unter den Wenshin-Modellen sind."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) bietet stabile und anpassbare Leistung und ist die ideale Wahl für Lösungen komplexer Aufgaben."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro ist Googles leistungsstarkes KI-Modell, das für die Skalierung einer Vielzahl von Aufgaben konzipiert ist."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash ist Googles neuestes multimodales KI-Modell, das über eine schnelle Verarbeitungskapazität verfügt und Texte, Bilder und Videoeingaben unterstützt, um eine effiziente Skalierung für verschiedene Aufgaben zu ermöglichen."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 ist ein effizientes multimodales Modell, das eine breite Anwendbarkeit unterstützt."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 ist ein effizientes multimodales Modell, das eine breite Palette von Anwendungen unterstützt."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 ist für die Verarbeitung großangelegter Aufgabenszenarien konzipiert und bietet unvergleichliche Verarbeitungsgeschwindigkeit."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B ist ein leistungsstarkes multimodales Modell, das eine breite Palette von Anwendungen unterstützt."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 ist das neueste experimentelle Modell, das in Text- und multimodalen Anwendungsfällen erhebliche Leistungsverbesserungen aufweist."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 bietet optimierte multimodale Verarbeitungsfähigkeiten, die für verschiedene komplexe Aufgabenszenarien geeignet sind."
+ "description": "Gemini 1.5 Flash 0827 bietet optimierte multimodale Verarbeitungskapazitäten, die für verschiedene komplexe Aufgaben geeignet sind."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash ist Googles neuestes multimodales KI-Modell, das über schnelle Verarbeitungsfähigkeiten verfügt und Text-, Bild- und Videoeingaben unterstützt, um eine effiziente Skalierung für verschiedene Aufgaben zu ermöglichen."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002 ist das neueste produktionsbereite Modell, das eine höhere Ausgabequalität bietet, insbesondere bei mathematischen, langen Kontexten und visuellen Aufgaben erhebliche Verbesserungen aufweist."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 bietet hervorragende multimodale Verarbeitungsfähigkeiten und bringt mehr Flexibilität in die Anwendungsentwicklung."
+ "description": "Gemini 1.5 Pro 0801 bietet herausragende multimodale Verarbeitungskapazitäten und bringt größere Flexibilität in die Anwendungsentwicklung."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 kombiniert die neuesten Optimierungstechniken und bietet eine effizientere multimodale Datenverarbeitung."
+ "description": "Gemini 1.5 Pro 0827 kombiniert die neuesten Optimierungstechnologien, um eine effizientere multimodale Datenverarbeitung zu ermöglichen."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro unterstützt bis zu 2 Millionen Tokens und ist die ideale Wahl für mittelgroße multimodale Modelle, die umfassende Unterstützung für komplexe Aufgaben bieten."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash bietet nächste Generation Funktionen und Verbesserungen, einschließlich außergewöhnlicher Geschwindigkeit, nativer Werkzeugnutzung, multimodaler Generierung und einem Kontextfenster von 1M Tokens."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash bietet nächste Generation Funktionen und Verbesserungen, einschließlich außergewöhnlicher Geschwindigkeit, nativer Werkzeugnutzung, multimodaler Generierung und einem Kontextfenster von 1M Tokens."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash ist eine Modellvariante, die auf Kosteneffizienz und niedrige Latenz optimiert ist."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash ist eine Modellvariante, die auf Kosteneffizienz und niedrige Latenz optimiert ist."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Ein Gemini 2.0 Flash Modell, das auf Kosteneffizienz und niedrige Latenz optimiert wurde."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp ist Googles neuestes experimentelles multimodales KI-Modell mit der nächsten Generation von Funktionen, außergewöhnlicher Geschwindigkeit, nativer Tool-Nutzung und multimodaler Generierung."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp ist Googles neuestes experimentelles multimodales KI-Modell mit der nächsten Generation von Funktionen, außergewöhnlicher Geschwindigkeit, nativer Tool-Nutzung und multimodaler Generierung."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental ist Googles neuestes experimentelles multimodales KI-Modell, das im Vergleich zu früheren Versionen eine gewisse Qualitätsverbesserung aufweist, insbesondere in Bezug auf Weltwissen, Code und lange Kontexte."
+ },
"gemma-7b-it": {
"description": "Gemma 7B eignet sich für die Verarbeitung von mittelgroßen Aufgaben und bietet ein gutes Kosten-Nutzen-Verhältnis."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 ist ein effizientes Modell von Google, das eine Vielzahl von Anwendungsszenarien von kleinen Anwendungen bis hin zu komplexen Datenverarbeitungen abdeckt."
},
- "general": {
- "description": "Spark Lite ist ein leichtgewichtiges großes Sprachmodell mit extrem niedriger Latenz und hoher Verarbeitungsfähigkeit, das vollständig kostenlos und offen ist und eine Echtzeitsuchfunktion unterstützt. Seine schnelle Reaktionsfähigkeit macht es in der Inferenzanwendung und Modellanpassung auf Geräten mit geringer Rechenleistung besonders effektiv und bietet den Nutzern ein hervorragendes Kosten-Nutzen-Verhältnis und intelligente Erfahrungen, insbesondere in den Bereichen Wissensabfrage, Inhaltserstellung und Suchszenarien."
- },
"generalv3": {
"description": "Spark Pro ist ein hochleistungsfähiges großes Sprachmodell, das für professionelle Bereiche optimiert ist und sich auf Mathematik, Programmierung, Medizin, Bildung und andere Bereiche konzentriert, und unterstützt die Online-Suche sowie integrierte Plugins für Wetter, Datum usw. Das optimierte Modell zeigt hervorragende Leistungen und hohe Effizienz in komplexen Wissensabfragen, Sprachverständnis und hochrangiger Textgenerierung und ist die ideale Wahl für professionelle Anwendungsszenarien."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 ist die neueste Modellversion, die für hochkomplexe und vielfältige Aufgaben konzipiert wurde und hervorragende Leistungen zeigt."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat zeigt in den Bereichen Semantik, Mathematik, Schlussfolgerungen, Code und Wissen eine hohe Leistung. Es verfügt auch über Funktionen wie Web-Browsing, Code-Ausführung, benutzerdefinierte Toolaufrufe und langes Textverständnis. Es unterstützt 26 Sprachen, darunter Japanisch, Koreanisch und Deutsch."
+ },
"glm-4-air": {
"description": "GLM-4-Air ist eine kosteneffiziente Version, die in der Leistung nahe am GLM-4 liegt und schnelle Geschwindigkeiten zu einem erschwinglichen Preis bietet."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash ist die ideale Wahl für die Verarbeitung einfacher Aufgaben, mit der schnellsten Geschwindigkeit und dem besten Preis."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX ist eine verbesserte Version von Flash mit extrem schneller Inferenzgeschwindigkeit."
+ },
"glm-4-long": {
"description": "GLM-4-Long unterstützt extrem lange Texteingaben und eignet sich für Gedächtnisaufgaben und die Verarbeitung großer Dokumente."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V bietet starke Fähigkeiten zur Bildverständnis und -schlussfolgerung und unterstützt eine Vielzahl visueller Aufgaben."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash konzentriert sich auf die effiziente Verarbeitung einzelner Bilder und eignet sich für Szenarien der schnellen Bildanalyse, wie z. B. die Echtzeitanalyse von Bildern oder die Verarbeitung von Bilddaten in großen Mengen."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus hat die Fähigkeit, Videoinhalte und mehrere Bilder zu verstehen und eignet sich für multimodale Aufgaben."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 bietet optimierte multimodale Verarbeitungsfähigkeiten und ist für eine Vielzahl komplexer Aufgaben geeignet."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview verfügt über starke Fähigkeiten zur komplexen Schlussfolgerung und zeigt hervorragende Leistungen in den Bereichen logisches Denken, Mathematik und Programmierung."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash bietet nächste Generation Funktionen und Verbesserungen, einschließlich außergewöhnlicher Geschwindigkeit, nativer Werkzeugnutzung, multimodaler Generierung und einem Kontextfenster von 1M Tokens."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental ist Googles neuestes experimentelles multimodales KI-Modell, das im Vergleich zu früheren Versionen eine gewisse Qualitätsverbesserung aufweist, insbesondere in Bezug auf Weltwissen, Code und lange Kontexte."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 kombiniert die neuesten Optimierungstechnologien und bietet effizientere multimodale Datenverarbeitungsfähigkeiten."
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash bietet optimierte multimodale Verarbeitungsfähigkeiten, die für verschiedene komplexe Aufgabenszenarien geeignet sind."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro kombiniert die neuesten Optimierungstechnologien und bietet eine effizientere Verarbeitung multimodaler Daten."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 ist ein effizientes Modell von Google, das eine Vielzahl von Anwendungsszenarien von kleinen Anwendungen bis hin zu komplexer Datenverarbeitung abdeckt."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 setzt das Designkonzept von Leichtbau und Effizienz fort."
},
+ "google/gemma-2-2b-it": {
+ "description": "Das leichtgewichtige Anweisungsoptimierungsmodell von Google."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 ist ein effizientes Modell von Google, das eine Vielzahl von Anwendungsszenarien von kleinen Anwendungen bis hin zu komplexer Datenverarbeitung abdeckt."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 ist eine leichtgewichtige Open-Source-Textmodellreihe von Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo eignet sich für eine Vielzahl von Textgenerierungs- und Verständnisaufgaben. Derzeit verweist es auf gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo ist ein effizientes Modell von OpenAI, das für Chat- und Textgenerierungsaufgaben geeignet ist und parallele Funktionsaufrufe unterstützt."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k ist ein hochkapazitives Textgenerierungsmodell, das sich für komplexe Aufgaben eignet."
+ },
"gpt-4": {
"description": "GPT-4 bietet ein größeres Kontextfenster, das in der Lage ist, längere Texteingaben zu verarbeiten, und eignet sich für Szenarien, die eine umfassende Informationsintegration und Datenanalyse erfordern."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "Das neueste GPT-4 Turbo-Modell verfügt über visuelle Funktionen. Jetzt können visuelle Anfragen im JSON-Format und durch Funktionsaufrufe gestellt werden. GPT-4 Turbo ist eine verbesserte Version, die kosteneffiziente Unterstützung für multimodale Aufgaben bietet. Es findet ein Gleichgewicht zwischen Genauigkeit und Effizienz und eignet sich für Anwendungen, die Echtzeitanpassungen erfordern."
},
- "gpt-4-1106-vision-preview": {
- "description": "Das neueste GPT-4 Turbo-Modell verfügt über visuelle Funktionen. Jetzt können visuelle Anfragen im JSON-Format und durch Funktionsaufrufe gestellt werden. GPT-4 Turbo ist eine verbesserte Version, die kosteneffiziente Unterstützung für multimodale Aufgaben bietet. Es findet ein Gleichgewicht zwischen Genauigkeit und Effizienz und eignet sich für Anwendungen, die Echtzeitanpassungen erfordern."
- },
"gpt-4-32k": {
"description": "GPT-4 bietet ein größeres Kontextfenster, das in der Lage ist, längere Texteingaben zu verarbeiten, und eignet sich für Szenarien, die eine umfassende Informationsintegration und Datenanalyse erfordern."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "Das neueste GPT-4 Turbo-Modell verfügt über visuelle Funktionen. Jetzt können visuelle Anfragen im JSON-Format und durch Funktionsaufrufe gestellt werden. GPT-4 Turbo ist eine verbesserte Version, die kosteneffiziente Unterstützung für multimodale Aufgaben bietet. Es findet ein Gleichgewicht zwischen Genauigkeit und Effizienz und eignet sich für Anwendungen, die Echtzeitanpassungen erfordern."
},
+ "gpt-4.5-preview": {
+ "description": "Die Forschungs-Vorschau von GPT-4.5, unserem bisher größten und leistungsstärksten GPT-Modell. Es verfügt über umfangreiches Weltwissen und kann die Absichten der Benutzer besser verstehen, was es in kreativen Aufgaben und autonomer Planung herausragend macht. GPT-4.5 akzeptiert Text- und Bild-Eingaben und generiert Textausgaben (einschließlich strukturierter Ausgaben). Es unterstützt wichtige Entwicklerfunktionen wie Funktionsaufrufe, Batch-APIs und Streaming-Ausgaben. In Aufgaben, die kreatives, offenes Denken und Dialog erfordern (wie Schreiben, Lernen oder das Erkunden neuer Ideen), zeigt GPT-4.5 besonders gute Leistungen. Der Wissensstand ist bis Oktober 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o ist ein dynamisches Modell, das in Echtzeit aktualisiert wird, um die neueste Version zu gewährleisten. Es kombiniert starke Sprachverständnis- und Generierungsfähigkeiten und eignet sich für großangelegte Anwendungsszenarien, einschließlich Kundenservice, Bildung und technische Unterstützung."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o ist ein dynamisches Modell, das in Echtzeit aktualisiert wird, um die neueste Version zu gewährleisten. Es kombiniert starke Sprachverständnis- und Generierungsfähigkeiten und eignet sich für großangelegte Anwendungsszenarien, einschließlich Kundenservice, Bildung und technische Unterstützung."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o ist ein dynamisches Modell, das in Echtzeit aktualisiert wird, um die neueste Version zu gewährleisten. Es kombiniert starke Sprachverständnis- und Generierungsfähigkeiten und eignet sich für großangelegte Anwendungsbereiche, einschließlich Kundenservice, Bildung und technischen Support."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o Audio-Modell, unterstützt Audioeingabe und -ausgabe."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini ist das neueste Modell von OpenAI, das nach GPT-4 Omni veröffentlicht wurde und sowohl Text- als auch Bildinput unterstützt. Als ihr fortschrittlichstes kleines Modell ist es viel günstiger als andere neueste Modelle und kostet über 60 % weniger als GPT-3.5 Turbo. Es behält die fortschrittliche Intelligenz bei und bietet gleichzeitig ein hervorragendes Preis-Leistungs-Verhältnis. GPT-4o mini erzielte 82 % im MMLU-Test und rangiert derzeit in den Chat-Präferenzen über GPT-4."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Echtzeitversion von GPT-4o-mini, unterstützt Audio- und Texteingabe sowie -ausgabe in Echtzeit."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Echtzeitversion von GPT-4o, unterstützt Audio- und Texteingabe sowie -ausgabe in Echtzeit."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Echtzeitversion von GPT-4o, unterstützt Audio- und Texteingabe sowie -ausgabe in Echtzeit."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Echtzeitversion von GPT-4o, unterstützt Audio- und Texteingabe sowie -ausgabe in Echtzeit."
+ },
+ "grok-2-1212": {
+ "description": "Dieses Modell hat Verbesserungen in Bezug auf Genauigkeit, Befolgung von Anweisungen und Mehrsprachigkeit erfahren."
+ },
+ "grok-2-vision-1212": {
+ "description": "Dieses Modell hat Verbesserungen in Bezug auf Genauigkeit, Befolgung von Anweisungen und Mehrsprachigkeit erfahren."
+ },
+ "grok-beta": {
+ "description": "Bietet eine Leistung, die mit Grok 2 vergleichbar ist, jedoch mit höherer Effizienz, Geschwindigkeit und Funktionalität."
+ },
+ "grok-vision-beta": {
+ "description": "Das neueste Modell zur Bildverständnis, das eine Vielzahl von visuellen Informationen verarbeiten kann, einschließlich Dokumenten, Diagrammen, Screenshots und Fotos."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B ist ein Sprachmodell, das Kreativität und Intelligenz kombiniert und mehrere führende Modelle integriert."
},
+ "hunyuan-code": {
+ "description": "Das neueste Code-Generierungsmodell von Hunyuan, das auf einem Basismodell mit 200B hochwertigen Code-Daten trainiert wurde, hat ein halbes Jahr lang mit hochwertigen SFT-Daten trainiert, das Kontextfenster auf 8K erhöht und belegt in den automatischen Bewertungsmetriken für die fünf großen Programmiersprachen Spitzenplätze; in den zehn Aspekten der umfassenden Codeaufgabenbewertung für die fünf großen Sprachen liegt die Leistung in der ersten Reihe."
+ },
+ "hunyuan-functioncall": {
+ "description": "Das neueste MOE-Architektur-FunctionCall-Modell von Hunyuan, das mit hochwertigen FunctionCall-Daten trainiert wurde, hat ein Kontextfenster von 32K und führt in mehreren Bewertungsmetriken."
+ },
+ "hunyuan-large": {
+ "description": "Das Hunyuan-large Modell hat insgesamt etwa 389B Parameter, davon etwa 52B aktivierte Parameter, und ist das derzeit größte und leistungsstärkste Open-Source MoE-Modell mit Transformer-Architektur in der Branche."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Besonders gut geeignet für lange Textaufgaben wie Dokumentenzusammenfassungen und Dokumentenfragen, verfügt es auch über die Fähigkeit, allgemeine Textgenerierungsaufgaben zu bearbeiten. Es zeigt hervorragende Leistungen bei der Analyse und Generierung von langen Texten und kann effektiv mit komplexen und detaillierten Anforderungen an die Verarbeitung von langen Inhalten umgehen."
+ },
+ "hunyuan-lite": {
+ "description": "Aufgerüstet auf eine MOE-Struktur mit einem Kontextfenster von 256k, führt es in mehreren Bewertungssets in NLP, Code, Mathematik und Industrie zahlreiche Open-Source-Modelle an."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Das neueste 7B multimodale Modell von Hunyuan, mit einem Kontextfenster von 32K, unterstützt multimodale Dialoge in Chinesisch und Englisch, Objekterkennung in Bildern, Dokumenten- und Tabellenverständnis sowie multimodale Mathematik und übertrifft in mehreren Dimensionen die Bewertungskennzahlen von 7B Wettbewerbsmodellen."
+ },
+ "hunyuan-pro": {
+ "description": "Ein MOE-32K-Modell für lange Texte mit einer Billion Parametern. Es erreicht in verschiedenen Benchmarks ein absolut führendes Niveau, hat komplexe Anweisungen und Schlussfolgerungen, verfügt über komplexe mathematische Fähigkeiten und unterstützt Funktionsaufrufe, mit Schwerpunkt auf Optimierung in den Bereichen mehrsprachige Übersetzung, Finanzrecht und Medizin."
+ },
+ "hunyuan-role": {
+ "description": "Das neueste Rollenspielmodell von Hunyuan, das auf dem offiziellen feinabgestimmten Training von Hunyuan basiert, wurde mit einem Datensatz für Rollenspiel-Szenarien weiter trainiert und bietet in Rollenspiel-Szenarien bessere Grundeffekte."
+ },
+ "hunyuan-standard": {
+ "description": "Verwendet eine verbesserte Routing-Strategie und mildert gleichzeitig die Probleme der Lastenverteilung und Expertenkonvergenz. Bei langen Texten erreicht der Needle-in-a-Haystack-Indikator 99,9%. MOE-32K bietet ein besseres Preis-Leistungs-Verhältnis und ermöglicht die Verarbeitung von langen Texteingaben bei ausgewogenem Effekt und Preis."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Verwendet eine verbesserte Routing-Strategie und mildert gleichzeitig die Probleme der Lastenverteilung und Expertenkonvergenz. Bei langen Texten erreicht der Needle-in-a-Haystack-Indikator 99,9%. MOE-256K bricht in Länge und Effektivität weiter durch und erweitert die eingabefähige Länge erheblich."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Das neueste multimodale Modell von Hunyuan, das mehrsprachige Antworten unterstützt und sowohl in Chinesisch als auch in Englisch ausgewogen ist."
+ },
+ "hunyuan-translation": {
+ "description": "Unterstützt die Übersetzung zwischen Chinesisch und Englisch, Japanisch, Französisch, Portugiesisch, Spanisch, Türkisch, Russisch, Arabisch, Koreanisch, Italienisch, Deutsch, Vietnamesisch, Malaiisch und Indonesisch in 15 Sprachen. Basierend auf einem automatisierten Bewertungs-Framework COMET, das auf mehrsprachigen Übersetzungsbewertungsszenarien basiert, übertrifft es insgesamt die Übersetzungsfähigkeiten anderer Modelle ähnlicher Größe auf dem Markt."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Das Hunyuan-Übersetzungsmodell unterstützt die dialogbasierte Übersetzung in natürlicher Sprache; es unterstützt die Übersetzung zwischen Chinesisch und Englisch, Japanisch, Französisch, Portugiesisch, Spanisch, Türkisch, Russisch, Arabisch, Koreanisch, Italienisch, Deutsch, Vietnamesisch, Malaiisch und Indonesisch in 15 Sprachen."
+ },
+ "hunyuan-turbo": {
+ "description": "Die Vorschauversion des neuen großen Sprachmodells von Hunyuan verwendet eine neuartige hybride Expertenmodellstruktur (MoE) und bietet im Vergleich zu Hunyuan-Pro eine schnellere Inferenz und bessere Leistung."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Hunyuan-turbo Version vom 20. November 2024, eine feste Version, die zwischen hunyuan-turbo und hunyuan-turbo-latest liegt."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Diese Version optimiert: Datenanweisungs-Skalierung, erhebliche Verbesserung der allgemeinen Generalisierungsfähigkeit des Modells; erhebliche Verbesserung der mathematischen, programmierbaren und logischen Denkfähigkeiten; Optimierung der Fähigkeiten im Textverständnis und der Wortverständnisfähigkeiten; Optimierung der Qualität der Inhaltserzeugung in der Texterstellung."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Allgemeine Optimierung der Benutzererfahrung, einschließlich NLP-Verständnis, Texterstellung, Smalltalk, Wissensfragen, Übersetzung, Fachgebieten usw.; Verbesserung der Menschlichkeit, Optimierung der emotionalen Intelligenz des Modells; Verbesserung der Fähigkeit des Modells, bei unklaren Absichten aktiv Klarheit zu schaffen; Verbesserung der Bearbeitungsfähigkeit von Fragen zur Wort- und Satzanalyse; Verbesserung der Qualität und Interaktivität der Kreation; Verbesserung der Mehrfachinteraktionserfahrung."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Das neue Flaggschiff-Modell der visuellen Sprache von Hunyuan, das eine brandneue Struktur des gemischten Expertenmodells (MoE) verwendet, bietet umfassende Verbesserungen in den Fähigkeiten zur grundlegenden Erkennung, Inhaltserstellung, Wissensfragen und Analyse sowie Schlussfolgerungen im Vergleich zum vorherigen Modell."
+ },
+ "hunyuan-vision": {
+ "description": "Das neueste multimodale Modell von Hunyuan unterstützt die Eingabe von Bildern und Text zur Generierung von Textinhalten."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Das innovative Open-Source-Modell InternLM2.5 hat durch eine große Anzahl von Parametern die Dialogintelligenz erhöht."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 bietet intelligente Dialoglösungen in mehreren Szenarien."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Das Llama 3.1 70B Instruct-Modell hat 70B Parameter und bietet herausragende Leistungen bei der Generierung großer Texte und Anweisungsaufgaben."
+ "internlm2-pro-chat": {
+ "description": "Die ältere Modellversion, die wir weiterhin pflegen, bietet eine Auswahl an Modellparametern von 7B und 20B."
+ },
+ "internlm2.5-latest": {
+ "description": "Unsere neueste Modellreihe mit herausragender Schlussfolgerungsleistung, die eine Kontextlänge von 1M unterstützt und über verbesserte Anweisungsbefolgung und Toolaufrufmöglichkeiten verfügt."
+ },
+ "internlm3-latest": {
+ "description": "Unsere neueste Modellreihe bietet herausragende Inferenzleistungen und führt die Open-Source-Modelle in ihrer Gewichtsklasse an. Standardmäßig verweist sie auf unser neuestes veröffentlichtes InternLM3-Modell."
+ },
+ "jina-deepsearch-v1": {
+ "description": "Die Tiefensuche kombiniert Websuche, Lesen und Schlussfolgern und ermöglicht umfassende Untersuchungen. Sie können es als einen Agenten betrachten, der Ihre Forschungsaufgaben übernimmt – er führt eine umfassende Suche durch und iteriert mehrfach, bevor er eine Antwort gibt. Dieser Prozess umfasst kontinuierliche Forschung, Schlussfolgerungen und die Lösung von Problemen aus verschiedenen Perspektiven. Dies unterscheidet sich grundlegend von den Standard-Großmodellen, die Antworten direkt aus vortrainierten Daten generieren, sowie von traditionellen RAG-Systemen, die auf einmaligen Oberflächensuchen basieren."
+ },
+ "kimi-latest": {
+ "description": "Das Kimi intelligente Assistenzprodukt verwendet das neueste Kimi Großmodell, das möglicherweise noch instabile Funktionen enthält. Es unterstützt die Bildverarbeitung und wählt automatisch das Abrechnungsmodell 8k/32k/128k basierend auf der Länge des angeforderten Kontexts aus."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM ist ein experimentelles, aufgabenorientiertes Sprachmodell, das darauf trainiert wurde, den Prinzipien der Lernwissenschaft zu entsprechen und in Lehr- und Lernszenarien systematische Anweisungen zu befolgen, als Expertenmentor zu fungieren usw."
+ },
+ "lite": {
+ "description": "Spark Lite ist ein leichtgewichtiges großes Sprachmodell mit extrem niedriger Latenz und effizienter Verarbeitung, das vollständig kostenlos und offen ist und Echtzeitsuchfunktionen unterstützt. Seine schnelle Reaktionsfähigkeit macht es besonders geeignet für Inferenzanwendungen und Modellanpassungen auf Geräten mit geringer Rechenleistung und bietet den Nutzern ein hervorragendes Kosten-Nutzen-Verhältnis sowie ein intelligentes Erlebnis, insbesondere in den Bereichen Wissensabfragen, Inhaltserstellung und Suchszenarien."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B bietet leistungsstarke KI-Schlussfolgerungsfähigkeiten, die für komplexe Anwendungen geeignet sind und eine hohe Rechenverarbeitung bei gleichzeitiger Effizienz und Genauigkeit unterstützen."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B ist ein leistungsstarkes Modell, das schnelle Textgenerierungsfähigkeiten bietet und sich hervorragend für Anwendungen eignet, die große Effizienz und Kosteneffektivität erfordern."
},
- "llama-3.1-8b-instruct": {
- "description": "Das Llama 3.1 8B Instruct-Modell hat 8B Parameter und unterstützt die effiziente Ausführung von bildbasierten Anweisungsaufgaben und bietet hochwertige Textgenerierungsfähigkeiten."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Überlegene Bildverarbeitungsfähigkeiten auf hochauflösenden Bildern, geeignet für visuelle Verständnisanwendungen."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Das Llama 3.1 Sonar Huge Online-Modell hat 405B Parameter und unterstützt eine Kontextlänge von etwa 127.000 Markierungen, es wurde für komplexe Online-Chat-Anwendungen entwickelt."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 ist darauf ausgelegt, Aufgaben zu bearbeiten, die visuelle und textuelle Daten kombinieren. Es zeigt hervorragende Leistungen bei Aufgaben wie Bildbeschreibung und visuellen Fragen und Antworten und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Das Llama 3.1 Sonar Large Chat-Modell hat 70B Parameter und unterstützt eine Kontextlänge von etwa 127.000 Markierungen, es eignet sich für komplexe Offline-Chat-Aufgaben."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Erweiterte Bildverarbeitungsfähigkeiten für visuelle Verständnisagentenanwendungen."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Das Llama 3.1 Sonar Large Online-Modell hat 70B Parameter und unterstützt eine Kontextlänge von etwa 127.000 Markierungen, es eignet sich für hochvolumige und vielfältige Chat-Aufgaben."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 ist darauf ausgelegt, Aufgaben zu bearbeiten, die visuelle und textuelle Daten kombinieren. Es zeigt hervorragende Leistungen bei Aufgaben wie Bildbeschreibung und visuellen Fragen und Antworten und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Das Llama 3.1 Sonar Small Chat-Modell hat 8B Parameter und wurde speziell für Offline-Chat entwickelt, es unterstützt eine Kontextlänge von etwa 127.000 Markierungen."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 ist das fortschrittlichste mehrsprachige Open-Source-Sprachmodell der Llama-Serie, das eine Leistung bietet, die mit einem 405B-Modell vergleichbar ist, und das zu extrem niedrigen Kosten. Es basiert auf der Transformer-Architektur und verbessert die Nützlichkeit und Sicherheit durch überwachte Feinabstimmung (SFT) und verstärkendes Lernen mit menschlichem Feedback (RLHF). Die auf Anweisungen optimierte Version ist speziell für mehrsprachige Dialoge optimiert und übertrifft in mehreren Branchenbenchmarks viele Open-Source- und geschlossene Chat-Modelle. Das Wissensdatum endet im Dezember 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Das Llama 3.1 Sonar Small Online-Modell hat 8B Parameter und unterstützt eine Kontextlänge von etwa 127.000 Markierungen, es wurde speziell für Online-Chat entwickelt und kann verschiedene Textinteraktionen effizient verarbeiten."
+ "llama-3.3-70b-versatile": {
+ "description": "Das Meta Llama 3.3 ist ein mehrsprachiges, großes Sprachmodell (LLM), das aus einem vortrainierten und anweisungsorientierten generativen Modell mit 70B (Text-Eingabe/Text-Ausgabe) besteht. Das anweisungsorientierte Modell von Llama 3.3 ist für mehrsprachige Dialoganwendungen optimiert und übertrifft viele verfügbare Open-Source- und Closed-Source-Chat-Modelle bei gängigen Branchenbenchmarks."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B bietet unvergleichliche Fähigkeiten zur Verarbeitung von Komplexität und ist maßgeschneidert für Projekte mit hohen Anforderungen."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral ist für wissenschaftliche Forschung und mathematische Schlussfolgerungen konzipiert und bietet effektive Rechenfähigkeiten und Ergebnisinterpretationen."
},
+ "max-32k": {
+ "description": "Spark Max 32K bietet eine große Kontextverarbeitungsfähigkeit mit verbesserter Kontextverständnis und logischer Schlussfolgerungsfähigkeit und unterstützt Texteingaben von bis zu 32K Tokens, was es ideal für das Lesen langer Dokumente und private Wissensabfragen macht."
+ },
"meta-llama-3-70b-instruct": {
"description": "Ein leistungsstarkes Modell mit 70 Milliarden Parametern, das in den Bereichen Schlussfolgerungen, Programmierung und breiten Sprachanwendungen herausragt."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) bietet hervorragende Sprachverarbeitungsfähigkeiten und ein ausgezeichnetes Interaktionserlebnis."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 bietet hervorragende Sprachverarbeitungsfähigkeiten und ein großartiges Interaktionserlebnis."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) ist ein leistungsstarkes Chat-Modell, das komplexe Dialoganforderungen unterstützt."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) bietet mehrsprachige Unterstützung und deckt ein breites Spektrum an Fachwissen ab."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 ist darauf ausgelegt, Aufgaben zu bewältigen, die sowohl visuelle als auch Textdaten kombinieren. Es erzielt hervorragende Ergebnisse bei Aufgaben wie Bildbeschreibung und visueller Fragebeantwortung und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 ist darauf ausgelegt, Aufgaben zu bewältigen, die sowohl visuelle als auch Textdaten kombinieren. Es erzielt hervorragende Ergebnisse bei Aufgaben wie Bildbeschreibung und visueller Fragebeantwortung und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 ist darauf ausgelegt, Aufgaben zu bewältigen, die sowohl visuelle als auch Textdaten kombinieren. Es erzielt hervorragende Ergebnisse bei Aufgaben wie Bildbeschreibung und visueller Fragebeantwortung und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 ist das fortschrittlichste mehrsprachige Open-Source-Sprachmodell der Llama-Serie, das zu extrem niedrigen Kosten eine Leistung bietet, die mit der eines 405B-Modells vergleichbar ist. Basierend auf der Transformer-Architektur und verbessert durch überwachte Feinabstimmung (SFT) und verstärkendes Lernen mit menschlichem Feedback (RLHF) für Nützlichkeit und Sicherheit. Die optimierte Version für Anweisungen ist speziell für mehrsprachige Dialoge optimiert und übertrifft in mehreren Branchenbenchmarks viele Open-Source- und geschlossene Chat-Modelle. Wissensstichtag ist der 31. Dezember 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Das Meta Llama 3.3 mehrsprachige große Sprachmodell (LLM) ist ein vortrainiertes und anweisungsoptimiertes Generierungsmodell mit 70B (Textinput/Textoutput). Das anweisungsoptimierte reine Textmodell von Llama 3.3 wurde für mehrsprachige Dialoganwendungen optimiert und übertrifft viele verfügbare Open-Source- und geschlossene Chat-Modelle in gängigen Branchenbenchmarks."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 ist darauf ausgelegt, Aufgaben zu bewältigen, die sowohl visuelle als auch Textdaten kombinieren. Es erzielt hervorragende Ergebnisse bei Aufgaben wie Bildbeschreibung und visueller Fragebeantwortung und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite ist für Umgebungen geeignet, die hohe Leistung und niedrige Latenz erfordern."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "Das 405B Llama 3.1 Turbo-Modell bietet eine enorme Kapazität zur Unterstützung von Kontexten für die Verarbeitung großer Datenmengen und zeigt herausragende Leistungen in groß angelegten KI-Anwendungen."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 ist das führende Modell von Meta, das bis zu 405B Parameter unterstützt und in komplexen Gesprächen, mehrsprachiger Übersetzung und Datenanalyse eingesetzt werden kann."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B bietet effiziente Dialogunterstützung in mehreren Sprachen."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct optimiert qualitativ hochwertige Dialogszenarien und bietet bessere Leistungen als viele geschlossene Modelle."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct ist die neueste Version von Meta, optimiert zur Generierung qualitativ hochwertiger Dialoge und übertrifft viele führende geschlossene Modelle."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct ist speziell für qualitativ hochwertige Dialoge konzipiert und zeigt herausragende Leistungen in menschlichen Bewertungen, besonders geeignet für hochinteraktive Szenarien."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 bietet Unterstützung für mehrere Sprachen und gehört zu den führenden generativen Modellen der Branche."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 ist darauf ausgelegt, Aufgaben zu bearbeiten, die visuelle und textuelle Daten kombinieren. Es zeigt hervorragende Leistungen bei Aufgaben wie Bildbeschreibung und visuellem Fragen und Antworten und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 ist darauf ausgelegt, Aufgaben zu bearbeiten, die visuelle und textuelle Daten kombinieren. Es zeigt hervorragende Leistungen bei Aufgaben wie Bildbeschreibung und visuellem Fragen und Antworten und überbrückt die Kluft zwischen Sprachgenerierung und visueller Schlussfolgerung."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 ist das fortschrittlichste mehrsprachige Open-Source-Sprachmodell der Llama-Serie, das eine Leistung bietet, die mit einem 405B-Modell vergleichbar ist, und das zu extrem niedrigen Kosten. Es basiert auf der Transformer-Architektur und verbessert die Nützlichkeit und Sicherheit durch überwachte Feinabstimmung (SFT) und verstärkendes Lernen mit menschlichem Feedback (RLHF). Die auf Anweisungen optimierte Version ist speziell für mehrsprachige Dialoge optimiert und übertrifft in mehreren Branchenbenchmarks viele Open-Source- und geschlossene Chat-Modelle. Das Wissensdatum endet im Dezember 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 ist das fortschrittlichste mehrsprachige Open-Source-Sprachmodell der Llama-Serie, das eine Leistung bietet, die mit einem 405B-Modell vergleichbar ist, und das zu extrem niedrigen Kosten. Es basiert auf der Transformer-Architektur und verbessert die Nützlichkeit und Sicherheit durch überwachte Feinabstimmung (SFT) und verstärkendes Lernen mit menschlichem Feedback (RLHF). Die auf Anweisungen optimierte Version ist speziell für mehrsprachige Dialoge optimiert und übertrifft in mehreren Branchenbenchmarks viele Open-Source- und geschlossene Chat-Modelle. Das Wissensdatum endet im Dezember 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct ist das größte und leistungsstärkste Modell innerhalb des Llama 3.1 Instruct Modells. Es handelt sich um ein hochentwickeltes Modell für dialogbasierte Schlussfolgerungen und die Generierung synthetischer Daten, das auch als Grundlage für die professionelle kontinuierliche Vorab- und Feinabstimmung in bestimmten Bereichen verwendet werden kann. Die mehrsprachigen großen Sprachmodelle (LLMs) von Llama 3.1 sind eine Gruppe von vortrainierten, anweisungsoptimierten Generierungsmodellen, die in den Größen 8B, 70B und 405B (Text-Eingabe/Ausgabe) verfügbar sind. Die anweisungsoptimierten Textmodelle (8B, 70B, 405B) sind speziell für mehrsprachige Dialoganwendungen optimiert und haben in gängigen Branchenbenchmarks viele verfügbare Open-Source-Chat-Modelle übertroffen. Llama 3.1 ist für kommerzielle und Forschungszwecke in mehreren Sprachen konzipiert. Die anweisungsoptimierten Textmodelle eignen sich für assistentengleiche Chats, während die vortrainierten Modelle für verschiedene Aufgaben der natürlichen Sprachgenerierung angepasst werden können. Das Llama 3.1 Modell unterstützt auch die Nutzung seiner Ausgaben zur Verbesserung anderer Modelle, einschließlich der Generierung synthetischer Daten und der Verfeinerung. Llama 3.1 ist ein autoregressives Sprachmodell, das auf einer optimierten Transformer-Architektur basiert. Die angepasste Version verwendet überwachte Feinabstimmung (SFT) und verstärkendes Lernen mit menschlichem Feedback (RLHF), um den menschlichen Präferenzen für Hilfsbereitschaft und Sicherheit zu entsprechen."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 ist ein offenes großes Sprachmodell (LLM), das sich an Entwickler, Forscher und Unternehmen richtet und ihnen hilft, ihre Ideen für generative KI zu entwickeln, zu experimentieren und verantwortungsbewusst zu skalieren. Als Teil eines globalen Innovationssystems ist es besonders geeignet für Umgebungen mit begrenzter Rechenleistung und Ressourcen, für Edge-Geräte und schnellere Trainingszeiten."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B ist das neueste schnelle und leichte Modell von Microsoft AI, dessen Leistung fast zehnmal so hoch ist wie die bestehender führender Open-Source-Modelle."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "Fortgeschrittenes LLM, das die Generierung synthetischer Daten, Wissensverdichtung und Schlussfolgerungen unterstützt, geeignet für Chatbots, Programmierung und spezifische Aufgaben."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Ermöglicht komplexe Gespräche mit hervorragendem Kontextverständnis, Schlussfolgerungsfähigkeiten und Textgenerierungsfähigkeiten."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Fortschrittliches, hochmodernes Modell mit Sprachverständnis, hervorragenden Schlussfolgerungsfähigkeiten und Textgenerierungsfähigkeiten."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Spitzenmäßiges visuelles Sprachmodell, das in der Lage ist, qualitativ hochwertige Schlussfolgerungen aus Bildern zu ziehen."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Fortschrittliches, hochmodernes kleines Sprachmodell mit Sprachverständnis, hervorragenden Schlussfolgerungsfähigkeiten und Textgenerierungsfähigkeiten."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Fortschrittliches, hochmodernes kleines Sprachmodell mit Sprachverständnis, hervorragenden Schlussfolgerungsfähigkeiten und Textgenerierungsfähigkeiten."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Spitzenmäßiges visuelles Sprachmodell, das in der Lage ist, qualitativ hochwertige Schlussfolgerungen aus Bildern zu ziehen."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Fortschrittliches LLM, das auf Schlussfolgern, Mathematik, Allgemeinwissen und Funktionsaufrufen spezialisiert ist."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 ist ein Sprachmodell von Microsoft AI, das in komplexen Dialogen, Mehrsprachigkeit, Inferenz und intelligenten Assistenten besonders gut abschneidet."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B ist das fortschrittlichste Wizard-Modell von Microsoft AI und zeigt äußerst wettbewerbsfähige Leistungen."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V ist das neue multimodale Großmodell von OpenBMB, das über hervorragende OCR-Erkennungs- und multimodale Verständnisfähigkeiten verfügt und eine Vielzahl von Anwendungsszenarien unterstützt."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B ist das weltbeste Edge-Modell von Mistral."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B ist das kosteneffizienteste Edge-Modell von Mistral."
+ },
"mistral": {
"description": "Mistral ist ein 7B-Modell von Mistral AI, das sich für vielfältige Anforderungen an die Sprachverarbeitung eignet."
},
"mistral-large": {
"description": "Mixtral Large ist das Flaggschiff-Modell von Mistral, das die Fähigkeiten zur Codegenerierung, Mathematik und Schlussfolgerungen kombiniert und ein Kontextfenster von 128k unterstützt."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) ist ein fortschrittliches großes Sprachmodell (LLM) mit modernsten Fähigkeiten in den Bereichen Schlussfolgerungen, Wissen und Programmierung."
- },
"mistral-large-latest": {
"description": "Mistral Large ist das Flaggschiff-Modell, das sich gut für mehrsprachige Aufgaben, komplexe Schlussfolgerungen und Codegenerierung eignet und die ideale Wahl für hochentwickelte Anwendungen ist."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 bietet effiziente Rechenleistung und natürliche Sprachverständnisfähigkeiten und eignet sich für eine Vielzahl von Anwendungen."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B ist ein kompaktes, aber leistungsstarkes Modell, das gut für Batch-Verarbeitung und einfache Aufgaben wie Klassifizierung und Textgenerierung geeignet ist und über gute Schlussfolgerungsfähigkeiten verfügt."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) ist ein super großes Sprachmodell, das extrem hohe Verarbeitungsanforderungen unterstützt."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B ist ein vortrainiertes sparsames Mischmodell, das für allgemeine Textaufgaben verwendet wird."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B ist ein sparsames Expertenmodell, das mehrere Parameter nutzt, um die Schlussfolgerungsgeschwindigkeit zu erhöhen, und sich gut für mehrsprachige und Code-Generierungsaufgaben eignet."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct ist ein hochleistungsfähiges Branchenstandardmodell mit Geschwindigkeitsoptimierung und Unterstützung für lange Kontexte."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K ist ein Modell mit überragenden Fähigkeiten zur Verarbeitung von langen Kontexten, das für die Generierung von sehr langen Texten geeignet ist und die Anforderungen komplexer Generierungsaufgaben erfüllt. Es kann Inhalte mit bis zu 128.000 Tokens verarbeiten und eignet sich hervorragend für Anwendungen in der Forschung, Wissenschaft und der Erstellung großer Dokumente."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Das Kimi-Visionsmodell (einschließlich moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview usw.) kann Bildinhalte verstehen, einschließlich Bildtext, Bildfarbe und Objektformen."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K bietet die Fähigkeit zur Verarbeitung von mittellangen Kontexten und kann 32.768 Tokens verarbeiten, was es besonders geeignet für die Generierung verschiedener langer Dokumente und komplexer Dialoge macht, die in den Bereichen Inhaltserstellung, Berichtsgenerierung und Dialogsysteme eingesetzt werden."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Das Kimi-Visionsmodell (einschließlich moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview usw.) kann Bildinhalte verstehen, einschließlich Bildtext, Bildfarbe und Objektformen."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K ist für die Generierung von Kurztextaufgaben konzipiert und bietet eine effiziente Verarbeitungsleistung, die 8.192 Tokens verarbeiten kann. Es eignet sich hervorragend für kurze Dialoge, Notizen und schnelle Inhaltserstellung."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Das Kimi-Visionsmodell (einschließlich moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview usw.) kann Bildinhalte verstehen, einschließlich Bildtext, Bildfarbe und Objektformen."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto kann basierend auf der Anzahl der im aktuellen Kontext verwendeten Tokens das geeignete Modell auswählen."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B ist die aktualisierte Version von Nous Hermes 2 und enthält die neuesten intern entwickelten Datensätze."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B ist ein von NVIDIA maßgeschneidertes großes Sprachmodell, das darauf abzielt, die Hilfsfähigkeit der von LLM generierten Antworten auf Benutzeranfragen zu verbessern. Dieses Modell hat in Benchmark-Tests wie Arena Hard, AlpacaEval 2 LC und GPT-4-Turbo MT-Bench hervorragende Leistungen gezeigt und belegt bis zum 1. Oktober 2024 den ersten Platz in allen drei automatischen Ausrichtungsbenchmarks. Das Modell wurde mit RLHF (insbesondere REINFORCE), Llama-3.1-Nemotron-70B-Reward und HelpSteer2-Preference-Prompts auf dem Llama-3.1-70B-Instruct-Modell trainiert."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Einzigartiges Sprachmodell, das unvergleichliche Genauigkeit und Effizienz bietet."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct ist ein von NVIDIA maßgeschneidertes großes Sprachmodell, das darauf abzielt, die Hilfsbereitschaft der von LLM generierten Antworten zu verbessern."
+ },
+ "o1": {
+ "description": "Konzentriert sich auf fortgeschrittene Inferenz und die Lösung komplexer Probleme, einschließlich mathematischer und wissenschaftlicher Aufgaben. Besonders geeignet für Anwendungen, die ein tiefes Verständnis des Kontexts und die Abwicklung von Arbeitsabläufen erfordern."
+ },
"o1-mini": {
"description": "o1-mini ist ein schnelles und kosteneffizientes Inferenzmodell, das für Programmier-, Mathematik- und Wissenschaftsanwendungen entwickelt wurde. Das Modell hat einen Kontext von 128K und einen Wissensstand bis Oktober 2023."
},
"o1-preview": {
"description": "o1 ist OpenAIs neues Inferenzmodell, das für komplexe Aufgaben geeignet ist, die umfangreiches Allgemeinwissen erfordern. Das Modell hat einen Kontext von 128K und einen Wissensstand bis Oktober 2023."
},
+ "o3-mini": {
+ "description": "o3-mini ist unser neuestes kompaktes Inferenzmodell, das bei den gleichen Kosten- und Verzögerungszielen wie o1-mini hohe Intelligenz bietet."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba ist ein auf die Codegenerierung spezialisiertes Mamba 2-Sprachmodell, das starke Unterstützung für fortschrittliche Code- und Schlussfolgerungsaufgaben bietet."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B ist ein spärliches Expertenmodell, das mehrere Parameter nutzt, um die Schlussfolgerungsgeschwindigkeit zu erhöhen und sich für die Verarbeitung mehrsprachiger und Codegenerierungsaufgaben eignet."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o ist ein dynamisches Modell, das in Echtzeit aktualisiert wird, um die neueste Version zu gewährleisten. Es kombiniert starke Sprachverständnis- und Generierungsfähigkeiten und eignet sich für großangelegte Anwendungsszenarien, einschließlich Kundenservice, Bildung und technische Unterstützung."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o ist ein dynamisches Modell, das in Echtzeit aktualisiert wird, um die neueste Version zu gewährleisten. Es kombiniert starke Sprachverständnis- und Generierungsfähigkeiten und eignet sich für großangelegte Anwendungsszenarien, einschließlich Kundenservice, Bildung und technischem Support."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini ist das neueste Modell von OpenAI, das nach GPT-4 Omni veröffentlicht wurde und Text- und Bild-Eingaben unterstützt. Als ihr fortschrittlichstes kleines Modell ist es viel günstiger als andere neueste Modelle und über 60 % günstiger als GPT-3.5 Turbo. Es behält die fortschrittlichste Intelligenz bei und bietet gleichzeitig ein hervorragendes Preis-Leistungs-Verhältnis. GPT-4o mini erzielte 82 % im MMLU-Test und rangiert derzeit in den Chat-Präferenzen über GPT-4."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Das Pixtral-Modell zeigt starke Fähigkeiten in Aufgaben wie Diagramm- und Bildverständnis, Dokumentenfragen, multimodale Schlussfolgerungen und Befolgung von Anweisungen. Es kann Bilder in natürlicher Auflösung und Seitenverhältnis aufnehmen und in einem langen Kontextfenster von bis zu 128K Tokens beliebig viele Bilder verarbeiten."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large ist ein Open-Source-Multimodalmodell mit 124 Milliarden Parametern, das auf Mistral Large 2 basiert. Dies ist unser zweites Modell in der multimodalen Familie und zeigt fortschrittliche Fähigkeiten im Bereich der Bildverständnis."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K verfügt über eine außergewöhnliche Kontextverarbeitungsfähigkeit und kann bis zu 128K Kontextinformationen verarbeiten, was es besonders geeignet für die Analyse langer Texte und die Verarbeitung langfristiger logischer Zusammenhänge macht. Es bietet in komplexen Textkommunikationen flüssige und konsistente Logik sowie vielfältige Unterstützung für Zitate."
+ },
+ "qvq-72b-preview": {
+ "description": "Das QVQ-Modell ist ein experimentelles Forschungsmodell, das vom Qwen-Team entwickelt wurde und sich auf die Verbesserung der visuellen Schlussfolgerungsfähigkeiten konzentriert, insbesondere im Bereich der mathematischen Schlussfolgerungen."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Tongyi Qianwen Code-Modell."
+ },
"qwen-coder-turbo-latest": {
"description": "Das Tongyi Qianwen Code-Modell."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Das Tongyi Qianwen Mathematikmodell ist speziell für die Lösung von mathematischen Problemen konzipiert."
},
+ "qwen-max": {
+ "description": "Qwen Max ist ein großangelegtes Sprachmodell auf Billionenebene, das Eingaben in verschiedenen Sprachen wie Chinesisch und Englisch unterstützt und das API-Modell hinter der aktuellen Produktversion von Qwen 2.5 ist."
+ },
"qwen-max-latest": {
"description": "Der Tongyi Qianwen ist ein Sprachmodell mit einem Umfang von mehreren Billionen, das Eingaben in verschiedenen Sprachen wie Chinesisch und Englisch unterstützt und die API-Modelle hinter der aktuellen Version 2.5 von Tongyi Qianwen darstellt."
},
+ "qwen-omni-turbo-latest": {
+ "description": "Die Qwen-Omni-Serie unterstützt die Eingabe von Daten in verschiedenen Modalitäten, einschließlich Video, Audio, Bilder und Text, und gibt Audio und Text aus."
+ },
+ "qwen-plus": {
+ "description": "Qwen Plus ist die verbesserte Version des großangelegten Sprachmodells, das Eingaben in verschiedenen Sprachen wie Chinesisch und Englisch unterstützt."
+ },
"qwen-plus-latest": {
"description": "Der Tongyi Qianwen ist die erweiterte Version eines groß angelegten Sprachmodells, das Eingaben in verschiedenen Sprachen wie Chinesisch und Englisch unterstützt."
},
+ "qwen-turbo": {
+ "description": "Qwen Turbo ist ein großangelegtes Sprachmodell, das Eingaben in verschiedenen Sprachen wie Chinesisch und Englisch unterstützt."
+ },
"qwen-turbo-latest": {
"description": "Der Tongyi Qianwen ist ein groß angelegtes Sprachmodell, das Eingaben in verschiedenen Sprachen wie Chinesisch und Englisch unterstützt."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL unterstützt flexible Interaktionsmethoden, einschließlich Mehrbild-, Mehrfachfragen und kreativen Fähigkeiten."
},
- "qwen-vl-max": {
- "description": "Qwen ist ein groß angelegtes visuelles Sprachmodell. Im Vergleich zur verbesserten Version hat es die visuelle Schlussfolgerungsfähigkeit und die Befolgung von Anweisungen weiter verbessert und bietet ein höheres Maß an visueller Wahrnehmung und Kognition."
+ "qwen-vl-max-latest": {
+ "description": "Das Tongyi Qianwen Ultra-Scale Visuelle Sprachmodell. Im Vergleich zur verbesserten Version wurden die Fähigkeiten zur visuellen Schlussfolgerung und Befolgung von Anweisungen weiter gesteigert, was ein höheres Niveau an visueller Wahrnehmung und Kognition bietet."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Tongyi Qianwen OCR ist ein spezialisiertes Modell zur Textextraktion, das sich auf die Textextraktionsfähigkeiten von Dokumenten, Tabellen, Prüfungsfragen und handschriftlichen Texten konzentriert. Es kann verschiedene Schriftarten erkennen und unterstützt derzeit folgende Sprachen: Chinesisch, Englisch, Französisch, Japanisch, Koreanisch, Deutsch, Russisch, Italienisch, Vietnamesisch und Arabisch."
},
- "qwen-vl-plus": {
- "description": "Qwen ist eine verbesserte Version des groß angelegten visuellen Sprachmodells. Es verbessert erheblich die Fähigkeit zur Detailerkennung und Texterkennung und unterstützt Bilder mit über einer Million Pixeln und beliebigen Seitenverhältnissen."
+ "qwen-vl-plus-latest": {
+ "description": "Die verbesserte Version des Tongyi Qianwen, eines großangelegten visuellen Sprachmodells. Deutlich verbesserte Fähigkeiten zur Detailerkennung und Texterkennung, unterstützt Bildauflösungen von über einer Million Pixel und beliebige Seitenverhältnisse."
},
"qwen-vl-v1": {
"description": "Initiiert mit dem Qwen-7B-Sprachmodell, fügt es ein Bildmodell hinzu, das für Bildeingaben mit einer Auflösung von 448 vortrainiert wurde."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 ist die brandneue Serie von großen Sprachmodellen von Qwen. Qwen2 7B ist ein transformerbasiertes Modell, das in den Bereichen Sprachverständnis, Mehrsprachigkeit, Programmierung, Mathematik und logisches Denken hervorragende Leistungen zeigt."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 ist eine neue Serie großer Sprachmodelle mit stärkeren Verständnis- und Generierungsfähigkeiten."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL ist die neueste Iteration des Qwen-VL-Modells und hat in Benchmark-Tests zur visuellen Verständlichkeit eine fortschrittliche Leistung erreicht, einschließlich MathVista, DocVQA, RealWorldQA und MTVQA. Qwen2-VL kann über 20 Minuten Video verstehen und ermöglicht qualitativ hochwertige, videobasierte Fragen und Antworten, Dialoge und Inhaltserstellung. Es verfügt auch über komplexe Denk- und Entscheidungsfähigkeiten und kann mit mobilen Geräten, Robotern usw. integriert werden, um basierend auf visuellen Umgebungen und Textanweisungen automatisch zu agieren. Neben Englisch und Chinesisch unterstützt Qwen2-VL jetzt auch das Verständnis von Text in Bildern in verschiedenen Sprachen, einschließlich der meisten europäischen Sprachen, Japanisch, Koreanisch, Arabisch und Vietnamesisch."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct ist eines der neuesten großen Sprachmodell-Serien, die von Alibaba Cloud veröffentlicht wurden. Dieses 72B-Modell hat signifikante Verbesserungen in den Bereichen Codierung und Mathematik. Das Modell bietet auch mehrsprachige Unterstützung und deckt über 29 Sprachen ab, einschließlich Chinesisch und Englisch. Das Modell hat signifikante Verbesserungen in der Befolgung von Anweisungen, im Verständnis von strukturierten Daten und in der Generierung von strukturierten Ausgaben (insbesondere JSON) erzielt."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct ist eines der neuesten großen Sprachmodell-Serien, die von Alibaba Cloud veröffentlicht wurden. Dieses 32B-Modell hat signifikante Verbesserungen in den Bereichen Codierung und Mathematik. Das Modell bietet auch mehrsprachige Unterstützung und deckt über 29 Sprachen ab, einschließlich Chinesisch und Englisch. Das Modell hat signifikante Verbesserungen in der Befolgung von Anweisungen, im Verständnis von strukturierten Daten und in der Generierung von strukturierten Ausgaben (insbesondere JSON) erzielt."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM, das auf Chinesisch und Englisch ausgerichtet ist und sich auf Sprache, Programmierung, Mathematik, Schlussfolgern und andere Bereiche konzentriert."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "Fortgeschrittenes LLM, das die Codegenerierung, Schlussfolgerungen und Korrekturen unterstützt und gängige Programmiersprachen abdeckt."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Leistungsstarkes, mittelgroßes Codierungsmodell, das 32K Kontextlängen unterstützt und in der mehrsprachigen Programmierung versiert ist."
+ },
"qwen2": {
"description": "Qwen2 ist das neue große Sprachmodell von Alibaba, das mit hervorragender Leistung eine Vielzahl von Anwendungsanforderungen unterstützt."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 ist das neue, groß angelegte Sprachmodell der Alibaba-Gruppe, das hervorragende Leistungen zur Unterstützung vielfältiger Anwendungsbedürfnisse bietet."
+ },
"qwen2.5-14b-instruct": {
"description": "Das 14B-Modell von Tongyi Qianwen 2.5 ist öffentlich zugänglich."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Tongyi Qianwen 2.5 ist ein Open-Source-Modell mit einer Größe von 72B."
+ },
"qwen2.5-32b-instruct": {
"description": "Das 32B-Modell von Tongyi Qianwen 2.5 ist öffentlich zugänglich."
},
@@ -824,7 +1599,10 @@
"description": "Das 7B-Modell von Tongyi Qianwen 2.5 ist öffentlich zugänglich."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "Die Open-Source-Version des Tongyi Qianwen Code-Modells."
+ "description": "Die Open-Source-Version des Qwen-Codemodells."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Open-Source-Version des Tongyi Qianwen Code-Modells."
},
"qwen2.5-coder-7b-instruct": {
"description": "Die Open-Source-Version des Tongyi Qianwen Code-Modells."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Das Qwen-Math-Modell verfügt über starke Fähigkeiten zur Lösung mathematischer Probleme."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Verbesserte Befolgung von Anweisungen, Mathematik, Problemlösung und Programmierung, gesteigerte Erkennungsfähigkeiten für alle Arten von visuellen Elementen, Unterstützung für die präzise Lokalisierung visueller Elemente in verschiedenen Formaten, Verständnis von langen Videodateien (maximal 10 Minuten) und sekundengenauer Ereigniszeitpunktlokalisierung, Fähigkeit zur zeitlichen Einordnung und Geschwindigkeitsverständnis, Unterstützung für die Steuerung von OS- oder Mobile-Agenten basierend auf Analyse- und Lokalisierungsfähigkeiten, starke Fähigkeit zur Extraktion von Schlüsselinformationen und JSON-Format-Ausgabe. Diese Version ist die leistungsstärkste Version der 72B-Serie."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Verbesserte Befolgung von Anweisungen, Mathematik, Problemlösung und Programmierung, gesteigerte Erkennungsfähigkeiten für alle Arten von visuellen Elementen, Unterstützung für die präzise Lokalisierung visueller Elemente in verschiedenen Formaten, Verständnis von langen Videodateien (maximal 10 Minuten) und sekundengenauer Ereigniszeitpunktlokalisierung, Fähigkeit zur zeitlichen Einordnung und Geschwindigkeitsverständnis, Unterstützung für die Steuerung von OS- oder Mobile-Agenten basierend auf Analyse- und Lokalisierungsfähigkeiten, starke Fähigkeit zur Extraktion von Schlüsselinformationen und JSON-Format-Ausgabe. Diese Version ist die leistungsstärkste Version der 72B-Serie."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 ist das neue, groß angelegte Sprachmodell der Alibaba-Gruppe, das hervorragende Leistungen zur Unterstützung vielfältiger Anwendungsbedürfnisse bietet."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 ist das neue, groß angelegte Sprachmodell der Alibaba-Gruppe, das hervorragende Leistungen zur Unterstützung vielfältiger Anwendungsbedürfnisse bietet."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 ist das neue, groß angelegte Sprachmodell der Alibaba-Gruppe, das hervorragende Leistungen zur Unterstützung vielfältiger Anwendungsbedürfnisse bietet."
+ },
"qwen2:0.5b": {
"description": "Qwen2 ist das neue große Sprachmodell von Alibaba, das mit hervorragender Leistung eine Vielzahl von Anwendungsanforderungen unterstützt."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 ist das neue große Sprachmodell von Alibaba, das mit hervorragender Leistung eine Vielzahl von Anwendungsanforderungen unterstützt."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini ist ein kompaktes LLM, das besser als GPT-3.5 abschneidet und über starke Mehrsprachigkeitsfähigkeiten verfügt, unterstützt Englisch und Koreanisch und bietet eine effiziente, kompakte Lösung."
+ "qwq": {
+ "description": "QwQ ist ein experimentelles Forschungsmodell, das sich auf die Verbesserung der KI-Inferenzfähigkeiten konzentriert."
+ },
+ "qwq-32b": {
+ "description": "Das QwQ-Inferenzmodell, das auf dem Qwen2.5-32B-Modell trainiert wurde, hat durch verstärktes Lernen die Inferenzfähigkeiten des Modells erheblich verbessert. Die Kernmetriken des Modells, wie mathematische Codes (AIME 24/25, LiveCodeBench) sowie einige allgemeine Metriken (IFEval, LiveBench usw.), erreichen das Niveau der DeepSeek-R1 Vollversion, wobei alle Metriken deutlich die ebenfalls auf Qwen2.5-32B basierende DeepSeek-R1-Distill-Qwen-32B übertreffen."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) erweitert die Fähigkeiten von Solar Mini und konzentriert sich auf Japanisch, während es gleichzeitig in der Nutzung von Englisch und Koreanisch effizient und leistungsstark bleibt."
+ "qwq-32b-preview": {
+ "description": "Das QwQ-Modell ist ein experimentelles Forschungsmodell, das vom Qwen-Team entwickelt wurde und sich auf die Verbesserung der KI-Inferenzfähigkeiten konzentriert."
+ },
+ "qwq-plus-latest": {
+ "description": "Das QwQ-Inferenzmodell, das auf dem Qwen2.5-Modell trainiert wurde, hat durch verstärktes Lernen die Inferenzfähigkeiten des Modells erheblich verbessert. Die Kernmetriken des Modells, wie mathematische Codes (AIME 24/25, LiveCodeBench) sowie einige allgemeine Metriken (IFEval, LiveBench usw.), erreichen das Niveau der DeepSeek-R1 Vollversion."
+ },
+ "r1-1776": {
+ "description": "R1-1776 ist eine Version des DeepSeek R1 Modells, die nachtrainiert wurde, um unverfälschte, unvoreingenommene Fakteninformationen bereitzustellen."
+ },
+ "solar-mini": {
+ "description": "Solar Mini ist ein kompaktes LLM, das besser abschneidet als GPT-3.5 und über starke Mehrsprachigkeitsfähigkeiten verfügt. Es unterstützt Englisch und Koreanisch und bietet eine effiziente und kompakte Lösung."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) erweitert die Fähigkeiten von Solar Mini und konzentriert sich auf Japanisch, während es gleichzeitig in der Nutzung von Englisch und Koreanisch hohe Effizienz und hervorragende Leistung beibehält."
},
"solar-pro": {
"description": "Solar Pro ist ein hochintelligentes LLM, das von Upstage entwickelt wurde und sich auf die Befolgung von Anweisungen mit einer einzigen GPU konzentriert, mit einem IFEval-Score von über 80. Derzeit unterstützt es Englisch, die offizielle Version ist für November 2024 geplant und wird die Sprachunterstützung und Kontextlänge erweitern."
},
+ "sonar": {
+ "description": "Ein leichtgewichtiges Suchprodukt, das auf kontextbezogener Suche basiert und schneller und günstiger ist als Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research führt umfassende Expertenforschung durch und fasst diese in zugänglichen, umsetzbaren Berichten zusammen."
+ },
+ "sonar-pro": {
+ "description": "Ein fortschrittliches Suchprodukt, das kontextbezogene Suche unterstützt und erweiterte Abfragen sowie Nachverfolgung ermöglicht."
+ },
+ "sonar-reasoning": {
+ "description": "Ein neues API-Produkt, das von DeepSeek-Inferenzmodellen unterstützt wird."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Ein neues API-Produkt, das von dem DeepSeek-Inferenzmodell unterstützt wird."
+ },
"step-1-128k": {
"description": "Bietet ein ausgewogenes Verhältnis zwischen Leistung und Kosten, geeignet für allgemeine Szenarien."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Hochgeschwindigkeitsmodell, geeignet für Echtzeitdialoge."
},
+ "step-1.5v-mini": {
+ "description": "Dieses Modell verfügt über starke Fähigkeiten zur Videoanalyse."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Dieses Modell verfügt über starke Fähigkeiten zur Bildverständnis und übertrifft 1o in den Bereichen Mathematik und Programmierung. Das Modell ist kleiner als 1o und bietet eine schnellere Ausgabegeschwindigkeit."
+ },
+ "step-1o-vision-32k": {
+ "description": "Dieses Modell verfügt über starke Fähigkeiten zur Bildverständnis. Im Vergleich zu den Modellen der Schritt-1v-Serie bietet es eine verbesserte visuelle Leistung."
+ },
"step-1v-32k": {
"description": "Unterstützt visuelle Eingaben und verbessert die multimodale Interaktionserfahrung."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Unterstützt groß angelegte Kontextinteraktionen und eignet sich für komplexe Dialogszenarien."
},
+ "step-2-mini": {
+ "description": "Ein ultraschnelles Großmodell, das auf der neuen, selbstentwickelten Attention-Architektur MFA basiert. Es erreicht mit extrem niedrigen Kosten ähnliche Ergebnisse wie Schritt 1 und bietet gleichzeitig eine höhere Durchsatzrate und schnellere Reaktionszeiten. Es kann allgemeine Aufgaben bearbeiten und hat besondere Fähigkeiten im Bereich der Codierung."
+ },
"taichu_llm": {
"description": "Das Zīdōng Taichu Sprachmodell verfügt über außergewöhnliche Sprachverständnisfähigkeiten sowie Fähigkeiten in Textgenerierung, Wissensabfrage, Programmierung, mathematischen Berechnungen, logischem Denken, Sentimentanalyse und Textzusammenfassung. Es kombiniert innovativ große Datenvortrainings mit reichhaltigem Wissen aus mehreren Quellen, verfeinert kontinuierlich die Algorithmen und absorbiert ständig neues Wissen aus umfangreichen Textdaten in Bezug auf Vokabular, Struktur, Grammatik und Semantik, um die Leistung des Modells kontinuierlich zu verbessern. Es bietet den Nutzern bequemere Informationen und Dienstleistungen sowie ein intelligenteres Erlebnis."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V vereint Fähigkeiten wie Bildverständnis, Wissensübertragung und logische Attribution und zeigt herausragende Leistungen im Bereich der Bild-Text-Fragen."
+ "taichu_vl": {
+ "description": "Integriert Fähigkeiten wie Bildverständnis, Wissensübertragung und logische Attribution und zeigt herausragende Leistungen im Bereich der Bild-Text-Fragen."
+ },
+ "text-embedding-3-large": {
+ "description": "Das leistungsstärkste Vektormodell, geeignet für englische und nicht-englische Aufgaben."
+ },
+ "text-embedding-3-small": {
+ "description": "Effizientes und kostengünstiges neues Embedding-Modell, geeignet für Wissensabruf, RAG-Anwendungen und andere Szenarien."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Die Open-Source-Version des neuesten vortrainierten Modells der GLM-4-Serie, das von Zhizhu AI veröffentlicht wurde."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) bietet durch effiziente Strategien und Modellarchitekturen verbesserte Rechenfähigkeiten."
},
+ "tts-1": {
+ "description": "Das neueste Text-zu-Sprache-Modell, optimiert für Geschwindigkeit in Echtzeitszenarien."
+ },
+ "tts-1-hd": {
+ "description": "Das neueste Text-zu-Sprache-Modell, optimiert für Qualität."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) eignet sich für präzise Anweisungsaufgaben und bietet hervorragende Sprachverarbeitungsfähigkeiten."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet hebt den Branchenstandard an, übertrifft die Konkurrenzmodelle und Claude 3 Opus und zeigt in umfangreichen Bewertungen hervorragende Leistungen, während es die Geschwindigkeit und Kosten unserer mittelgroßen Modelle beibehält."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 Sonett ist das schnellste nächste Modell von Anthropic. Im Vergleich zu Claude 3 Haiku hat Claude 3.7 Sonett in allen Fähigkeiten Verbesserungen erfahren und übertrifft in vielen intellektuellen Benchmark-Tests das größte Modell der vorherigen Generation, Claude 3 Opus."
+ },
+ "whisper-1": {
+ "description": "Allgemeines Spracherkennungsmodell, unterstützt mehrsprachige Spracherkennung, Sprachübersetzung und Spracherkennung."
+ },
"wizardlm2": {
"description": "WizardLM 2 ist ein Sprachmodell von Microsoft AI, das in komplexen Dialogen, mehrsprachigen Anwendungen, Schlussfolgerungen und intelligenten Assistenten besonders gut abschneidet."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Hervorragendes Preis-Leistungs-Verhältnis und außergewöhnliche Leistung. Hochpräzise Feinabstimmung basierend auf Leistung, Schlussfolgerungsgeschwindigkeit und Kosten."
},
+ "yi-lightning": {
+ "description": "Das neueste Hochleistungsmodell, das hochwertige Ausgaben gewährleistet und gleichzeitig die Schlussfolgerungsgeschwindigkeit erheblich verbessert."
+ },
+ "yi-lightning-lite": {
+ "description": "Leichte Version, empfohlen wird die Verwendung von yi-lightning."
+ },
"yi-medium": {
"description": "Mittelgroßes Modell mit verbesserten Feinabstimmungen, ausgewogene Fähigkeiten und gutes Preis-Leistungs-Verhältnis. Tiefgehende Optimierung der Anweisungsbefolgung."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Modell für komplexe visuelle Aufgaben, das hohe Leistungsfähigkeit bei der Bildverarbeitung und -analyse bietet."
+ },
+ "yi-vision-v2": {
+ "description": "Ein Modell für komplexe visuelle Aufgaben, das leistungsstarke Verständnis- und Analysefähigkeiten auf der Grundlage mehrerer Bilder bietet."
}
}
diff --git a/DigitalHumanWeb/locales/de-DE/plugin.json b/DigitalHumanWeb/locales/de-DE/plugin.json
index f1c41d5..a338a2b 100644
--- a/DigitalHumanWeb/locales/de-DE/plugin.json
+++ b/DigitalHumanWeb/locales/de-DE/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Fehler beim Aktualisieren des Plugins {{name}}.",
"urlError": "Der Link hat keine JSON-Format-Inhalte zurückgegeben. Stellen Sie sicher, dass der Link gültig ist."
},
+ "inspector": {
+ "args": "Parameterliste anzeigen",
+ "pluginRender": "Plugin-Oberfläche anzeigen"
+ },
"list": {
"item": {
"deprecated.title": "Veraltet",
@@ -130,6 +134,34 @@
"plugin": "Plugin wird ausgeführt..."
},
"pluginList": "Plugin-Liste",
+ "search": {
+ "config": {
+ "addKey": "Schlüssel hinzufügen",
+ "close": "Löschen",
+ "confirm": "Konfiguration abgeschlossen und erneut versucht"
+ },
+ "crawPages": {
+ "crawling": "Linkerkennung läuft",
+ "detail": {
+ "preview": "Vorschau",
+ "raw": "Ursprünglicher Text",
+ "tooLong": "Der Textinhalt ist zu lang, der Kontext des Gesprächs behält nur die ersten {{characters}} Zeichen bei, der übersteigende Teil wird nicht in den Gesprächskontext einbezogen."
+ },
+ "meta": {
+ "crawler": "Crawler-Modus",
+ "words": "Zeichenanzahl"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Bitte eingeben",
+ "description": "Geben Sie die URL von SearchXNG ein, um mit der Online-Suche zu beginnen",
+ "keyPlaceholder": "Bitte Schlüssel eingeben",
+ "title": "SearchXNG-Suchmaschine konfigurieren",
+ "unconfiguredDesc": "Bitte wenden Sie sich an den Administrator, um die Konfiguration der SearchXNG-Suchmaschine abzuschließen und mit der Online-Suche zu beginnen",
+ "unconfiguredTitle": "SearchXNG-Suchmaschine ist noch nicht konfiguriert"
+ },
+ "title": "Online-Suche"
+ },
"setting": "Plugin-Einstellung",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/de-DE/portal.json b/DigitalHumanWeb/locales/de-DE/portal.json
index a34ae2d..576a468 100644
--- a/DigitalHumanWeb/locales/de-DE/portal.json
+++ b/DigitalHumanWeb/locales/de-DE/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Plugins",
- "actions": {
- "genAiMessage": "Assistenten-Nachricht erstellen",
- "summary": "Zusammenfassung",
- "summaryTooltip": "Zusammenfassung des aktuellen Inhalts"
- },
"artifacts": {
"display": {
"code": "Code",
diff --git a/DigitalHumanWeb/locales/de-DE/providers.json b/DigitalHumanWeb/locales/de-DE/providers.json
index d1d14a6..0a8f7d0 100644
--- a/DigitalHumanWeb/locales/de-DE/providers.json
+++ b/DigitalHumanWeb/locales/de-DE/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs entwickelt Basis-Modelle und KI-Systeme für Unternehmen und beschleunigt die Anwendung generativer KI in der Produktion."
+ },
"ai360": {
"description": "360 AI ist die von der 360 Company eingeführte Plattform für KI-Modelle und -Dienste, die eine Vielzahl fortschrittlicher Modelle zur Verarbeitung natürlicher Sprache anbietet, darunter 360GPT2 Pro, 360GPT Pro, 360GPT Turbo und 360GPT Turbo Responsibility 8K. Diese Modelle kombinieren große Parameter mit multimodalen Fähigkeiten und finden breite Anwendung in den Bereichen Textgenerierung, semantisches Verständnis, Dialogsysteme und Codegenerierung. Durch flexible Preisstrategien erfüllt 360 AI die vielfältigen Bedürfnisse der Nutzer, unterstützt Entwickler bei der Integration und fördert die Innovation und Entwicklung intelligenter Anwendungen."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure bietet eine Vielzahl fortschrittlicher KI-Modelle, darunter GPT-3.5 und die neueste GPT-4-Serie, die verschiedene Datentypen und komplexe Aufgaben unterstützen und sich auf sichere, zuverlässige und nachhaltige KI-Lösungen konzentrieren."
},
+ "azureai": {
+ "description": "Azure bietet eine Vielzahl fortschrittlicher KI-Modelle, darunter GPT-3.5 und die neueste GPT-4-Serie, die verschiedene Datentypen und komplexe Aufgaben unterstützen und sich auf sichere, zuverlässige und nachhaltige KI-Lösungen konzentrieren."
+ },
"baichuan": {
"description": "Baichuan Intelligent ist ein Unternehmen, das sich auf die Forschung und Entwicklung großer KI-Modelle spezialisiert hat. Ihre Modelle zeigen hervorragende Leistungen in chinesischen Aufgaben wie Wissensdatenbanken, Verarbeitung langer Texte und kreative Generierung und übertreffen die gängigen Modelle im Ausland. Baichuan Intelligent verfügt auch über branchenführende multimodale Fähigkeiten und hat in mehreren renommierten Bewertungen hervorragend abgeschnitten. Ihre Modelle umfassen Baichuan 4, Baichuan 3 Turbo und Baichuan 3 Turbo 128k, die jeweils für unterschiedliche Anwendungsszenarien optimiert sind und kosteneffiziente Lösungen bieten."
},
"bedrock": {
"description": "Bedrock ist ein Service von Amazon AWS, der sich darauf konzentriert, Unternehmen fortschrittliche KI-Sprach- und visuelle Modelle bereitzustellen. Die Modellfamilie umfasst die Claude-Serie von Anthropic, die Llama 3.1-Serie von Meta und mehr, und bietet eine Vielzahl von Optionen von leichtgewichtig bis hochleistungsfähig, die Textgenerierung, Dialoge, Bildverarbeitung und andere Aufgaben unterstützen und für Unternehmensanwendungen unterschiedlicher Größen und Anforderungen geeignet sind."
},
+ "cloudflare": {
+ "description": "Führen Sie von serverlosen GPUs betriebene Machine-Learning-Modelle im globalen Netzwerk von Cloudflare aus."
+ },
"deepseek": {
"description": "DeepSeek ist ein Unternehmen, das sich auf die Forschung und Anwendung von KI-Technologien spezialisiert hat. Ihr neuestes Modell, DeepSeek-V2.5, kombiniert allgemeine Dialog- und Codeverarbeitungsfähigkeiten und hat signifikante Fortschritte in den Bereichen menschliche Präferenzanpassung, Schreibaufgaben und Befehlsbefolgung erzielt."
},
+ "doubao": {
+ "description": "Ein von ByteDance entwickeltes großes Modell. Durch die praktische Validierung in über 50 internen Geschäftsszenarien und die kontinuierliche Verfeinerung mit täglich Billionen von Tokens bietet es vielfältige Modalitäten und schafft mit hochwertigen Modellergebnissen ein reichhaltiges Geschäftserlebnis für Unternehmen."
+ },
"fireworksai": {
"description": "Fireworks AI ist ein führender Anbieter von fortschrittlichen Sprachmodellen, der sich auf Funktionsaufrufe und multimodale Verarbeitung spezialisiert hat. Ihr neuestes Modell, Firefunction V2, basiert auf Llama-3 und ist für Funktionsaufrufe, Dialoge und Befehlsbefolgung optimiert. Das visuelle Sprachmodell FireLLaVA-13B unterstützt gemischte Eingaben von Bildern und Text. Weitere bemerkenswerte Modelle sind die Llama-Serie und die Mixtral-Serie, die effiziente mehrsprachige Befehlsbefolgung und Generierungsunterstützung bieten."
},
+ "giteeai": {
+ "description": "Die serverlose API von Gitee AI bietet KI-Entwicklern einen sofort einsatzbereiten großen Modell-Inferenz-API-Service."
+ },
"github": {
"description": "Mit GitHub-Modellen können Entwickler zu KI-Ingenieuren werden und mit den führenden KI-Modellen der Branche arbeiten."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Der LPU-Inferenz-Engine von Groq hat in den neuesten unabhängigen Benchmark-Tests für große Sprachmodelle (LLM) hervorragende Leistungen gezeigt und definiert mit seiner erstaunlichen Geschwindigkeit und Effizienz die Standards für KI-Lösungen neu. Groq ist ein Beispiel für sofortige Inferenzgeschwindigkeit und zeigt in cloudbasierten Bereitstellungen eine gute Leistung."
},
+ "higress": {
+ "description": "Higress ist ein cloud-natives API-Gateway, das intern bei Alibaba entwickelt wurde, um die Probleme von Tengine Reload bei langanhaltenden Verbindungen zu lösen und die unzureichenden Lastverteilungsmöglichkeiten von gRPC/Dubbo zu verbessern."
+ },
+ "huggingface": {
+ "description": "Die HuggingFace Inference API bietet eine schnelle und kostenlose Möglichkeit, Tausende von Modellen für verschiedene Aufgaben zu erkunden. Egal, ob Sie Prototypen für neue Anwendungen erstellen oder die Funktionen des maschinellen Lernens ausprobieren, diese API ermöglicht Ihnen den sofortigen Zugriff auf leistungsstarke Modelle aus verschiedenen Bereichen."
+ },
+ "hunyuan": {
+ "description": "Ein von Tencent entwickeltes großes Sprachmodell, das über starke Fähigkeiten zur Erstellung von Inhalten in chinesischer Sprache, logisches Denkvermögen in komplexen Kontexten und zuverlässige Fähigkeiten zur Aufgabenerfüllung verfügt."
+ },
+ "internlm": {
+ "description": "Eine Open-Source-Organisation, die sich der Forschung und Entwicklung von großen Modellen und Werkzeugketten widmet. Sie bietet allen KI-Entwicklern eine effiziente und benutzerfreundliche Open-Source-Plattform, die den Zugang zu den neuesten Technologien und Algorithmen für große Modelle ermöglicht."
+ },
+ "jina": {
+ "description": "Jina AI wurde 2020 gegründet und ist ein führendes Unternehmen im Bereich Such-KI. Unsere Suchplattform umfasst Vektormodelle, Re-Ranker und kleine Sprachmodelle, die Unternehmen dabei helfen, zuverlässige und qualitativ hochwertige generative KI- und multimodale Suchanwendungen zu entwickeln."
+ },
+ "lmstudio": {
+ "description": "LM Studio ist eine Desktop-Anwendung zum Entwickeln und Experimentieren mit LLMs auf Ihrem Computer."
+ },
"minimax": {
"description": "MiniMax ist ein im Jahr 2021 gegründetes Unternehmen für allgemeine künstliche Intelligenz, das sich der gemeinsamen Schaffung von Intelligenz mit den Nutzern widmet. MiniMax hat verschiedene multimodale allgemeine große Modelle entwickelt, darunter ein Textmodell mit Billionen von Parametern, ein Sprachmodell und ein Bildmodell. Außerdem wurden Anwendungen wie Conch AI eingeführt."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI ist eine Plattform, die eine Vielzahl von großen Sprachmodellen und API-Diensten für die KI-Bilderzeugung anbietet, die flexibel, zuverlässig und kosteneffektiv ist. Sie unterstützt die neuesten Open-Source-Modelle wie Llama3 und Mistral und bietet umfassende, benutzerfreundliche und automatisch skalierbare API-Lösungen für die Entwicklung generativer KI-Anwendungen, die für das schnelle Wachstum von KI-Startups geeignet sind."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ bietet Container für selbstgehostete, GPU-beschleunigte Inferenz-Mikrodienste, die die Bereitstellung von vortrainierten und benutzerdefinierten KI-Modellen in der Cloud, in Rechenzentren, auf RTX™ AI-PCs und Workstations unterstützen."
+ },
"ollama": {
"description": "Die von Ollama angebotenen Modelle decken ein breites Spektrum ab, darunter Code-Generierung, mathematische Berechnungen, mehrsprachige Verarbeitung und dialogbasierte Interaktionen, und unterstützen die vielfältigen Anforderungen an unternehmensgerechte und lokal angepasste Bereitstellungen."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity ist ein führender Anbieter von Dialoggenerierungsmodellen und bietet eine Vielzahl fortschrittlicher Llama 3.1-Modelle an, die sowohl für Online- als auch Offline-Anwendungen geeignet sind und sich besonders für komplexe Aufgaben der Verarbeitung natürlicher Sprache eignen."
},
+ "ppio": {
+ "description": "PPIO Paiou Cloud bietet stabile und kosteneffiziente Open-Source-Modell-API-Dienste und unterstützt die gesamte DeepSeek-Serie, Llama, Qwen und andere führende große Modelle der Branche."
+ },
"qwen": {
"description": "Tongyi Qianwen ist ein von Alibaba Cloud selbst entwickeltes, groß angelegtes Sprachmodell mit starken Fähigkeiten zur Verarbeitung und Generierung natürlicher Sprache. Es kann eine Vielzahl von Fragen beantworten, Texte erstellen, Meinungen äußern und Code schreiben und spielt in mehreren Bereichen eine Rolle."
},
+ "sambanova": {
+ "description": "SambaNova Cloud ermöglicht es Entwicklern, die besten Open-Source-Modelle einfach zu nutzen und von der schnellsten Inferenzgeschwindigkeit zu profitieren."
+ },
+ "sensenova": {
+ "description": "SenseTime bietet mit der starken Basisunterstützung von SenseTimes großem Gerät effiziente und benutzerfreundliche Full-Stack-Modelldienste."
+ },
"siliconcloud": {
"description": "SiliconFlow hat sich zum Ziel gesetzt, AGI zu beschleunigen, um der Menschheit zu dienen, und die Effizienz großangelegter KI durch eine benutzerfreundliche und kostengünstige GenAI-Stack zu steigern."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "Das Institut für Automatisierung der Chinesischen Akademie der Wissenschaften und das Wuhan Institute of Artificial Intelligence haben ein neues Generation multimodales großes Modell eingeführt, das umfassende Frage-Antwort-Aufgaben unterstützt, darunter mehrstufige Fragen, Textgenerierung, Bildgenerierung, 3D-Verständnis und Signalverarbeitung, mit stärkeren kognitiven, verstehenden und kreativen Fähigkeiten, die ein neues interaktives Erlebnis bieten."
},
+ "tencentcloud": {
+ "description": "Die atomare Fähigkeit der Wissensmaschine (LLM Knowledge Engine Atomic Power) basiert auf der Entwicklung der Wissensmaschine und bietet eine umfassende Fähigkeit zur Wissensabfrage für Unternehmen und Entwickler. Sie können mit verschiedenen atomaren Fähigkeiten Ihren eigenen Modellservice erstellen und Dokumentenanalysen, -aufteilungen, Embeddings, mehrfache Umformulierungen und andere Dienste kombinieren, um maßgeschneiderte KI-Lösungen für Ihr Unternehmen zu entwickeln."
+ },
"togetherai": {
"description": "Together AI strebt an, durch innovative KI-Modelle führende Leistungen zu erzielen und bietet umfangreiche Anpassungsmöglichkeiten, einschließlich schneller Skalierungsunterstützung und intuitiver Bereitstellungsprozesse, um den unterschiedlichen Anforderungen von Unternehmen gerecht zu werden."
},
"upstage": {
"description": "Upstage konzentriert sich auf die Entwicklung von KI-Modellen für verschiedene geschäftliche Anforderungen, einschließlich Solar LLM und Dokumenten-KI, mit dem Ziel, künstliche allgemeine Intelligenz (AGI) zu erreichen. Es ermöglicht die Erstellung einfacher Dialogagenten über die Chat-API und unterstützt Funktionsaufrufe, Übersetzungen, Einbettungen und spezifische Anwendungsbereiche."
},
+ "vertexai": {
+ "description": "Die Gemini-Serie von Google ist das fortschrittlichste, universelle KI-Modell, das von Google DeepMind entwickelt wurde. Es ist speziell für multimodale Anwendungen konzipiert und unterstützt das nahtlose Verständnis und die Verarbeitung von Text, Code, Bildern, Audio und Video. Es eignet sich für eine Vielzahl von Umgebungen, von Rechenzentren bis hin zu mobilen Geräten, und verbessert erheblich die Effizienz und Anwendbarkeit von KI-Modellen."
+ },
+ "vllm": {
+ "description": "vLLM ist eine schnelle und benutzerfreundliche Bibliothek für LLM-Inferenz und -Dienste."
+ },
+ "volcengine": {
+ "description": "Die von ByteDance eingeführte Entwicklungsplattform für große Modellservices bietet funktionsreiche, sichere und preislich wettbewerbsfähige Modellaufrufdienste. Sie bietet zudem End-to-End-Funktionen wie Moduldaten, Feinabstimmung, Inferenz und Bewertung, um die Entwicklung Ihrer KI-Anwendungen umfassend zu unterstützen."
+ },
+ "wenxin": {
+ "description": "Eine unternehmensweite, umfassende Plattform für die Entwicklung und den Service von großen Modellen und KI-nativen Anwendungen, die die vollständigsten und benutzerfreundlichsten Werkzeuge für die Entwicklung generativer KI-Modelle und den gesamten Anwendungsentwicklungsprozess bietet."
+ },
+ "xai": {
+ "description": "xAI ist ein Unternehmen, das sich der Entwicklung von Künstlicher Intelligenz widmet, um menschliche wissenschaftliche Entdeckungen zu beschleunigen. Unsere Mission ist es, unser gemeinsames Verständnis des Universums voranzutreiben."
+ },
"zeroone": {
"description": "01.AI konzentriert sich auf die künstliche Intelligenz-Technologie der AI 2.0-Ära und fördert aktiv die Innovation und Anwendung von 'Mensch + künstliche Intelligenz', indem sie leistungsstarke Modelle und fortschrittliche KI-Technologien einsetzt, um die Produktivität der Menschen zu steigern und technologische Befähigung zu erreichen."
},
diff --git a/DigitalHumanWeb/locales/de-DE/setting.json b/DigitalHumanWeb/locales/de-DE/setting.json
index 4cf3937..13a24aa 100644
--- a/DigitalHumanWeb/locales/de-DE/setting.json
+++ b/DigitalHumanWeb/locales/de-DE/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Benutzerdefinierte Modellkonfiguration",
"tokens": {
- "title": "Maximale Token-Anzahl",
- "unlimited": "unbegrenzt"
+ "title": "Maximale Token-Anzahl"
},
"vision": {
"extra": "Diese Konfiguration aktiviert nur die Bild-Upload-Einstellungen innerhalb der Anwendung. Ob die Erkennung unterstützt wird, hängt vollständig vom Modell selbst ab. Bitte teste die Verwendbarkeit der visuellen Erkennungsfähigkeit des Modells selbst.",
@@ -98,6 +97,7 @@
"title": "Client Fetch-Modus verwenden"
},
"fetcher": {
+ "clear": "Abgerufenes Modell löschen",
"fetch": "Modelle abrufen",
"fetching": "Modelle werden abgerufen...",
"latestTime": "Letzte Aktualisierung: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Automatische Erstellung eines Themas während des Gesprächs, nur in temporären Themen aktiv",
"title": "Automatische Themen-Erstellung aktivieren"
},
- "enableCompressThreshold": {
- "title": "Aktivieren der Komprimierungsschwelle für Historienlänge"
+ "enableCompressHistory": {
+ "title": "Automatische Zusammenfassung der Verlaufnachrichten aktivieren"
},
"enableHistoryCount": {
"alias": "Unbegrenzt",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Maximale Token pro Antwort aktivieren"
},
+ "enableReasoningEffort": {
+ "title": "Aktivieren Sie die Anpassung der Schlussfolgerungsintensität"
+ },
"frequencyPenalty": {
- "desc": "Je höher der Wert, desto wahrscheinlicher ist es, dass sich wiederholende Wörter reduziert werden",
- "title": "Frequenzstrafe"
+ "desc": "Je höher der Wert, desto vielfältiger und abwechslungsreicher die Wortwahl; je niedriger der Wert, desto einfacher und schlichter die Wortwahl",
+ "title": "Wortvielfalt"
},
"maxTokens": {
"desc": "Maximale Anzahl von Tokens, die pro Interaktion verwendet werden",
@@ -212,19 +215,31 @@
"desc": "{{provider}} Modell",
"title": "Modell"
},
+ "params": {
+ "title": "Erweiterte Parameter"
+ },
"presencePenalty": {
- "desc": "Je höher der Wert, desto wahrscheinlicher ist es, dass sich das Gespräch auf neue Themen ausweitet",
- "title": "Themenfrische"
+ "desc": "Je höher der Wert, desto eher werden unterschiedliche Ausdrucksweisen bevorzugt, um Wiederholungen zu vermeiden; je niedriger der Wert, desto eher werden wiederholte Konzepte oder Erzählungen verwendet, was zu einer konsistenteren Ausdrucksweise führt",
+ "title": "Ausdrucksvielfalt"
+ },
+ "reasoningEffort": {
+ "desc": "Je höher der Wert, desto stärker die Schlussfolgerungsfähigkeit, aber dies kann die Antwortzeit und den Tokenverbrauch erhöhen.",
+ "options": {
+ "high": "Hoch",
+ "low": "Niedrig",
+ "medium": "Mittel"
+ },
+ "title": "Schlussfolgerungsintensität"
},
"temperature": {
- "desc": "Je höher der Wert, desto zufälliger die Antwort",
- "title": "Zufälligkeit",
- "titleWithValue": "Zufälligkeit {{value}}"
+ "desc": "Je höher der Wert, desto kreativer und einfallsreicher die Antworten; je niedriger der Wert, desto strenger die Antworten",
+ "title": "Kreativitätsgrad",
+ "warning": "Ein zu hoher Kreativitätsgrad kann zu unverständlichen Ausgaben führen"
},
- "title": "Modelleinstellungen",
+ "title": "Modell Einstellungen",
"topP": {
- "desc": "Ähnlich wie Zufälligkeit, aber nicht zusammen mit Zufälligkeit ändern",
- "title": "Top-P-Sampling"
+ "desc": "Wie viele Möglichkeiten in Betracht gezogen werden, je höher der Wert, desto mehr mögliche Antworten werden akzeptiert; je niedriger der Wert, desto eher wird die wahrscheinlichste Antwort gewählt. Es wird nicht empfohlen, dies zusammen mit dem Kreativitätsgrad zu ändern",
+ "title": "Offenheit des Denkens"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Das Modell, das zur Generierung von Assistentennamen, -beschreibungen, -avatars und -tags verwendet wird",
"title": "Automatische Generierung von Assistenteninformationen"
},
+ "customPrompt": {
+ "addPrompt": "Benutzerdefinierte Eingabe hinzufügen",
+ "desc": "Nachdem Sie dies ausgefüllt haben, verwendet der Systemassistent die benutzerdefinierte Eingabe zur Generierung von Inhalten",
+ "placeholder": "Bitte benutzerdefinierte Eingabe eingeben",
+ "title": "Benutzerdefinierte Eingabe"
+ },
+ "historyCompress": {
+ "label": "Gesprächshistorienmodell",
+ "modelDesc": "Das Modell, das zur Komprimierung der Gesprächshistorie verwendet wird",
+ "title": "Automatische Zusammenfassung der Gesprächshistorie"
+ },
"queryRewrite": {
"label": "Fragenumformulierung Modell",
"modelDesc": "Modell zur Optimierung der Benutzeranfragen",
- "title": "Wissensdatenbank"
+ "title": "Wiederformulierung von Fragen aus der Wissensdatenbank"
+ },
+ "thread": {
+ "label": "Unterthema-Namensmodell",
+ "modelDesc": "Modell zur automatischen Umbenennung von Unterthemen",
+ "title": "Automatische Benennung von Unterthemen"
},
"title": "Systemassistent",
"topic": {
@@ -395,6 +426,7 @@
"common": "Allgemeine Einstellungen",
"experiment": "Experiment",
"llm": "Sprachmodell",
+ "provider": "KI-Dienstanbieter",
"sync": "Cloud-Synchronisierung",
"system-agent": "Systemassistent",
"tts": "Sprachdienste"
diff --git a/DigitalHumanWeb/locales/de-DE/thread.json b/DigitalHumanWeb/locales/de-DE/thread.json
new file mode 100644
index 0000000..007cc6d
--- /dev/null
+++ b/DigitalHumanWeb/locales/de-DE/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Sie sind dabei, dieses Unterthema zu löschen. Nach dem Löschen kann es nicht wiederhergestellt werden. Bitte seien Sie vorsichtig."
+ },
+ "newPortalThread": {
+ "includeContext": "Themenkontext einbeziehen",
+ "title": "Neues Unterthema eröffnen"
+ },
+ "notSupportMultiModals": "Unterthemen unterstützen derzeit keinen Datei-/Bilderupload. Bei Bedarf freuen wir uns über Nachrichten: <1>💬 Diskussionsbereich1>"
+}
diff --git a/DigitalHumanWeb/locales/de-DE/tool.json b/DigitalHumanWeb/locales/de-DE/tool.json
index 02a9c5e..24f5bc7 100644
--- a/DigitalHumanWeb/locales/de-DE/tool.json
+++ b/DigitalHumanWeb/locales/de-DE/tool.json
@@ -6,5 +6,23 @@
"generating": "Generiert",
"images": "Bilder:",
"prompt": "Hinweiswort"
+ },
+ "search": {
+ "createNewSearch": "Neue Suchanfrage erstellen",
+ "emptyResult": "Keine Ergebnisse gefunden, bitte ändern Sie die Schlüsselwörter und versuchen Sie es erneut",
+ "genAiMessage": "Assistentnachricht erstellen",
+ "includedTooltip": "Die aktuellen Suchergebnisse werden in den Kontext der Sitzung aufgenommen",
+ "keywords": "Schlüsselwörter:",
+ "scoreTooltip": "Relevanzpunktzahl, je höher die Punktzahl, desto relevanter ist sie für die Suchanfrage",
+ "searchBar": {
+ "button": "Suchen",
+ "placeholder": "Schlüsselwörter",
+ "tooltip": "Die Suchergebnisse werden erneut abgerufen und eine neue Zusammenfassungsnachricht wird erstellt"
+ },
+ "searchEngine": "Suchmaschine:",
+ "searchResult": "Anzahl der Suchergebnisse:",
+ "summary": "Zusammenfassung",
+ "summaryTooltip": "Aktuellen Inhalt zusammenfassen",
+ "viewMoreResults": "Weitere {{results}} Ergebnisse anzeigen"
}
}
diff --git a/DigitalHumanWeb/locales/de-DE/topic.json b/DigitalHumanWeb/locales/de-DE/topic.json
new file mode 100644
index 0000000..d22d460
--- /dev/null
+++ b/DigitalHumanWeb/locales/de-DE/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Intelligente Umbenennung",
+ "confirmRemoveAll": "Alle Themen werden gelöscht. Nach dem Löschen können sie nicht wiederhergestellt werden. Bitte vorsichtig handeln.",
+ "confirmRemoveTopic": "Dieses Thema wird gelöscht. Nach dem Löschen kann es nicht wiederhergestellt werden. Bitte vorsichtig handeln.",
+ "confirmRemoveUnstarred": "Nicht markierte Themen werden gelöscht. Nach dem Löschen können sie nicht wiederhergestellt werden. Bitte vorsichtig handeln.",
+ "duplicate": "Kopie erstellen",
+ "export": "Thema exportieren",
+ "removeAll": "Alle Themen löschen",
+ "removeUnstarred": "Nicht markierte Themen löschen"
+ },
+ "defaultTitle": "Standardthema",
+ "duplicateLoading": "Thema wird kopiert...",
+ "duplicateSuccess": "Thema erfolgreich kopiert",
+ "favorite": "Favorit",
+ "groupMode": {
+ "ascMessages": "Nach Gesamtanzahl der Nachrichten aufsteigend",
+ "byTime": "Nach Zeit gruppiert",
+ "descMessages": "Nach Gesamtanzahl der Nachrichten absteigend",
+ "flat": "Nicht gruppiert"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Diesen Monat",
+ "today": "Heute",
+ "week": "Diese Woche",
+ "yesterday": "Gestern"
+ }
+ },
+ "guide": {
+ "desc": "Klicken Sie auf die Schaltfläche links von Senden, um den aktuellen Chat als historisches Thema zu speichern und eine neue Runde des Chats zu beginnen.",
+ "title": "Themenliste"
+ },
+ "searchPlaceholder": "Themen suchen...",
+ "searchResultEmpty": "Keine Suchergebnisse vorhanden",
+ "temp": "Vorübergehend",
+ "title": "Thema"
+}
diff --git a/DigitalHumanWeb/locales/de-DE/welcome.json b/DigitalHumanWeb/locales/de-DE/welcome.json
index b4f105e..517c694 100644
--- a/DigitalHumanWeb/locales/de-DE/welcome.json
+++ b/DigitalHumanWeb/locales/de-DE/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Konfiguration importieren",
- "market": "Markt durchstöbern",
- "start": "Jetzt starten"
- },
"guide": {
"agents": {
"replaceBtn": "Ersetzen",
diff --git a/DigitalHumanWeb/locales/en-US/auth.json b/DigitalHumanWeb/locales/en-US/auth.json
index d363724..cbe39b9 100644
--- a/DigitalHumanWeb/locales/en-US/auth.json
+++ b/DigitalHumanWeb/locales/en-US/auth.json
@@ -1,8 +1,96 @@
{
- "login": "Login",
- "loginOrSignup": "Log in / Sign up",
- "profile": "Profile",
- "security": "Security",
- "signout": "Sign out",
- "signup": "Sign up"
+ "date": {
+ "prevMonth": "Last Month",
+ "recent30Days": "Last 30 Days"
+ },
+ "header": {
+ "desc": "Manage your account information.",
+ "title": "Account"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Inactive",
+ "more": "Active"
+ },
+ "months": {
+ "apr": "Apr",
+ "aug": "Aug",
+ "dec": "Dec",
+ "feb": "Feb",
+ "jan": "Jan",
+ "jul": "Jul",
+ "jun": "Jun",
+ "mar": "Mar",
+ "may": "May",
+ "nov": "Nov",
+ "oct": "Oct",
+ "sep": "Sep"
+ },
+ "tooltip": "{{date}} sent {{count}} messages that day",
+ "totalCount": "A total of {{count}} messages sent in the past year"
+ },
+ "login": "Log In",
+ "loginOrSignup": "Log In / Sign Up",
+ "profile": {
+ "avatar": "Avatar",
+ "email": "Email Address",
+ "sso": {
+ "loading": "Loading linked third-party accounts",
+ "providers": "Connected Accounts",
+ "unlink": {
+ "description": "After unlinking, you will not be able to log in using the {{provider}} account \"{{providerAccountId}}\". If you need to re-link your {{provider}} account to the current account, please ensure that the email address for your {{provider}} account is {{email}}. We will automatically link it to the current logged-in account upon login.",
+ "forbidden": "You must retain at least one linked third-party account.",
+ "title": "Are you sure you want to unlink the third-party account {{provider}}?"
+ }
+ },
+ "username": "Username"
+ },
+ "signout": "Log Out",
+ "signup": "Sign Up",
+ "stats": {
+ "aiheatmaps": "Activity Index",
+ "assistants": "Assistants",
+ "assistantsRank": {
+ "left": "Assistant",
+ "right": "Topics",
+ "title": "Assistant Usage Rank"
+ },
+ "createdAt": "Registered at",
+ "days": "days",
+ "empty": {
+ "desc": "Please accumulate more chat data to view",
+ "title": "No Data"
+ },
+ "lastYearActivity": "Activity in the past year",
+ "loginGuide": {
+ "f1": "Get free usage",
+ "f2": "Sync messages across devices",
+ "f3": "Access a wealth of assistants",
+ "f4": "Explore powerful plugins",
+ "title": "After logging in, you can:"
+ },
+ "messages": "Messages",
+ "modelsRank": {
+ "left": "Model",
+ "right": "Messages",
+ "title": "Model Usage Rank"
+ },
+ "share": {
+ "title": "My AI Activity Index"
+ },
+ "topics": "Topics",
+ "topicsRank": {
+ "left": "Topic",
+ "right": "Messages",
+ "title": "Topic Content Rank"
+ },
+ "updatedAt": "Updated at",
+ "welcome": "{{username}}, this is your {{days}} day with {{appName}}",
+ "words": "Total Words"
+ },
+ "tab": {
+ "profile": "Profile",
+ "security": "Security",
+ "stats": "Statistics"
+ }
}
diff --git a/DigitalHumanWeb/locales/en-US/changelog.json b/DigitalHumanWeb/locales/en-US/changelog.json
new file mode 100644
index 0000000..f9563dd
--- /dev/null
+++ b/DigitalHumanWeb/locales/en-US/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Follow us on X",
+ "subscribeToUpdates": "Subscribe for updates",
+ "versions": "Version details"
+ },
+ "addedWhileAway": "We've introduced new features while you were away.",
+ "allChangelog": "View all changelogs",
+ "description": "Stay updated on the new features and improvements of {{appName}}",
+ "pagination": {
+ "next": "Next Page",
+ "older": "View Historical Changes"
+ },
+ "readDetails": "Read details",
+ "title": "Changelog",
+ "versionDetails": "Version details",
+ "welcomeBack": "Welcome back!"
+}
diff --git a/DigitalHumanWeb/locales/en-US/chat.json b/DigitalHumanWeb/locales/en-US/chat.json
index 2d1dd43..006186a 100644
--- a/DigitalHumanWeb/locales/en-US/chat.json
+++ b/DigitalHumanWeb/locales/en-US/chat.json
@@ -8,8 +8,9 @@
"agents": "Assistants",
"artifact": {
"generating": "Generating",
+ "inThread": "Cannot view in subtopic, please switch to the main conversation area to open",
"thinking": "Thinking",
- "thought": "Thought Process",
+ "thought": "Thought",
"unknownTitle": "Untitled Work"
},
"backToBottom": "Back to bottom",
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Copy",
"emptyAgent": "No assistant available",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "The cost of generating a single conversation can be reduced by up to 90%, and the response speed is increased by 4 times (<1>Learn more1>). Enabling this will automatically disable the limit on the number of historical messages.",
+ "title": "Enable Context Caching"
+ },
+ "enableReasoning": {
+ "desc": "Based on the Claude Thinking mechanism limit (<1>Learn more1>), enabling this will automatically disable the limit on the number of historical messages.",
+ "title": "Enable Deep Thinking"
+ },
+ "reasoningBudgetToken": {
+ "title": "Thinking Consumption Token"
+ },
+ "title": "Model Extension Features"
+ },
+ "history": {
+ "title": "The assistant will only remember the last {{count}} messages."
+ },
"historyRange": "History Range",
+ "historySummary": "Historical Message Summary",
"inbox": {
"desc": "Activate the brain cluster and spark creative thinking. Your virtual assistant is here to communicate with you about everything.",
"title": "Just Chat"
@@ -45,6 +64,9 @@
"stop": "Stop",
"warp": "New Line"
},
+ "intentUnderstanding": {
+ "title": "Understanding and analyzing your intent..."
+ },
"knowledgeBase": {
"all": "All Content",
"allFiles": "All Files",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Delete and Regenerate",
+ "deleteDisabledByThreads": "There are subtopics, deletion is not allowed",
"regenerate": "Regenerate"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Credits",
+ "creditPricing": "Pricing",
+ "creditTooltip": "For counting purposes, we convert $1 to 1M credits; for example, $3/M tokens can be converted to 3 credits/token.",
+ "pricing": {
+ "inputCachedTokens": "Cached input {{amount}}/credits · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M characters",
+ "inputMinutes": "${{amount}}/minute",
+ "inputTokens": "Input {{amount}}/credits · ${{amount}}/M",
+ "outputTokens": "Output {{amount}}/credits · ${{amount}}/M",
+ "writeCacheInputTokens": "Cache input write {{amount}}/points · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Average unit price",
+ "input": "Input",
+ "inputAudio": "Audio Input",
+ "inputCached": "Cached Input",
+ "inputCitation": "Input citation",
+ "inputText": "Text Input",
+ "inputTitle": "Input Details",
+ "inputUncached": "Uncached Input",
+ "inputWriteCached": "Input cache write",
+ "output": "Output",
+ "outputAudio": "Audio Output",
+ "outputText": "Text Output",
+ "outputTitle": "Output Details",
+ "reasoning": "Deep Thinking",
+ "title": "Generation Details",
+ "total": "Total Consumption"
+ }
+ },
"newAgent": "New Assistant",
"pin": "Pin",
"pinOff": "Unpin",
@@ -81,6 +137,32 @@
},
"regenerate": "Regenerate",
"roleAndArchive": "Role and Archive",
+ "search": {
+ "grounding": {
+ "searchQueries": "Search Keywords",
+ "title": "Found {{count}} results"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Intelligently determine whether a search is needed based on the conversation content",
+ "title": "Smart Online Search"
+ },
+ "off": {
+ "desc": "Use only the model's basic knowledge without performing a web search",
+ "title": "Disable Online Search"
+ },
+ "on": {
+ "desc": "Continuously perform web searches to obtain the latest information",
+ "title": "Always Online"
+ },
+ "useModelBuiltin": "Use the model's built-in search engine"
+ },
+ "searchModel": {
+ "desc": "The current model does not support function calls, so it needs to be paired with a model that does support function calls for online searching.",
+ "title": "Search Assistant Model"
+ },
+ "title": "Online Search"
+ },
"searchAgentPlaceholder": "Search assistants...",
"sendPlaceholder": "Type your message here...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Group name length should be between 1-20"
},
"shareModal": {
+ "copy": "Copy",
"download": "Download Screenshot",
+ "downloadFile": "Download File",
+ "exportTitle": "Default Title",
"imageType": "Image Format",
+ "includeTool": "Include Plugin Messages",
+ "includeUser": "Include User Messages",
"screenshot": "Screenshot",
"settings": "Export Settings",
- "shareToShareGPT": "Generate ShareGPT Sharing Link",
+ "text": "Text",
"withBackground": "Include Background Image",
"withFooter": "Include Footer",
"withPluginInfo": "Include Plugin Information",
+ "withRole": "Include Message Role",
"withSystemRole": "Include Assistant Role Setting"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Recognizing...",
"prettifying": "Polishing..."
},
- "temp": "Temporary",
+ "thread": {
+ "divider": "Subtopic",
+ "threadMessageCount": "{{messageCount}} messages",
+ "title": "Subtopic"
+ },
"tokenDetails": {
"chats": "Chat Messages",
+ "historySummary": "History Summary",
"rest": "Remaining",
"systemRole": "Role Settings",
"title": "Context Details",
@@ -131,29 +224,10 @@
"used": "Used"
},
"topic": {
- "actions": {
- "autoRename": "Auto Rename",
- "duplicate": "Create Copy",
- "export": "Export Topic"
- },
"checkOpenNewTopic": "Enable new topic?",
"checkSaveCurrentMessages": "Do you want to save the current conversation as a topic?",
- "confirmRemoveAll": "You are about to delete all topics. Once deleted, they cannot be recovered. Please proceed with caution.",
- "confirmRemoveTopic": "You are about to delete this topic. Once deleted, it cannot be recovered. Please proceed with caution.",
- "confirmRemoveUnstarred": "You are about to delete unstarred topics. Once deleted, they cannot be recovered. Please proceed with caution.",
- "defaultTitle": "Default Topic",
- "duplicateLoading": "Topic duplicating...",
- "duplicateSuccess": "Topic duplicated successfully",
- "guide": {
- "desc": "Click the button on the left to save the current session as a historical topic and start a new session.",
- "title": "Topic List"
- },
"openNewTopic": "Open New Topic",
- "removeAll": "Remove All Topics",
- "removeUnstarred": "Remove Unstarred Topics",
- "saveCurrentMessages": "Save current session as topic",
- "searchPlaceholder": "Search topics...",
- "title": "Topic List"
+ "saveCurrentMessages": "Save current session as topic"
},
"translate": {
"action": "Translate",
@@ -184,5 +258,6 @@
"processing": "Processing file..."
}
}
- }
+ },
+ "zenMode": "Zen Mode"
}
diff --git a/DigitalHumanWeb/locales/en-US/common.json b/DigitalHumanWeb/locales/en-US/common.json
index 38194dc..ca92f23 100644
--- a/DigitalHumanWeb/locales/en-US/common.json
+++ b/DigitalHumanWeb/locales/en-US/common.json
@@ -9,15 +9,79 @@
"title": "Launch {{name}}"
}
},
- "appInitializing": "Application is starting...",
+ "appLoading": {
+ "appIdle": "Ready to start",
+ "appInitializing": "Application is starting...",
+ "failed": "Sorry, the application initialization failed. Please check the details for troubleshooting.",
+ "finished": "Database initialization completed",
+ "goToChat": "Loading chat page...",
+ "initAuth": "Initializing authentication service...",
+ "initUser": "Initializing user status...",
+ "initializing": "Initializing PGlite database...",
+ "loadingDependencies": "Initializing dependencies...",
+ "loadingWasm": "Loading WASM module...",
+ "migrating": "Performing database migration...",
+ "ready": "Database is ready",
+ "showDetail": "View details"
+ },
"autoGenerate": "Auto Generate",
"autoGenerateTooltip": "Auto-generate assistant description based on prompts",
"autoGenerateTooltipDisabled": "Please enter a tooltip before using the autocomplete feature",
"back": "Back",
"batchDelete": "Batch Delete",
"blog": "Product Blog",
+ "branching": "Create Subtopic",
+ "branchingDisable": "The 'Subtopic' feature is only available in the server version. If you need this feature, please switch to server deployment mode or use LobeChat Cloud.",
"cancel": "Cancel",
"changelog": "Changelog",
+ "clientDB": {
+ "autoInit": {
+ "title": "Initializing PGlite Database"
+ },
+ "error": {
+ "desc": "We apologize, an error occurred during the Pglite database initialization process. Please click the button to retry. If the error persists after multiple attempts, please <1>submit an issue1>, and we will assist you as soon as possible.",
+ "detail": "Error reason: [{{type}}] {{message}}. Details are as follows:",
+ "retry": "Retry",
+ "title": "Database Initialization Failed"
+ },
+ "initing": {
+ "error": "An error occurred, please try again",
+ "idle": "Waiting for initialization...",
+ "initializing": "Initializing...",
+ "loadingDependencies": "Loading dependencies...",
+ "loadingWasmModule": "Loading WASM module...",
+ "migrating": "Performing database migration...",
+ "ready": "Database is ready"
+ },
+ "modal": {
+ "desc": "Enable the PGlite client database to persistently store chat data in your browser and use advanced features like knowledge base.",
+ "enable": "Enable Now",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Build your personal knowledge base and easily start conversations with your assistant (coming soon)",
+ "title": "Support for knowledge base conversations"
+ },
+ "localFirst": {
+ "desc": "Chat data is stored entirely in the browser, keeping your data always under your control.",
+ "title": "Local first, privacy first"
+ },
+ "pglite": {
+ "desc": "Built on PGlite, natively supports AI Native advanced features (vector search)",
+ "title": "Next-generation client storage architecture"
+ }
+ },
+ "init": {
+ "desc": "Initializing the database, which may take 5 to 30 seconds depending on network conditions.",
+ "title": "Initializing PGlite Database"
+ },
+ "title": "Enable Client Database"
+ },
+ "ready": {
+ "button": "Use Now",
+ "desc": "Ready to use",
+ "title": "PGlite Database is Ready"
+ }
+ },
"close": "Close",
"contact": "Contact Us",
"copy": "Copy",
@@ -112,6 +176,7 @@
"en": "English",
"en-US": "English",
"es-ES": "Spanish",
+ "fa-IR": "Persian",
"fi-FI": "Finnish",
"fr-FR": "French",
"hi-IN": "Hindi",
@@ -153,6 +218,7 @@
"pinOff": "Unpin",
"privacy": "Privacy Policy",
"regenerate": "Regenerate",
+ "releaseNotes": "Version Details",
"rename": "Rename",
"reset": "Reset",
"retry": "Retry",
@@ -209,6 +275,7 @@
},
"temp": "Temporary",
"terms": "Terms of Service",
+ "update": "Update",
"updateAgent": "Update Assistant Information",
"upgradeVersion": {
"action": "Upgrade",
@@ -219,6 +286,7 @@
"anonymousNickName": "Anonymous User",
"billing": "Billing Management",
"cloud": "Launch {{name}}",
+ "community": "Community Edition",
"data": "Data Storage",
"defaultNickname": "Community User",
"discord": "Community Support",
@@ -228,8 +296,7 @@
"help": "Help Center",
"moveGuide": "The settings button has been moved here",
"plans": "Subscription Plans",
- "preview": "Preview",
- "profile": "Account Management",
+ "profile": "Account",
"setting": "Settings",
"usages": "Usage Statistics"
},
diff --git a/DigitalHumanWeb/locales/en-US/components.json b/DigitalHumanWeb/locales/en-US/components.json
index e257f55..802c637 100644
--- a/DigitalHumanWeb/locales/en-US/components.json
+++ b/DigitalHumanWeb/locales/en-US/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Batch Chunking",
"chunking": "Chunking",
"chunkingTooltip": "Split the file into multiple text chunks and embedding them for semantic search and file dialogue.",
+ "chunkingUnsupported": "This file does not support chunking.",
"confirmDelete": "You are about to delete this file. Once deleted, it cannot be recovered. Please confirm your action.",
"confirmDeleteMultiFiles": "You are about to delete the selected {{count}} files. Once deleted, they cannot be recovered. Please confirm your action.",
"confirmRemoveFromKnowledgeBase": "You are about to remove the selected {{count}} files from the knowledge base. They will still be viewable in all files. Please confirm your action.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Back"
},
+ "MaxTokenSlider": {
+ "unlimited": "Unlimited"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Custom model, by default, supports both function call and visual recognition. Please verify the availability of the above capabilities based on actual situations.",
"file": "This model supports file upload for reading and recognition.",
"functionCall": "This model supports function call.",
+ "reasoning": "This model supports deep thinking",
+ "search": "This model supports online search",
"tokens": "This model supports up to {{tokens}} tokens in a single session.",
"vision": "This model supports visual recognition."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "No enabled model. Please go to settings to enable.",
+ "emptyProvider": "No enabled providers. Please go to settings to enable one.",
+ "goToSettings": "Go to settings",
"provider": "Provider"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Due to browser security restrictions, you need to configure cross-origin settings for Ollama to function properly.",
+ "linux": {
+ "env": "Add `Environment` under the [Service] section, and set the OLLAMA_ORIGINS environment variable:",
+ "reboot": "Reload systemd and restart Ollama",
+ "systemd": "Edit the ollama service using systemd:"
+ },
+ "macos": "Please open the 'Terminal' application, paste the following command, and press Enter to run it.",
+ "reboot": "Please restart the Ollama service after the execution is complete.",
+ "title": "Configure Ollama for Cross-Origin Access",
+ "windows": "On Windows, click 'Control Panel' and go to edit system environment variables. Create a new environment variable named 'OLLAMA_ORIGINS' for your user account, with the value set to *, and click 'OK/Apply' to save."
+ },
+ "install": {
+ "description": "Please ensure that you have started Ollama. If you haven't downloaded Ollama, please visit the official website to <1>download1> it.",
+ "docker": "If you prefer to use Docker, Ollama also provides an official Docker image, which you can pull using the following command:",
+ "linux": {
+ "command": "Install using the following command:",
+ "manual": "Alternatively, you can refer to the <1>Linux Manual Installation Guide1> for a manual installation."
+ },
+ "title": "Install and Start the Ollama Application Locally",
+ "windowsTab": "Windows (Preview)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Deep Thinking...",
+ "thought": "Deeply Thought (in {{duration}} seconds)",
+ "thoughtWithDuration": "Deeply Thought"
}
}
diff --git a/DigitalHumanWeb/locales/en-US/discover.json b/DigitalHumanWeb/locales/en-US/discover.json
index 84e71d0..3d2a702 100644
--- a/DigitalHumanWeb/locales/en-US/discover.json
+++ b/DigitalHumanWeb/locales/en-US/discover.json
@@ -126,6 +126,10 @@
"title": "Topic Freshness"
},
"range": "Range",
+ "reasoning_effort": {
+ "desc": "This setting controls the intensity of reasoning the model applies before generating a response. Low intensity prioritizes response speed and saves tokens, while high intensity provides more comprehensive reasoning but consumes more tokens and slows down response time. The default value is medium, balancing reasoning accuracy with response speed.",
+ "title": "Reasoning Intensity"
+ },
"temperature": {
"desc": "This setting affects the diversity of the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. When set to 0, the model always gives the same response to a given input.",
"title": "Randomness"
diff --git a/DigitalHumanWeb/locales/en-US/error.json b/DigitalHumanWeb/locales/en-US/error.json
index 02c3ff3..2b0301b 100644
--- a/DigitalHumanWeb/locales/en-US/error.json
+++ b/DigitalHumanWeb/locales/en-US/error.json
@@ -12,8 +12,14 @@
"retry": "Reload",
"title": "Oops, something went wrong.."
},
- "fetchError": "Request Failed",
- "fetchErrorDetail": "Error Details",
+ "fetchError": {
+ "detail": "Error details",
+ "title": "Request failed"
+ },
+ "loginRequired": {
+ "desc": "You will be redirected to the login page shortly",
+ "title": "Please log in to use this feature"
+ },
"notFound": {
"backHome": "Back to Home",
"check": "Please check if your URL is correct.",
@@ -51,22 +57,34 @@
"431": "Sorry, the header fields of your request are too large for the server to process",
"451": "Sorry, the server refuses to provide this resource due to legal reasons",
"500": "Sorry, the server seems to be experiencing some difficulties and is temporarily unable to complete your request. Please try again later.",
+ "501": "Sorry, the server does not know how to handle this request yet. Please confirm that your operation is correct.",
"502": "Sorry, the server seems to be lost and is temporarily unable to provide service. Please try again later.",
"503": "Sorry, the server is currently unable to process your request, possibly due to overload or maintenance. Please try again later.",
"504": "Sorry, the server did not receive a response from the upstream server. Please try again later.",
+ "505": "Sorry, the server does not support the HTTP version you are using. Please update and try again.",
+ "506": "Sorry, there is a configuration issue with the server. Please contact the administrator for resolution.",
+ "507": "Sorry, the server has insufficient storage space to process your request. Please try again later.",
+ "509": "Sorry, the server's bandwidth has been exhausted. Please try again later.",
+ "510": "Sorry, the server does not support the requested extension. Please contact the administrator.",
+ "524": "Sorry, the server timed out while waiting for a response, possibly due to a slow reply. Please try again later.",
"AgentRuntimeError": "Lobe language model runtime execution error. Please troubleshoot or retry based on the following information.",
+ "ConnectionCheckFailed": "The request returned empty. Please check if the API proxy address does not end with `/v1`.",
+ "ExceededContextWindow": "The current request content exceeds the length that the model can handle. Please reduce the amount of content and try again.",
"FreePlanLimit": "You are currently a free user and cannot use this feature. Please upgrade to a paid plan to continue using it.",
+ "InsufficientQuota": "Sorry, the quota for this key has been reached. Please check your account balance or increase the key quota and try again.",
"InvalidAccessCode": "Invalid access code or empty. Please enter the correct access code or add a custom API Key.",
"InvalidBedrockCredentials": "Bedrock authentication failed. Please check the AccessKeyId/SecretAccessKey and retry.",
"InvalidClerkUser": "Sorry, you are not currently logged in. Please log in or register an account to continue.",
"InvalidGithubToken": "The GitHub Personal Access Token is incorrect or empty. Please check your GitHub Personal Access Token and try again.",
"InvalidOllamaArgs": "Invalid Ollama configuration, please check Ollama configuration and try again",
"InvalidProviderAPIKey": "{{provider}} API Key is incorrect or empty, please check your {{provider}} API Key and try again",
+ "InvalidVertexCredentials": "Vertex authentication failed. Please check your credentials and try again.",
"LocationNotSupportError": "We're sorry, your current location does not support this model service. This may be due to regional restrictions or the service not being available. Please confirm if the current location supports using this service, or try using a different location.",
+ "ModelNotFound": "Sorry, the requested model could not be found. It may not exist or you may not have the necessary access permissions. Please try again after changing the API Key or adjusting your access permissions.",
"NoOpenAIAPIKey": "OpenAI API Key is empty, please add a custom OpenAI API Key",
"OllamaBizError": "Error requesting Ollama service, please troubleshoot or retry based on the following information",
"OllamaServiceUnavailable": "Ollama service is unavailable. Please check if Ollama is running properly or if the cross-origin configuration of Ollama is set correctly.",
- "OpenAIBizError": "Error requesting OpenAI service, please troubleshoot or retry based on the following information",
+ "PermissionDenied": "Sorry, you do not have permission to access this service. Please check if your key has the necessary access rights.",
"PluginApiNotFound": "Sorry, the API does not exist in the plugin's manifest. Please check if your request method matches the plugin manifest API",
"PluginApiParamsError": "Sorry, the input parameter validation for the plugin request failed. Please check if the input parameters match the API description",
"PluginFailToTransformArguments": "Sorry, the plugin failed to parse the arguments. Please try regenerating the assistant message or switch to a more powerful AI model with Tools Calling capability and try again",
@@ -81,8 +99,11 @@
"PluginServerError": "Plugin server request returned an error. Please check your plugin manifest file, plugin configuration, or server implementation based on the error information below",
"PluginSettingsInvalid": "This plugin needs to be correctly configured before it can be used. Please check if your configuration is correct",
"ProviderBizError": "Error requesting {{provider}} service, please troubleshoot or retry based on the following information",
+ "QuotaLimitReached": "We apologize, but the current token usage or number of requests has reached the quota limit for this key. Please increase the quota for this key or try again later.",
"StreamChunkError": "Error parsing the message chunk of the streaming request. Please check if the current API interface complies with the standard specifications, or contact your API provider for assistance.",
- "SubscriptionPlanLimit": "Your subscription limit has been reached, and you cannot use this feature. Please upgrade to a higher plan or purchase a resource pack to continue using it.",
+ "SubscriptionKeyMismatch": "We apologize for the inconvenience. Due to a temporary system malfunction, your current subscription usage is inactive. Please click the button below to restore your subscription, or contact us via email for support.",
+ "SubscriptionPlanLimit": "Your subscription points have been exhausted, and you cannot use this feature. Please upgrade to a higher plan or configure a custom model API to continue using it.",
+ "SystemTimeNotMatchError": "Sorry, your system time does not match the server. Please check your system time and try again.",
"UnknownChatFetchError": "Sorry, an unknown request error occurred. Please check the information below or try again."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/en-US/metadata.json b/DigitalHumanWeb/locales/en-US/metadata.json
index ce08892..30df2d8 100644
--- a/DigitalHumanWeb/locales/en-US/metadata.json
+++ b/DigitalHumanWeb/locales/en-US/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Stay updated on the new features and improvements of {{appName}}",
+ "title": "Changelog"
+ },
"chat": {
"description": "{{appName}} brings you the best UI experience for ChatGPT, Claude, Gemini, and OLLaMA.",
"title": "{{appName}}: Your personal AI productivity tool for a smarter brain."
diff --git a/DigitalHumanWeb/locales/en-US/modelProvider.json b/DigitalHumanWeb/locales/en-US/modelProvider.json
index e48d8bf..b9064b7 100644
--- a/DigitalHumanWeb/locales/en-US/modelProvider.json
+++ b/DigitalHumanWeb/locales/en-US/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "The API version for Azure, following the YYYY-MM-DD format. Refer to the [latest version](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Fetch List",
+ "title": "Azure API Version"
+ },
+ "endpoint": {
+ "desc": "Find the Azure AI model inference endpoint from the Azure AI project overview",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AI Endpoint"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Find the API key from the Azure AI project overview",
+ "placeholder": "Azure Key",
+ "title": "Key"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Enter AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "Use Custom Bedrock Authentication Information"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Please enter Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Enter your Cloudflare account ID or custom API address",
+ "placeholder": "Cloudflare Account ID / custom API URL",
+ "title": "Cloudflare Account ID / API Address"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Please enter your API Key",
+ "title": "API Key"
+ },
+ "basicTitle": "Basic Information",
+ "configTitle": "Configuration Information",
+ "confirm": "Create",
+ "createSuccess": "Creation successful",
+ "description": {
+ "placeholder": "Provider description (optional)",
+ "title": "Provider Description"
+ },
+ "id": {
+ "desc": "Unique identifier for the service provider, which cannot be modified after creation",
+ "format": "Can only contain numbers, lowercase letters, hyphens (-), and underscores (_) ",
+ "placeholder": "Suggested all lowercase, e.g., openai, cannot be modified after creation",
+ "required": "Please enter the provider ID",
+ "title": "Provider ID"
+ },
+ "logo": {
+ "required": "Please upload a valid provider logo",
+ "title": "Provider Logo"
+ },
+ "name": {
+ "placeholder": "Please enter the display name of the provider",
+ "required": "Please enter the provider name",
+ "title": "Provider Name"
+ },
+ "proxyUrl": {
+ "required": "Please enter the proxy address",
+ "title": "Proxy URL"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Please select SDK type",
+ "title": "Request Format"
+ },
+ "title": "Create Custom AI Provider"
+ },
"github": {
"personalAccessToken": {
"desc": "Enter your GitHub PAT. Click [here](https://github.com/settings/tokens) to create one.",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Enter your HuggingFace Token, click [here](https://huggingface.co/settings/tokens) to create one",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace Token"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Disabled",
+ "enabled": "Enabled"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Add Custom Provider",
+ "all": "All",
+ "list": {
+ "disabled": "Disabled",
+ "enabled": "Enabled"
+ },
+ "notFound": "No search results found",
+ "searchProviders": "Search Providers...",
+ "sort": "Custom Sort"
+ },
"ollama": {
"checker": {
"desc": "Test if the proxy address is correctly filled in",
@@ -71,37 +165,13 @@
"download": {
"desc": "Ollama is downloading the model. Please try not to close this page. The download will resume from where it left off if interrupted.",
"remainingTime": "Remaining Time",
- "speed": "Download Speed",
+ "speed": "Speed",
"title": "Downloading model {{model}}"
},
"endpoint": {
- "desc": "Enter the Ollama interface proxy address, leave blank if not specified locally",
+ "desc": "Must include http(s)://; can be left blank if not specified locally.",
"title": "Interface proxy address"
},
- "setup": {
- "cors": {
- "description": "Due to browser security restrictions, you need to configure cross-origin settings for Ollama to function properly.",
- "linux": {
- "env": "Add `Environment` under [Service] section, and set the OLLAMA_ORIGINS environment variable:",
- "reboot": "Reload systemd and restart Ollama.",
- "systemd": "Invoke systemd to edit the ollama service:"
- },
- "macos": "Open the 'Terminal' application, paste the following command, and press Enter to run it.",
- "reboot": "Please restart the Ollama service after completion.",
- "title": "Configure Ollama for Cross-Origin Access",
- "windows": "On Windows, go to 'Control Panel' and edit system environment variables. Create a new environment variable named 'OLLAMA_ORIGINS' for your user account, set the value to '*', and click 'OK/Apply' to save."
- },
- "install": {
- "description": "Please make sure you have enabled Ollama. If you haven't downloaded Ollama yet, please visit the official website <1>to download1>.",
- "docker": "If you prefer using Docker, Ollama also provides an official Docker image. You can pull it using the following command:",
- "linux": {
- "command": "Install using the following command:",
- "manual": "Alternatively, you can refer to the <1>Linux Manual Installation Guide1> for manual installation."
- },
- "title": "Install and Start Ollama Locally",
- "windowsTab": "Windows (Preview)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Cancel Download",
@@ -112,6 +182,156 @@
"title": "Download specified Ollama model"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "Your key and proxy URL will be encrypted using <1>AES-GCM1> encryption algorithm",
+ "apiKey": {
+ "desc": "Please enter your {{name}} API Key",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "Must include http(s)://",
+ "invalid": "Please enter a valid URL",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API Proxy URL"
+ },
+ "checker": {
+ "button": "Check",
+ "desc": "Test if the API Key and proxy URL are correctly filled",
+ "pass": "Check passed",
+ "title": "Connectivity Check"
+ },
+ "fetchOnClient": {
+ "desc": "Client request mode will initiate session requests directly from the browser, which can improve response speed",
+ "title": "Use Client Request Mode"
+ },
+ "helpDoc": "Configuration Guide",
+ "waitingForMore": "More models are currently <1>planned for integration1>, please stay tuned"
+ },
+ "createNew": {
+ "title": "Create Custom AI Model"
+ },
+ "item": {
+ "config": "Configure Model",
+ "customModelCards": {
+ "addNew": "Create and add {{id}} model",
+ "confirmDelete": "You are about to delete this custom model. Once deleted, it cannot be recovered. Please proceed with caution."
+ },
+ "delete": {
+ "confirm": "Are you sure you want to delete model {{displayName}}?",
+ "success": "Deletion successful",
+ "title": "Delete Model"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Field used for actual requests in Azure OpenAI",
+ "placeholder": "Please enter the model deployment name in Azure",
+ "title": "Model Deployment Name"
+ },
+ "deployName": {
+ "extra": "This field will be used as the model ID when sending requests",
+ "placeholder": "Please enter the actual deployment name or ID of the model",
+ "title": "Model Deployment Name"
+ },
+ "displayName": {
+ "placeholder": "Please enter the display name of the model, e.g., ChatGPT, GPT-4, etc.",
+ "title": "Model Display Name"
+ },
+ "files": {
+ "extra": "The current file upload implementation is just a hack solution, limited to self-experimentation. Please wait for complete file upload capabilities in future implementations.",
+ "title": "File Upload Support"
+ },
+ "functionCall": {
+ "extra": "This configuration will only enable the model's ability to use tools, allowing for the addition of tool-type plugins. However, whether the model can truly use the tools depends entirely on the model itself; please test for usability on your own.",
+ "title": "Support for Tool Usage"
+ },
+ "id": {
+ "extra": "This cannot be modified after creation and will be used as the model ID when calling AI",
+ "placeholder": "Please enter the model ID, e.g., gpt-4o or claude-3.5-sonnet",
+ "title": "Model ID"
+ },
+ "modalTitle": "Custom Model Configuration",
+ "reasoning": {
+ "extra": "This configuration will enable the model's deep thinking capabilities, and the specific effects depend entirely on the model itself. Please test whether this model has usable deep thinking abilities.",
+ "title": "Support Deep Thinking"
+ },
+ "tokens": {
+ "extra": "Set the maximum number of tokens supported by the model",
+ "title": "Maximum Context Window",
+ "unlimited": "Unlimited"
+ },
+ "vision": {
+ "extra": "This configuration will only enable image upload capabilities in the application. Whether recognition is supported depends entirely on the model itself. Please test the visual recognition capabilities of the model yourself.",
+ "title": "Support Vision"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/Image",
+ "inputCharts": "${{amount}}/M Characters",
+ "inputMinutes": "${{amount}}/Minutes",
+ "inputTokens": "Input ${{amount}}/M",
+ "outputTokens": "Output ${{amount}}/M"
+ },
+ "releasedAt": "Released at {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Add Model",
+ "disabled": "Disabled",
+ "disabledActions": {
+ "showMore": "Show All"
+ },
+ "empty": {
+ "desc": "Please create a custom model or pull a model to get started.",
+ "title": "No available models"
+ },
+ "enabled": "Enabled",
+ "enabledActions": {
+ "disableAll": "Disable All",
+ "enableAll": "Enable All",
+ "sort": "Custom Model Sorting"
+ },
+ "enabledEmpty": "No enabled models available. Please enable your preferred models from the list below~",
+ "fetcher": {
+ "clear": "Clear fetched models",
+ "fetch": "Fetch models",
+ "fetching": "Fetching model list...",
+ "latestTime": "Last updated: {{time}}",
+ "noLatestTime": "Model list not yet fetched"
+ },
+ "resetAll": {
+ "conform": "Are you sure you want to reset all modifications to the current model? After resetting, the current model list will return to its default state.",
+ "success": "Reset successful",
+ "title": "Reset All Modifications"
+ },
+ "search": "Search Models...",
+ "searchResult": "{{count}} models found",
+ "title": "Model List",
+ "total": "{{count}} models available"
+ },
+ "searchNotFound": "No search results found"
+ },
+ "sortModal": {
+ "success": "Sort update successful",
+ "title": "Custom Order",
+ "update": "Update"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "You are about to delete this AI provider. Once deleted, it cannot be retrieved. Are you sure you want to delete?",
+ "deleteSuccess": "Deletion successful",
+ "tooltip": "Update provider basic configuration",
+ "updateSuccess": "Update successful"
+ },
+ "updateCustomAiProvider": {
+ "title": "Update Custom AI Provider Configuration"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Enter your Vertex AI Keys",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI Keys"
+ }
+ },
"zeroone": {
"title": "01.AI Zero One Everything"
},
diff --git a/DigitalHumanWeb/locales/en-US/models.json b/DigitalHumanWeb/locales/en-US/models.json
index 46161be..94c00ac 100644
--- a/DigitalHumanWeb/locales/en-US/models.json
+++ b/DigitalHumanWeb/locales/en-US/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B delivers superior performance in industry applications with a wealth of training samples."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat is a variant of the Yi-1.5 series, belonging to the open-source chat model. Yi-1.5 is an upgraded version of Yi, continuously pre-trained on 500B high-quality corpora and fine-tuned on over 3M diverse samples. Compared to Yi, Yi-1.5 demonstrates stronger capabilities in coding, mathematics, reasoning, and instruction following, while maintaining excellent language understanding, common sense reasoning, and reading comprehension abilities. The model is available in context length versions of 4K, 16K, and 32K, with a total pre-training volume reaching 3.6T tokens."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B supports 16K tokens, providing efficient and smooth language generation capabilities."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Everything, the latest open-source fine-tuned model with 34 billion parameters, supports various dialogue scenarios with high-quality training data aligned with human preferences."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Everything, the latest open-source fine-tuned model with 9 billion parameters, supports various dialogue scenarios with high-quality training data aligned with human preferences."
+ },
"360gpt-pro": {
"description": "360GPT Pro, as an important member of the 360 AI model series, meets diverse natural language application scenarios with efficient text processing capabilities, supporting long text understanding and multi-turn dialogue."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K emphasizes semantic safety and responsibility, designed specifically for applications with high content safety requirements, ensuring accuracy and robustness in user experience."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 builds a chain of thought using tree search and incorporates a reflection mechanism, trained with reinforcement learning, enabling the model to self-reflect and correct errors."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro is an advanced natural language processing model launched by 360, featuring exceptional text generation and understanding capabilities, particularly excelling in generation and creative tasks, capable of handling complex language transformations and role-playing tasks."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 uses tree search to build a chain of thought and introduces a reflection mechanism, utilizing reinforcement learning for training, enabling the model to possess self-reflection and error-correction capabilities."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra is the most powerful version in the Spark large model series, enhancing text content understanding and summarization capabilities while upgrading online search links. It is a comprehensive solution for improving office productivity and accurately responding to demands, leading the industry as an intelligent product."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "The model is the best in the country, surpassing mainstream foreign models in Chinese tasks such as knowledge encyclopedias, long texts, and creative generation. It also boasts industry-leading multimodal capabilities, excelling in multiple authoritative evaluation benchmarks."
},
+ "Baichuan4-Air": {
+ "description": "The leading model in the country, surpassing mainstream foreign models in Chinese tasks such as knowledge encyclopedias, long texts, and creative generation. It also possesses industry-leading multimodal capabilities, excelling in multiple authoritative evaluation benchmarks."
+ },
+ "Baichuan4-Turbo": {
+ "description": "The leading model in the country, surpassing mainstream foreign models in Chinese tasks such as knowledge encyclopedias, long texts, and creative generation. It also possesses industry-leading multimodal capabilities, excelling in multiple authoritative evaluation benchmarks."
+ },
+ "DeepSeek-R1": {
+ "description": "A state-of-the-art efficient LLM, skilled in reasoning, mathematics, and programming."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1— the larger and smarter model in the DeepSeek suite— distilled into the Llama 70B architecture. Based on benchmark testing and human evaluation, this model is smarter than the original Llama 70B, particularly excelling in tasks requiring mathematical and factual accuracy."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "The DeepSeek-R1 distillation model based on Qwen2.5-Math-1.5B optimizes inference performance through reinforcement learning and cold-start data, refreshing the benchmark for open-source models across multiple tasks."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "The DeepSeek-R1 distillation model based on Qwen2.5-14B optimizes inference performance through reinforcement learning and cold-start data, refreshing the benchmark for open-source models across multiple tasks."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "The DeepSeek-R1 series optimizes inference performance through reinforcement learning and cold-start data, refreshing the benchmark for open-source models across multiple tasks, surpassing the level of OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "The DeepSeek-R1 distillation model based on Qwen2.5-Math-7B optimizes inference performance through reinforcement learning and cold-start data, refreshing the benchmark for open-source models across multiple tasks."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro is a newly upgraded multimodal large model that supports image recognition at any resolution and extreme aspect ratios, enhancing visual reasoning, document recognition, detail understanding, and instruction-following capabilities."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite provides extreme response speed and better cost-effectiveness, offering flexible options for various customer scenarios. It supports inference and fine-tuning with a 128k context window."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite offers extreme response speed and better cost-effectiveness, providing flexible options for various customer scenarios. It supports inference and fine-tuning with a 32k context window."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite boasts extreme response speed and better cost-effectiveness, providing flexible options for various customer scenarios. It supports inference and fine-tuning with a 4k context window."
+ },
+ "Doubao-pro-128k": {
+ "description": "The best-performing primary model designed to handle complex tasks, achieving strong performance in scenarios such as reference Q&A, summarization, creative writing, text classification, and role-playing. It supports inference and fine-tuning with a 128k context window."
+ },
+ "Doubao-pro-256k": {
+ "description": "The best-performing flagship model, suitable for handling complex tasks, with excellent results in reference Q&A, summarization, creative writing, text classification, role-playing, and more. It supports reasoning and fine-tuning with a 256k context window."
+ },
+ "Doubao-pro-32k": {
+ "description": "The best-performing primary model suited for complex tasks, showing great results in reference Q&A, summarization, creative writing, text classification, and role-playing. It supports inference and fine-tuning with a 32k context window."
+ },
+ "Doubao-pro-4k": {
+ "description": "The best-performing primary model suitable for handling complex tasks, demonstrating excellent performance in scenarios such as reference Q&A, summarization, creative writing, text classification, and role-playing. It supports inference and fine-tuning with a 4k context window."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "The Doubao-vision model is a multimodal large model launched by Doubao, featuring powerful image understanding and reasoning capabilities, as well as precise instruction comprehension. The model has demonstrated strong performance in image-text information extraction and image-based reasoning tasks, making it applicable to more complex and broader visual question-answering tasks."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "The Doubao-vision model is a multimodal large model launched by Doubao, featuring powerful image understanding and reasoning capabilities, as well as precise instruction comprehension. The model has demonstrated strong performance in image-text information extraction and image-based reasoning tasks, making it applicable to more complex and broader visual question-answering tasks."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Baidu's self-developed flagship large-scale language model, covering a vast amount of Chinese and English corpus. It possesses strong general capabilities, meeting the requirements for most dialogue Q&A, creative generation, and plugin application scenarios; it supports automatic integration with Baidu's search plugin to ensure the timeliness of Q&A information."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Baidu's self-developed flagship large-scale language model, covering a vast amount of Chinese and English corpus. It possesses strong general capabilities, meeting the requirements for most dialogue Q&A, creative generation, and plugin application scenarios; it supports automatic integration with Baidu's search plugin to ensure the timeliness of Q&A information."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Baidu's self-developed flagship large-scale language model, covering a vast amount of Chinese and English corpus. It possesses strong general capabilities, meeting the requirements for most dialogue Q&A, creative generation, and plugin application scenarios; it supports automatic integration with Baidu's search plugin to ensure the timeliness of Q&A information."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Baidu's self-developed flagship ultra-large-scale language model, which has achieved a comprehensive upgrade in model capabilities compared to ERNIE 3.5, widely applicable to complex task scenarios across various fields; supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Baidu's self-developed flagship ultra-large-scale language model, which has achieved a comprehensive upgrade in model capabilities compared to ERNIE 3.5, widely applicable to complex task scenarios across various fields; supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Baidu's self-developed flagship ultra-large-scale language model, demonstrating excellent overall performance, suitable for complex task scenarios across various fields; supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information. It offers better performance compared to ERNIE 4.0."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Baidu's self-developed flagship ultra-large-scale language model, demonstrating excellent overall performance, widely applicable to complex task scenarios across various fields; supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information. It outperforms ERNIE 4.0 in performance."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Baidu's self-developed vertical scene large language model, suitable for applications such as game NPCs, customer service dialogues, and role-playing conversations, featuring more distinct and consistent character styles, stronger adherence to instructions, and superior inference performance."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Baidu's self-developed lightweight large language model, balancing excellent model performance with inference efficiency, offering better results than ERNIE Lite, suitable for inference on low-power AI acceleration cards."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Baidu's latest self-developed high-performance large language model released in 2024, with outstanding general capabilities, suitable as a base model for fine-tuning, effectively addressing specific scenario issues while also exhibiting excellent inference performance."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Baidu's latest self-developed high-performance large language model released in 2024, with outstanding general capabilities, providing better results than ERNIE Speed, suitable as a base model for fine-tuning, effectively addressing specific scenario issues while also exhibiting excellent inference performance."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) is an innovative model suitable for multi-domain applications and complex tasks."
},
- "Max-32k": {
- "description": "Spark Max 32K is equipped with enhanced context processing capabilities, stronger context understanding, and logical reasoning abilities, supporting text input of up to 32K tokens, suitable for scenarios such as long document reading and private knowledge Q&A."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B is a powerful visual language model that supports multimodal processing of images and text, capable of accurately recognizing image content and generating relevant descriptions or answers."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B is a powerful visual language model that supports multimodal processing of images and text, capable of accurately recognizing image content and generating relevant descriptions or answers."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Exhibits outstanding image reasoning capabilities on high-resolution images, suitable for visual understanding applications."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Advanced image reasoning capabilities suitable for visual understanding agent applications."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct is one of the latest large language models released by Alibaba Cloud. This 72B model shows significant improvements in coding and mathematics. It also provides multilingual support, covering over 29 languages, including Chinese and English. The model has made notable advancements in instruction following, understanding structured data, and generating structured outputs, especially JSON."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct is one of the latest large language models released by Alibaba Cloud. This 7B model shows significant improvements in coding and mathematics. It also provides multilingual support, covering over 29 languages, including Chinese and English. The model has made notable advancements in instruction following, understanding structured data, and generating structured outputs, especially JSON."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Llama 3.1 instruction-tuned text model optimized for multilingual dialogue use cases, performing excellently on common industry benchmarks among many available open-source and closed chat models."
+ },
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Llama 3.1 instruction-tuned text model optimized for multilingual dialogue use cases, performing excellently on common industry benchmarks among many available open-source and closed chat models."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO is a highly flexible multi-model fusion designed to provide an exceptional creative experience."
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Llama 3.1 instruction-tuned text model optimized for multilingual dialogue use cases, performing excellently on common industry benchmarks among many available open-source and closed chat models."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "An advanced cutting-edge small language model with language understanding, excellent reasoning capabilities, and text generation abilities."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "An advanced cutting-edge small language model with language understanding, excellent reasoning capabilities, and text generation abilities."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 is the most advanced multilingual open-source large language model in the Llama series, offering performance comparable to a 405B model at a very low cost. Based on the Transformer architecture, it enhances usability and safety through supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Its instruction-tuned version is optimized for multilingual dialogue and outperforms many open-source and closed chat models on various industry benchmarks. Knowledge cutoff date is December 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "In the MiniMax-01 series of models, we have made bold innovations: for the first time, we have implemented a linear attention mechanism on a large scale, making the traditional Transformer architecture no longer the only option. This model has a parameter count of up to 456 billion, with a single activation of 45.9 billion. Its overall performance rivals that of top overseas models while efficiently handling the world's longest context of 4 million tokens, which is 32 times that of GPT-4o and 20 times that of Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) is a high-precision instruction model suitable for complex computations."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) provides optimized language output and diverse application possibilities."
- },
- "Phi-3-5-mini-instruct": {
- "description": "An update of the Phi-3-mini model."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 demonstrates exceptional performance across various visual language tasks, including document and chart understanding, scene text understanding, OCR, and solving scientific and mathematical problems."
},
"Phi-3-medium-128k-instruct": {
"description": "The same Phi-3-medium model, but with a larger context size for RAG or few-shot prompting."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "A 7B parameter model that provides better quality than Phi-3-mini, focusing on high-quality, reasoning-dense data."
},
- "Pro-128k": {
- "description": "Spark Pro-128K is configured with ultra-large context processing capabilities, able to handle up to 128K of contextual information, particularly suitable for long texts requiring comprehensive analysis and long-term logical connections, providing smooth and consistent logic and diverse citation support in complex text communication."
+ "Phi-3.5-mini-instruct": {
+ "description": "An updated version of the Phi-3-mini model."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "An updated version of the Phi-3-vision model."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 demonstrates exceptional performance across various visual language tasks, including document and chart understanding, scene text understanding, OCR, and solving scientific and mathematical problems."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct is an instruction-tuned large language model in the Qwen2 series, with a parameter size of 1.5B. This model is based on the Transformer architecture and employs techniques such as the SwiGLU activation function, attention QKV bias, and group query attention. It excels in language understanding, generation, multilingual capabilities, coding, mathematics, and reasoning across multiple benchmark tests, surpassing most open-source models. Compared to Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct shows significant performance improvements in tests such as MMLU, HumanEval, GSM8K, C-Eval, and IFEval, despite having slightly fewer parameters."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct is an instruction-tuned large language model in the Qwen2 series, with a parameter size of 7B. This model is based on the Transformer architecture and employs techniques such as the SwiGLU activation function, attention QKV bias, and group query attention. It can handle large-scale inputs. The model excels in language understanding, generation, multilingual capabilities, coding, mathematics, and reasoning across multiple benchmark tests, surpassing most open-source models and demonstrating competitive performance comparable to proprietary models in certain tasks. Qwen2-7B-Instruct outperforms Qwen1.5-7B-Chat in multiple evaluations, showing significant performance improvements."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL is the latest iteration of the Qwen-VL model, achieving state-of-the-art performance in visual understanding benchmarks."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct is one of the latest large language models released by Alibaba Cloud. This 7B model shows significant improvements in coding and mathematics. It also provides multilingual support, covering over 29 languages, including Chinese and English. The model has made notable advancements in instruction following, understanding structured data, and generating structured outputs, especially JSON."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct is the latest version in Alibaba Cloud's series of code-specific large language models. This model significantly enhances code generation, reasoning, and repair capabilities based on Qwen2.5, trained on 55 trillion tokens. It not only improves coding abilities but also maintains advantages in mathematics and general capabilities, providing a more comprehensive foundation for practical applications such as code agents."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat is the open-source version of the GLM-4 series pre-trained models launched by Zhipu AI. This model excels in semantics, mathematics, reasoning, code, and knowledge. In addition to supporting multi-turn dialogues, GLM-4-9B-Chat also features advanced capabilities such as web browsing, code execution, custom tool invocation (Function Call), and long-text reasoning. The model supports 26 languages, including Chinese, English, Japanese, Korean, and German. In multiple benchmark tests, GLM-4-9B-Chat has demonstrated excellent performance, such as in AlignBench-v2, MT-Bench, MMLU, and C-Eval. The model supports a maximum context length of 128K, making it suitable for academic research and commercial applications."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 is a reinforcement learning (RL) driven inference model that addresses issues of repetitiveness and readability in models. Prior to RL, DeepSeek-R1 introduced cold start data to further optimize inference performance. It performs comparably to OpenAI-o1 in mathematical, coding, and reasoning tasks, and enhances overall effectiveness through carefully designed training methods."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 is a mixed expert (MoE) language model with 671 billion parameters, utilizing multi-head latent attention (MLA) and the DeepSeekMoE architecture, combined with a load balancing strategy without auxiliary loss to optimize inference and training efficiency. Pre-trained on 14.8 trillion high-quality tokens and fine-tuned with supervision and reinforcement learning, DeepSeek-V3 outperforms other open-source models and approaches leading closed-source models."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma is one of Google's lightweight, state-of-the-art open model series. It is a large language model with a decoder-only architecture, supporting English, and providing open weights, pre-trained variants, and instruction-tuned variants. The Gemma model is suitable for various text generation tasks, including question answering, summarization, and reasoning. This 9B model is trained on 80 trillion tokens. Its relatively small size allows it to be deployed in resource-constrained environments, such as laptops, desktops, or your own cloud infrastructure, making cutting-edge AI models more accessible and fostering innovation."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 is a family of multilingual large language models developed by Meta, including pre-trained and instruction-tuned variants with parameter sizes of 8B, 70B, and 405B. This 8B instruction-tuned model is optimized for multilingual dialogue scenarios and performs excellently in multiple industry benchmark tests. The model is trained using over 150 trillion tokens of public data and employs techniques such as supervised fine-tuning and human feedback reinforcement learning to enhance the model's usefulness and safety. Llama 3.1 supports text generation and code generation, with a knowledge cutoff date of December 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview is an innovative natural language processing model capable of efficiently handling complex dialogue generation and context understanding tasks."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview is a research-oriented model developed by the Qwen team, focusing on visual reasoning capabilities, with unique advantages in understanding complex scenes and solving visually related mathematical problems."
+ },
+ "Qwen/QwQ-32B": {
+ "description": "QwQ is the inference model of the Qwen series. Compared to traditional instruction-tuned models, QwQ possesses reasoning and cognitive abilities, achieving significantly enhanced performance in downstream tasks, especially in solving difficult problems. QwQ-32B is a medium-sized inference model that competes effectively against state-of-the-art inference models (such as DeepSeek-R1 and o1-mini). This model employs technologies such as RoPE, SwiGLU, RMSNorm, and Attention QKV bias, featuring a 64-layer network structure and 40 Q attention heads (with 8 KV heads in the GQA architecture)."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "As a beta version of Qwen2, Qwen1.5 utilizes large-scale data to achieve more precise conversational capabilities."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview is Qwen's latest experimental research model, focusing on enhancing AI reasoning capabilities. By exploring complex mechanisms such as language mixing and recursive reasoning, its main advantages include strong analytical reasoning, mathematical, and programming abilities. However, it also faces challenges such as language switching issues, reasoning loops, safety considerations, and differences in other capabilities."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) provides quick responses and natural conversational abilities, suitable for multilingual environments."
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct is an instruction-tuned large language model in the Qwen2 series, with a parameter size of 1.5B. This model is based on the Transformer architecture and employs techniques such as the SwiGLU activation function, attention QKV bias, and group query attention. It excels in language understanding, generation, multilingual capabilities, coding, mathematics, and reasoning across multiple benchmark tests, surpassing most open-source models. Compared to Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct shows significant performance improvements in tests such as MMLU, HumanEval, GSM8K, C-Eval, and IFEval, despite having slightly fewer parameters."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 is an advanced general-purpose language model that supports various types of instructions."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct is an instruction-tuned large language model in the Qwen2 series, with a parameter size of 72B. This model is based on the Transformer architecture and employs techniques such as the SwiGLU activation function, attention QKV bias, and group query attention. It can handle large-scale inputs. The model excels in language understanding, generation, multilingual capabilities, coding, mathematics, and reasoning across multiple benchmark tests, surpassing most open-source models and demonstrating competitive performance comparable to proprietary models in certain tasks."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL is the latest iteration of the Qwen-VL model, achieving state-of-the-art performance in visual understanding benchmarks."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 is a brand new series of large language models designed to optimize the handling of instruction-based tasks."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 is a brand new series of large language models designed to optimize the handling of instruction-based tasks."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 is a brand new series of large language models with enhanced understanding and generation capabilities."
+ "description": "A large language model developed by the Alibaba Cloud Tongyi Qianwen team"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 is a new large language model series with enhanced understanding and generation capabilities."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 is a new large language model series designed to optimize instruction-based task processing."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 is a brand new series of large language models designed to optimize the handling of instruction-based tasks."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 is a new large language model series designed to optimize instruction-based task processing."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder focuses on code writing."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math focuses on problem-solving in the field of mathematics, providing expert solutions for challenging problems."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct is the latest version in Alibaba Cloud's series of code-specific large language models. This model significantly enhances code generation, reasoning, and repair capabilities based on Qwen2.5, trained on 55 trillion tokens. It not only improves coding abilities but also maintains advantages in mathematics and general capabilities, providing a more comprehensive foundation for practical applications such as code agents."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 is the latest series of the Qwen model, supporting 128k context. Compared to the current best open-source models, Qwen2-72B significantly surpasses leading models in natural language understanding, knowledge, coding, mathematics, and multilingual capabilities."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 is the latest series of the Qwen model, capable of outperforming optimal open-source models of similar size and even larger models. Qwen2 7B has achieved significant advantages in multiple evaluations, especially in coding and Chinese comprehension."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B is a powerful visual language model that supports multimodal processing of images and text, capable of accurately recognizing image content and generating relevant descriptions or answers."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct is a large language model with 14 billion parameters, delivering excellent performance, optimized for Chinese and multilingual scenarios, and supporting applications such as intelligent Q&A and content generation."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct is a large language model with 32 billion parameters, offering balanced performance, optimized for Chinese and multilingual scenarios, and supporting applications such as intelligent Q&A and content generation."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct supports 16k context and generates long texts exceeding 8K. It enables seamless interaction with external systems through function calls, greatly enhancing flexibility and scalability. The model's knowledge has significantly increased, and its coding and mathematical abilities have been greatly improved, with multilingual support for over 29 languages."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct is a large language model with 7 billion parameters, supporting function calls and seamless interaction with external systems, greatly enhancing flexibility and scalability. It is optimized for Chinese and multilingual scenarios, supporting applications such as intelligent Q&A and content generation."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct is a large-scale pre-trained programming instruction model with strong code understanding and generation capabilities, efficiently handling various programming tasks, particularly suited for intelligent code writing, automated script generation, and programming problem-solving."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct is a large language model specifically designed for code generation, code understanding, and efficient development scenarios, featuring an industry-leading 32 billion parameters to meet diverse programming needs."
+ },
+ "SenseChat": {
+ "description": "Basic version model (V4) with a context length of 4K, featuring strong general capabilities."
+ },
+ "SenseChat-128K": {
+ "description": "Basic version model (V4) with a context length of 128K, excelling in long text comprehension and generation tasks."
+ },
+ "SenseChat-32K": {
+ "description": "Basic version model (V4) with a context length of 32K, flexibly applicable to various scenarios."
+ },
+ "SenseChat-5": {
+ "description": "The latest version model (V5.5) with a context length of 128K shows significant improvements in mathematical reasoning, English conversation, instruction following, and long text comprehension, comparable to GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "This is the latest version based on V5.5, showing significant improvements in basic capabilities in Chinese and English, chatting, scientific knowledge, humanities knowledge, writing, mathematical logic, and word count control compared to the previous version."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "With a context length of 32K, it surpasses GPT-4 in Cantonese conversation comprehension and is competitive with GPT-4 Turbo in knowledge, reasoning, mathematics, and code writing across multiple domains."
+ },
+ "SenseChat-Character": {
+ "description": "Standard version model with an 8K context length and high response speed."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Advanced version model with a context length of 32K, offering comprehensive capability enhancements and supporting both Chinese and English conversations."
+ },
+ "SenseChat-Turbo": {
+ "description": "Suitable for fast question answering and model fine-tuning scenarios."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "This is the latest lightweight version model, achieving over 90% of the full model's capabilities while significantly reducing inference costs."
+ },
+ "SenseChat-Vision": {
+ "description": "The latest version model (V5.5) supports multi-image input and fully optimizes the model's basic capabilities, achieving significant improvements in object attribute recognition, spatial relationships, action event recognition, scene understanding, emotion recognition, logical reasoning, and text understanding and generation."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Skylark 2nd generation model, Skylark2-lite model is characterized by high response speed, suitable for high real-time requirements, cost-sensitive scenarios, and situations where model accuracy is less critical, with a context window length of 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Skylark 2nd generation model, Skylark2-pro version has high model accuracy, suitable for more complex text generation scenarios such as professional field copy generation, novel writing, and high-quality translation, with a context window length of 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Skylark 2nd generation model, Skylark2-pro model has high model accuracy, suitable for more complex text generation scenarios such as professional field copy generation, novel writing, and high-quality translation, with a context window length of 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Skylark 2nd generation model, Skylark2-pro-character has excellent role-playing and chat capabilities, adept at engaging in conversations with users based on their prompt requests, showcasing distinct character styles and flowing dialogue, making it well-suited for building chatbots, virtual assistants, and online customer service, with high response speed."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Skylark 2nd generation model, Skylark2-pro-turbo-8k provides faster inference at a lower cost, with a context window length of 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B is an open-source model from the ChatGLM series, developed by Zhipu AI. This model retains the excellent features of its predecessor, such as smooth dialogue and low deployment barriers, while introducing new features. It utilizes more diverse training data, more extensive training steps, and more reasonable training strategies, performing exceptionally well among pre-trained models under 10B. ChatGLM3-6B supports multi-turn dialogues, tool invocation, code execution, and complex scenarios such as Agent tasks. In addition to the dialogue model, the foundational model ChatGLM-6B-Base and the long-text dialogue model ChatGLM3-6B-32K are also open-sourced. The model is fully open for academic research and allows free commercial use after registration."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B is an open-source version that provides an optimized conversational experience for chat applications."
},
+ "TeleAI/TeleChat2": {
+ "description": "The TeleChat2 large model is a generative semantic model independently developed from scratch by China Telecom, supporting functions such as encyclopedia Q&A, code generation, and long text generation, providing users with conversational consulting services. It can interact with users, answer questions, assist in creation, and efficiently help users obtain information, knowledge, and inspiration. The model performs well in areas such as hallucination issues, long text generation, and logical understanding."
+ },
+ "TeleAI/TeleMM": {
+ "description": "The TeleMM multimodal large model is a multimodal understanding model independently developed by China Telecom, capable of processing various modal inputs such as text and images, supporting functions like image understanding and chart analysis, providing users with cross-modal understanding services. The model can interact with users in a multimodal manner, accurately understand input content, answer questions, assist in creation, and efficiently provide multimodal information and inspiration support. It excels in fine-grained perception, logical reasoning, and other multimodal tasks."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct is one of the latest large language models released by Alibaba Cloud. This 72B model shows significant improvements in coding and mathematics. It also provides multilingual support, covering over 29 languages, including Chinese and English. The model has made notable advancements in instruction following, understanding structured data, and generating structured outputs, especially JSON."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B significantly enhances mathematical logic and coding abilities by incrementally training on 500 billion high-quality tokens while maintaining the excellent general language capabilities of the original series."
+ },
"abab5.5-chat": {
"description": "Targeted at productivity scenarios, supporting complex task processing and efficient text generation, suitable for professional applications."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Optimized for Chinese persona dialogue scenarios, providing smooth dialogue generation that aligns with Chinese expression habits."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworks open-source function-calling model provides excellent instruction execution capabilities and customizable features."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Fireworks' latest Firefunction-v2 is a high-performance function-calling model developed based on Llama-3, optimized for function calls, dialogues, and instruction following."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b is a visual language model that can accept both image and text inputs, trained on high-quality data, suitable for multimodal tasks."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 is a state-of-the-art large language model optimized through reinforcement learning and cold-start data, excelling in reasoning, mathematics, and programming performance."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B instruction model, based on previous Google technology, suitable for answering questions, summarizing, and reasoning across various text generation tasks."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "A powerful Mixture-of-Experts (MoE) language model provided by Deepseek, with a total parameter count of 671B, activating 37B parameters per token."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Llama 3 70B instruction model, optimized for multilingual dialogues and natural language understanding, outperforming most competitive models."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B instruction model (HF version), aligned with official implementation results, suitable for high-quality instruction following tasks."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Llama 3 8B instruction model, optimized for dialogues and multilingual tasks, delivering outstanding and efficient performance."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Llama 3.1 8B instruction model, optimized for multilingual dialogues, capable of surpassing most open-source and closed-source models on common industry benchmarks."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Meta's 11B parameter instruction-tuned image reasoning model. This model is optimized for visual recognition, image reasoning, image description, and answering general questions about images. It understands visual data like charts and graphs, generating text descriptions of image details to bridge the gap between vision and language."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "The Llama 3.2 3B instruction model is a lightweight multilingual model introduced by Meta. This model aims to enhance efficiency, providing significant improvements in latency and cost compared to larger models. Sample use cases include querying, prompt rewriting, and writing assistance."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Meta's 90B parameter instruction-tuned image reasoning model. This model is optimized for visual recognition, image reasoning, image description, and answering general questions about images. It understands visual data like charts and graphs, generating text descriptions of image details to bridge the gap between vision and language."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct is the December update of Llama 3.1 70B. This model builds upon Llama 3.1 70B (released in July 2024) with enhancements in tool invocation, multilingual text support, mathematics, and programming capabilities. It achieves industry-leading performance in reasoning, mathematics, and instruction following, providing similar performance to 3.1 405B while offering significant advantages in speed and cost."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "A 24B parameter model that possesses state-of-the-art capabilities comparable to larger models."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B instruction model, featuring large-scale parameters and a multi-expert architecture, fully supporting efficient processing of complex tasks."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B instruction model, with a multi-expert architecture providing efficient instruction following and execution."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B instruction model (HF version), performance consistent with official implementation, suitable for various efficient task scenarios."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "MythoMax L2 13B model, combining novel merging techniques, excels in narrative and role-playing."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision instruction model, a lightweight multimodal model capable of handling complex visual and textual information, with strong reasoning abilities."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5B model supports advanced programming tasks, enhanced multilingual capabilities, suitable for complex code generation and understanding."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "The QwQ model is an experimental research model developed by the Qwen team, focusing on enhancing AI reasoning capabilities."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7B model, trained on over 80 programming languages, boasts excellent code completion capabilities and contextual understanding."
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "The 72B version of the Qwen-VL model is the latest iteration from Alibaba, representing nearly a year of innovation."
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 is a series of decoder-only language models developed by the Alibaba Cloud Qwen team. These models come in different sizes including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B, available in both base and instruct variants."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct is the latest version in Alibaba Cloud's series of code-specific large language models. This model significantly enhances code generation, reasoning, and repair capabilities based on Qwen2.5, trained on 55 trillion tokens. It not only improves coding abilities but also maintains advantages in mathematics and general capabilities, providing a more comprehensive foundation for practical applications such as code agents."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Yi-Large model, featuring exceptional multilingual processing capabilities, suitable for various language generation and understanding tasks."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "A 52B parameter (12B active) multilingual model, offering a 256K long context window, function calling, structured output, and grounded generation."
},
- "ai21-jamba-instruct": {
- "description": "A production-grade Mamba-based LLM model designed to achieve best-in-class performance, quality, and cost efficiency."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet raises the industry standard, outperforming competitor models and Claude 3 Opus, excelling in a wide range of evaluations while maintaining the speed and cost of our mid-tier models."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet raises the industry standard, outperforming competing models and Claude 3 Opus, excelling in extensive evaluations while maintaining the speed and cost of our mid-tier models."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku is Anthropic's fastest and most compact model, providing near-instantaneous response times. It can quickly answer simple queries and requests. Customers will be able to build seamless AI experiences that mimic human interaction. Claude 3 Haiku can process images and return text output, with a context window of 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus is Anthropic's most powerful model for handling highly complex tasks. It excels in performance, intelligence, fluency, and comprehension."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku is Anthropic's fastest next-generation model. Compared to Claude 3 Haiku, Claude 3.5 Haiku shows improvements across various skills and surpasses the previous generation's largest model, Claude 3 Opus, in many intelligence benchmarks."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet offers capabilities that surpass Opus and faster speeds than Sonnet, while maintaining the same pricing as Sonnet. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet is Anthropic's most advanced model to date and the first hybrid reasoning model on the market. Claude 3.7 Sonnet can generate near-instant responses or extended step-by-step reasoning, allowing users to clearly observe these processes. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
+ },
"aya": {
"description": "Aya 23 is a multilingual model launched by Cohere, supporting 23 languages, facilitating diverse language applications."
},
"aya:35b": {
"description": "Aya 23 is a multilingual model launched by Cohere, supporting 23 languages, facilitating diverse language applications."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B is an open-source, commercially usable large language model developed by Baichuan Intelligence, containing 13 billion parameters, achieving the best results in its size on authoritative Chinese and English benchmarks."
+ },
"charglm-3": {
"description": "CharGLM-3 is designed for role-playing and emotional companionship, supporting ultra-long multi-turn memory and personalized dialogue, with wide applications."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 provides advancements in key capabilities for enterprises, including industry-leading 200K token context, significantly reducing the occurrence of model hallucinations, system prompts, and a new testing feature: tool invocation."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku is Anthropic's fastest next-generation model. Compared to Claude 3 Haiku, Claude 3.5 Haiku has improved in various skills and has surpassed the previous generation's largest model, Claude 3 Opus, in many intelligence benchmark tests."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet offers capabilities that surpass Opus and faster speeds than Sonnet, while maintaining the same price as Sonnet. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet offers capabilities that surpass Opus and faster speeds than Sonnet, while maintaining the same pricing as Sonnet. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet is Anthropic's latest model, offering a balance of speed and performance. It excels in a wide range of tasks, including programming, data science, visual processing, and agent tasks."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku is Anthropic's fastest and most compact model, designed for near-instantaneous responses. It features rapid and accurate directional performance."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet provides an ideal balance of intelligence and speed for enterprise workloads. It offers maximum utility at a lower price, reliable and suitable for large-scale deployment."
},
- "claude-instant-1.2": {
- "description": "Anthropic's model for low-latency, high-throughput text generation, capable of generating hundreds of pages of text."
- },
"codegeex-4": {
"description": "CodeGeeX-4 is a powerful AI programming assistant that supports intelligent Q&A and code completion in various programming languages, enhancing development efficiency."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B is a multilingual code generation model that supports comprehensive functions including code completion and generation, code interpretation, web search, function calls, and repository-level code Q&A, covering various scenarios in software development. It is a top-tier code generation model with fewer than 10B parameters."
+ },
"codegemma": {
"description": "CodeGemma is a lightweight language model dedicated to various programming tasks, supporting rapid iteration and integration."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama is an LLM focused on code generation and discussion, combining extensive programming language support, suitable for developer environments."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama is an LLM focused on code generation and discussion, with extensive support for various programming languages, suitable for developer environments."
+ },
"codellama:13b": {
"description": "Code Llama is an LLM focused on code generation and discussion, combining extensive programming language support, suitable for developer environments."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ is a high-performance large language model designed for real enterprise scenarios and complex applications."
},
+ "dall-e-2": {
+ "description": "The second generation DALL·E model, supporting more realistic and accurate image generation, with a resolution four times that of the first generation."
+ },
+ "dall-e-3": {
+ "description": "The latest DALL·E model, released in November 2023. It supports more realistic and accurate image generation with enhanced detail representation."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct provides highly reliable instruction processing capabilities, supporting applications across multiple industries."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 is a reinforcement learning (RL) driven inference model that addresses issues of repetitiveness and readability within the model. Prior to RL, DeepSeek-R1 introduced cold start data to further optimize inference performance. It performs comparably to OpenAI-o1 in mathematical, coding, and reasoning tasks, and enhances overall effectiveness through meticulously designed training methods."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "The DeepSeek-R1 distillation model optimizes inference performance through reinforcement learning and cold-start data, refreshing the benchmark for open-source models across multiple tasks."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B is a distillation model developed based on Llama-3.1-8B. This model is fine-tuned using samples generated by DeepSeek-R1, demonstrating excellent reasoning capabilities. It has performed well in multiple benchmark tests, achieving an 89.1% accuracy rate on MATH-500, a 50.4% pass rate on AIME 2024, and a score of 1205 on CodeForces, showcasing strong mathematical and programming abilities as an 8B scale model."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "The DeepSeek-R1 distillation model optimizes inference performance through reinforcement learning and cold-start data, refreshing the benchmark for open-source models across multiple tasks."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "The DeepSeek-R1 distillation model optimizes inference performance through reinforcement learning and cold-start data, refreshing the benchmark for open-source models across multiple tasks."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B is a model obtained through knowledge distillation based on Qwen2.5-32B. This model is fine-tuned using 800,000 selected samples generated by DeepSeek-R1, demonstrating exceptional performance in mathematics, programming, and reasoning across multiple domains. It has achieved excellent results in various benchmark tests, including a 94.3% accuracy rate on MATH-500, showcasing strong mathematical reasoning capabilities."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B is a model obtained through knowledge distillation based on Qwen2.5-Math-7B. This model is fine-tuned using 800,000 selected samples generated by DeepSeek-R1, demonstrating excellent reasoning capabilities. It has performed outstandingly in multiple benchmark tests, achieving a 92.8% accuracy rate on MATH-500, a 55.5% pass rate on AIME 2024, and a score of 1189 on CodeForces, showcasing strong mathematical and programming abilities as a 7B scale model."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 combines the excellent features of previous versions, enhancing general and coding capabilities."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 is a mixture of experts (MoE) language model with 671 billion parameters, utilizing multi-head latent attention (MLA) and the DeepSeekMoE architecture, combined with a load balancing strategy that does not rely on auxiliary loss, optimizing inference and training efficiency. Pre-trained on 14.8 trillion high-quality tokens and fine-tuned with supervision and reinforcement learning, DeepSeek-V3 outperforms other open-source models and approaches leading closed-source models in performance."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B is an advanced model trained for highly complex conversations."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "A state-of-the-art efficient LLM skilled in reasoning, mathematics, and programming."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 is a mixture of experts (MoE) visual language model developed based on DeepSeekMoE-27B, employing a sparsely activated MoE architecture that achieves outstanding performance while activating only 4.5 billion parameters. This model excels in various tasks, including visual question answering, optical character recognition, document/table/chart understanding, and visual localization."
+ },
"deepseek-chat": {
"description": "A new open-source model that integrates general and coding capabilities, retaining the general conversational abilities of the original Chat model and the powerful code handling capabilities of the Coder model, while better aligning with human preferences. Additionally, DeepSeek-V2.5 has achieved significant improvements in writing tasks, instruction following, and more."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B is a code language model trained on 20 trillion data points, of which 87% are code and 13% are in Chinese and English. The model introduces a 16K window size and fill-in-the-blank tasks, providing project-level code completion and snippet filling capabilities."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 is an open-source hybrid expert code model that performs excellently in coding tasks, comparable to GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 is an open-source hybrid expert code model that performs excellently in coding tasks, comparable to GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 is a reinforcement learning (RL) driven inference model that addresses issues of repetitiveness and readability within the model. Prior to RL, DeepSeek-R1 introduced cold start data to further optimize inference performance. It performs comparably to OpenAI-o1 in mathematical, coding, and reasoning tasks, and enhances overall effectiveness through meticulously designed training methods."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1—the larger and smarter model in the DeepSeek suite—has been distilled into the Llama 70B architecture. Based on benchmark tests and human evaluations, this model is smarter than the original Llama 70B, especially excelling in tasks requiring mathematical and factual accuracy."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "The DeepSeek-R1-Distill series models are fine-tuned versions of samples generated by DeepSeek-R1, using knowledge distillation techniques on open-source models like Qwen and Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "The DeepSeek-R1-Distill series models are fine-tuned versions of samples generated by DeepSeek-R1, using knowledge distillation techniques on open-source models like Qwen and Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "The DeepSeek-R1-Distill series models are fine-tuned versions of samples generated by DeepSeek-R1, using knowledge distillation techniques on open-source models like Qwen and Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "The DeepSeek-R1-Distill series models are fine-tuned versions of samples generated by DeepSeek-R1, using knowledge distillation techniques on open-source models like Qwen and Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "The DeepSeek-R1-Distill series models are fine-tuned versions of samples generated by DeepSeek-R1, using knowledge distillation techniques on open-source models like Qwen and Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "The reasoning model launched by DeepSeek. Before outputting the final answer, the model first provides a chain of thought to enhance the accuracy of the final response."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 is an efficient Mixture-of-Experts language model, suitable for cost-effective processing needs."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B is the design code model of DeepSeek, providing powerful code generation capabilities."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 is a MoE model developed by Hangzhou DeepSeek Artificial Intelligence Technology Research Co., Ltd., achieving outstanding results in multiple evaluations and ranking first among open-source models on mainstream leaderboards. Compared to the V2.5 model, V3 has achieved a threefold increase in generation speed, providing users with a faster and smoother experience."
+ },
"deepseek/deepseek-chat": {
"description": "A new open-source model that integrates general and coding capabilities, retaining the general conversational abilities of the original Chat model and the powerful code handling capabilities of the Coder model, while better aligning with human preferences. Additionally, DeepSeek-V2.5 has achieved significant improvements in writing tasks, instruction following, and more."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 significantly enhances model reasoning capabilities with minimal labeled data. Before outputting the final answer, the model first provides a chain of thought to improve the accuracy of the final response."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B is a large language model based on Llama3.3 70B, which achieves competitive performance comparable to large cutting-edge models by utilizing fine-tuning from DeepSeek R1 outputs."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B is a distilled large language model based on Llama-3.1-8B-Instruct, trained using outputs from DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, trained using outputs from DeepSeek R1. This model has surpassed OpenAI's o1-mini in several benchmark tests, achieving state-of-the-art results for dense models. Here are some benchmark results:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nThis model demonstrates competitive performance comparable to larger cutting-edge models through fine-tuning from DeepSeek R1 outputs."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, trained using outputs from DeepSeek R1. This model has surpassed OpenAI's o1-mini in several benchmark tests, achieving state-of-the-art results for dense models. Here are some benchmark results:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nThis model demonstrates competitive performance comparable to larger cutting-edge models through fine-tuning from DeepSeek R1 outputs."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 is the latest open-source model released by the DeepSeek team, featuring impressive inference performance, particularly in mathematics, programming, and reasoning tasks, reaching levels comparable to OpenAI's o1 model."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 significantly enhances model reasoning capabilities with minimal labeled data. Before outputting the final answer, the model first provides a chain of thought to improve the accuracy of the final response."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 has achieved a significant breakthrough in inference speed compared to previous models. It ranks first among open-source models and can compete with the world's most advanced closed-source models. DeepSeek-V3 employs Multi-Head Latent Attention (MLA) and DeepSeekMoE architectures, which have been thoroughly validated in DeepSeek-V2. Additionally, DeepSeek-V3 introduces an auxiliary lossless strategy for load balancing and sets multi-label prediction training objectives for enhanced performance."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 has achieved a significant breakthrough in inference speed compared to previous models. It ranks first among open-source models and can compete with the world's most advanced closed-source models. DeepSeek-V3 employs Multi-Head Latent Attention (MLA) and DeepSeekMoE architectures, which have been thoroughly validated in DeepSeek-V2. Additionally, DeepSeek-V3 introduces an auxiliary lossless strategy for load balancing and sets multi-label prediction training objectives for enhanced performance."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite is a new generation lightweight model, offering extreme response speed with performance and latency at a world-class level."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k is an upgraded version of Doubao-1.5-Pro, significantly enhancing overall performance by 10%. It supports reasoning with a 256k context window and an output length of up to 12k tokens. With higher performance, a larger window, and exceptional cost-effectiveness, it is suitable for a wider range of applications."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro is a new generation flagship model with comprehensive performance upgrades, excelling in knowledge, coding, reasoning, and more."
+ },
"emohaa": {
"description": "Emohaa is a psychological model with professional counseling capabilities, helping users understand emotional issues."
},
+ "ernie-3.5-128k": {
+ "description": "Baidu's flagship large-scale language model, covering a vast amount of Chinese and English corpus, possesses strong general capabilities to meet the requirements of most dialogue Q&A, creative generation, and plugin application scenarios; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information."
+ },
+ "ernie-3.5-8k": {
+ "description": "Baidu's flagship large-scale language model, covering a vast amount of Chinese and English corpus, possesses strong general capabilities to meet the requirements of most dialogue Q&A, creative generation, and plugin application scenarios; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Baidu's flagship large-scale language model, covering a vast amount of Chinese and English corpus, possesses strong general capabilities to meet the requirements of most dialogue Q&A, creative generation, and plugin application scenarios; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Baidu's flagship ultra-large-scale language model, which has achieved a comprehensive upgrade in model capabilities compared to ERNIE 3.5, widely applicable to complex task scenarios across various fields; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Baidu's flagship ultra-large-scale language model, which has achieved a comprehensive upgrade in model capabilities compared to ERNIE 3.5, widely applicable to complex task scenarios across various fields; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Baidu's flagship ultra-large-scale language model, demonstrating outstanding overall performance, widely applicable to complex task scenarios across various fields; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information. It performs better than ERNIE 4.0 in terms of performance."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Baidu's flagship ultra-large-scale language model, demonstrating outstanding overall performance, widely applicable to complex task scenarios across various fields; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information. It performs better than ERNIE 4.0 in terms of performance."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Baidu's flagship ultra-large-scale language model, demonstrating outstanding overall performance, widely applicable to complex task scenarios across various fields; it supports automatic integration with Baidu search plugins to ensure the timeliness of Q&A information. It performs better than ERNIE 4.0 in terms of performance."
+ },
+ "ernie-char-8k": {
+ "description": "Baidu's vertical scene large language model, suitable for applications such as game NPCs, customer service dialogues, and role-playing conversations, with a more distinct and consistent character style, stronger instruction-following capabilities, and superior inference performance."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Baidu's vertical scene large language model, suitable for applications such as game NPCs, customer service dialogues, and role-playing conversations, with a more distinct and consistent character style, stronger instruction-following capabilities, and superior inference performance."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite is Baidu's lightweight large language model, balancing excellent model performance with inference efficiency, suitable for low-power AI acceleration card inference."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Baidu's lightweight large language model, balancing excellent model performance with inference efficiency, offering better performance than ERNIE Lite, suitable for low-power AI acceleration card inference."
+ },
+ "ernie-novel-8k": {
+ "description": "Baidu's general-purpose large language model, which has a significant advantage in novel continuation capabilities and can also be used in short plays, movies, and other scenarios."
+ },
+ "ernie-speed-128k": {
+ "description": "Baidu's latest self-developed high-performance large language model released in 2024, with excellent general capabilities, suitable as a base model for fine-tuning to better address specific scenario issues while also demonstrating excellent inference performance."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Baidu's latest self-developed high-performance large language model released in 2024, with excellent general capabilities, offering better performance than ERNIE Speed, suitable as a base model for fine-tuning to better address specific scenario issues while also demonstrating excellent inference performance."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny is Baidu's ultra-high-performance large language model, with the lowest deployment and fine-tuning costs among the Wenxin series models."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) offers stable and tunable performance, making it an ideal choice for complex task solutions."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro is Google's high-performance AI model, designed for extensive task scaling."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash is Google's latest multimodal AI model, featuring rapid processing capabilities and supporting text, image, and video inputs, making it efficient for scaling across various tasks."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 is an efficient multimodal model that supports extensive application scaling."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 is an efficient multimodal model that supports a wide range of applications."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 is designed for handling large-scale task scenarios, providing unparalleled processing speed."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B is an efficient multimodal model that supports a wide range of applications."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 is the latest experimental model, showcasing significant performance improvements in both text and multimodal use cases."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 offers optimized multimodal processing capabilities, suitable for a variety of complex task scenarios."
+ "description": "Gemini 1.5 Flash 0827 provides optimized multimodal processing capabilities, suitable for various complex task scenarios."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash is Google's latest multimodal AI model, featuring fast processing capabilities and supporting text, image, and video inputs, making it suitable for efficient scaling across various tasks."
@@ -357,11 +822,35 @@
"description": "Gemini 1.5 Pro 0801 offers excellent multimodal processing capabilities, providing greater flexibility for application development."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 combines the latest optimization technologies to deliver more efficient multimodal data processing capabilities."
+ "description": "Gemini 1.5 Pro 0827 combines the latest optimization technologies for more efficient multimodal data processing."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro supports up to 2 million tokens, making it an ideal choice for medium-sized multimodal models, providing multifaceted support for complex tasks."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash offers next-generation features and improvements, including exceptional speed, native tool usage, multimodal generation, and a 1M token context window."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash offers next-generation features and improvements, including exceptional speed, native tool usage, multimodal generation, and a 1M token context window."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash is a variant of the model optimized for cost-effectiveness and low latency."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash is a variant of the model optimized for cost-effectiveness and low latency."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "A Gemini 2.0 Flash model optimized for cost-effectiveness and low latency."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp is Google's latest experimental multimodal AI model, featuring next-generation capabilities, exceptional speed, native tool invocation, and multimodal generation."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp is Google's latest experimental multimodal AI model, featuring next-generation capabilities, exceptional speed, native tool invocation, and multimodal generation."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental is Google's latest experimental multimodal AI model, showing a quality improvement compared to previous versions, especially in world knowledge, coding, and long context."
+ },
"gemma-7b-it": {
"description": "Gemma 7B is suitable for medium to small-scale task processing, offering cost-effectiveness."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 is an efficient model launched by Google, covering a variety of application scenarios from small applications to complex data processing."
},
- "general": {
- "description": "Spark Lite is a lightweight large language model with extremely low latency and efficient processing capabilities, completely free and open, supporting real-time online search functionality. Its fast response characteristics make it excel in inference applications and model fine-tuning on low-power devices, providing users with excellent cost-effectiveness and intelligent experiences, particularly in knowledge Q&A, content generation, and search scenarios."
- },
"generalv3": {
"description": "Spark Pro is a high-performance large language model optimized for professional fields, focusing on mathematics, programming, healthcare, education, and more, supporting online search and built-in plugins for weather, dates, etc. Its optimized model demonstrates excellent performance and efficiency in complex knowledge Q&A, language understanding, and high-level text creation, making it an ideal choice for professional application scenarios."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 is the latest model version designed for highly complex and diverse tasks, demonstrating outstanding performance."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat demonstrates high performance across various aspects, including semantics, mathematics, reasoning, coding, and knowledge. It also features web browsing, code execution, custom tool invocation, and long text reasoning, supporting 26 languages including Japanese, Korean, and German."
+ },
"glm-4-air": {
"description": "GLM-4-Air is a cost-effective version with performance close to GLM-4, offering fast speed at an affordable price."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash is the ideal choice for handling simple tasks, being the fastest and most cost-effective."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX is an enhanced version of Flash, featuring ultra-fast inference speed."
+ },
"glm-4-long": {
"description": "GLM-4-Long supports ultra-long text inputs, suitable for memory-based tasks and large-scale document processing."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V provides strong image understanding and reasoning capabilities, supporting various visual tasks."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash focuses on efficient single image understanding, suitable for scenarios that require rapid image parsing, such as real-time image analysis or batch image processing."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus has the ability to understand video content and multiple images, suitable for multimodal tasks."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 provides optimized multimodal processing capabilities, suitable for various complex task scenarios."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview possesses strong complex reasoning abilities, excelling in logical reasoning, mathematics, programming, and other fields."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash offers next-generation features and improvements, including exceptional speed, native tool usage, multimodal generation, and a 1M token context window."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental is Google's latest experimental multimodal AI model, showing a quality improvement compared to previous versions, especially in world knowledge, coding, and long context."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 combines the latest optimization technologies to deliver more efficient multimodal data processing capabilities."
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash offers optimized multimodal processing capabilities, suitable for various complex task scenarios."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro combines the latest optimization technologies to deliver more efficient multimodal data processing capabilities."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 is an efficient model launched by Google, covering a variety of application scenarios from small applications to complex data processing."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 continues the design philosophy of being lightweight and efficient."
},
+ "google/gemma-2-2b-it": {
+ "description": "Google's lightweight instruction-tuning model."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 is an efficient model launched by Google, covering a variety of application scenarios from small applications to complex data processing."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 is Google's lightweight open-source text model series."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo is suitable for various text generation and understanding tasks. Currently points to gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo is an efficient model provided by OpenAI, suitable for chat and text generation tasks, supporting parallel function calls."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k is a high-capacity text generation model suitable for complex tasks."
+ },
"gpt-4": {
"description": "GPT-4 offers a larger context window, capable of handling longer text inputs, making it suitable for scenarios that require extensive information integration and data analysis."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
},
- "gpt-4-1106-vision-preview": {
- "description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
- },
"gpt-4-32k": {
"description": "GPT-4 offers a larger context window, capable of handling longer text inputs, making it suitable for scenarios that require extensive information integration and data analysis."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
},
+ "gpt-4.5-preview": {
+ "description": "The research preview of GPT-4.5, our largest and most powerful GPT model to date. It possesses extensive world knowledge and better understands user intent, excelling in creative tasks and autonomous planning. GPT-4.5 accepts both text and image inputs and generates text outputs (including structured outputs). It supports key developer features such as function calling, batch API, and streaming output. GPT-4.5 particularly shines in tasks that require creativity, open-ended thinking, and dialogue, such as writing, learning, or exploring new ideas. Knowledge cutoff date is October 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o is a dynamic model that updates in real-time to stay current with the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale applications, including customer service, education, and technical support."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o is a dynamic model that updates in real-time to stay current with the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale applications, including customer service, education, and technical support."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o is a dynamic model that updates in real-time to maintain the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale applications including customer service, education, and technical support."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o Audio model, supporting audio input and output."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini is the latest model released by OpenAI after GPT-4 Omni, supporting both image and text input while outputting text. As their most advanced small model, it is significantly cheaper than other recent cutting-edge models, costing over 60% less than GPT-3.5 Turbo. It maintains state-of-the-art intelligence while offering remarkable cost-effectiveness. GPT-4o mini scored 82% on the MMLU test and currently ranks higher than GPT-4 in chat preferences."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "GPT-4o-mini real-time version, supporting real-time audio and text input and output."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "GPT-4o real-time version, supporting real-time audio and text input and output."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "GPT-4o real-time version, supporting real-time audio and text input and output."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "GPT-4o real-time version, supporting real-time audio and text input and output."
+ },
+ "grok-2-1212": {
+ "description": "This model has improved in accuracy, instruction adherence, and multilingual capabilities."
+ },
+ "grok-2-vision-1212": {
+ "description": "This model has improved in accuracy, instruction adherence, and multilingual capabilities."
+ },
+ "grok-beta": {
+ "description": "Offers performance comparable to Grok 2 but with higher efficiency, speed, and functionality."
+ },
+ "grok-vision-beta": {
+ "description": "The latest image understanding model that can handle a wide range of visual information, including documents, charts, screenshots, and photographs."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B is a language model that combines creativity and intelligence by merging multiple top models."
},
+ "hunyuan-code": {
+ "description": "The latest code generation model from Hunyuan, trained on a base model with 200B high-quality code data, iteratively trained for six months with high-quality SFT data, increasing the context window length to 8K. It ranks among the top in automatic evaluation metrics for code generation across five major programming languages, and performs in the first tier for comprehensive human quality assessments across ten aspects of coding tasks."
+ },
+ "hunyuan-functioncall": {
+ "description": "The latest MOE architecture FunctionCall model from Hunyuan, trained on high-quality FunctionCall data, with a context window of 32K, leading in multiple dimensions of evaluation metrics."
+ },
+ "hunyuan-large": {
+ "description": "The Hunyuan-large model has a total parameter count of approximately 389B, with about 52B active parameters, making it the largest and most effective open-source MoE model in the industry based on the Transformer architecture."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Specializes in handling long text tasks such as document summarization and question answering, while also capable of general text generation tasks. It excels in analyzing and generating long texts, effectively addressing complex and detailed long-form content processing needs."
+ },
+ "hunyuan-lite": {
+ "description": "Upgraded to a MOE structure with a context window of 256k, leading many open-source models in various NLP, coding, mathematics, and industry benchmarks."
+ },
+ "hunyuan-lite-vision": {
+ "description": "The latest 7B multimodal model from Hunyuan, with a context window of 32K, supports multimodal dialogue in both Chinese and English scenarios, image object recognition, document table understanding, and multimodal mathematics, outperforming 7B competing models across multiple evaluation dimensions."
+ },
+ "hunyuan-pro": {
+ "description": "A trillion-parameter scale MOE-32K long text model. Achieves absolute leading levels across various benchmarks, capable of handling complex instructions and reasoning, with advanced mathematical abilities, supporting function calls, and optimized for applications in multilingual translation, finance, law, and healthcare."
+ },
+ "hunyuan-role": {
+ "description": "The latest role-playing model from Hunyuan, fine-tuned and trained by Hunyuan's official team, based on the Hunyuan model combined with role-playing scenario datasets for enhanced foundational performance in role-playing contexts."
+ },
+ "hunyuan-standard": {
+ "description": "Utilizes a superior routing strategy while alleviating issues of load balancing and expert convergence. For long texts, the needle-in-a-haystack metric reaches 99.9%. MOE-32K offers a relatively higher cost-performance ratio, balancing effectiveness and price while enabling processing of long text inputs."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Utilizes a superior routing strategy while alleviating issues of load balancing and expert convergence. For long texts, the needle-in-a-haystack metric reaches 99.9%. MOE-256K further breaks through in length and effectiveness, greatly expanding the input length capacity."
+ },
+ "hunyuan-standard-vision": {
+ "description": "The latest multimodal model from Hunyuan, supporting multilingual responses with balanced capabilities in both Chinese and English."
+ },
+ "hunyuan-translation": {
+ "description": "Supports translation between Chinese and 15 other languages including English, Japanese, French, Portuguese, Spanish, Turkish, Russian, Arabic, Korean, Italian, German, Vietnamese, Malay, and Indonesian. It is based on a multi-scenario translation evaluation set with automated COMET scoring, demonstrating overall superior translation capabilities compared to similarly scaled models in the market."
+ },
+ "hunyuan-translation-lite": {
+ "description": "The Hunyuan translation model supports natural language conversational translation; it supports translation between Chinese and 15 other languages including English, Japanese, French, Portuguese, Spanish, Turkish, Russian, Arabic, Korean, Italian, German, Vietnamese, Malay, and Indonesian."
+ },
+ "hunyuan-turbo": {
+ "description": "The preview version of the next-generation Hunyuan large language model, featuring a brand-new mixed expert model (MoE) structure, which offers faster inference efficiency and stronger performance compared to Hunyuan Pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Hunyuan-turbo fixed version as of November 20, 2024, a version that lies between hunyuan-turbo and hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "This version optimizes: data instruction scaling, significantly enhancing the model's generalization capabilities; greatly improving mathematical, coding, and logical reasoning abilities; optimizing text understanding and word comprehension capabilities; enhancing the quality of content generation in text creation."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "General experience optimization, including NLP understanding, text creation, casual conversation, knowledge Q&A, translation, and domain-specific tasks; enhanced personification and emotional intelligence of the model; improved the model's ability to clarify when intentions are ambiguous; enhanced handling of word parsing-related questions; improved the quality and interactivity of creative outputs; enhanced multi-turn experience."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "The next-generation flagship visual language model from Hunyuan, utilizing a new mixed expert model (MoE) structure, with comprehensive improvements in basic recognition, content creation, knowledge Q&A, and analytical reasoning capabilities compared to the previous generation model."
+ },
+ "hunyuan-vision": {
+ "description": "The latest multimodal model from Hunyuan, supporting image + text input to generate textual content."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "The innovative open-source model InternLM2.5 enhances dialogue intelligence through a large number of parameters."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 offers intelligent dialogue solutions across multiple scenarios."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct model, featuring 70B parameters, delivers outstanding performance in large text generation and instruction tasks."
+ "internlm2-pro-chat": {
+ "description": "An older version of the model that we still maintain, available in various parameter sizes of 7B and 20B."
+ },
+ "internlm2.5-latest": {
+ "description": "Our latest model series, featuring exceptional reasoning performance, supporting a context length of 1M, and enhanced instruction following and tool invocation capabilities."
+ },
+ "internlm3-latest": {
+ "description": "Our latest model series boasts exceptional inference performance, leading the pack among open-source models of similar scale. It defaults to our most recently released InternLM3 series models."
+ },
+ "jina-deepsearch-v1": {
+ "description": "DeepSearch combines web search, reading, and reasoning for comprehensive investigations. You can think of it as an agent that takes on your research tasks—it conducts extensive searches and iterates multiple times before providing answers. This process involves ongoing research, reasoning, and problem-solving from various angles. This fundamentally differs from standard large models that generate answers directly from pre-trained data and traditional RAG systems that rely on one-time surface searches."
+ },
+ "kimi-latest": {
+ "description": "The Kimi Smart Assistant product uses the latest Kimi large model, which may include features that are not yet stable. It supports image understanding and will automatically select the 8k/32k/128k model as the billing model based on the length of the request context."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM is an experimental, task-specific language model trained to align with learning science principles, capable of following systematic instructions in teaching and learning scenarios, acting as an expert tutor, among other roles."
+ },
+ "lite": {
+ "description": "Spark Lite is a lightweight large language model with extremely low latency and efficient processing capabilities, completely free and open, supporting real-time online search functionality. Its quick response feature makes it excel in inference applications and model fine-tuning on low-power devices, providing users with excellent cost-effectiveness and intelligent experiences, particularly in knowledge Q&A, content generation, and search scenarios."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B provides enhanced AI reasoning capabilities, suitable for complex applications, supporting extensive computational processing while ensuring efficiency and accuracy."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B is a high-performance model that offers rapid text generation capabilities, making it ideal for applications requiring large-scale efficiency and cost-effectiveness."
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct model, featuring 8B parameters, supports efficient execution of visual instruction tasks, providing high-quality text generation capabilities."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Excellent image reasoning capabilities on high-resolution images, suitable for visual understanding applications."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Online model, featuring 405B parameters, supports a context length of approximately 127,000 tokens, designed for complex online chat applications."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 is designed to handle tasks that combine visual and textual data. It excels in tasks such as image description and visual question answering, bridging the gap between language generation and visual reasoning."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chat model, featuring 70B parameters, supports a context length of approximately 127,000 tokens, suitable for complex offline chat tasks."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Advanced image reasoning capabilities suitable for visual understanding agent applications."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Online model, featuring 70B parameters, supports a context length of approximately 127,000 tokens, suitable for high-capacity and diverse chat tasks."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 is designed to handle tasks that combine visual and textual data. It excels in tasks such as image description and visual question answering, bridging the gap between language generation and visual reasoning."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chat model, featuring 8B parameters, designed for offline chat, supports a context length of approximately 127,000 tokens."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 is the most advanced multilingual open-source large language model in the Llama series, offering performance comparable to a 405B model at an extremely low cost. Based on the Transformer architecture, it enhances usability and safety through supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Its instruction-tuned version is optimized for multilingual dialogue and outperforms many open-source and closed chat models on various industry benchmarks. Knowledge cutoff date is December 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Online model, featuring 8B parameters, supports a context length of approximately 127,000 tokens, designed for online chat, efficiently handling various text interactions."
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 is a multilingual large language model (LLM) with 70 billion parameters (text input/text output), featuring pre-training and instruction-tuning. The instruction-tuned pure text model of Llama 3.3 is optimized for multilingual conversational use cases and outperforms many available open-source and closed chat models on common industry benchmarks."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B provides unparalleled complexity handling capabilities, tailored for high-demand projects."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral is designed for scientific research and mathematical reasoning, providing effective computational capabilities and result interpretation."
},
+ "max-32k": {
+ "description": "Spark Max 32K is configured with large context processing capabilities, enhanced contextual understanding, and logical reasoning abilities, supporting text input of 32K tokens, suitable for long document reading, private knowledge Q&A, and other scenarios."
+ },
"meta-llama-3-70b-instruct": {
"description": "A powerful 70-billion parameter model excelling in reasoning, coding, and broad language applications."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) offers excellent language processing capabilities and outstanding interactive experiences."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 provides excellent language processing capabilities and outstanding interactive experiences."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) is a powerful chat model that supports complex conversational needs."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) provides multilingual support, covering a rich array of domain knowledge."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 is designed for tasks involving both visual and textual data. It excels in tasks like image description and visual question answering, bridging the gap between language generation and visual reasoning."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 is designed for tasks involving both visual and textual data. It excels in tasks like image description and visual question answering, bridging the gap between language generation and visual reasoning."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 is designed for tasks involving both visual and textual data. It excels in tasks like image description and visual question answering, bridging the gap between language generation and visual reasoning."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 is the most advanced multilingual open-source large language model in the Llama series, offering performance comparable to 405B models at a very low cost. Based on the Transformer architecture, it enhances usability and safety through supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Its instruction-tuned version is optimized for multilingual dialogue and outperforms many open-source and closed chat models on multiple industry benchmarks. Knowledge cutoff date is December 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 is a multilingual large language model (LLM) that is a pre-trained and instruction-tuned generative model within the 70B (text input/text output) framework. The instruction-tuned pure text model is optimized for multilingual dialogue use cases and outperforms many available open-source and closed chat models on common industry benchmarks."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 is designed for tasks involving both visual and textual data. It excels in tasks like image description and visual question answering, bridging the gap between language generation and visual reasoning."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite is suitable for environments requiring high performance and low latency."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "The 405B Llama 3.1 Turbo model provides massive context support for big data processing, excelling in large-scale AI applications."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 is a leading model launched by Meta, supporting up to 405B parameters, applicable in complex conversations, multilingual translation, and data analysis."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B offers efficient conversational support in multiple languages."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct is optimized for high-quality conversational scenarios, performing better than many closed-source models."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct is the latest version from Meta, optimized for generating high-quality dialogues, surpassing many leading closed-source models."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct is designed for high-quality conversations, excelling in human evaluations, particularly in highly interactive scenarios."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 offers multilingual support and is one of the industry's leading generative models."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 is designed to handle tasks that combine visual and textual data. It excels in tasks such as image description and visual question answering, bridging the gap between language generation and visual reasoning."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 is designed to handle tasks that combine visual and textual data. It excels in tasks such as image description and visual question answering, bridging the gap between language generation and visual reasoning."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 is the most advanced multilingual open-source large language model in the Llama series, offering performance comparable to a 405B model at an extremely low cost. Based on the Transformer architecture, it enhances usability and safety through supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Its instruction-tuned version is optimized for multilingual dialogue and outperforms many open-source and closed chat models on various industry benchmarks. Knowledge cutoff date is December 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 is the most advanced multilingual open-source large language model in the Llama series, offering performance comparable to a 405B model at an extremely low cost. Based on the Transformer architecture, it enhances usability and safety through supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Its instruction-tuned version is optimized for multilingual dialogue and outperforms many open-source and closed chat models on various industry benchmarks. Knowledge cutoff date is December 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct is the largest and most powerful model in the Llama 3.1 Instruct series. It is a highly advanced conversational reasoning and synthetic data generation model, which can also serve as a foundation for specialized continuous pre-training or fine-tuning in specific domains. The multilingual large language models (LLMs) provided by Llama 3.1 are a set of pre-trained, instruction-tuned generative models, including sizes of 8B, 70B, and 405B (text input/output). The instruction-tuned text models (8B, 70B, 405B) are optimized for multilingual conversational use cases and have outperformed many available open-source chat models in common industry benchmarks. Llama 3.1 is designed for commercial and research purposes across multiple languages. The instruction-tuned text models are suitable for assistant-like chat, while the pre-trained models can adapt to various natural language generation tasks. The Llama 3.1 models also support improving other models using their outputs, including synthetic data generation and refinement. Llama 3.1 is an autoregressive language model built using an optimized transformer architecture. The tuned versions utilize supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 is an open large language model (LLM) aimed at developers, researchers, and enterprises, designed to help them build, experiment, and responsibly scale their generative AI ideas. As part of a foundational system for global community innovation, it is particularly suitable for those with limited computational power and resources, edge devices, and faster training times."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B is Microsoft's latest lightweight AI model, performing nearly ten times better than existing leading open-source models."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "An advanced LLM supporting synthetic data generation, knowledge distillation, and reasoning, suitable for chatbots, programming, and domain-specific tasks."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Empowering complex conversations with exceptional context understanding, reasoning capabilities, and text generation abilities."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "An advanced cutting-edge model with language understanding, excellent reasoning capabilities, and text generation abilities."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "A state-of-the-art vision-language model adept at high-quality reasoning from images."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "A cutting-edge small language model with language understanding, excellent reasoning capabilities, and text generation abilities."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "A cutting-edge small language model with language understanding, excellent reasoning capabilities, and text generation abilities."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "A state-of-the-art vision-language model adept at high-quality reasoning from images."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "An advanced LLM skilled in reasoning, mathematics, common sense, and function calling."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 is a language model provided by Microsoft AI, excelling in complex dialogues, multilingual capabilities, reasoning, and intelligent assistant tasks."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B is Microsoft's state-of-the-art Wizard model, demonstrating extremely competitive performance."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V is a next-generation multimodal large model launched by OpenBMB, boasting exceptional OCR recognition and multimodal understanding capabilities, supporting a wide range of application scenarios."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B is Mistral's top-tier edge model."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B is Mistral's cost-effective edge model."
+ },
"mistral": {
"description": "Mistral is a 7B model released by Mistral AI, suitable for diverse language processing needs."
},
"mistral-large": {
"description": "Mixtral Large is Mistral's flagship model, combining capabilities in code generation, mathematics, and reasoning, supporting a 128k context window."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) is an advanced Large Language Model (LLM) with state-of-the-art reasoning, knowledge, and coding capabilities."
- },
"mistral-large-latest": {
"description": "Mistral Large is the flagship model, excelling in multilingual tasks, complex reasoning, and code generation, making it an ideal choice for high-end applications."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 offers efficient computational power and natural language understanding, suitable for a wide range of applications."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B is a compact yet high-performance model, adept at handling batch processing and simple tasks like classification and text generation, featuring good reasoning capabilities."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) is a super large language model that supports extremely high processing demands."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B is a pre-trained sparse mixture of experts model for general text tasks."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B is a sparse expert model that utilizes multiple parameters to enhance reasoning speed, suitable for multilingual and code generation tasks."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct is a high-performance industry-standard model optimized for speed and long context support."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K is a model with ultra-long context processing capabilities, suitable for generating extremely long texts, meeting the demands of complex generation tasks, capable of handling up to 128,000 tokens, making it ideal for research, academia, and large document generation."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "The Kimi visual model (including moonshot-v1-8k-vision-preview, moonshot-v1-32k-vision-preview, moonshot-v1-128k-vision-preview, etc.) can understand image content, including text in images, colors, and shapes of objects."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K offers medium-length context processing capabilities, able to handle 32,768 tokens, particularly suitable for generating various long documents and complex dialogues, applicable in content creation, report generation, and dialogue systems."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "The Kimi visual model (including moonshot-v1-8k-vision-preview, moonshot-v1-32k-vision-preview, moonshot-v1-128k-vision-preview, etc.) can understand image content, including text in images, colors, and shapes of objects."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K is designed for generating short text tasks, featuring efficient processing performance, capable of handling 8,192 tokens, making it ideal for brief dialogues, note-taking, and rapid content generation."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "The Kimi visual model (including moonshot-v1-8k-vision-preview, moonshot-v1-32k-vision-preview, moonshot-v1-128k-vision-preview, etc.) can understand image content, including text in images, colors, and shapes of objects."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto can select the appropriate model based on the number of tokens used in the current context."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B is an upgraded version of Nous Hermes 2, featuring the latest internally developed datasets."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B is a large language model customized by NVIDIA, designed to enhance the helpfulness of LLM-generated responses to user queries. The model has excelled in benchmark tests such as Arena Hard, AlpacaEval 2 LC, and GPT-4-Turbo MT-Bench, ranking first in all three automatic alignment benchmarks as of October 1, 2024. The model is trained using RLHF (specifically REINFORCE), Llama-3.1-Nemotron-70B-Reward, and HelpSteer2-Preference prompts based on the Llama-3.1-70B-Instruct model."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "A unique language model offering unparalleled accuracy and efficiency."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct is a custom large language model by NVIDIA designed to enhance the helpfulness of LLM-generated responses."
+ },
+ "o1": {
+ "description": "Focused on advanced reasoning and solving complex problems, including mathematical and scientific tasks. It is particularly well-suited for applications that require deep contextual understanding and agent workflow."
+ },
"o1-mini": {
"description": "o1-mini is a fast and cost-effective reasoning model designed for programming, mathematics, and scientific applications. This model features a 128K context and has a knowledge cutoff date of October 2023."
},
"o1-preview": {
"description": "o1 is OpenAI's new reasoning model, suitable for complex tasks that require extensive general knowledge. This model features a 128K context and has a knowledge cutoff date of October 2023."
},
+ "o3-mini": {
+ "description": "o3-mini is our latest small inference model that delivers high intelligence while maintaining the same cost and latency targets as o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba is a language model focused on code generation, providing strong support for advanced coding and reasoning tasks."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B is a sparse expert model that leverages multiple parameters to enhance reasoning speed, suitable for handling multilingual and code generation tasks."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o is a dynamic model that updates in real-time to maintain the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale application scenarios, including customer service, education, and technical support."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o is a dynamic model that updates in real-time to maintain the latest version. It combines powerful language understanding and generation capabilities, suitable for large-scale application scenarios, including customer service, education, and technical support."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini is the latest model released by OpenAI following GPT-4 Omni, supporting both text and image input while outputting text. As their most advanced small model, it is significantly cheaper than other recent cutting-edge models and over 60% cheaper than GPT-3.5 Turbo. It maintains state-of-the-art intelligence while offering remarkable cost-effectiveness. GPT-4o mini scored 82% on the MMLU test and currently ranks higher than GPT-4 in chat preferences."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "The Pixtral model demonstrates strong capabilities in tasks such as chart and image understanding, document question answering, multimodal reasoning, and instruction following. It can ingest images at natural resolutions and aspect ratios and handle an arbitrary number of images within a long context window of up to 128K tokens."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large is an open-source multimodal model with 124 billion parameters, built on Mistral Large 2. This is the second model in our multimodal family, showcasing cutting-edge image understanding capabilities."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K is equipped with an extra-large context processing capability, able to handle up to 128K of contextual information, making it particularly suitable for long-form content that requires comprehensive analysis and long-term logical connections, providing smooth and consistent logic and diverse citation support in complex text communication."
+ },
+ "qvq-72b-preview": {
+ "description": "The QVQ model is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities, particularly in the field of mathematical reasoning."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Tongyi Qianwen code model."
+ },
"qwen-coder-turbo-latest": {
"description": "The Tongyi Qianwen Coder model."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "The Tongyi Qianwen Math model is specifically designed for solving mathematical problems."
},
+ "qwen-max": {
+ "description": "Qwen Max is a trillion-level large-scale language model that supports input in various languages including Chinese and English, and is the API model behind the current Qwen 2.5 product version."
+ },
"qwen-max-latest": {
"description": "Tongyi Qianwen Max is a large-scale language model with hundreds of billions of parameters, supporting input in various languages, including Chinese and English. It is the API model behind the current Tongyi Qianwen 2.5 product version."
},
+ "qwen-omni-turbo-latest": {
+ "description": "The Qwen-Omni series of models supports input of various modalities, including video, audio, images, and text, and outputs both audio and text."
+ },
+ "qwen-plus": {
+ "description": "Qwen Plus is an enhanced large-scale language model supporting input in various languages including Chinese and English."
+ },
"qwen-plus-latest": {
"description": "Tongyi Qianwen Plus is an enhanced version of the large-scale language model, supporting input in various languages, including Chinese and English."
},
+ "qwen-turbo": {
+ "description": "Qwen Turbo is a large-scale language model supporting input in various languages including Chinese and English."
+ },
"qwen-turbo-latest": {
"description": "Tongyi Qianwen is a large-scale language model that supports input in various languages, including Chinese and English."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL supports flexible interaction methods, including multi-image, multi-turn Q&A, and creative capabilities."
},
- "qwen-vl-max": {
- "description": "Qwen is a large-scale visual language model. Compared to the enhanced version, it further improves visual reasoning and instruction-following capabilities, providing higher levels of visual perception and cognition."
+ "qwen-vl-max-latest": {
+ "description": "Tongyi Qianwen's ultra-large-scale visual language model. Compared to the enhanced version, it further improves visual reasoning and instruction-following abilities, providing a higher level of visual perception and cognition."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "The Tongyi Qianwen OCR is a proprietary model for text extraction, focusing on the ability to extract text from images of documents, tables, exam papers, and handwritten text. It can recognize multiple languages, currently supporting: Chinese, English, French, Japanese, Korean, German, Russian, Italian, Vietnamese, and Arabic."
},
- "qwen-vl-plus": {
- "description": "Qwen is a large-scale visual language model enhanced version. It significantly improves detail recognition and text recognition capabilities, supporting images with resolutions over one million pixels and any aspect ratio."
+ "qwen-vl-plus-latest": {
+ "description": "Tongyi Qianwen's large-scale visual language model enhanced version. Significantly improves detail recognition and text recognition capabilities, supporting ultra-high pixel resolution and images of any aspect ratio."
},
"qwen-vl-v1": {
"description": "Initialized with the Qwen-7B language model, this pre-trained model adds an image model with an input resolution of 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 is a brand new series of large language models. Qwen2 7B is a transformer-based model that excels in language understanding, multilingual capabilities, programming, mathematics, and reasoning."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 is a brand new series of large language models with enhanced understanding and generation capabilities."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL is the latest iteration of the Qwen-VL model, achieving state-of-the-art performance in visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, and MTVQA. Qwen2-VL can understand videos over 20 minutes long for high-quality video-based Q&A, dialogue, and content creation. It also possesses complex reasoning and decision-making capabilities, allowing integration with mobile devices, robots, and more for automated operations based on visual environments and text instructions. In addition to English and Chinese, Qwen2-VL now supports understanding text in different languages within images, including most European languages, Japanese, Korean, Arabic, and Vietnamese."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct is one of the latest large language model series released by Alibaba Cloud. This 72B model has significantly improved capabilities in coding and mathematics. The model also offers multilingual support, covering over 29 languages, including Chinese and English. It shows significant enhancements in instruction following, understanding structured data, and generating structured outputs (especially JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct is one of the latest large language model series released by Alibaba Cloud. This 32B model has significantly improved capabilities in coding and mathematics. The model provides multilingual support, covering over 29 languages, including Chinese and English. It shows significant enhancements in instruction following, understanding structured data, and generating structured outputs (especially JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "An LLM focused on both Chinese and English, targeting language, programming, mathematics, reasoning, and more."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "An advanced LLM supporting code generation, reasoning, and debugging, covering mainstream programming languages."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "A powerful medium-sized code model supporting 32K context length, proficient in multilingual programming."
+ },
"qwen2": {
"description": "Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 is Alibaba's next-generation large-scale language model, supporting diverse application needs with outstanding performance."
+ },
"qwen2.5-14b-instruct": {
"description": "The 14B model of Tongyi Qianwen 2.5 is open-sourced."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "The Tongyi Qianwen 2.5 model is open-sourced at a scale of 72B."
+ },
"qwen2.5-32b-instruct": {
"description": "The 32B model of Tongyi Qianwen 2.5 is open-sourced."
},
@@ -824,13 +1599,16 @@
"description": "The 7B model of Tongyi Qianwen 2.5 is open-sourced."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "The open-source version of the Tongyi Qianwen Coder model."
+ "description": "Open-source version of the Qwen coding model."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Open-source version of the Tongyi Qianwen code model."
},
"qwen2.5-coder-7b-instruct": {
"description": "The open-source version of the Tongyi Qianwen Coder model."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "The Qwen-Math model possesses strong capabilities for solving mathematical problems."
+ "description": "Qwen-Math model has powerful mathematical problem-solving capabilities."
},
"qwen2.5-math-72b-instruct": {
"description": "The Qwen-Math model possesses strong capabilities for solving mathematical problems."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "The Qwen-Math model possesses strong capabilities for solving mathematical problems."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "This version enhances instruction following, mathematics, problem-solving, and coding capabilities, improving the ability to recognize various formats and accurately locate visual elements. It supports understanding long video files (up to 10 minutes) and pinpointing events in seconds, comprehending the sequence and speed of time, and based on parsing and locating capabilities, it supports controlling OS or Mobile agents. It has strong key information extraction and JSON output capabilities, and this version is the most powerful in the series at 72B."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "This version enhances instruction following, mathematics, problem-solving, and coding capabilities, improving the ability to recognize various formats and accurately locate visual elements. It supports understanding long video files (up to 10 minutes) and pinpointing events in seconds, comprehending the sequence and speed of time, and based on parsing and locating capabilities, it supports controlling OS or Mobile agents. It has strong key information extraction and JSON output capabilities, and this version is the most powerful in the series at 72B."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 is Alibaba's next-generation large-scale language model, supporting diverse application needs with outstanding performance."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 is Alibaba's next-generation large-scale language model, supporting diverse application needs with outstanding performance."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 is Alibaba's next-generation large-scale language model, supporting diverse application needs with outstanding performance."
+ },
"qwen2:0.5b": {
"description": "Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini is a compact LLM that outperforms GPT-3.5, featuring strong multilingual capabilities, supporting English and Korean, and providing an efficient and compact solution."
+ "qwq": {
+ "description": "QwQ is an experimental research model focused on improving AI reasoning capabilities."
+ },
+ "qwq-32b": {
+ "description": "The QwQ inference model is trained based on the Qwen2.5-32B model, significantly enhancing its reasoning capabilities through reinforcement learning. The core metrics of the model, including mathematical code (AIME 24/25, LiveCodeBench) and some general metrics (IFEval, LiveBench, etc.), reach the level of the full version of DeepSeek-R1, with all metrics significantly surpassing those of DeepSeek-R1-Distill-Qwen-32B, which is also based on Qwen2.5-32B."
},
- "solar-1-mini-chat-ja": {
+ "qwq-32b-preview": {
+ "description": "The QwQ model is an experimental research model developed by the Qwen team, focusing on enhancing AI reasoning capabilities."
+ },
+ "qwq-plus-latest": {
+ "description": "The QwQ inference model is trained based on the Qwen2.5 model, significantly enhancing its reasoning capabilities through reinforcement learning. The core metrics of the model, including mathematical code (AIME 24/25, LiveCodeBench) and some general metrics (IFEval, LiveBench, etc.), reach the level of the full version of DeepSeek-R1."
+ },
+ "r1-1776": {
+ "description": "R1-1776 is a version of the DeepSeek R1 model, fine-tuned to provide unfiltered, unbiased factual information."
+ },
+ "solar-mini": {
+ "description": "Solar Mini is a compact LLM that outperforms GPT-3.5, featuring strong multilingual capabilities and supporting English and Korean, providing an efficient and compact solution."
+ },
+ "solar-mini-ja": {
"description": "Solar Mini (Ja) extends the capabilities of Solar Mini, focusing on Japanese while maintaining efficiency and excellent performance in English and Korean usage."
},
"solar-pro": {
"description": "Solar Pro is a highly intelligent LLM launched by Upstage, focusing on single-GPU instruction-following capabilities, with an IFEval score above 80. Currently supports English, with a formal version planned for release in November 2024, which will expand language support and context length."
},
+ "sonar": {
+ "description": "A lightweight search product based on contextual search, faster and cheaper than Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research conducts comprehensive expert-level studies and synthesizes them into accessible, actionable reports."
+ },
+ "sonar-pro": {
+ "description": "An advanced search product that supports contextual search, advanced queries, and follow-ups."
+ },
+ "sonar-reasoning": {
+ "description": "A new API product powered by the DeepSeek reasoning model."
+ },
+ "sonar-reasoning-pro": {
+ "description": "A new API product powered by the DeepSeek reasoning model."
+ },
"step-1-128k": {
"description": "Balances performance and cost, suitable for general scenarios."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "High-speed model, suitable for real-time dialogues."
},
+ "step-1.5v-mini": {
+ "description": "This model has powerful video understanding capabilities."
+ },
+ "step-1o-turbo-vision": {
+ "description": "This model has powerful image understanding capabilities, outperforming 1o in mathematical and coding fields. The model is smaller than 1o and has a faster output speed."
+ },
+ "step-1o-vision-32k": {
+ "description": "This model possesses powerful image understanding capabilities. Compared to the step-1v series models, it offers enhanced visual performance."
+ },
"step-1v-32k": {
"description": "Supports visual input, enhancing multimodal interaction experiences."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Supports large-scale context interactions, suitable for complex dialogue scenarios."
},
+ "step-2-mini": {
+ "description": "A high-speed large model based on the next-generation self-developed Attention architecture MFA, achieving results similar to step-1 at a very low cost, while maintaining higher throughput and faster response times. It is capable of handling general tasks and has specialized skills in coding."
+ },
"taichu_llm": {
"description": "The ZD Taichu language model possesses strong language understanding capabilities and excels in text creation, knowledge Q&A, code programming, mathematical calculations, logical reasoning, sentiment analysis, and text summarization. It innovatively combines large-scale pre-training with rich knowledge from multiple sources, continuously refining algorithmic techniques and absorbing new knowledge in vocabulary, structure, grammar, and semantics from vast text data, resulting in an evolving model performance. It provides users with more convenient information and services, as well as a more intelligent experience."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V integrates capabilities such as image understanding, knowledge transfer, and logical reasoning, excelling in the field of image-text question answering."
+ "taichu_vl": {
+ "description": "Integrates capabilities in image understanding, knowledge transfer, and logical attribution, excelling in the field of image-text question answering."
+ },
+ "text-embedding-3-large": {
+ "description": "The most powerful vectorization model, suitable for both English and non-English tasks."
+ },
+ "text-embedding-3-small": {
+ "description": "An efficient and cost-effective next-generation embedding model, suitable for knowledge retrieval, RAG applications, and more."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "The open-source version of the latest generation pre-trained model from the GLM-4 series released by Zhiyuan AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) provides enhanced computational capabilities through efficient strategies and model architecture."
},
+ "tts-1": {
+ "description": "The latest text-to-speech model, optimized for speed in real-time scenarios."
+ },
+ "tts-1-hd": {
+ "description": "The latest text-to-speech model, optimized for quality."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) is suitable for refined instruction tasks, offering excellent language processing capabilities."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet raises the industry standard, outperforming competitor models and Claude 3 Opus, excelling in a wide range of evaluations while maintaining the speed and cost of our mid-tier models."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 Sonnet is Anthropic's fastest next-generation model. Compared to Claude 3 Haiku, Claude 3.7 Sonnet shows improvements across various skills and surpasses the previous generation's largest model, Claude 3 Opus, in many intelligence benchmark tests."
+ },
+ "whisper-1": {
+ "description": "A universal speech recognition model that supports multilingual speech recognition, speech translation, and language identification."
+ },
"wizardlm2": {
"description": "WizardLM 2 is a language model provided by Microsoft AI, excelling in complex dialogues, multilingual capabilities, reasoning, and intelligent assistant applications."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Exceptional performance at a high cost-performance ratio. Conducts high-precision tuning based on performance, inference speed, and cost."
},
+ "yi-lightning": {
+ "description": "The latest high-performance model, ensuring high-quality output while significantly improving reasoning speed."
+ },
+ "yi-lightning-lite": {
+ "description": "A lightweight version, recommended to use yi-lightning."
+ },
"yi-medium": {
"description": "Medium-sized model upgraded and fine-tuned, balanced capabilities, and high cost-performance ratio. Deeply optimized instruction-following capabilities."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Model for complex visual tasks, providing high-performance image understanding and analysis capabilities."
+ },
+ "yi-vision-v2": {
+ "description": "A complex visual task model that provides high-performance understanding and analysis capabilities based on multiple images."
}
}
diff --git a/DigitalHumanWeb/locales/en-US/plugin.json b/DigitalHumanWeb/locales/en-US/plugin.json
index 081cb29..d19da4a 100644
--- a/DigitalHumanWeb/locales/en-US/plugin.json
+++ b/DigitalHumanWeb/locales/en-US/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Failed to refresh plugin {{name}}",
"urlError": "The link did not return content in JSON format. Please ensure it is a valid link."
},
+ "inspector": {
+ "args": "View parameter list",
+ "pluginRender": "View plugin interface"
+ },
"list": {
"item": {
"deprecated.title": "Deleted",
@@ -130,6 +134,34 @@
"plugin": "Plugin is running..."
},
"pluginList": "Plugin List",
+ "search": {
+ "config": {
+ "addKey": "Add Key",
+ "close": "Delete",
+ "confirm": "Configuration completed, please retry"
+ },
+ "crawPages": {
+ "crawling": "Identifying links",
+ "detail": {
+ "preview": "Preview",
+ "raw": "Raw text",
+ "tooLong": "The text content is too long; only the first {{characters}} characters of the conversation context will be retained, and the excess will not be included in the conversation context."
+ },
+ "meta": {
+ "crawler": "Crawling Mode",
+ "words": "Character count"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Please enter",
+ "description": "Enter the URL for SearchXNG to start online searching",
+ "keyPlaceholder": "Please enter key",
+ "title": "Configure SearchXNG Search Engine",
+ "unconfiguredDesc": "Please contact the administrator to complete the SearchXNG search engine configuration to start online searching",
+ "unconfiguredTitle": "SearchXNG search engine not configured yet"
+ },
+ "title": "Online Search"
+ },
"setting": "Plugin Settings",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/en-US/portal.json b/DigitalHumanWeb/locales/en-US/portal.json
index a02b51c..83cb546 100644
--- a/DigitalHumanWeb/locales/en-US/portal.json
+++ b/DigitalHumanWeb/locales/en-US/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Plugins",
- "actions": {
- "genAiMessage": "Generate Assistant Message",
- "summary": "Summary",
- "summaryTooltip": "Summarize current content"
- },
"artifacts": {
"display": {
"code": "Code",
diff --git a/DigitalHumanWeb/locales/en-US/providers.json b/DigitalHumanWeb/locales/en-US/providers.json
index e1976ae..67c0019 100644
--- a/DigitalHumanWeb/locales/en-US/providers.json
+++ b/DigitalHumanWeb/locales/en-US/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs builds foundational models and AI systems for enterprises, accelerating the application of generative AI in production."
+ },
"ai360": {
"description": "360 AI is an AI model and service platform launched by 360 Company, offering various advanced natural language processing models, including 360GPT2 Pro, 360GPT Pro, 360GPT Turbo, and 360GPT Turbo Responsibility 8K. These models combine large-scale parameters and multimodal capabilities, widely applied in text generation, semantic understanding, dialogue systems, and code generation. With flexible pricing strategies, 360 AI meets diverse user needs, supports developer integration, and promotes the innovation and development of intelligent applications."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure offers a variety of advanced AI models, including GPT-3.5 and the latest GPT-4 series, supporting various data types and complex tasks, dedicated to secure, reliable, and sustainable AI solutions."
},
+ "azureai": {
+ "description": "Azure offers a variety of advanced AI models, including GPT-3.5 and the latest GPT-4 series, supporting multiple data types and complex tasks, dedicated to secure, reliable, and sustainable AI solutions."
+ },
"baichuan": {
"description": "Baichuan Intelligence is a company focused on the research and development of large AI models, with its models excelling in domestic knowledge encyclopedias, long text processing, and generative creation tasks in Chinese, surpassing mainstream foreign models. Baichuan Intelligence also possesses industry-leading multimodal capabilities, performing excellently in multiple authoritative evaluations. Its models include Baichuan 4, Baichuan 3 Turbo, and Baichuan 3 Turbo 128k, each optimized for different application scenarios, providing cost-effective solutions."
},
"bedrock": {
"description": "Bedrock is a service provided by Amazon AWS, focusing on delivering advanced AI language and visual models for enterprises. Its model family includes Anthropic's Claude series, Meta's Llama 3.1 series, and more, offering a range of options from lightweight to high-performance, supporting tasks such as text generation, conversation, and image processing for businesses of varying scales and needs."
},
+ "cloudflare": {
+ "description": "Run serverless GPU-powered machine learning models on Cloudflare's global network."
+ },
"deepseek": {
"description": "DeepSeek is a company focused on AI technology research and application, with its latest model DeepSeek-V2.5 integrating general dialogue and code processing capabilities, achieving significant improvements in human preference alignment, writing tasks, and instruction following."
},
+ "doubao": {
+ "description": "A self-developed large model launched by ByteDance. Verified through practical applications in over 50 internal business scenarios, it continuously refines its capabilities with a daily usage of trillions of tokens, providing various modal abilities to create a rich business experience for enterprises with high-quality model performance."
+ },
"fireworksai": {
"description": "Fireworks AI is a leading provider of advanced language model services, focusing on functional calling and multimodal processing. Its latest model, Firefunction V2, is based on Llama-3, optimized for function calling, conversation, and instruction following. The visual language model FireLLaVA-13B supports mixed input of images and text. Other notable models include the Llama series and Mixtral series, providing efficient multilingual instruction following and generation support."
},
+ "giteeai": {
+ "description": "Gitee AI's Serverless API provides AI developers with an out of the box large model inference API service."
+ },
"github": {
"description": "With GitHub Models, developers can become AI engineers and leverage the industry's leading AI models."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Groq's LPU inference engine has excelled in the latest independent large language model (LLM) benchmarks, redefining the standards for AI solutions with its remarkable speed and efficiency. Groq represents instant inference speed, demonstrating strong performance in cloud-based deployments."
},
+ "higress": {
+ "description": "Higress is a cloud-native API gateway that was developed internally at Alibaba to address the issues of Tengine reload affecting long-lived connections and the insufficient load balancing capabilities for gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "The HuggingFace Inference API provides a fast and free way for you to explore thousands of models for various tasks. Whether you are prototyping for a new application or experimenting with the capabilities of machine learning, this API gives you instant access to high-performance models across multiple domains."
+ },
+ "hunyuan": {
+ "description": "A large language model developed by Tencent, equipped with powerful Chinese creative capabilities, logical reasoning abilities in complex contexts, and reliable task execution skills."
+ },
+ "internlm": {
+ "description": "An open-source organization dedicated to the research and development of large model toolchains. It provides an efficient and user-friendly open-source platform for all AI developers, making cutting-edge large models and algorithm technologies easily accessible."
+ },
+ "jina": {
+ "description": "Founded in 2020, Jina AI is a leading search AI company. Our search base platform includes vector models, rerankers, and small language models to help businesses build reliable and high-quality generative AI and multimodal search applications."
+ },
+ "lmstudio": {
+ "description": "LM Studio is a desktop application for developing and experimenting with LLMs on your computer."
+ },
"minimax": {
"description": "MiniMax is a general artificial intelligence technology company established in 2021, dedicated to co-creating intelligence with users. MiniMax has independently developed general large models of different modalities, including trillion-parameter MoE text models, voice models, and image models, and has launched applications such as Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI is a platform providing a variety of large language models and AI image generation API services, flexible, reliable, and cost-effective. It supports the latest open-source models like Llama3 and Mistral, offering a comprehensive, user-friendly, and auto-scaling API solution for generative AI application development, suitable for the rapid growth of AI startups."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ provides containers for self-hosted GPU-accelerated inference microservices, supporting the deployment of pre-trained and custom AI models in the cloud, data centers, RTX™ AI personal computers, and workstations."
+ },
"ollama": {
"description": "Ollama provides models that cover a wide range of fields, including code generation, mathematical operations, multilingual processing, and conversational interaction, catering to diverse enterprise-level and localized deployment needs."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity is a leading provider of conversational generation models, offering various advanced Llama 3.1 models that support both online and offline applications, particularly suited for complex natural language processing tasks."
},
+ "ppio": {
+ "description": "PPIO supports stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc."
+ },
"qwen": {
"description": "Tongyi Qianwen is a large-scale language model independently developed by Alibaba Cloud, featuring strong natural language understanding and generation capabilities. It can answer various questions, create written content, express opinions, and write code, playing a role in multiple fields."
},
+ "sambanova": {
+ "description": "SambaNova Cloud allows developers to easily utilize the best open-source models and enjoy the fastest inference speeds."
+ },
+ "sensenova": {
+ "description": "SenseNova, backed by SenseTime's robust infrastructure, offers efficient and user-friendly full-stack large model services."
+ },
"siliconcloud": {
"description": "SiliconFlow is dedicated to accelerating AGI for the benefit of humanity, enhancing large-scale AI efficiency through an easy-to-use and cost-effective GenAI stack."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "The Institute of Automation, Chinese Academy of Sciences, and Wuhan Artificial Intelligence Research Institute have launched a new generation of multimodal large models, supporting comprehensive question-answering tasks such as multi-turn Q&A, text creation, image generation, 3D understanding, and signal analysis, with stronger cognitive, understanding, and creative abilities, providing a new interactive experience."
},
+ "tencentcloud": {
+ "description": "The Knowledge Engine Atomic Power, based on the Knowledge Engine, provides a comprehensive knowledge Q&A capability for enterprises and developers. It offers the ability to flexibly assemble and develop model applications. You can create your own model services using various atomic capabilities, integrating services such as document parsing, splitting, embedding, and multi-turn rewriting to customize AI solutions tailored to your business."
+ },
"togetherai": {
"description": "Together AI is dedicated to achieving leading performance through innovative AI models, offering extensive customization capabilities, including rapid scaling support and intuitive deployment processes to meet various enterprise needs."
},
"upstage": {
"description": "Upstage focuses on developing AI models for various business needs, including Solar LLM and document AI, aiming to achieve artificial general intelligence (AGI) for work. It allows for the creation of simple conversational agents through Chat API and supports functional calling, translation, embedding, and domain-specific applications."
},
+ "vertexai": {
+ "description": "Google's Gemini series is its most advanced and versatile AI model, developed by Google DeepMind. It is designed for multimodal use, supporting seamless understanding and processing of text, code, images, audio, and video. Suitable for a variety of environments, from data centers to mobile devices, it significantly enhances the efficiency and applicability of AI models."
+ },
+ "vllm": {
+ "description": "vLLM is a fast and easy-to-use library for LLM inference and serving."
+ },
+ "volcengine": {
+ "description": "A development platform for large model services launched by ByteDance, offering feature-rich, secure, and competitively priced model invocation services. It also provides end-to-end functionalities such as model data, fine-tuning, inference, and evaluation, ensuring comprehensive support for the development and implementation of your AI applications."
+ },
+ "wenxin": {
+ "description": "An enterprise-level one-stop platform for large model and AI-native application development and services, providing the most comprehensive and user-friendly toolchain for the entire process of generative artificial intelligence model development and application development."
+ },
+ "xai": {
+ "description": "xAI is a company dedicated to building artificial intelligence to accelerate human scientific discovery. Our mission is to advance our collective understanding of the universe."
+ },
"zeroone": {
"description": "01.AI focuses on AI 2.0 era technologies, vigorously promoting the innovation and application of 'human + artificial intelligence', using powerful models and advanced AI technologies to enhance human productivity and achieve technological empowerment."
},
diff --git a/DigitalHumanWeb/locales/en-US/setting.json b/DigitalHumanWeb/locales/en-US/setting.json
index 2395ed1..7793058 100644
--- a/DigitalHumanWeb/locales/en-US/setting.json
+++ b/DigitalHumanWeb/locales/en-US/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Custom Model Configuration",
"tokens": {
- "title": "Maximum Token Count",
- "unlimited": "unlimited"
+ "title": "Maximum Token Count"
},
"vision": {
"extra": "This configuration will only enable image upload capabilities within the application. Whether recognition is supported depends entirely on the model itself; please test the model's visual recognition capabilities on your own.",
@@ -98,6 +97,7 @@
"title": "Use Client-Side Fetching Mode"
},
"fetcher": {
+ "clear": "Clear fetched model",
"fetch": "Get Model List",
"fetching": "Fetching Model List...",
"latestTime": "Last Updated: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Whether to automatically create a topic during the conversation, only effective in temporary topics",
"title": "Auto Create Topic"
},
- "enableCompressThreshold": {
- "title": "Enable History Message Length Compression Threshold"
+ "enableCompressHistory": {
+ "title": "Enable Automatic Summary of Chat History"
},
"enableHistoryCount": {
"alias": "Unlimited",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Enable Max Tokens Limit"
},
+ "enableReasoningEffort": {
+ "title": "Enable Reasoning Effort Adjustment"
+ },
"frequencyPenalty": {
- "desc": "The higher the value, the more likely it is to reduce repeated words",
- "title": "Frequency Penalty"
+ "desc": "The higher the value, the more diverse and rich the vocabulary; the lower the value, the simpler and more straightforward the language.",
+ "title": "Vocabulary Richness"
},
"maxTokens": {
"desc": "The maximum number of tokens used for each interaction",
@@ -212,19 +215,31 @@
"desc": "{{provider}} model",
"title": "Model"
},
+ "params": {
+ "title": "Advanced Parameters"
+ },
"presencePenalty": {
- "desc": "The higher the value, the more likely it is to expand to new topics",
- "title": "Topic Freshness"
+ "desc": "The higher the value, the more inclined to use different expressions and avoid concept repetition; the lower the value, the more inclined to use repeated concepts or narratives, resulting in more consistent expression.",
+ "title": "Expression Divergence"
+ },
+ "reasoningEffort": {
+ "desc": "The higher the value, the stronger the reasoning ability, but it may increase response time and token consumption.",
+ "options": {
+ "high": "High",
+ "low": "Low",
+ "medium": "Medium"
+ },
+ "title": "Reasoning Effort"
},
"temperature": {
- "desc": "The higher the value, the more random the response",
- "title": "Randomness",
- "titleWithValue": "Randomness {{value}}"
+ "desc": "The higher the value, the more creative and imaginative the responses; the lower the value, the more rigorous the responses.",
+ "title": "Creativity Level",
+ "warning": "If the creativity level is set too high, the output may become garbled."
},
"title": "Model Settings",
"topP": {
- "desc": "Similar to randomness, but do not change together with randomness",
- "title": "Top P Sampling"
+ "desc": "How many possibilities to consider; a higher value accepts more potential answers, while a lower value tends to choose the most likely answer. It is not recommended to change this alongside the creativity level.",
+ "title": "Openness to Ideas"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Model designated for generating assistant name, description, avatar, and tags",
"title": "Automatically Generate Assistant Information"
},
+ "customPrompt": {
+ "addPrompt": "Add Custom Prompt",
+ "desc": "Once filled out, the system assistant will use the custom prompt when generating content",
+ "placeholder": "Please enter custom prompt",
+ "title": "Custom Prompt"
+ },
+ "historyCompress": {
+ "label": "Conversation History Model",
+ "modelDesc": "Specify the model used to compress conversation history",
+ "title": "Automatically Summarize Conversation History"
+ },
"queryRewrite": {
"label": "Question Rewriting Model",
"modelDesc": "Specify the model used to optimize user inquiries",
- "title": "Knowledge Base"
+ "title": "Knowledge Base Question Rewrite"
+ },
+ "thread": {
+ "label": "Subtopic Naming Model",
+ "modelDesc": "The model designated for automatic renaming of subtopics",
+ "title": "Automatic Subtopic Naming"
},
"title": "System Assistants",
"topic": {
@@ -395,6 +426,7 @@
"common": "Common Settings",
"experiment": "Experiment",
"llm": "Language Model",
+ "provider": "AI Service Provider",
"sync": "Cloud Sync",
"system-agent": "System Assistant",
"tts": "Text-to-Speech"
diff --git a/DigitalHumanWeb/locales/en-US/thread.json b/DigitalHumanWeb/locales/en-US/thread.json
new file mode 100644
index 0000000..0136c51
--- /dev/null
+++ b/DigitalHumanWeb/locales/en-US/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "You are about to delete this subtopic. Once deleted, it cannot be recovered. Please proceed with caution."
+ },
+ "newPortalThread": {
+ "includeContext": "Include topic context",
+ "title": "Start a new subtopic"
+ },
+ "notSupportMultiModals": "Subtopics do not currently support file/image uploads. If you have any requests, feel free to leave a message: <1>💬 Discussion Area1>"
+}
diff --git a/DigitalHumanWeb/locales/en-US/tool.json b/DigitalHumanWeb/locales/en-US/tool.json
index 75d75ce..0798577 100644
--- a/DigitalHumanWeb/locales/en-US/tool.json
+++ b/DigitalHumanWeb/locales/en-US/tool.json
@@ -6,5 +6,23 @@
"generating": "Generating...",
"images": "Images:",
"prompt": "Prompt"
+ },
+ "search": {
+ "createNewSearch": "Create a new search record",
+ "emptyResult": "No results found, please modify your keywords and try again",
+ "genAiMessage": "Create Assistant Message",
+ "includedTooltip": "The current search results will be included in the context of the conversation",
+ "keywords": "Keywords:",
+ "scoreTooltip": "Relevance score; a higher score indicates a closer match to the query keywords",
+ "searchBar": {
+ "button": "Search",
+ "placeholder": "Keywords",
+ "tooltip": "This will refresh the search results and create a new summary message"
+ },
+ "searchEngine": "Search engine:",
+ "searchResult": "Number of searches:",
+ "summary": "Summary",
+ "summaryTooltip": "Summarize the current content",
+ "viewMoreResults": "View {{results}} more results"
}
}
diff --git a/DigitalHumanWeb/locales/en-US/topic.json b/DigitalHumanWeb/locales/en-US/topic.json
new file mode 100644
index 0000000..7acd6cf
--- /dev/null
+++ b/DigitalHumanWeb/locales/en-US/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Smart Rename",
+ "confirmRemoveAll": "You are about to delete all topics. This action cannot be undone, please proceed with caution.",
+ "confirmRemoveTopic": "You are about to delete this topic. This action cannot be undone, please proceed with caution.",
+ "confirmRemoveUnstarred": "You are about to delete unstarred topics. This action cannot be undone, please proceed with caution.",
+ "duplicate": "Create Copy",
+ "export": "Export Topics",
+ "removeAll": "Delete All Topics",
+ "removeUnstarred": "Delete Unstarred Topics"
+ },
+ "defaultTitle": "Default Topic",
+ "duplicateLoading": "Copying Topic...",
+ "duplicateSuccess": "Topic Copied Successfully",
+ "favorite": "Favorite",
+ "groupMode": {
+ "ascMessages": "Sort by Total Messages Ascending",
+ "byTime": "Group by Time",
+ "descMessages": "Sort by Total Messages Descending",
+ "flat": "No Grouping"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "This Month",
+ "today": "Today",
+ "week": "This Week",
+ "yesterday": "Yesterday"
+ }
+ },
+ "guide": {
+ "desc": "Click the button on the left to save the current conversation as a historical topic and start a new conversation.",
+ "title": "Topic List"
+ },
+ "searchPlaceholder": "Search Topics...",
+ "searchResultEmpty": "No search results found.",
+ "temp": "Temporary",
+ "title": "Topic"
+}
diff --git a/DigitalHumanWeb/locales/en-US/welcome.json b/DigitalHumanWeb/locales/en-US/welcome.json
index 1b4bc23..741027d 100644
--- a/DigitalHumanWeb/locales/en-US/welcome.json
+++ b/DigitalHumanWeb/locales/en-US/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Import Configuration",
- "market": "Visit Market",
- "start": "Start Now"
- },
"guide": {
"agents": {
"replaceBtn": "Replace Batch",
diff --git a/DigitalHumanWeb/locales/es-ES/auth.json b/DigitalHumanWeb/locales/es-ES/auth.json
index f62b326..760c3f7 100644
--- a/DigitalHumanWeb/locales/es-ES/auth.json
+++ b/DigitalHumanWeb/locales/es-ES/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Último mes",
+ "recent30Days": "Últimos 30 días"
+ },
+ "header": {
+ "desc": "Gestiona la información de tu cuenta.",
+ "title": "Cuenta"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Inactivo",
+ "more": "Activo"
+ },
+ "months": {
+ "apr": "Abr",
+ "aug": "Ago",
+ "dec": "Dic",
+ "feb": "Feb",
+ "jan": "Ene",
+ "jul": "Jul",
+ "jun": "Jun",
+ "mar": "Mar",
+ "may": "May",
+ "nov": "Nov",
+ "oct": "Oct",
+ "sep": "Sep"
+ },
+ "tooltip": "{{date}} envió {{count}} mensajes ese día",
+ "totalCount": "Un total de {{count}} mensajes enviados en el último año"
+ },
"login": "Iniciar sesión",
"loginOrSignup": "Iniciar sesión / Registrarse",
- "profile": "Perfil",
- "security": "Seguridad",
+ "profile": {
+ "avatar": "Avatar",
+ "email": "Dirección de correo electrónico",
+ "sso": {
+ "loading": "Cargando cuentas de terceros vinculadas",
+ "providers": "Cuentas conectadas",
+ "unlink": {
+ "description": "Al desvincular, no podrá iniciar sesión con la cuenta de {{provider}} \"{{providerAccountId}}\". Si necesita volver a vincular la cuenta de {{provider}} a la cuenta actual, asegúrese de que la dirección de correo electrónico de la cuenta {{provider}} sea {{email}} y la vincularemos automáticamente a la cuenta actual al iniciar sesión.",
+ "forbidden": "Debe conservar al menos una cuenta de terceros vinculada.",
+ "title": "¿Desea desvincular la cuenta de terceros {{provider}}?"
+ }
+ },
+ "username": "Nombre de usuario"
+ },
"signout": "Cerrar sesión",
- "signup": "Registrarse"
+ "signup": "Registrarse",
+ "stats": {
+ "aiheatmaps": "Índice de Actividad",
+ "assistants": "Asistentes",
+ "assistantsRank": {
+ "left": "Asistente",
+ "right": "Temas",
+ "title": "Clasificación de Uso de Asistentes"
+ },
+ "createdAt": "Registrado en",
+ "days": "días",
+ "empty": {
+ "desc": "Por favor, acumula más datos de chat para ver",
+ "title": "Sin datos"
+ },
+ "lastYearActivity": "actividad en el último año",
+ "loginGuide": {
+ "f1": "Obtener uso gratuito",
+ "f2": "Sincronizar mensajes en múltiples dispositivos",
+ "f3": "Tener un asistente completo",
+ "f4": "Explorar potentes complementos",
+ "title": "Después de iniciar sesión, puedes:"
+ },
+ "messages": "Mensajes",
+ "modelsRank": {
+ "left": "Modelo",
+ "right": "Mensajes",
+ "title": "Clasificación de Uso de Modelos"
+ },
+ "share": {
+ "title": "Mi Índice de Actividad AI"
+ },
+ "topics": "Temas",
+ "topicsRank": {
+ "left": "Tema",
+ "right": "Mensajes",
+ "title": "Clasificación de Contenido de Temas"
+ },
+ "updatedAt": "Actualizado en",
+ "welcome": "{{username}}, este es tu {{days}} día con {{appName}}",
+ "words": "Palabras"
+ },
+ "tab": {
+ "profile": "Perfil",
+ "security": "Seguridad",
+ "stats": "Estadísticas"
+ }
}
diff --git a/DigitalHumanWeb/locales/es-ES/changelog.json b/DigitalHumanWeb/locales/es-ES/changelog.json
new file mode 100644
index 0000000..c289032
--- /dev/null
+++ b/DigitalHumanWeb/locales/es-ES/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Síguenos en X",
+ "subscribeToUpdates": "Suscríbete a las actualizaciones",
+ "versions": "Detalles de la versión"
+ },
+ "addedWhileAway": "Hemos traído nuevas características mientras estabas ausente.",
+ "allChangelog": "Ver todos los registros de cambios",
+ "description": "Sigue las nuevas funciones y mejoras de {{appName}}",
+ "pagination": {
+ "next": "Siguiente página",
+ "older": "Ver cambios anteriores"
+ },
+ "readDetails": "Leer detalles",
+ "title": "Registro de cambios",
+ "versionDetails": "Detalles de la versión",
+ "welcomeBack": "¡Bienvenido de nuevo!"
+}
diff --git a/DigitalHumanWeb/locales/es-ES/chat.json b/DigitalHumanWeb/locales/es-ES/chat.json
index a1cc602..27326a1 100644
--- a/DigitalHumanWeb/locales/es-ES/chat.json
+++ b/DigitalHumanWeb/locales/es-ES/chat.json
@@ -8,6 +8,7 @@
"agents": "Asistente",
"artifact": {
"generating": "Generando",
+ "inThread": "No se puede ver en el subtema, cambie a la zona de conversación principal para abrirlo",
"thinking": "Pensando",
"thought": "Proceso de pensamiento",
"unknownTitle": "Obra sin título"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Copia",
"emptyAgent": "No hay asistente disponible",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "El costo de generación de una sola conversación puede reducirse hasta en un 90%, y la velocidad de respuesta se incrementa 4 veces (<1>Más información1>). Al activarlo, se desactivará automáticamente el límite de mensajes históricos",
+ "title": "Activar caché de contexto"
+ },
+ "enableReasoning": {
+ "desc": "Basado en las restricciones del mecanismo Claude Thinking (<1>Más información1>), al activarlo se desactivará automáticamente el límite de mensajes históricos",
+ "title": "Activar el pensamiento profundo"
+ },
+ "reasoningBudgetToken": {
+ "title": "Token de consumo de pensamiento"
+ },
+ "title": "Funcionalidad de extensión del modelo"
+ },
+ "history": {
+ "title": "El asistente solo recordará los últimos {{count}} mensajes"
+ },
"historyRange": "Rango de historial",
+ "historySummary": "Resumen de mensajes históricos",
"inbox": {
"desc": "Despierta la mente con el poder del cerebro colectivo. Tu asistente inteligente está aquí para conversar contigo sobre cualquier cosa.",
"title": "Charla casual"
@@ -45,6 +64,9 @@
"stop": "Detener",
"warp": "Salto de línea"
},
+ "intentUnderstanding": {
+ "title": "Entendiendo y analizando su intención..."
+ },
"knowledgeBase": {
"all": "Todo el contenido",
"allFiles": "Todos los archivos",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Eliminar y Regenerar",
+ "deleteDisabledByThreads": "Existen subtemas, no se puede eliminar",
"regenerate": "Regenerar"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Créditos",
+ "creditPricing": "Precios",
+ "creditTooltip": "Para facilitar el conteo, convertimos 1$ en 1M créditos, por ejemplo, $3/M tokens se convierte en 3 créditos/token",
+ "pricing": {
+ "inputCachedTokens": "Entradas en caché {{amount}}/créditos · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M caracteres",
+ "inputMinutes": "${{amount}}/minuto",
+ "inputTokens": "Entradas {{amount}}/créditos · ${{amount}}/M",
+ "outputTokens": "Salidas {{amount}}/créditos · ${{amount}}/M",
+ "writeCacheInputTokens": "Escritura en caché de entrada {{amount}}/puntos · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Precio promedio",
+ "input": "Entrada",
+ "inputAudio": "Entrada de audio",
+ "inputCached": "Entrada en caché",
+ "inputCitation": "Citación de entrada",
+ "inputText": "Entrada de texto",
+ "inputTitle": "Detalles de entrada",
+ "inputUncached": "Entrada no en caché",
+ "inputWriteCached": "Escritura en caché de entrada",
+ "output": "Salida",
+ "outputAudio": "Salida de audio",
+ "outputText": "Salida de texto",
+ "outputTitle": "Detalles de salida",
+ "reasoning": "Razonamiento profundo",
+ "title": "Detalles de generación",
+ "total": "Total consumido"
+ }
+ },
"newAgent": "Nuevo asistente",
"pin": "Fijar",
"pinOff": "Desfijar",
@@ -81,6 +137,32 @@
},
"regenerate": "Regenerar",
"roleAndArchive": "Rol y archivo",
+ "search": {
+ "grounding": {
+ "searchQueries": "Palabras clave de búsqueda",
+ "title": "Se han encontrado {{count}} resultados"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Determina inteligentemente si se necesita buscar según el contenido de la conversación",
+ "title": "Conexión inteligente"
+ },
+ "off": {
+ "desc": "Utiliza solo el conocimiento básico del modelo, sin realizar búsquedas en línea",
+ "title": "Desactivar conexión"
+ },
+ "on": {
+ "desc": "Realiza búsquedas en línea continuamente para obtener la información más reciente",
+ "title": "Siempre conectado"
+ },
+ "useModelBuiltin": "Utilizar el motor de búsqueda integrado del modelo"
+ },
+ "searchModel": {
+ "desc": "El modelo actual no admite llamadas a funciones, por lo que se necesita combinarlo con un modelo que admita llamadas a funciones para realizar búsquedas en línea",
+ "title": "Modelo de búsqueda auxiliar"
+ },
+ "title": "Búsqueda en línea"
+ },
"searchAgentPlaceholder": "Asistente de búsqueda...",
"sendPlaceholder": "Escribe tu mensaje...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "El nombre del grupo debe tener entre 1 y 20 caracteres"
},
"shareModal": {
+ "copy": "Copiar",
"download": "Descargar captura de pantalla",
+ "downloadFile": "Descargar archivo",
+ "exportTitle": "Título predeterminado",
"imageType": "Tipo de imagen",
+ "includeTool": "Incluir mensajes de herramientas",
+ "includeUser": "Incluir mensajes de usuario",
"screenshot": "Captura de pantalla",
"settings": "Configuración de exportación",
- "shareToShareGPT": "Generar enlace de compartición ShareGPT",
+ "text": "Texto",
"withBackground": "Incluir imagen de fondo",
"withFooter": "Incluir pie de página",
"withPluginInfo": "Incluir información del plugin",
+ "withRole": "Incluir rol de mensaje",
"withSystemRole": "Incluir configuración de rol del asistente"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Reconociendo...",
"prettifying": "Embelleciendo..."
},
- "temp": "Temporal",
+ "thread": {
+ "divider": "Subtema",
+ "threadMessageCount": "{{messageCount}} mensajes",
+ "title": "Subtema"
+ },
"tokenDetails": {
"chats": "Mensajes de chat",
+ "historySummary": "Resumen histórico",
"rest": "Restante",
"systemRole": "Rol del sistema",
"title": "Detalles del token",
@@ -131,29 +224,10 @@
"used": "Usado"
},
"topic": {
- "actions": {
- "autoRename": "Renombrar automáticamente",
- "duplicate": "Crear copia",
- "export": "Exportar tema"
- },
"checkOpenNewTopic": "¿Abrir un nuevo tema?",
"checkSaveCurrentMessages": "¿Desea guardar la conversación actual como tema?",
- "confirmRemoveAll": "Estás a punto de eliminar todos los temas. Una vez eliminados, no se podrán recuperar. Por favor, procede con precaución.",
- "confirmRemoveTopic": "Estás a punto de eliminar este tema. Una vez eliminado, no se podrá recuperar. Por favor, procede con precaución.",
- "confirmRemoveUnstarred": "Estás a punto de eliminar los temas no marcados como favoritos. Una vez eliminados, no se podrán recuperar. Por favor, procede con precaución.",
- "defaultTitle": "Tema predeterminado",
- "duplicateLoading": "Duplicando tema...",
- "duplicateSuccess": "Tema duplicado exitosamente",
- "guide": {
- "desc": "Haz clic en el botón izquierdo para guardar la conversación actual como un tema histórico y comenzar una nueva sesión",
- "title": "Lista de temas"
- },
"openNewTopic": "Abrir nuevo tema",
- "removeAll": "Eliminar todos los temas",
- "removeUnstarred": "Eliminar temas no marcados como favoritos",
- "saveCurrentMessages": "Guardar la conversación actual como tema",
- "searchPlaceholder": "Buscar temas...",
- "title": "Lista de temas"
+ "saveCurrentMessages": "Guardar la conversación actual como tema"
},
"translate": {
"action": "Traducir",
@@ -184,5 +258,6 @@
"processing": "Procesando archivo..."
}
}
- }
+ },
+ "zenMode": "Modo de concentración"
}
diff --git a/DigitalHumanWeb/locales/es-ES/common.json b/DigitalHumanWeb/locales/es-ES/common.json
index f7742da..05d56e0 100644
--- a/DigitalHumanWeb/locales/es-ES/common.json
+++ b/DigitalHumanWeb/locales/es-ES/common.json
@@ -9,15 +9,79 @@
"title": "Bienvenido a {{name}}"
}
},
- "appInitializing": "Iniciando la aplicación...",
+ "appLoading": {
+ "appIdle": "Listo para iniciar",
+ "appInitializing": "Iniciando la aplicación...",
+ "failed": "Lo siento, la inicialización de la aplicación ha fallado. Por favor, consulta los detalles para investigar.",
+ "finished": "Inicialización de la base de datos completada",
+ "goToChat": "Cargando la página de chat...",
+ "initAuth": "Inicializando el servicio de autenticación...",
+ "initUser": "Inicializando el estado del usuario...",
+ "initializing": "Inicializando la base de datos PGlite...",
+ "loadingDependencies": "Inicializando dependencias...",
+ "loadingWasm": "Cargando módulo WASM...",
+ "migrating": "Ejecutando migración de tablas de datos...",
+ "ready": "Base de datos lista",
+ "showDetail": "Ver detalles"
+ },
"autoGenerate": "Generación automática",
"autoGenerateTooltip": "Completar automáticamente la descripción del asistente basándose en las sugerencias",
"autoGenerateTooltipDisabled": "Por favor, complete la palabra clave antes de usar la función de autocompletar",
"back": "Volver",
"batchDelete": "Eliminar en lote",
"blog": "Blog de productos",
+ "branching": "Crear subtemas",
+ "branchingDisable": "La función de «subtemas» solo está disponible en la versión del servidor. Si necesita esta función, cambie al modo de implementación del servidor o utilice LobeChat Cloud.",
"cancel": "Cancelar",
"changelog": "Registro de cambios",
+ "clientDB": {
+ "autoInit": {
+ "title": "Inicializando la base de datos PGlite"
+ },
+ "error": {
+ "desc": "Lo sentimos, ha ocurrido una excepción en el proceso de inicialización de la base de datos Pglite. Por favor, haga clic en el botón para intentar de nuevo. Si después de varios intentos sigue ocurriendo el mismo error, por favor <1>envíe un problema1>, y lo resolveremos lo antes posible.",
+ "detail": "Razón del error: [{{type}}] {{message}}. Detalles a continuación:",
+ "retry": "Reintentar",
+ "title": "Falló la inicialización de la base de datos"
+ },
+ "initing": {
+ "error": "Ha ocurrido un error, por favor reintente",
+ "idle": "Esperando la inicialización...",
+ "initializing": "Inicializando...",
+ "loadingDependencies": "Cargando dependencias...",
+ "loadingWasmModule": "Cargando módulo WASM...",
+ "migrating": "Ejecutando migración de tablas de datos...",
+ "ready": "La base de datos está lista"
+ },
+ "modal": {
+ "desc": "Habilite la base de datos del cliente PGlite para almacenar de forma persistente los datos del chat en su navegador y utilizar características avanzadas como la base de conocimientos.",
+ "enable": "Habilitar ahora",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Consolida tu base de conocimientos personal y comienza conversaciones sobre ella con tu asistente fácilmente (próximamente)",
+ "title": "Soporte para conversaciones de base de conocimientos, activa tu segundo cerebro"
+ },
+ "localFirst": {
+ "desc": "Los datos de chat se almacenan completamente en el navegador, tus datos siempre están bajo tu control.",
+ "title": "Prioridad local, privacidad ante todo"
+ },
+ "pglite": {
+ "desc": "Construido sobre PGlite, soporte nativo para características avanzadas de AI Native (búsqueda vectorial)",
+ "title": "Nueva arquitectura de almacenamiento de cliente de próxima generación"
+ }
+ },
+ "init": {
+ "desc": "Inicializando la base de datos, el tiempo puede variar de 5 a 30 segundos dependiendo de la red.",
+ "title": "Inicializando la base de datos PGlite"
+ },
+ "title": "Activar la base de datos del cliente"
+ },
+ "ready": {
+ "button": "Usar ahora",
+ "desc": "Listo para usar",
+ "title": "La base de datos PGlite está lista"
+ }
+ },
"close": "Cerrar",
"contact": "Contacto",
"copy": "Copiar",
@@ -112,6 +176,7 @@
"en": "Inglés",
"en-US": "Inglés",
"es-ES": "Español",
+ "fa-IR": "persa",
"fi-FI": "finlandés",
"fr-FR": "Francés",
"hi-IN": "hindi",
@@ -153,6 +218,7 @@
"pinOff": "Quitar fijación",
"privacy": "Política de privacidad",
"regenerate": "Regenerar",
+ "releaseNotes": "Detalles de la versión",
"rename": "Renombrar",
"reset": "Restablecer",
"retry": "Reintentar",
@@ -209,6 +275,7 @@
},
"temp": "Temporal",
"terms": "Términos de servicio",
+ "update": "Actualizar",
"updateAgent": "Actualizar información del asistente",
"upgradeVersion": {
"action": "Actualizar",
@@ -219,6 +286,7 @@
"anonymousNickName": "Usuario Anónimo",
"billing": "Gestión de facturación",
"cloud": "Prueba {{name}}",
+ "community": "Versión comunitaria",
"data": "Almacenamiento de datos",
"defaultNickname": "Usuario de la comunidad",
"discord": "Soporte de la comunidad",
@@ -228,7 +296,6 @@
"help": "Centro de ayuda",
"moveGuide": "El botón de configuración se ha movido aquí",
"plans": "Planes de suscripción",
- "preview": "Vista previa",
"profile": "Gestión de cuenta",
"setting": "Configuración de la aplicación",
"usages": "Estadísticas de uso"
diff --git a/DigitalHumanWeb/locales/es-ES/components.json b/DigitalHumanWeb/locales/es-ES/components.json
index b1619b6..02b4079 100644
--- a/DigitalHumanWeb/locales/es-ES/components.json
+++ b/DigitalHumanWeb/locales/es-ES/components.json
@@ -12,6 +12,7 @@
"batchChunking": "División por lotes",
"chunking": "División",
"chunkingTooltip": "Divida el archivo en múltiples bloques de texto y vectorícelos para su uso en búsqueda semántica y diálogo de archivos",
+ "chunkingUnsupported": "Este archivo no admite la fragmentación",
"confirmDelete": "Está a punto de eliminar este archivo. Una vez eliminado, no podrá recuperarlo. Por favor, confirme su acción.",
"confirmDeleteMultiFiles": "Está a punto de eliminar los {{count}} archivos seleccionados. Una vez eliminados, no podrá recuperarlos. Por favor, confirme su acción.",
"confirmRemoveFromKnowledgeBase": "Está a punto de eliminar los {{count}} archivos seleccionados de la base de conocimientos. Los archivos seguirán siendo visibles en todos los archivos. Por favor, confirme su acción.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Regresar"
},
+ "MaxTokenSlider": {
+ "unlimited": "Sin límite"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Modelo personalizado: admite llamadas de función y reconocimiento visual. Verifique la disponibilidad de estas capacidades según sea necesario.",
"file": "Este modelo admite la carga y reconocimiento de archivos.",
"functionCall": "Este modelo admite llamadas de función.",
+ "reasoning": "Este modelo admite un pensamiento profundo",
+ "search": "Este modelo admite búsqueda en línea",
"tokens": "Este modelo admite un máximo de {{tokens}} tokens por sesión.",
"vision": "Este modelo admite el reconocimiento visual."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "No hay modelos habilitados. Vaya a la configuración para habilitarlos.",
+ "emptyProvider": "No hay proveedores habilitados, por favor ve a la configuración para activarlos",
+ "goToSettings": "Ir a la configuración",
"provider": "Proveedor"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Debido a las restricciones de seguridad del navegador, necesitas configurar CORS para Ollama antes de poder usarlo correctamente.",
+ "linux": {
+ "env": "Agrega `Environment` en la sección [Service] y añade la variable de entorno OLLAMA_ORIGINS:",
+ "reboot": "Recarga systemd y reinicia Ollama",
+ "systemd": "Usa systemd para editar el servicio de ollama:"
+ },
+ "macos": "Abre la aplicación 'Terminal', pega el siguiente comando y presiona Enter para ejecutarlo",
+ "reboot": "Reinicia el servicio de Ollama después de completar la ejecución",
+ "title": "Configura Ollama para permitir el acceso CORS",
+ "windows": "En Windows, haz clic en 'Panel de control' y entra en la edición de variables de entorno del sistema. Crea una nueva variable de entorno llamada 'OLLAMA_ORIGINS' para tu cuenta de usuario, con el valor * y haz clic en 'OK/Aplicar' para guardar."
+ },
+ "install": {
+ "description": "Asegúrate de que has iniciado Ollama. Si no has descargado Ollama, visita el sitio web oficial <1>para descargar1>.",
+ "docker": "Si prefieres usar Docker, Ollama también ofrece una imagen oficial de Docker que puedes descargar con el siguiente comando:",
+ "linux": {
+ "command": "Instala con el siguiente comando:",
+ "manual": "O también puedes consultar la <1>guía de instalación manual de Linux1> para instalarlo tú mismo."
+ },
+ "title": "Instala y ejecuta la aplicación Ollama localmente",
+ "windowsTab": "Windows (versión preliminar)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Pensando profundamente...",
+ "thought": "He pensado profundamente (durante {{duration}} segundos)",
+ "thoughtWithDuration": "He pensado profundamente"
}
}
diff --git a/DigitalHumanWeb/locales/es-ES/discover.json b/DigitalHumanWeb/locales/es-ES/discover.json
index 42386cb..1caad33 100644
--- a/DigitalHumanWeb/locales/es-ES/discover.json
+++ b/DigitalHumanWeb/locales/es-ES/discover.json
@@ -126,6 +126,10 @@
"title": "Novedad del tema"
},
"range": "Rango",
+ "reasoning_effort": {
+ "desc": "Esta configuración se utiliza para controlar la intensidad de razonamiento del modelo antes de generar una respuesta. Una baja intensidad prioriza la velocidad de respuesta y ahorra tokens, mientras que una alta intensidad proporciona un razonamiento más completo, pero consume más tokens y reduce la velocidad de respuesta. El valor predeterminado es medio, equilibrando la precisión del razonamiento con la velocidad de respuesta.",
+ "title": "Intensidad de razonamiento"
+ },
"temperature": {
"desc": "Esta configuración afecta la diversidad de las respuestas del modelo. Un valor más bajo resultará en respuestas más predecibles y típicas, mientras que un valor más alto alentará respuestas más diversas y menos comunes. Cuando el valor se establece en 0, el modelo siempre dará la misma respuesta para una entrada dada.",
"title": "Aleatoriedad"
diff --git a/DigitalHumanWeb/locales/es-ES/error.json b/DigitalHumanWeb/locales/es-ES/error.json
index 9aa7424..e63cfe5 100644
--- a/DigitalHumanWeb/locales/es-ES/error.json
+++ b/DigitalHumanWeb/locales/es-ES/error.json
@@ -12,8 +12,14 @@
"retry": "Reintentar",
"title": "Se ha producido un problema en la página.."
},
- "fetchError": "Error en la solicitud",
- "fetchErrorDetail": "Detalles del error",
+ "fetchError": {
+ "detail": "Detalles del error",
+ "title": "Solicitud fallida"
+ },
+ "loginRequired": {
+ "desc": "Serás redirigido automáticamente a la página de inicio de sesión",
+ "title": "Por favor, inicie sesión para utilizar esta función"
+ },
"notFound": {
"backHome": "Volver a la página de inicio",
"check": "Por favor, verifica si tu URL es correcta",
@@ -51,22 +57,34 @@
"431": "Lo sentimos, el campo de encabezado de su solicitud es demasiado grande para ser procesado por el servidor",
"451": "Lo sentimos, el servidor se niega a proporcionar este recurso debido a razones legales",
"500": "Lo sentimos, el servidor parece estar experimentando dificultades y no puede completar su solicitud en este momento. Por favor, inténtelo de nuevo más tarde",
+ "501": "Lo sentimos, el servidor aún no sabe cómo manejar esta solicitud, por favor confirme que su operación es correcta",
"502": "Lo sentimos, el servidor parece estar desorientado y no puede proporcionar servicio en este momento. Por favor, inténtelo de nuevo más tarde",
"503": "Lo sentimos, el servidor no puede procesar su solicitud en este momento, posiblemente debido a una sobrecarga o mantenimiento. Por favor, inténtelo de nuevo más tarde",
"504": "Lo sentimos, el servidor no recibió respuesta del servidor upstream. Por favor, inténtelo de nuevo más tarde",
+ "505": "Lo sentimos, el servidor no soporta la versión HTTP que está utilizando, por favor actualice y vuelva a intentarlo",
+ "506": "Lo sentimos, hay un problema con la configuración del servidor, por favor contacte al administrador para resolverlo",
+ "507": "Lo sentimos, el servidor no tiene suficiente espacio de almacenamiento para procesar su solicitud, por favor inténtelo de nuevo más tarde",
+ "509": "Lo sentimos, el ancho de banda del servidor se ha agotado, por favor inténtelo de nuevo más tarde",
+ "510": "Lo sentimos, el servidor no soporta la funcionalidad de extensión solicitada, por favor contacte al administrador",
+ "524": "Lo sentimos, el servidor ha agotado el tiempo de espera mientras esperaba una respuesta, puede ser debido a que la respuesta es demasiado lenta, por favor inténtelo de nuevo más tarde",
"AgentRuntimeError": "Se produjo un error en la ejecución del tiempo de ejecución del modelo de lenguaje Lobe, por favor, verifica la siguiente información o inténtalo de nuevo",
+ "ConnectionCheckFailed": "La respuesta de la solicitud está vacía, por favor verifica que la dirección del proxy de la API no termine con `/v1`",
+ "ExceededContextWindow": "El contenido de la solicitud actual excede la longitud que el modelo puede procesar. Por favor, reduzca la cantidad de contenido y vuelva a intentarlo.",
"FreePlanLimit": "Actualmente eres un usuario gratuito y no puedes utilizar esta función. Por favor, actualiza a un plan de pago para seguir utilizando.",
+ "InsufficientQuota": "Lo sentimos, la cuota de esta clave ha alcanzado su límite. Por favor, verifique si el saldo de su cuenta es suficiente o aumente la cuota de la clave y vuelva a intentarlo.",
"InvalidAccessCode": "La contraseña no es válida o está vacía. Por favor, introduce una contraseña de acceso válida o añade una clave API personalizada",
"InvalidBedrockCredentials": "La autenticación de Bedrock no se ha completado con éxito, por favor, verifica AccessKeyId/SecretAccessKey e inténtalo de nuevo",
"InvalidClerkUser": "Lo siento mucho, actualmente no has iniciado sesión. Por favor, inicia sesión o regístrate antes de continuar.",
"InvalidGithubToken": "El token de acceso personal de Github es incorrecto o está vacío. Por favor, verifica el token de acceso personal de Github y vuelve a intentarlo.",
"InvalidOllamaArgs": "La configuración de Ollama no es válida, por favor revisa la configuración de Ollama e inténtalo de nuevo",
"InvalidProviderAPIKey": "{{provider}} API Key incorrecta o vacía, por favor revisa tu {{provider}} API Key e intenta de nuevo",
+ "InvalidVertexCredentials": "La autenticación de Vertex no se ha completado, por favor verifica las credenciales de autenticación y vuelve a intentarlo",
"LocationNotSupportError": "Lo sentimos, tu ubicación actual no es compatible con este servicio de modelo, puede ser debido a restricciones geográficas o a que el servicio no está disponible. Por favor, verifica si tu ubicación actual es compatible con este servicio o intenta usar otra información de ubicación.",
+ "ModelNotFound": "Lo sentimos, no se pudo solicitar el modelo correspondiente, puede que el modelo no exista o que no tenga permisos de acceso. Por favor, cambie la clave API o ajuste los permisos de acceso y vuelva a intentarlo.",
"NoOpenAIAPIKey": "La clave de API de OpenAI está vacía. Agregue una clave de API de OpenAI personalizada",
"OllamaBizError": "Error al solicitar el servicio de Ollama, por favor verifica la siguiente información o inténtalo de nuevo",
"OllamaServiceUnavailable": "El servicio Ollama no está disponible. Por favor, verifica si Ollama está funcionando correctamente o si la configuración de Ollama para el acceso entre dominios está configurada correctamente.",
- "OpenAIBizError": "Se produjo un error al solicitar el servicio de OpenAI, por favor, revise la siguiente información o inténtelo de nuevo",
+ "PermissionDenied": "Lo sentimos, no tienes permiso para acceder a este servicio. Por favor, verifica si tu clave tiene los permisos necesarios.",
"PluginApiNotFound": "Lo sentimos, el API especificado no existe en el manifiesto del complemento. Verifique si su método de solicitud coincide con el API del manifiesto del complemento",
"PluginApiParamsError": "Lo sentimos, la validación de los parámetros de entrada de la solicitud del complemento no ha pasado. Verifique si los parámetros de entrada coinciden con la información de descripción del API",
"PluginFailToTransformArguments": "Lo siento, no se pudieron transformar los argumentos de la llamada al plugin. Por favor, intenta generar de nuevo el mensaje del asistente o prueba con un modelo de IA de Tools Calling más potente.",
@@ -81,8 +99,11 @@
"PluginServerError": "Error al recibir la respuesta del servidor del complemento. Verifique el archivo de descripción del complemento, la configuración del complemento o la implementación del servidor según la información de error a continuación",
"PluginSettingsInvalid": "Este complemento necesita una configuración correcta antes de poder usarse. Verifique si su configuración es correcta",
"ProviderBizError": "Se produjo un error al solicitar el servicio de {{provider}}, por favor, revise la siguiente información o inténtelo de nuevo",
+ "QuotaLimitReached": "Lo sentimos, el uso actual de tokens o el número de solicitudes ha alcanzado el límite de cuota de esta clave. Por favor, aumenta la cuota de esta clave o intenta de nuevo más tarde.",
"StreamChunkError": "Error de análisis del bloque de mensajes de la solicitud en streaming. Por favor, verifica si la API actual cumple con las normas estándar o contacta a tu proveedor de API para más información.",
- "SubscriptionPlanLimit": "Has alcanzado el límite de tu suscripción y no puedes utilizar esta función. Por favor, actualiza a un plan superior o compra un paquete de recursos para seguir utilizando.",
+ "SubscriptionKeyMismatch": "Lo sentimos, debido a un fallo ocasional del sistema, el uso de la suscripción actual ha dejado de ser válido temporalmente. Por favor, haga clic en el botón de abajo para restaurar la suscripción o contáctenos por correo electrónico para obtener soporte.",
+ "SubscriptionPlanLimit": "Se han agotado sus puntos de suscripción, no puede utilizar esta función. Por favor, actualice a un plan superior o configure la API del modelo personalizado para continuar.",
+ "SystemTimeNotMatchError": "Lo sentimos, la hora de su sistema no coincide con la del servidor. Por favor, verifique la hora de su sistema y vuelva a intentarlo.",
"UnknownChatFetchError": "Lo sentimos, se ha producido un error desconocido en la solicitud. Por favor, verifica la información a continuación o intenta de nuevo."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/es-ES/metadata.json b/DigitalHumanWeb/locales/es-ES/metadata.json
index f7fb594..f39fbc9 100644
--- a/DigitalHumanWeb/locales/es-ES/metadata.json
+++ b/DigitalHumanWeb/locales/es-ES/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Sigue las nuevas funciones y mejoras de {{appName}}",
+ "title": "Registro de cambios"
+ },
"chat": {
"description": "{{appName}} te ofrece la mejor experiencia de uso de ChatGPT, Claude, Gemini y OLLaMA WebUI",
"title": "{{appName}}: Herramienta de productividad personal de IA, dale a tu cerebro un impulso más inteligente"
diff --git a/DigitalHumanWeb/locales/es-ES/modelProvider.json b/DigitalHumanWeb/locales/es-ES/modelProvider.json
index cadb4e2..c4eefa4 100644
--- a/DigitalHumanWeb/locales/es-ES/modelProvider.json
+++ b/DigitalHumanWeb/locales/es-ES/modelProvider.json
@@ -19,6 +19,24 @@
"title": "Clave API"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Versión de la API de Azure, siguiendo el formato AAAA-MM-DD, consulta la [última versión](https://learn.microsoft.com/es-es/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Obtener lista",
+ "title": "Versión de la API de Azure"
+ },
+ "endpoint": {
+ "desc": "Encuentra el punto final de inferencia del modelo de Azure AI en la descripción general del proyecto de Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Punto final de Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Encuentra la clave API en la descripción general del proyecto de Azure AI",
+ "placeholder": "Clave de Azure",
+ "title": "Clave"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Introduce tu AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "Usar información de autenticación de Bedrock personalizada"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Por favor complete la Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Ingrese el ID de cuenta de Cloudflare o la dirección URL personalizada de API",
+ "placeholder": "ID de cuenta de Cloudflare / URL de API personalizada",
+ "title": "ID de cuenta de Cloudflare / dirección URL de API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Por favor, introduce tu API Key",
+ "title": "API Key"
+ },
+ "basicTitle": "Información básica",
+ "configTitle": "Información de configuración",
+ "confirm": "Crear nuevo",
+ "createSuccess": "Creación exitosa",
+ "description": {
+ "placeholder": "Descripción del proveedor (opcional)",
+ "title": "Descripción del proveedor"
+ },
+ "id": {
+ "desc": "Identificador único del proveedor de servicios, no se puede modificar una vez creado",
+ "format": "Solo puede contener números, letras minúsculas, guiones (-) y guiones bajos (_) ",
+ "placeholder": "Se recomienda en minúsculas, por ejemplo openai, no se puede modificar después de crear",
+ "required": "Por favor, introduce el ID del proveedor",
+ "title": "ID del proveedor"
+ },
+ "logo": {
+ "required": "Por favor, sube un logo correcto del proveedor",
+ "title": "Logo del proveedor"
+ },
+ "name": {
+ "placeholder": "Por favor, introduce el nombre del proveedor",
+ "required": "Por favor, introduce el nombre del proveedor",
+ "title": "Nombre del proveedor"
+ },
+ "proxyUrl": {
+ "required": "Por favor, introduce la dirección del proxy",
+ "title": "Dirección del proxy"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Por favor, selecciona el tipo de SDK",
+ "title": "Formato de solicitud"
+ },
+ "title": "Crear proveedor de AI personalizado"
+ },
"github": {
"personalAccessToken": {
"desc": "Introduce tu PAT de Github, haz clic [aquí](https://github.com/settings/tokens) para crear uno",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Introduce tu token de HuggingFace, haz clic [aquí](https://huggingface.co/settings/tokens) para crear uno",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "Token de HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Proveedor no habilitado",
+ "enabled": "Proveedor habilitado"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Agregar proveedor personalizado",
+ "all": "Todo",
+ "list": {
+ "disabled": "No habilitado",
+ "enabled": "Habilitado"
+ },
+ "notFound": "No se encontraron resultados de búsqueda",
+ "searchProviders": "Buscar proveedores...",
+ "sort": "Orden personalizado"
+ },
"ollama": {
"checker": {
"desc": "Prueba si la dirección del proxy de la interfaz se ha introducido correctamente",
@@ -69,39 +163,15 @@
"title": "Nombre de modelos personalizados"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. The download will resume from where it left off if interrupted.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama está descargando este modelo, por favor intenta no cerrar esta página. La descarga se reanudará desde donde se interrumpió",
+ "remainingTime": "Tiempo restante",
+ "speed": "Velocidad de descarga",
+ "title": "Descargando el modelo {{model}} "
},
"endpoint": {
- "desc": "Introduce la dirección del proxy de la interfaz de Ollama, déjalo en blanco si no se ha especificado localmente",
+ "desc": "Debe incluir http(s)://, se puede dejar vacío si no se especifica localmente",
"title": "Dirección del proxy de la interfaz"
},
- "setup": {
- "cors": {
- "description": "Debido a restricciones de seguridad del navegador, es necesario configurar Ollama para permitir el acceso entre dominios.",
- "linux": {
- "env": "En la sección [Service], agrega `Environment` y añade la variable de entorno OLLAMA_ORIGINS:",
- "reboot": "Recarga systemd y reinicia Ollama.",
- "systemd": "Edita el servicio ollama llamando a systemd:"
- },
- "macos": "Abre la aplicación 'Terminal', pega y ejecuta el siguiente comando, luego presiona Enter.",
- "reboot": "Reinicia el servicio de Ollama una vez completada la ejecución.",
- "title": "Configuración para permitir el acceso entre dominios en Ollama",
- "windows": "En Windows, ve a 'Panel de control', edita las variables de entorno del sistema. Crea una nueva variable de entorno llamada 'OLLAMA_ORIGINS' para tu cuenta de usuario, con el valor '*', y haz clic en 'OK/Aplicar' para guardar los cambios."
- },
- "install": {
- "description": "Por favor, asegúrate de que has activado Ollama. Si no has descargado Ollama, por favor visita el sitio web oficial para <1>descargarlo1>.",
- "docker": "Si prefieres usar Docker, Ollama también ofrece una imagen oficial en Docker. Puedes obtenerla con el siguiente comando:",
- "linux": {
- "command": "Instala con el siguiente comando:",
- "manual": "O también puedes consultar la <1>Guía de instalación manual en Linux1> para instalarlo por tu cuenta."
- },
- "title": "Instalación local y activación de la aplicación Ollama",
- "windowsTab": "Windows (Versión de vista previa)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Cancel Download",
@@ -112,6 +182,156 @@
"title": "Download specified Ollama model"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "Tu clave y dirección del proxy se cifrarán utilizando el algoritmo de cifrado <1>AES-GCM1>",
+ "apiKey": {
+ "desc": "Por favor, introduce tu {{name}} API Key",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "Debe incluir http(s)://",
+ "invalid": "Por favor, introduce una URL válida",
+ "placeholder": "https://tu-direccion-proxy.com/v1",
+ "title": "Dirección del proxy API"
+ },
+ "checker": {
+ "button": "Verificar",
+ "desc": "Prueba si la API Key y la dirección del proxy están correctamente introducidas",
+ "pass": "Verificación exitosa",
+ "title": "Verificación de conectividad"
+ },
+ "fetchOnClient": {
+ "desc": "El modo de solicitud del cliente iniciará la solicitud de sesión directamente desde el navegador, lo que puede mejorar la velocidad de respuesta",
+ "title": "Usar modo de solicitud del cliente"
+ },
+ "helpDoc": "Guía de configuración",
+ "waitingForMore": "Más modelos están en <1>planificación de integración1>, por favor, espera"
+ },
+ "createNew": {
+ "title": "Crear modelo de AI personalizado"
+ },
+ "item": {
+ "config": "Configurar modelo",
+ "customModelCards": {
+ "addNew": "Crear y agregar modelo {{id}}",
+ "confirmDelete": "Estás a punto de eliminar este modelo personalizado, una vez eliminado no se puede recuperar, por favor actúa con precaución."
+ },
+ "delete": {
+ "confirm": "¿Confirmar eliminación del modelo {{displayName}}?",
+ "success": "Eliminación exitosa",
+ "title": "Eliminar modelo"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Campo solicitado en Azure OpenAI",
+ "placeholder": "Por favor, introduce el nombre de despliegue del modelo en Azure",
+ "title": "Nombre de despliegue del modelo"
+ },
+ "deployName": {
+ "extra": "Este campo se enviará como ID del modelo al hacer la solicitud",
+ "placeholder": "Introduce el nombre o ID real del modelo desplegado",
+ "title": "Nombre de despliegue del modelo"
+ },
+ "displayName": {
+ "placeholder": "Por favor, introduce el nombre de visualización del modelo, por ejemplo, ChatGPT, GPT-4, etc.",
+ "title": "Nombre de visualización del modelo"
+ },
+ "files": {
+ "extra": "La implementación actual de carga de archivos es solo una solución temporal, solo para prueba personal. La capacidad completa de carga de archivos estará disponible en futuras implementaciones.",
+ "title": "Soporte para carga de archivos"
+ },
+ "functionCall": {
+ "extra": "Esta configuración solo habilitará la capacidad del modelo para usar herramientas, lo que permite agregar complementos de tipo herramienta al modelo. Sin embargo, si realmente se admiten las herramientas depende completamente del modelo en sí, por favor pruebe su disponibilidad",
+ "title": "Soporte para el uso de herramientas"
+ },
+ "id": {
+ "extra": "No se puede modificar después de la creación, se utilizará como id del modelo al llamar a la IA",
+ "placeholder": "Introduce el id del modelo, por ejemplo gpt-4o o claude-3.5-sonnet",
+ "title": "ID del modelo"
+ },
+ "modalTitle": "Configuración del modelo personalizado",
+ "reasoning": {
+ "extra": "Esta configuración solo activará la capacidad de pensamiento profundo del modelo, el efecto específico depende completamente del modelo en sí, por favor, pruebe si este modelo tiene la capacidad de pensamiento profundo utilizable",
+ "title": "Soporte para pensamiento profundo"
+ },
+ "tokens": {
+ "extra": "Establecer el número máximo de tokens que el modelo puede soportar",
+ "title": "Máximo de ventana de contexto",
+ "unlimited": "Sin límite"
+ },
+ "vision": {
+ "extra": "Esta configuración solo habilitará la configuración de carga de imágenes en la aplicación, si se admite el reconocimiento depende completamente del modelo en sí, prueba la disponibilidad de la capacidad de reconocimiento visual de este modelo.",
+ "title": "Soporte para reconocimiento visual"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/imagen",
+ "inputCharts": "${{amount}}/M caracteres",
+ "inputMinutes": "${{amount}}/minuto",
+ "inputTokens": "Entrada ${{amount}}/M",
+ "outputTokens": "Salida ${{amount}}/M"
+ },
+ "releasedAt": "Publicado el {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Agregar modelo",
+ "disabled": "No habilitado",
+ "disabledActions": {
+ "showMore": "Mostrar todo"
+ },
+ "empty": {
+ "desc": "Por favor, crea un modelo personalizado o importa un modelo para comenzar a usarlo.",
+ "title": "No hay modelos disponibles"
+ },
+ "enabled": "Habilitado",
+ "enabledActions": {
+ "disableAll": "Deshabilitar todo",
+ "enableAll": "Habilitar todo",
+ "sort": "Ordenar modelos personalizados"
+ },
+ "enabledEmpty": "No hay modelos habilitados, por favor habilita los modelos que te gusten de la lista a continuación~",
+ "fetcher": {
+ "clear": "Eliminar modelos obtenidos",
+ "fetch": "Obtener lista de modelos",
+ "fetching": "Obteniendo lista de modelos...",
+ "latestTime": "Última actualización: {{time}}",
+ "noLatestTime": "Lista aún no obtenida"
+ },
+ "resetAll": {
+ "conform": "¿Confirmar el restablecimiento de todas las modificaciones del modelo actual? Después del restablecimiento, la lista de modelos actuales volverá al estado predeterminado",
+ "success": "Restablecimiento exitoso",
+ "title": "Restablecer todas las modificaciones"
+ },
+ "search": "Buscar modelos...",
+ "searchResult": "Se encontraron {{count}} modelos",
+ "title": "Lista de modelos",
+ "total": "Un total de {{count}} modelos disponibles"
+ },
+ "searchNotFound": "No se encontraron resultados de búsqueda"
+ },
+ "sortModal": {
+ "success": "Orden actualizado con éxito",
+ "title": "Orden personalizado",
+ "update": "Actualizar"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Estás a punto de eliminar este proveedor de AI, una vez eliminado no se puede recuperar, ¿confirmar eliminación?",
+ "deleteSuccess": "Eliminación exitosa",
+ "tooltip": "Actualizar configuración básica del proveedor",
+ "updateSuccess": "Actualización exitosa"
+ },
+ "updateCustomAiProvider": {
+ "title": "Actualizar la configuración del proveedor de IA personalizado"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Introduce tus claves de Vertex AI",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Claves de Vertex AI"
+ }
+ },
"zeroone": {
"title": "01.AI Cero Uno Todo"
},
diff --git a/DigitalHumanWeb/locales/es-ES/models.json b/DigitalHumanWeb/locales/es-ES/models.json
index f6d8cee..b96aef2 100644
--- a/DigitalHumanWeb/locales/es-ES/models.json
+++ b/DigitalHumanWeb/locales/es-ES/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, con un rico conjunto de muestras de entrenamiento, ofrece un rendimiento superior en aplicaciones industriales."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat es una variante de la serie Yi-1.5, que pertenece a los modelos de chat de código abierto. Yi-1.5 es una versión mejorada de Yi, que ha sido preentrenada de manera continua en 500B de corpus de alta calidad y ajustada en más de 3M de muestras de ajuste diversificadas. En comparación con Yi, Yi-1.5 muestra un rendimiento superior en codificación, matemáticas, razonamiento y capacidad de seguimiento de instrucciones, manteniendo al mismo tiempo una excelente comprensión del lenguaje, razonamiento de sentido común y comprensión de lectura. Este modelo tiene versiones con longitudes de contexto de 4K, 16K y 32K, con un total de preentrenamiento de 3.6T de tokens."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B soporta 16K Tokens, proporcionando una capacidad de generación de lenguaje eficiente y fluida."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Cero Uno, el último modelo de ajuste fino de código abierto, cuenta con 34 mil millones de parámetros, con ajuste fino que admite múltiples escenarios de conversación y datos de entrenamiento de alta calidad, alineados con las preferencias humanas."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Cero Uno, el último modelo de ajuste fino de código abierto, cuenta con 9 mil millones de parámetros, con ajuste fino que admite múltiples escenarios de conversación y datos de entrenamiento de alta calidad, alineados con las preferencias humanas."
+ },
"360gpt-pro": {
"description": "360GPT Pro, como un miembro importante de la serie de modelos de IA de 360, satisface diversas aplicaciones de procesamiento de lenguaje natural con su eficiente capacidad de manejo de textos, soportando la comprensión de textos largos y funciones de diálogo en múltiples turnos."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K enfatiza la seguridad semántica y la responsabilidad, diseñado específicamente para aplicaciones que requieren altos estándares de seguridad de contenido, asegurando la precisión y robustez de la experiencia del usuario."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 utiliza la búsqueda en árbol para construir cadenas de pensamiento e introduce un mecanismo de reflexión, entrenado mediante aprendizaje por refuerzo, lo que le permite tener la capacidad de auto-reflexión y corrección de errores."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro es un modelo avanzado de procesamiento de lenguaje natural lanzado por la empresa 360, con una excelente capacidad de generación y comprensión de textos, destacándose especialmente en la generación y creación de contenido, capaz de manejar tareas complejas de conversión de lenguaje y representación de roles."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 utiliza búsqueda en árbol para construir cadenas de pensamiento e introduce un mecanismo de reflexión, entrenando el modelo con aprendizaje por refuerzo, lo que le confiere la capacidad de auto-reflexión y corrección de errores."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra es la versión más poderosa de la serie de modelos grandes de Xinghuo, mejorando la comprensión y capacidad de resumen de contenido textual al actualizar la conexión de búsqueda en línea. Es una solución integral para mejorar la productividad en la oficina y responder con precisión a las necesidades, siendo un producto inteligente líder en la industria."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "El modelo tiene la mejor capacidad en el país, superando a los modelos principales extranjeros en tareas en chino como enciclopedias, textos largos y creación generativa. También cuenta con capacidades multimodales líderes en la industria, destacándose en múltiples evaluaciones de referencia autorizadas."
},
+ "Baichuan4-Air": {
+ "description": "El modelo más potente del país, superando a los modelos principales extranjeros en tareas en chino como enciclopedias, textos largos y creación generativa. También cuenta con capacidades multimodales líderes en la industria, destacándose en múltiples evaluaciones de referencia."
+ },
+ "Baichuan4-Turbo": {
+ "description": "El modelo más potente del país, superando a los modelos principales extranjeros en tareas en chino como enciclopedias, textos largos y creación generativa. También cuenta con capacidades multimodales líderes en la industria, destacándose en múltiples evaluaciones de referencia."
+ },
+ "DeepSeek-R1": {
+ "description": "LLM eficiente de última generación, experto en razonamiento, matemáticas y programación."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1, el modelo más grande e inteligente del conjunto DeepSeek, ha sido destilado en la arquitectura Llama 70B. Basado en pruebas de referencia y evaluaciones humanas, este modelo es más inteligente que el Llama 70B original, destacándose especialmente en tareas que requieren precisión matemática y factual."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "El modelo de destilación DeepSeek-R1 basado en Qwen2.5-Math-1.5B optimiza el rendimiento de inferencia mediante aprendizaje por refuerzo y datos de arranque en frío, actualizando el estándar de múltiples tareas en modelos de código abierto."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "El modelo de destilación DeepSeek-R1 basado en Qwen2.5-14B optimiza el rendimiento de inferencia mediante aprendizaje por refuerzo y datos de arranque en frío, actualizando el estándar de múltiples tareas en modelos de código abierto."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "La serie DeepSeek-R1 optimiza el rendimiento de inferencia mediante aprendizaje por refuerzo y datos de arranque en frío, actualizando el estándar de múltiples tareas en modelos de código abierto, superando el nivel de OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "El modelo de destilación DeepSeek-R1 basado en Qwen2.5-Math-7B optimiza el rendimiento de inferencia mediante aprendizaje por refuerzo y datos de arranque en frío, actualizando el estándar de múltiples tareas en modelos de código abierto."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro es un modelo multimodal de gran tamaño, actualizado, que soporta el reconocimiento de imágenes de cualquier resolución y proporciones extremas, mejorando la capacidad de razonamiento visual, reconocimiento de documentos, comprensión de información detallada y cumplimiento de instrucciones."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite presenta una velocidad de respuesta extrema y una mejor relación calidad-precio, ofreciendo opciones más flexibles para diferentes escenarios de clientes. Admite inferencia y ajuste fino con ventanas de contexto de 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite presenta una velocidad de respuesta extrema y una mejor relación calidad-precio, ofreciendo opciones más flexibles para diferentes escenarios de clientes. Admite inferencia y ajuste fino con ventanas de contexto de 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite presenta una velocidad de respuesta extrema y una mejor relación calidad-precio, ofreciendo opciones más flexibles para diferentes escenarios de clientes. Admite inferencia y ajuste fino con ventanas de contexto de 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "El modelo principal más eficaz, adecuado para manejar tareas complejas, con un excelente rendimiento en escenarios como preguntas y respuestas de referencia, resúmenes, creación de contenido, clasificación de textos y juegos de roles. Admite inferencia y ajuste fino con ventanas de contexto de 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "El modelo principal con el mejor rendimiento, adecuado para manejar tareas complejas, mostrando buenos resultados en escenarios como preguntas y respuestas de referencia, resúmenes, creación, clasificación de textos y juegos de roles. Soporta razonamiento y ajuste fino con una ventana de contexto de 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "El modelo principal más eficaz, adecuado para manejar tareas complejas, con un excelente rendimiento en escenarios como preguntas y respuestas de referencia, resúmenes, creación de contenido, clasificación de textos y juegos de roles. Admite inferencia y ajuste fino con ventanas de contexto de 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "El modelo principal más eficaz, adecuado para manejar tareas complejas, con un excelente rendimiento en escenarios como preguntas y respuestas de referencia, resúmenes, creación de contenido, clasificación de textos y juegos de roles. Admite inferencia y ajuste fino con ventanas de contexto de 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "El modelo Doubao-vision es un modelo multimodal lanzado por Doubao, que cuenta con potentes capacidades de comprensión e inferencia de imágenes, así como una precisa capacidad de comprensión de instrucciones. El modelo ha demostrado un rendimiento excepcional en la extracción de información textual de imágenes y en tareas de razonamiento basadas en imágenes, siendo aplicable a tareas de preguntas y respuestas visuales más complejas y amplias."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "El modelo Doubao-vision es un modelo multimodal lanzado por Doubao, que cuenta con potentes capacidades de comprensión e inferencia de imágenes, así como una precisa capacidad de comprensión de instrucciones. El modelo ha demostrado un rendimiento excepcional en la extracción de información textual de imágenes y en tareas de razonamiento basadas en imágenes, siendo aplicable a tareas de preguntas y respuestas visuales más complejas y amplias."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Modelo de lenguaje a gran escala de primera línea desarrollado por Baidu, que abarca una vasta cantidad de corpus en chino y en inglés, con potentes capacidades generales que pueden satisfacer la mayoría de los requisitos de preguntas y respuestas en diálogos, generación de contenido y aplicaciones de plugins; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información en las respuestas."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Modelo de lenguaje a gran escala de primera línea desarrollado por Baidu, que abarca una vasta cantidad de corpus en chino y en inglés, con potentes capacidades generales que pueden satisfacer la mayoría de los requisitos de preguntas y respuestas en diálogos, generación de contenido y aplicaciones de plugins; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información en las respuestas."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Modelo de lenguaje a gran escala de primera línea desarrollado por Baidu, que abarca una vasta cantidad de corpus en chino y en inglés, con potentes capacidades generales que pueden satisfacer la mayoría de los requisitos de preguntas y respuestas en diálogos, generación de contenido y aplicaciones de plugins; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información en las respuestas."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Modelo de lenguaje a gran escala ultra avanzado desarrollado por Baidu, que ha logrado una actualización completa de las capacidades del modelo en comparación con ERNIE 3.5, siendo ampliamente aplicable a escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información en las respuestas."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Modelo de lenguaje a gran escala ultra avanzado desarrollado por Baidu, que ha logrado una actualización completa de las capacidades del modelo en comparación con ERNIE 3.5, siendo ampliamente aplicable a escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información en las respuestas."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Modelo de lenguaje a gran escala desarrollado por Baidu, con un rendimiento general excepcional, ampliamente aplicable a escenas complejas en diversos campos; soporta la conexión automática al complemento de búsqueda de Baidu, garantizando la actualidad de la información de las preguntas y respuestas. En comparación con ERNIE 4.0, tiene un rendimiento superior."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Modelo de lenguaje a gran escala ultra avanzado desarrollado por Baidu, con un rendimiento excepcional en efectos generales, siendo ampliamente aplicable a escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información en las respuestas. En comparación con ERNIE 4.0, ofrece un rendimiento superior."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Modelo de lenguaje vertical desarrollado por Baidu, adecuado para aplicaciones como NPC en juegos, diálogos de servicio al cliente, y juegos de rol conversacionales, con un estilo de personaje más distintivo y coherente, y una mayor capacidad de seguir instrucciones, además de un rendimiento de inferencia superior."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Modelo de lenguaje ligero desarrollado por Baidu, que combina un excelente rendimiento del modelo con una alta eficiencia de inferencia, superando a ERNIE Lite, adecuado para su uso en tarjetas de aceleración de IA de bajo consumo."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Modelo de lenguaje de alto rendimiento desarrollado por Baidu, lanzado en 2024, con capacidades generales excepcionales, adecuado como modelo base para ajustes finos, manejando mejor problemas en escenarios específicos, y con un rendimiento de inferencia excelente."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Modelo de lenguaje de alto rendimiento desarrollado por Baidu, lanzado en 2024, con capacidades generales excepcionales, superando a ERNIE Speed, adecuado como modelo base para ajustes finos, manejando mejor problemas en escenarios específicos, y con un rendimiento de inferencia excelente."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) es un modelo innovador, adecuado para aplicaciones en múltiples campos y tareas complejas."
},
- "Max-32k": {
- "description": "Spark Max 32K está equipado con una gran capacidad de procesamiento de contexto, una comprensión de contexto más fuerte y habilidades de razonamiento lógico, soporta entradas de texto de 32K tokens, adecuado para la lectura de documentos largos, preguntas y respuestas de conocimiento privado y otros escenarios."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B es un potente modelo de lenguaje visual, que admite el procesamiento multimodal de imágenes y texto, capaz de identificar con precisión el contenido de las imágenes y generar descripciones o respuestas relacionadas."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B es un potente modelo de lenguaje visual, que admite el procesamiento multimodal de imágenes y texto, capaz de identificar con precisión el contenido de las imágenes y generar descripciones o respuestas relacionadas."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Capacidad de razonamiento de imágenes excepcional en imágenes de alta resolución, adecuada para aplicaciones de comprensión visual."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Capacidad avanzada de razonamiento de imágenes para aplicaciones de agentes de comprensión visual."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct es uno de los últimos modelos de lenguaje a gran escala lanzados por Alibaba Cloud. Este modelo de 72B ha mejorado significativamente en áreas como codificación y matemáticas. También ofrece soporte multilingüe, abarcando más de 29 idiomas, incluidos chino e inglés. El modelo ha mostrado mejoras significativas en el seguimiento de instrucciones, comprensión de datos estructurados y generación de salidas estructuradas (especialmente JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct es uno de los últimos modelos de lenguaje a gran escala lanzados por Alibaba Cloud. Este modelo de 7B ha mejorado significativamente en áreas como codificación y matemáticas. También ofrece soporte multilingüe, abarcando más de 29 idiomas, incluidos chino e inglés. El modelo ha mostrado mejoras significativas en el seguimiento de instrucciones, comprensión de datos estructurados y generación de salidas estructuradas (especialmente JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Modelo de texto ajustado por instrucciones de Llama 3.1, optimizado para casos de uso de diálogos multilingües, que se destaca en muchos modelos de chat de código abierto y cerrados en benchmarks de la industria comunes."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO es una fusión de múltiples modelos altamente flexible, diseñada para ofrecer una experiencia creativa excepcional."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Modelo de texto ajustado por instrucciones de Llama 3.1, optimizado para casos de uso de diálogos multilingües, que se destaca en muchos modelos de chat de código abierto y cerrados en benchmarks de la industria comunes."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Modelo de texto ajustado por instrucciones de Llama 3.1, optimizado para casos de uso de diálogos multilingües, que se destaca en muchos modelos de chat de código abierto y cerrados en benchmarks de la industria comunes."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Modelo de lenguaje pequeño de última generación, con comprensión del lenguaje, excelente capacidad de razonamiento y generación de texto."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Modelo de lenguaje pequeño de última generación, con comprensión del lenguaje, excelente capacidad de razonamiento y generación de texto."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 es el modelo de lenguaje de código abierto multilingüe más avanzado de la serie Llama, que ofrece un rendimiento comparable al modelo de 405B a un costo extremadamente bajo. Basado en la estructura Transformer, y mejorado en utilidad y seguridad a través de ajuste fino supervisado (SFT) y aprendizaje por refuerzo con retroalimentación humana (RLHF). Su versión ajustada por instrucciones está optimizada para diálogos multilingües, superando a muchos modelos de chat de código abierto y cerrados en múltiples benchmarks de la industria. La fecha límite de conocimiento es diciembre de 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "En la serie de modelos MiniMax-01, hemos realizado una innovación audaz: la implementación a gran escala del mecanismo de atención lineal, donde la arquitectura Transformer tradicional ya no es la única opción. Este modelo tiene una cantidad de parámetros de hasta 456 mil millones, con 45.9 mil millones por activación. El rendimiento general del modelo es comparable a los mejores modelos internacionales, y puede manejar de manera eficiente contextos de hasta 4 millones de tokens, que es 32 veces más que GPT-4o y 20 veces más que Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) es un modelo de instrucciones de alta precisión, adecuado para cálculos complejos."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) ofrece salidas de lenguaje optimizadas y diversas posibilidades de aplicación."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Actualización del modelo Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 ha demostrado un rendimiento sobresaliente en diversas tareas de lenguaje visual, incluidas la comprensión de documentos y gráficos, comprensión de texto en escenas, OCR, resolución de problemas científicos y matemáticos."
},
"Phi-3-medium-128k-instruct": {
"description": "El mismo modelo Phi-3-medium, pero con un tamaño de contexto más grande para RAG o indicaciones de pocos disparos."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Un modelo de 7B parámetros, que demuestra mejor calidad que Phi-3-mini, con un enfoque en datos densos de razonamiento de alta calidad."
},
- "Pro-128k": {
- "description": "Spark Pro-128K está configurado con una capacidad de procesamiento de contexto extremadamente grande, capaz de manejar hasta 128K de información contextual, especialmente adecuado para contenido largo que requiere análisis completo y manejo de relaciones lógicas a largo plazo, proporcionando una lógica fluida y consistente y un soporte diverso de citas en comunicaciones de texto complejas."
+ "Phi-3.5-mini-instruct": {
+ "description": "Versión actualizada del modelo Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Versión actualizada del modelo Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 ha demostrado un rendimiento sobresaliente en diversas tareas de lenguaje visual, incluidas la comprensión de documentos y gráficos, comprensión de texto en escenas, OCR, resolución de problemas científicos y matemáticos."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct es un modelo de lenguaje a gran escala de ajuste fino por instrucciones dentro de la serie Qwen2, con un tamaño de parámetros de 1.5B. Este modelo se basa en la arquitectura Transformer, utilizando funciones de activación SwiGLU, sesgos de atención QKV y atención de consulta agrupada, entre otras técnicas. Ha destacado en múltiples pruebas de referencia en comprensión del lenguaje, generación, capacidad multilingüe, codificación, matemáticas y razonamiento, superando a la mayoría de los modelos de código abierto. En comparación con Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct ha mostrado mejoras significativas en pruebas como MMLU, HumanEval, GSM8K, C-Eval e IFEval, a pesar de tener un número de parámetros ligeramente menor."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct es un modelo de lenguaje a gran escala de ajuste fino por instrucciones dentro de la serie Qwen2, con un tamaño de parámetros de 7B. Este modelo se basa en la arquitectura Transformer, utilizando funciones de activación SwiGLU, sesgos de atención QKV y atención de consulta agrupada, entre otras técnicas. Es capaz de manejar entradas a gran escala. Este modelo ha destacado en múltiples pruebas de referencia en comprensión del lenguaje, generación, capacidad multilingüe, codificación, matemáticas y razonamiento, superando a la mayoría de los modelos de código abierto y mostrando competitividad comparable a modelos propietarios en ciertas tareas. Qwen2-7B-Instruct ha mostrado mejoras significativas en múltiples evaluaciones en comparación con Qwen1.5-7B-Chat."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL es la última iteración del modelo Qwen-VL, alcanzando un rendimiento de vanguardia en pruebas de comprensión visual."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct es uno de los últimos modelos de lenguaje a gran escala lanzados por Alibaba Cloud. Este modelo de 7B ha mejorado significativamente en áreas como codificación y matemáticas. También ofrece soporte multilingüe, abarcando más de 29 idiomas, incluidos chino e inglés. El modelo ha mostrado mejoras significativas en el seguimiento de instrucciones, comprensión de datos estructurados y generación de salidas estructuradas (especialmente JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct es la última versión de la serie de modelos de lenguaje a gran escala específicos para código lanzada por Alibaba Cloud. Este modelo, basado en Qwen2.5, ha mejorado significativamente la generación, razonamiento y reparación de código a través de un entrenamiento con 55 billones de tokens. No solo ha mejorado la capacidad de codificación, sino que también ha mantenido ventajas en habilidades matemáticas y generales. El modelo proporciona una base más completa para aplicaciones prácticas como agentes de código."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat es la versión de código abierto de la serie de modelos preentrenados GLM-4 lanzada por Zhipu AI. Este modelo destaca en semántica, matemáticas, razonamiento, código y conocimiento. Además de soportar diálogos de múltiples turnos, GLM-4-9B-Chat también cuenta con funciones avanzadas como navegación web, ejecución de código, llamadas a herramientas personalizadas (Function Call) y razonamiento de textos largos. El modelo admite 26 idiomas, incluidos chino, inglés, japonés, coreano y alemán. En múltiples pruebas de referencia, GLM-4-9B-Chat ha demostrado un rendimiento excepcional, como AlignBench-v2, MT-Bench, MMLU y C-Eval. Este modelo admite una longitud de contexto máxima de 128K, adecuado para investigación académica y aplicaciones comerciales."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 es un modelo de inferencia impulsado por aprendizaje por refuerzo (RL) que aborda problemas de repetitividad y legibilidad en el modelo. Antes del RL, DeepSeek-R1 introdujo datos de arranque en frío, optimizando aún más el rendimiento de inferencia. Se desempeña de manera comparable a OpenAI-o1 en tareas matemáticas, de código e inferencia, y mejora el rendimiento general a través de métodos de entrenamiento cuidadosamente diseñados."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 es un modelo de lenguaje de expertos mixtos (MoE) con 671 mil millones de parámetros, que utiliza atención potencial de múltiples cabezas (MLA) y la arquitectura DeepSeekMoE, combinando estrategias de balanceo de carga sin pérdidas auxiliares para optimizar la eficiencia de inferencia y entrenamiento. Preentrenado en 14.8 billones de tokens de alta calidad, y ajustado mediante supervisión y aprendizaje por refuerzo, DeepSeek-V3 supera a otros modelos de código abierto y se acerca a los modelos cerrados líderes."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma es una de las series de modelos abiertos más avanzados y ligeros desarrollados por Google. Es un modelo de lenguaje a gran escala solo de decodificación, que admite inglés y proporciona pesos abiertos, variantes preentrenadas y variantes de ajuste fino por instrucciones. El modelo Gemma es adecuado para diversas tareas de generación de texto, incluyendo preguntas y respuestas, resúmenes y razonamiento. Este modelo de 9B se ha entrenado con 80 billones de tokens. Su tamaño relativamente pequeño permite su implementación en entornos con recursos limitados, como computadoras portátiles, de escritorio o su propia infraestructura en la nube, lo que permite a más personas acceder a modelos de IA de vanguardia y fomentar la innovación."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 es parte de la familia de modelos de lenguaje a gran escala multilingües desarrollados por Meta, que incluye variantes preentrenadas y de ajuste fino por instrucciones con tamaños de parámetros de 8B, 70B y 405B. Este modelo de 8B ha sido optimizado para escenarios de diálogo multilingüe y ha destacado en múltiples pruebas de referencia de la industria. El entrenamiento del modelo utilizó más de 150 billones de tokens de datos públicos y empleó técnicas como ajuste fino supervisado y aprendizaje por refuerzo con retroalimentación humana para mejorar la utilidad y seguridad del modelo. Llama 3.1 admite generación de texto y generación de código, con una fecha límite de conocimiento hasta diciembre de 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview es un modelo de procesamiento de lenguaje natural innovador, capaz de manejar de manera eficiente tareas complejas de generación de diálogos y comprensión del contexto."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview es un modelo de investigación desarrollado por el equipo de Qwen, enfocado en la capacidad de razonamiento visual, que tiene ventajas únicas en la comprensión de escenas complejas y en la resolución de problemas matemáticos relacionados con la visión."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Como versión beta de Qwen2, Qwen1.5 utiliza datos a gran escala para lograr funciones de conversación más precisas."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ es el modelo de inferencia de la serie Qwen. A diferencia de los modelos tradicionales de ajuste por instrucciones, QwQ posee habilidades de pensamiento e inferencia, lo que le permite lograr un rendimiento significativamente mejorado en tareas posteriores, especialmente en la resolución de problemas difíciles. QwQ-32B es un modelo de inferencia de tamaño mediano que puede competir en rendimiento con los modelos de inferencia más avanzados (como DeepSeek-R1, o1-mini). Este modelo utiliza tecnologías como RoPE, SwiGLU, RMSNorm y sesgo de atención QKV, y cuenta con una estructura de red de 64 capas y 40 cabezas de atención Q (en la arquitectura GQA, KV es de 8)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) ofrece respuestas rápidas y capacidades de conversación natural, adecuado para entornos multilingües."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview es el último modelo de investigación experimental de Qwen, enfocado en mejorar la capacidad de razonamiento de la IA. A través de la exploración de mecanismos complejos como la mezcla de lenguajes y el razonamiento recursivo, sus principales ventajas incluyen una poderosa capacidad de análisis de razonamiento, así como habilidades matemáticas y de programación. Sin embargo, también presenta problemas de cambio de idioma, ciclos de razonamiento, consideraciones de seguridad y diferencias en otras capacidades."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct es un modelo de lenguaje a gran escala de ajuste fino por instrucciones dentro de la serie Qwen2, con un tamaño de parámetros de 1.5B. Este modelo se basa en la arquitectura Transformer, utilizando funciones de activación SwiGLU, sesgos de atención QKV y atención de consulta agrupada, entre otras técnicas. Ha destacado en múltiples pruebas de referencia en comprensión del lenguaje, generación, capacidad multilingüe, codificación, matemáticas y razonamiento, superando a la mayoría de los modelos de código abierto. En comparación con Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct ha mostrado mejoras significativas en pruebas como MMLU, HumanEval, GSM8K, C-Eval e IFEval, a pesar de tener un número de parámetros ligeramente menor."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 es un modelo de lenguaje general avanzado, que soporta múltiples tipos de instrucciones."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct es un modelo de lenguaje a gran escala de ajuste fino por instrucciones dentro de la serie Qwen2, con un tamaño de parámetros de 72B. Este modelo se basa en la arquitectura Transformer, utilizando funciones de activación SwiGLU, sesgos de atención QKV y atención de consulta agrupada, entre otras técnicas. Es capaz de manejar entradas a gran escala. Este modelo ha destacado en múltiples pruebas de referencia en comprensión del lenguaje, generación, capacidad multilingüe, codificación, matemáticas y razonamiento, superando a la mayoría de los modelos de código abierto y mostrando competitividad comparable a modelos propietarios en ciertas tareas."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL es la última iteración del modelo Qwen-VL, alcanzando un rendimiento de vanguardia en pruebas de comprensión visual."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 es una nueva serie de modelos de lenguaje a gran escala, diseñada para optimizar el procesamiento de tareas de instrucción."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 es una nueva serie de modelos de lenguaje a gran escala, diseñada para optimizar el procesamiento de tareas de instrucción."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 es una nueva serie de modelos de lenguaje a gran escala, con una mayor capacidad de comprensión y generación."
+ "description": "Modelo de lenguaje de gran escala desarrollado por el equipo de Tongyi Qianwen de Alibaba Cloud"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 es una nueva serie de grandes modelos de lenguaje, con capacidades de comprensión y generación más fuertes."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 es una nueva serie de grandes modelos de lenguaje, diseñada para optimizar el manejo de tareas instructivas."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 es una nueva serie de modelos de lenguaje a gran escala, diseñada para optimizar el procesamiento de tareas de instrucción."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 es una nueva serie de grandes modelos de lenguaje, diseñada para optimizar el manejo de tareas instructivas."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder se centra en la escritura de código."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math se centra en la resolución de problemas en el ámbito de las matemáticas, proporcionando respuestas profesionales a preguntas de alta dificultad."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct es la última versión de la serie de modelos de lenguaje a gran escala específicos para código lanzada por Alibaba Cloud. Este modelo, basado en Qwen2.5, ha mejorado significativamente la generación, razonamiento y reparación de código a través de un entrenamiento con 55 billones de tokens. No solo ha mejorado la capacidad de codificación, sino que también ha mantenido ventajas en habilidades matemáticas y generales. El modelo proporciona una base más completa para aplicaciones prácticas como agentes de código."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 es la última serie del modelo Qwen, que admite un contexto de 128k. En comparación con los modelos de código abierto más óptimos actuales, Qwen2-72B supera significativamente a los modelos líderes actuales en comprensión del lenguaje natural, conocimiento, código, matemáticas y capacidades multilingües."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 es la última serie del modelo Qwen, capaz de superar a los modelos de código abierto de tamaño equivalente e incluso a modelos de mayor tamaño. Qwen2 7B ha logrado ventajas significativas en múltiples evaluaciones, especialmente en comprensión de código y chino."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B es un potente modelo de lenguaje visual que admite el procesamiento multimodal de imágenes y texto, capaz de identificar con precisión el contenido de las imágenes y generar descripciones o respuestas relacionadas."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct es un modelo de lenguaje grande de 14 mil millones de parámetros, con un rendimiento excelente, optimizado para escenarios en chino y multilingües, que admite aplicaciones de preguntas y respuestas inteligentes, generación de contenido, entre otros."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct es un modelo de lenguaje grande de 32 mil millones de parámetros, con un rendimiento equilibrado, optimizado para escenarios en chino y multilingües, que admite aplicaciones de preguntas y respuestas inteligentes, generación de contenido, entre otros."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct admite un contexto de 16k, generando textos largos de más de 8K. Soporta llamadas a funciones e interacción sin problemas con sistemas externos, lo que mejora enormemente la flexibilidad y escalabilidad. El conocimiento del modelo ha aumentado significativamente, y se ha mejorado considerablemente la capacidad de codificación y matemáticas, con soporte para más de 29 idiomas."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct es un modelo de lenguaje grande de 7 mil millones de parámetros, que admite llamadas a funciones e interacción sin problemas con sistemas externos, mejorando enormemente la flexibilidad y escalabilidad. Optimizado para escenarios en chino y multilingües, admite aplicaciones de preguntas y respuestas inteligentes, generación de contenido, entre otros."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct es un modelo de instrucciones de programación basado en un preentrenamiento a gran escala, con una potente capacidad de comprensión y generación de código, capaz de manejar eficientemente diversas tareas de programación, especialmente adecuado para la escritura inteligente de código, generación de scripts automatizados y resolución de problemas de programación."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct es un modelo de lenguaje grande diseñado específicamente para la generación de código, comprensión de código y escenarios de desarrollo eficiente, con una escala de 32B parámetros, líder en la industria, capaz de satisfacer diversas necesidades de programación."
+ },
+ "SenseChat": {
+ "description": "Modelo de versión básica (V4), longitud de contexto de 4K, con potentes capacidades generales."
+ },
+ "SenseChat-128K": {
+ "description": "Modelo de versión básica (V4), longitud de contexto de 128K, se destaca en tareas de comprensión y generación de textos largos."
+ },
+ "SenseChat-32K": {
+ "description": "Modelo de versión básica (V4), longitud de contexto de 32K, aplicable de manera flexible en diversos escenarios."
+ },
+ "SenseChat-5": {
+ "description": "Modelo de última versión (V5.5), longitud de contexto de 128K, con capacidades significativamente mejoradas en razonamiento matemático, diálogos en inglés, seguimiento de instrucciones y comprensión de textos largos, comparable a GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "Es la última versión basada en V5.5, que muestra mejoras significativas en varios aspectos como la capacidad básica en chino e inglés, conversación, conocimientos de ciencias, conocimientos de humanidades, escritura, lógica matemática y control de palabras en comparación con la versión anterior."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Longitud de contexto de 32K, supera a GPT-4 en la comprensión de diálogos en cantonés, siendo comparable a GPT-4 Turbo en múltiples áreas como conocimiento, razonamiento, matemáticas y programación."
+ },
+ "SenseChat-Character": {
+ "description": "Modelo estándar, longitud de contexto de 8K, alta velocidad de respuesta."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Modelo de versión avanzada, longitud de contexto de 32K, con capacidades completamente mejoradas, admite diálogos en chino/inglés."
+ },
+ "SenseChat-Turbo": {
+ "description": "Adecuado para preguntas rápidas y escenarios de ajuste fino del modelo."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "Es la última versión ligera del modelo, alcanzando más del 90% de la capacidad del modelo completo, reduciendo significativamente el costo de inferencia."
+ },
+ "SenseChat-Vision": {
+ "description": "La última versión del modelo (V5.5) admite la entrada de múltiples imágenes, logrando una optimización completa de las capacidades básicas del modelo, con mejoras significativas en el reconocimiento de atributos de objetos, relaciones espaciales, reconocimiento de eventos de acción, comprensión de escenas, reconocimiento de emociones, razonamiento lógico y comprensión y generación de texto."
+ },
+ "Skylark2-lite-8k": {
+ "description": "El modelo de segunda generación Skaylark (Skylark), el modelo Skylark2-lite, tiene una alta velocidad de respuesta, adecuado para escenarios donde se requiere alta inmediatez, sensibilidad de costos y baja necesidad de precisión del modelo, con una longitud de ventana de contexto de 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "El modelo de segunda generación Skaylark (Skylark), la versión Skylark2-pro, cuenta con una alta precisión, adecuada para escenarios de generación de texto más complejos, como redacción de copy en campos especializados, creación de novelas y traducciones de alta calidad, con una longitud de ventana de contexto de 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "El modelo de segunda generación Skaylark (Skylark), el modelo Skylark2-pro, tiene una alta precisión, adecuado para escenarios de generación de texto más complejos, como redacción de copy en campos especializados, creación de novelas y traducciones de alta calidad, con una longitud de ventana de contexto de 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "El modelo de segunda generación Skaylark (Skylark), el modelo Skylark2-pro-character, presenta habilidades excepcionales para el juego de roles y la conversación, destacándose en interpretar diversos roles según las solicitudes del usuario, con un contenido conversacional natural y fluido, ideal para la construcción de chatbots, asistentes virtuales y servicios al cliente en línea, con una alta velocidad de respuesta."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "El modelo de segunda generación Skaylark (Skylark), Skylark2-pro-turbo-8k, ofrece una inferencia más rápida y costos más bajos, con una longitud de ventana de contexto de 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B es un modelo de código abierto de la serie ChatGLM, desarrollado por Zhipu AI. Este modelo conserva las excelentes características de su predecesor, como la fluidez en el diálogo y un bajo umbral de implementación, al tiempo que introduce nuevas características. Utiliza datos de entrenamiento más diversos, un mayor número de pasos de entrenamiento y estrategias de entrenamiento más razonables, destacando entre los modelos preentrenados de menos de 10B. ChatGLM3-6B admite diálogos de múltiples turnos, llamadas a herramientas, ejecución de código y tareas de agente en escenarios complejos. Además del modelo de diálogo, también se han lanzado el modelo base ChatGLM-6B-Base y el modelo de diálogo de texto largo ChatGLM3-6B-32K. Este modelo está completamente abierto para la investigación académica y permite el uso comercial gratuito tras el registro."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B es una versión de código abierto, que proporciona una experiencia de conversación optimizada para aplicaciones de diálogo."
},
+ "TeleAI/TeleChat2": {
+ "description": "El modelo grande TeleChat2 ha sido desarrollado de manera independiente por China Telecom desde cero, siendo un modelo semántico generativo que admite funciones como preguntas y respuestas enciclopédicas, generación de código y generación de textos largos, proporcionando servicios de consulta conversacional a los usuarios, permitiendo interacciones de diálogo, respondiendo preguntas y asistiendo en la creación, ayudando a los usuarios a obtener información, conocimiento e inspiración de manera eficiente y conveniente. El modelo ha mostrado un rendimiento destacado en problemas de alucinación, generación de textos largos y comprensión lógica."
+ },
+ "TeleAI/TeleMM": {
+ "description": "El modelo multimodal TeleMM ha sido desarrollado de manera independiente por China Telecom, siendo un modelo de comprensión multimodal que puede manejar entradas de múltiples modalidades como texto e imágenes, apoyando funciones como comprensión de imágenes y análisis de gráficos, proporcionando servicios de comprensión cruzada para los usuarios. El modelo puede interactuar con los usuarios de manera multimodal, entendiendo con precisión el contenido de entrada, respondiendo preguntas, asistiendo en la creación y proporcionando de manera eficiente información y apoyo inspirador multimodal. Ha mostrado un rendimiento excepcional en tareas multimodales como percepción de alta resolución y razonamiento lógico."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct es uno de los últimos modelos de lenguaje a gran escala lanzados por Alibaba Cloud. Este modelo de 72B ha mejorado significativamente en áreas como codificación y matemáticas. También ofrece soporte multilingüe, abarcando más de 29 idiomas, incluidos chino e inglés. El modelo ha mostrado mejoras significativas en el seguimiento de instrucciones, comprensión de datos estructurados y generación de salidas estructuradas (especialmente JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, manteniendo la excelente capacidad de lenguaje general de la serie original, ha mejorado significativamente la lógica matemática y la capacidad de codificación mediante un entrenamiento incremental de 500 mil millones de tokens de alta calidad."
+ },
"abab5.5-chat": {
"description": "Orientado a escenarios de productividad, admite el procesamiento de tareas complejas y la generación eficiente de texto, adecuado para aplicaciones en campos profesionales."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Optimizado para escenarios de diálogo de personajes en chino, ofrece capacidades de generación de diálogos fluidos y acordes con las expresiones chinas."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Modelo de llamada de función de código abierto de Fireworks, que ofrece capacidades de ejecución de instrucciones sobresalientes y características personalizables."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2, lanzado por Fireworks, es un modelo de llamada de función de alto rendimiento, desarrollado sobre Llama-3 y optimizado para escenarios como llamadas de función, diálogos y seguimiento de instrucciones."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b es un modelo de lenguaje visual que puede recibir entradas de imagen y texto simultáneamente, entrenado con datos de alta calidad, adecuado para tareas multimodales."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 es un modelo de lenguaje grande de última generación, optimizado mediante aprendizaje por refuerzo y datos de arranque en frío, con un rendimiento excepcional en razonamiento, matemáticas y programación."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "El modelo de instrucciones Gemma 2 9B, basado en la tecnología anterior de Google, es adecuado para responder preguntas, resumir y razonar en diversas tareas de generación de texto."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Modelo de lenguaje potente de Deepseek, basado en Mixture-of-Experts (MoE), con un total de 671B de parámetros, activando 37B de parámetros por cada token."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "El modelo de instrucciones Llama 3 70B está optimizado para diálogos multilingües y comprensión del lenguaje natural, superando el rendimiento de la mayoría de los modelos competidores."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "El modelo de instrucciones Llama 3 70B (versión HF) es consistente con los resultados de la implementación oficial, adecuado para tareas de seguimiento de instrucciones de alta calidad."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "El modelo de instrucciones Llama 3 8B está optimizado para diálogos y tareas multilingües, ofreciendo un rendimiento excepcional y eficiente."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "El modelo de instrucciones Llama 3.1 8B está optimizado para diálogos multilingües, capaz de superar la mayoría de los modelos de código abierto y cerrado en estándares de la industria."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Modelo de razonamiento de imágenes de 11B parámetros ajustado por Meta. Este modelo está optimizado para el reconocimiento visual, razonamiento de imágenes, descripción de imágenes y respuestas a preguntas generales sobre imágenes. Puede entender datos visuales, como gráficos y diagramas, y cerrar la brecha entre la visión y el lenguaje generando descripciones textuales de los detalles de las imágenes."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "El modelo de instrucciones Llama 3.2 3B es un modelo multilingüe ligero lanzado por Meta. Está diseñado para mejorar la eficiencia, ofreciendo mejoras significativas en latencia y costos en comparación con modelos más grandes. Ejemplos de uso de este modelo incluyen consultas, reescritura de indicaciones y asistencia en la escritura."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Modelo de razonamiento de imágenes de 90B parámetros ajustado por Meta. Este modelo está optimizado para el reconocimiento visual, razonamiento de imágenes, descripción de imágenes y respuestas a preguntas generales sobre imágenes. Puede entender datos visuales, como gráficos y diagramas, y cerrar la brecha entre la visión y el lenguaje generando descripciones textuales de los detalles de las imágenes."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct es la versión actualizada de diciembre de Llama 3.1 70B. Este modelo ha sido mejorado sobre la base de Llama 3.1 70B (lanzado en julio de 2024), mejorando la invocación de herramientas, el soporte de texto multilingüe, así como las capacidades matemáticas y de programación. El modelo alcanza niveles de liderazgo en la industria en razonamiento, matemáticas y cumplimiento de instrucciones, y puede ofrecer un rendimiento similar al de 3.1 405B, al tiempo que presenta ventajas significativas en velocidad y costo."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Modelo de 24B parámetros, con capacidades de vanguardia comparables a modelos más grandes."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "El modelo de instrucciones Mixtral MoE 8x22B, con parámetros a gran escala y arquitectura de múltiples expertos, soporta de manera integral el procesamiento eficiente de tareas complejas."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "El modelo de instrucciones Mixtral MoE 8x7B, con una arquitectura de múltiples expertos, ofrece un seguimiento y ejecución de instrucciones eficientes."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "El modelo de instrucciones Mixtral MoE 8x7B (versión HF) tiene un rendimiento consistente con la implementación oficial, adecuado para una variedad de escenarios de tareas eficientes."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "El modelo MythoMax L2 13B combina técnicas de fusión innovadoras, destacándose en narración y juegos de rol."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "El modelo de instrucciones Phi 3 Vision es un modelo multimodal ligero, capaz de manejar información visual y textual compleja, con una fuerte capacidad de razonamiento."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "El modelo StarCoder 15.5B soporta tareas de programación avanzadas, con capacidades multilingües mejoradas, adecuado para la generación y comprensión de código complejo."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "El modelo QwQ es un modelo de investigación experimental desarrollado por el equipo de Qwen, enfocado en mejorar la capacidad de razonamiento de la IA."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "La versión de 72B del modelo Qwen-VL es el resultado de la última iteración de Alibaba, representando casi un año de innovación."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "El modelo StarCoder 7B está entrenado en más de 80 lenguajes de programación, con una excelente capacidad de completado de código y comprensión del contexto."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 es una serie de modelos de lenguaje solo decodificadores desarrollados por el equipo Qwen de Alibaba Cloud. Estos modelos ofrecen diferentes tamaños, incluidos 0.5B, 1.5B, 3B, 7B, 14B, 32B y 72B, y tienen variantes base y de instrucciones."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct es la última versión de la serie de modelos de lenguaje a gran escala específicos para código lanzada por Alibaba Cloud. Este modelo, basado en Qwen2.5, ha mejorado significativamente la generación, razonamiento y reparación de código a través de un entrenamiento con 55 billones de tokens. No solo ha mejorado la capacidad de codificación, sino que también ha mantenido ventajas en habilidades matemáticas y generales. El modelo proporciona una base más completa para aplicaciones prácticas como agentes de código."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "El modelo Yi-Large ofrece una capacidad de procesamiento multilingüe excepcional, adecuado para diversas tareas de generación y comprensión de lenguaje."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Un modelo multilingüe de 52B parámetros (12B activos), que ofrece una ventana de contexto larga de 256K, llamada a funciones, salida estructurada y generación fundamentada."
},
- "ai21-jamba-instruct": {
- "description": "Un modelo LLM basado en Mamba de calidad de producción para lograr un rendimiento, calidad y eficiencia de costos de primera clase."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet eleva el estándar de la industria, superando a modelos competidores y a Claude 3 Opus, destacándose en evaluaciones amplias, mientras mantiene la velocidad y costo de nuestros modelos de nivel medio."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet ha elevado los estándares de la industria, superando el rendimiento de modelos competidores y de Claude 3 Opus, destacándose en evaluaciones amplias, mientras mantiene la velocidad y el costo de nuestros modelos de nivel medio."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku es el modelo más rápido y compacto de Anthropic, ofreciendo una velocidad de respuesta casi instantánea. Puede responder rápidamente a consultas y solicitudes simples. Los clientes podrán construir experiencias de IA sin costuras que imiten la interacción humana. Claude 3 Haiku puede manejar imágenes y devolver salidas de texto, con una ventana de contexto de 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus es el modelo más potente de Anthropic para manejar tareas altamente complejas. Destaca en rendimiento, inteligencia, fluidez y comprensión."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku es el modelo de próxima generación más rápido de Anthropic. En comparación con Claude 3 Haiku, Claude 3.5 Haiku ha mejorado en todas las habilidades y ha superado al modelo más grande de la generación anterior, Claude 3 Opus, en muchas pruebas de inteligencia."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet ofrece capacidades que superan a Opus y una velocidad más rápida que Sonnet, manteniendo el mismo precio que Sonnet. Sonnet es especialmente hábil en programación, ciencia de datos, procesamiento visual y tareas de agente."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet es el modelo más inteligente de Anthropic hasta la fecha y el primer modelo de razonamiento híbrido en el mercado. Claude 3.7 Sonnet puede generar respuestas casi instantáneas o un pensamiento prolongado y gradual, permitiendo a los usuarios observar claramente estos procesos. Sonnet es especialmente hábil en programación, ciencia de datos, procesamiento visual y tareas de agente."
+ },
"aya": {
"description": "Aya 23 es un modelo multilingüe lanzado por Cohere, que admite 23 idiomas, facilitando aplicaciones de lenguaje diversas."
},
"aya:35b": {
"description": "Aya 23 es un modelo multilingüe lanzado por Cohere, que admite 23 idiomas, facilitando aplicaciones de lenguaje diversas."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B es un modelo de lenguaje de gran escala de código abierto y comercializable desarrollado por Baichuan Intelligence, que cuenta con 13 mil millones de parámetros y ha logrado los mejores resultados en benchmarks autorizados en chino e inglés."
+ },
"charglm-3": {
"description": "CharGLM-3 está diseñado para juegos de rol y acompañamiento emocional, soportando memoria de múltiples rondas y diálogos personalizados, con aplicaciones amplias."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 ofrece avances en capacidades clave para empresas, incluyendo un contexto líder en la industria de 200K tokens, una reducción significativa en la tasa de alucinaciones del modelo, indicaciones del sistema y una nueva función de prueba: llamadas a herramientas."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku es el modelo de próxima generación más rápido de Anthropic. En comparación con Claude 3 Haiku, Claude 3.5 Haiku ha mejorado en todas las habilidades y ha superado al modelo más grande de la generación anterior, Claude 3 Opus, en muchas pruebas de referencia de inteligencia."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet ofrece capacidades que superan a Opus y una velocidad más rápida que Sonnet, manteniendo el mismo precio que Sonnet. Sonnet es especialmente bueno en programación, ciencia de datos, procesamiento visual y tareas de agentes."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet ofrece capacidades que superan a Opus y una velocidad más rápida que Sonnet, manteniendo el mismo precio que Sonnet. Sonnet es especialmente hábil en programación, ciencia de datos, procesamiento visual y tareas de agencia."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet es el modelo de IA más potente de Anthropic, con un rendimiento de vanguardia en tareas altamente complejas. Puede manejar indicaciones abiertas y escenarios no vistos, con una fluidez y comprensión humana excepcionales. Claude 3.7 Sonnet muestra la vanguardia de las posibilidades de la IA generativa."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku es el modelo más rápido y compacto de Anthropic, diseñado para lograr respuestas casi instantáneas. Tiene un rendimiento de orientación rápido y preciso."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet proporciona un equilibrio ideal entre inteligencia y velocidad para cargas de trabajo empresariales. Ofrece la máxima utilidad a un costo más bajo, siendo fiable y adecuado para implementaciones a gran escala."
},
- "claude-instant-1.2": {
- "description": "El modelo de Anthropic está diseñado para generación de texto de baja latencia y alto rendimiento, soportando la generación de cientos de páginas de texto."
- },
"codegeex-4": {
"description": "CodeGeeX-4 es un potente asistente de programación AI, que admite preguntas y respuestas inteligentes y autocompletado de código en varios lenguajes de programación, mejorando la eficiencia del desarrollo."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B es un modelo de generación de código multilingüe, que admite funciones completas, incluyendo autocompletado y generación de código, intérprete de código, búsqueda en la web, llamadas a funciones y preguntas y respuestas de código a nivel de repositorio, cubriendo diversos escenarios de desarrollo de software. Es un modelo de generación de código de primer nivel con menos de 10B de parámetros."
+ },
"codegemma": {
"description": "CodeGemma es un modelo de lenguaje ligero especializado en diversas tareas de programación, que admite iteraciones rápidas e integración."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama es un LLM enfocado en la generación y discusión de código, combinando un amplio soporte para lenguajes de programación, adecuado para entornos de desarrolladores."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama es un LLM enfocado en la generación y discusión de código, que combina un amplio soporte para lenguajes de programación, adecuado para entornos de desarrolladores."
+ },
"codellama:13b": {
"description": "Code Llama es un LLM enfocado en la generación y discusión de código, combinando un amplio soporte para lenguajes de programación, adecuado para entornos de desarrolladores."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ es un modelo de lenguaje de gran tamaño de alto rendimiento, diseñado para escenarios empresariales reales y aplicaciones complejas."
},
+ "dall-e-2": {
+ "description": "El segundo modelo DALL·E, que admite generación de imágenes más realistas y precisas, con una resolución cuatro veces mayor que la de la primera generación."
+ },
+ "dall-e-3": {
+ "description": "El modelo DALL·E más reciente, lanzado en noviembre de 2023. Admite generación de imágenes más realistas y precisas, con una mayor capacidad de detalle."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct ofrece capacidades de procesamiento de instrucciones de alta fiabilidad, soportando aplicaciones en múltiples industrias."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 es un modelo de inferencia impulsado por aprendizaje reforzado (RL) que aborda los problemas de repetitividad y legibilidad en el modelo. Antes de RL, DeepSeek-R1 introdujo datos de arranque en frío, optimizando aún más el rendimiento de la inferencia. Su desempeño en tareas matemáticas, de código e inferencia es comparable al de OpenAI-o1, y ha mejorado su efectividad general a través de métodos de entrenamiento cuidadosamente diseñados."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "El modelo de destilación DeepSeek-R1 optimiza el rendimiento de inferencia mediante aprendizaje por refuerzo y datos de arranque en frío, actualizando el estándar de múltiples tareas en modelos de código abierto."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B es un modelo de destilación desarrollado a partir de Llama-3.1-8B. Este modelo se ajustó utilizando muestras generadas por DeepSeek-R1, mostrando una excelente capacidad de inferencia. Ha tenido un buen desempeño en múltiples pruebas de referencia, alcanzando una precisión del 89.1% en MATH-500, una tasa de aprobación del 50.4% en AIME 2024, y una puntuación de 1205 en CodeForces, demostrando una fuerte capacidad matemática y de programación como modelo de 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "El modelo de destilación DeepSeek-R1 optimiza el rendimiento de inferencia mediante aprendizaje por refuerzo y datos de arranque en frío, actualizando el estándar de múltiples tareas en modelos de código abierto."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "El modelo de destilación DeepSeek-R1 optimiza el rendimiento de inferencia mediante aprendizaje por refuerzo y datos de arranque en frío, actualizando el estándar de múltiples tareas en modelos de código abierto."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B es un modelo obtenido mediante destilación de conocimiento basado en Qwen2.5-32B. Este modelo se ajustó utilizando 800,000 muestras seleccionadas generadas por DeepSeek-R1, mostrando un rendimiento excepcional en múltiples campos como matemáticas, programación e inferencia. Ha obtenido excelentes resultados en varias pruebas de referencia, alcanzando una precisión del 94.3% en MATH-500, demostrando una fuerte capacidad de razonamiento matemático."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B es un modelo obtenido mediante destilación de conocimiento basado en Qwen2.5-Math-7B. Este modelo se ajustó utilizando 800,000 muestras seleccionadas generadas por DeepSeek-R1, mostrando un rendimiento excepcional en múltiples campos como matemáticas, programación e inferencia. Ha obtenido excelentes resultados en varias pruebas de referencia, alcanzando una precisión del 92.8% en MATH-500, una tasa de aprobación del 55.5% en AIME 2024, y una puntuación de 1189 en CodeForces, demostrando una fuerte capacidad matemática y de programación como modelo de 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 combina las excelentes características de versiones anteriores, mejorando la capacidad general y de codificación."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 es un modelo de lenguaje de expertos mixtos (MoE) con 6710 millones de parámetros, que utiliza atención latente de múltiples cabezas (MLA) y la arquitectura DeepSeekMoE, combinando una estrategia de balanceo de carga sin pérdidas auxiliares para optimizar la eficiencia de inferencia y entrenamiento. Al ser preentrenado en 14.8 billones de tokens de alta calidad y realizar ajustes supervisados y aprendizaje reforzado, DeepSeek-V3 supera en rendimiento a otros modelos de código abierto, acercándose a los modelos cerrados líderes."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B es un modelo avanzado entrenado para diálogos de alta complejidad."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "LLM eficiente de última generación, experto en razonamiento, matemáticas y programación."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 es un modelo de lenguaje visual de expertos mixtos (MoE) desarrollado sobre DeepSeekMoE-27B, que utiliza una arquitectura MoE de activación dispersa, logrando un rendimiento excepcional al activar solo 4.5B de parámetros. Este modelo destaca en múltiples tareas como preguntas visuales, reconocimiento óptico de caracteres, comprensión de documentos/tablas/gráficos y localización visual."
+ },
"deepseek-chat": {
"description": "Un nuevo modelo de código abierto que fusiona capacidades generales y de codificación, que no solo conserva la capacidad de diálogo general del modelo Chat original y la potente capacidad de procesamiento de código del modelo Coder, sino que también se alinea mejor con las preferencias humanas. Además, DeepSeek-V2.5 ha logrado mejoras significativas en tareas de escritura, seguimiento de instrucciones y más."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B es un modelo de lenguaje de código, entrenado con 20 billones de datos, de los cuales el 87% son código y el 13% son lenguajes en chino e inglés. El modelo introduce un tamaño de ventana de 16K y tareas de llenado de espacios, proporcionando funciones de autocompletado de código a nivel de proyecto y llenado de fragmentos."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 es un modelo de código de expertos híbrido de código abierto, que destaca en tareas de codificación, comparable a GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 es un modelo de código de expertos híbrido de código abierto, que destaca en tareas de codificación, comparable a GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 es un modelo de inferencia impulsado por aprendizaje reforzado (RL) que aborda los problemas de repetitividad y legibilidad en el modelo. Antes de RL, DeepSeek-R1 introdujo datos de arranque en frío, optimizando aún más el rendimiento de la inferencia. Su desempeño en tareas matemáticas, de código e inferencia es comparable al de OpenAI-o1, y ha mejorado su efectividad general a través de métodos de entrenamiento cuidadosamente diseñados."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1, el modelo más grande e inteligente del conjunto DeepSeek, ha sido destilado en la arquitectura Llama 70B. Basado en pruebas de referencia y evaluaciones humanas, este modelo es más inteligente que el Llama 70B original, destacándose especialmente en tareas que requieren precisión matemática y factual."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "El modelo de la serie DeepSeek-R1-Distill se obtiene mediante la técnica de destilación de conocimiento, ajustando muestras generadas por DeepSeek-R1 a modelos de código abierto como Qwen y Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "El modelo de la serie DeepSeek-R1-Distill se obtiene mediante la técnica de destilación de conocimiento, ajustando muestras generadas por DeepSeek-R1 a modelos de código abierto como Qwen y Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "El modelo de la serie DeepSeek-R1-Distill se obtiene mediante la técnica de destilación de conocimiento, ajustando muestras generadas por DeepSeek-R1 a modelos de código abierto como Qwen y Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "El modelo de la serie DeepSeek-R1-Distill se obtiene mediante la técnica de destilación de conocimiento, ajustando muestras generadas por DeepSeek-R1 a modelos de código abierto como Qwen y Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "El modelo de la serie DeepSeek-R1-Distill se obtiene mediante la técnica de destilación de conocimiento, ajustando muestras generadas por DeepSeek-R1 a modelos de código abierto como Qwen y Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "Modelo de inferencia lanzado por DeepSeek. Antes de proporcionar la respuesta final, el modelo genera primero una cadena de pensamiento para mejorar la precisión de la respuesta final."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 es un modelo de lenguaje Mixture-of-Experts eficiente, adecuado para necesidades de procesamiento económico."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B es el modelo de código de diseño de DeepSeek, que ofrece una potente capacidad de generación de código."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 es un modelo MoE desarrollado por Hangzhou DeepSeek Artificial Intelligence Technology Research Co., Ltd., que ha destacado en múltiples evaluaciones, ocupando el primer lugar en la lista de modelos de código abierto. En comparación con el modelo V2.5, la velocidad de generación se ha incrementado tres veces, brindando a los usuarios una experiencia de uso más rápida y fluida."
+ },
"deepseek/deepseek-chat": {
"description": "Un nuevo modelo de código abierto que fusiona capacidades generales y de codificación, no solo conserva la capacidad de diálogo general del modelo Chat original y la potente capacidad de procesamiento de código del modelo Coder, sino que también se alinea mejor con las preferencias humanas. Además, DeepSeek-V2.5 ha logrado mejoras significativas en tareas de escritura, seguimiento de instrucciones y más."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 mejora significativamente la capacidad de razonamiento del modelo con muy pocos datos etiquetados. Antes de proporcionar la respuesta final, el modelo genera una cadena de pensamiento para mejorar la precisión de la respuesta final."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B es un modelo de lenguaje de gran tamaño basado en Llama3.3 70B, que utiliza el ajuste fino de la salida de DeepSeek R1 para lograr un rendimiento competitivo comparable a los modelos de vanguardia de gran tamaño."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B es un modelo de lenguaje grande destilado basado en Llama-3.1-8B-Instruct, entrenado utilizando la salida de DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B es un modelo de lenguaje grande destilado basado en Qwen 2.5 14B, entrenado utilizando la salida de DeepSeek R1. Este modelo ha superado a o1-mini de OpenAI en múltiples pruebas de referencia, logrando resultados de vanguardia en modelos densos. A continuación se presentan algunos resultados de las pruebas de referencia:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCalificación de CodeForces: 1481\nEste modelo, ajustado a partir de la salida de DeepSeek R1, muestra un rendimiento competitivo comparable al de modelos de vanguardia de mayor escala."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B es un modelo de lenguaje grande destilado basado en Qwen 2.5 32B, entrenado utilizando la salida de DeepSeek R1. Este modelo ha superado a o1-mini de OpenAI en múltiples pruebas de referencia, logrando resultados de vanguardia en modelos densos. A continuación se presentan algunos resultados de las pruebas de referencia:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCalificación de CodeForces: 1691\nEste modelo, ajustado a partir de la salida de DeepSeek R1, muestra un rendimiento competitivo comparable al de modelos de vanguardia de mayor escala."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 es el último modelo de código abierto lanzado por el equipo de DeepSeek, que cuenta con un rendimiento de inferencia excepcional, especialmente en tareas de matemáticas, programación y razonamiento, alcanzando niveles comparables al modelo o1 de OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 mejora significativamente la capacidad de razonamiento del modelo con muy pocos datos etiquetados. Antes de proporcionar la respuesta final, el modelo genera una cadena de pensamiento para mejorar la precisión de la respuesta final."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 ha logrado un avance significativo en la velocidad de inferencia en comparación con modelos anteriores. Se clasifica como el número uno entre los modelos de código abierto y puede competir con los modelos cerrados más avanzados del mundo. DeepSeek-V3 utiliza la arquitectura de atención multi-cabeza (MLA) y DeepSeekMoE, que han sido completamente validadas en DeepSeek-V2. Además, DeepSeek-V3 ha introducido una estrategia auxiliar sin pérdidas para el balanceo de carga y ha establecido objetivos de entrenamiento de predicción de múltiples etiquetas para lograr un rendimiento más robusto."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 ha logrado un avance significativo en la velocidad de inferencia en comparación con modelos anteriores. Se clasifica como el número uno entre los modelos de código abierto y puede competir con los modelos cerrados más avanzados del mundo. DeepSeek-V3 utiliza la arquitectura de atención multi-cabeza (MLA) y DeepSeekMoE, que han sido completamente validadas en DeepSeek-V2. Además, DeepSeek-V3 ha introducido una estrategia auxiliar sin pérdidas para el balanceo de carga y ha establecido objetivos de entrenamiento de predicción de múltiples etiquetas para lograr un rendimiento más robusto."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite es un modelo ligero de nueva generación, con una velocidad de respuesta extrema, alcanzando niveles de rendimiento y latencia de clase mundial."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k es una versión mejorada de Doubao-1.5-Pro, con un aumento del 10% en el rendimiento general. Soporta razonamiento con una ventana de contexto de 256k y una longitud de salida de hasta 12k tokens. Mayor rendimiento, ventana más grande y una excelente relación calidad-precio, adecuado para una amplia gama de escenarios de aplicación."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro es un modelo de nueva generación, con un rendimiento completamente mejorado, destacando en conocimientos, código, razonamiento, entre otros."
+ },
"emohaa": {
"description": "Emohaa es un modelo psicológico con capacidades de consulta profesional, ayudando a los usuarios a comprender problemas emocionales."
},
+ "ernie-3.5-128k": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, cubre una vasta cantidad de corpus en chino e inglés, con potentes capacidades generales que satisfacen la mayoría de los requisitos de preguntas y respuestas en diálogos, generación creativa y aplicaciones de plugins; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas."
+ },
+ "ernie-3.5-8k": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, cubre una vasta cantidad de corpus en chino e inglés, con potentes capacidades generales que satisfacen la mayoría de los requisitos de preguntas y respuestas en diálogos, generación creativa y aplicaciones de plugins; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, cubre una vasta cantidad de corpus en chino e inglés, con potentes capacidades generales que satisfacen la mayoría de los requisitos de preguntas y respuestas en diálogos, generación creativa y aplicaciones de plugins; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, de ultra gran escala, ha logrado una actualización completa de capacidades en comparación con ERNIE 3.5, siendo ampliamente aplicable en escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, de ultra gran escala, ha logrado una actualización completa de capacidades en comparación con ERNIE 3.5, siendo ampliamente aplicable en escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, de ultra gran escala, muestra un rendimiento excepcional en general, siendo ampliamente aplicable en escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas. En comparación con ERNIE 4.0, presenta un rendimiento superior."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, de ultra gran escala, muestra un rendimiento excepcional en general, siendo ampliamente aplicable en escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas. En comparación con ERNIE 4.0, presenta un rendimiento superior."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "El modelo de lenguaje grande de bandera de Baidu, desarrollado internamente, de ultra gran escala, muestra un rendimiento excepcional en general, siendo ampliamente aplicable en escenarios de tareas complejas en diversos campos; soporta la integración automática con el plugin de búsqueda de Baidu, garantizando la actualidad de la información de preguntas y respuestas. En comparación con ERNIE 4.0, presenta un rendimiento superior."
+ },
+ "ernie-char-8k": {
+ "description": "Modelo de lenguaje grande de escenario vertical desarrollado internamente por Baidu, adecuado para aplicaciones como NPC de juegos, diálogos de servicio al cliente y juegos de rol de diálogos, con un estilo de personaje más distintivo y consistente, y una mayor capacidad de seguimiento de instrucciones y rendimiento de inferencia."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Modelo de lenguaje grande de escenario vertical desarrollado internamente por Baidu, adecuado para aplicaciones como NPC de juegos, diálogos de servicio al cliente y juegos de rol de diálogos, con un estilo de personaje más distintivo y consistente, y una mayor capacidad de seguimiento de instrucciones y rendimiento de inferencia."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite es un modelo de lenguaje grande ligero desarrollado internamente por Baidu, que combina un excelente rendimiento del modelo con una buena capacidad de inferencia, adecuado para su uso en tarjetas de aceleración de IA de bajo consumo."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Modelo de lenguaje grande ligero desarrollado internamente por Baidu, que combina un excelente rendimiento del modelo con una buena capacidad de inferencia, con un rendimiento superior al de ERNIE Lite, adecuado para su uso en tarjetas de aceleración de IA de bajo consumo."
+ },
+ "ernie-novel-8k": {
+ "description": "Modelo de lenguaje grande general desarrollado internamente por Baidu, con ventajas notables en la capacidad de continuar novelas, también aplicable en escenarios de cortometrajes y películas."
+ },
+ "ernie-speed-128k": {
+ "description": "El modelo de lenguaje grande de alto rendimiento desarrollado internamente por Baidu, lanzado en 2024, tiene capacidades generales excepcionales, adecuado como modelo base para ajustes finos, manejando mejor problemas específicos de escenarios, y con un excelente rendimiento de inferencia."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "El modelo de lenguaje grande de alto rendimiento desarrollado internamente por Baidu, lanzado en 2024, tiene capacidades generales excepcionales, con un rendimiento superior al de ERNIE Speed, adecuado como modelo base para ajustes finos, manejando mejor problemas específicos de escenarios, y con un excelente rendimiento de inferencia."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny es un modelo de lenguaje grande de alto rendimiento desarrollado internamente por Baidu, con los costos de implementación y ajuste más bajos entre los modelos de la serie Wenxin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Ajuste) ofrece un rendimiento estable y ajustable, siendo una opción ideal para soluciones de tareas complejas."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro es el modelo de IA de alto rendimiento de Google, diseñado para la escalabilidad en una amplia gama de tareas."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash es el último modelo de IA multimodal de Google, que cuenta con una capacidad de procesamiento rápido, admite entradas de texto, imágenes y videos, y es adecuado para la escalabilidad eficiente en diversas tareas."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 es un modelo multimodal eficiente, que admite la escalabilidad para aplicaciones amplias."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 es un modelo multimodal eficiente, que admite una amplia gama de aplicaciones."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 está diseñado para manejar escenarios de tareas a gran escala, ofreciendo una velocidad de procesamiento inigualable."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B es un modelo multimodal eficiente que admite una amplia gama de aplicaciones."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 es el último modelo experimental, con mejoras significativas en el rendimiento tanto en casos de uso de texto como multimodal."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 ofrece capacidades de procesamiento multimodal optimizadas, adecuadas para una variedad de escenarios de tareas complejas."
+ "description": "Gemini 1.5 Flash 0827 ofrece capacidades de procesamiento multimodal optimizadas, adecuadas para diversas tareas complejas."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash es el último modelo de IA multimodal de Google, con capacidades de procesamiento rápido, que admite entradas de texto, imagen y video, adecuado para la escalabilidad eficiente en diversas tareas."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002 es el último modelo listo para producción, que ofrece una calidad de salida superior, especialmente en tareas matemáticas, contextos largos y tareas visuales."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 ofrece una excelente capacidad de procesamiento multimodal, brindando mayor flexibilidad para el desarrollo de aplicaciones."
+ "description": "Gemini 1.5 Pro 0801 ofrece excelentes capacidades de procesamiento multimodal, brindando mayor flexibilidad para el desarrollo de aplicaciones."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 combina las últimas tecnologías de optimización, ofreciendo una capacidad de procesamiento de datos multimodal más eficiente."
+ "description": "Gemini 1.5 Pro 0827 combina las últimas tecnologías optimizadas para brindar capacidades de procesamiento de datos multimodales más eficientes."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro admite hasta 2 millones de tokens, siendo una opción ideal para modelos multimodales de tamaño medio, adecuados para un soporte multifacético en tareas complejas."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash ofrece funciones y mejoras de próxima generación, incluyendo velocidad excepcional, uso de herramientas nativas, generación multimodal y una ventana de contexto de 1M tokens."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash ofrece funciones y mejoras de próxima generación, incluyendo velocidad excepcional, uso de herramientas nativas, generación multimodal y una ventana de contexto de 1M tokens."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Variante del modelo Gemini 2.0 Flash, optimizada para objetivos como la rentabilidad y la baja latencia."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Variante del modelo Gemini 2.0 Flash, optimizada para objetivos como la rentabilidad y la baja latencia."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Un modelo Gemini 2.0 Flash optimizado para objetivos de costo-efectividad y baja latencia."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp es el último modelo experimental de IA multimodal de Google, con características de próxima generación, velocidad excepcional, llamadas nativas a herramientas y generación multimodal."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp es el último modelo experimental de IA multimodal de Google, con características de próxima generación, velocidad excepcional, llamadas nativas a herramientas y generación multimodal."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental es el último modelo de IA multimodal experimental de Google, con mejoras de calidad en comparación con versiones anteriores, especialmente en conocimiento del mundo, código y contextos largos."
+ },
"gemma-7b-it": {
"description": "Gemma 7B es adecuado para el procesamiento de tareas de pequeña y mediana escala, combinando rentabilidad."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 es un modelo eficiente lanzado por Google, que abarca una variedad de escenarios de aplicación desde aplicaciones pequeñas hasta procesamiento de datos complejos."
},
- "general": {
- "description": "Spark Lite es un modelo de lenguaje grande y ligero, con una latencia extremadamente baja y una capacidad de procesamiento eficiente, completamente gratuito y abierto, que soporta funciones de búsqueda en línea en tiempo real. Su característica de respuesta rápida lo hace destacar en aplicaciones de inferencia y ajuste de modelos en dispositivos de baja potencia, brindando a los usuarios una excelente relación costo-beneficio y una experiencia inteligente, especialmente en escenarios de preguntas y respuestas, generación de contenido y búsqueda."
- },
"generalv3": {
"description": "Spark Pro es un modelo de lenguaje grande de alto rendimiento optimizado para campos profesionales, enfocado en matemáticas, programación, medicina, educación y más, y soporta búsqueda en línea y plugins integrados como clima y fecha. Su modelo optimizado muestra un rendimiento excepcional y eficiente en preguntas y respuestas complejas, comprensión del lenguaje y creación de textos de alto nivel, siendo la opción ideal para escenarios de aplicación profesional."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 es la última versión del modelo, diseñada para tareas altamente complejas y diversas, con un rendimiento excepcional."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat muestra un alto rendimiento en semántica, matemáticas, razonamiento, código y conocimiento. También cuenta con navegación web, ejecución de código, llamadas a herramientas personalizadas y razonamiento de textos largos. Soporta 26 idiomas, incluidos japonés, coreano y alemán."
+ },
"glm-4-air": {
"description": "GLM-4-Air es una versión de alto costo-beneficio, con un rendimiento cercano al GLM-4, ofreciendo velocidad y precios asequibles."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash es la opción ideal para tareas simples, con la velocidad más rápida y el precio más bajo."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX es una versión mejorada de Flash, con una velocidad de inferencia ultrarrápida."
+ },
"glm-4-long": {
"description": "GLM-4-Long admite entradas de texto extremadamente largas, adecuado para tareas de memoria y procesamiento de documentos a gran escala."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V proporciona una poderosa capacidad de comprensión e inferencia de imágenes, soportando diversas tareas visuales."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash se centra en la comprensión eficiente de una única imagen, adecuada para escenarios de análisis de imágenes rápidos, como análisis de imágenes en tiempo real o procesamiento por lotes de imágenes."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus tiene la capacidad de entender contenido de video y múltiples imágenes, adecuado para tareas multimodales."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 ofrece capacidades de procesamiento multimodal optimizadas, adecuadas para una variedad de escenarios de tareas complejas."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview posee una poderosa capacidad de razonamiento complejo, destacándose en áreas como razonamiento lógico, matemáticas y programación."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash ofrece funciones y mejoras de próxima generación, incluyendo velocidad excepcional, uso de herramientas nativas, generación multimodal y una ventana de contexto de 1M tokens."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental es el último modelo de IA multimodal experimental de Google, con mejoras de calidad en comparación con versiones anteriores, especialmente en conocimiento del mundo, código y contextos largos."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 combina las últimas tecnologías de optimización, ofreciendo una capacidad de procesamiento de datos multimodal más eficiente."
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash ofrece capacidades de procesamiento multimodal optimizadas, adecuadas para una variedad de escenarios de tareas complejas."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro combina las últimas tecnologías de optimización, proporcionando una capacidad de procesamiento de datos multimodal más eficiente."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 es un modelo eficiente lanzado por Google, que abarca una variedad de escenarios de aplicación desde aplicaciones pequeñas hasta procesamiento de datos complejos."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 continúa con el concepto de diseño ligero y eficiente."
},
+ "google/gemma-2-2b-it": {
+ "description": "Modelo de ajuste de instrucciones ligero de Google."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 es un modelo eficiente lanzado por Google, que abarca una variedad de escenarios de aplicación desde aplicaciones pequeñas hasta procesamiento de datos complejos."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 es una serie de modelos de texto de código abierto y ligeros de Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, adecuado para diversas tareas de generación y comprensión de texto, actualmente apunta a gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo, un modelo eficiente proporcionado por OpenAI, es adecuado para tareas de conversación y generación de texto, con soporte para llamadas a funciones en paralelo."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k, un modelo de generación de texto de alta capacidad, adecuado para tareas complejas."
+ },
"gpt-4": {
"description": "GPT-4 ofrece una ventana de contexto más grande, capaz de manejar entradas de texto más largas, adecuado para escenarios que requieren integración de información amplia y análisis de datos."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "El último modelo GPT-4 Turbo cuenta con funciones visuales. Ahora, las solicitudes visuales pueden utilizar el modo JSON y llamadas a funciones. GPT-4 Turbo es una versión mejorada que ofrece soporte rentable para tareas multimodales. Encuentra un equilibrio entre precisión y eficiencia, adecuado para aplicaciones que requieren interacción en tiempo real."
},
- "gpt-4-1106-vision-preview": {
- "description": "El último modelo GPT-4 Turbo cuenta con funciones visuales. Ahora, las solicitudes visuales pueden utilizar el modo JSON y llamadas a funciones. GPT-4 Turbo es una versión mejorada que ofrece soporte rentable para tareas multimodales. Encuentra un equilibrio entre precisión y eficiencia, adecuado para aplicaciones que requieren interacción en tiempo real."
- },
"gpt-4-32k": {
"description": "GPT-4 ofrece una ventana de contexto más grande, capaz de manejar entradas de texto más largas, adecuado para escenarios que requieren integración de información amplia y análisis de datos."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "El último modelo GPT-4 Turbo cuenta con funciones visuales. Ahora, las solicitudes visuales pueden utilizar el modo JSON y llamadas a funciones. GPT-4 Turbo es una versión mejorada que ofrece soporte rentable para tareas multimodales. Encuentra un equilibrio entre precisión y eficiencia, adecuado para aplicaciones que requieren interacción en tiempo real."
},
+ "gpt-4.5-preview": {
+ "description": "Versión de investigación de GPT-4.5, que es nuestro modelo GPT más grande y potente hasta la fecha. Posee un amplio conocimiento del mundo y puede comprender mejor la intención del usuario, lo que lo hace destacar en tareas creativas y planificación autónoma. GPT-4.5 acepta entradas de texto e imagen y genera salidas de texto (incluidas salidas estructuradas). Soporta funciones clave para desarrolladores, como llamadas a funciones, API por lotes y salida en streaming. En tareas que requieren pensamiento creativo, abierto y diálogo (como escritura, aprendizaje o exploración de nuevas ideas), GPT-4.5 brilla especialmente. La fecha límite de conocimiento es octubre de 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o es un modelo dinámico que se actualiza en tiempo real para mantener la versión más actual. Combina una poderosa comprensión y generación de lenguaje, adecuado para aplicaciones a gran escala, incluyendo servicio al cliente, educación y soporte técnico."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o es un modelo dinámico que se actualiza en tiempo real para mantener la versión más actual. Combina una poderosa comprensión y generación de lenguaje, adecuado para aplicaciones a gran escala, incluyendo servicio al cliente, educación y soporte técnico."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o es un modelo dinámico que se actualiza en tiempo real para mantener la versión más reciente. Combina una poderosa comprensión del lenguaje con habilidades de generación, adecuada para escenarios de aplicación a gran escala, incluidos servicio al cliente, educación y soporte técnico."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Modelo de audio GPT-4o, que admite entrada y salida de audio."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini es el último modelo lanzado por OpenAI después de GPT-4 Omni, que admite entradas de texto e imagen y genera texto como salida. Como su modelo más avanzado de menor tamaño, es mucho más económico que otros modelos de vanguardia recientes y es más de un 60% más barato que GPT-3.5 Turbo. Mantiene una inteligencia de vanguardia mientras ofrece una relación calidad-precio significativa. GPT-4o mini obtuvo un puntaje del 82% en la prueba MMLU y actualmente se clasifica por encima de GPT-4 en preferencias de chat."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Versión en tiempo real de GPT-4o-mini, que admite entrada y salida de audio y texto en tiempo real."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Versión en tiempo real de GPT-4o, que admite entrada y salida de audio y texto en tiempo real."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Versión en tiempo real de GPT-4o, que admite entrada y salida de audio y texto en tiempo real."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Versión en tiempo real de GPT-4o, que admite entrada y salida de audio y texto en tiempo real."
+ },
+ "grok-2-1212": {
+ "description": "Este modelo ha mejorado en precisión, cumplimiento de instrucciones y capacidades multilingües."
+ },
+ "grok-2-vision-1212": {
+ "description": "Este modelo ha mejorado en precisión, cumplimiento de instrucciones y capacidades multilingües."
+ },
+ "grok-beta": {
+ "description": "Ofrece un rendimiento comparable al de Grok 2, pero con mayor eficiencia, velocidad y funcionalidad."
+ },
+ "grok-vision-beta": {
+ "description": "El último modelo de comprensión de imágenes, capaz de manejar una amplia variedad de información visual, incluyendo documentos, gráficos, capturas de pantalla y fotos."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B es un modelo de lenguaje que combina creatividad e inteligencia, fusionando múltiples modelos de vanguardia."
},
+ "hunyuan-code": {
+ "description": "El último modelo de generación de código de Hunyuan, entrenado con 200B de datos de código de alta calidad, con medio año de entrenamiento de datos SFT de alta calidad, aumentando la longitud de la ventana de contexto a 8K, destacándose en métricas automáticas de generación de código en cinco lenguajes; en evaluaciones de calidad humana de tareas de código en diez aspectos en cinco lenguajes, su rendimiento se encuentra en la primera categoría."
+ },
+ "hunyuan-functioncall": {
+ "description": "El último modelo FunctionCall de Hunyuan con arquitectura MOE, entrenado con datos de FunctionCall de alta calidad, con una ventana de contexto de 32K, liderando en múltiples dimensiones de métricas de evaluación."
+ },
+ "hunyuan-large": {
+ "description": "El modelo Hunyuan-large tiene un total de aproximadamente 389B de parámetros, con aproximadamente 52B de parámetros activados, siendo el modelo MoE de código abierto con la mayor escala de parámetros y el mejor rendimiento en la arquitectura Transformer en la industria actual."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Especializado en tareas de texto largo como resúmenes de documentos y preguntas y respuestas de documentos, también tiene la capacidad de manejar tareas generales de generación de texto. Destaca en el análisis y generación de textos largos, pudiendo abordar eficazmente las necesidades de procesamiento de contenido largo y complejo."
+ },
+ "hunyuan-lite": {
+ "description": "Actualizado a una estructura MOE, con una ventana de contexto de 256k, lidera en múltiples conjuntos de evaluación en NLP, código, matemáticas, industria y más, superando a muchos modelos de código abierto."
+ },
+ "hunyuan-lite-vision": {
+ "description": "El modelo multimodal más reciente de 7B de Hunyuan, con una ventana de contexto de 32K, soporta diálogos multimodales en chino e inglés, reconocimiento de objetos en imágenes, comprensión de documentos y tablas, matemáticas multimodales, entre otros, superando a modelos competidores de 7B en múltiples dimensiones de evaluación."
+ },
+ "hunyuan-pro": {
+ "description": "Modelo de texto largo MOE-32K con un tamaño de parámetros de billones. Alcanzando niveles de liderazgo absoluto en varios benchmarks, con capacidades complejas de instrucciones y razonamiento, habilidades matemáticas complejas, soporte para llamadas a funciones, optimizado para aplicaciones en traducción multilingüe, finanzas, derecho y medicina."
+ },
+ "hunyuan-role": {
+ "description": "El último modelo de rol de Hunyuan, un modelo de rol ajustado y entrenado oficialmente por Hunyuan, que se basa en el modelo Hunyuan y se entrena con un conjunto de datos de escenarios de rol, logrando un mejor rendimiento en escenarios de rol."
+ },
+ "hunyuan-standard": {
+ "description": "Adopta una estrategia de enrutamiento mejorada, al tiempo que mitiga problemas de equilibrio de carga y convergencia de expertos. En el caso de textos largos, el índice de precisión alcanza el 99.9%. MOE-32K ofrece una mejor relación calidad-precio, equilibrando efectividad y costo, permitiendo el procesamiento de entradas de texto largo."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Adopta una estrategia de enrutamiento mejorada, al tiempo que mitiga problemas de equilibrio de carga y convergencia de expertos. En el caso de textos largos, el índice de precisión alcanza el 99.9%. MOE-256K rompe barreras en longitud y efectividad, ampliando enormemente la longitud de entrada permitida."
+ },
+ "hunyuan-standard-vision": {
+ "description": "El modelo multimodal más reciente de Hunyuan, que soporta respuestas en múltiples idiomas, con capacidades equilibradas en chino e inglés."
+ },
+ "hunyuan-translation": {
+ "description": "Soporta la traducción entre 15 idiomas, incluyendo chino, inglés, japonés, francés, portugués, español, turco, ruso, árabe, coreano, italiano, alemán, vietnamita, malayo e indonesio, con evaluación automatizada basada en el conjunto de evaluación de traducción en múltiples escenarios y puntuación COMET, superando en general a modelos de tamaño similar en la capacidad de traducción entre idiomas comunes."
+ },
+ "hunyuan-translation-lite": {
+ "description": "El modelo de traducción Hunyuan admite traducción en un formato de diálogo natural; soporta la traducción entre chino, inglés, japonés, francés, portugués, español, turco, ruso, árabe, coreano, italiano, alemán, vietnamita, malayo e indonesio."
+ },
+ "hunyuan-turbo": {
+ "description": "Versión preliminar de la nueva generación del modelo de lenguaje de Hunyuan, que utiliza una nueva estructura de modelo de expertos mixtos (MoE), con una eficiencia de inferencia más rápida y un rendimiento más fuerte en comparación con Hunyuan-Pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Versión fija de hunyuan-turbo del 20 de noviembre de 2024, una versión intermedia entre hunyuan-turbo y hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Optimización de esta versión: escalado de instrucciones de datos, mejora significativa de la capacidad de generalización del modelo; mejora significativa de las capacidades de matemáticas, código y razonamiento lógico; optimización de la comprensión de texto y de palabras relacionadas; optimización de la calidad de generación de contenido en la creación de texto."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Optimización de la experiencia general, incluyendo comprensión de NLP, creación de texto, conversación casual, preguntas y respuestas de conocimiento, traducción, entre otros; mejora de la humanización, optimización de la inteligencia emocional del modelo; mejora de la capacidad del modelo para aclarar proactivamente en caso de ambigüedad en la intención; mejora de la capacidad de manejo de problemas de análisis de palabras; mejora de la calidad y la interactividad de la creación; mejora de la experiencia en múltiples turnos."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "El nuevo modelo insignia de lenguaje visual de Hunyuan de nueva generación, que utiliza una nueva estructura de modelo de expertos mixtos (MoE), mejorando de manera integral las capacidades de reconocimiento básico, creación de contenido, preguntas y respuestas de conocimiento, y análisis y razonamiento en comparación con la generación anterior de modelos."
+ },
+ "hunyuan-vision": {
+ "description": "El último modelo multimodal de Hunyuan, que admite la entrada de imágenes y texto para generar contenido textual."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "El innovador modelo de código abierto InternLM2.5 mejora la inteligencia del diálogo mediante un gran número de parámetros."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 ofrece soluciones de diálogo inteligente en múltiples escenarios."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "El modelo Llama 3.1 70B Instruct, con 70B de parámetros, puede ofrecer un rendimiento excepcional en tareas de generación de texto y de instrucciones a gran escala."
+ "internlm2-pro-chat": {
+ "description": "Modelo de versión anterior que seguimos manteniendo, disponible en opciones de 7B y 20B parámetros."
+ },
+ "internlm2.5-latest": {
+ "description": "Nuestra última serie de modelos, con un rendimiento de inferencia excepcional, que admite una longitud de contexto de 1M y una mayor capacidad de seguimiento de instrucciones y llamadas a herramientas."
+ },
+ "internlm3-latest": {
+ "description": "Nuestra última serie de modelos, con un rendimiento de inferencia excepcional, lidera el mercado de modelos de código abierto de tamaño similar. Apunta por defecto a nuestra serie de modelos InternLM3 más reciente."
+ },
+ "jina-deepsearch-v1": {
+ "description": "La búsqueda profunda combina la búsqueda en la web, la lectura y el razonamiento para realizar investigaciones exhaustivas. Puedes considerarlo como un agente que acepta tus tareas de investigación: realiza una búsqueda amplia y pasa por múltiples iteraciones antes de proporcionar una respuesta. Este proceso implica una investigación continua, razonamiento y resolución de problemas desde diferentes ángulos. Esto es fundamentalmente diferente de los grandes modelos estándar que generan respuestas directamente a partir de datos preentrenados y de los sistemas RAG tradicionales que dependen de búsquedas superficiales únicas."
+ },
+ "kimi-latest": {
+ "description": "El producto asistente inteligente Kimi utiliza el último modelo grande de Kimi, que puede incluir características que aún no están estables. Soporta la comprensión de imágenes y seleccionará automáticamente el modelo de facturación de 8k/32k/128k según la longitud del contexto de la solicitud."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM es un modelo de lenguaje experimental y específico para tareas, entrenado para cumplir con los principios de la ciencia del aprendizaje, capaz de seguir instrucciones sistemáticas en escenarios de enseñanza y aprendizaje, actuando como un tutor experto, entre otros."
+ },
+ "lite": {
+ "description": "Spark Lite es un modelo de lenguaje grande y ligero, con una latencia extremadamente baja y una capacidad de procesamiento eficiente, completamente gratuito y de código abierto, que admite funciones de búsqueda en línea en tiempo real. Su característica de respuesta rápida lo hace destacar en aplicaciones de inferencia y ajuste de modelos en dispositivos de baja potencia, brindando a los usuarios una excelente relación costo-beneficio y experiencia inteligente, especialmente en escenarios de preguntas y respuestas, generación de contenido y búsqueda."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B ofrece una capacidad de razonamiento AI más potente, adecuada para aplicaciones complejas, soportando un procesamiento computacional extenso y garantizando eficiencia y precisión."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B es un modelo de alto rendimiento que ofrece una rápida capacidad de generación de texto, ideal para aplicaciones que requieren eficiencia a gran escala y rentabilidad."
},
- "llama-3.1-8b-instruct": {
- "description": "El modelo Llama 3.1 8B Instruct, con 8B de parámetros, soporta la ejecución eficiente de tareas de instrucciones visuales, ofreciendo una excelente capacidad de generación de texto."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Capacidad excepcional de razonamiento visual en imágenes de alta resolución, adecuada para aplicaciones de comprensión visual."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "El modelo Llama 3.1 Sonar Huge Online, con 405B de parámetros, soporta una longitud de contexto de aproximadamente 127,000 tokens, diseñado para aplicaciones de chat en línea complejas."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Destaca en tareas como la descripción de imágenes y preguntas visuales, cruzando la brecha entre la generación de lenguaje y el razonamiento visual."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "El modelo Llama 3.1 Sonar Large Chat, con 70B de parámetros, soporta una longitud de contexto de aproximadamente 127,000 tokens, adecuado para tareas de chat fuera de línea complejas."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Capacidad avanzada de razonamiento de imágenes para aplicaciones de agentes de comprensión visual."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "El modelo Llama 3.1 Sonar Large Online, con 70B de parámetros, soporta una longitud de contexto de aproximadamente 127,000 tokens, adecuado para tareas de chat de alta capacidad y diversidad."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Destaca en tareas como la descripción de imágenes y preguntas visuales, cruzando la brecha entre la generación de lenguaje y el razonamiento visual."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "El modelo Llama 3.1 Sonar Small Chat, con 8B de parámetros, está diseñado para chat fuera de línea, soportando una longitud de contexto de aproximadamente 127,000 tokens."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 es el modelo de lenguaje de código abierto multilingüe más avanzado de la serie Llama, que ofrece un rendimiento comparable al modelo de 405B a un costo extremadamente bajo. Basado en la estructura Transformer, y mejorado en utilidad y seguridad a través de ajuste fino supervisado (SFT) y aprendizaje por refuerzo con retroalimentación humana (RLHF). Su versión ajustada para instrucciones está optimizada para diálogos multilingües, superando a muchos modelos de chat de código abierto y cerrado en múltiples benchmarks de la industria. La fecha límite de conocimiento es diciembre de 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "El modelo Llama 3.1 Sonar Small Online, con 8B de parámetros, soporta una longitud de contexto de aproximadamente 127,000 tokens, diseñado para chat en línea, capaz de manejar eficientemente diversas interacciones textuales."
+ "llama-3.3-70b-versatile": {
+ "description": "El modelo de lenguaje multilingüe Meta Llama 3.3 (LLM) es un modelo generativo preentrenado y ajustado para instrucciones de 70B (entrada/salida de texto). El modelo de texto puro ajustado para instrucciones de Llama 3.3 está optimizado para casos de uso de conversación multilingüe y supera a muchos modelos de chat de código abierto y cerrado en benchmarks industriales comunes."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B proporciona una capacidad de procesamiento de complejidad inigualable, diseñado a medida para proyectos de alta demanda."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral está diseñado para la investigación científica y el razonamiento matemático, proporcionando capacidades de cálculo efectivas y explicación de resultados."
},
+ "max-32k": {
+ "description": "Spark Max 32K está equipado con una capacidad de procesamiento de contexto grande, con una comprensión contextual más fuerte y habilidades de razonamiento lógico, soportando entradas de texto de 32K tokens, adecuado para la lectura de documentos largos, preguntas y respuestas de conocimiento privado y otros escenarios."
+ },
"meta-llama-3-70b-instruct": {
"description": "Un poderoso modelo de 70 mil millones de parámetros que sobresale en razonamiento, codificación y amplias aplicaciones de lenguaje."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) ofrece una excelente capacidad de procesamiento de lenguaje y una experiencia de interacción sobresaliente."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 ofrece excelentes capacidades de procesamiento del lenguaje y una experiencia de interacción excepcional."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) es un modelo de chat potente, que soporta necesidades de conversación complejas."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) ofrece soporte multilingüe, abarcando un amplio conocimiento en diversos campos."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Se destaca en tareas como descripción de imágenes y preguntas visuales, cruzando la brecha entre la generación de lenguaje y el razonamiento visual."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Se destaca en tareas como descripción de imágenes y preguntas visuales, cruzando la brecha entre la generación de lenguaje y el razonamiento visual."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Se destaca en tareas como descripción de imágenes y preguntas visuales, cruzando la brecha entre la generación de lenguaje y el razonamiento visual."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 es el modelo de lenguaje de código abierto multilingüe más avanzado de la serie Llama, que ofrece un rendimiento comparable al modelo de 405B a un costo muy bajo. Basado en la estructura Transformer, y mejorado en utilidad y seguridad a través de ajuste fino supervisado (SFT) y aprendizaje por refuerzo con retroalimentación humana (RLHF). Su versión ajustada por instrucciones está optimizada para diálogos multilingües, superando a muchos modelos de chat de código abierto y cerrado en múltiples benchmarks de la industria. La fecha de corte de conocimiento es diciembre de 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "El modelo de lenguaje grande multilingüe Meta Llama 3.3 (LLM) es un modelo generativo preentrenado y ajustado por instrucciones de 70B (entrada de texto/salida de texto). El modelo de texto puro ajustado por instrucciones de Llama 3.3 está optimizado para casos de uso de diálogo multilingüe y supera a muchos modelos de chat de código abierto y cerrados en benchmarks de la industria."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Se destaca en tareas como descripción de imágenes y preguntas visuales, cruzando la brecha entre la generación de lenguaje y el razonamiento visual."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite es ideal para entornos que requieren alto rendimiento y baja latencia."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "El modelo Llama 3.1 Turbo de 405B proporciona un soporte de contexto de gran capacidad para el procesamiento de grandes datos, destacándose en aplicaciones de inteligencia artificial a gran escala."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 es el modelo líder lanzado por Meta, que soporta hasta 405B de parámetros, aplicable en diálogos complejos, traducción multilingüe y análisis de datos."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B proporciona soporte de conversación eficiente en múltiples idiomas."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct optimiza los escenarios de conversación de alta calidad, con un rendimiento superior a muchos modelos cerrados."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct es la última versión lanzada por Meta, optimizada para generar diálogos de alta calidad, superando a muchos modelos cerrados líderes."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct está diseñado para conversaciones de alta calidad, destacándose en evaluaciones humanas, especialmente en escenarios de alta interacción."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 ofrece soporte multilingüe y es uno de los modelos generativos más avanzados de la industria."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Destaca en tareas como la descripción de imágenes y preguntas visuales, superando la brecha entre la generación de lenguaje y el razonamiento visual."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 está diseñado para manejar tareas que combinan datos visuales y textuales. Destaca en tareas como la descripción de imágenes y preguntas visuales, superando la brecha entre la generación de lenguaje y el razonamiento visual."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 es el modelo de lenguaje de código abierto multilingüe más avanzado de la serie Llama, que ofrece un rendimiento comparable al modelo de 405B a un costo extremadamente bajo. Basado en la estructura Transformer, y mejorado en utilidad y seguridad a través de ajuste fino supervisado (SFT) y aprendizaje por refuerzo con retroalimentación humana (RLHF). Su versión ajustada para instrucciones está optimizada para diálogos multilingües, superando a muchos modelos de chat de código abierto y cerrado en múltiples benchmarks de la industria. La fecha límite de conocimiento es diciembre de 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 es el modelo de lenguaje de código abierto multilingüe más avanzado de la serie Llama, que ofrece un rendimiento comparable al modelo de 405B a un costo extremadamente bajo. Basado en la estructura Transformer, y mejorado en utilidad y seguridad a través de ajuste fino supervisado (SFT) y aprendizaje por refuerzo con retroalimentación humana (RLHF). Su versión ajustada para instrucciones está optimizada para diálogos multilingües, superando a muchos modelos de chat de código abierto y cerrado en múltiples benchmarks de la industria. La fecha límite de conocimiento es diciembre de 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct es el modelo más grande y potente de la serie Llama 3.1 Instruct, un modelo de generación de datos de diálogo y razonamiento altamente avanzado, que también puede servir como base para un preentrenamiento o ajuste fino especializado en dominios específicos. Los modelos de lenguaje de gran tamaño (LLMs) multilingües que ofrece Llama 3.1 son un conjunto de modelos generativos preentrenados y ajustados por instrucciones, que incluyen tamaños de 8B, 70B y 405B (entrada/salida de texto). Los modelos de texto ajustados por instrucciones de Llama 3.1 (8B, 70B, 405B) están optimizados para casos de uso de diálogo multilingüe y superan a muchos modelos de chat de código abierto disponibles en pruebas de referencia de la industria. Llama 3.1 está diseñado para usos comerciales y de investigación en múltiples idiomas. Los modelos de texto ajustados por instrucciones son adecuados para chats similares a asistentes, mientras que los modelos preentrenados pueden adaptarse a diversas tareas de generación de lenguaje natural. El modelo Llama 3.1 también admite el uso de su salida para mejorar otros modelos, incluida la generación de datos sintéticos y el refinamiento. Llama 3.1 es un modelo de lenguaje autorregresivo que utiliza una arquitectura de transformador optimizada. Las versiones ajustadas utilizan ajuste fino supervisado (SFT) y aprendizaje por refuerzo con retroalimentación humana (RLHF) para alinearse con las preferencias humanas de ayuda y seguridad."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 es un modelo de lenguaje de gran tamaño (LLM) abierto dirigido a desarrolladores, investigadores y empresas, diseñado para ayudarles a construir, experimentar y escalar de manera responsable sus ideas de IA generativa. Como parte de un sistema base para la innovación de la comunidad global, es ideal para dispositivos de borde con recursos y capacidades computacionales limitadas, así como para tiempos de entrenamiento más rápidos."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B es el último modelo ligero y rápido de Microsoft AI, con un rendimiento cercano a 10 veces el de los modelos líderes de código abierto existentes."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "LLM avanzado, que soporta generación de datos sintéticos, destilación de conocimiento y razonamiento, adecuado para chatbots, programación y tareas de dominio específico."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Potencia diálogos complejos, con excelente comprensión del contexto, capacidad de razonamiento y generación de texto."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Modelo de última generación avanzado, con comprensión del lenguaje, excelente capacidad de razonamiento y generación de texto."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Modelo de visión-lenguaje de vanguardia, experto en razonamiento de alta calidad a partir de imágenes."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Modelo de lenguaje pequeño de última generación, con comprensión del lenguaje, excelente capacidad de razonamiento y generación de texto."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Modelo de lenguaje pequeño de última generación, con comprensión del lenguaje, excelente capacidad de razonamiento y generación de texto."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Modelo de visión-lenguaje de vanguardia, experto en razonamiento de alta calidad a partir de imágenes."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Modelo LLM avanzado, experto en razonamiento, matemáticas, sentido común y llamadas a funciones."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 es un modelo de lenguaje proporcionado por Microsoft AI, que destaca en diálogos complejos, multilingüismo, razonamiento y asistentes inteligentes."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B es el modelo Wizard más avanzado de Microsoft AI, mostrando un rendimiento extremadamente competitivo."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V es la nueva generación de modelos multimodales lanzada por OpenBMB, que cuenta con una excelente capacidad de reconocimiento OCR y comprensión multimodal, soportando una amplia gama de escenarios de aplicación."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B es el modelo de borde de primer nivel mundial de Mistral."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B es el modelo de borde con la mejor relación calidad-precio de Mistral."
+ },
"mistral": {
"description": "Mistral es un modelo de 7B lanzado por Mistral AI, adecuado para necesidades de procesamiento de lenguaje variables."
},
"mistral-large": {
"description": "Mixtral Large es el modelo insignia de Mistral, combinando capacidades de generación de código, matemáticas y razonamiento, soportando una ventana de contexto de 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) es un modelo de lenguaje grande (LLM) avanzado con capacidades de razonamiento, conocimiento y codificación de última generación."
- },
"mistral-large-latest": {
"description": "Mistral Large es el modelo insignia, especializado en tareas multilingües, razonamiento complejo y generación de código, ideal para aplicaciones de alta gama."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 ofrece una capacidad de cálculo eficiente y comprensión del lenguaje natural, adecuado para una amplia gama de aplicaciones."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B es un modelo compacto pero de alto rendimiento, ideal para tareas simples como clasificación y generación de texto, con buenas capacidades de razonamiento."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) es un modelo de lenguaje de gran tamaño, que soporta demandas de procesamiento extremadamente altas."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B es un modelo de expertos dispersos preentrenado, utilizado para tareas de texto de uso general."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B es un modelo de expertos dispersos que utiliza múltiples parámetros para aumentar la velocidad de razonamiento, adecuado para tareas de generación de múltiples idiomas y códigos."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct es un modelo de estándar industrial de alto rendimiento, optimizado para velocidad y soporte de contexto largo."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K es un modelo con capacidad de procesamiento de contexto ultra largo, adecuado para generar textos extensos, satisfaciendo las demandas de tareas de generación complejas, capaz de manejar hasta 128,000 tokens, ideal para aplicaciones en investigación, académicas y generación de documentos grandes."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "El modelo visual Kimi (incluyendo moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) puede entender el contenido de las imágenes, incluyendo texto en imágenes, colores de imágenes y formas de objetos."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K ofrece capacidad de procesamiento de contexto de longitud media, capaz de manejar 32,768 tokens, especialmente adecuado para generar diversos documentos largos y diálogos complejos, aplicable en creación de contenido, generación de informes y sistemas de diálogo."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "El modelo visual Kimi (incluyendo moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) puede entender el contenido de las imágenes, incluyendo texto en imágenes, colores de imágenes y formas de objetos."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K está diseñado para tareas de generación de texto corto, con un rendimiento de procesamiento eficiente, capaz de manejar 8,192 tokens, ideal para diálogos breves, toma de notas y generación rápida de contenido."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "El modelo visual Kimi (incluyendo moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) puede entender el contenido de las imágenes, incluyendo texto en imágenes, colores de imágenes y formas de objetos."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto puede seleccionar el modelo adecuado según la cantidad de tokens ocupados en el contexto actual."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B es una versión mejorada de Nous Hermes 2, que incluye los conjuntos de datos más recientes desarrollados internamente."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B es un modelo de lenguaje a gran escala personalizado por NVIDIA, diseñado para mejorar la utilidad de las respuestas generadas por LLM a las consultas de los usuarios. Este modelo ha destacado en pruebas de referencia como Arena Hard, AlpacaEval 2 LC y GPT-4-Turbo MT-Bench, ocupando el primer lugar en los tres benchmarks de alineación automática hasta el 1 de octubre de 2024. El modelo se entrena utilizando RLHF (especialmente REINFORCE), Llama-3.1-Nemotron-70B-Reward y HelpSteer2-Preference sobre la base del modelo Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Modelo de lenguaje único, que ofrece una precisión y eficiencia inigualables."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct es un modelo de lenguaje grande personalizado por NVIDIA, diseñado para mejorar la utilidad de las respuestas generadas por LLM."
+ },
+ "o1": {
+ "description": "Se centra en el razonamiento avanzado y la resolución de problemas complejos, incluidas tareas matemáticas y científicas. Es muy adecuado para aplicaciones que requieren una comprensión profunda del contexto y flujos de trabajo de agentes."
+ },
"o1-mini": {
"description": "o1-mini es un modelo de inferencia rápido y rentable diseñado para aplicaciones de programación, matemáticas y ciencias. Este modelo tiene un contexto de 128K y una fecha de corte de conocimiento en octubre de 2023."
},
"o1-preview": {
"description": "o1 es el nuevo modelo de inferencia de OpenAI, adecuado para tareas complejas que requieren un amplio conocimiento general. Este modelo tiene un contexto de 128K y una fecha de corte de conocimiento en octubre de 2023."
},
+ "o3-mini": {
+ "description": "o3-mini es nuestro último modelo de inferencia de tamaño pequeño, que ofrece alta inteligencia con los mismos objetivos de costo y latencia que o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba es un modelo de lenguaje Mamba 2 enfocado en la generación de código, que proporciona un fuerte apoyo para tareas avanzadas de codificación y razonamiento."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B es un modelo de expertos dispersos que utiliza múltiples parámetros para mejorar la velocidad de razonamiento, adecuado para el procesamiento de tareas de múltiples idiomas y generación de código."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o es un modelo dinámico que se actualiza en tiempo real para mantener la versión más actual. Combina una poderosa capacidad de comprensión y generación de lenguaje, adecuado para escenarios de aplicación a gran escala, incluyendo servicio al cliente, educación y soporte técnico."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o es un modelo dinámico que se actualiza en tiempo real para mantener la versión más actual. Combina una poderosa comprensión y generación de lenguaje, adecuado para escenarios de aplicación a gran escala, incluyendo servicio al cliente, educación y soporte técnico."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini es el modelo más reciente de OpenAI, lanzado después de GPT-4 Omni, que admite entradas de texto e imagen y genera texto como salida. Como su modelo más avanzado de tamaño pequeño, es mucho más económico que otros modelos de vanguardia recientes y más de un 60% más barato que GPT-3.5 Turbo. Mantiene una inteligencia de vanguardia mientras ofrece una relación calidad-precio notable. GPT-4o mini obtuvo un puntaje del 82% en la prueba MMLU y actualmente se clasifica por encima de GPT-4 en preferencias de chat."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "El modelo Pixtral muestra una fuerte capacidad en tareas como comprensión de gráficos e imágenes, preguntas y respuestas de documentos, razonamiento multimodal y seguimiento de instrucciones, capaz de ingerir imágenes en resolución y proporción natural, y manejar una cantidad arbitraria de imágenes en una ventana de contexto larga de hasta 128K tokens."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large es un modelo multimodal de código abierto con 124 mil millones de parámetros, construido sobre Mistral Large 2. Este es nuestro segundo modelo en la familia multimodal, que muestra un nivel de comprensión de imágenes de vanguardia."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K está equipado con una capacidad de procesamiento de contexto extragrande, capaz de manejar hasta 128K de información contextual, especialmente adecuado para el análisis completo y el manejo de relaciones lógicas a largo plazo en contenido extenso, proporcionando una lógica fluida y coherente y un soporte diverso de citas en comunicaciones de texto complejas."
+ },
+ "qvq-72b-preview": {
+ "description": "El modelo QVQ es un modelo de investigación experimental desarrollado por el equipo de Qwen, enfocado en mejorar la capacidad de razonamiento visual, especialmente en el ámbito del razonamiento matemático."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Modelo de código Qwen de Tongyi."
+ },
"qwen-coder-turbo-latest": {
"description": "El modelo de código Tongyi Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "El modelo de matemáticas Tongyi Qwen está diseñado específicamente para resolver problemas matemáticos."
},
+ "qwen-max": {
+ "description": "El modelo de lenguaje a gran escala Qwen Max, de billones de parámetros, admite entradas en diferentes idiomas como chino e inglés, y actualmente es el modelo API detrás de la versión del producto Qwen 2.5."
+ },
"qwen-max-latest": {
"description": "El modelo de lenguaje a gran escala Tongyi Qwen de nivel de cientos de miles de millones, que admite entradas en diferentes idiomas como chino e inglés, es el modelo API detrás de la versión del producto Tongyi Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "La serie de modelos Qwen-Omni admite la entrada de datos en múltiples modalidades, incluyendo video, audio, imágenes y texto, y produce audio y texto como salida."
+ },
+ "qwen-plus": {
+ "description": "La versión mejorada del modelo de lenguaje a gran escala Qwen admite entradas en diferentes idiomas como chino e inglés."
+ },
"qwen-plus-latest": {
"description": "La versión mejorada del modelo de lenguaje a gran escala Tongyi Qwen, que admite entradas en diferentes idiomas como chino e inglés."
},
+ "qwen-turbo": {
+ "description": "El modelo de lenguaje a gran escala Qwen-Turbo admite entradas en diferentes idiomas como chino e inglés."
+ },
"qwen-turbo-latest": {
"description": "El modelo de lenguaje a gran escala Tongyi Qwen, que admite entradas en diferentes idiomas como chino e inglés."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL admite formas de interacción flexibles, incluyendo múltiples imágenes, preguntas y respuestas en múltiples rondas, y capacidades creativas."
},
- "qwen-vl-max": {
- "description": "Qwen es un modelo de lenguaje visual a gran escala. En comparación con la versión mejorada, mejora aún más la capacidad de razonamiento visual y la capacidad de seguir instrucciones, proporcionando un mayor nivel de percepción y cognición visual."
+ "qwen-vl-max-latest": {
+ "description": "Modelo de lenguaje visual a ultra gran escala Tongyi Qianwen. En comparación con la versión mejorada, mejora aún más la capacidad de razonamiento visual y de seguimiento de instrucciones, ofreciendo un nivel más alto de percepción y cognición visual."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Qwen OCR es un modelo especializado en extracción de texto, enfocado en la capacidad de extraer texto de imágenes de documentos, tablas, exámenes, escritura a mano, entre otros. Puede reconocer múltiples idiomas, actualmente soporta: chino, inglés, francés, japonés, coreano, alemán, ruso, italiano, vietnamita y árabe."
},
- "qwen-vl-plus": {
- "description": "Qwen es una versión mejorada del modelo de lenguaje visual a gran escala. Mejora significativamente la capacidad de reconocimiento de detalles y de texto, admite imágenes con resolución de más de un millón de píxeles y proporciones de aspecto de cualquier tamaño."
+ "qwen-vl-plus-latest": {
+ "description": "Versión mejorada del modelo de lenguaje visual a gran escala Tongyi Qianwen. Mejora significativamente la capacidad de reconocimiento de detalles y de texto, soportando imágenes con resolución de más de un millón de píxeles y proporciones de ancho y alto arbitrarias."
},
"qwen-vl-v1": {
"description": "Iniciado con el modelo de lenguaje Qwen-7B, se añade un modelo de imagen, un modelo preentrenado con una resolución de entrada de imagen de 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 es una nueva serie de modelos de lenguaje grande Qwen. Qwen2 7B es un modelo basado en transformador que destaca en comprensión del lenguaje, capacidades multilingües, programación, matemáticas y razonamiento."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 es una nueva serie de modelos de lenguaje de gran tamaño, con una mayor capacidad de comprensión y generación."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL es la última iteración del modelo Qwen-VL, alcanzando un rendimiento de vanguardia en pruebas de comprensión visual, incluyendo MathVista, DocVQA, RealWorldQA y MTVQA. Qwen2-VL puede entender videos de más de 20 minutos, permitiendo preguntas y respuestas, diálogos y creación de contenido de alta calidad basados en video. También posee capacidades complejas de razonamiento y toma de decisiones, pudiendo integrarse con dispositivos móviles, robots, etc., para realizar operaciones automáticas basadas en el entorno visual y las instrucciones de texto. Además del inglés y el chino, Qwen2-VL ahora también admite la comprensión de texto en diferentes idiomas dentro de imágenes, incluyendo la mayoría de los idiomas europeos, japonés, coreano, árabe y vietnamita."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct es una de las últimas series de modelos de lenguaje grande lanzadas por Alibaba Cloud. Este modelo de 72B presenta capacidades significativamente mejoradas en áreas como codificación y matemáticas. También ofrece soporte multilingüe, abarcando más de 29 idiomas, incluidos chino e inglés. El modelo ha mejorado notablemente en el seguimiento de instrucciones, la comprensión de datos estructurados y la generación de salidas estructuradas (especialmente JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct es una de las últimas series de modelos de lenguaje grande lanzadas por Alibaba Cloud. Este modelo de 32B presenta capacidades significativamente mejoradas en áreas como codificación y matemáticas. También ofrece soporte multilingüe, abarcando más de 29 idiomas, incluidos chino e inglés. El modelo ha mejorado notablemente en el seguimiento de instrucciones, la comprensión de datos estructurados y la generación de salidas estructuradas (especialmente JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM orientado a chino e inglés, enfocado en áreas como lenguaje, programación, matemáticas y razonamiento."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "LLM avanzado, que soporta generación de código, razonamiento y corrección, abarcando lenguajes de programación populares."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Poderoso modelo de código de tamaño mediano, que soporta longitudes de contexto de 32K, experto en programación multilingüe."
+ },
"qwen2": {
"description": "Qwen2 es el nuevo modelo de lenguaje a gran escala de Alibaba, que ofrece un rendimiento excepcional para satisfacer diversas necesidades de aplicación."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 es la nueva generación de modelos de lenguaje a gran escala de Alibaba, que ofrece un rendimiento excepcional para satisfacer diversas necesidades de aplicación."
+ },
"qwen2.5-14b-instruct": {
"description": "El modelo de 14B de Tongyi Qwen 2.5, de código abierto."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "El modelo de 72B de Qwen2.5 es de código abierto."
+ },
"qwen2.5-32b-instruct": {
"description": "El modelo de 32B de Tongyi Qwen 2.5, de código abierto."
},
@@ -824,13 +1599,16 @@
"description": "El modelo de 7B de Tongyi Qwen 2.5, de código abierto."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "La versión de código abierto del modelo de código Tongyi Qwen."
+ "description": "La versión de código abierto del modelo Qwen para codificación."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Versión de código abierto del modelo de código Qwen de Tongyi."
},
"qwen2.5-coder-7b-instruct": {
"description": "La versión de código abierto del modelo de código Tongyi Qwen."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "El modelo Qwen-Math tiene una poderosa capacidad para resolver problemas matemáticos."
+ "description": "El modelo Qwen-Math tiene habilidades poderosas para resolver problemas matemáticos."
},
"qwen2.5-math-72b-instruct": {
"description": "El modelo Qwen-Math tiene una poderosa capacidad para resolver problemas matemáticos."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "El modelo Qwen-Math tiene una poderosa capacidad para resolver problemas matemáticos."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Mejora general en seguimiento de instrucciones, matemáticas, resolución de problemas y código, con capacidades de reconocimiento de objetos mejoradas, soporta formatos diversos para localizar elementos visuales con precisión, y puede entender archivos de video largos (hasta 10 minutos) y localizar eventos en segundos, comprendiendo la secuencia y velocidad del tiempo, soportando el control de agentes en OS o móviles, con fuerte capacidad de extracción de información clave y salida en formato Json. Esta versión es la de 72B, la más potente de la serie."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Mejora general en seguimiento de instrucciones, matemáticas, resolución de problemas y código, con capacidades de reconocimiento de objetos mejoradas, soporta formatos diversos para localizar elementos visuales con precisión, y puede entender archivos de video largos (hasta 10 minutos) y localizar eventos en segundos, comprendiendo la secuencia y velocidad del tiempo, soportando el control de agentes en OS o móviles, con fuerte capacidad de extracción de información clave y salida en formato Json. Esta versión es la de 72B, la más potente de la serie."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 es la nueva generación de modelos de lenguaje a gran escala de Alibaba, que ofrece un rendimiento excepcional para satisfacer diversas necesidades de aplicación."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 es la nueva generación de modelos de lenguaje a gran escala de Alibaba, que ofrece un rendimiento excepcional para satisfacer diversas necesidades de aplicación."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 es la nueva generación de modelos de lenguaje a gran escala de Alibaba, que ofrece un rendimiento excepcional para satisfacer diversas necesidades de aplicación."
+ },
"qwen2:0.5b": {
"description": "Qwen2 es el nuevo modelo de lenguaje a gran escala de Alibaba, que ofrece un rendimiento excepcional para satisfacer diversas necesidades de aplicación."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 es el nuevo modelo de lenguaje a gran escala de Alibaba, que ofrece un rendimiento excepcional para satisfacer diversas necesidades de aplicación."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini es un LLM compacto, con un rendimiento superior al de GPT-3.5, que cuenta con potentes capacidades multilingües, soportando inglés y coreano, ofreciendo una solución eficiente y compacta."
+ "qwq": {
+ "description": "QwQ es un modelo de investigación experimental que se centra en mejorar la capacidad de razonamiento de la IA."
+ },
+ "qwq-32b": {
+ "description": "El modelo de inferencia QwQ, entrenado con el modelo Qwen2.5-32B, ha mejorado significativamente su capacidad de inferencia a través del aprendizaje por refuerzo. Los indicadores clave del modelo, como el código matemático y otros indicadores centrales (AIME 24/25, LiveCodeBench), así como algunos indicadores generales (IFEval, LiveBench, etc.), han alcanzado el nivel del modelo DeepSeek-R1 en su versión completa, superando notablemente a DeepSeek-R1-Distill-Qwen-32B, que también se basa en Qwen2.5-32B."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) amplía las capacidades de Solar Mini, enfocándose en el japonés, mientras mantiene un rendimiento eficiente y sobresaliente en el uso del inglés y el coreano."
+ "qwq-32b-preview": {
+ "description": "El modelo QwQ es un modelo de investigación experimental desarrollado por el equipo de Qwen, enfocado en mejorar la capacidad de razonamiento de la IA."
+ },
+ "qwq-plus-latest": {
+ "description": "El modelo de inferencia QwQ, entrenado con el modelo Qwen2.5, ha mejorado significativamente su capacidad de inferencia a través del aprendizaje por refuerzo. Los indicadores clave del modelo, como el código matemático y otros indicadores centrales (AIME 24/25, LiveCodeBench), así como algunos indicadores generales (IFEval, LiveBench, etc.), han alcanzado el nivel del modelo DeepSeek-R1 en su versión completa."
+ },
+ "r1-1776": {
+ "description": "R1-1776 es una versión del modelo DeepSeek R1, que ha sido entrenada posteriormente para proporcionar información factual sin censura y sin sesgos."
+ },
+ "solar-mini": {
+ "description": "Solar Mini es un LLM compacto que supera a GPT-3.5, con potentes capacidades multilingües, soportando inglés y coreano, ofreciendo soluciones eficientes y compactas."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) amplía las capacidades de Solar Mini, enfocándose en japonés, mientras mantiene un rendimiento eficiente y excelente en el uso de inglés y coreano."
},
"solar-pro": {
"description": "Solar Pro es un LLM de alta inteligencia lanzado por Upstage, enfocado en la capacidad de seguimiento de instrucciones en un solo GPU, con una puntuación IFEval superior a 80. Actualmente soporta inglés, y se planea lanzar la versión oficial en noviembre de 2024, ampliando el soporte de idiomas y la longitud del contexto."
},
+ "sonar": {
+ "description": "Producto de búsqueda ligero basado en contexto de búsqueda, más rápido y económico que Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research realiza una investigación exhaustiva a nivel de expertos y la compila en informes accesibles y prácticos."
+ },
+ "sonar-pro": {
+ "description": "Producto de búsqueda avanzada que soporta contexto de búsqueda, consultas avanzadas y seguimiento."
+ },
+ "sonar-reasoning": {
+ "description": "Nuevo producto API respaldado por el modelo de razonamiento de DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Un nuevo producto API respaldado por el modelo de razonamiento DeepSeek."
+ },
"step-1-128k": {
"description": "Equilibrio entre rendimiento y costo, adecuado para escenarios generales."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Modelo de alta velocidad, adecuado para diálogos en tiempo real."
},
+ "step-1.5v-mini": {
+ "description": "Este modelo tiene una potente capacidad de comprensión de video."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Este modelo tiene una poderosa capacidad de comprensión de imágenes, superando a 1o en matemáticas y programación. El modelo es más pequeño que 1o y tiene una velocidad de salida más rápida."
+ },
+ "step-1o-vision-32k": {
+ "description": "Este modelo posee una poderosa capacidad de comprensión de imágenes. En comparación con la serie de modelos step-1v, ofrece un rendimiento visual superior."
+ },
"step-1v-32k": {
"description": "Soporta entradas visuales, mejorando la experiencia de interacción multimodal."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Soporta interacciones de contexto a gran escala, adecuado para escenarios de diálogo complejos."
},
+ "step-2-mini": {
+ "description": "Un modelo de gran velocidad basado en la nueva arquitectura de atención autogestionada MFA, que logra efectos similares a los de step1 a un costo muy bajo, manteniendo al mismo tiempo un mayor rendimiento y tiempos de respuesta más rápidos. Capaz de manejar tareas generales, con habilidades destacadas en programación."
+ },
"taichu_llm": {
"description": "El modelo de lenguaje Taichu de Zīdōng tiene una poderosa capacidad de comprensión del lenguaje, así como habilidades en creación de textos, preguntas y respuestas, programación de código, cálculos matemáticos, razonamiento lógico, análisis de sentimientos y resúmenes de texto. Combina de manera innovadora el preentrenamiento con grandes datos y un conocimiento rico de múltiples fuentes, perfeccionando continuamente la tecnología algorítmica y absorbiendo nuevos conocimientos en vocabulario, estructura, gramática y semántica de grandes volúmenes de datos textuales, logrando una evolución constante del modelo. Proporciona a los usuarios información y servicios más convenientes, así como una experiencia más inteligente."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V combina capacidades de comprensión de imágenes, transferencia de conocimiento y atribución lógica, destacándose en el campo de preguntas y respuestas basadas en texto e imagen."
+ "taichu_vl": {
+ "description": "Integra capacidades de comprensión de imágenes, transferencia de conocimiento y atribución lógica, destacándose en el campo de preguntas y respuestas basadas en texto e imagen."
+ },
+ "text-embedding-3-large": {
+ "description": "El modelo de vectorización más potente, adecuado para tareas en inglés y no inglés."
+ },
+ "text-embedding-3-small": {
+ "description": "Un modelo de Embedding de nueva generación, eficiente y económico, adecuado para la recuperación de conocimiento, aplicaciones RAG y más."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Versión de código abierto de la última generación del modelo preentrenado GLM-4 lanzado por Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) proporciona una capacidad de cálculo mejorada a través de estrategias y arquitecturas de modelos eficientes."
},
+ "tts-1": {
+ "description": "El modelo más reciente de texto a voz, optimizado para velocidad en escenarios en tiempo real."
+ },
+ "tts-1-hd": {
+ "description": "El modelo más reciente de texto a voz, optimizado para calidad."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) es adecuado para tareas de instrucciones detalladas, ofreciendo una excelente capacidad de procesamiento de lenguaje."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet eleva el estándar de la industria, superando a modelos competidores y a Claude 3 Opus, destacándose en evaluaciones amplias, mientras mantiene la velocidad y costo de nuestros modelos de nivel medio."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet es el modelo de próxima generación más rápido de Anthropic. En comparación con Claude 3 Haiku, Claude 3.7 Sonnet ha mejorado en todas las habilidades y ha superado al modelo más grande de la generación anterior, Claude 3 Opus, en muchas pruebas de referencia de inteligencia."
+ },
+ "whisper-1": {
+ "description": "Modelo de reconocimiento de voz general, que admite reconocimiento de voz multilingüe, traducción de voz y reconocimiento de idiomas."
+ },
"wizardlm2": {
"description": "WizardLM 2 es un modelo de lenguaje proporcionado por Microsoft AI, que destaca en diálogos complejos, multilingües, razonamiento y asistentes inteligentes."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Excelente relación calidad-precio y rendimiento excepcional. Ajuste de alta precisión basado en el rendimiento, velocidad de razonamiento y costo."
},
+ "yi-lightning": {
+ "description": "Último modelo de alto rendimiento que garantiza una salida de alta calidad y mejora significativamente la velocidad de razonamiento."
+ },
+ "yi-lightning-lite": {
+ "description": "Versión ligera, se recomienda usar yi-lightning."
+ },
"yi-medium": {
"description": "Modelo de tamaño mediano, ajustado y equilibrado, con una buena relación calidad-precio. Optimización profunda de la capacidad de seguimiento de instrucciones."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Modelo para tareas visuales complejas, que ofrece un alto rendimiento en comprensión y análisis de imágenes."
+ },
+ "yi-vision-v2": {
+ "description": "Modelo para tareas visuales complejas, que ofrece capacidades de comprensión y análisis de alto rendimiento basadas en múltiples imágenes."
}
}
diff --git a/DigitalHumanWeb/locales/es-ES/plugin.json b/DigitalHumanWeb/locales/es-ES/plugin.json
index 49d34d1..4696f77 100644
--- a/DigitalHumanWeb/locales/es-ES/plugin.json
+++ b/DigitalHumanWeb/locales/es-ES/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Error al volver a instalar el complemento {{name}}.",
"urlError": "El enlace no devuelve contenido en formato JSON. Asegúrese de que sea un enlace válido."
},
+ "inspector": {
+ "args": "Ver lista de parámetros",
+ "pluginRender": "Ver interfaz del plugin"
+ },
"list": {
"item": {
"deprecated.title": "Obsoleto",
@@ -130,6 +134,34 @@
"plugin": "Ejecutando complemento..."
},
"pluginList": "Lista de complementos",
+ "search": {
+ "config": {
+ "addKey": "Agregar clave",
+ "close": "Eliminar",
+ "confirm": "Configuración completada, intente de nuevo"
+ },
+ "crawPages": {
+ "crawling": "Reconocimiento de enlaces",
+ "detail": {
+ "preview": "Vista previa",
+ "raw": "Texto original",
+ "tooLong": "El contenido del texto es demasiado largo, el contexto de la conversación solo retiene los primeros {{characters}} caracteres, el resto no se incluye en el contexto de la conversación"
+ },
+ "meta": {
+ "crawler": "Modo de rastreo",
+ "words": "Número de caracteres"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Introduzca",
+ "description": "Introduzca la URL de SearchXNG para comenzar la búsqueda en línea",
+ "keyPlaceholder": "Introduzca la clave",
+ "title": "Configurar el motor de búsqueda SearchXNG",
+ "unconfiguredDesc": "Por favor, contacte al administrador para completar la configuración del motor de búsqueda SearchXNG y comenzar la búsqueda en línea",
+ "unconfiguredTitle": "Motor de búsqueda SearchXNG no configurado"
+ },
+ "title": "Búsqueda en línea"
+ },
"setting": "Configuración de complementos",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/es-ES/portal.json b/DigitalHumanWeb/locales/es-ES/portal.json
index 4dec581..356715b 100644
--- a/DigitalHumanWeb/locales/es-ES/portal.json
+++ b/DigitalHumanWeb/locales/es-ES/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Complementos",
- "actions": {
- "genAiMessage": "Crear mensaje de IA",
- "summary": "Resumen",
- "summaryTooltip": "Resumir el contenido actual"
- },
"artifacts": {
"display": {
"code": "Código",
diff --git a/DigitalHumanWeb/locales/es-ES/providers.json b/DigitalHumanWeb/locales/es-ES/providers.json
index 37a5e6d..bbddc8f 100644
--- a/DigitalHumanWeb/locales/es-ES/providers.json
+++ b/DigitalHumanWeb/locales/es-ES/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs construye modelos fundamentales y sistemas de inteligencia artificial para empresas, acelerando la aplicación de la inteligencia artificial generativa en producción."
+ },
"ai360": {
"description": "360 AI es una plataforma de modelos y servicios de IA lanzada por la empresa 360, que ofrece una variedad de modelos avanzados de procesamiento del lenguaje natural, incluidos 360GPT2 Pro, 360GPT Pro, 360GPT Turbo y 360GPT Turbo Responsibility 8K. Estos modelos combinan parámetros a gran escala y capacidades multimodales, siendo ampliamente utilizados en generación de texto, comprensión semántica, sistemas de diálogo y generación de código. A través de una estrategia de precios flexible, 360 AI satisface diversas necesidades de los usuarios, apoyando la integración de desarrolladores y promoviendo la innovación y desarrollo de aplicaciones inteligentes."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure ofrece una variedad de modelos de IA avanzados, incluidos GPT-3.5 y la última serie GPT-4, que admiten múltiples tipos de datos y tareas complejas, comprometidos con soluciones de IA seguras, confiables y sostenibles."
},
+ "azureai": {
+ "description": "Azure ofrece una variedad de modelos de IA avanzados, incluidos GPT-3.5 y la última serie GPT-4, que admiten múltiples tipos de datos y tareas complejas, comprometidos con soluciones de IA seguras, confiables y sostenibles."
+ },
"baichuan": {
"description": "Baichuan Intelligent es una empresa centrada en el desarrollo de modelos de gran tamaño de inteligencia artificial, cuyos modelos han demostrado un rendimiento excepcional en tareas en chino como enciclopedias de conocimiento, procesamiento de textos largos y creación de contenido, superando a los modelos principales extranjeros. Baichuan Intelligent también posee capacidades multimodales líderes en la industria, destacándose en múltiples evaluaciones de autoridad. Sus modelos incluyen Baichuan 4, Baichuan 3 Turbo y Baichuan 3 Turbo 128k, optimizados para diferentes escenarios de aplicación, ofreciendo soluciones de alta relación calidad-precio."
},
"bedrock": {
"description": "Bedrock es un servicio proporcionado por Amazon AWS, enfocado en ofrecer modelos de lenguaje y visuales avanzados para empresas. Su familia de modelos incluye la serie Claude de Anthropic, la serie Llama 3.1 de Meta, entre otros, abarcando una variedad de opciones desde ligeras hasta de alto rendimiento, apoyando tareas como generación de texto, diálogos y procesamiento de imágenes, adecuadas para aplicaciones empresariales de diferentes escalas y necesidades."
},
+ "cloudflare": {
+ "description": "Ejecuta modelos de aprendizaje automático impulsados por GPU sin servidor en la red global de Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek es una empresa centrada en la investigación y aplicación de tecnologías de inteligencia artificial, cuyo modelo más reciente, DeepSeek-V2.5, combina capacidades de diálogo general y procesamiento de código, logrando mejoras significativas en alineación con preferencias humanas, tareas de escritura y seguimiento de instrucciones."
},
+ "doubao": {
+ "description": "Un modelo grande desarrollado internamente por ByteDance. Validado a través de más de 50 escenarios de negocio internos, con un uso diario de tokens en billones que se perfecciona continuamente, ofrece múltiples capacidades modales y crea experiencias comerciales ricas para las empresas con un rendimiento de modelo de alta calidad."
+ },
"fireworksai": {
"description": "Fireworks AI es un proveedor líder de servicios de modelos de lenguaje avanzados, enfocado en la llamada de funciones y el procesamiento multimodal. Su modelo más reciente, Firefunction V2, basado en Llama-3, está optimizado para llamadas de funciones, diálogos y seguimiento de instrucciones. El modelo de lenguaje visual FireLLaVA-13B admite entradas mixtas de imágenes y texto. Otros modelos notables incluyen la serie Llama y la serie Mixtral, que ofrecen un soporte eficiente para el seguimiento y generación de instrucciones multilingües."
},
+ "giteeai": {
+ "description": "La API serverless de gitee ai proporciona a los desarrolladores de Ia un servicio API de razonamiento de modelos grandes listo para abrir la Caja."
+ },
"github": {
"description": "Con los Modelos de GitHub, los desarrolladores pueden convertirse en ingenieros de IA y construir con los modelos de IA líderes en la industria."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "El motor de inferencia LPU de Groq ha demostrado un rendimiento excepcional en las pruebas de referencia de modelos de lenguaje de gran tamaño (LLM), redefiniendo los estándares de soluciones de IA con su asombrosa velocidad y eficiencia. Groq es un referente en velocidad de inferencia instantánea, mostrando un buen rendimiento en implementaciones basadas en la nube."
},
+ "higress": {
+ "description": "Higress es una puerta de enlace API nativa de la nube, que nació en Alibaba para resolver los problemas que el recargado de Tengine causa en los negocios de conexiones largas, así como la insuficiencia de la capacidad de balanceo de carga de gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "La API de Inferencia de HuggingFace ofrece una forma rápida y gratuita de explorar miles de modelos para diversas tareas. Ya sea que esté prototipando una nueva aplicación o probando las capacidades del aprendizaje automático, esta API le brinda acceso instantáneo a modelos de alto rendimiento en múltiples dominios."
+ },
+ "hunyuan": {
+ "description": "Un modelo de lenguaje desarrollado por Tencent, que posee una poderosa capacidad de creación en chino, habilidades de razonamiento lógico en contextos complejos y una capacidad confiable para ejecutar tareas."
+ },
+ "internlm": {
+ "description": "Organización de código abierto dedicada a la investigación y desarrollo de herramientas para modelos grandes. Proporciona a todos los desarrolladores de IA una plataforma de código abierto eficiente y fácil de usar, permitiendo el acceso a las tecnologías y algoritmos más avanzados."
+ },
+ "jina": {
+ "description": "Jina AI, fundada en 2020, es una empresa líder en búsqueda de IA. Nuestra plataforma de búsqueda base incluye modelos vectoriales, reordenadores y pequeños modelos de lenguaje, que ayudan a las empresas a construir aplicaciones de búsqueda generativa y multimodal confiables y de alta calidad."
+ },
+ "lmstudio": {
+ "description": "LM Studio es una aplicación de escritorio para desarrollar y experimentar con LLMs en su computadora."
+ },
"minimax": {
"description": "MiniMax es una empresa de tecnología de inteligencia artificial general fundada en 2021, dedicada a co-crear inteligencia con los usuarios. MiniMax ha desarrollado de forma independiente modelos de gran tamaño de diferentes modalidades, que incluyen un modelo de texto MoE de un billón de parámetros, un modelo de voz y un modelo de imagen. También ha lanzado aplicaciones como Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI es una plataforma que ofrece servicios API para múltiples modelos de lenguaje de gran tamaño y generación de imágenes de IA, siendo flexible, confiable y rentable. Soporta los últimos modelos de código abierto como Llama3 y Mistral, proporcionando soluciones API completas, amigables para el usuario y autoescalables para el desarrollo de aplicaciones de IA, adecuadas para el rápido crecimiento de startups de IA."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ proporciona contenedores que se pueden utilizar para microservicios de inferencia acelerados por GPU autohospedados, admitiendo el despliegue de modelos de IA preentrenados y personalizados en la nube, centros de datos, PC RTX™ AI y estaciones de trabajo."
+ },
"ollama": {
"description": "Los modelos ofrecidos por Ollama abarcan ampliamente áreas como la generación de código, cálculos matemáticos, procesamiento multilingüe e interacciones conversacionales, apoyando diversas necesidades de implementación empresarial y local."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity es un proveedor líder de modelos de generación de diálogos, ofreciendo varios modelos avanzados de Llama 3.1, que son adecuados para aplicaciones en línea y fuera de línea, especialmente para tareas complejas de procesamiento del lenguaje natural."
},
+ "ppio": {
+ "description": "PPIO Paiouyun ofrece servicios de API de modelos de código abierto estables y de alto rendimiento, que admiten toda la serie DeepSeek, Llama, Qwen y otros modelos grandes líderes en la industria."
+ },
"qwen": {
"description": "Tongyi Qianwen es un modelo de lenguaje de gran escala desarrollado de forma independiente por Alibaba Cloud, con potentes capacidades de comprensión y generación de lenguaje natural. Puede responder a diversas preguntas, crear contenido escrito, expresar opiniones y redactar código, desempeñando un papel en múltiples campos."
},
+ "sambanova": {
+ "description": "SambaNova Cloud permite a los desarrolladores utilizar fácilmente los mejores modelos de código abierto y disfrutar de la velocidad de inferencia más rápida."
+ },
+ "sensenova": {
+ "description": "SenseTime ofrece servicios de modelos grandes de pila completa, aprovechando el sólido soporte de la gran infraestructura de SenseTime."
+ },
"siliconcloud": {
"description": "SiliconFlow se dedica a acelerar la AGI para beneficiar a la humanidad, mejorando la eficiencia de la IA a gran escala a través de un stack GenAI fácil de usar y de bajo costo."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "El Instituto de Automatización de la Academia de Ciencias de China y el Instituto de Investigación de Inteligencia Artificial de Wuhan han lanzado una nueva generación de modelos de gran tamaño multimodal, que apoyan tareas de preguntas y respuestas de múltiples rondas, creación de texto, generación de imágenes, comprensión 3D, análisis de señales y más, con capacidades de cognición, comprensión y creación más fuertes, ofreciendo una nueva experiencia de interacción."
},
+ "tencentcloud": {
+ "description": "La capacidad atómica del motor de conocimiento (LLM Knowledge Engine Atomic Power) se basa en el desarrollo del motor de conocimiento y ofrece una capacidad completa de preguntas y respuestas, dirigida a empresas y desarrolladores, proporcionando la capacidad de construir y desarrollar aplicaciones de modelos de manera flexible. Puede ensamblar su propio servicio de modelo utilizando varias capacidades atómicas, invocando servicios de análisis de documentos, división, embedding, reescritura en múltiples turnos, entre otros, para personalizar un negocio de IA exclusivo para su empresa."
+ },
"togetherai": {
"description": "Together AI se dedica a lograr un rendimiento líder a través de modelos de IA innovadores, ofreciendo amplias capacidades de personalización, incluyendo soporte para escalado rápido y procesos de implementación intuitivos, satisfaciendo diversas necesidades empresariales."
},
"upstage": {
"description": "Upstage se centra en desarrollar modelos de IA para diversas necesidades comerciales, incluidos Solar LLM y Document AI, con el objetivo de lograr una inteligencia general artificial (AGI) que trabaje para las personas. Crea agentes de diálogo simples a través de la API de Chat y admite llamadas de funciones, traducción, incrustaciones y aplicaciones de dominio específico."
},
+ "vertexai": {
+ "description": "La serie Gemini de Google es su modelo de IA más avanzado y versátil, desarrollado por Google DeepMind, diseñado específicamente para ser multimodal, soportando la comprensión y procesamiento sin interrupciones de texto, código, imágenes, audio y video. Es adecuado para una variedad de entornos, desde centros de datos hasta dispositivos móviles, mejorando enormemente la eficiencia y la aplicabilidad de los modelos de IA."
+ },
+ "vllm": {
+ "description": "vLLM es una biblioteca rápida y fácil de usar para la inferencia y el servicio de LLM."
+ },
+ "volcengine": {
+ "description": "Plataforma de desarrollo de servicios de modelos grandes lanzada por ByteDance, que ofrece servicios de invocación de modelos ricos en funciones, seguros y competitivos en precio, al tiempo que proporciona datos de modelos, ajuste fino, inferencia, evaluación y otras funciones de extremo a extremo, garantizando de manera integral el desarrollo y la implementación de sus aplicaciones de IA."
+ },
+ "wenxin": {
+ "description": "Plataforma de desarrollo y servicios de modelos grandes y aplicaciones nativas de IA de nivel empresarial, que ofrece la cadena de herramientas más completa y fácil de usar para el desarrollo de modelos de inteligencia artificial generativa y el desarrollo de aplicaciones en todo el proceso."
+ },
+ "xai": {
+ "description": "xAI es una empresa dedicada a construir inteligencia artificial para acelerar los descubrimientos científicos humanos. Nuestra misión es promover nuestra comprensión compartida del universo."
+ },
"zeroone": {
"description": "01.AI se centra en la tecnología de inteligencia artificial de la era 2.0, promoviendo enérgicamente la innovación y aplicación de 'humano + inteligencia artificial', utilizando modelos extremadamente potentes y tecnologías de IA avanzadas para mejorar la productividad humana y lograr el empoderamiento tecnológico."
},
diff --git a/DigitalHumanWeb/locales/es-ES/setting.json b/DigitalHumanWeb/locales/es-ES/setting.json
index 90461c4..79c315c 100644
--- a/DigitalHumanWeb/locales/es-ES/setting.json
+++ b/DigitalHumanWeb/locales/es-ES/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Configuración del modelo personalizado",
"tokens": {
- "title": "Número máximo de tokens",
- "unlimited": "ilimitado"
+ "title": "Número máximo de tokens"
},
"vision": {
"extra": "Esta configuración solo habilitará la configuración de carga de imágenes en la aplicación; si se admite el reconocimiento depende completamente del modelo en sí. Por favor, prueba la disponibilidad de la capacidad de reconocimiento visual de este modelo.",
@@ -98,6 +97,7 @@
"title": "Usar el modo de solicitud en el cliente"
},
"fetcher": {
+ "clear": "Eliminar el modelo obtenido",
"fetch": "Obtener lista de modelos",
"fetching": "Obteniendo lista de modelos...",
"latestTime": "Última actualización: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Indica si se debe crear automáticamente un tema durante la conversación, solo se aplica en temas temporales",
"title": "Crear tema automáticamente"
},
- "enableCompressThreshold": {
- "title": "Activar umbral de compresión de longitud de mensajes históricos"
+ "enableCompressHistory": {
+ "title": "Activar resumen automático de mensajes históricos"
},
"enableHistoryCount": {
"alias": "Sin límite",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Activar límite de tokens por respuesta"
},
+ "enableReasoningEffort": {
+ "title": "Activar ajuste de intensidad de razonamiento"
+ },
"frequencyPenalty": {
- "desc": "Cuanto mayor sea el valor, más probable es que se reduzcan las repeticiones de palabras",
- "title": "Penalización de frecuencia"
+ "desc": "Cuanto mayor sea el valor, más rica y variada será la elección de palabras; cuanto menor sea el valor, más simples y directas serán las palabras.",
+ "title": "Riqueza del vocabulario"
},
"maxTokens": {
"desc": "Número máximo de tokens utilizados en una interacción",
@@ -212,19 +215,31 @@
"desc": "{{provider}} modelo",
"title": "Modelo"
},
+ "params": {
+ "title": "Parámetros avanzados"
+ },
"presencePenalty": {
- "desc": "Cuanto mayor sea el valor, más probable es que se amplíe a nuevos temas",
- "title": "Penalización de novedad del tema"
+ "desc": "Cuanto mayor sea el valor, más se inclinará hacia diferentes formas de expresión, evitando la repetición de conceptos; cuanto menor sea el valor, más se inclinará hacia el uso de conceptos o narrativas repetidas, expresando mayor consistencia.",
+ "title": "Diversidad de expresión"
+ },
+ "reasoningEffort": {
+ "desc": "Cuanto mayor sea el valor, más fuerte será la capacidad de razonamiento, pero puede aumentar el tiempo de respuesta y el consumo de tokens.",
+ "options": {
+ "high": "Alto",
+ "low": "Bajo",
+ "medium": "Medio"
+ },
+ "title": "Intensidad de razonamiento"
},
"temperature": {
- "desc": "Cuanto mayor sea el valor, más aleatoria será la respuesta",
- "title": "Temperatura",
- "titleWithValue": "Temperatura {{value}}"
+ "desc": "Cuanto mayor sea el valor, más creativas e imaginativas serán las respuestas; cuanto menor sea el valor, más rigurosas serán las respuestas",
+ "title": "Nivel de creatividad",
+ "warning": "Un valor de creatividad demasiado alto puede generar salidas confusas"
},
"title": "Configuración del modelo",
"topP": {
- "desc": "Similar a la temperatura, pero no se debe cambiar junto con la temperatura",
- "title": "Muestreo de núcleo"
+ "desc": "Cuántas posibilidades se consideran, cuanto mayor sea el valor, más respuestas posibles se aceptan; cuanto menor sea el valor, se tiende a elegir la respuesta más probable. No se recomienda cambiarlo junto con el nivel de creatividad",
+ "title": "Apertura mental"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Modelo designado para generar el nombre, descripción, avatar y etiquetas del asistente",
"title": "Generación automática de información del asistente"
},
+ "customPrompt": {
+ "addPrompt": "Agregar aviso personalizado",
+ "desc": "Al completarlo, el asistente del sistema utilizará el aviso personalizado al generar contenido",
+ "placeholder": "Introduce la palabra clave personalizada",
+ "title": "Palabra clave personalizada"
+ },
+ "historyCompress": {
+ "label": "Modelo de historial de conversación",
+ "modelDesc": "Especifica el modelo utilizado para comprimir el historial de conversación",
+ "title": "Resumen automático del historial de conversación"
+ },
"queryRewrite": {
"label": "Modelo de reescritura de preguntas",
"modelDesc": "Modelo designado para optimizar las preguntas de los usuarios",
- "title": "Base de conocimientos"
+ "title": "Reescritura de preguntas de la base de conocimientos"
+ },
+ "thread": {
+ "label": "Modelo de nombramiento de subtemas",
+ "modelDesc": "Modelo designado para el renombramiento automático de subtemas",
+ "title": "Nombramiento automático de subtemas"
},
"title": "Asistente del sistema",
"topic": {
@@ -395,6 +426,7 @@
"common": "Configuración común",
"experiment": "Experimento",
"llm": "Modelo de lenguaje",
+ "provider": "Proveedor de servicios de IA",
"sync": "Sincronización en la nube",
"system-agent": "Asistente del sistema",
"tts": "Servicio de voz"
diff --git a/DigitalHumanWeb/locales/es-ES/thread.json b/DigitalHumanWeb/locales/es-ES/thread.json
new file mode 100644
index 0000000..3cb3b3b
--- /dev/null
+++ b/DigitalHumanWeb/locales/es-ES/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Está a punto de eliminar este subtema. Una vez eliminado, no se podrá recuperar. Por favor, actúe con precaución."
+ },
+ "newPortalThread": {
+ "includeContext": "Incluir contexto del tema",
+ "title": "Iniciar un nuevo subtema"
+ },
+ "notSupportMultiModals": "Los subtemas no admiten la carga de archivos/imágenes por el momento. Si tienes alguna necesidad, no dudes en dejar un comentario: <1>💬 Foro de discusión1>"
+}
diff --git a/DigitalHumanWeb/locales/es-ES/tool.json b/DigitalHumanWeb/locales/es-ES/tool.json
index 2677a4d..ba38af7 100644
--- a/DigitalHumanWeb/locales/es-ES/tool.json
+++ b/DigitalHumanWeb/locales/es-ES/tool.json
@@ -6,5 +6,23 @@
"generating": "Generando...",
"images": "Imágenes:",
"prompt": "Palabra de aviso"
+ },
+ "search": {
+ "createNewSearch": "Crear un nuevo registro de búsqueda",
+ "emptyResult": "No se encontraron resultados, por favor modifica las palabras clave y vuelve a intentarlo",
+ "genAiMessage": "Crear mensaje del asistente",
+ "includedTooltip": "Los resultados de búsqueda actuales se incluirán en el contexto de la conversación",
+ "keywords": "Palabras clave:",
+ "scoreTooltip": "Puntuación de relevancia, cuanto más alta sea la puntuación, más relevante será para las palabras clave de la consulta",
+ "searchBar": {
+ "button": "Buscar",
+ "placeholder": "Palabras clave",
+ "tooltip": "Se volverán a obtener los resultados de búsqueda y se creará un nuevo mensaje de resumen"
+ },
+ "searchEngine": "Motor de búsqueda:",
+ "searchResult": "Número de búsquedas:",
+ "summary": "Resumen",
+ "summaryTooltip": "Resumir el contenido actual",
+ "viewMoreResults": "Ver más {{results}} resultados"
}
}
diff --git a/DigitalHumanWeb/locales/es-ES/topic.json b/DigitalHumanWeb/locales/es-ES/topic.json
new file mode 100644
index 0000000..d3d707e
--- /dev/null
+++ b/DigitalHumanWeb/locales/es-ES/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Renombrar automáticamente",
+ "confirmRemoveAll": "Se eliminarán todos los temas. Una vez eliminados, no se podrán recuperar. Por favor, actúe con precaución.",
+ "confirmRemoveTopic": "Se eliminará este tema. Una vez eliminado, no se podrá recuperar. Por favor, actúe con precaución.",
+ "confirmRemoveUnstarred": "Se eliminarán los temas no favoritos. Una vez eliminados, no se podrán recuperar. Por favor, actúe con precaución.",
+ "duplicate": "Crear copia",
+ "export": "Exportar tema",
+ "removeAll": "Eliminar todos los temas",
+ "removeUnstarred": "Eliminar temas no favoritos"
+ },
+ "defaultTitle": "Tema por defecto",
+ "duplicateLoading": "Copiando tema...",
+ "duplicateSuccess": "Tema copiado con éxito",
+ "favorite": "Favorito",
+ "groupMode": {
+ "ascMessages": "Ordenar por número total de mensajes ascendente",
+ "byTime": "Agrupar por tiempo",
+ "descMessages": "Ordenar por número total de mensajes descendente",
+ "flat": "Sin agrupar"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Este mes",
+ "today": "Hoy",
+ "week": "Esta semana",
+ "yesterday": "Ayer"
+ }
+ },
+ "guide": {
+ "desc": "Haga clic en el botón a la izquierda para guardar la conversación actual como un tema histórico y comenzar una nueva conversación.",
+ "title": "Lista de temas"
+ },
+ "searchPlaceholder": "Buscar temas...",
+ "searchResultEmpty": "No hay resultados de búsqueda disponibles",
+ "temp": "Temporal",
+ "title": "Tema"
+}
diff --git a/DigitalHumanWeb/locales/es-ES/welcome.json b/DigitalHumanWeb/locales/es-ES/welcome.json
index 50f9c55..5c5ce51 100644
--- a/DigitalHumanWeb/locales/es-ES/welcome.json
+++ b/DigitalHumanWeb/locales/es-ES/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Importar configuración",
- "market": "Explorar el mercado",
- "start": "Comenzar ahora"
- },
"guide": {
"agents": {
"replaceBtn": "Cambiar grupo",
diff --git a/DigitalHumanWeb/locales/fa-IR/auth.json b/DigitalHumanWeb/locales/fa-IR/auth.json
new file mode 100644
index 0000000..e49d9b3
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/auth.json
@@ -0,0 +1,96 @@
+{
+ "date": {
+ "prevMonth": "ماه گذشته",
+ "recent30Days": "۳۰ روز گذشته"
+ },
+ "header": {
+ "desc": "اطلاعات حساب کاربری خود را مدیریت کنید.",
+ "title": "حساب کاربری"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "غیرفعال",
+ "more": "فعال"
+ },
+ "months": {
+ "apr": "آوریل",
+ "aug": "اوت",
+ "dec": "دسامبر",
+ "feb": "فوریه",
+ "jan": "ژانویه",
+ "jul": "ژوئیه",
+ "jun": "ژوئن",
+ "mar": "مارس",
+ "may": "مه",
+ "nov": "نوامبر",
+ "oct": "اکتبر",
+ "sep": "سپتامبر"
+ },
+ "tooltip": "{{date}} در آن روز {{count}} پیام ارسال کرد",
+ "totalCount": "در مجموع {{count}} پیام در سال گذشته ارسال شده است"
+ },
+ "login": "ورود",
+ "loginOrSignup": "ورود / ثبت نام",
+ "profile": {
+ "avatar": "آواتار",
+ "email": "آدرس ایمیل",
+ "sso": {
+ "loading": "در حال بارگذاری حسابهای شخص ثالث متصل شده",
+ "providers": "حسابهای متصل",
+ "unlink": {
+ "description": "با لغو اتصال، شما نمیتوانید با حساب {{provider}} «{{providerAccountId}}» وارد شوید. اگر نیاز دارید حساب {{provider}} را دوباره به حساب جاری متصل کنید، لطفا اطمینان حاصل کنید که آدرس ایمیل حساب {{provider}} {{email}} است، ما در هنگام ورود به طور خودکار آن را به حساب جاری متصل خواهیم کرد.",
+ "forbidden": "شما حداقل باید یک حساب شخص ثالث متصل را حفظ کنید.",
+ "title": "آیا میخواهید این حساب شخص ثالث {{provider}} را لغو اتصال کنید؟"
+ }
+ },
+ "username": "نام کاربری"
+ },
+ "signout": "خروج",
+ "signup": "ثبت نام",
+ "stats": {
+ "aiheatmaps": "شاخص فعالیت",
+ "assistants": "دستیاران",
+ "assistantsRank": {
+ "left": "دستیار",
+ "right": "موضوعات",
+ "title": "رتبه استفاده از دستیار"
+ },
+ "createdAt": "تاریخ ثبت نام",
+ "days": "روز",
+ "empty": {
+ "desc": "لطفاً دادههای چت بیشتری جمعآوری کنید تا مشاهده کنید",
+ "title": "دادهای وجود ندارد"
+ },
+ "lastYearActivity": "فعالیت در سال گذشته",
+ "loginGuide": {
+ "f1": "دریافت حجم رایگان",
+ "f2": "همگامسازی پیامها در چند دستگاه",
+ "f3": "داشتن دستیارهای متنوع",
+ "f4": "کشف افزونههای قدرتمند",
+ "title": "پس از ورود میتوانید:"
+ },
+ "messages": "پیامها",
+ "modelsRank": {
+ "left": "مدل",
+ "right": "پیامها",
+ "title": "رتبه استفاده از مدل"
+ },
+ "share": {
+ "title": "شاخص فعالیت هوش مصنوعی من"
+ },
+ "topics": "موضوعات",
+ "topicsRank": {
+ "left": "موضوع",
+ "right": "پیامها",
+ "title": "رتبه محتوای موضوع"
+ },
+ "updatedAt": "تاریخ بهروزرسانی",
+ "welcome": "{{username}}، این {{days}} روز شما با {{appName}} است",
+ "words": "کلمات"
+ },
+ "tab": {
+ "profile": "پروفایل",
+ "security": "امنیت",
+ "stats": "آمار"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/changelog.json b/DigitalHumanWeb/locales/fa-IR/changelog.json
new file mode 100644
index 0000000..e70752a
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "ما را در X دنبال کنید",
+ "subscribeToUpdates": "برای دریافت بهروزرسانیها مشترک شوید",
+ "versions": "جزئیات نسخه"
+ },
+ "addedWhileAway": "در زمان غیبت شما، ویژگیهای جدیدی اضافه کردیم.",
+ "allChangelog": "تمام تغییرات را مشاهده کنید",
+ "description": "بهروزرسانیهای جدید و بهبودهای {{appName}} را دنبال کنید",
+ "pagination": {
+ "next": "صفحه بعدی",
+ "older": "مشاهده تغییرات قبلی"
+ },
+ "readDetails": "جزئیات را بخوانید",
+ "title": "تغییرات",
+ "versionDetails": "جزئیات نسخه",
+ "welcomeBack": "خوش آمدید!"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/chat.json b/DigitalHumanWeb/locales/fa-IR/chat.json
new file mode 100644
index 0000000..54edd66
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/chat.json
@@ -0,0 +1,263 @@
+{
+ "ModelSwitch": {
+ "title": "مدل"
+ },
+ "agentDefaultMessage": "سلام، من **{{name}}** هستم. میتوانید همین حالا با من گفتگو را شروع کنید یا به [تنظیمات دستیار]({{url}}) بروید و اطلاعات من را تکمیل کنید.",
+ "agentDefaultMessageWithSystemRole": "سلام، من **{{name}}** هستم، {{systemRole}}، بیایید گفتگو را شروع کنیم!",
+ "agentDefaultMessageWithoutEdit": "سلام، من **{{name}}** هستم، بیایید گفتگو را شروع کنیم!",
+ "agents": "دستیار",
+ "artifact": {
+ "generating": "در حال تولید",
+ "inThread": "در زیرموضوع نمیتوانید مشاهده کنید، لطفاً به ناحیه اصلی گفتگو بروید",
+ "thinking": "در حال تفکر",
+ "thought": "فرآیند تفکر",
+ "unknownTitle": "اثر بدون نام"
+ },
+ "backToBottom": "بازگشت به پایین",
+ "chatList": {
+ "longMessageDetail": "مشاهده جزئیات"
+ },
+ "clearCurrentMessages": "پاک کردن پیامهای جلسه فعلی",
+ "confirmClearCurrentMessages": "پیامهای جلسه فعلی به زودی پاک خواهند شد و پس از پاک شدن قابل بازیابی نخواهند بود. لطفاً عملیات خود را تأیید کنید.",
+ "confirmRemoveSessionItemAlert": "این دستیار به زودی حذف خواهد شد و پس از حذف قابل بازیابی نخواهد بود، لطفاً عملیات خود را تأیید کنید.",
+ "confirmRemoveSessionSuccess": "حذف دستیار با موفقیت انجام شد",
+ "defaultAgent": "دستیار سفارشی",
+ "defaultList": "فهرست پیشفرض",
+ "defaultSession": "دستیار سفارشی",
+ "duplicateSession": {
+ "loading": "در حال کپی کردن...",
+ "success": "کپی با موفقیت انجام شد",
+ "title": "نسخه کپی {{title}}"
+ },
+ "duplicateTitle": "نسخهای از {{title}}",
+ "emptyAgent": "دستیار موجود نیست",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "هزینه تولید یک گفتوگو میتواند تا 90% کاهش یابد و سرعت پاسخدهی 4 برابر افزایش یابد (<1>بیشتر بدانید1>) . با فعالسازی این گزینه، محدودیت تعداد پیامهای تاریخی بهطور خودکار غیرفعال خواهد شد",
+ "title": "فعالسازی کش زمینه"
+ },
+ "enableReasoning": {
+ "desc": "محدودیتهای مبتنی بر مکانیزم تفکر کلاود (<1>بیشتر بدانید1>) . با فعالسازی این گزینه، محدودیت تعداد پیامهای تاریخی بهطور خودکار غیرفعال خواهد شد",
+ "title": "فعالسازی تفکر عمیق"
+ },
+ "reasoningBudgetToken": {
+ "title": "توکن مصرف تفکر"
+ },
+ "title": "ویژگیهای گسترش مدل"
+ },
+ "history": {
+ "title": "دستیار فقط آخرین {{count}} پیام را به خاطر خواهد سپرد"
+ },
+ "historyRange": "محدوده تاریخی",
+ "historySummary": "خلاصه پیامهای تاریخی",
+ "inbox": {
+ "desc": "خوشههای مغزی را فعال کنید و جرقههای تفکر را برانگیزید. دستیار هوشمند شما اینجاست تا با شما در مورد هر چیزی صحبت کند.",
+ "title": "گپ دوستانه"
+ },
+ "input": {
+ "addAi": "افزودن یک پیام AI",
+ "addUser": "افزودن یک پیام کاربر",
+ "more": "بیشتر",
+ "send": "ارسال",
+ "sendWithCmdEnter": "فشار دهید {{meta}} + Enter برای ارسال",
+ "sendWithEnter": "فشار دهید Enter برای ارسال",
+ "stop": "توقف",
+ "warp": "خط جدید"
+ },
+ "intentUnderstanding": {
+ "title": "در حال درک و تحلیل نیت شما..."
+ },
+ "knowledgeBase": {
+ "all": "همه محتوا",
+ "allFiles": "همه فایلها",
+ "allKnowledgeBases": "همه پایگاههای دانش",
+ "disabled": "حالت فعلی استقرار از مکالمات پایگاه دانش پشتیبانی نمیکند. برای استفاده، به استقرار پایگاه داده سرور تغییر دهید یا از خدمات {{cloud}} استفاده کنید.",
+ "library": {
+ "action": {
+ "add": "افزودن",
+ "detail": "جزئیات",
+ "remove": "حذف"
+ },
+ "title": "فایل/پایگاه دانش"
+ },
+ "relativeFilesOrKnowledgeBases": "فایلها/پایگاههای دانش مرتبط",
+ "title": "پایگاه دانش",
+ "uploadGuide": "فایلهای آپلود شده را میتوانید در «پایگاه دانش» مشاهده کنید.",
+ "viewMore": "مشاهده بیشتر"
+ },
+ "messageAction": {
+ "delAndRegenerate": "حذف و بازتولید",
+ "deleteDisabledByThreads": "زیرموضوع وجود دارد، نمیتوان حذف کرد",
+ "regenerate": "بازتولید"
+ },
+ "messages": {
+ "modelCard": {
+ "credit": "اعتبار",
+ "creditPricing": "قیمت گذاری",
+ "creditTooltip": "برای سهولت در شمارش، ما 1$ را به 1M اعتبار تبدیل میکنیم، به عنوان مثال $3/M توکنها معادل 3 اعتبار/token است",
+ "pricing": {
+ "inputCachedTokens": "ورودی کش شده {{amount}}/اعتبار · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M کاراکتر",
+ "inputMinutes": "${{amount}}/دقیقه",
+ "inputTokens": "ورودی {{amount}}/اعتبار · ${{amount}}/M",
+ "outputTokens": "خروجی {{amount}}/اعتبار · ${{amount}}/M",
+ "writeCacheInputTokens": "ذخیره ورودی نوشتن {{amount}}/امتیاز · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "میانگین قیمت",
+ "input": "ورودی",
+ "inputAudio": "ورودی صوتی",
+ "inputCached": "ورودی کش شده",
+ "inputCitation": "ارجاع ورودی",
+ "inputText": "ورودی متنی",
+ "inputTitle": "جزئیات ورودی",
+ "inputUncached": "ورودی غیر کش شده",
+ "inputWriteCached": "ذخیره ورودی نوشتن",
+ "output": "خروجی",
+ "outputAudio": "خروجی صوتی",
+ "outputText": "خروجی متنی",
+ "outputTitle": "جزئیات خروجی",
+ "reasoning": "تفکر عمیق",
+ "title": "جزئیات تولید",
+ "total": "مجموع مصرف"
+ }
+ },
+ "newAgent": "دستیار جدید",
+ "pin": "سنجاق کردن",
+ "pinOff": "لغو سنجاق",
+ "rag": {
+ "referenceChunks": "منابع ارجاعی",
+ "userQuery": {
+ "actions": {
+ "delete": "حذف بازنویسی پرسش",
+ "regenerate": "بازتولید پرسش"
+ }
+ }
+ },
+ "regenerate": "بازتولید",
+ "roleAndArchive": "نقشها و بایگانی",
+ "search": {
+ "grounding": {
+ "searchQueries": "کلمات کلیدی جستجو",
+ "title": "تعداد {{count}} نتیجه پیدا شد"
+ },
+ "mode": {
+ "auto": {
+ "desc": "به طور هوشمندانه بر اساس محتوای گفتگو تشخیص میدهد که آیا نیاز به جستجو است",
+ "title": "اتصال هوشمند"
+ },
+ "off": {
+ "desc": "فقط از دانش پایه مدل استفاده میکند و جستجوی اینترنتی انجام نمیدهد",
+ "title": "قطع اتصال"
+ },
+ "on": {
+ "desc": "به طور مداوم جستجوی اینترنتی انجام میدهد و اطلاعات جدید را به دست میآورد",
+ "title": "همیشه متصل"
+ },
+ "useModelBuiltin": "استفاده از موتور جستجوی داخلی مدل"
+ },
+ "searchModel": {
+ "desc": "مدل فعلی از فراخوانی توابع پشتیبانی نمیکند، بنابراین نیاز است که با مدلی که از فراخوانی توابع پشتیبانی میکند، برای جستجوی آنلاین ترکیب شود",
+ "title": "مدل جستجوی کمکی"
+ },
+ "title": "جستجوی متصل"
+ },
+ "searchAgentPlaceholder": "جستجوی دستیار...",
+ "sendPlaceholder": "نوشتن پیام...",
+ "sessionGroup": {
+ "config": "مدیریت گروه",
+ "confirmRemoveGroupAlert": "این گروه در حال حذف شدن است. پس از حذف، دستیارهای این گروه به لیست پیشفرض منتقل خواهند شد. لطفاً عملیات خود را تأیید کنید.",
+ "createAgentSuccess": "دستیار با موفقیت ایجاد شد",
+ "createGroup": "افزودن گروه جدید",
+ "createSuccess": "گروه با موفقیت ایجاد شد",
+ "creatingAgent": "در حال ایجاد دستیار...",
+ "inputPlaceholder": "لطفاً نام گروه را وارد کنید...",
+ "moveGroup": "انتقال به گروه",
+ "newGroup": "گروه جدید",
+ "rename": "تغییر نام گروه",
+ "renameSuccess": "تغییر نام با موفقیت انجام شد",
+ "sortSuccess": "مرتبسازی با موفقیت انجام شد",
+ "sorting": "در حال بهروزرسانی مرتبسازی گروه...",
+ "tooLong": "طول نام گروه باید بین 1 تا 20 کاراکتر باشد"
+ },
+ "shareModal": {
+ "copy": "کپی",
+ "download": "دانلود اسکرینشات",
+ "downloadFile": "دانلود فایل",
+ "exportTitle": "عنوان پیشفرض",
+ "imageType": "فرمت تصویر",
+ "includeTool": "شامل پیامهای ابزار",
+ "includeUser": "شامل پیامهای کاربر",
+ "screenshot": "اسکرینشات",
+ "settings": "تنظیمات خروجی",
+ "text": "متن",
+ "withBackground": "شامل تصویر پسزمینه",
+ "withFooter": "شامل پاورقی",
+ "withPluginInfo": "شامل اطلاعات افزونه",
+ "withRole": "شامل نقش پیام",
+ "withSystemRole": "شامل تنظیمات نقش دستیار"
+ },
+ "stt": {
+ "action": "ورودی صوتی",
+ "loading": "در حال شناسایی...",
+ "prettifying": "در حال ویرایش..."
+ },
+ "thread": {
+ "divider": "زیرموضوع",
+ "threadMessageCount": "{{messageCount}} پیام",
+ "title": "زیرموضوع"
+ },
+ "tokenDetails": {
+ "chats": "پیامهای گفتگو",
+ "historySummary": "خلاصه تاریخ",
+ "rest": "باقیمانده قابل استفاده",
+ "systemRole": "تنظیم نقش",
+ "title": "جزئیات پیامها",
+ "tools": "تنظیمات افزونه",
+ "total": "کل قابل استفاده",
+ "used": "مجموع استفاده شده"
+ },
+ "tokenTag": {
+ "overload": "بیش از حد",
+ "remained": "باقیمانده",
+ "used": "استفاده شده"
+ },
+ "topic": {
+ "checkOpenNewTopic": "آیا مایل به باز کردن موضوع جدید هستید؟",
+ "checkSaveCurrentMessages": "آیا مایل به ذخیره مکالمه فعلی به عنوان موضوع هستید؟",
+ "openNewTopic": "باز کردن موضوع جدید",
+ "saveCurrentMessages": "ذخیره مکالمه فعلی به عنوان موضوع"
+ },
+ "translate": {
+ "action": "ترجمه",
+ "clear": "حذف ترجمه"
+ },
+ "tts": {
+ "action": "خواندن با صدا",
+ "clear": "حذف صدا"
+ },
+ "updateAgent": "بهروزرسانی اطلاعات دستیار",
+ "upload": {
+ "action": {
+ "fileUpload": "بارگذاری فایل",
+ "folderUpload": "بارگذاری پوشه",
+ "imageDisabled": "مدل فعلی از تشخیص بصری پشتیبانی نمیکند، لطفاً مدل را تغییر دهید و دوباره امتحان کنید",
+ "imageUpload": "بارگذاری تصویر",
+ "tooltip": "بارگذاری"
+ },
+ "clientMode": {
+ "actionFiletip": "بارگذاری فایل",
+ "actionTooltip": "بارگذاری",
+ "disabled": "مدل فعلی از تشخیص بصری و تحلیل فایل پشتیبانی نمیکند، لطفاً مدل را تغییر دهید و دوباره امتحان کنید"
+ },
+ "preview": {
+ "prepareTasks": "آمادهسازی بخشها...",
+ "status": {
+ "pending": "آماده برای بارگذاری...",
+ "processing": "در حال پردازش فایل..."
+ }
+ }
+ },
+ "zenMode": "حالت تمرکز"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/clerk.json b/DigitalHumanWeb/locales/fa-IR/clerk.json
new file mode 100644
index 0000000..8b57db6
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/clerk.json
@@ -0,0 +1,769 @@
+{
+ "backButton": "بازگشت",
+ "badge__default": "پیشفرض",
+ "badge__otherImpersonatorDevice": "دستگاه شبیهساز دیگر",
+ "badge__primary": "اصلی",
+ "badge__requiresAction": "نیاز به اقدام دارد",
+ "badge__thisDevice": "این دستگاه",
+ "badge__unverified": "تأیید نشده",
+ "badge__userDevice": "دستگاه کاربر",
+ "badge__you": "شما",
+ "createOrganization": {
+ "formButtonSubmit": "ایجاد سازمان",
+ "invitePage": {
+ "formButtonReset": "رد کردن"
+ },
+ "title": "ایجاد سازمان"
+ },
+ "dates": {
+ "lastDay": "دیروز {{ date | timeString('fa-IR') }}",
+ "next6Days": "{{ date | weekday('fa-IR','long') }} {{ date | timeString('fa-IR') }}",
+ "nextDay": "فردا {{ date | timeString('fa-IR') }}",
+ "numeric": "{{ date | numeric('fa-IR') }}",
+ "previous6Days": "هفته گذشته {{ date | weekday('fa-IR','long') }} {{ date | timeString('fa-IR') }}",
+ "sameDay": "امروز {{ date | timeString('fa-IR') }}"
+ },
+ "dividerText": "یا",
+ "footerActionLink__useAnotherMethod": "استفاده از روش دیگر",
+ "footerPageLink__help": "کمک",
+ "footerPageLink__privacy": "حریم خصوصی",
+ "footerPageLink__terms": "شرایط",
+ "formButtonPrimary": "ادامه",
+ "formButtonPrimary__verify": "تأیید",
+ "formFieldAction__forgotPassword": "فراموشی رمز عبور؟",
+ "formFieldError__matchingPasswords": "رمزهای عبور مطابقت دارند.",
+ "formFieldError__notMatchingPasswords": "رمزهای عبور مطابقت ندارند.",
+ "formFieldError__verificationLinkExpired": "لینک تأیید منقضی شده است. لطفاً یک لینک جدید درخواست کنید.",
+ "formFieldHintText__optional": "اختیاری",
+ "formFieldHintText__slug": "Slug یک شناسه قابل خواندن توسط انسان است که باید منحصربهفرد باشد. معمولاً در URL استفاده میشود.",
+ "formFieldInputPlaceholder__backupCode": "",
+ "formFieldInputPlaceholder__confirmDeletionUserAccount": "حذف حساب",
+ "formFieldInputPlaceholder__emailAddress": "",
+ "formFieldInputPlaceholder__emailAddress_username": "",
+ "formFieldInputPlaceholder__emailAddresses": "یک یا چند آدرس ایمیل را وارد یا جایگذاری کنید، با فاصله یا ویرگول جدا کنید",
+ "formFieldInputPlaceholder__firstName": "",
+ "formFieldInputPlaceholder__lastName": "نام خانوادگی",
+ "formFieldInputPlaceholder__organizationDomain": "",
+ "formFieldInputPlaceholder__organizationDomainEmailAddress": "",
+ "formFieldInputPlaceholder__organizationName": "",
+ "formFieldInputPlaceholder__organizationSlug": "سازمان-من",
+ "formFieldInputPlaceholder__password": "",
+ "formFieldInputPlaceholder__phoneNumber": "",
+ "formFieldInputPlaceholder__username": "",
+ "formFieldLabel__automaticInvitations": "فعالسازی دعوتنامههای خودکار برای این دامنه",
+ "formFieldLabel__backupCode": "کد پشتیبان",
+ "formFieldLabel__confirmDeletion": "تأیید",
+ "formFieldLabel__confirmPassword": "تأیید رمز عبور",
+ "formFieldLabel__currentPassword": "رمز عبور فعلی",
+ "formFieldLabel__emailAddress": "آدرس ایمیل",
+ "formFieldLabel__emailAddress_username": "آدرس ایمیل یا نام کاربری",
+ "formFieldLabel__emailAddresses": "آدرسهای ایمیل",
+ "formFieldLabel__firstName": "نام",
+ "formFieldLabel__lastName": "نام خانوادگی",
+ "formFieldLabel__newPassword": "رمز عبور جدید",
+ "formFieldLabel__organizationDomain": "دامنه",
+ "formFieldLabel__organizationDomainDeletePending": "حذف دعوتنامهها و پیشنهادات در انتظار بررسی",
+ "formFieldLabel__organizationDomainEmailAddress": "تأیید آدرس ایمیل",
+ "formFieldLabel__organizationDomainEmailAddressDescription": "یک آدرس ایمیل تحت این دامنه وارد کنید تا کد تأیید دریافت کرده و این دامنه را تأیید کنید.",
+ "formFieldLabel__organizationName": "نام سازمان",
+ "formFieldLabel__organizationSlug": "نام مختصر URL",
+ "formFieldLabel__passkeyName": "نام کلید عبور",
+ "formFieldLabel__password": "رمز عبور",
+ "formFieldLabel__phoneNumber": "شماره تلفن",
+ "formFieldLabel__role": "نقش",
+ "formFieldLabel__signOutOfOtherSessions": "خروج از تمام دستگاههای دیگر",
+ "formFieldLabel__username": "نام کاربری",
+ "impersonationFab": {
+ "action__signOut": "خروج از حساب",
+ "title": "ورود به عنوان {{identifier}}"
+ },
+ "locale": "fa-IR",
+ "maintenanceMode": "ما در حال حاضر در حال انجام تعمیرات هستیم، اما نگران نباشید، این کار بیش از چند دقیقه طول نخواهد کشید.",
+ "membershipRole__admin": "مدیر",
+ "membershipRole__basicMember": "عضو",
+ "membershipRole__guestMember": "مهمان",
+ "organizationList": {
+ "action__createOrganization": "ایجاد سازمان",
+ "action__invitationAccept": "پیوستن",
+ "action__suggestionsAccept": "درخواست پیوستن",
+ "createOrganization": "ایجاد سازمان",
+ "invitationAcceptedLabel": "پیوسته شد",
+ "subtitle": "برای ادامه استفاده از {{applicationName}}",
+ "suggestionsAcceptedLabel": "در انتظار تأیید",
+ "title": "یک حساب کاربری انتخاب کنید",
+ "titleWithoutPersonal": "یک سازمان انتخاب کنید"
+ },
+ "organizationProfile": {
+ "badge__automaticInvitation": "دعوت خودکار",
+ "badge__automaticSuggestion": "پیشنهاد خودکار",
+ "badge__manualInvitation": "بدون ثبتنام خودکار",
+ "badge__unverified": "تأیید نشده",
+ "createDomainPage": {
+ "subtitle": "دامنهای اضافه کنید تا تأیید شود. کاربرانی که آدرس ایمیل با این دامنه دارند میتوانند بهطور خودکار به سازمان بپیوندند یا درخواست عضویت دهند.",
+ "title": "افزودن دامنه"
+ },
+ "invitePage": {
+ "detailsTitle__inviteFailed": "دعوت ارسال نشد. آدرسهای ایمیل زیر دعوتهای در حال انتظار دارند: {{email_addresses}}.",
+ "formButtonPrimary__continue": "ارسال دعوت",
+ "selectDropdown__role": "انتخاب نقش",
+ "subtitle": "یک یا چند آدرس ایمیل وارد یا جایگذاری کنید، با فاصله یا ویرگول جدا کنید.",
+ "successMessage": "دعوت با موفقیت ارسال شد",
+ "title": "دعوت از اعضای جدید"
+ },
+ "membersPage": {
+ "action__invite": "دعوت",
+ "activeMembersTab": {
+ "menuAction__remove": "حذف عضو",
+ "tableHeader__actions": "",
+ "tableHeader__joined": "زمان پیوستن",
+ "tableHeader__role": "نقش",
+ "tableHeader__user": "کاربر"
+ },
+ "detailsTitle__emptyRow": "هیچ عضوی برای نمایش وجود ندارد",
+ "invitationsTab": {
+ "autoInvitations": {
+ "headerSubtitle": "کاربران را از طریق اتصال دامنه ایمیل به سازمان دعوت کنید. هر کاربری که با دامنه ایمیل مطابقت داشته باشد میتواند در هر زمان به سازمان بپیوندد.",
+ "headerTitle": "دعوت خودکار",
+ "primaryButton": "مدیریت دامنههای تأیید شده"
+ },
+ "table__emptyRow": "هیچ دعوتی برای نمایش وجود ندارد"
+ },
+ "invitedMembersTab": {
+ "menuAction__revoke": "لغو دعوت",
+ "tableHeader__invited": "دعوت شده"
+ },
+ "requestsTab": {
+ "autoSuggestions": {
+ "headerSubtitle": "کاربرانی که با دامنه ایمیل مطابقت دارند میتوانند پیشنهاد درخواست عضویت در سازمان را مشاهده کنند.",
+ "headerTitle": "پیشنهاد خودکار",
+ "primaryButton": "مدیریت دامنههای تأیید شده"
+ },
+ "menuAction__approve": "تأیید",
+ "menuAction__reject": "رد",
+ "tableHeader__requested": "درخواست دسترسی",
+ "table__emptyRow": "هیچ درخواستی برای نمایش وجود ندارد"
+ },
+ "start": {
+ "headerTitle__invitations": "دعوتها",
+ "headerTitle__members": "اعضا",
+ "headerTitle__requests": "درخواستها"
+ }
+ },
+ "navbar": {
+ "description": "مدیریت سازمان شما",
+ "general": "عمومی",
+ "members": "اعضا",
+ "title": "سازمان"
+ },
+ "profilePage": {
+ "dangerSection": {
+ "deleteOrganization": {
+ "actionDescription": "برای ادامه، «{{organizationName}}» را در زیر وارد کنید.",
+ "messageLine1": "آیا مطمئن هستید که میخواهید این سازمان را حذف کنید؟",
+ "messageLine2": "این عمل دائمی و غیرقابل بازگشت است.",
+ "successMessage": "شما سازمان را حذف کردهاید",
+ "title": "حذف سازمان"
+ },
+ "leaveOrganization": {
+ "actionDescription": "برای ادامه، «{{organizationName}}» را در زیر وارد کنید.",
+ "messageLine1": "آیا مطمئن هستید که میخواهید این سازمان را ترک کنید؟ شما دسترسی به این سازمان و برنامههای آن را از دست خواهید داد.",
+ "messageLine2": "این عمل دائمی و غیرقابل بازگشت است.",
+ "successMessage": "شما سازمان را ترک کردهاید",
+ "title": "ترک سازمان"
+ },
+ "title": "خطرناک"
+ },
+ "domainSection": {
+ "menuAction__manage": "مدیریت",
+ "menuAction__remove": "حذف",
+ "menuAction__verify": "تأیید",
+ "primaryButton": "افزودن دامنه",
+ "subtitle": "به کاربران اجازه دهید بر اساس دامنههای تأیید شده ایمیل بهطور خودکار به سازمان بپیوندند یا درخواست عضویت دهند.",
+ "title": "دامنههای تأیید شده"
+ },
+ "successMessage": "سازمان بهروزرسانی شد",
+ "title": "بهروزرسانی پروفایل"
+ },
+ "removeDomainPage": {
+ "messageLine1": "دامنه ایمیل {{domain}} حذف خواهد شد.",
+ "messageLine2": "پس از آن، کاربران نمیتوانند بهطور خودکار به سازمان بپیوندند.",
+ "successMessage": "{{domain}} حذف شد",
+ "title": "حذف دامنه"
+ },
+ "start": {
+ "headerTitle__general": "عمومی",
+ "headerTitle__members": "اعضا",
+ "profileSection": {
+ "primaryButton": "بهروزرسانی پروفایل",
+ "title": "پروفایل سازمان",
+ "uploadAction__title": "لوگو"
+ }
+ },
+ "verifiedDomainPage": {
+ "dangerTab": {
+ "calloutInfoLabel": "حذف این دامنه بر کاربران دعوتشده تأثیر خواهد گذاشت.",
+ "removeDomainActionLabel__remove": "حذف دامنه",
+ "removeDomainSubtitle": "حذف این دامنه از دامنههای تأیید شده",
+ "removeDomainTitle": "حذف دامنه"
+ },
+ "enrollmentTab": {
+ "automaticInvitationOption__description": "کاربران هنگام ثبتنام بهطور خودکار به سازمان دعوت میشوند و میتوانند در هر زمان بپیوندند.",
+ "automaticInvitationOption__label": "دعوت خودکار",
+ "automaticSuggestionOption__description": "کاربران پیشنهاد درخواست عضویت را دریافت میکنند، اما باید توسط مدیر تأیید شوند تا به سازمان بپیوندند.",
+ "automaticSuggestionOption__label": "پیشنهاد خودکار",
+ "calloutInfoLabel": "تغییر حالت ثبتنام فقط بر کاربران جدید تأثیر میگذارد.",
+ "calloutInvitationCountLabel": "دعوتهای در حال انتظار ارسال شده به کاربران: {{count}}",
+ "calloutSuggestionCountLabel": "پیشنهادهای در حال انتظار ارسال شده به کاربران: {{count}}",
+ "manualInvitationOption__description": "کاربران فقط میتوانند بهصورت دستی به سازمان دعوت شوند.",
+ "manualInvitationOption__label": "بدون پیوستن خودکار",
+ "subtitle": "انتخاب کنید که کاربران از این دامنه چگونه به سازمان بپیوندند."
+ },
+ "start": {
+ "headerTitle__danger": "خطرناک",
+ "headerTitle__enrollment": "گزینههای ثبتنام"
+ },
+ "subtitle": "دامنه {{domain}} تأیید شده است. ادامه دهید و حالت ثبتنام را انتخاب کنید.",
+ "title": "بهروزرسانی {{domain}}"
+ },
+ "verifyDomainPage": {
+ "formSubtitle": "کد تأیید ارسال شده به آدرس ایمیل خود را وارد کنید",
+ "formTitle": "کد تأیید",
+ "resendButton": "کد را دریافت نکردید؟ دوباره ارسال کنید",
+ "subtitle": "دامنه {{domainName}} باید از طریق ایمیل تأیید شود.",
+ "subtitleVerificationCodeScreen": "کد تأیید به {{emailAddress}} ارسال شده است. کد را وارد کنید تا ادامه دهید.",
+ "title": "تأیید دامنه"
+ }
+ },
+ "organizationSwitcher": {
+ "action__createOrganization": "ایجاد سازمان",
+ "action__invitationAccept": "پیوستن",
+ "action__manageOrganization": "مدیریت",
+ "action__suggestionsAccept": "درخواست پیوستن",
+ "notSelected": "سازمانی انتخاب نشده",
+ "personalWorkspace": "حساب شخصی",
+ "suggestionsAcceptedLabel": "در انتظار تأیید"
+ },
+ "paginationButton__next": "صفحه بعد",
+ "paginationButton__previous": "صفحه قبل",
+ "paginationRowText__displaying": "نمایش",
+ "paginationRowText__of": "از",
+ "signIn": {
+ "accountSwitcher": {
+ "action__addAccount": "افزودن حساب",
+ "action__signOutAll": "خروج از همه حسابها",
+ "subtitle": "حسابی را برای ادامه انتخاب کنید.",
+ "title": "یک حساب انتخاب کنید"
+ },
+ "alternativeMethods": {
+ "actionLink": "دریافت کمک",
+ "actionText": "اینها را ندارید؟",
+ "blockButton__backupCode": "استفاده از کد پشتیبان",
+ "blockButton__emailCode": "ارسال کد به {{identifier}}",
+ "blockButton__emailLink": "ارسال لینک به {{identifier}}",
+ "blockButton__passkey": "ورود با کلید امنیتی",
+ "blockButton__password": "ورود با رمز عبور",
+ "blockButton__phoneCode": "ارسال کد پیامکی به {{identifier}}",
+ "blockButton__totp": "استفاده از برنامه احراز هویت",
+ "getHelp": {
+ "blockButton__emailSupport": "پشتیبانی ایمیلی",
+ "content": "اگر در ورود به حساب خود مشکل دارید، برای ما ایمیل بفرستید و ما در اسرع وقت با شما همکاری خواهیم کرد تا دسترسی شما را بازیابی کنیم.",
+ "title": "دریافت کمک"
+ },
+ "subtitle": "مشکلی دارید؟ میتوانید از یکی از روشهای زیر برای ورود استفاده کنید.",
+ "title": "استفاده از روشهای دیگر"
+ },
+ "backupCodeMfa": {
+ "subtitle": "کد پشتیبان شما هنگام تنظیم احراز هویت دو مرحلهای دریافت شده است.",
+ "title": "کد پشتیبان را وارد کنید"
+ },
+ "emailCode": {
+ "formTitle": "کد تأیید",
+ "resendButton": "کد را دریافت نکردید؟ ارسال مجدد",
+ "subtitle": "برای ادامه به {{applicationName}}",
+ "title": "ایمیل خود را بررسی کنید"
+ },
+ "emailLink": {
+ "expired": {
+ "subtitle": "به برگه اصلی بازگردید و ادامه دهید.",
+ "title": "این لینک تأیید منقضی شده است"
+ },
+ "failed": {
+ "subtitle": "به برگه اصلی بازگردید و ادامه دهید.",
+ "title": "این لینک تأیید نامعتبر است"
+ },
+ "formSubtitle": "از لینک تأیید ارسال شده به ایمیل خود استفاده کنید",
+ "formTitle": "لینک تأیید",
+ "loading": {
+ "subtitle": "به زودی هدایت خواهید شد",
+ "title": "در حال ورود..."
+ },
+ "resendButton": "لینک را دریافت نکردید؟ ارسال مجدد",
+ "subtitle": "برای ادامه به {{applicationName}}",
+ "title": "ایمیل خود را بررسی کنید",
+ "unusedTab": {
+ "title": "میتوانید این برگه را ببندید"
+ },
+ "verified": {
+ "subtitle": "به زودی هدایت خواهید شد",
+ "title": "ورود موفقیتآمیز"
+ },
+ "verifiedSwitchTab": {
+ "subtitle": "به برگه اصلی بازگردید و ادامه دهید",
+ "subtitleNewTab": "به برگه جدید بازگردید و ادامه دهید",
+ "titleNewTab": "ورود در برگه دیگر"
+ }
+ },
+ "forgotPassword": {
+ "formTitle": "کد بازنشانی رمز عبور",
+ "resendButton": "کد را دریافت نکردید؟ ارسال مجدد",
+ "subtitle": "رمز عبور خود را بازنشانی کنید",
+ "subtitle_email": "ابتدا کدی که به ایمیل شما ارسال شده است را وارد کنید",
+ "subtitle_phone": "ابتدا کدی که به تلفن شما ارسال شده است را وارد کنید",
+ "title": "بازنشانی رمز عبور"
+ },
+ "forgotPasswordAlternativeMethods": {
+ "blockButton__resetPassword": "بازنشانی رمز عبور",
+ "label__alternativeMethods": "یا از روشهای دیگر برای ورود استفاده کنید",
+ "title": "رمز عبور را فراموش کردهاید؟"
+ },
+ "noAvailableMethods": {
+ "message": "امکان ادامه ورود وجود ندارد. هیچ عامل احراز هویتی در دسترس نیست.",
+ "subtitle": "خطایی رخ داده است",
+ "title": "ورود امکانپذیر نیست"
+ },
+ "passkey": {
+ "subtitle": "با استفاده از کلید امنیتی خود تأیید کنید که شما هستید. دستگاه شما ممکن است از شما اثر انگشت، چهره یا قفل صفحه بخواهد.",
+ "title": "استفاده از کلید امنیتی"
+ },
+ "password": {
+ "actionLink": "استفاده از روشهای دیگر",
+ "subtitle": "رمز عبور مرتبط با حساب خود را وارد کنید",
+ "title": "رمز عبور خود را وارد کنید"
+ },
+ "passwordPwned": {
+ "title": "رمز عبور افشا شده است"
+ },
+ "phoneCode": {
+ "formTitle": "کد تأیید",
+ "resendButton": "کد را دریافت نکردید؟ ارسال مجدد",
+ "subtitle": "برای ادامه به {{applicationName}}",
+ "title": "تلفن خود را بررسی کنید"
+ },
+ "phoneCodeMfa": {
+ "formTitle": "کد تأیید",
+ "resendButton": "کد را دریافت نکردید؟ ارسال مجدد",
+ "subtitle": "لطفاً ادامه دهید و کدی که به تلفن شما ارسال شده است را وارد کنید",
+ "title": "تلفن خود را بررسی کنید"
+ },
+ "resetPassword": {
+ "formButtonPrimary": "بازنشانی رمز عبور",
+ "requiredMessage": "به دلایل امنیتی، لازم است رمز عبور خود را بازنشانی کنید.",
+ "successMessage": "رمز عبور شما با موفقیت تغییر کرد. در حال ورود، لطفاً صبر کنید.",
+ "title": "تنظیم رمز عبور جدید"
+ },
+ "resetPasswordMfa": {
+ "detailsLabel": "قبل از بازنشانی رمز عبور، باید هویت شما تأیید شود."
+ },
+ "start": {
+ "actionLink": "ثبتنام",
+ "actionLink__use_email": "استفاده از ایمیل",
+ "actionLink__use_email_username": "استفاده از ایمیل یا نام کاربری",
+ "actionLink__use_passkey": "استفاده از کلید امنیتی",
+ "actionLink__use_phone": "استفاده از تلفن",
+ "actionLink__use_username": "استفاده از نام کاربری",
+ "actionText": "حساب ندارید؟",
+ "subtitle": "خوش آمدید! لطفاً برای ادامه وارد شوید",
+ "title": "ورود به {{applicationName}}"
+ },
+ "totpMfa": {
+ "formTitle": "کد تأیید",
+ "subtitle": "لطفاً ادامه دهید و کدی که توسط برنامه احراز هویت شما تولید شده است را وارد کنید",
+ "title": "احراز هویت دو مرحلهای"
+ }
+ },
+ "signInEnterPasswordTitle": "رمز عبور خود را وارد کنید",
+ "signUp": {
+ "continue": {
+ "actionLink": "ورود",
+ "actionText": "حساب کاربری دارید؟",
+ "subtitle": "لطفاً جزئیات باقیمانده را برای ادامه پر کنید.",
+ "title": "فیلدهای ناقص را پر کنید"
+ },
+ "emailCode": {
+ "formSubtitle": "کد ارسالشده به آدرس ایمیل خود را وارد کنید",
+ "formTitle": "کد تأیید",
+ "resendButton": "کد را دریافت نکردید؟ دوباره ارسال کنید",
+ "subtitle": "کد ارسالشده به ایمیل خود را وارد کنید",
+ "title": "ایمیل خود را تأیید کنید"
+ },
+ "emailLink": {
+ "formSubtitle": "از لینک تأییدی که به آدرس ایمیل شما ارسال شده استفاده کنید",
+ "formTitle": "لینک تأیید",
+ "loading": {
+ "title": "در حال ثبتنام..."
+ },
+ "resendButton": "لینک را دریافت نکردید؟ دوباره ارسال کنید",
+ "subtitle": "برای ادامه به {{applicationName}} دسترسی پیدا کنید",
+ "title": "ایمیل خود را تأیید کنید",
+ "verified": {
+ "title": "ثبتنام موفقیتآمیز"
+ },
+ "verifiedSwitchTab": {
+ "subtitle": "برای ادامه به تب جدید بازگشته و ادامه دهید",
+ "subtitleNewTab": "برای ادامه به تب قبلی بازگردید",
+ "title": "ایمیل با موفقیت تأیید شد"
+ }
+ },
+ "phoneCode": {
+ "formSubtitle": "کد ارسالشده به شماره تلفن خود را وارد کنید",
+ "formTitle": "کد تأیید",
+ "resendButton": "کد را دریافت نکردید؟ دوباره ارسال کنید",
+ "subtitle": "کد ارسالشده به تلفن همراه خود را وارد کنید",
+ "title": "تلفن خود را تأیید کنید"
+ },
+ "start": {
+ "actionLink": "ورود",
+ "actionText": "حساب کاربری دارید؟",
+ "subtitle": "خوش آمدید! لطفاً برای شروع اطلاعات خود را وارد کنید.",
+ "title": "حساب کاربری خود را ایجاد کنید"
+ }
+ },
+ "socialButtonsBlockButton": "ادامه با {{provider|titleize}}",
+ "unstable__errors": {
+ "captcha_invalid": "ثبتنام به دلیل شکست در تأیید امنیتی ناموفق بود. لطفاً صفحه را تازهسازی کرده و دوباره تلاش کنید یا برای کمک بیشتر با پشتیبانی تماس بگیرید.",
+ "captcha_unavailable": "ثبتنام به دلیل شکست در تأیید ربات ناموفق بود. لطفاً صفحه را تازهسازی کرده و دوباره تلاش کنید یا برای کمک بیشتر با پشتیبانی تماس بگیرید.",
+ "form_code_incorrect": "",
+ "form_identifier_exists": "",
+ "form_identifier_exists__email_address": "این آدرس ایمیل قبلاً استفاده شده است. لطفاً یکی دیگر را امتحان کنید.",
+ "form_identifier_exists__phone_number": "این شماره تلفن قبلاً استفاده شده است. لطفاً یکی دیگر را امتحان کنید.",
+ "form_identifier_exists__username": "این نام کاربری قبلاً استفاده شده است. لطفاً یکی دیگر را امتحان کنید.",
+ "form_identifier_not_found": "",
+ "form_param_format_invalid": "",
+ "form_param_format_invalid__email_address": "آدرس ایمیل باید یک آدرس ایمیل معتبر باشد.",
+ "form_param_format_invalid__phone_number": "شماره تلفن باید با فرمت بینالمللی معتبر مطابقت داشته باشد.",
+ "form_param_max_length_exceeded__first_name": "نام نباید بیش از ۲۵۶ کاراکتر باشد.",
+ "form_param_max_length_exceeded__last_name": "نام خانوادگی نباید بیش از ۲۵۶ کاراکتر باشد.",
+ "form_param_max_length_exceeded__name": "نام نباید بیش از ۲۵۶ کاراکتر باشد.",
+ "form_param_nil": "",
+ "form_password_incorrect": "",
+ "form_password_length_too_short": "",
+ "form_password_not_strong_enough": "رمز عبور شما به اندازه کافی قوی نیست.",
+ "form_password_pwned": "این رمز عبور به عنوان بخشی از یک افشای اطلاعات شناسایی شده است و نمیتوان از آن استفاده کرد. لطفاً رمز عبور دیگری را امتحان کنید.",
+ "form_password_pwned__sign_in": "این رمز عبور به عنوان بخشی از یک افشای اطلاعات شناسایی شده است و نمیتوان از آن استفاده کرد. لطفاً رمز عبور خود را بازنشانی کنید.",
+ "form_password_size_in_bytes_exceeded": "رمز عبور شما از حداکثر تعداد بایت مجاز فراتر رفته است. لطفاً آن را کوتاهتر کنید یا برخی از کاراکترهای خاص را حذف کنید.",
+ "form_password_validation_failed": "رمز عبور نادرست است.",
+ "form_username_invalid_character": "",
+ "form_username_invalid_length": "",
+ "identification_deletion_failed": "شما نمیتوانید آخرین تأیید هویت خود را حذف کنید.",
+ "not_allowed_access": "",
+ "passkey_already_exists": "این دستگاه قبلاً کلید عبور را ثبت کرده است.",
+ "passkey_not_supported": "این دستگاه از کلید عبور پشتیبانی نمیکند.",
+ "passkey_pa_not_supported": "ثبتنام نیاز به تأییدکننده پلتفرم دارد، اما دستگاه پشتیبانی نمیکند.",
+ "passkey_registration_cancelled": "ثبتنام کلید عبور لغو یا منقضی شد.",
+ "passkey_retrieval_cancelled": "تأیید کلید عبور لغو یا منقضی شد.",
+ "passwordComplexity": {
+ "maximumLength": "کمتر از {{length}} کاراکتر",
+ "minimumLength": "{{length}} کاراکتر یا بیشتر",
+ "requireLowercase": "یک حرف کوچک",
+ "requireNumbers": "یک عدد",
+ "requireSpecialCharacter": "یک کاراکتر خاص",
+ "requireUppercase": "یک حرف بزرگ",
+ "sentencePrefix": "رمز عبور شما باید شامل موارد زیر باشد"
+ },
+ "phone_number_exists": "این شماره تلفن قبلاً استفاده شده است. لطفاً یکی دیگر را امتحان کنید.",
+ "zxcvbn": {
+ "couldBeStronger": "رمز عبور شما میتواند قویتر باشد. سعی کنید کاراکترهای بیشتری اضافه کنید.",
+ "goodPassword": "رمز عبور شما تمام الزامات لازم را برآورده میکند.",
+ "notEnough": "رمز عبور شما به اندازه کافی قوی نیست.",
+ "suggestions": {
+ "allUppercase": "برخی از حروف را بزرگ کنید، اما نه همه.",
+ "anotherWord": "یک کلمه کمتر رایج اضافه کنید.",
+ "associatedYears": "از سالهایی که با شما مرتبط هستند اجتناب کنید.",
+ "capitalization": "بیش از یک حرف اول را بزرگ کنید.",
+ "dates": "از تاریخها و سالهایی که با شما مرتبط هستند اجتناب کنید.",
+ "l33t": "از جایگزینیهای قابل پیشبینی حروف مانند جایگزینی '@' به جای 'a' اجتناب کنید.",
+ "longerKeyboardPattern": "از یک الگوی صفحهکلید طولانیتر استفاده کنید و چندین بار جهت ورودی را تغییر دهید.",
+ "noNeed": "شما میتوانید یک رمز عبور قوی ایجاد کنید بدون نیاز به استفاده از نمادها، اعداد یا حروف بزرگ.",
+ "pwned": "اگر از این رمز عبور در جای دیگری استفاده کردهاید، باید آن را تغییر دهید.",
+ "recentYears": "از سالهای اخیر اجتناب کنید.",
+ "repeated": "از کلمات و کاراکترهای تکراری اجتناب کنید.",
+ "reverseWords": "از معکوس کردن املای کلمات رایج اجتناب کنید.",
+ "sequences": "از توالیهای کاراکتر رایج اجتناب کنید.",
+ "useWords": "از چندین کلمه استفاده کنید، اما از عبارات رایج اجتناب کنید."
+ },
+ "warnings": {
+ "common": "این یک رمز عبور رایج است.",
+ "commonNames": "نامها و نامهای خانوادگی رایج به راحتی قابل حدس زدن هستند.",
+ "dates": "تاریخها به راحتی قابل حدس زدن هستند.",
+ "extendedRepeat": "الگوهای تکراری کاراکتر مانند 'abcabcabc' به راحتی قابل حدس زدن هستند.",
+ "keyPattern": "الگوهای کوتاه صفحهکلید به راحتی قابل حدس زدن هستند.",
+ "namesByThemselves": "نام یا نام خانوادگی به تنهایی به راحتی قابل حدس زدن هستند.",
+ "pwned": "رمز عبور شما در یک افشای دادههای اینترنتی فاش شده است.",
+ "recentYears": "سالهای اخیر به راحتی قابل حدس زدن هستند.",
+ "sequences": "توالیهای کاراکتر رایج مانند 'abc' به راحتی قابل حدس زدن هستند.",
+ "similarToCommon": "این شبیه به رمزهای عبور رایج است.",
+ "simpleRepeat": "کاراکترهای تکراری مانند 'aaa' به راحتی قابل حدس زدن هستند.",
+ "straightRow": "کلیدهای مرتب شده در یک ردیف مستقیم روی صفحهکلید به راحتی قابل حدس زدن هستند.",
+ "topHundred": "این یک رمز عبور رایج است.",
+ "topTen": "این یک رمز عبور بسیار رایج است.",
+ "userInputs": "رمز عبور نباید شامل هیچگونه اطلاعات شخصی یا مرتبط با صفحه باشد.",
+ "wordByItself": "یک کلمه به تنهایی به راحتی قابل حدس زدن است."
+ }
+ }
+ },
+ "userButton": {
+ "action__addAccount": "افزودن حساب",
+ "action__manageAccount": "مدیریت حسابها",
+ "action__signOut": "خروج",
+ "action__signOutAll": "خروج از همه حسابها"
+ },
+ "userProfile": {
+ "backupCodePage": {
+ "actionLabel__copied": "کپی شد!",
+ "actionLabel__copy": "کپی همه",
+ "actionLabel__download": "دانلود .txt",
+ "actionLabel__print": "چاپ",
+ "infoText1": "این حساب کدهای پشتیبان را فعال خواهد کرد.",
+ "infoText2": "کدهای پشتیبان را محرمانه نگه دارید و در مکانی امن ذخیره کنید. اگر مشکوک هستید که کدهای پشتیبان فاش شدهاند، میتوانید آنها را دوباره تولید کنید.",
+ "subtitle__codelist": "کدهای پشتیبان را بهطور امن ذخیره و محرمانه نگه دارید.",
+ "successMessage": "کدهای پشتیبان اکنون فعال شدهاند. اگر به دستگاه احراز هویت خود دسترسی ندارید، میتوانید از یکی از این کدها برای ورود به حساب خود استفاده کنید. هر کد فقط یکبار قابل استفاده است.",
+ "successSubtitle": "اگر به دستگاه احراز هویت خود دسترسی ندارید، میتوانید از یکی از این کدها برای ورود به حساب خود استفاده کنید.",
+ "title": "افزودن تأیید کد پشتیبان",
+ "title__codelist": "کدهای پشتیبان"
+ },
+ "connectedAccountPage": {
+ "formHint": "ارائهدهندهای را برای اتصال حساب خود انتخاب کنید.",
+ "formHint__noAccounts": "هیچ ارائهدهنده حساب خارجی در دسترس نیست.",
+ "removeResource": {
+ "messageLine1": "{{identifier}} از این حساب حذف خواهد شد.",
+ "messageLine2": "شما دیگر نمیتوانید از این حساب متصل استفاده کنید و هر ویژگی وابسته به آن دیگر کار نخواهد کرد.",
+ "successMessage": "{{connectedAccount}} از حساب شما حذف شد.",
+ "title": "حذف حساب متصل"
+ },
+ "socialButtonsBlockButton": "{{provider|titleize}}",
+ "successMessage": "ارائهدهنده به حساب شما اضافه شد",
+ "title": "افزودن حساب متصل"
+ },
+ "deletePage": {
+ "actionDescription": "برای ادامه، 'حذف حساب' را در زیر وارد کنید.",
+ "confirm": "حذف حساب",
+ "messageLine1": "آیا مطمئن هستید که میخواهید حساب خود را حذف کنید؟",
+ "messageLine2": "این عمل دائمی و غیرقابل بازگشت است.",
+ "title": "حذف حساب"
+ },
+ "emailAddressPage": {
+ "emailCode": {
+ "formHint": "یک ایمیل حاوی کد تأیید به این آدرس ایمیل ارسال خواهد شد.",
+ "formSubtitle": "کد ارسالشده به {{identifier}} را وارد کنید.",
+ "formTitle": "کد تأیید",
+ "resendButton": "کد را دریافت نکردید؟ دوباره ارسال کنید",
+ "successMessage": "ایمیل {{identifier}} به حساب شما اضافه شد."
+ },
+ "emailLink": {
+ "formHint": "یک ایمیل حاوی لینک تأیید به این آدرس ایمیل ارسال خواهد شد.",
+ "formSubtitle": "روی لینک تأیید در ایمیل ارسالشده به {{identifier}} کلیک کنید.",
+ "formTitle": "لینک تأیید",
+ "resendButton": "لینک را دریافت نکردید؟ دوباره ارسال کنید",
+ "successMessage": "ایمیل {{identifier}} به حساب شما اضافه شد."
+ },
+ "removeResource": {
+ "messageLine1": "{{identifier}} از این حساب حذف خواهد شد.",
+ "messageLine2": "شما دیگر نمیتوانید با این آدرس ایمیل وارد شوید.",
+ "successMessage": "{{emailAddress}} از حساب شما حذف شد.",
+ "title": "حذف آدرس ایمیل"
+ },
+ "title": "افزودن آدرس ایمیل",
+ "verifyTitle": "تأیید آدرس ایمیل"
+ },
+ "formButtonPrimary__add": "افزودن",
+ "formButtonPrimary__continue": "ادامه",
+ "formButtonPrimary__finish": "پایان",
+ "formButtonPrimary__remove": "حذف",
+ "formButtonPrimary__save": "ذخیره",
+ "formButtonReset": "لغو",
+ "mfaPage": {
+ "formHint": "روشی را برای افزودن انتخاب کنید.",
+ "title": "افزودن تأیید دو مرحلهای"
+ },
+ "mfaPhoneCodePage": {
+ "backButton": "استفاده از شماره موجود",
+ "primaryButton__addPhoneNumber": "افزودن شماره تلفن",
+ "removeResource": {
+ "messageLine1": "{{identifier}} دیگر کد تأیید را هنگام ورود دریافت نخواهد کرد.",
+ "messageLine2": "حساب شما ممکن است به اندازه کافی امن نباشد. آیا مطمئن هستید که میخواهید ادامه دهید؟",
+ "successMessage": "تأیید دو مرحلهای با کد پیامکی برای {{mfaPhoneCode}} حذف شد.",
+ "title": "حذف تأیید دو مرحلهای"
+ },
+ "subtitle__availablePhoneNumbers": "یک شماره تلفن موجود را برای ثبتنام در تأیید دو مرحلهای با کد پیامکی انتخاب کنید یا شماره جدیدی اضافه کنید.",
+ "subtitle__unavailablePhoneNumbers": "هیچ شماره تلفنی برای ثبتنام در تأیید دو مرحلهای با کد پیامکی در دسترس نیست، لطفاً شماره جدیدی اضافه کنید.",
+ "successMessage1": "هنگام ورود، باید کدی که به این شماره تلفن ارسال میشود را به عنوان یک مرحله اضافی وارد کنید.",
+ "successMessage2": "این کدهای پشتیبان را ذخیره کرده و در مکانی امن نگه دارید. اگر به دستگاه احراز هویت خود دسترسی ندارید، میتوانید از کدهای پشتیبان برای ورود استفاده کنید.",
+ "successTitle": "تأیید کد پیامکی فعال شد",
+ "title": "افزودن تأیید کد پیامکی"
+ },
+ "mfaTOTPPage": {
+ "authenticatorApp": {
+ "buttonAbleToScan__nonPrimary": "اسکن کد QR",
+ "buttonUnableToScan__nonPrimary": "نمیتوانید کد QR را اسکن کنید؟",
+ "infoText__ableToScan": "یک روش ورود جدید را در برنامه احراز هویت خود تنظیم کرده و کد QR زیر را اسکن کنید تا آن را به حساب خود لینک کنید.",
+ "infoText__unableToScan": "یک روش ورود جدید را در برنامه احراز هویت خود تنظیم کرده و کلید زیر را وارد کنید.",
+ "inputLabel__unableToScan1": "مطمئن شوید که رمز عبور یکبار مصرف یا مبتنی بر زمان فعال است، سپس لینک کردن حساب خود را کامل کنید.",
+ "inputLabel__unableToScan2": "یا اگر برنامه احراز هویت شما از URI TOTP پشتیبانی میکند، میتوانید URI کامل را کپی کنید."
+ },
+ "removeResource": {
+ "messageLine1": "دیگر نیازی به کد تأیید از این برنامه احراز هویت هنگام ورود نخواهد بود.",
+ "messageLine2": "حساب شما ممکن است به اندازه کافی امن نباشد. آیا مطمئن هستید که میخواهید ادامه دهید؟",
+ "successMessage": "تأیید دو مرحلهای از طریق برنامه احراز هویت حذف شد.",
+ "title": "حذف تأیید دو مرحلهای"
+ },
+ "successMessage": "تأیید دو مرحلهای اکنون فعال شده است. هنگام ورود، باید کدی که توسط این برنامه احراز هویت تولید میشود را به عنوان یک مرحله اضافی وارد کنید.",
+ "title": "افزودن برنامه احراز هویت",
+ "verifySubtitle": "کد تولیدشده توسط برنامه احراز هویت خود را وارد کنید",
+ "verifyTitle": "تأیید کد"
+ },
+ "mobileButton__menu": "منو",
+ "navbar": {
+ "account": "پروفایل",
+ "description": "مدیریت اطلاعات حساب خود",
+ "security": "امنیت",
+ "title": "حساب"
+ },
+ "passkeyScreen": {
+ "removeResource": {
+ "messageLine1": "{{name}} از این حساب حذف خواهد شد.",
+ "title": "حذف کلید عبور"
+ },
+ "subtitle__rename": "میتوانید نام کلید عبور را تغییر دهید تا راحتتر آن را پیدا کنید.",
+ "title__rename": "تغییر نام کلید عبور"
+ },
+ "passwordPage": {
+ "checkboxInfoText__signOutOfOtherSessions": "پیشنهاد میشود از تمام دستگاههایی که ممکن است از رمز عبور قدیمی استفاده کنند، خارج شوید.",
+ "readonly": "در حال حاضر نمیتوانید رمز عبور را ویرایش کنید زیرا فقط از طریق اتصال سازمانی وارد شدهاید.",
+ "successMessage__set": "رمز عبور شما تنظیم شد.",
+ "successMessage__signOutOfOtherSessions": "تمام دستگاههای دیگر خارج شدند.",
+ "successMessage__update": "رمز عبور شما بهروزرسانی شد.",
+ "title__set": "تنظیم رمز عبور",
+ "title__update": "بهروزرسانی رمز عبور"
+ },
+ "phoneNumberPage": {
+ "infoText": "یک پیامک حاوی کد تأیید به این شماره تلفن ارسال خواهد شد. ممکن است هزینههای پیامک و داده اعمال شود.",
+ "removeResource": {
+ "messageLine1": "{{identifier}} از این حساب حذف خواهد شد.",
+ "messageLine2": "شما دیگر نمیتوانید با این شماره تلفن وارد شوید.",
+ "successMessage": "{{phoneNumber}} از حساب شما حذف شد.",
+ "title": "حذف شماره تلفن"
+ },
+ "successMessage": "{{identifier}} به حساب شما اضافه شد.",
+ "title": "افزودن شماره تلفن",
+ "verifySubtitle": "کد ارسالشده به {{identifier}} را وارد کنید",
+ "verifyTitle": "تأیید شماره تلفن"
+ },
+ "profilePage": {
+ "fileDropAreaHint": "اندازه پیشنهادی 1:1، حداکثر 10MB.",
+ "imageFormDestructiveActionSubtitle": "حذف",
+ "imageFormSubtitle": "آپلود",
+ "imageFormTitle": "تصویر پروفایل",
+ "readonly": "اطلاعات پروفایل شما توسط اتصال سازمانی ارائه شده و قابل ویرایش نیست.",
+ "successMessage": "پروفایل شما بهروزرسانی شد.",
+ "title": "بهروزرسانی پروفایل"
+ },
+ "start": {
+ "activeDevicesSection": {
+ "destructiveAction": "خروج از دستگاه",
+ "title": "دستگاههای فعال"
+ },
+ "connectedAccountsSection": {
+ "actionLabel__connectionFailed": "دوباره تلاش کنید",
+ "actionLabel__reauthorize": "اکنون مجوز دهید",
+ "destructiveActionTitle": "حذف",
+ "primaryButton": "اتصال حساب",
+ "subtitle__reauthorize": "محدودههای مورد نیاز بهروزرسانی شدهاند، ممکن است با محدودیتهایی مواجه شوید. لطفاً این برنامه را دوباره مجوز دهید تا از هرگونه مشکل جلوگیری کنید.",
+ "title": "حسابهای متصل"
+ },
+ "dangerSection": {
+ "deleteAccountButton": "حذف حساب",
+ "title": "حذف حساب"
+ },
+ "emailAddressesSection": {
+ "destructiveAction": "حذف ایمیل",
+ "detailsAction__nonPrimary": "تنظیم به عنوان اصلی",
+ "detailsAction__primary": "تأیید کامل",
+ "detailsAction__unverified": "تأیید",
+ "primaryButton": "افزودن آدرس ایمیل",
+ "title": "آدرسهای ایمیل"
+ },
+ "enterpriseAccountsSection": {
+ "title": "حسابهای سازمانی"
+ },
+ "headerTitle__account": "جزئیات پروفایل",
+ "headerTitle__security": "امنیت",
+ "mfaSection": {
+ "backupCodes": {
+ "actionLabel__regenerate": "دوباره تولید کنید",
+ "headerTitle": "کدهای پشتیبان",
+ "subtitle__regenerate": "یک مجموعه جدید از کدهای پشتیبان امن دریافت کنید. کدهای پشتیبان قبلی حذف شده و دیگر قابل استفاده نخواهند بود.",
+ "title__regenerate": "دوباره تولید کدهای پشتیبان"
+ },
+ "phoneCode": {
+ "actionLabel__setDefault": "تنظیم به عنوان پیشفرض",
+ "destructiveActionLabel": "حذف"
+ },
+ "primaryButton": "افزودن تأیید دو مرحلهای",
+ "title": "تأیید دو مرحلهای",
+ "totp": {
+ "destructiveActionTitle": "حذف",
+ "headerTitle": "برنامه احراز هویت"
+ }
+ },
+ "passkeysSection": {
+ "menuAction__destructive": "حذف",
+ "menuAction__rename": "تغییر نام",
+ "title": "کلیدهای عبور"
+ },
+ "passwordSection": {
+ "primaryButton__setPassword": "تنظیم رمز عبور",
+ "primaryButton__updatePassword": "بهروزرسانی رمز عبور",
+ "title": "رمز عبور"
+ },
+ "phoneNumbersSection": {
+ "destructiveAction": "حذف شماره تلفن",
+ "detailsAction__nonPrimary": "تنظیم به عنوان اصلی",
+ "detailsAction__primary": "تأیید کامل",
+ "detailsAction__unverified": "تأیید شماره تلفن",
+ "primaryButton": "افزودن شماره تلفن",
+ "title": "شمارههای تلفن"
+ },
+ "profileSection": {
+ "primaryButton": "بهروزرسانی پروفایل",
+ "title": "پروفایل"
+ },
+ "usernameSection": {
+ "primaryButton__setUsername": "تنظیم نام کاربری",
+ "primaryButton__updateUsername": "بهروزرسانی نام کاربری",
+ "title": "نام کاربری"
+ },
+ "web3WalletsSection": {
+ "destructiveAction": "حذف کیف پول",
+ "primaryButton": "کیف پول Web3",
+ "title": "کیف پول Web3"
+ }
+ },
+ "usernamePage": {
+ "successMessage": "نام کاربری شما بهروزرسانی شد.",
+ "title__set": "تنظیم نام کاربری",
+ "title__update": "بهروزرسانی نام کاربری"
+ },
+ "web3WalletPage": {
+ "removeResource": {
+ "messageLine1": "{{identifier}} از این حساب حذف خواهد شد.",
+ "messageLine2": "شما دیگر نمیتوانید با این کیف پول Web3 وارد شوید.",
+ "successMessage": "{{web3Wallet}} از حساب شما حذف شد.",
+ "title": "حذف کیف پول Web3"
+ },
+ "subtitle__availableWallets": "کیف پول Web3 را که میخواهید به حساب خود متصل کنید، انتخاب کنید.",
+ "subtitle__unavailableWallets": "هیچ کیف پول Web3 در دسترس نیست.",
+ "successMessage": "کیف پول به حساب شما اضافه شد.",
+ "title": "افزودن کیف پول Web3"
+ }
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/common.json b/DigitalHumanWeb/locales/fa-IR/common.json
new file mode 100644
index 0000000..b9a4cf0
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/common.json
@@ -0,0 +1,304 @@
+{
+ "about": "درباره",
+ "advanceSettings": "تنظیمات پیشرفته",
+ "alert": {
+ "cloud": {
+ "action": "همین حالا امتحان کنید",
+ "desc": "ما به تمام کاربران ثبتنامشده {{credit}} اعتبار رایگان برای محاسبه امتیاز ارائه میدهیم. بدون نیاز به پیکربندی پیچیده، آماده به کار است و از همگامسازی ابری جهانی و جستجوی پیشرفته شبکه پشتیبانی میکند. ویژگیهای پیشرفته بیشتری در انتظار شماست.",
+ "descOnMobile": "ما به تمام کاربران ثبتنامشده {{credit}} اعتبار رایگان برای محاسبه امتیاز ارائه میدهیم. بدون نیاز به پیکربندی پیچیده، آماده به کار است.",
+ "title": "{{name}} شروع به آزمایش عمومی کرد"
+ }
+ },
+ "appLoading": {
+ "appIdle": "در حال آمادهسازی برای راهاندازی",
+ "appInitializing": "در حال راهاندازی برنامه...",
+ "failed": "متأسفیم، راهاندازی برنامه با شکست مواجه شد، لطفاً برای بررسی جزئیات به آن مراجعه کنید",
+ "finished": "راهاندازی پایگاه داده کامل شد",
+ "goToChat": "در حال بارگذاری صفحه گفتگو...",
+ "initAuth": "در حال راهاندازی سرویس احراز هویت...",
+ "initUser": "در حال راهاندازی وضعیت کاربر...",
+ "initializing": "در حال راهاندازی پایگاه داده PGlite...",
+ "loadingDependencies": "در حال بارگذاری وابستگیها...",
+ "loadingWasm": "در حال بارگذاری ماژول WASM...",
+ "migrating": "در حال اجرای مهاجرت جداول داده...",
+ "ready": "پایگاه داده آماده است",
+ "showDetail": "مشاهده جزئیات"
+ },
+ "autoGenerate": "تکمیل خودکار",
+ "autoGenerateTooltip": "تکمیل خودکار توضیحات دستیار بر اساس کلمات راهنما",
+ "autoGenerateTooltipDisabled": "لطفاً پس از وارد کردن کلمات کلیدی از قابلیت تکمیل خودکار استفاده کنید",
+ "back": "بازگشت",
+ "batchDelete": "حذف دستهای",
+ "blog": "وبلاگ محصولات",
+ "branching": "ایجاد زیرموضوع",
+ "branchingDisable": "ویژگی «زیرموضوع» تنها در نسخه سرور قابل استفاده است، اگر به این ویژگی نیاز دارید، لطفاً به حالت استقرار سرور تغییر دهید یا از LobeChat Cloud استفاده کنید.",
+ "cancel": "لغو",
+ "changelog": "تغییرات",
+ "clientDB": {
+ "autoInit": {
+ "title": "راهاندازی پایگاه داده PGlite"
+ },
+ "error": {
+ "desc": "متأسفیم، در روند初始化 پایگاه داده Pglite خطایی رخ داده است. لطفاً دکمه را برای تلاش مجدد فشار دهید. اگر پس از چندین بار تلاش، هنوز خطا تکرار شد، لطفاً <1>مسئله را گزارش کنید1>، ما در اولین فرصت به شما کمک خواهیم کرد.",
+ "detail": "علت خطا: [{{type}}] {{message}}، جزئیات به شرح زیر است:",
+ "retry": "تکرار",
+ "title": "خطای در初始化 پایگاه داده"
+ },
+ "initing": {
+ "error": "خطایی رخ داده است، لطفاً دوباره تلاش کنید",
+ "idle": "در حال انتظار برای راهاندازی...",
+ "initializing": "در حال راهاندازی...",
+ "loadingDependencies": "در حال بارگذاری وابستگیها...",
+ "loadingWasmModule": "در حال بارگذاری ماژول WASM...",
+ "migrating": "در حال انجام مهاجرت جدول دادهها...",
+ "ready": "پایگاه داده آماده است"
+ },
+ "modal": {
+ "desc": "فعالسازی پایگاه داده کلاینت PGlite، برای ذخیرهسازی دائمی دادههای گفتگو در مرورگر شما و استفاده از ویژگیهای پیشرفته مانند دانشنامه",
+ "enable": "همین حالا فعالسازی کنید",
+ "features": {
+ "knowledgeBase": {
+ "desc": "دانشنامه شخصی خود را بسازید و به راحتی با دستیار خود گفتگو کنید (به زودی منتشر میشود)",
+ "title": "پشتیبانی از گفتگو در دانشنامه، آغاز مغز دوم"
+ },
+ "localFirst": {
+ "desc": "تمام دادههای چت در مرورگر ذخیره میشوند و دادههای شما همیشه در کنترل شماست.",
+ "title": "اولویت محلی، حریم خصوصی در اولویت"
+ },
+ "pglite": {
+ "desc": "بر اساس PGlite ساخته شده، پشتیبانی بومی از ویژگیهای پیشرفته AI Native (جستجوی برداری)",
+ "title": "معماری ذخیرهسازی کلاینت نسل جدید"
+ }
+ },
+ "init": {
+ "desc": "در حال راهاندازی پایگاه داده، بسته به تفاوتهای شبکه ممکن است ۵ تا ۳۰ ثانیه طول بکشد",
+ "title": "در حال راهاندازی پایگاه داده PGlite"
+ },
+ "title": "فعالسازی پایگاه داده کلاینت"
+ },
+ "ready": {
+ "button": "همین حالا استفاده کنید",
+ "desc": "همین حالا میخواهید استفاده کنید",
+ "title": "پایگاه داده PGlite آماده است"
+ }
+ },
+ "close": "بستن",
+ "contact": "تماس با ما",
+ "copy": "کپی",
+ "copyFail": "کپی ناموفق بود",
+ "copySuccess": "کپی با موفقیت انجام شد",
+ "dataStatistics": {
+ "messages": "پیامها",
+ "sessions": "دستیار",
+ "today": "افزودههای امروز",
+ "topics": "موضوعات"
+ },
+ "defaultAgent": "دستیار سفارشی",
+ "defaultSession": "دستیار سفارشی",
+ "delete": "حذف",
+ "document": "استفاده از مستندات",
+ "download": "دانلود",
+ "duplicate": "ایجاد نسخه کپی",
+ "edit": "ویرایش",
+ "export": "صدور تنظیمات",
+ "exportType": {
+ "agent": "خروجی تنظیمات دستیار",
+ "agentWithMessage": "خروجی دستیار و پیامها",
+ "all": "خروجی تنظیمات کلی و تمام دادههای دستیار",
+ "allAgent": "خروجی تمام تنظیمات دستیار",
+ "allAgentWithMessage": "خروجی تمام دستیارها و پیامها",
+ "globalSetting": "خروجی تنظیمات کلی"
+ },
+ "feedback": "بازخورد و پیشنهادات",
+ "follow": "ما را در {{name}} دنبال کنید",
+ "footer": {
+ "action": {
+ "feedback": "نظرات ارزشمند خود را با ما به اشتراک بگذارید",
+ "star": "در GitHub به ما ستاره بدهید"
+ },
+ "and": "و",
+ "feedback": {
+ "action": "اشتراکگذاری بازخورد",
+ "desc": "هر ایده و نظری که دارید برای ما بسیار ارزشمند است و ما بیصبرانه منتظر شنیدن نظرات شما هستیم! خوشحال میشویم که با ما تماس بگیرید و بازخورد خود را در مورد ویژگیهای محصول و تجربه کاربری ارائه دهید تا به ما کمک کنید {{appName}} را بهتر کنیم.",
+ "title": "بازخورد ارزشمند خود را در GitHub به اشتراک بگذارید"
+ },
+ "later": "بعداً",
+ "star": {
+ "action": "ستاره بدهید",
+ "desc": "اگر از محصول ما لذت میبرید و مایل به حمایت از ما هستید، آیا میتوانید در GitHub به ما یک ستاره بدهید؟ این حرکت کوچک برای ما بسیار مهم است و ما را تشویق میکند تا به ارائه تجربههای بهتر برای شما ادامه دهیم.",
+ "title": "در GitHub به ما ستاره بدهید"
+ },
+ "title": "آیا از محصول ما خوشتان آمده؟"
+ },
+ "fullscreen": "حالت تمام صفحه",
+ "historyRange": "محدوده تاریخی",
+ "import": "وارد کردن تنظیمات",
+ "importModal": {
+ "error": {
+ "desc": "متأسفانه در فرآیند وارد کردن دادهها خطایی رخ داده است. لطفاً دوباره تلاش کنید یا <1>مشکل را گزارش دهید1> تا ما در اسرع وقت به شما کمک کنیم.",
+ "title": "وارد کردن دادهها ناموفق بود"
+ },
+ "finish": {
+ "onlySettings": "تنظیمات سیستم با موفقیت وارد شد",
+ "start": "شروع به استفاده",
+ "subTitle": "وارد کردن دادهها با موفقیت انجام شد و {{duration}} ثانیه طول کشید. جزئیات واردات به شرح زیر است:",
+ "title": "وارد کردن دادهها کامل شد"
+ },
+ "loading": "در حال وارد کردن دادهها، لطفاً صبور باشید...",
+ "preparing": "در حال آمادهسازی ماژول وارد کردن دادهها...",
+ "result": {
+ "added": "واردات موفقیتآمیز بود",
+ "errors": "خطا در واردات",
+ "messages": "پیامها",
+ "sessionGroups": "گروهها",
+ "sessions": "دستیار",
+ "skips": "تکراریها رد شدند",
+ "topics": "موضوعات",
+ "type": "نوع داده"
+ },
+ "title": "وارد کردن دادهها",
+ "uploading": {
+ "desc": "فایل فعلی بزرگ است، در حال تلاش برای آپلود...",
+ "restTime": "زمان باقیمانده",
+ "speed": "سرعت آپلود"
+ }
+ },
+ "information": "جامعه و اطلاعات",
+ "installPWA": "نصب برنامه وب پیشرو (PWA)",
+ "lang": {
+ "ar": "عربی",
+ "bg-BG": "بلغاری",
+ "bn": "بنگالی",
+ "cs-CZ": "چکی",
+ "da-DK": "دانمارکی",
+ "de-DE": "آلمانی",
+ "el-GR": "یونانی",
+ "en": "انگلیسی",
+ "en-US": "انگلیسی",
+ "es-ES": "اسپانیایی",
+ "fa-IR": "فارسی",
+ "fi-FI": "فنلاندی",
+ "fr-FR": "فرانسوی",
+ "hi-IN": "هندی",
+ "hu-HU": "مجاری",
+ "id-ID": "اندونزیایی",
+ "it-IT": "ایتالیایی",
+ "ja-JP": "ژاپنی",
+ "ko-KR": "کرهای",
+ "nl-NL": "هلندی",
+ "no-NO": "نروژی",
+ "pl-PL": "لهستانی",
+ "pt-BR": "پرتغالی (برزیل)",
+ "pt-PT": "پرتغالی (پرتغال)",
+ "ro-RO": "رومانیایی",
+ "ru-RU": "روسی",
+ "sk-SK": "اسلواکی",
+ "sr-RS": "صربی",
+ "sv-SE": "سوئدی",
+ "th-TH": "تایلندی",
+ "tr-TR": "ترکی",
+ "uk-UA": "اوکراینی",
+ "vi-VN": "ویتنامی",
+ "zh": "چینی سادهشده",
+ "zh-CN": "چینی سادهشده",
+ "zh-TW": "چینی سنتی"
+ },
+ "layoutInitializing": "در حال بارگذاری چیدمان...",
+ "legal": "بیانیه حقوقی",
+ "loading": "در حال بارگذاری...",
+ "mail": {
+ "business": "همکاری تجاری",
+ "support": "پشتیبانی ایمیل"
+ },
+ "oauth": "ورود با SSO",
+ "officialSite": "وبسایت رسمی",
+ "ok": "تأیید",
+ "password": "رمز عبور",
+ "pin": "سنجاق کردن",
+ "pinOff": "لغو سنجاق کردن",
+ "privacy": "سیاست حفظ حریم خصوصی",
+ "regenerate": "بازتولید",
+ "releaseNotes": "جزئیات نسخه",
+ "rename": "تغییر نام",
+ "reset": "بازنشانی",
+ "retry": "تلاش مجدد",
+ "send": "ارسال",
+ "setting": "تنظیمات",
+ "share": "اشتراکگذاری",
+ "stop": "توقف",
+ "sync": {
+ "actions": {
+ "settings": "تنظیمات همگامسازی",
+ "sync": "همگامسازی فوری"
+ },
+ "awareness": {
+ "current": "دستگاه فعلی"
+ },
+ "channel": "کانال",
+ "disabled": {
+ "actions": {
+ "enable": "فعالسازی همگامسازی ابری",
+ "settings": "پیکربندی پارامترهای همگامسازی"
+ },
+ "desc": "دادههای جلسه فعلی فقط در این مرورگر ذخیره میشوند. اگر نیاز به همگامسازی دادهها بین چندین دستگاه دارید، لطفاً همگامسازی ابری را پیکربندی و فعال کنید.",
+ "title": "همگامسازی داده غیرفعال است"
+ },
+ "enabled": {
+ "title": "همگامسازی داده"
+ },
+ "status": {
+ "connecting": "در حال اتصال",
+ "disabled": "همگامسازی غیرفعال است",
+ "ready": "متصل شد",
+ "synced": "همگامسازی شد",
+ "syncing": "در حال همگامسازی",
+ "unconnected": "اتصال ناموفق"
+ },
+ "title": "وضعیت همگامسازی",
+ "unconnected": {
+ "tip": "اتصال به سرور سیگنالدهی ناموفق بود، امکان برقراری کانال ارتباطی نقطه به نقطه وجود ندارد. لطفاً پس از بررسی شبکه دوباره تلاش کنید."
+ }
+ },
+ "tab": {
+ "chat": "گفتگو",
+ "discover": "کشف",
+ "files": "فایلها",
+ "me": "من",
+ "setting": "تنظیمات"
+ },
+ "telemetry": {
+ "allow": "اجازه دادن",
+ "deny": "رد کردن",
+ "desc": "ما میخواهیم به صورت ناشناس اطلاعات استفاده شما را جمعآوری کنیم تا به ما در بهبود {{appName}} کمک کند و تجربه بهتری از محصول را برای شما فراهم کنیم. شما میتوانید هر زمان از طریق «تنظیمات» - «درباره» آن را غیرفعال کنید.",
+ "learnMore": "بیشتر بدانید",
+ "title": "به {{appName}} کمک کنید بهتر شود"
+ },
+ "temp": "موقت",
+ "terms": "شرایط خدمات",
+ "update": "بهروزرسانی",
+ "updateAgent": "بهروزرسانی اطلاعات دستیار",
+ "upgradeVersion": {
+ "action": "ارتقاء",
+ "hasNew": "بهروزرسانی موجود است",
+ "newVersion": "نسخه جدید موجود است: {{version}}"
+ },
+ "userPanel": {
+ "anonymousNickName": "کاربر ناشناس",
+ "billing": "مدیریت صورتحساب",
+ "cloud": "تجربه {{name}}",
+ "community": "نسخه جامعه",
+ "data": "ذخیرهسازی داده",
+ "defaultNickname": "کاربر نسخه جامعه",
+ "discord": "پشتیبانی جامعه",
+ "docs": "مستندات استفاده",
+ "email": "پشتیبانی ایمیل",
+ "feedback": "بازخورد و پیشنهادات",
+ "help": "مرکز راهنما",
+ "moveGuide": "دکمه تنظیمات به اینجا منتقل شد",
+ "plans": "طرحهای اشتراک",
+ "profile": "مدیریت حساب",
+ "setting": "تنظیمات برنامه",
+ "usages": "آمار استفاده"
+ },
+ "version": "نسخه"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/components.json b/DigitalHumanWeb/locales/fa-IR/components.json
new file mode 100644
index 0000000..0d67aa1
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/components.json
@@ -0,0 +1,121 @@
+{
+ "DragUpload": {
+ "dragDesc": "فایلها را اینجا بکشید، امکان بارگذاری چندین تصویر وجود دارد.",
+ "dragFileDesc": "تصاویر و فایلها را اینجا بکشید، امکان بارگذاری چندین تصویر و فایل وجود دارد.",
+ "dragFileTitle": "بارگذاری فایل",
+ "dragTitle": "بارگذاری تصویر"
+ },
+ "FileManager": {
+ "actions": {
+ "addToKnowledgeBase": "افزودن به پایگاه دانش",
+ "addToOtherKnowledgeBase": "افزودن به پایگاه دانش دیگر",
+ "batchChunking": "تقسیم دستهای",
+ "chunking": "تقسیم",
+ "chunkingTooltip": "فایل را به چندین بخش متنی تقسیم کرده و پس از بردارسازی، برای جستجوی معنایی و مکالمه با فایل قابل استفاده است",
+ "chunkingUnsupported": "این فایل از تقسیمبندی پشتیبانی نمیکند",
+ "confirmDelete": "این فایل در حال حذف است و پس از حذف قابل بازیابی نخواهد بود. لطفاً عملیات خود را تأیید کنید",
+ "confirmDeleteMultiFiles": "در حال حذف {{count}} فایل انتخاب شده هستید. پس از حذف، این فایلها قابل بازیابی نخواهند بود. لطفاً عملیات خود را تأیید کنید",
+ "confirmRemoveFromKnowledgeBase": "در حال حذف {{count}} فایل انتخاب شده از پایگاه دانش هستید. پس از حذف، فایلها همچنان در بخش همه فایلها قابل مشاهده خواهند بود. لطفاً عملیات خود را تأیید کنید",
+ "copyUrl": "کپی کردن لینک",
+ "copyUrlSuccess": "آدرس فایل با موفقیت کپی شد",
+ "createChunkingTask": "در حال آمادهسازی...",
+ "deleteSuccess": "فایل با موفقیت حذف شد",
+ "downloading": "در حال دانلود فایل...",
+ "removeFromKnowledgeBase": "حذف از پایگاه دانش",
+ "removeFromKnowledgeBaseSuccess": "فایل با موفقیت حذف شد"
+ },
+ "bottom": "به انتها رسیدید",
+ "config": {
+ "showFilesInKnowledgeBase": "نمایش محتویات در پایگاه دانش"
+ },
+ "emptyStatus": {
+ "actions": {
+ "file": "آپلود فایل",
+ "folder": "آپلود پوشه",
+ "knowledgeBase": "ایجاد پایگاه دانش جدید"
+ },
+ "or": "یا",
+ "title": "فایل یا پوشه را به اینجا بکشید"
+ },
+ "title": {
+ "createdAt": "زمان ایجاد",
+ "size": "اندازه",
+ "title": "فایل"
+ },
+ "total": {
+ "fileCount": "مجموعاً {{count}} مورد",
+ "selectedCount": "{{count}} مورد انتخاب شده"
+ }
+ },
+ "FileParsingStatus": {
+ "chunks": {
+ "embeddingStatus": {
+ "empty": "بلوکهای متن هنوز به طور کامل برداری نشدهاند، که باعث میشود قابلیت جستجوی معنایی غیرفعال باشد. برای بهبود کیفیت جستجو، لطفاً بلوکهای متن را برداری کنید.",
+ "error": "برداریسازی ناموفق بود",
+ "errorResult": "برداریسازی ناموفق بود، لطفاً بررسی کرده و دوباره تلاش کنید. دلیل شکست:",
+ "processing": "بلوکهای متن در حال برداریسازی هستند، لطفاً صبور باشید",
+ "success": "تمام بلوکهای متن با موفقیت برداریسازی شدهاند"
+ },
+ "embeddings": "برداریسازی",
+ "status": {
+ "error": "تقسیمبندی ناموفق بود",
+ "errorResult": "تقسیمبندی ناموفق بود، لطفاً بررسی کرده و دوباره تلاش کنید. دلیل شکست:",
+ "processing": "در حال تقسیمبندی",
+ "processingTip": "سرور در حال تقسیمبندی بلوکهای متن است، بستن صفحه بر پیشرفت تقسیمبندی تأثیری ندارد."
+ }
+ }
+ },
+ "GoBack": {
+ "back": "بازگشت"
+ },
+ "MaxTokenSlider": {
+ "unlimited": "نامحدود"
+ },
+ "ModelSelect": {
+ "featureTag": {
+ "custom": "مدل سفارشی، تنظیمات پیشفرض از فراخوانی توابع و تشخیص بصری پشتیبانی میکند، لطفاً قابلیتهای فوق را بر اساس شرایط واقعی بررسی کنید",
+ "file": "این مدل از بارگذاری و شناسایی فایلها پشتیبانی میکند",
+ "functionCall": "این مدل از فراخوانی توابع (Function Call) پشتیبانی میکند",
+ "reasoning": "این مدل از تفکر عمیق پشتیبانی میکند",
+ "search": "این مدل از جستجوی آنلاین پشتیبانی میکند",
+ "tokens": "این مدل در هر جلسه حداکثر از {{tokens}} توکن پشتیبانی میکند",
+ "vision": "این مدل از تشخیص بصری پشتیبانی میکند"
+ },
+ "removed": "این مدل دیگر در فهرست نیست، در صورت لغو انتخاب بهطور خودکار حذف خواهد شد"
+ },
+ "ModelSwitchPanel": {
+ "emptyModel": "هیچ مدلی فعال نیست، لطفاً به تنظیمات بروید و آن را فعال کنید",
+ "emptyProvider": "هیچ ارائهدهندهای فعال نیست، لطفاً به تنظیمات بروید و آن را فعال کنید",
+ "goToSettings": "به تنظیمات بروید",
+ "provider": "ارائهدهنده"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "به دلیل محدودیتهای امنیتی مرورگر، شما باید تنظیمات跨域 برای Ollama را انجام دهید تا بتوانید به درستی از آن استفاده کنید.",
+ "linux": {
+ "env": "در بخش [Service]، `Environment` را اضافه کنید و متغیر محیطی OLLAMA_ORIGINS را اضافه کنید:",
+ "reboot": "systemd را بارگذاری مجدد کرده و Ollama را راهاندازی مجدد کنید",
+ "systemd": "برای ویرایش سرویس ollama از systemd استفاده کنید:"
+ },
+ "macos": "لطفاً برنامه «ترمینال» را باز کرده و دستورات زیر را کپی کرده و با فشار دادن Enter اجرا کنید",
+ "reboot": "لطفاً پس از اتمام اجرا، سرویس Ollama را راهاندازی مجدد کنید",
+ "title": "تنظیمات Ollama برای اجازه دسترسی跨域",
+ "windows": "در ویندوز، بر روی «کنترل پنل» کلیک کنید و به ویرایش متغیرهای محیطی سیستم بروید. برای حساب کاربری خود یک متغیر محیطی جدید به نام «OLLAMA_ORIGINS» با مقدار * ایجاد کنید و بر روی «OK/اعمال» کلیک کنید تا ذخیره شود."
+ },
+ "install": {
+ "description": "لطفاً اطمینان حاصل کنید که Ollama را فعال کردهاید. اگر Ollama را دانلود نکردهاید، لطفاً به وبسایت رسمی <1>دانلود1> بروید.",
+ "docker": "اگر تمایل دارید از Docker استفاده کنید، Ollama همچنین تصویر Docker رسمی را ارائه میدهد که میتوانید با استفاده از دستور زیر آن را بارگیری کنید:",
+ "linux": {
+ "command": "با استفاده از دستور زیر نصب کنید:",
+ "manual": "یا میتوانید به <1>راهنمای نصب دستی لینوکس1> مراجعه کنید و خودتان نصب کنید."
+ },
+ "title": "نصب و راهاندازی محلی برنامه Ollama",
+ "windowsTab": "ویندوز (نسخه پیشنمایش)"
+ }
+ },
+ "Thinking": {
+ "thinking": "در حال تفکر عمیق...",
+ "thought": "بهطور عمیق فکر شده است (مدت زمان {{duration}} ثانیه)",
+ "thoughtWithDuration": "بهطور عمیق فکر شده است"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/discover.json b/DigitalHumanWeb/locales/fa-IR/discover.json
new file mode 100644
index 0000000..4860754
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/discover.json
@@ -0,0 +1,208 @@
+{
+ "assistants": {
+ "addAgent": "افزودن دستیار",
+ "addAgentAndConverse": "افزودن دستیار و گفتگو",
+ "addAgentSuccess": "افزودن موفقیتآمیز بود",
+ "conversation": {
+ "l1": "سلام، من **{{name}}** هستم، میتوانید هر سوالی از من بپرسید و من تمام تلاشم را برای پاسخ دادن به شما خواهم کرد ~",
+ "l2": "در اینجا تواناییهای من معرفی شده است: ",
+ "l3": "بیایید گفتگو را شروع کنیم!"
+ },
+ "description": "معرفی دستیار",
+ "detail": "جزئیات",
+ "list": "فهرست دستیاران",
+ "more": "بیشتر",
+ "plugins": "افزونههای یکپارچه",
+ "recentSubmits": "آخرین بهروزرسانیها",
+ "suggestions": "پیشنهادات مرتبط",
+ "systemRole": "تنظیمات دستیار",
+ "try": "امتحان کنید"
+ },
+ "back": "بازگشت به اکتشاف",
+ "category": {
+ "assistant": {
+ "academic": "تحصیلی",
+ "all": "همه",
+ "career": "شغلی",
+ "copywriting": "کپینویسی",
+ "design": "طراحی",
+ "education": "آموزش",
+ "emotions": "احساسات",
+ "entertainment": "سرگرمی",
+ "games": "بازیها",
+ "general": "عمومی",
+ "life": "زندگی",
+ "marketing": "بازاریابی",
+ "office": "اداری",
+ "programming": "برنامهنویسی",
+ "translation": "ترجمه"
+ },
+ "plugin": {
+ "all": "همه",
+ "gaming-entertainment": "بازی و سرگرمی",
+ "life-style": "سبک زندگی",
+ "media-generate": "تولید رسانه",
+ "science-education": "علم و آموزش",
+ "social": "رسانههای اجتماعی",
+ "stocks-finance": "سهام و مالی",
+ "tools": "ابزارهای کاربردی",
+ "web-search": "جستجوی وب"
+ }
+ },
+ "cleanFilter": "پاک کردن فیلتر",
+ "create": "ایجاد",
+ "createGuide": {
+ "func1": {
+ "desc1": "در پنجره گفتگو از طریق تنظیمات در گوشه بالا سمت راست به صفحه تنظیماتی که میخواهید دستیار را ارسال کنید، وارد شوید؛",
+ "desc2": "روی دکمه ارسال به بازار دستیار در گوشه بالا سمت راست کلیک کنید.",
+ "tag": "روش اول",
+ "title": "ارسال از طریق LobeChat"
+ },
+ "func2": {
+ "button": "رفتن به مخزن دستیار در Github",
+ "desc": "اگر میخواهید دستیار را به فهرست اضافه کنید، از agent-template.json یا agent-template-full.json استفاده کنید تا یک ورودی در دایرکتوری plugins ایجاد کنید، توضیح کوتاهی بنویسید و بهطور مناسب برچسبگذاری کنید، سپس یک درخواست کششی (Pull Request) ایجاد کنید.",
+ "tag": "روش دوم",
+ "title": "ارسال از طریق Github"
+ }
+ },
+ "dislike": "دوست ندارم",
+ "filter": "فیلتر",
+ "filterBy": {
+ "authorRange": {
+ "everyone": "همه نویسندگان",
+ "followed": "نویسندگان دنبالشده",
+ "title": "محدوده نویسنده"
+ },
+ "contentLength": "حداقل طول محتوا",
+ "maxToken": {
+ "title": "تنظیم حداکثر طول (توکن)",
+ "unlimited": "نامحدود"
+ },
+ "other": {
+ "functionCall": "پشتیبانی از فراخوانی تابع",
+ "title": "سایر",
+ "vision": "پشتیبانی از تشخیص بصری",
+ "withKnowledge": "همراه با پایگاه دانش",
+ "withTool": "همراه با افزونه"
+ },
+ "pricing": "قیمت مدل",
+ "timePeriod": {
+ "all": "تمام زمانها",
+ "day": "24 ساعت گذشته",
+ "month": "30 روز گذشته",
+ "title": "بازه زمانی",
+ "week": "7 روز گذشته",
+ "year": "یک سال گذشته"
+ }
+ },
+ "home": {
+ "featuredAssistants": "دستیارهای پیشنهادی",
+ "featuredModels": "مدلهای پیشنهادی",
+ "featuredProviders": "ارائهدهندگان مدل پیشنهادی",
+ "featuredTools": "افزونههای پیشنهادی",
+ "more": "کشف بیشتر"
+ },
+ "like": "دوست داشتن",
+ "models": {
+ "chat": "شروع گفتگو",
+ "contentLength": "حداکثر طول محتوا",
+ "free": "رایگان",
+ "guide": "راهنمای پیکربندی",
+ "list": "فهرست مدلها",
+ "more": "بیشتر",
+ "parameterList": {
+ "defaultValue": "مقدار پیشفرض",
+ "docs": "مشاهده مستندات",
+ "frequency_penalty": {
+ "desc": "این تنظیمات فرکانس استفاده مجدد از کلمات خاصی که در ورودی ظاهر شدهاند را تنظیم میکند. مقادیر بالاتر احتمال تکرار این کلمات را کاهش میدهد، در حالی که مقادیر منفی اثر معکوس دارند. جریمه کلمات با افزایش تعداد تکرار افزایش نمییابد. مقادیر منفی استفاده مجدد از کلمات را تشویق میکند.",
+ "title": "جریمه فرکانس"
+ },
+ "max_tokens": {
+ "desc": "این تنظیمات حداکثر طولی که مدل میتواند در یک پاسخ واحد تولید کند را تعریف میکند. مقادیر بالاتر به مدل اجازه میدهد پاسخهای طولانیتری تولید کند، در حالی که مقادیر پایینتر طول پاسخ را محدود کرده و آن را مختصرتر میکند. با توجه به سناریوهای مختلف، تنظیم مناسب این مقدار میتواند به دستیابی به طول و جزئیات مورد انتظار پاسخ کمک کند.",
+ "title": "محدودیت پاسخ واحد"
+ },
+ "presence_penalty": {
+ "desc": "این تنظیمات به منظور کنترل استفاده مجدد از کلمات بر اساس فرکانس ظاهر شدن آنها در ورودی طراحی شده است. این تنظیمات تلاش میکند تا از استفاده مکرر از کلماتی که بیشتر در ورودی ظاهر شدهاند جلوگیری کند و فرکانس استفاده از آنها را متناسب با فرکانس ظاهر شدنشان تنظیم میکند. جریمه کلمات با افزایش تعداد تکرار افزایش مییابد. مقادیر منفی استفاده مجدد از کلمات را تشویق میکند.",
+ "title": "تازگی موضوع"
+ },
+ "range": "محدوده",
+ "reasoning_effort": {
+ "desc": "این تنظیم برای کنترل شدت استدلال مدل قبل از تولید پاسخ استفاده میشود. شدت پایین به سرعت پاسخدهی اولویت میدهد و توکن را صرفهجویی میکند، در حالی که شدت بالا استدلال کاملتری ارائه میدهد اما توکن بیشتری مصرف کرده و سرعت پاسخدهی را کاهش میدهد. مقدار پیشفرض متوسط است که تعادل بین دقت استدلال و سرعت پاسخدهی را برقرار میکند.",
+ "title": "شدت استدلال"
+ },
+ "temperature": {
+ "desc": "این تنظیمات بر تنوع پاسخهای مدل تأثیر میگذارد. مقادیر پایینتر منجر به پاسخهای قابل پیشبینیتر و معمولیتر میشود، در حالی که مقادیر بالاتر تنوع و پاسخهای غیرمعمولتر را تشویق میکند. وقتی مقدار به 0 تنظیم شود، مدل همیشه برای ورودی داده شده یک پاسخ یکسان ارائه میدهد.",
+ "title": "تصادفی بودن"
+ },
+ "title": "پارامترهای مدل",
+ "top_p": {
+ "desc": "این تنظیمات انتخاب مدل را به درصدی از کلماتی که بالاترین احتمال را دارند محدود میکند: فقط کلماتی که احتمال تجمعی آنها به P میرسد انتخاب میشوند. مقادیر پایینتر پاسخهای مدل را قابل پیشبینیتر میکند، در حالی که تنظیمات پیشفرض به مدل اجازه میدهد از کل دامنه کلمات انتخاب کند.",
+ "title": "نمونهگیری هستهای"
+ },
+ "type": "نوع"
+ },
+ "providerInfo": {
+ "apiTooltip": "LobeChat از کلید API سفارشی برای این ارائهدهنده پشتیبانی میکند.",
+ "input": "قیمت ورودی",
+ "inputTooltip": "هزینه به ازای هر یک میلیون توکن",
+ "latency": "تأخیر",
+ "latencyTooltip": "میانگین زمان پاسخ برای ارسال اولین توکن توسط ارائهدهنده",
+ "maxOutput": "حداکثر طول خروجی",
+ "maxOutputTooltip": "حداکثر تعداد توکنهایی که این نقطه انتهایی میتواند تولید کند",
+ "officialTooltip": "خدمات رسمی LobeHub",
+ "output": "قیمت خروجی",
+ "outputTooltip": "هزینه به ازای هر یک میلیون توکن",
+ "streamCancellationTooltip": "این ارائهدهنده از قابلیت لغو جریان پشتیبانی میکند.",
+ "throughput": "توان عملیاتی",
+ "throughputTooltip": "میانگین تعداد توکنهای منتقل شده در هر ثانیه در درخواستهای جریانی"
+ },
+ "suggestions": "مدلهای مرتبط",
+ "supportedProviders": "ارائهدهندگان پشتیبانی شده برای این مدل"
+ },
+ "plugins": {
+ "community": "پلاگینهای انجمن",
+ "install": "نصب پلاگین",
+ "installed": "نصب شده",
+ "list": "فهرست پلاگینها",
+ "meta": {
+ "description": "توضیحات",
+ "parameter": "پارامتر",
+ "title": "پارامترهای ابزار",
+ "type": "نوع"
+ },
+ "more": "بیشتر",
+ "official": "پلاگینهای رسمی",
+ "recentSubmits": "آخرین بهروزرسانیها",
+ "suggestions": "پیشنهادات مرتبط"
+ },
+ "providers": {
+ "config": "پیکربندی ارائهدهنده",
+ "list": "فهرست ارائهدهندگان مدل",
+ "modelCount": "{{count}} مدل",
+ "modelSite": "مستندات مدل",
+ "more": "بیشتر",
+ "officialSite": "وبسایت رسمی",
+ "showAllModels": "نمایش همه مدلها",
+ "suggestions": "ارائهدهندگان مرتبط",
+ "supportedModels": "مدلهای پشتیبانیشده"
+ },
+ "search": {
+ "placeholder": "جستجوی نام، توضیحات یا کلمات کلیدی...",
+ "result": "{{count}} نتیجه برای {{keyword}} یافت شد",
+ "searching": "در حال جستجو..."
+ },
+ "sort": {
+ "mostLiked": "بیشترین پسند",
+ "mostUsed": "بیشترین استفاده",
+ "newest": "جدیدترین",
+ "oldest": "قدیمیترین",
+ "recommended": "توصیهشده"
+ },
+ "tab": {
+ "assistants": "دستیارها",
+ "home": "صفحه اصلی",
+ "models": "مدلها",
+ "plugins": "افزونهها",
+ "providers": "ارائهدهندگان مدل"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/error.json b/DigitalHumanWeb/locales/fa-IR/error.json
new file mode 100644
index 0000000..9b5ec00
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/error.json
@@ -0,0 +1,147 @@
+{
+ "clerkAuth": {
+ "loginSuccess": {
+ "action": "ادامه جلسه",
+ "desc": "{{greeting}}، خوشحالیم که میتوانیم دوباره به شما خدمت کنیم. بیایید مکالمه قبلی را ادامه دهیم.",
+ "title": "خوش آمدید، {{nickName}}"
+ }
+ },
+ "error": {
+ "backHome": "بازگشت به صفحه اصلی",
+ "desc": "بعداً دوباره امتحان کنید، یا به دنیای آشنا بازگردید",
+ "retry": "بارگذاری مجدد",
+ "title": "مشکلی در صفحه رخ داده است.."
+ },
+ "fetchError": {
+ "detail": "جزئیات خطا",
+ "title": "درخواست ناموفق بود"
+ },
+ "loginRequired": {
+ "desc": "به زودی به صفحه ورود منتقل خواهید شد",
+ "title": "لطفاً پس از ورود از این قابلیت استفاده کنید"
+ },
+ "notFound": {
+ "backHome": "بازگشت به صفحه اصلی",
+ "check": "لطفاً بررسی کنید که آیا URL شما صحیح است",
+ "desc": "ما نتوانستیم صفحهای که به دنبال آن هستید را پیدا کنیم",
+ "title": "وارد قلمروی ناشناخته شدهاید؟"
+ },
+ "pluginSettings": {
+ "desc": "با انجام تنظیمات زیر، میتوانید از این افزونه استفاده کنید",
+ "title": "تنظیمات افزونه {{name}}"
+ },
+ "response": {
+ "400": "متأسفیم، سرور درخواست شما را متوجه نشد، لطفاً پارامترهای درخواست خود را بررسی کنید",
+ "401": "متأسفیم، سرور درخواست شما را رد کرد، ممکن است به دلیل عدم دسترسی یا عدم ارائه احراز هویت معتبر باشد",
+ "403": "متأسفیم، سرور درخواست شما را رد کرد، شما اجازه دسترسی به این محتوا را ندارید",
+ "404": "متأسفیم، سرور صفحه یا منبع درخواستی شما را پیدا نکرد، لطفاً URL خود را بررسی کنید",
+ "405": "متأسفیم، سرور از روش درخواست شما پشتیبانی نمیکند، لطفاً روش درخواست خود را بررسی کنید",
+ "406": "متأسفیم، سرور نمیتواند درخواست شما را بر اساس ویژگیهای محتوای درخواست شده انجام دهد",
+ "407": "متأسفیم، شما باید ابتدا احراز هویت پروکسی را انجام دهید تا بتوانید ادامه دهید",
+ "408": "متأسفیم، سرور در انتظار درخواست شما زمانسنجی کرد، لطفاً اتصال شبکه خود را بررسی کرده و دوباره تلاش کنید",
+ "409": "متأسفیم، درخواست شما با تعارض مواجه است و نمیتواند پردازش شود، ممکن است به دلیل ناسازگاری وضعیت منابع با درخواست باشد",
+ "410": "متأسفیم، منبع درخواستی شما به طور دائم حذف شده و قابل یافتن نیست",
+ "411": "متأسفیم، سرور نمیتواند درخواست بدون طول محتوای معتبر را پردازش کند",
+ "412": "متأسفیم، درخواست شما شرایط سرور را برآورده نمیکند و نمیتواند انجام شود",
+ "413": "متأسفیم، دادههای درخواست شما بیش از حد بزرگ است و سرور نمیتواند آن را پردازش کند",
+ "414": "متأسفیم، URI درخواست شما بیش از حد طولانی است و سرور نمیتواند آن را پردازش کند",
+ "415": "متأسفیم، سرور نمیتواند فرمت رسانهای درخواست شده را پردازش کند",
+ "416": "متأسفیم، سرور نمیتواند محدوده درخواست شما را برآورده کند",
+ "417": "متأسفیم، سرور نمیتواند انتظارات شما را برآورده کند",
+ "422": "متأسفیم، فرمت درخواست شما صحیح است اما به دلیل خطای معنایی نمیتواند پاسخ دهد",
+ "423": "متأسفیم، منبع درخواستی شما قفل شده است",
+ "424": "متأسفیم، به دلیل شکست درخواست قبلی، درخواست فعلی نمیتواند انجام شود",
+ "426": "متأسفیم، سرور از شما میخواهد که به نسخه بالاتری از پروتکل ارتقا دهید",
+ "428": "متأسفیم، سرور نیاز به شرایط پیشنیاز دارد و درخواست شما باید شامل هدرهای شرطی صحیح باشد",
+ "429": "متأسفیم، درخواستهای شما بیش از حد است، سرور خسته شده است، لطفاً بعداً دوباره تلاش کنید",
+ "431": "متأسفیم، فیلدهای هدر درخواست شما بیش از حد بزرگ است و سرور نمیتواند آن را پردازش کند",
+ "451": "متأسفیم، به دلیل مسائل قانونی، سرور از ارائه این منبع خودداری میکند",
+ "500": "متأسفیم، سرور با مشکلی مواجه شده و نمیتواند درخواست شما را در حال حاضر انجام دهد، لطفاً بعداً دوباره تلاش کنید",
+ "501": "متأسفیم، سرور هنوز نمیداند چگونه این درخواست را پردازش کند، لطفاً بررسی کنید که آیا عملیات شما صحیح است",
+ "502": "متأسفیم، سرور به نظر میرسد مسیر خود را گم کرده و نمیتواند خدمات ارائه دهد، لطفاً بعداً دوباره تلاش کنید",
+ "503": "متأسفیم، سرور در حال حاضر نمیتواند درخواست شما را پردازش کند، ممکن است به دلیل بار زیاد یا نگهداری باشد، لطفاً بعداً دوباره تلاش کنید",
+ "504": "متأسفیم، سرور پاسخی از سرور بالادستی دریافت نکرده است، لطفاً بعداً دوباره تلاش کنید",
+ "505": "متأسفیم، سرور از نسخه HTTP شما پشتیبانی نمیکند، لطفاً بهروزرسانی کنید و دوباره تلاش کنید",
+ "506": "متأسفیم، پیکربندی سرور با مشکل مواجه شده است، لطفاً با مدیر سیستم تماس بگیرید",
+ "507": "متأسفیم، فضای ذخیرهسازی سرور کافی نیست و نمیتواند درخواست شما را پردازش کند، لطفاً بعداً دوباره تلاش کنید",
+ "509": "متأسفیم، پهنای باند سرور به پایان رسیده است، لطفاً بعداً دوباره تلاش کنید",
+ "510": "متأسفیم، سرور از قابلیتهای افزوده درخواست پشتیبانی نمیکند، لطفاً با مدیر سیستم تماس بگیرید",
+ "524": "متأسفیم، سرور در انتظار پاسخ زمانسنجی کرد، ممکن است به دلیل کندی پاسخ باشد، لطفاً بعداً دوباره تلاش کنید",
+ "AgentRuntimeError": "اجرای Lobe AI Runtime با خطا مواجه شد، لطفاً بر اساس اطلاعات زیر بررسی کنید یا دوباره تلاش کنید",
+ "ConnectionCheckFailed": "درخواست بدون پاسخ برگشت، لطفاً بررسی کنید که آیا آدرس پروکسی API در انتها شامل `/v1` نیست",
+ "ExceededContextWindow": "محتوای درخواست فعلی از طول قابل پردازش مدل فراتر رفته است، لطفاً حجم محتوا را کاهش داده و دوباره تلاش کنید",
+ "FreePlanLimit": "شما در حال حاضر کاربر رایگان هستید و نمیتوانید از این قابلیت استفاده کنید، لطفاً به یک طرح پولی ارتقا دهید تا ادامه دهید",
+ "InsufficientQuota": "متأسفیم، سهمیه این کلید به حداکثر رسیده است، لطفاً موجودی حساب خود را بررسی کرده یا سهمیه کلید را افزایش دهید و دوباره تلاش کنید",
+ "InvalidAccessCode": "رمز عبور نادرست یا خالی است، لطفاً رمز عبور صحیح را وارد کنید یا API Key سفارشی اضافه کنید",
+ "InvalidBedrockCredentials": "اعتبارسنجی Bedrock ناموفق بود، لطفاً AccessKeyId/SecretAccessKey را بررسی کرده و دوباره تلاش کنید",
+ "InvalidClerkUser": "متأسفیم، شما هنوز وارد نشدهاید، لطفاً ابتدا وارد شوید یا ثبتنام کنید و سپس ادامه دهید",
+ "InvalidGithubToken": "Github PAT نادرست یا خالی است، لطفاً Github PAT را بررسی کرده و دوباره تلاش کنید",
+ "InvalidOllamaArgs": "پیکربندی Ollama نادرست است، لطفاً پیکربندی Ollama را بررسی کرده و دوباره تلاش کنید",
+ "InvalidProviderAPIKey": "{{provider}} API Key نادرست یا خالی است، لطفاً {{provider}} API Key را بررسی کرده و دوباره تلاش کنید",
+ "InvalidVertexCredentials": "احراز هویت Vertex ناموفق بود، لطفاً گواهی احراز هویت را بررسی کرده و دوباره تلاش کنید",
+ "LocationNotSupportError": "متأسفیم، منطقه شما از این سرویس مدل پشتیبانی نمیکند، ممکن است به دلیل محدودیتهای منطقهای یا عدم دسترسی به سرویس باشد. لطفاً بررسی کنید که آیا منطقه فعلی شما از این سرویس پشتیبانی میکند یا سعی کنید به منطقه دیگری تغییر دهید و دوباره تلاش کنید",
+ "ModelNotFound": "متأسفیم، نمیتوانیم مدل مربوطه را درخواست کنیم، ممکن است مدل وجود نداشته باشد یا به دلیل عدم دسترسی، لطفاً کلید API خود را تغییر دهید یا دسترسیها را تنظیم کنید و دوباره تلاش کنید",
+ "NoOpenAIAPIKey": "OpenAI API Key نادرست یا خالی است، لطفاً OpenAI API Key سفارشی اضافه کنید",
+ "OllamaBizError": "درخواست به سرویس Ollama با خطا مواجه شد، لطفاً بر اساس اطلاعات زیر بررسی کنید یا دوباره تلاش کنید",
+ "OllamaServiceUnavailable": "اتصال به سرویس Ollama ناموفق بود، لطفاً بررسی کنید که آیا Ollama به درستی کار میکند یا پیکربندیهای cross-origin Ollama به درستی تنظیم شده است",
+ "PermissionDenied": "متأسفیم، شما اجازه دسترسی به این سرویس را ندارید، لطفاً بررسی کنید که آیا کلید شما دسترسی لازم را دارد",
+ "PluginApiNotFound": "متأسفیم، API در فایل توصیف افزونه وجود ندارد، لطفاً روش درخواست خود را با API افزونه مطابقت دهید",
+ "PluginApiParamsError": "متأسفیم، اعتبارسنجی پارامترهای درخواست افزونه ناموفق بود، لطفاً پارامترها را با اطلاعات API مطابقت دهید",
+ "PluginFailToTransformArguments": "متأسفیم، تجزیه پارامترهای فراخوانی افزونه ناموفق بود، لطفاً دوباره پیام دستیار را تولید کنید یا از مدل AI قویتری برای فراخوانی ابزارها استفاده کنید",
+ "PluginGatewayError": "متأسفیم، دروازه افزونه با خطا مواجه شد، لطفاً پیکربندی دروازه افزونه را بررسی کنید",
+ "PluginManifestInvalid": "متأسفیم، اعتبارسنجی فایل توصیف افزونه ناموفق بود، لطفاً فرمت فایل توصیف را بررسی کنید",
+ "PluginManifestNotFound": "متأسفیم، سرور فایل توصیف افزونه (manifest.json) را پیدا نکرد، لطفاً آدرس فایل توصیف افزونه را بررسی کنید",
+ "PluginMarketIndexInvalid": "متأسفیم، اعتبارسنجی شاخص افزونه ناموفق بود، لطفاً فرمت فایل شاخص را بررسی کنید",
+ "PluginMarketIndexNotFound": "متأسفیم، سرور شاخص افزونه را پیدا نکرد، لطفاً آدرس شاخص را بررسی کنید",
+ "PluginMetaInvalid": "متأسفیم، اعتبارسنجی متادیتای افزونه ناموفق بود، لطفاً فرمت متادیتای افزونه را بررسی کنید",
+ "PluginMetaNotFound": "متأسفیم، افزونه در شاخص یافت نشد، لطفاً اطلاعات پیکربندی افزونه در شاخص را بررسی کنید",
+ "PluginOpenApiInitError": "متأسفیم، کلاینت OpenAPI با شکست مواجه شد، لطفاً پیکربندی OpenAPI را بررسی کنید",
+ "PluginServerError": "درخواست سرور افزونه با خطا مواجه شد، لطفاً بر اساس اطلاعات زیر فایل توصیف افزونه، پیکربندی افزونه یا پیادهسازی سرور را بررسی کنید",
+ "PluginSettingsInvalid": "این افزونه نیاز به پیکربندی صحیح دارد تا قابل استفاده باشد، لطفاً پیکربندی خود را بررسی کنید",
+ "ProviderBizError": "درخواست به سرویس {{provider}} با خطا مواجه شد، لطفاً بر اساس اطلاعات زیر بررسی کنید یا دوباره تلاش کنید",
+ "QuotaLimitReached": "متأسفیم، میزان استفاده از توکن یا تعداد درخواستهای شما به حد مجاز این کلید رسیده است، لطفاً سهمیه کلید را افزایش دهید یا بعداً دوباره تلاش کنید",
+ "StreamChunkError": "خطا در تجزیه بلوک پیام درخواست جریانی، لطفاً بررسی کنید که آیا API فعلی با استانداردها مطابقت دارد یا با ارائهدهنده API خود تماس بگیرید",
+ "SubscriptionKeyMismatch": "متأسفیم، به دلیل یک نقص موقتی در سیستم، مصرف فعلی اشتراک به طور موقت غیر فعال شده است. لطفاً بر روی دکمه زیر کلیک کنید تا اشتراک خود را بازیابی کنید، یا با ما از طریق ایمیل تماس بگیرید تا از ما پشتیبانی دریافت کنید.",
+ "SubscriptionPlanLimit": "نقاط اشتراک شما تمام شده است و نمیتوانید از این ویژگی استفاده کنید. لطفاً به یک طرح بالاتر ارتقا دهید یا پس از پیکربندی API مدل سفارشی، به استفاده ادامه دهید.",
+ "SystemTimeNotMatchError": "متأسفیم، زمان سیستم شما با سرور مطابقت ندارد، لطفاً زمان سیستم خود را بررسی کرده و دوباره تلاش کنید",
+ "UnknownChatFetchError": "متأسفیم، با خطای ناشناخته در درخواست مواجه شدیم، لطفاً بر اساس اطلاعات زیر بررسی کنید یا دوباره تلاش کنید"
+ },
+ "stt": {
+ "responseError": "درخواست سرویس ناموفق بود، لطفاً تنظیمات را بررسی کرده و دوباره تلاش کنید."
+ },
+ "tts": {
+ "responseError": "درخواست سرویس ناموفق بود، لطفاً تنظیمات را بررسی کرده و دوباره تلاش کنید."
+ },
+ "unlock": {
+ "addProxyUrl": "افزودن آدرس پروکسی OpenAI (اختیاری)",
+ "apiKey": {
+ "description": "API Key {{name}} خود را وارد کنید تا مکالمه را شروع کنید",
+ "title": "استفاده از API Key سفارشی {{name}}"
+ },
+ "closeMessage": "بستن پیام",
+ "confirm": "تأیید و تلاش مجدد",
+ "oauth": {
+ "description": "مدیر احراز هویت یکپارچه را فعال کرده است، برای ورود و باز کردن قفل برنامه روی دکمه زیر کلیک کنید",
+ "success": "ورود موفقیتآمیز",
+ "title": "ورود به حساب کاربری",
+ "welcome": "خوش آمدید!"
+ },
+ "password": {
+ "description": "مدیر رمزگذاری برنامه را فعال کرده است، پس از وارد کردن رمز عبور برنامه، میتوانید قفل برنامه را باز کنید. رمز عبور فقط یک بار نیاز به وارد کردن دارد",
+ "placeholder": "لطفاً رمز عبور را وارد کنید",
+ "title": "وارد کردن رمز عبور برای باز کردن قفل برنامه"
+ },
+ "tabs": {
+ "apiKey": "API Key سفارشی",
+ "password": "رمز عبور"
+ }
+ },
+ "upload": {
+ "desc": "جزئیات: {{detail}}",
+ "fileOnlySupportInServerMode": "حالت فعلی استقرار از آپلود فایلهای غیرتصویری پشتیبانی نمیکند. برای آپلود فایل با فرمت {{ext}}، لطفاً به حالت استقرار سرور تغییر دهید یا از سرویس {{cloud}} استفاده کنید.",
+ "networkError": "لطفاً مطمئن شوید که شبکه شما به درستی کار میکند و تنظیمات CORS سرویس ذخیرهسازی فایل صحیح است.",
+ "title": "آپلود فایل ناموفق بود، لطفاً اتصال شبکه خود را بررسی کنید یا بعداً دوباره تلاش کنید.",
+ "unknownError": "دلیل خطا: {{reason}}",
+ "uploadFailed": "آپلود فایل ناموفق بود"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/file.json b/DigitalHumanWeb/locales/fa-IR/file.json
new file mode 100644
index 0000000..2a62f07
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/file.json
@@ -0,0 +1,94 @@
+{
+ "desc": "مدیریت فایلها و مخزن دانش خود",
+ "detail": {
+ "basic": {
+ "createdAt": "زمان ایجاد",
+ "filename": "نام فایل",
+ "size": "اندازه فایل",
+ "title": "اطلاعات پایه",
+ "type": "فرمت",
+ "updatedAt": "زمان بهروزرسانی"
+ },
+ "data": {
+ "chunkCount": "تعداد بخشها",
+ "embedding": {
+ "default": "هنوز برداری نشده",
+ "error": "ناموفق",
+ "pending": "در انتظار شروع",
+ "processing": "در حال پردازش",
+ "success": "تکمیل شد"
+ },
+ "embeddingStatus": "برداریسازی"
+ }
+ },
+ "empty": "هیچ فایل/پوشهای بارگذاری نشده است",
+ "header": {
+ "actions": {
+ "newFolder": "ایجاد پوشه جدید",
+ "uploadFile": "بارگذاری فایل",
+ "uploadFolder": "بارگذاری پوشه"
+ },
+ "uploadButton": "بارگذاری"
+ },
+ "knowledgeBase": {
+ "list": {
+ "confirmRemoveKnowledgeBase": "این پایگاه دانش به زودی حذف خواهد شد، اما فایلهای آن حذف نخواهند شد و به بخش همه فایلها منتقل میشوند. پس از حذف پایگاه دانش، امکان بازیابی آن وجود نخواهد داشت، لطفاً با دقت عمل کنید.",
+ "empty": "برای شروع ایجاد پایگاه دانش، روی <1>+1> کلیک کنید."
+ },
+ "new": "ایجاد پایگاه دانش جدید",
+ "title": "پایگاه دانش"
+ },
+ "networkError": "دریافت مخزن دانش ناموفق بود، لطفاً پس از بررسی اتصال شبکه دوباره تلاش کنید.",
+ "notSupportGuide": {
+ "desc": "استقرار فعلی در حالت پایگاه داده کلاینت است و امکان استفاده از قابلیت مدیریت فایل وجود ندارد. لطفاً به <1>حالت استقرار پایگاه داده سرور1> تغییر دهید، یا مستقیماً از <3>LobeChat Cloud3> استفاده کنید.",
+ "features": {
+ "allKind": {
+ "desc": "پشتیبانی از انواع فایلهای رایج، از جمله فرمتهای متداول اسناد مانند Word، PPT، Excel، PDF، TXT و همچنین فایلهای کد مانند JS، Python و غیره",
+ "title": "تجزیه و تحلیل انواع فایلها"
+ },
+ "embeddings": {
+ "desc": "استفاده از مدلهای برداری با کارایی بالا برای برداریسازی بخشهای متنی و دستیابی به جستجوی معنایی در محتوای فایل",
+ "title": "برداریسازی معنایی"
+ },
+ "repos": {
+ "desc": "پشتیبانی از ایجاد مخازن دانش و امکان افزودن انواع مختلف فایلها برای ساخت دانش تخصصی خودتان",
+ "title": "مخزن دانش"
+ }
+ },
+ "title": "حالت استقرار فعلی از مدیریت فایل پشتیبانی نمیکند"
+ },
+ "preview": {
+ "downloadFile": "دانلود فایل",
+ "unsupportedFileAndContact": "فرمت این فایل در حال حاضر از پیشنمایش آنلاین پشتیبانی نمیکند. در صورت نیاز به پیشنمایش، لطفاً <1>به ما بازخورد دهید1>."
+ },
+ "searchFilePlaceholder": "جستجوی فایل",
+ "tab": {
+ "all": "همه فایلها",
+ "audios": "صداها",
+ "documents": "اسناد",
+ "images": "تصاویر",
+ "videos": "ویدیوها",
+ "websites": "وبسایتها"
+ },
+ "title": "فایل",
+ "uploadDock": {
+ "body": {
+ "collapse": "بستن",
+ "item": {
+ "done": "بارگذاری شد",
+ "error": "بارگذاری ناموفق بود، لطفاً دوباره تلاش کنید",
+ "pending": "آماده برای بارگذاری...",
+ "processing": "در حال پردازش فایل...",
+ "restTime": "زمان باقیمانده {{time}}"
+ }
+ },
+ "totalCount": "مجموعاً {{count}} مورد",
+ "uploadStatus": {
+ "error": "خطا در بارگذاری",
+ "pending": "در انتظار بارگذاری",
+ "processing": "در حال بارگذاری",
+ "success": "بارگذاری کامل شد",
+ "uploading": "در حال بارگذاری"
+ }
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/knowledgeBase.json b/DigitalHumanWeb/locales/fa-IR/knowledgeBase.json
new file mode 100644
index 0000000..02185ab
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/knowledgeBase.json
@@ -0,0 +1,32 @@
+{
+ "addToKnowledgeBase": {
+ "addSuccess": "فایل با موفقیت اضافه شد، <1>همین حالا مشاهده کنید1>",
+ "confirm": "اضافه کردن",
+ "id": {
+ "placeholder": "لطفاً پایگاه دانش مورد نظر را انتخاب کنید",
+ "required": "لطفاً پایگاه دانش را انتخاب کنید",
+ "title": "پایگاه دانش هدف"
+ },
+ "title": "اضافه کردن به پایگاه دانش",
+ "totalFiles": "{{count}} فایل انتخاب شده است"
+ },
+ "createNew": {
+ "confirm": "ایجاد جدید",
+ "description": {
+ "placeholder": "توضیحات دانشنامه (اختیاری)"
+ },
+ "formTitle": "اطلاعات پایه",
+ "name": {
+ "placeholder": "نام دانشنامه",
+ "required": "لطفاً نام دانشنامه را وارد کنید"
+ },
+ "title": "ایجاد دانشنامه جدید"
+ },
+ "tab": {
+ "evals": "ارزیابیها",
+ "files": "اسناد",
+ "settings": "تنظیمات",
+ "testing": "آزمون فراخوانی"
+ },
+ "title": "دانشنامه"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/market.json b/DigitalHumanWeb/locales/fa-IR/market.json
new file mode 100644
index 0000000..347bb1d
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/market.json
@@ -0,0 +1,32 @@
+{
+ "addAgent": "افزودن دستیار",
+ "addAgentAndConverse": "افزودن دستیار و گفتگو",
+ "addAgentSuccess": "افزودن با موفقیت انجام شد",
+ "guide": {
+ "func1": {
+ "desc1": "در پنجره گفتگو از طریق تنظیمات در گوشه بالا سمت راست به صفحه تنظیماتی که میخواهید دستیار را ارسال کنید، وارد شوید;",
+ "desc2": "روی دکمه ارسال به بازار دستیار در گوشه بالا سمت راست کلیک کنید.",
+ "tag": "روش اول",
+ "title": "ارسال از طریق {{appName}}"
+ },
+ "func2": {
+ "button": "رفتن به مخزن دستیار در Github",
+ "desc": "اگر میخواهید دستیار را به فهرست اضافه کنید، از agent-template.json یا agent-template-full.json استفاده کنید تا یک ورودی در دایرکتوری plugins ایجاد کنید، توضیح کوتاهی بنویسید و بهطور مناسب برچسبگذاری کنید، سپس یک درخواست کششی ایجاد کنید.",
+ "tag": "روش دوم",
+ "title": "ارسال از طریق Github"
+ }
+ },
+ "search": {
+ "placeholder": "جستجوی نام دستیار، توضیحات یا کلمات کلیدی..."
+ },
+ "sidebar": {
+ "comment": "بخش گفتگو",
+ "prompt": "کلمات پیشنهادی",
+ "title": "جزئیات دستیار"
+ },
+ "submitAgent": "ارسال دستیار",
+ "title": {
+ "allAgents": "همه دستیارها",
+ "recentSubmits": "آخرین ارسالها"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/metadata.json b/DigitalHumanWeb/locales/fa-IR/metadata.json
new file mode 100644
index 0000000..2a617ee
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/metadata.json
@@ -0,0 +1,39 @@
+{
+ "changelog": {
+ "description": "پیگیری مداوم ویژگیها و بهبودهای جدید {{appName}}",
+ "title": "گزارش تغییرات"
+ },
+ "chat": {
+ "description": "{{appName}} بهترین تجربه استفاده از ChatGPT، Claude، Gemini، OLLaMA WebUI را برای شما به ارمغان میآورد",
+ "title": "{{appName}}: ابزار بهرهوری شخصی AI، به خودتان یک مغز هوشمندتر بدهید"
+ },
+ "discover": {
+ "assistants": {
+ "description": "تولید محتوا، نوشتن متن، پرسش و پاسخ، تولید تصویر، تولید ویدئو، تولید صدا، عامل هوشمند، جریانهای کاری خودکار، دستیار هوشمند AI / GPTs / OLLaMA شخصیسازیشده خود را بسازید",
+ "title": "دستیارهای AI"
+ },
+ "description": "تولید محتوا، نوشتن متن، پرسش و پاسخ، تولید تصویر، تولید ویدئو، تولید صدا، عامل هوشمند، جریانهای کاری خودکار، برنامههای AI سفارشیسازیشده خود را بسازید",
+ "models": {
+ "description": "کاوش مدلهای اصلی AI مانند OpenAI / GPT / Claude 3 / Gemini / Ollama / Azure / DeepSeek",
+ "title": "مدلهای AI"
+ },
+ "plugins": {
+ "description": "جستجو، تولید نمودار، علمی، تولید تصویر، تولید ویدئو، تولید صدا، جریانهای کاری خودکار، قابلیتهای افزونههای متنوع را به دستیار خود اضافه کنید",
+ "title": "افزونههای AI"
+ },
+ "providers": {
+ "description": "کاوش ارائهدهندگان اصلی مدلها مانند OpenAI / Qwen / Ollama / Anthropic / DeepSeek / Google Gemini / OpenRouter",
+ "title": "ارائهدهندگان مدلهای AI"
+ },
+ "search": "جستجو",
+ "title": "کشف"
+ },
+ "plugins": {
+ "description": "جستجو، تولید نمودار، علمی، تولید تصویر، تولید ویدئو، تولید صدا، جریان کاری خودکار، سفارشیسازی قابلیتهای ToolCall اختصاصی ChatGPT / Claude",
+ "title": "بازار افزونهها"
+ },
+ "welcome": {
+ "description": "{{appName}} بهترین تجربه استفاده از ChatGPT، Claude، Gemini و OLLaMA WebUI را برای شما به ارمغان میآورد",
+ "title": "به {{appName}} خوش آمدید: ابزار بهرهوری شخصی AI، به خودتان یک مغز هوشمندتر هدیه دهید"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/migration.json b/DigitalHumanWeb/locales/fa-IR/migration.json
new file mode 100644
index 0000000..40498aa
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/migration.json
@@ -0,0 +1,45 @@
+{
+ "dbV1": {
+ "action": {
+ "clearDB": "پاک کردن دادههای محلی",
+ "downloadBackup": "دانلود پشتیبان دادهها",
+ "reUpgrade": "ارتقاء مجدد",
+ "start": "شروع به استفاده",
+ "upgrade": "ارتقاء با یک کلیک"
+ },
+ "clear": {
+ "confirm": "دادههای محلی به زودی پاک خواهند شد (تنظیمات کلی تحت تأثیر قرار نمیگیرند)، لطفاً تأیید کنید که پشتیبان دادهها را دانلود کردهاید."
+ },
+ "description": "در نسخه جدید، ذخیرهسازی دادههای {{appName}} به پیشرفت بزرگی دست یافته است. بنابراین ما باید دادههای نسخه قدیمی را ارتقاء دهیم تا تجربه بهتری برای شما فراهم کنیم.",
+ "features": {
+ "capability": {
+ "desc": "بر اساس فناوری IndexedDB، به اندازه کافی بزرگ است تا پیامهای مکالمه شما را برای تمام عمر ذخیره کند",
+ "title": "ظرفیت بالا"
+ },
+ "performance": {
+ "desc": "میلیونها پیام به صورت خودکار ایندکس میشوند و جستجوها در کسری از ثانیه پاسخ داده میشوند",
+ "title": "عملکرد بالا"
+ },
+ "use": {
+ "desc": "پشتیبانی از جستجو در عنوان، توضیحات، برچسبها، محتوای پیام و حتی متنهای ترجمه شده، کارایی جستجوی روزانه به طور قابل توجهی افزایش یافته است",
+ "title": "استفاده آسانتر"
+ }
+ },
+ "title": "تحول دادههای {{appName}}",
+ "upgrade": {
+ "error": {
+ "subTitle": "بسیار متأسفیم، در فرآیند ارتقاء پایگاه داده خطایی رخ داده است. لطفاً راهحلهای زیر را امتحان کنید: الف. پس از پاک کردن دادههای محلی، دادههای پشتیبان را دوباره وارد کنید؛ ب. روی دکمه «ارتقاء مجدد» کلیک کنید.
اگر همچنان خطا وجود دارد، لطفاً <1>مشکل را گزارش دهید1>، ما در اسرع وقت به شما کمک خواهیم کرد.",
+ "title": "ارتقاء پایگاه داده ناموفق بود"
+ },
+ "success": {
+ "subTitle": "پایگاه داده {{appName}} به آخرین نسخه ارتقاء یافته است، بلافاصله شروع به تجربه کنید",
+ "title": "ارتقاء پایگاه داده موفقیتآمیز بود"
+ }
+ },
+ "upgradeTip": "ارتقاء حدود ۱۰ تا ۲۰ ثانیه طول میکشد، لطفاً در طول فرآیند ارتقاء {{appName}} را نبندید."
+ },
+ "migrateError": {
+ "missVersion": "دادههای وارد شده فاقد شماره نسخه است، لطفاً فایل را بررسی کرده و دوباره تلاش کنید.",
+ "noMigration": "طرح مهاجرت مربوط به نسخه فعلی یافت نشد، لطفاً شماره نسخه را بررسی کرده و دوباره تلاش کنید. اگر مشکل همچنان ادامه داشت، لطفاً بازخورد مشکل را ارسال کنید."
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/modelProvider.json b/DigitalHumanWeb/locales/fa-IR/modelProvider.json
new file mode 100644
index 0000000..af271a5
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/modelProvider.json
@@ -0,0 +1,341 @@
+{
+ "azure": {
+ "azureApiVersion": {
+ "desc": "نسخه API Azure، با فرمت YYYY-MM-DD، برای مشاهده [آخرین نسخه](https://learn.microsoft.com/fa-ir/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "دریافت لیست",
+ "title": "نسخه API Azure"
+ },
+ "empty": "لطفاً شناسه مدل را وارد کنید تا اولین مدل را اضافه کنید",
+ "endpoint": {
+ "desc": "هنگام بررسی منابع از پورتال Azure، این مقدار را میتوانید در بخش «کلیدها و نقاط پایانی» پیدا کنید",
+ "placeholder": "https://docs-test-001.openai.azure.com",
+ "title": "آدرس API Azure"
+ },
+ "modelListPlaceholder": "لطفاً مدل OpenAI مستقر شده خود را انتخاب یا اضافه کنید",
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "هنگام بررسی منابع از پورتال Azure، این مقدار را میتوانید در بخش «کلیدها و نقاط پایانی» پیدا کنید. میتوانید از KEY1 یا KEY2 استفاده کنید",
+ "placeholder": "کلید API Azure",
+ "title": "کلید API"
+ }
+ },
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "نسخه API آژور، با فرمت YYYY-MM-DD، برای مشاهده [آخرین نسخه](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "دریافت لیست",
+ "title": "نسخه API آژور"
+ },
+ "endpoint": {
+ "desc": "نقطه پایانی استنتاج مدل آژور AI را از نمای کلی پروژه آژور AI پیدا کنید",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "نقطه پایانی آژور AI"
+ },
+ "title": "آژور OpenAI",
+ "token": {
+ "desc": "کلید API را از نمای کلی پروژه آژور AI پیدا کنید",
+ "placeholder": "کلید آژور",
+ "title": "کلید"
+ }
+ },
+ "bedrock": {
+ "accessKeyId": {
+ "desc": "AWS Access Key Id را وارد کنید",
+ "placeholder": "AWS Access Key Id",
+ "title": "AWS Access Key Id"
+ },
+ "checker": {
+ "desc": "بررسی کنید که آیا AccessKeyId / SecretAccessKey به درستی وارد شده است"
+ },
+ "region": {
+ "desc": "AWS Region را وارد کنید",
+ "placeholder": "AWS Region",
+ "title": "AWS Region"
+ },
+ "secretAccessKey": {
+ "desc": "AWS Secret Access Key را وارد کنید",
+ "placeholder": "AWS Secret Access Key",
+ "title": "AWS Secret Access Key"
+ },
+ "sessionToken": {
+ "desc": "اگر از AWS SSO/STS استفاده میکنید، لطفاً AWS Session Token خود را وارد کنید",
+ "placeholder": "AWS Session Token",
+ "title": "AWS Session Token (اختیاری)"
+ },
+ "title": "Bedrock",
+ "unlock": {
+ "customRegion": "منطقه خدمات سفارشی",
+ "customSessionToken": "توکن نشست سفارشی",
+ "description": "برای شروع جلسه، AWS AccessKeyId / SecretAccessKey خود را وارد کنید. برنامه تنظیمات احراز هویت شما را ذخیره نخواهد کرد",
+ "title": "استفاده از اطلاعات احراز هویت سفارشی Bedrock"
+ }
+ },
+ "cloudflare": {
+ "apiKey": {
+ "desc": "لطفاً کلید API Cloudflare را وارد کنید",
+ "placeholder": "کلید API Cloudflare",
+ "title": "کلید API Cloudflare"
+ },
+ "baseURLOrAccountID": {
+ "desc": "شناسه حساب Cloudflare یا آدرس API سفارشی را وارد کنید",
+ "placeholder": "شناسه حساب Cloudflare / آدرس API سفارشی",
+ "title": "شناسه حساب Cloudflare / آدرس API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "لطفاً کلید API خود را وارد کنید",
+ "title": "کلید API"
+ },
+ "basicTitle": "اطلاعات پایه",
+ "configTitle": "اطلاعات پیکربندی",
+ "confirm": "ایجاد جدید",
+ "createSuccess": "ایجاد با موفقیت انجام شد",
+ "description": {
+ "placeholder": "توضیحات ارائهدهنده (اختیاری)",
+ "title": "توضیحات ارائهدهنده"
+ },
+ "id": {
+ "desc": "به عنوان شناسه منحصر به فرد ارائهدهنده خدمات، پس از ایجاد قابل ویرایش نخواهد بود",
+ "format": "فقط میتواند شامل اعداد، حروف کوچک، خط تیره (-) و زیرخط (_) باشد",
+ "placeholder": "توصیه میشود تماماً با حروف کوچک باشد، مانند openai، پس از ایجاد قابل ویرایش نخواهد بود",
+ "required": "لطفاً شناسه ارائهدهنده را وارد کنید",
+ "title": "شناسه ارائهدهنده"
+ },
+ "logo": {
+ "required": "لطفاً لوگوی صحیح ارائهدهنده را بارگذاری کنید",
+ "title": "لوگوی ارائهدهنده"
+ },
+ "name": {
+ "placeholder": "لطفاً نام نمایشی ارائهدهنده را وارد کنید",
+ "required": "لطفاً نام ارائهدهنده را وارد کنید",
+ "title": "نام ارائهدهنده"
+ },
+ "proxyUrl": {
+ "required": "لطفاً آدرس پروکسی را وارد کنید",
+ "title": "آدرس پروکسی"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "لطفاً نوع SDK را انتخاب کنید",
+ "title": "فرمت درخواست"
+ },
+ "title": "ایجاد ارائهدهنده AI سفارشی"
+ },
+ "github": {
+ "personalAccessToken": {
+ "desc": "توکن دسترسی شخصی Github خود را وارد کنید، برای ایجاد [اینجا](https://github.com/settings/tokens) کلیک کنید",
+ "placeholder": "ghp_xxxxxx",
+ "title": "توکن دسترسی شخصی Github"
+ }
+ },
+ "huggingface": {
+ "accessToken": {
+ "desc": "توکن HuggingFace خود را وارد کنید، برای ایجاد [اینجا](https://huggingface.co/settings/tokens) کلیک کنید",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "توکن HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "سرویسدهنده غیرفعال",
+ "enabled": "سرویسدهنده فعال"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "اضافه کردن ارائهدهنده سفارشی",
+ "all": "همه",
+ "list": {
+ "disabled": "غیرفعال",
+ "enabled": "فعال"
+ },
+ "notFound": "نتیجهای برای جستجو پیدا نشد",
+ "searchProviders": "جستجوی ارائهدهندگان...",
+ "sort": "مرتبسازی سفارشی"
+ },
+ "ollama": {
+ "checker": {
+ "desc": "آزمایش کنید که آیا آدرس پروکسی به درستی وارد شده است",
+ "title": "بررسی اتصال"
+ },
+ "customModelName": {
+ "desc": "مدلهای سفارشی را اضافه کنید، چندین مدل را با کاما (,) جدا کنید",
+ "placeholder": "vicuna,llava,codellama,llama2:13b-text",
+ "title": "نام مدل سفارشی"
+ },
+ "download": {
+ "desc": "Ollama در حال دانلود این مدل است، لطفاً تا حد امکان این صفحه را نبندید. در صورت دانلود مجدد، از نقطه قطع شده ادامه خواهد یافت",
+ "remainingTime": "زمان باقیمانده",
+ "speed": "سرعت دانلود",
+ "title": "در حال دانلود مدل {{model}} "
+ },
+ "endpoint": {
+ "desc": "باید شامل http(s):// باشد، اگر محلی به طور اضافی مشخص نشده باشد میتوان خالی گذاشت",
+ "title": "آدرس سرویس Ollama"
+ },
+ "title": "Ollama",
+ "unlock": {
+ "cancel": "لغو دانلود",
+ "confirm": "دانلود",
+ "description": "برچسب مدل Ollama خود را وارد کنید تا بتوانید به مکالمه ادامه دهید",
+ "downloaded": "{{completed}} / {{total}}",
+ "starting": "شروع دانلود...",
+ "title": "دانلود مدل مشخص شده Ollama"
+ }
+ },
+ "providerModels": {
+ "config": {
+ "aesGcm": "کلید شما و آدرس پروکسی و غیره با استفاده از <1>AES-GCM1> رمزگذاری خواهد شد",
+ "apiKey": {
+ "desc": "لطفاً کلید API {{name}} خود را وارد کنید",
+ "placeholder": "{{name}} کلید API",
+ "title": "کلید API"
+ },
+ "baseURL": {
+ "desc": "باید شامل http(s):// باشد",
+ "invalid": "لطفاً یک URL معتبر وارد کنید",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "آدرس پروکسی API"
+ },
+ "checker": {
+ "button": "بررسی",
+ "desc": "آزمون کلید API و آدرس پروکسی برای صحت",
+ "pass": "بررسی موفقیتآمیز",
+ "title": "بررسی اتصال"
+ },
+ "fetchOnClient": {
+ "desc": "مدل درخواست کلاینت به طور مستقیم از مرورگر درخواست جلسه را آغاز میکند و میتواند سرعت پاسخ را افزایش دهد",
+ "title": "استفاده از مدل درخواست کلاینت"
+ },
+ "helpDoc": "راهنمای پیکربندی",
+ "waitingForMore": "مدلهای بیشتری در حال <1>برنامهریزی برای اتصال1> هستند، لطفاً منتظر بمانید"
+ },
+ "createNew": {
+ "title": "ایجاد مدل AI سفارشی"
+ },
+ "item": {
+ "config": "پیکربندی مدل",
+ "customModelCards": {
+ "addNew": "ایجاد و افزودن مدل {{id}}",
+ "confirmDelete": "در حال حذف این مدل سفارشی هستید، پس از حذف قابل بازیابی نخواهد بود، لطفاً با احتیاط عمل کنید."
+ },
+ "delete": {
+ "confirm": "آیا مطمئن هستید که میخواهید مدل {{displayName}} را حذف کنید؟",
+ "success": "حذف با موفقیت انجام شد",
+ "title": "حذف مدل"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "فیلدی که در Azure OpenAI درخواست واقعی میشود",
+ "placeholder": "لطفاً نام استقرار مدل در Azure را وارد کنید",
+ "title": "نام استقرار مدل"
+ },
+ "deployName": {
+ "extra": "این فیلد به عنوان شناسه مدل هنگام ارسال درخواست استفاده میشود",
+ "placeholder": "لطفاً نام یا شناسه واقعی مدل را وارد کنید",
+ "title": "نام مدل برای استقرار"
+ },
+ "displayName": {
+ "placeholder": "لطفاً نام نمایشی مدل را وارد کنید، مانند ChatGPT، GPT-4 و غیره",
+ "title": "نام نمایشی مدل"
+ },
+ "files": {
+ "extra": "پیادهسازی بارگذاری فایل فعلی تنها یک راهحل Hack است و فقط برای آزمایش شخصی محدود است. لطفاً منتظر پیادهسازی کامل قابلیت بارگذاری فایل باشید",
+ "title": "پشتیبانی از بارگذاری فایل"
+ },
+ "functionCall": {
+ "extra": "این پیکربندی تنها قابلیت استفاده از ابزارها را برای مدل فعال میکند و به این ترتیب میتوان افزونههای نوع ابزار را به مدل اضافه کرد. اما اینکه آیا واقعاً از ابزارها استفاده میشود به خود مدل بستگی دارد، لطفاً قابلیت استفاده را خودتان آزمایش کنید",
+ "title": "پشتیبانی از استفاده از ابزار"
+ },
+ "id": {
+ "extra": "پس از ایجاد قابل ویرایش نیست و در هنگام فراخوانی AI به عنوان شناسه مدل استفاده خواهد شد",
+ "placeholder": "لطفاً شناسه مدل را وارد کنید، مانند gpt-4o یا claude-3.5-sonnet",
+ "title": "شناسه مدل"
+ },
+ "modalTitle": "پیکربندی مدل سفارشی",
+ "reasoning": {
+ "extra": "این تنظیم فقط قابلیت تفکر عمیق مدل را فعال میکند و تأثیر دقیق آن کاملاً به خود مدل بستگی دارد، لطفاً خودتان آزمایش کنید که آیا این مدل قابلیت تفکر عمیق قابل استفاده را دارد یا خیر",
+ "title": "پشتیبانی از تفکر عمیق"
+ },
+ "tokens": {
+ "extra": "حداکثر تعداد توکنهای پشتیبانی شده توسط مدل را تنظیم کنید",
+ "title": "حداکثر پنجره زمینه",
+ "unlimited": "بدون محدودیت"
+ },
+ "vision": {
+ "extra": "این پیکربندی تنها قابلیت بارگذاری تصویر در برنامه را فعال میکند، اینکه آیا شناسایی پشتیبانی میشود به خود مدل بستگی دارد، لطفاً قابلیت استفاده از شناسایی بصری این مدل را آزمایش کنید",
+ "title": "پشتیبانی از شناسایی بصری"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/تصویر",
+ "inputCharts": "${{amount}}/M کاراکتر",
+ "inputMinutes": "${{amount}}/دقیقه",
+ "inputTokens": "ورودی ${{amount}}/M",
+ "outputTokens": "خروجی ${{amount}}/M"
+ },
+ "releasedAt": "منتشر شده در {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "مدل جدید اضافه کنید",
+ "disabled": "غیرفعال",
+ "disabledActions": {
+ "showMore": "نمایش همه"
+ },
+ "empty": {
+ "desc": "لطفاً یک مدل سفارشی ایجاد کنید یا پس از بارگذاری مدلها، شروع به استفاده کنید",
+ "title": "مدل قابل استفادهای وجود ندارد"
+ },
+ "enabled": "فعال",
+ "enabledActions": {
+ "disableAll": "غیرفعال کردن همه",
+ "enableAll": "فعال کردن همه",
+ "sort": "مرتبسازی مدلهای سفارشی"
+ },
+ "enabledEmpty": "مدل فعال وجود ندارد، لطفاً از لیست زیر مدل مورد نظر خود را فعال کنید~",
+ "fetcher": {
+ "clear": "پاک کردن مدلهای دریافت شده",
+ "fetch": "دریافت لیست مدلها",
+ "fetching": "در حال دریافت لیست مدلها...",
+ "latestTime": "آخرین زمان بهروزرسانی: {{time}}",
+ "noLatestTime": "لیست هنوز دریافت نشده است"
+ },
+ "resetAll": {
+ "conform": "آیا مطمئن هستید که میخواهید تمام تغییرات مدل فعلی را بازنشانی کنید؟ پس از بازنشانی، لیست مدلهای فعلی به حالت پیشفرض باز خواهد گشت",
+ "success": "بازنشانی با موفقیت انجام شد",
+ "title": "بازنشانی تمام تغییرات"
+ },
+ "search": "جستجوی مدل...",
+ "searchResult": "{{count}} مدل پیدا شد",
+ "title": "لیست مدلها",
+ "total": "در مجموع {{count}} مدل در دسترس است"
+ },
+ "searchNotFound": "نتیجهای برای جستجو پیدا نشد"
+ },
+ "sortModal": {
+ "success": "بهروزرسانی مرتبسازی با موفقیت انجام شد",
+ "title": "مرتبسازی سفارشی",
+ "update": "بهروزرسانی"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "در حال حذف این ارائهدهنده AI هستید، پس از حذف قابل بازیابی نخواهد بود، آیا مطمئن هستید که میخواهید حذف کنید؟",
+ "deleteSuccess": "حذف با موفقیت انجام شد",
+ "tooltip": "بهروزرسانی پیکربندی پایه ارائهدهنده",
+ "updateSuccess": "بهروزرسانی با موفقیت انجام شد"
+ },
+ "updateCustomAiProvider": {
+ "title": "بهروزرسانی تنظیمات ارائهدهنده AI سفارشی"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "کلیدهای Vertex AI خود را وارد کنید",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "کلیدهای Vertex AI"
+ }
+ },
+ "zeroone": {
+ "title": "01.AI صفر و یک همه چیز"
+ },
+ "zhipu": {
+ "title": "ژھیپو"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/models.json b/DigitalHumanWeb/locales/fa-IR/models.json
new file mode 100644
index 0000000..486bd79
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/models.json
@@ -0,0 +1,1796 @@
+{
+ "01-ai/Yi-1.5-34B-Chat-16K": {
+ "description": "Yi-1.5 34B، با استفاده از نمونههای آموزشی غنی، عملکرد برتری در کاربردهای صنعتی ارائه میدهد."
+ },
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat یک واریانت از سری Yi-1.5 است که متعلق به مدلهای گفتگویی متن باز است. Yi-1.5 نسخه بهروز شده Yi است که بر روی 500B توکن با کیفیت بالا به طور مداوم پیشآموزش دیده و بر روی 3M نمونههای متنوع تنظیم دقیق شده است. در مقایسه با Yi، Yi-1.5 در تواناییهای کدنویسی، ریاضی، استدلال و پیروی از دستورات عملکرد بهتری دارد و در عین حال تواناییهای عالی در درک زبان، استدلال عمومی و درک خواندن را حفظ کرده است. این مدل دارای نسخههای طول زمینه 4K، 16K و 32K است و مجموع پیشآموزش به 3.6T توکن میرسد."
+ },
+ "01-ai/Yi-1.5-9B-Chat-16K": {
+ "description": "Yi-1.5 9B از 16K توکن پشتیبانی میکند و توانایی تولید زبان بهصورت کارآمد و روان را ارائه میدهد."
+ },
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Everything، جدیدترین مدل متن باز تنظیم شده با 34 میلیارد پارامتر، که تنظیمات آن از چندین سناریوی گفتگویی پشتیبانی میکند و دادههای آموزشی با کیفیت بالا را برای همراستایی با ترجیحات انسانی فراهم میکند."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Everything، جدیدترین مدل متن باز تنظیم شده با 9 میلیارد پارامتر، که تنظیمات آن از چندین سناریوی گفتگویی پشتیبانی میکند و دادههای آموزشی با کیفیت بالا را برای همراستایی با ترجیحات انسانی فراهم میکند."
+ },
+ "360gpt-pro": {
+ "description": "360GPT Pro به عنوان یکی از اعضای مهم سری مدلهای 360 AI، با توانایی پردازش متون بهصورت کارآمد، نیازهای متنوع در زمینههای مختلف کاربردهای زبان طبیعی را برآورده میکند و از قابلیتهایی مانند درک متون طولانی و مکالمات چندمرحلهای پشتیبانی میکند."
+ },
+ "360gpt-turbo": {
+ "description": "360GPT Turbo تواناییهای محاسباتی و مکالمهای قدرتمندی ارائه میدهد و دارای کارایی بالایی در درک و تولید معنا است. این یک راهحل ایدهآل برای دستیار هوشمند برای شرکتها و توسعهدهندگان است."
+ },
+ "360gpt-turbo-responsibility-8k": {
+ "description": "360GPT Turbo Responsibility 8K بر امنیت معنایی و مسئولیتپذیری تأکید دارد و بهطور ویژه برای سناریوهایی طراحی شده است که نیاز بالایی به امنیت محتوا دارند، تا دقت و پایداری تجربه کاربری را تضمین کند."
+ },
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 از جستجوی درخت برای ساخت زنجیرههای تفکر استفاده میکند و مکانیزم بازتاب را معرفی کرده است و با استفاده از یادگیری تقویتی آموزش دیده است، این مدل توانایی خودبازتابی و اصلاح خطا را دارد."
+ },
+ "360gpt2-pro": {
+ "description": "360GPT2 Pro مدل پیشرفته پردازش زبان طبیعی است که توسط شرکت 360 ارائه شده است. این مدل دارای تواناییهای برجستهای در تولید و درک متن است و به ویژه در زمینه تولید و خلاقیت عملکرد فوقالعادهای دارد. همچنین قادر به انجام وظایف پیچیده تبدیل زبان و ایفای نقش میباشد."
+ },
+ "360zhinao2-o1": {
+ "description": "مدل 360zhinao2-o1 با استفاده از جستجوی درختی زنجیره تفکر را ایجاد کرده و مکانیزم بازتاب را معرفی کرده است و با استفاده از یادگیری تقویتی آموزش دیده است، این مدل توانایی خودبازتابی و اصلاح خطا را دارد."
+ },
+ "4.0Ultra": {
+ "description": "Spark Ultra قدرتمندترین نسخه از سری مدلهای بزرگ Spark است که با ارتقاء مسیر جستجوی متصل به شبکه، توانایی درک و خلاصهسازی محتوای متنی را بهبود میبخشد. این یک راهحل جامع برای افزایش بهرهوری در محیط کار و پاسخگویی دقیق به نیازها است و به عنوان یک محصول هوشمند پیشرو در صنعت شناخته میشود."
+ },
+ "Baichuan2-Turbo": {
+ "description": "با استفاده از فناوری تقویت جستجو، مدل بزرگ را به دانش حوزهای و دانش کل وب متصل میکند. از آپلود انواع اسناد مانند PDF، Word و همچنین وارد کردن آدرسهای وب پشتیبانی میکند. اطلاعات بهموقع و جامع دریافت میشود و نتایج خروجی دقیق و حرفهای هستند."
+ },
+ "Baichuan3-Turbo": {
+ "description": "بهینهسازی شده برای سناریوهای پرتکرار سازمانی، با بهبود قابل توجه و نسبت عملکرد به هزینه بالا. در مقایسه با مدل Baichuan2، تولید محتوا ۲۰٪ بهبود یافته، پاسخ به سوالات ۱۷٪ بهتر شده و توانایی نقشآفرینی ۴۰٪ افزایش یافته است. عملکرد کلی بهتر از GPT3.5 است."
+ },
+ "Baichuan3-Turbo-128k": {
+ "description": "دارای پنجره متنی فوقالعاده طولانی ۱۲۸K، بهینهسازی شده برای سناریوهای پرتکرار سازمانی، با بهبود قابل توجه در عملکرد و مقرون به صرفه بودن. در مقایسه با مدل Baichuan2، ۲۰٪ بهبود در تولید محتوا، ۱۷٪ بهبود در پرسش و پاسخ دانش، و ۴۰٪ بهبود در توانایی نقشآفرینی. عملکرد کلی بهتر از GPT3.5 است."
+ },
+ "Baichuan4": {
+ "description": "این مدل از نظر توانایی در داخل کشور رتبه اول را دارد و در وظایف چینی مانند دانشنامه، متون طولانی و تولید محتوا از مدلهای اصلی خارجی پیشی میگیرد. همچنین دارای توانایی چندوجهی پیشرو در صنعت است و در چندین معیار ارزیابی معتبر عملکرد برجستهای دارد."
+ },
+ "Baichuan4-Air": {
+ "description": "توانایی مدل در کشور اول است و در وظایف چینی مانند دانشنامه، متنهای طولانی و تولید خلاقانه از مدلهای اصلی خارجی پیشی میگیرد. همچنین دارای قابلیتهای چندرسانهای پیشرفته در صنعت است و در چندین معیار ارزیابی معتبر عملکرد عالی دارد."
+ },
+ "Baichuan4-Turbo": {
+ "description": "توانایی مدل در کشور اول است و در وظایف چینی مانند دانشنامه، متنهای طولانی و تولید خلاقانه از مدلهای اصلی خارجی پیشی میگیرد. همچنین دارای قابلیتهای چندرسانهای پیشرفته در صنعت است و در چندین معیار ارزیابی معتبر عملکرد عالی دارد."
+ },
+ "DeepSeek-R1": {
+ "description": "مدل LLM پیشرفته و کارآمد که در استدلال، ریاضیات و برنامهنویسی تخصص دارد."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 - مدل بزرگتر و هوشمندتر در مجموعه DeepSeek - به ساختار لاما 70B تقطیر شده است. بر اساس آزمونهای معیار و ارزیابیهای انسانی، این مدل نسبت به لاما 70B اصلی هوشمندتر است و به ویژه در وظایفی که نیاز به دقت ریاضی و واقعیات دارند، عملکرد عالی دارد."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "مدل تقطیر DeepSeek-R1 مبتنی بر Qwen2.5-Math-1.5B است که با استفاده از یادگیری تقویتی و دادههای شروع سرد عملکرد استدلال را بهینهسازی کرده و مدلهای متنباز را به روز کرده است."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "مدل تقطیر DeepSeek-R1 مبتنی بر Qwen2.5-14B است که با استفاده از یادگیری تقویتی و دادههای شروع سرد عملکرد استدلال را بهینهسازی کرده و مدلهای متنباز را به روز کرده است."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "سری DeepSeek-R1 با استفاده از یادگیری تقویتی و دادههای شروع سرد عملکرد استدلال را بهینهسازی کرده و مدلهای متنباز را به روز کرده و از سطح OpenAI-o1-mini فراتر رفته است."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "مدل تقطیر DeepSeek-R1 مبتنی بر Qwen2.5-Math-7B است که با استفاده از یادگیری تقویتی و دادههای شروع سرد عملکرد استدلال را بهینهسازی کرده و مدلهای متنباز را به روز کرده است."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "مدل بزرگ چندرسانهای ارتقاء یافته Doubao-1.5-vision-pro، از شناسایی تصاویر با هر وضوح و نسبت ابعاد بسیار طولانی پشتیبانی میکند و تواناییهای استدلال بصری، شناسایی اسناد، درک اطلاعات جزئی و پیروی از دستورات را تقویت میکند."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite دارای سرعت پاسخدهی بسیار بالا و قیمت مناسبتر است و برای سناریوهای مختلف مشتریان گزینههای منعطفتری ارائه میدهد. این مدل از استنتاج و تنظیم 128k پنجره متنی پشتیبانی میکند."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite دارای سرعت پاسخدهی بسیار بالا و قیمت مناسبتر است و برای سناریوهای مختلف مشتریان گزینههای منعطفتری ارائه میدهد. این مدل از استنتاج و تنظیم 32k پنجره متنی پشتیبانی میکند."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite دارای سرعت پاسخدهی بسیار بالا و قیمت مناسبتر است و برای سناریوهای مختلف مشتریان گزینههای منعطفتری ارائه میدهد. این مدل از استنتاج و تنظیم 4k پنجره متنی پشتیبانی میکند."
+ },
+ "Doubao-pro-128k": {
+ "description": "بهترین مدل اصلی با عملکرد بسیار خوب برای پردازش وظایف پیچیده است و در سناریوهایی مانند پرسش و پاسخ مدل مرجع، خلاصهنویسی، خلاقیت، طبقهبندی متن و بازی نقش عملکرد خوبی دارد. این مدل از استنتاج و تنظیم 128k پنجره متنی پشتیبانی میکند."
+ },
+ "Doubao-pro-256k": {
+ "description": "بهترین مدل اصلی از نظر عملکرد، مناسب برای پردازش وظایف پیچیده، در زمینههای پرسش و پاسخ مرجع، خلاصهسازی، خلاقیت، طبقهبندی متن و نقشآفرینی عملکرد خوبی دارد. از استدلال و تنظیم دقیق با پنجره زمینه 256k پشتیبانی میکند."
+ },
+ "Doubao-pro-32k": {
+ "description": "بهترین مدل اصلی با عملکرد بسیار خوب برای پردازش وظایف پیچیده است و در سناریوهایی مانند پرسش و پاسخ مدل مرجع، خلاصهنویسی، خلاقیت، طبقهبندی متن و بازی نقش عملکرد خوبی دارد. این مدل از استنتاج و تنظیم 32k پنجره متنی پشتیبانی میکند."
+ },
+ "Doubao-pro-4k": {
+ "description": "بهترین مدل اصلی با عملکرد بسیار خوب برای پردازش وظایف پیچیده است و در سناریوهایی مانند پرسش و پاسخ مدل مرجع، خلاصهنویسی، خلاقیت، طبقهبندی متن و بازی نقش عملکرد خوبی دارد. این مدل از استنتاج و تنظیم 4k پنجره متنی پشتیبانی میکند."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "مدل Doubao-vision یک مدل بزرگ چندرسانهای است که توسط Doubao ارائه شده و دارای تواناییهای قوی در درک و استدلال تصاویر و همچنین درک دقیق دستورات است. این مدل در استخراج اطلاعات متنی از تصاویر و وظایف استدلال مبتنی بر تصویر عملکرد قوی از خود نشان داده و میتواند در وظایف پیچیدهتر و گستردهتر پرسش و پاسخ بصری به کار رود."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "مدل Doubao-vision یک مدل بزرگ چندرسانهای است که توسط Doubao ارائه شده و دارای تواناییهای قوی در درک و استدلال تصاویر و همچنین درک دقیق دستورات است. این مدل در استخراج اطلاعات متنی از تصاویر و وظایف استدلال مبتنی بر تصویر عملکرد قوی از خود نشان داده و میتواند در وظایف پیچیدهتر و گستردهتر پرسش و پاسخ بصری به کار رود."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "مدل زبان بزرگ پرچمدار توسعهیافته توسط بایدو، که حجم عظیمی از متون چینی و انگلیسی را پوشش میدهد و دارای تواناییهای عمومی قدرتمندی است. این مدل میتواند نیازهای اکثر سناریوهای پرسش و پاسخ، تولید محتوا و استفاده از افزونهها را برآورده کند؛ همچنین از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا بهروز بودن اطلاعات پرسش و پاسخ را تضمین کند."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "مدل زبان بزرگ پرچمدار توسعهیافته توسط بایدو، که حجم عظیمی از متون چینی و انگلیسی را پوشش میدهد و دارای تواناییهای عمومی قدرتمندی است. این مدل میتواند نیازهای اکثر سناریوهای پرسش و پاسخ، تولید محتوا و استفاده از افزونهها را برآورده کند؛ همچنین از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا بهروز بودن اطلاعات پرسش و پاسخ را تضمین نماید."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "مدل زبان بزرگ پرچمدار توسعهیافته توسط بایدو، که حجم عظیمی از متون چینی و انگلیسی را پوشش میدهد و دارای تواناییهای عمومی قدرتمندی است. این مدل میتواند نیازهای اکثر سناریوهای پرسش و پاسخ، تولید محتوا و استفاده از افزونهها را برآورده کند؛ همچنین از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا بهروز بودن اطلاعات پرسش و پاسخ را تضمین کند."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "مدل زبان بزرگ مقیاس پرچمدار توسعهیافته توسط بایدو، که نسبت به ERNIE 3.5 ارتقاء کامل در تواناییهای مدل را به ارمغان آورده است و برای وظایف پیچیده در حوزههای مختلف مناسب است؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند و بهروزرسانی اطلاعات پرسش و پاسخ را تضمین مینماید."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "مدل زبان بزرگ مقیاس پرچمدار توسعهیافته توسط بایدو، در مقایسه با ERNIE 3.5 ارتقاء کامل تواناییهای مدل را به ارمغان آورده و برای وظایف پیچیده در حوزههای مختلف مناسب است؛ از افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ بهروز بماند."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "مدل زبان بزرگ و پیشرفتهای که توسط بایدو توسعه یافته است، با عملکرد برجسته در زمینههای مختلف و مناسب برای وظایف پیچیده؛ از افزونه جستجوی بایدو بهطور خودکار پشتیبانی میکند تا اطلاعات بهروز را در پاسخها تضمین کند. در مقایسه با ERNIE 4.0، عملکرد بهتری دارد."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "مدل زبان بزرگ و پرچمدار با مقیاس فوقالعاده که توسط بایدو توسعه یافته است، با عملکرد برجسته در زمینههای مختلف و مناسب برای وظایف پیچیده؛ پشتیبانی از اتصال خودکار به افزونه جستجوی بایدو برای اطمینان از بهروز بودن اطلاعات پرسش و پاسخ. در مقایسه با ERNIE 4.0، عملکرد بهتری دارد."
+ },
+ "ERNIE-Character-8K": {
+ "description": "مدل زبان بزرگ عمودی توسعهیافته توسط بایدو، مناسب برای صحنههای کاربردی مانند NPCهای بازی، مکالمات پشتیبانی مشتری، و نقشآفرینی در مکالمات. سبک شخصیتها برجستهتر و یکپارچهتر است، توانایی پیروی از دستورات قویتر و عملکرد استدلالی بهینهتر است."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "مدل زبان بزرگ سبکوزن توسعهیافته توسط بایدو، که تعادل بین عملکرد مدل عالی و کارایی استنتاج را حفظ میکند. عملکرد آن بهتر از ERNIE Lite است و برای استفاده در کارتهای شتابدهنده AI با قدرت محاسباتی پایین مناسب است."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "مدل زبان بزرگ با عملکرد بالا که در سال 2024 توسط بایدو توسعه یافته است. این مدل دارای تواناییهای عمومی برجستهای است و به عنوان یک مدل پایه برای تنظیم دقیق در سناریوهای خاص مناسب است و همچنین از عملکرد استنتاجی بسیار خوبی برخوردار است."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "مدل زبان بزرگ با عملکرد بالا که در سال 2024 توسط بایدو بهطور مستقل توسعه یافته است. این مدل دارای تواناییهای عمومی برجستهای است و عملکرد بهتری نسبت به ERNIE Speed دارد. مناسب برای استفاده به عنوان مدل پایه برای تنظیم دقیق و حل بهتر مسائل در سناریوهای خاص، همچنین دارای عملکرد استنتاجی بسیار عالی است."
+ },
+ "Gryphe/MythoMax-L2-13b": {
+ "description": "MythoMax-L2 (13B) یک مدل نوآورانه است که برای کاربردهای چندرشتهای و وظایف پیچیده مناسب است."
+ },
+ "InternVL2-8B": {
+ "description": "InternVL2-8B یک مدل زبان بصری قدرتمند است که از پردازش چند حالتی تصویر و متن پشتیبانی میکند و قادر است محتوای تصویر را به دقت شناسایی کرده و توصیف یا پاسخهای مرتبط تولید کند."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B یک مدل زبان بصری قدرتمند است که از پردازش چند حالتی تصویر و متن پشتیبانی میکند و قادر است محتوای تصویر را به دقت شناسایی کرده و توصیف یا پاسخهای مرتبط تولید کند."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "توانایی استدلال تصویری عالی در تصاویر با وضوح بالا، مناسب برای برنامههای درک بصری."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "توانایی استدلال تصویری پیشرفته برای برنامههای نمایندگی درک بصری."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct یکی از جدیدترین سری مدلهای زبانی بزرگ منتشر شده توسط Alibaba Cloud است. این مدل 72B در زمینههای کدنویسی و ریاضی دارای تواناییهای بهبود یافته قابل توجهی است. این مدل همچنین از پشتیبانی چند زبانه برخوردار است و بیش از 29 زبان از جمله چینی و انگلیسی را پوشش میدهد. این مدل در پیروی از دستورات، درک دادههای ساختاری و تولید خروجیهای ساختاری (به ویژه JSON) به طور قابل توجهی بهبود یافته است."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct یکی از جدیدترین سری مدلهای زبانی بزرگ منتشر شده توسط Alibaba Cloud است. این مدل 7B در زمینههای کدنویسی و ریاضی دارای تواناییهای بهبود یافته قابل توجهی است. این مدل همچنین از پشتیبانی چند زبانه برخوردار است و بیش از 29 زبان از جمله چینی و انگلیسی را پوشش میدهد. این مدل در پیروی از دستورات، درک دادههای ساختاری و تولید خروجیهای ساختاری (به ویژه JSON) به طور قابل توجهی بهبود یافته است."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "مدل متنی تنظیم شده لاما 3.1 که برای موارد مکالمه چند زبانه بهینهسازی شده و در بسیاری از مدلهای چت متن باز و بسته موجود، در معیارهای صنعتی رایج عملکرد عالی دارد."
+ },
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "مدل متنی تنظیم شده لاما 3.1 که برای موارد مکالمه چند زبانه بهینهسازی شده و در بسیاری از مدلهای چت متن باز و بسته موجود، در معیارهای صنعتی رایج عملکرد عالی دارد."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "مدل متنی تنظیم شده لاما 3.1 که برای موارد مکالمه چند زبانه بهینهسازی شده و در بسیاری از مدلهای چت متن باز و بسته موجود، در معیارهای صنعتی رایج عملکرد عالی دارد."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "مدل زبان کوچک پیشرفته و پیشرفته، با قابلیت درک زبان، توانایی استدلال عالی و توانایی تولید متن."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "مدل زبان کوچک پیشرفته و پیشرفته، با قابلیت درک زبان، توانایی استدلال عالی و توانایی تولید متن."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "لاما 3.3 پیشرفتهترین مدل زبان چند زبانه و متن باز در سری لاما است که با هزینهای بسیار کم، عملکردی مشابه مدل 405B را ارائه میدهد. این مدل بر اساس ساختار ترنسفورمر طراحی شده و از طریق تنظیم دقیق نظارتی (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) بهبود یافته است تا کارایی و ایمنی آن افزایش یابد. نسخه تنظیم شده آن به طور خاص برای مکالمات چند زبانه بهینهسازی شده و در چندین معیار صنعتی، عملکردی بهتر از بسیاری از مدلهای چت متن باز و بسته دارد. تاریخ قطع دانش آن تا دسامبر 2023 است."
+ },
+ "MiniMax-Text-01": {
+ "description": "در سری مدلهای MiniMax-01، ما نوآوریهای جسورانهای انجام دادهایم: برای اولین بار مکانیزم توجه خطی را به طور وسیع پیادهسازی کردهایم و معماری سنتی Transformer دیگر تنها گزینه نیست. این مدل دارای 456 میلیارد پارامتر است که در یک بار فعالسازی 45.9 میلیارد است. عملکرد کلی این مدل با بهترین مدلهای خارجی برابری میکند و در عین حال میتواند به طور مؤثر به متنهای طولانی جهانی با 4 میلیون توکن رسیدگی کند، که 32 برابر GPT-4o و 20 برابر Claude-3.5-Sonnet است."
+ },
+ "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
+ "description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) یک مدل دستورالعمل با دقت بالا است که برای محاسبات پیچیده مناسب است."
+ },
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 در وظایف مختلف زبان تصویری عملکرد برجستهای از خود نشان داده است، از جمله درک اسناد و نمودارها، درک متن صحنه، OCR، حل مسائل علمی و ریاضی و غیره."
+ },
+ "Phi-3-medium-128k-instruct": {
+ "description": "همان مدل Phi-3-medium، اما با اندازه بزرگتر زمینه، مناسب برای RAG یا تعداد کمی از دستورات."
+ },
+ "Phi-3-medium-4k-instruct": {
+ "description": "یک مدل با ۱۴ میلیارد پارامتر که کیفیت آن بهتر از Phi-3-mini است و تمرکز آن بر دادههای با کیفیت بالا و فشردهسازی استدلالی است."
+ },
+ "Phi-3-mini-128k-instruct": {
+ "description": "مدل مشابه Phi-3-mini، اما با اندازه بزرگتر زمینه، مناسب برای RAG یا تعداد کمی از دستورات."
+ },
+ "Phi-3-mini-4k-instruct": {
+ "description": "کوچکترین عضو خانواده Phi-3، بهینهسازی شده برای کیفیت و تأخیر کم."
+ },
+ "Phi-3-small-128k-instruct": {
+ "description": "همان مدل Phi-3-small، اما با اندازه بزرگتر زمینه، مناسب برای RAG یا تعداد کمی از دستورات."
+ },
+ "Phi-3-small-8k-instruct": {
+ "description": "یک مدل با ۷ میلیارد پارامتر که کیفیت آن بهتر از Phi-3-mini است و تمرکز آن بر دادههای با کیفیت بالا و فشردهسازی استدلالی است."
+ },
+ "Phi-3.5-mini-instruct": {
+ "description": "نسخه بهروزرسانیشده مدل Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "نسخه بهروزرسانیشده مدل Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 در وظایف مختلف زبان تصویری عملکرد برجستهای از خود نشان داده است، از جمله درک اسناد و نمودارها، درک متن صحنه، OCR، حل مسائل علمی و ریاضی و غیره."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct یک مدل زبانی بزرگ با تنظیم دقیق دستوری در سری Qwen2 است که اندازه پارامتر آن 1.5B است. این مدل بر اساس معماری Transformer ساخته شده و از تکنیکهای SwiGLU،偏置 QKV توجه و توجه گروهی استفاده میکند. این مدل در درک زبان، تولید، توانایی چند زبانه، کدنویسی، ریاضی و استدلال در چندین آزمون معیار عملکرد عالی دارد و از اکثر مدلهای متن باز پیشی گرفته است. در مقایسه با Qwen1.5-1.8B-Chat، Qwen2-1.5B-Instruct در آزمونهای MMLU، HumanEval، GSM8K، C-Eval و IFEval بهبود قابل توجهی در عملکرد نشان داده است، هرچند که تعداد پارامترها کمی کمتر است."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct یک مدل زبانی بزرگ با تنظیم دقیق دستوری در سری Qwen2 است که اندازه پارامتر آن 7B است. این مدل بر اساس معماری Transformer ساخته شده و از تکنیکهای SwiGLU،偏置 QKV توجه و توجه گروهی استفاده میکند. این مدل قادر به پردازش ورودیهای بزرگ مقیاس است. این مدل در درک زبان، تولید، توانایی چند زبانه، کدنویسی، ریاضی و استدلال در چندین آزمون معیار عملکرد عالی دارد و از اکثر مدلهای متن باز پیشی گرفته و در برخی وظایف رقابت قابل توجهی با مدلهای اختصاصی نشان میدهد. Qwen2-7B-Instruct در چندین ارزیابی از Qwen1.5-7B-Chat پیشی گرفته و بهبود قابل توجهی در عملکرد نشان داده است."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL جدیدترین نسخه از مدل Qwen-VL است که در آزمونهای معیار درک بصری به پیشرفتهترین عملکرد دست یافته است."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct یکی از جدیدترین سری مدلهای زبانی بزرگ منتشر شده توسط Alibaba Cloud است. این مدل 7B در زمینههای کدنویسی و ریاضی دارای تواناییهای بهبود یافته قابل توجهی است. این مدل همچنین از پشتیبانی چند زبانه برخوردار است و بیش از 29 زبان از جمله چینی و انگلیسی را پوشش میدهد. این مدل در پیروی از دستورات، درک دادههای ساختاری و تولید خروجیهای ساختاری (به ویژه JSON) به طور قابل توجهی بهبود یافته است."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct جدیدترین نسخه از سری مدلهای زبانی بزرگ خاص کد است که توسط Alibaba Cloud منتشر شده است. این مدل بر اساس Qwen2.5 و با آموزش 5.5 تریلیون توکن، توانایی تولید کد، استدلال و اصلاح را به طور قابل توجهی افزایش داده است. این مدل نه تنها توانایی کدنویسی را تقویت کرده بلکه مزایای ریاضی و عمومی را نیز حفظ کرده است. این مدل پایهای جامعتر برای کاربردهای عملی مانند عاملهای کد فراهم میکند."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat نسخه متن باز از مدلهای پیشآموزش شده سری GLM-4 است که توسط AI Zhizhu ارائه شده است. این مدل در زمینههای معنایی، ریاضی، استدلال، کد و دانش عملکرد عالی دارد. علاوه بر پشتیبانی از گفتگوی چند دور، GLM-4-9B-Chat همچنین دارای قابلیتهای پیشرفتهای مانند مرور وب، اجرای کد، فراخوانی ابزارهای سفارشی (Function Call) و استدلال متن طولانی است. این مدل از 26 زبان پشتیبانی میکند، از جمله چینی، انگلیسی، ژاپنی، کرهای و آلمانی. در چندین آزمون معیار، GLM-4-9B-Chat عملکرد عالی نشان داده است، مانند AlignBench-v2، MT-Bench، MMLU و C-Eval. این مدل از حداکثر طول زمینه 128K پشتیبانی میکند و برای تحقیقات علمی و کاربردهای تجاری مناسب است."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 یک مدل استنتاجی مبتنی بر یادگیری تقویتی (RL) است که مشکلات تکرار و خوانایی را در مدل حل میکند. قبل از RL، DeepSeek-R1 دادههای شروع سرد را معرفی کرده و عملکرد استنتاج را بهینهسازی کرده است. این مدل در وظایف ریاضی، کد و استنتاج با OpenAI-o1 عملکرد مشابهی دارد و از طریق روشهای آموزشی به دقت طراحی شده، عملکرد کلی را بهبود میبخشد."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 یک مدل زبان با 671 میلیارد پارامتر است که از معماری متخصصان ترکیبی (MoE) و توجه چندسر (MLA) استفاده میکند و با استراتژی تعادل بار بدون ضرر کمکی بهینهسازی کارایی استنتاج و آموزش را انجام میدهد. این مدل با پیشآموزش بر روی 14.8 تریلیون توکن با کیفیت بالا و انجام تنظیم دقیق نظارتی و یادگیری تقویتی، در عملکرد از سایر مدلهای متنباز پیشی میگیرد و به مدلهای بسته پیشرو نزدیک میشود."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma یکی از مدلهای پیشرفته و سبک وزن متن باز است که توسط Google توسعه یافته است. این یک مدل زبانی بزرگ با تنها دیکودر است که از زبان انگلیسی پشتیبانی میکند و وزنهای باز، واریانتهای پیشآموزش شده و واریانتهای تنظیم دقیق دستوری را ارائه میدهد. مدل Gemma برای انواع وظایف تولید متن، از جمله پرسش و پاسخ، خلاصهسازی و استدلال مناسب است. این مدل 9B از طریق 8 تریلیون توکن آموزش دیده است. اندازه نسبتاً کوچک آن امکان استقرار در محیطهای با منابع محدود، مانند لپتاپ، دسکتاپ یا زیرساخت ابری خود را فراهم میکند و به این ترتیب دسترسی به مدلهای پیشرفته AI را برای افراد بیشتری فراهم میکند و نوآوری را تسهیل میکند."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 یکی از خانوادههای مدلهای زبانی بزرگ چند زبانه است که توسط Meta توسعه یافته و شامل واریانتهای پیشآموزش شده و تنظیم دقیق دستوری با اندازههای پارامتر 8B، 70B و 405B است. این مدل 8B به طور خاص برای سناریوهای گفتگوی چند زبانه بهینهسازی شده و در چندین آزمون معیار صنعتی عملکرد عالی دارد. آموزش مدل با استفاده از بیش از 15 تریلیون توکن دادههای عمومی انجام شده و از تکنیکهای تنظیم دقیق نظارتی و یادگیری تقویتی با بازخورد انسانی برای افزایش مفید بودن و ایمنی مدل استفاده شده است. Llama 3.1 از تولید متن و تولید کد پشتیبانی میکند و تاریخ قطع دانش آن دسامبر 2023 است."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview یک مدل پردازش زبان طبیعی نوآورانه است که قادر به پردازش کارآمد مکالمات پیچیده و درک زمینه است."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview یک مدل تحقیقاتی است که توسط تیم Qwen توسعه یافته و بر روی تواناییهای استنتاج بصری تمرکز دارد و در درک صحنههای پیچیده و حل مسائل ریاضی مرتبط با بصری دارای مزیتهای منحصر به فردی است."
+ },
+ "Qwen/QwQ-32B": {
+ "description": "QwQ مدل استنتاجی از سری Qwen است. در مقایسه با مدلهای سنتی بهینهسازی دستورالعمل، QwQ دارای توانایی تفکر و استنتاج است و میتواند در وظایف پاییندستی عملکرد قابل توجهی را به ویژه در حل مسائل دشوار ارائه دهد. QwQ-32B یک مدل استنتاجی متوسط است که میتواند در مقایسه با مدلهای استنتاجی پیشرفته (مانند DeepSeek-R1، o1-mini) عملکرد رقابتی را به دست آورد. این مدل از تکنیکهایی مانند RoPE، SwiGLU، RMSNorm و Attention QKV bias استفاده میکند و دارای ساختار شبکه 64 لایه و 40 سر توجه Q (در معماری GQA، KV برابر با 8 است) میباشد."
+ },
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview جدیدترین مدل تحقیقاتی تجربی Qwen است که بر بهبود توانایی استدلال AI تمرکز دارد. با کاوش در مکانیزمهای پیچیدهای مانند ترکیب زبان و استدلال بازگشتی، مزایای اصلی شامل توانایی تحلیل استدلال قوی، توانایی ریاضی و برنامهنویسی است. در عین حال، مشکلاتی مانند تغییر زبان، حلقههای استدلال، ملاحظات ایمنی و تفاوتهای دیگر در تواناییها وجود دارد."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct یک مدل زبانی بزرگ با تنظیم دقیق دستوری در سری Qwen2 است که اندازه پارامتر آن 1.5B است. این مدل بر اساس معماری Transformer ساخته شده و از تکنیکهای SwiGLU،偏置 QKV توجه و توجه گروهی استفاده میکند. این مدل در درک زبان، تولید، توانایی چند زبانه، کدنویسی، ریاضی و استدلال در چندین آزمون معیار عملکرد عالی دارد و از اکثر مدلهای متن باز پیشی گرفته است. در مقایسه با Qwen1.5-1.8B-Chat، Qwen2-1.5B-Instruct در آزمونهای MMLU، HumanEval، GSM8K، C-Eval و IFEval بهبود قابل توجهی در عملکرد نشان داده است، هرچند که تعداد پارامترها کمی کمتر است."
+ },
+ "Qwen/Qwen2-72B-Instruct": {
+ "description": "Qwen 2 Instruct (72B) دستورالعملهای دقیق برای کاربردهای سازمانی ارائه میدهد و به درستی به آنها پاسخ میدهد."
+ },
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct یک مدل زبانی بزرگ با تنظیم دقیق دستوری در سری Qwen2 است که اندازه پارامتر آن 72B است. این مدل بر اساس معماری Transformer ساخته شده و از تکنیکهای SwiGLU،偏置 QKV توجه و توجه گروهی استفاده میکند. این مدل قادر به پردازش ورودیهای بزرگ مقیاس است. این مدل در درک زبان، تولید، توانایی چند زبانه، کدنویسی، ریاضی و استدلال در چندین آزمون معیار عملکرد عالی دارد و از اکثر مدلهای متن باز پیشی گرفته و در برخی وظایف رقابت قابل توجهی با مدلهای اختصاصی نشان میدهد."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL جدیدترین نسخه از مدل Qwen-VL است که در آزمونهای معیار درک بصری به پیشرفتهترین عملکرد دست یافته است."
+ },
+ "Qwen/Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5 یک سری جدید از مدلهای زبانی بزرگ است که با هدف بهینهسازی پردازش وظایف دستوری طراحی شده است."
+ },
+ "Qwen/Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5 یک سری جدید از مدلهای زبانی بزرگ است که با هدف بهینهسازی پردازش وظایف دستوری طراحی شده است."
+ },
+ "Qwen/Qwen2.5-72B-Instruct": {
+ "description": "مدل زبانی بزرگ توسعه یافته توسط تیم علیبابا، تونگyi چنوِن."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 یک سری جدید از مدلهای زبان بزرگ است که دارای تواناییهای قویتر در درک و تولید میباشد."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 یک سری جدید از مدلهای زبانی بزرگ است که با هدف بهینهسازی پردازش وظایف دستوری طراحی شده است."
+ },
+ "Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5 یک سری جدید از مدلهای زبان بزرگ است که با هدف بهینهسازی پردازش وظایف دستوری طراحی شده است."
+ },
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 یک سری جدید از مدلهای زبانی بزرگ است که با هدف بهینهسازی پردازش وظایف دستوری طراحی شده است."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder بر نوشتن کد تمرکز دارد."
+ },
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct جدیدترین نسخه از سری مدلهای زبانی بزرگ خاص کد است که توسط Alibaba Cloud منتشر شده است. این مدل بر اساس Qwen2.5 و با آموزش 5.5 تریلیون توکن، توانایی تولید کد، استدلال و اصلاح را به طور قابل توجهی افزایش داده است. این مدل نه تنها توانایی کدنویسی را تقویت کرده بلکه مزایای ریاضی و عمومی را نیز حفظ کرده است. این مدل پایهای جامعتر برای کاربردهای عملی مانند عاملهای کد فراهم میکند."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 جدیدترین سری مدلهای Qwen است که از 128k زمینه پشتیبانی میکند. در مقایسه با بهترین مدلهای متنباز فعلی، Qwen2-72B در درک زبان طبیعی، دانش، کد، ریاضی و چندزبانگی به طور قابل توجهی از مدلهای پیشرو فعلی فراتر رفته است."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 جدیدترین سری مدلهای Qwen است که میتواند از مدلهای متنباز با مقیاس مشابه و حتی بزرگتر فراتر رود. Qwen2 7B در چندین ارزیابی برتری قابل توجهی به دست آورده است، به ویژه در درک کد و زبان چینی."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B یک مدل زبان بصری قدرتمند است که از پردازش چندرسانهای تصویر و متن پشتیبانی میکند و میتواند محتوای تصویر را به دقت شناسایی کرده و توصیف یا پاسخهای مرتبط تولید کند."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct یک مدل زبان بزرگ با 140 میلیارد پارامتر است که عملکرد عالی دارد و بهینهسازی شده برای سناریوهای چینی و چند زبانه، از کاربردهایی مانند پرسش و پاسخ هوشمند و تولید محتوا پشتیبانی میکند."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct یک مدل زبان بزرگ با 320 میلیارد پارامتر است که عملکرد متوازن دارد و بهینهسازی شده برای سناریوهای چینی و چند زبانه، از کاربردهایی مانند پرسش و پاسخ هوشمند و تولید محتوا پشتیبانی میکند."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct از 16k زمینه پشتیبانی میکند و قادر به تولید متنهای طولانی بیش از 8K است. این مدل از تماسهای تابع و تعامل بدون درز با سیستمهای خارجی پشتیبانی میکند و به طور قابل توجهی انعطافپذیری و گسترشپذیری را افزایش میدهد. دانش مدل به وضوح افزایش یافته و تواناییهای کدنویسی و ریاضی به طور چشمگیری بهبود یافته است و از بیش از 29 زبان پشتیبانی میکند."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct یک مدل زبان بزرگ با 70 میلیارد پارامتر است که از تماسهای تابع و تعامل بینقص با سیستمهای خارجی پشتیبانی میکند و به طور قابل توجهی انعطافپذیری و مقیاسپذیری را افزایش میدهد. این مدل بهینهسازی شده برای سناریوهای چینی و چند زبانه، از کاربردهایی مانند پرسش و پاسخ هوشمند و تولید محتوا پشتیبانی میکند."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct یک مدل دستور برنامهنویسی مبتنی بر پیشآموزش وسیع است که دارای تواناییهای قوی در درک و تولید کد است و میتواند به طور مؤثر به انواع وظایف برنامهنویسی رسیدگی کند، به ویژه برای نوشتن کد هوشمند، تولید اسکریپتهای خودکار و پاسخ به مسائل برنامهنویسی مناسب است."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct یک مدل زبان بزرگ است که به طور خاص برای تولید کد، درک کد و سناریوهای توسعه کارآمد طراحی شده است و از مقیاس 32B پارامتر پیشرفته در صنعت بهره میبرد و میتواند نیازهای متنوع برنامهنویسی را برآورده کند."
+ },
+ "SenseChat": {
+ "description": "نسخه پایه مدل (V4)، طول متن ۴K، با تواناییهای عمومی قوی"
+ },
+ "SenseChat-128K": {
+ "description": "نسخه پایه مدل (V4)، با طول زمینه ۱۲۸K، در وظایف درک و تولید متون طولانی عملکرد برجستهای دارد"
+ },
+ "SenseChat-32K": {
+ "description": "مدل نسخه پایه (V4)، طول زمینه 32K، قابل استفاده در انواع سناریوها"
+ },
+ "SenseChat-5": {
+ "description": "جدیدترین نسخه مدل (V5.5)، با طول زمینه 128K، بهبود قابل توجه در زمینههای استدلال ریاضی، مکالمه انگلیسی، پیروی از دستورات و درک متون طولانی، قابل مقایسه با GPT-4o"
+ },
+ "SenseChat-5-1202": {
+ "description": "نسخه جدید مبتنی بر V5.5 است که در مقایسه با نسخه قبلی در تواناییهای پایه چینی و انگلیسی، چت، دانش علوم، دانش انسانی، نوشتن، منطق ریاضی و کنترل تعداد کلمات بهبود قابل توجهی داشته است."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "طول متن 32K، در درک مکالمات به زبان کانتونی از GPT-4 پیشی میگیرد و در زمینههای مختلفی مانند دانش، استدلال، ریاضیات و برنامهنویسی با GPT-4 Turbo قابل مقایسه است."
+ },
+ "SenseChat-Character": {
+ "description": "نسخه استاندارد مدل، طول متن ۸۰۰۰ کاراکتر، سرعت پاسخدهی بالا"
+ },
+ "SenseChat-Character-Pro": {
+ "description": "مدل پیشرفته، طول متن 32K، بهبود کامل قابلیتها، پشتیبانی از مکالمه به زبانهای چینی/انگلیسی"
+ },
+ "SenseChat-Turbo": {
+ "description": "مناسب برای پرسش و پاسخ سریع و تنظیم دقیق مدل"
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "این نسخه جدید مدل سبک است که به بیش از ۹۰٪ تواناییهای مدل کامل دست یافته و هزینه استنتاج را به طور قابل توجهی کاهش میدهد."
+ },
+ "SenseChat-Vision": {
+ "description": "مدل جدیدترین نسخه (V5.5) است که از ورودی چند تصویر پشتیبانی میکند و به طور جامع به بهینهسازی تواناییهای پایه مدل پرداخته و در شناسایی ویژگیهای اشیاء، روابط فضایی، شناسایی رویدادهای حرکتی، درک صحنه، شناسایی احساسات، استدلال منطقی و درک و تولید متن بهبودهای قابل توجهی داشته است."
+ },
+ "Skylark2-lite-8k": {
+ "description": "مدل نسل دوم Skylark، مدل Skylark2-lite دارای سرعت پاسخدهی بالایی است و برای سناریوهایی که نیاز به زمان واقعی بالایی دارند و حساس به هزینه هستند و نیاز به دقت مدلی کمتری دارند مناسب است. طول پنجره متنی این مدل 8k است."
+ },
+ "Skylark2-pro-32k": {
+ "description": "مدل نسل دوم Skylark، مدل Skylark2-pro دارای دقت بالای مدلی است و برای سناریوهای پیچیدهتر تولید متن مانند تولید متن تخصصی، نوشتن رمان، ترجمه باکیفیت و غیره مناسب است. طول پنجره متنی این مدل 32k است."
+ },
+ "Skylark2-pro-4k": {
+ "description": "مدل نسل دوم Skylark، مدل Skylark2-pro دارای دقت بالای مدلی است و برای سناریوهای پیچیدهتر تولید متن مانند تولید متن تخصصی، نوشتن رمان، ترجمه باکیفیت و غیره مناسب است. طول پنجره متنی این مدل 4k است."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "مدل نسل دوم Skylark، مدل Skylark2-pro-character دارای قابلیتهای برجسته بازی نقش و چت است و میتواند بهطور طبیعی طبق خواستههای کاربر مختلف نقشها را ایفا کند. این مدل برای ساخت رباتهای چت، دستیاران مجازی و خدمات مشتری آنلاین مناسب است و دارای سرعت پاسخدهی بالایی است."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "مدل نسل دوم Skylark، مدل Skylark2-pro-turbo-8k دارای استنتاج سریعتر و هزینه کمتر است و طول پنجره متنی آن 8k است."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B مدل متن باز از سری ChatGLM است که توسط AI Zhizhu توسعه یافته است. این مدل ویژگیهای عالی نسل قبلی خود را حفظ کرده است، مانند روان بودن گفتگو و آستانه پایین برای استقرار، در عین حال ویژگیهای جدیدی را معرفی کرده است. این مدل از دادههای آموزشی متنوعتر، تعداد مراحل آموزشی بیشتر و استراتژیهای آموزشی منطقیتر استفاده کرده و در میان مدلهای پیشآموزش شده زیر 10B عملکرد عالی دارد. ChatGLM3-6B از گفتگوی چند دور، فراخوانی ابزار، اجرای کد و وظایف عامل در سناریوهای پیچیده پشتیبانی میکند. علاوه بر مدل گفتگویی، مدل پایه ChatGLM-6B-Base و مدل گفتگوی طولانی ChatGLM3-6B-32K نیز به صورت متن باز ارائه شده است. این مدل به طور کامل برای تحقیقات علمی باز است و پس از ثبتنام، استفاده تجاری رایگان نیز مجاز است."
+ },
+ "THUDM/glm-4-9b-chat": {
+ "description": "نسخه منبع باز GLM-4 9B، تجربه گفتگوی بهینهشده برای برنامههای مکالمه را ارائه میدهد."
+ },
+ "TeleAI/TeleChat2": {
+ "description": "مدل بزرگ TeleChat2 توسط China Telecom از صفر تا یک به طور مستقل توسعه یافته و یک مدل معنایی تولیدی است که از قابلیتهایی مانند پرسش و پاسخ دایرهالمعارف، تولید کد و تولید متن طولانی پشتیبانی میکند و خدمات مشاوره گفتگویی را به کاربران ارائه میدهد. این مدل قادر به تعامل گفتگویی با کاربران، پاسخ به سوالات و کمک به خلاقیت است و به طور کارآمد و راحت به کاربران در دستیابی به اطلاعات، دانش و الهام کمک میکند. این مدل در زمینههای مشکلات توهم، تولید متن طولانی و درک منطقی عملکرد خوبی دارد."
+ },
+ "TeleAI/TeleMM": {
+ "description": "مدل بزرگ چندرسانهای TeleMM یک مدل بزرگ درک چندرسانهای است که توسط China Telecom به طور مستقل توسعه یافته و قادر به پردازش ورودیهای چندرسانهای از جمله متن و تصویر است و از قابلیتهایی مانند درک تصویر و تحلیل نمودار پشتیبانی میکند و خدمات درک چندرسانهای را به کاربران ارائه میدهد. این مدل قادر به تعامل چندرسانهای با کاربران است و محتوا را به دقت درک کرده و به سوالات پاسخ میدهد، به خلاقیت کمک میکند و به طور کارآمد اطلاعات و الهام چندرسانهای را ارائه میدهد. این مدل در وظایف چندرسانهای مانند درک دقیق، استدلال منطقی و غیره عملکرد خوبی دارد."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct یکی از جدیدترین سری مدلهای زبانی بزرگ منتشر شده توسط Alibaba Cloud است. این مدل 72B در زمینههای کدنویسی و ریاضی دارای تواناییهای بهبود یافته قابل توجهی است. این مدل همچنین از پشتیبانی چند زبانه برخوردار است و بیش از 29 زبان از جمله چینی و انگلیسی را پوشش میدهد. این مدل در پیروی از دستورات، درک دادههای ساختاری و تولید خروجیهای ساختاری (به ویژه JSON) به طور قابل توجهی بهبود یافته است."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B با حفظ تواناییهای زبان عمومی عالی مدلهای قبلی خود، از طریق آموزش افزایشی 500 میلیارد توکن با کیفیت بالا، به طور قابل توجهی تواناییهای منطقی ریاضی و کدنویسی را افزایش داده است."
+ },
+ "abab5.5-chat": {
+ "description": "برای سناریوهای بهرهوری طراحی شده است، از پردازش وظایف پیچیده و تولید متن کارآمد پشتیبانی میکند و برای کاربردهای حرفهای مناسب است."
+ },
+ "abab5.5s-chat": {
+ "description": "طراحی شده برای سناریوهای مکالمه با شخصیتهای چینی، ارائه توانایی تولید مکالمات با کیفیت بالا به زبان چینی، مناسب برای انواع کاربردها."
+ },
+ "abab6.5g-chat": {
+ "description": "طراحی شده برای مکالمات چندزبانه با شخصیتهای مختلف، پشتیبانی از تولید مکالمات با کیفیت بالا به زبان انگلیسی و سایر زبانها."
+ },
+ "abab6.5s-chat": {
+ "description": "مناسب برای طیف گستردهای از وظایف پردازش زبان طبیعی، از جمله تولید متن، سیستمهای گفتگو و غیره."
+ },
+ "abab6.5t-chat": {
+ "description": "بهینهسازی شده برای سناریوهای مکالمه با شخصیتهای چینی، ارائه توانایی تولید مکالمات روان و مطابق با عادات بیانی چینی."
+ },
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 یک مدل زبان بزرگ پیشرفته است که با یادگیری تقویتی و بهینهسازی دادههای راهاندازی سرد، عملکرد استدلال، ریاضیات و برنامهنویسی فوقالعادهای دارد."
+ },
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "مدل زبان قدرتمند Mixture-of-Experts (MoE) ارائه شده توسط Deepseek، با مجموع پارامترها به میزان 671B و فعالسازی 37B پارامتر برای هر نشانه."
+ },
+ "accounts/fireworks/models/llama-v3-70b-instruct": {
+ "description": "مدل Llama 3 70B دستورالعمل، بهطور ویژه برای مکالمات چندزبانه و درک زبان طبیعی بهینهسازی شده است و عملکردی بهتر از اکثر مدلهای رقیب دارد."
+ },
+ "accounts/fireworks/models/llama-v3-8b-instruct": {
+ "description": "مدل Llama 3 8B دستورالعمل، بهینهسازی شده برای مکالمه و وظایف چندزبانه، با عملکرد برجسته و کارآمد."
+ },
+ "accounts/fireworks/models/llama-v3-8b-instruct-hf": {
+ "description": "مدل Llama 3 8B دستورالعمل (نسخه HF)، با نتایج پیادهسازی رسمی سازگار است و از سازگاری بالا و قابلیت همکاری بین پلتفرمی برخوردار است."
+ },
+ "accounts/fireworks/models/llama-v3p1-405b-instruct": {
+ "description": "مدل Llama 3.1 405B دستورالعمل، با پارامترهای بسیار بزرگ، مناسب برای وظایف پیچیده و سناریوهای با بار سنگین در پیروی از دستورالعملها."
+ },
+ "accounts/fireworks/models/llama-v3p1-70b-instruct": {
+ "description": "مدل Llama 3.1 70B دستورالعمل، با توانایی برجسته در درک و تولید زبان طبیعی، انتخابی ایدهآل برای وظایف مکالمه و تحلیل است."
+ },
+ "accounts/fireworks/models/llama-v3p1-8b-instruct": {
+ "description": "مدل Llama 3.1 8B دستورالعمل، بهینهسازی شده برای مکالمات چندزبانه، قادر به پیشی گرفتن از اکثر مدلهای متنباز و بسته در معیارهای صنعتی رایج."
+ },
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "مدل استنتاج تصویر با ۱۱ میلیارد پارامتر از Meta که برای دستورالعملها تنظیم شده است. این مدل برای تشخیص بصری، استنتاج تصویر، توصیف تصویر و پاسخ به سوالات عمومی درباره تصاویر بهینهسازی شده است. این مدل قادر به درک دادههای بصری مانند نمودارها و گرافها است و با تولید توضیحات متنی از جزئیات تصاویر، فاصله بین دیداری و زبانی را پر میکند."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "مدل Llama 3.2 3B دستورالعمل یک مدل چندزبانه سبک است که توسط Meta ارائه شده است. این مدل با هدف بهبود کارایی طراحی شده و در مقایسه با مدلهای بزرگتر، بهبودهای قابل توجهی در تأخیر و هزینه ارائه میدهد. نمونههای کاربردی این مدل شامل بازنویسی پرسشها و دستورات و همچنین کمک به نوشتن است."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "مدل استنتاج تصویر با 90 میلیارد پارامتر از Meta که برای دستورالعملها تنظیم شده است. این مدل برای تشخیص بصری، استنتاج تصویر، توصیف تصویر و پاسخ به سوالات عمومی در مورد تصاویر بهینهسازی شده است. این مدل قادر است دادههای بصری مانند نمودارها و گرافها را درک کند و با تولید توضیحات متنی از جزئیات تصویر، فاصله بین دیداری و زبانی را پر کند."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "مدل Llama 3.3 70B Instruct نسخه بهروزرسانی شده Llama 3.1 70B در دسامبر است. این مدل بر اساس Llama 3.1 70B (منتشر شده در ژوئیه 2024) بهبود یافته و قابلیتهای فراخوانی ابزار، پشتیبانی از متن چند زبانه، ریاضیات و برنامهنویسی را تقویت کرده است. این مدل در استدلال، ریاضیات و پیروی از دستورات به سطح پیشرفتهای در صنعت رسیده و میتواند عملکردی مشابه با 3.1 405B ارائه دهد، در حالی که از نظر سرعت و هزینه مزایای قابل توجهی دارد."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "مدل 24B با پارامترهایی که قابلیتهای پیشرفتهای مشابه مدلهای بزرگتر را داراست."
+ },
+ "accounts/fireworks/models/mixtral-8x22b-instruct": {
+ "description": "مدل Mixtral MoE 8x22B دستوری، با پارامترهای بزرگ و معماری چندین متخصص، پشتیبانی کامل از پردازش کارآمد وظایف پیچیده."
+ },
+ "accounts/fireworks/models/mixtral-8x7b-instruct": {
+ "description": "مدل Mixtral MoE 8x7B، معماری چندین متخصص برای پیروی و اجرای دستورات بهصورت کارآمد ارائه میدهد."
+ },
+ "accounts/fireworks/models/mythomax-l2-13b": {
+ "description": "مدل MythoMax L2 13B، با استفاده از تکنیکهای ترکیبی نوآورانه، در روایت داستان و نقشآفرینی مهارت دارد."
+ },
+ "accounts/fireworks/models/phi-3-vision-128k-instruct": {
+ "description": "Phi-3-Vision-128K-Instruct یک مدل چندوجهی پیشرفته و سبک است که بر اساس مجموعه دادههایی شامل دادههای مصنوعی و وبسایتهای عمومی فیلتر شده ساخته شده است. این مدل بر دادههای بسیار باکیفیت و متمرکز بر استدلال، که شامل متن و تصویر هستند، تمرکز دارد. این مدل بخشی از سری مدلهای Phi-3 است و نسخه چندوجهی آن از طول زمینه 128K (بر حسب توکن) پشتیبانی میکند. این مدل از یک فرآیند تقویت دقیق عبور کرده است که ترکیبی از تنظیم دقیق تحت نظارت و بهینهسازی مستقیم ترجیحات را شامل میشود تا از پیروی دقیق از دستورات و اقدامات امنیتی قوی اطمینان حاصل شود."
+ },
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "مدل QwQ یک مدل تحقیقاتی تجربی است که توسط تیم Qwen توسعه یافته و بر تقویت توانایی استدلال AI تمرکز دارد."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "نسخه 72B مدل Qwen-VL نتیجه جدیدترین بهروزرسانیهای علیبابا است که نمایانگر نوآوریهای نزدیک به یک سال اخیر است."
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 مجموعهای از مدلهای زبانی است که تنها شامل رمزگشاها میباشد و توسط تیم Qwen علیبابا کلود توسعه یافته است. این مدلها در اندازههای مختلف از جمله 0.5B، 1.5B، 3B، 7B، 14B، 32B و 72B ارائه میشوند و دارای دو نوع پایه (base) و دستوری (instruct) هستند."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct جدیدترین نسخه از سری مدلهای زبانی بزرگ خاص کد است که توسط Alibaba Cloud منتشر شده است. این مدل بر اساس Qwen2.5 و با آموزش 5.5 تریلیون توکن، توانایی تولید کد، استدلال و اصلاح را به طور قابل توجهی افزایش داده است. این مدل نه تنها توانایی کدنویسی را تقویت کرده بلکه مزایای ریاضی و عمومی را نیز حفظ کرده است. این مدل پایهای جامعتر برای کاربردهای عملی مانند عاملهای کد فراهم میکند."
+ },
+ "accounts/yi-01-ai/models/yi-large": {
+ "description": "مدل Yi-Large، با توانایی برجسته در پردازش چندزبانه، مناسب برای انواع وظایف تولید و درک زبان."
+ },
+ "ai21-jamba-1.5-large": {
+ "description": "یک مدل چندزبانه با 398 میلیارد پارامتر (94 میلیارد فعال) که پنجره متنی طولانی 256 هزار توکن، فراخوانی توابع، خروجی ساختاریافته و تولید مبتنی بر واقعیت را ارائه میدهد."
+ },
+ "ai21-jamba-1.5-mini": {
+ "description": "یک مدل چندزبانه با 52 میلیارد پارامتر (12 میلیارد فعال) که پنجره متنی طولانی 256K، فراخوانی توابع، خروجی ساختاریافته و تولید مبتنی بر واقعیت را ارائه میدهد."
+ },
+ "anthropic.claude-3-5-sonnet-20240620-v1:0": {
+ "description": "Claude 3.5 Sonnet استانداردهای صنعت را ارتقا داده است، عملکردی بهتر از مدلهای رقیب و Claude 3 Opus دارد، در ارزیابیهای گسترده به خوبی عمل کرده و در عین حال سرعت و هزینه مدلهای سطح متوسط ما را حفظ میکند."
+ },
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet استانداردهای صنعت را ارتقا داده است، عملکردی بهتر از مدلهای رقیب و Claude 3 Opus دارد، در ارزیابیهای گسترده به خوبی عمل کرده و در عین حال سرعت و هزینه مدلهای سطح متوسط ما را حفظ میکند."
+ },
+ "anthropic.claude-3-haiku-20240307-v1:0": {
+ "description": "Claude 3 Haiku سریعترین و فشردهترین مدل Anthropic است که پاسخهای تقریباً فوری ارائه میدهد. این مدل میتواند به سرعت به پرسشها و درخواستهای ساده پاسخ دهد. مشتریان قادر خواهند بود تجربههای هوش مصنوعی یکپارچهای را که تعاملات انسانی را تقلید میکند، ایجاد کنند. Claude 3 Haiku میتواند تصاویر را پردازش کرده و خروجی متنی ارائه دهد و دارای پنجره متنی 200K است."
+ },
+ "anthropic.claude-3-opus-20240229-v1:0": {
+ "description": "Claude 3 Opus قدرتمندترین مدل هوش مصنوعی Anthropic است که عملکرد پیشرفتهای در وظایف بسیار پیچیده دارد. این مدل میتواند با درخواستهای باز و سناریوهای ناآشنا کار کند و دارای روانی و درک شبهانسانی برجستهای است. Claude 3 Opus مرزهای جدیدی از امکانات هوش مصنوعی مولد را به نمایش میگذارد. Claude 3 Opus میتواند تصاویر را پردازش کرده و خروجی متنی ارائه دهد و دارای پنجره متنی 200K است."
+ },
+ "anthropic.claude-3-sonnet-20240229-v1:0": {
+ "description": "Claude 3 Sonnet از Anthropic به تعادلی ایدهآل بین هوش و سرعت دست یافته است—بهویژه برای بارهای کاری سازمانی مناسب است. این مدل با قیمتی کمتر از رقبا، بیشترین بهرهوری را ارائه میدهد و بهعنوان یک ماشین اصلی قابل اعتماد و با دوام بالا طراحی شده است که برای استقرارهای مقیاسپذیر AI مناسب است. Claude 3 Sonnet میتواند تصاویر را پردازش کرده و خروجی متنی ارائه دهد و دارای پنجره متنی 200K است."
+ },
+ "anthropic.claude-instant-v1": {
+ "description": "مدلی سریع، اقتصادی و همچنان بسیار توانمند که میتواند طیف وسیعی از وظایف از جمله مکالمات روزمره، تحلیل متن، خلاصهسازی و پاسخ به سوالات اسناد را انجام دهد."
+ },
+ "anthropic.claude-v2": {
+ "description": "Anthropic مدلی است که در انجام وظایف گستردهای از مکالمات پیچیده و تولید محتوای خلاقانه تا پیروی دقیق از دستورات، توانایی بالایی از خود نشان میدهد."
+ },
+ "anthropic.claude-v2:1": {
+ "description": "نسخه بهروزرسانی شده Claude 2، با دو برابر پنجره متنی و بهبود در قابلیت اطمینان، کاهش توهمات و دقت مبتنی بر شواهد در اسناد طولانی و زمینههای RAG."
+ },
+ "anthropic/claude-3-haiku": {
+ "description": "Claude 3 Haiku سریعترین و فشردهترین مدل Anthropic است که برای ارائه پاسخهای تقریباً فوری طراحی شده است. این مدل دارای عملکرد سریع و دقیق جهتدار است."
+ },
+ "anthropic/claude-3-opus": {
+ "description": "Claude 3 Opus قدرتمندترین مدل Anthropic برای انجام وظایف بسیار پیچیده است. این مدل در عملکرد، هوش، روانی و درک عالی عمل میکند."
+ },
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku سریعترین مدل نسل بعدی Anthropic است. در مقایسه با Claude 3 Haiku، Claude 3.5 Haiku در تمام مهارتها بهبود یافته و در بسیاری از آزمونهای هوش از بزرگترین مدل نسل قبلی، Claude 3 Opus پیشی گرفته است."
+ },
+ "anthropic/claude-3.5-sonnet": {
+ "description": "Claude 3.5 Sonnet تواناییهایی فراتر از Opus ارائه میدهد و سرعتی سریعتر از Sonnet دارد، در حالی که قیمت آن با Sonnet یکسان است. Sonnet بهویژه در برنامهنویسی، علم داده، پردازش بصری و وظایف نمایندگی مهارت دارد."
+ },
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet هو هوش مصنوعی پیشرفتهترین مدل Anthropic است و همچنین اولین مدل استدلال ترکیبی در بازار به شمار میرود. Claude 3.7 Sonnet میتواند پاسخهای تقریباً آنی یا تفکر تدریجی و طولانیتری تولید کند که کاربران میتوانند این فرآیندها را به وضوح مشاهده کنند. Sonnet بهویژه در برنامهنویسی، علم داده، پردازش بصری و وظایف نمایندگی مهارت دارد."
+ },
+ "aya": {
+ "description": "Aya 23 یک مدل چندزبانه است که توسط Cohere ارائه شده و از 23 زبان پشتیبانی میکند و برای برنامههای چندزبانه تسهیلات فراهم میآورد."
+ },
+ "aya:35b": {
+ "description": "Aya 23 یک مدل چندزبانه است که توسط Cohere ارائه شده و از 23 زبان پشتیبانی میکند و استفاده از برنامههای چندزبانه را تسهیل مینماید."
+ },
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B یک مدل زبان بزرگ متن باز و قابل تجاری با 130 میلیارد پارامتر است که در آزمونهای معتبر چینی و انگلیسی بهترین عملکرد را در اندازه مشابه به دست آورده است."
+ },
+ "charglm-3": {
+ "description": "CharGLM-3 بهطور ویژه برای نقشآفرینی و همراهی عاطفی طراحی شده است، از حافظه طولانیمدت و مکالمات شخصیسازیشده پشتیبانی میکند و کاربردهای گستردهای دارد."
+ },
+ "chatgpt-4o-latest": {
+ "description": "ChatGPT-4o یک مدل پویا است که بهصورت زنده بهروزرسانی میشود تا همیشه نسخهی جدید و بهروز باشد. این مدل ترکیبی از تواناییهای قوی در درک و تولید زبان است و برای کاربردهای گسترده مانند خدمات مشتری، آموزش و پشتیبانی فنی مناسب است."
+ },
+ "claude-2.0": {
+ "description": "Claude 2 پیشرفتهای کلیدی را برای کسبوکارها ارائه میدهد، از جمله زمینه 200K توکن پیشرو در صنعت، کاهش قابل توجه نرخ خطاهای مدل، اعلانهای سیستمی و یک ویژگی جدید آزمایشی: فراخوانی ابزار."
+ },
+ "claude-2.1": {
+ "description": "Claude 2 پیشرفتهای کلیدی را برای کسبوکارها فراهم میکند، از جمله زمینه 200K توکن پیشرو در صنعت، کاهش قابل توجه در نرخ توهم مدل، اعلانهای سیستمی و یک ویژگی آزمایشی جدید: فراخوانی ابزار."
+ },
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku سریعترین مدل نسل بعدی Anthropic است. در مقایسه با Claude 3 Haiku، Claude 3.5 Haiku در تمام مهارتها بهبود یافته و در بسیاری از آزمونهای استاندارد هوش، از بزرگترین مدل نسل قبلی یعنی Claude 3 Opus پیشی گرفته است."
+ },
+ "claude-3-5-sonnet-20240620": {
+ "description": "Claude 3.5 Sonnet تواناییهایی فراتر از Opus ارائه میدهد و سرعتی سریعتر از Sonnet دارد، در حالی که قیمت آن با Sonnet یکسان است. Sonnet بهویژه در برنامهنویسی، علم داده، پردازش بصری و وظایف نمایندگی مهارت دارد."
+ },
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet تواناییهایی فراتر از Opus ارائه میدهد و سرعتی سریعتر از Sonnet دارد، در حالی که قیمت آن با Sonnet یکسان است. Sonnet بهویژه در برنامهنویسی، علم داده، پردازش بصری و وظایف نمایندگی مهارت دارد."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet تواناییهایی فراتر از Opus ارائه میدهد و سرعتی سریعتر از Sonnet دارد، در حالی که قیمت آن با Sonnet یکسان است. Sonnet بهویژه در برنامهنویسی، علم داده، پردازش بصری و وظایف نمایندگی مهارت دارد."
+ },
+ "claude-3-haiku-20240307": {
+ "description": "Claude 3 Haiku سریعترین و فشردهترین مدل Anthropic است که برای ارائه پاسخهای تقریباً فوری طراحی شده است. این مدل دارای عملکرد سریع و دقیق جهتگیری است."
+ },
+ "claude-3-opus-20240229": {
+ "description": "Claude 3 Opus قدرتمندترین مدل Anthropic برای انجام وظایف بسیار پیچیده است. این مدل در عملکرد، هوش، روانی و درک عالی عمل میکند."
+ },
+ "claude-3-sonnet-20240229": {
+ "description": "Claude 3 Sonnet تعادلی ایدهآل بین هوش و سرعت برای بارهای کاری سازمانی فراهم میکند. این محصول با قیمتی پایینتر حداکثر بهرهوری را ارائه میدهد، قابل اعتماد است و برای استقرار در مقیاس بزرگ مناسب میباشد."
+ },
+ "codegeex-4": {
+ "description": "CodeGeeX-4 یک دستیار برنامهنویسی قدرتمند مبتنی بر هوش مصنوعی است که از پرسش و پاسخ هوشمند و تکمیل کد در زبانهای برنامهنویسی مختلف پشتیبانی میکند و بهرهوری توسعه را افزایش میدهد."
+ },
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B یک مدل تولید کد چندزبانگی است که از قابلیتهای جامع شامل تکمیل و تولید کد، مفسر کد، جستجوی وب، تماس با توابع و پرسش و پاسخ کد در سطح مخزن پشتیبانی میکند و تمام سناریوهای توسعه نرمافزار را پوشش میدهد. این مدل یکی از بهترین مدلهای تولید کد با پارامترهای کمتر از 10B است."
+ },
+ "codegemma": {
+ "description": "CodeGemma یک مدل زبانی سبک برای وظایف مختلف برنامهنویسی است که از تکرار سریع و یکپارچهسازی پشتیبانی میکند."
+ },
+ "codegemma:2b": {
+ "description": "CodeGemma یک مدل زبان سبک برای وظایف مختلف برنامهنویسی است که از تکرار سریع و یکپارچهسازی پشتیبانی میکند."
+ },
+ "codellama": {
+ "description": "Code Llama یک مدل زبانی بزرگ (LLM) است که بر تولید و بحث در مورد کد تمرکز دارد و از زبانهای برنامهنویسی گستردهای پشتیبانی میکند و برای محیطهای توسعهدهندگان مناسب است."
+ },
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama یک LLM است که بر تولید و بحث کد تمرکز دارد و از پشتیبانی گسترده زبانهای برنامهنویسی برخوردار است و برای محیطهای توسعهدهنده مناسب است."
+ },
+ "codellama:13b": {
+ "description": "Code Llama یک مدل زبانی بزرگ (LLM) است که بر تولید و بحث در مورد کد تمرکز دارد و از زبانهای برنامهنویسی گستردهای پشتیبانی میکند و برای محیطهای توسعهدهندگان مناسب است."
+ },
+ "codellama:34b": {
+ "description": "Code Llama یک مدل زبانی بزرگ (LLM) است که بر تولید و بحث در مورد کد تمرکز دارد و از زبانهای برنامهنویسی گستردهای پشتیبانی میکند و برای محیطهای توسعهدهندگان مناسب است."
+ },
+ "codellama:70b": {
+ "description": "Code Llama یک مدل زبانی بزرگ (LLM) است که بر تولید و بحث در مورد کد تمرکز دارد و با پشتیبانی گسترده از زبانهای برنامهنویسی، برای محیطهای توسعهدهندگان مناسب است."
+ },
+ "codeqwen": {
+ "description": "CodeQwen1.5 یک مدل زبان بزرگ است که بر اساس حجم زیادی از دادههای کد آموزش دیده و بهطور خاص برای حل وظایف پیچیده برنامهنویسی طراحی شده است."
+ },
+ "codestral": {
+ "description": "Codestral اولین مدل کد از Mistral AI است که پشتیبانی عالی برای وظایف تولید کد ارائه میدهد."
+ },
+ "codestral-latest": {
+ "description": "Codestral یک مدل پیشرفته تولید کد است که بر تولید کد تمرکز دارد و برای وظایف تکمیل کد و پر کردن میانمتن بهینهسازی شده است."
+ },
+ "cognitivecomputations/dolphin-mixtral-8x22b": {
+ "description": "Dolphin Mixtral 8x22B یک مدل طراحی شده برای پیروی از دستورات، مکالمه و برنامهنویسی است."
+ },
+ "cohere-command-r": {
+ "description": "Command R یک مدل تولیدی قابل گسترش است که برای RAG و استفاده از ابزارها طراحی شده است و به شرکتها امکان میدهد تا به هوش مصنوعی در سطح تولید دست یابند."
+ },
+ "cohere-command-r-plus": {
+ "description": "Command R+ یک مدل پیشرفته بهینهسازی RAG است که برای مدیریت بارهای کاری در سطح سازمانی طراحی شده است."
+ },
+ "command-r": {
+ "description": "Command R یک LLM بهینهسازی شده برای مکالمات و وظایف با متن طولانی است که بهویژه برای تعاملات پویا و مدیریت دانش مناسب است."
+ },
+ "command-r-plus": {
+ "description": "Command R+ یک مدل زبان بزرگ با عملکرد بالا است که برای سناریوهای واقعی کسبوکار و کاربردهای پیچیده طراحی شده است."
+ },
+ "dall-e-2": {
+ "description": "مدل نسل دوم DALL·E، پشتیبانی از تولید تصاویر واقعیتر و دقیقتر، با وضوح 4 برابر نسل اول."
+ },
+ "dall-e-3": {
+ "description": "جدیدترین مدل DALL·E، منتشر شده در نوامبر 2023. پشتیبانی از تولید تصاویر واقعیتر و دقیقتر، با جزئیات بیشتر."
+ },
+ "databricks/dbrx-instruct": {
+ "description": "DBRX Instruct قابلیت پردازش دستورات با قابلیت اطمینان بالا را فراهم میکند و از کاربردهای چندین صنعت پشتیبانی میکند."
+ },
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 یک مدل استنتاجی مبتنی بر یادگیری تقویتی (RL) است که به مشکلات تکرار و خوانایی در مدل پرداخته است. قبل از RL، DeepSeek-R1 دادههای شروع سرد را معرفی کرد و عملکرد استنتاج را بهینهتر کرد. این مدل در وظایف ریاضی، کدنویسی و استنتاج با OpenAI-o1 عملکرد مشابهی دارد و با استفاده از روشهای آموزشی به دقت طراحی شده، کیفیت کلی را بهبود بخشیده است."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "مدل تقطیر DeepSeek-R1 که با استفاده از یادگیری تقویتی و دادههای شروع سرد عملکرد استدلال را بهینهسازی کرده و مدلهای متنباز را به روز کرده است."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B مدلی است که بر اساس Llama-3.1-8B توسعه یافته است. این مدل با استفاده از نمونههای تولید شده توسط DeepSeek-R1 برای تنظیم دقیق، توانایی استدلال عالی را نشان میدهد. در چندین آزمون معیار عملکرد خوبی داشته است، به طوری که در MATH-500 به دقت 89.1% و در AIME 2024 به نرخ قبولی 50.4% دست یافته و در CodeForces امتیاز 1205 را کسب کرده است و به عنوان مدلی با مقیاس 8B تواناییهای ریاضی و برنامهنویسی قوی را نشان میدهد."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "مدل تقطیر DeepSeek-R1 که با استفاده از یادگیری تقویتی و دادههای شروع سرد عملکرد استدلال را بهینهسازی کرده و مدلهای متنباز را به روز کرده است."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "مدل تقطیر DeepSeek-R1 که با استفاده از یادگیری تقویتی و دادههای شروع سرد عملکرد استدلال را بهینهسازی کرده و مدلهای متنباز را به روز کرده است."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B مدلی است که از تقطیر دانش بر اساس Qwen2.5-32B به دست آمده است. این مدل با استفاده از 800000 نمونه منتخب تولید شده توسط DeepSeek-R1 برای تنظیم دقیق، در زمینههای مختلفی از جمله ریاضیات، برنامهنویسی و استدلال عملکرد برجستهای را نشان میدهد. در چندین آزمون معیار از جمله AIME 2024، MATH-500 و GPQA Diamond نتایج عالی کسب کرده است، به طوری که در MATH-500 به دقت 94.3% دست یافته و توانایی استدلال ریاضی قوی را نشان میدهد."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B مدلی است که از تقطیر دانش بر اساس Qwen2.5-Math-7B به دست آمده است. این مدل با استفاده از 800000 نمونه منتخب تولید شده توسط DeepSeek-R1 برای تنظیم دقیق، توانایی استدلال عالی را نشان میدهد. در چندین آزمون معیار عملکرد برجستهای داشته است، به طوری که در MATH-500 به دقت 92.8% و در AIME 2024 به نرخ قبولی 55.5% دست یافته و در CodeForces امتیاز 1189 را کسب کرده است و به عنوان مدلی با مقیاس 7B تواناییهای ریاضی و برنامهنویسی قوی را نشان میدهد."
+ },
+ "deepseek-ai/DeepSeek-V2.5": {
+ "description": "DeepSeek V2.5 ویژگیهای برجسته نسخههای قبلی را گرد هم آورده و تواناییهای عمومی و کدنویسی را تقویت کرده است."
+ },
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 یک مدل زبانی ترکیبی از متخصصان (MoE) با 671 میلیارد پارامتر است که از توجه چندسر (MLA) و معماری DeepSeekMoE استفاده میکند و با ترکیب استراتژی تعادل بار بدون ضرر کمکی، کارایی استنتاج و آموزش را بهینه میکند. با پیشآموزش بر روی 14.8 تریلیون توکن با کیفیت بالا و انجام تنظیم دقیق نظارتی و یادگیری تقویتی، DeepSeek-V3 در عملکرد از سایر مدلهای متنباز پیشی میگیرد و به مدلهای بسته پیشرو نزدیک میشود."
+ },
+ "deepseek-ai/deepseek-llm-67b-chat": {
+ "description": "DeepSeek LLM Chat (67B) یک مدل نوآورانه هوش مصنوعی است که توانایی درک عمیق زبان و تعامل را فراهم میکند."
+ },
+ "deepseek-ai/deepseek-r1": {
+ "description": "مدل LLM پیشرفته و کارآمد که در استدلال، ریاضیات و برنامهنویسی مهارت دارد."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 یک مدل زبانی بصری مبتنی بر DeepSeekMoE-27B است که از معماری MoE با فعالسازی پراکنده استفاده میکند و در حالی که تنها 4.5 میلیارد پارامتر فعال است، عملکرد فوقالعادهای را ارائه میدهد. این مدل در چندین وظیفه از جمله پرسش و پاسخ بصری، شناسایی کاراکتر نوری، درک اسناد/جدولها/نمودارها و مکانیابی بصری عملکرد عالی دارد."
+ },
+ "deepseek-chat": {
+ "description": "مدل متنباز جدیدی که تواناییهای عمومی و کدنویسی را ترکیب میکند. این مدل نه تنها توانایی گفتگوی عمومی مدل Chat و توانایی قدرتمند پردازش کد مدل Coder را حفظ کرده است، بلکه به ترجیحات انسانی نیز بهتر همسو شده است. علاوه بر این، DeepSeek-V2.5 در وظایف نوشتاری، پیروی از دستورات و سایر جنبهها نیز بهبودهای قابل توجهی داشته است."
+ },
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B یک مدل زبان کد است که بر اساس 20 تریلیون داده آموزش دیده است، که 87% آن کد و 13% آن زبانهای چینی و انگلیسی است. این مدل اندازه پنجره 16K و وظایف پر کردن جا را معرفی میکند و قابلیت تکمیل کد و پر کردن قطعات در سطح پروژه را ارائه میدهد."
+ },
+ "deepseek-coder-v2": {
+ "description": "DeepSeek Coder V2 یک مدل کد نویسی ترکیبی و متنباز است که در وظایف کدنویسی عملکرد عالی دارد و با GPT4-Turbo قابل مقایسه است."
+ },
+ "deepseek-coder-v2:236b": {
+ "description": "DeepSeek Coder V2 یک مدل کد نویسی ترکیبی و متنباز است که در وظایف کدنویسی عملکرد بسیار خوبی دارد و با GPT4-Turbo قابل مقایسه است."
+ },
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 یک مدل استنتاجی مبتنی بر یادگیری تقویتی (RL) است که به مشکلات تکرار و خوانایی در مدل پرداخته است. قبل از RL، DeepSeek-R1 دادههای شروع سرد را معرفی کرد و عملکرد استنتاج را بهینهتر کرد. این مدل در وظایف ریاضی، کدنویسی و استنتاج با OpenAI-o1 عملکرد مشابهی دارد و با استفاده از روشهای آموزشی به دقت طراحی شده، کیفیت کلی را بهبود بخشیده است."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - مدل بزرگتر و هوشمندتر در مجموعه DeepSeek - به معماری Llama 70B تقطیر شده است. بر اساس آزمونهای معیار و ارزیابیهای انسانی، این مدل از Llama 70B اصلی هوشمندتر است، به ویژه در وظایفی که نیاز به دقت ریاضی و واقعی دارند."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "مدلهای سری DeepSeek-R1-Distill از طریق تکنیک تقطیر دانش، نمونههای تولید شده توسط DeepSeek-R1 را برای تنظیم دقیق بر روی مدلهای متنباز مانند Qwen و Llama به کار میبرند."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "مدلهای سری DeepSeek-R1-Distill از طریق تکنیک تقطیر دانش، نمونههای تولید شده توسط DeepSeek-R1 را برای تنظیم دقیق بر روی مدلهای متنباز مانند Qwen و Llama به کار میبرند."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "مدلهای سری DeepSeek-R1-Distill از طریق تکنیک تقطیر دانش، نمونههای تولید شده توسط DeepSeek-R1 را برای تنظیم دقیق بر روی مدلهای متنباز مانند Qwen و Llama به کار میبرند."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "مدلهای سری DeepSeek-R1-Distill از طریق تکنیک تقطیر دانش، نمونههای تولید شده توسط DeepSeek-R1 را برای تنظیم دقیق بر روی مدلهای متنباز مانند Qwen و Llama به کار میبرند."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "مدلهای سری DeepSeek-R1-Distill از طریق تکنیک تقطیر دانش، نمونههای تولید شده توسط DeepSeek-R1 را برای تنظیم دقیق بر روی مدلهای متنباز مانند Qwen و Llama به کار میبرند."
+ },
+ "deepseek-reasoner": {
+ "description": "مدل استدلالی ارائه شده توسط DeepSeek. قبل از ارائه پاسخ نهایی، مدل ابتدا یک زنجیره تفکر را تولید میکند تا دقت پاسخ نهایی را افزایش دهد."
+ },
+ "deepseek-v2": {
+ "description": "DeepSeek V2 یک مدل زبانی Mixture-of-Experts کارآمد است که برای پردازش نیازهای اقتصادی و کارآمد مناسب میباشد."
+ },
+ "deepseek-v2:236b": {
+ "description": "DeepSeek V2 236B مدل طراحی کد DeepSeek است که تواناییهای قدرتمندی در تولید کد ارائه میدهد."
+ },
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 مدل MoE توسعه یافته توسط شرکت تحقیقاتی فناوری هوش مصنوعی DeepSeek در هانگژو است که در چندین ارزیابی عملکرد برجستهای دارد و در لیستهای اصلی در صدر مدلهای متنباز قرار دارد. V3 نسبت به مدل V2.5 سرعت تولید را 3 برابر افزایش داده و تجربه کاربری سریعتر و روانتری را برای کاربران فراهم میکند."
+ },
+ "deepseek/deepseek-chat": {
+ "description": "مدل متنباز جدیدی که تواناییهای عمومی و کدنویسی را ترکیب میکند. این مدل نه تنها توانایی گفتگوی عمومی مدل Chat و قدرت پردازش کد مدل Coder را حفظ کرده است، بلکه به ترجیحات انسانی نیز بهتر همسو شده است. علاوه بر این، DeepSeek-V2.5 در وظایف نوشتاری، پیروی از دستورات و سایر جنبهها نیز بهبودهای قابل توجهی داشته است."
+ },
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 با وجود دادههای برچسبگذاری شده بسیار کم، توانایی استدلال مدل را به طرز چشمگیری افزایش میدهد. قبل از ارائه پاسخ نهایی، مدل ابتدا یک زنجیره تفکر را تولید میکند تا دقت پاسخ نهایی را افزایش دهد."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B یک مدل زبان بزرگ مبتنی بر Llama3.3 70B است که با استفاده از تنظیمات DeepSeek R1 به عملکرد رقابتی معادل مدلهای پیشرفته بزرگ دست یافته است."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B یک مدل زبان بزرگ تقطیر شده مبتنی بر Llama-3.1-8B-Instruct است که با استفاده از خروجی DeepSeek R1 آموزش دیده است."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B یک مدل زبان بزرگ تقطیر شده مبتنی بر Qwen 2.5 14B است که با استفاده از خروجی DeepSeek R1 آموزش دیده است. این مدل در چندین آزمون معیار از o1-mini OpenAI پیشی گرفته و به آخرین دستاوردهای فناوری مدلهای متراکم (dense models) دست یافته است. نتایج برخی از آزمونهای معیار به شرح زیر است:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nاین مدل با تنظیمات خروجی DeepSeek R1، عملکرد رقابتی معادل مدلهای پیشرفته بزرگتر را نشان میدهد."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B یک مدل زبان بزرگ تقطیر شده مبتنی بر Qwen 2.5 32B است که با استفاده از خروجی DeepSeek R1 آموزش دیده است. این مدل در چندین آزمون معیار از o1-mini OpenAI پیشی گرفته و به آخرین دستاوردهای فناوری مدلهای متراکم (dense models) دست یافته است. نتایج برخی از آزمونهای معیار به شرح زیر است:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nاین مدل با تنظیمات خروجی DeepSeek R1، عملکرد رقابتی معادل مدلهای پیشرفته بزرگتر را نشان میدهد."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 جدیدترین مدل متن باز منتشر شده توسط تیم DeepSeek است که دارای عملکرد استدلال بسیار قوی است و به ویژه در وظایف ریاضی، برنامهنویسی و استدلال به سطحی معادل مدل o1 OpenAI رسیده است."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 با وجود دادههای برچسبگذاری شده بسیار کم، توانایی استدلال مدل را به طرز چشمگیری افزایش میدهد. قبل از ارائه پاسخ نهایی، مدل ابتدا یک زنجیره تفکر را تولید میکند تا دقت پاسخ نهایی را افزایش دهد."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 در سرعت استدلال به یک پیشرفت عمده نسبت به مدلهای قبلی دست یافته است. این مدل در بین مدلهای متن باز رتبه اول را دارد و میتواند با پیشرفتهترین مدلهای بسته جهانی رقابت کند. DeepSeek-V3 از معماری توجه چندسر (MLA) و DeepSeekMoE استفاده میکند که این معماریها در DeepSeek-V2 به طور کامل تأیید شدهاند. علاوه بر این، DeepSeek-V3 یک استراتژی کمکی بدون ضرر برای تعادل بار معرفی کرده و اهداف آموزشی پیشبینی چند برچسبی را برای بهبود عملکرد تعیین کرده است."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 در سرعت استدلال به یک پیشرفت عمده نسبت به مدلهای قبلی دست یافته است. این مدل در بین مدلهای متن باز رتبه اول را دارد و میتواند با پیشرفتهترین مدلهای بسته جهانی رقابت کند. DeepSeek-V3 از معماری توجه چندسر (MLA) و DeepSeekMoE استفاده میکند که این معماریها در DeepSeek-V2 به طور کامل تأیید شدهاند. علاوه بر این، DeepSeek-V3 یک استراتژی کمکی بدون ضرر برای تعادل بار معرفی کرده و اهداف آموزشی پیشبینی چند برچسبی را برای بهبود عملکرد تعیین کرده است."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "مدل سبک نسل جدید Doubao-1.5-lite، با سرعت پاسخدهی فوقالعاده، عملکرد و تأخیر در سطح جهانی را ارائه میدهد."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k نسخه ارتقاء یافته Doubao-1.5-Pro است که به طور کلی عملکرد را 10% بهبود میبخشد. از استدلال با پنجره زمینه 256k پشتیبانی میکند و طول خروجی حداکثر 12k توکن را پشتیبانی میکند. عملکرد بالاتر، پنجره بزرگتر و قیمت فوقالعاده، مناسب برای کاربردهای گستردهتر."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "مدل اصلی نسل جدید Doubao-1.5-pro، با ارتقاء کامل عملکرد، در زمینههای دانش، کد، استدلال و غیره عملکرد برجستهای دارد."
+ },
+ "emohaa": {
+ "description": "Emohaa یک مدل روانشناختی است که دارای توانایی مشاوره حرفهای بوده و به کاربران در درک مسائل احساسی کمک میکند."
+ },
+ "ernie-3.5-128k": {
+ "description": "مدل زبان بزرگ پرچمدار خود توسعه یافته توسط بایدو، که شامل حجم وسیعی از متون چینی و انگلیسی است و دارای تواناییهای عمومی قوی است که میتواند نیازهای اکثر موارد پرسش و پاسخ، تولید خلاقانه و کاربردهای افزونه را برآورده کند؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد."
+ },
+ "ernie-3.5-8k": {
+ "description": "مدل زبان بزرگ پرچمدار خود توسعه یافته توسط بایدو، که شامل حجم وسیعی از متون چینی و انگلیسی است و دارای تواناییهای عمومی قوی است که میتواند نیازهای اکثر موارد پرسش و پاسخ، تولید خلاقانه و کاربردهای افزونه را برآورده کند؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "مدل زبان بزرگ پرچمدار خود توسعه یافته توسط بایدو، که شامل حجم وسیعی از متون چینی و انگلیسی است و دارای تواناییهای عمومی قوی است که میتواند نیازهای اکثر موارد پرسش و پاسخ، تولید خلاقانه و کاربردهای افزونه را برآورده کند؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "مدل زبان بزرگ فوقالعاده پرچمدار خود توسعه یافته توسط بایدو، که نسبت به ERNIE 3.5 بهروزرسانیهای جامعتری در تواناییهای مدل داشته و به طور گستردهای در زمینههای مختلف برای وظایف پیچیده کاربرد دارد؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "مدل زبان بزرگ فوقالعاده پرچمدار خود توسعه یافته توسط بایدو، که نسبت به ERNIE 3.5 بهروزرسانیهای جامعتری در تواناییهای مدل داشته و به طور گستردهای در زمینههای مختلف برای وظایف پیچیده کاربرد دارد؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "مدل زبان بزرگ فوقالعاده پرچمدار خود توسعه یافته توسط بایدو، که عملکرد کلی آن بسیار خوب است و به طور گستردهای در زمینههای مختلف برای وظایف پیچیده کاربرد دارد؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد. نسبت به ERNIE 4.0 در عملکرد بهتر است."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "مدل زبان بزرگ فوقالعاده پرچمدار خود توسعه یافته توسط بایدو، که عملکرد کلی آن بسیار خوب است و به طور گستردهای در زمینههای مختلف برای وظایف پیچیده کاربرد دارد؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد. نسبت به ERNIE 4.0 در عملکرد بهتر است."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "مدل زبان بزرگ فوقالعاده پرچمدار خود توسعه یافته توسط بایدو، که عملکرد کلی آن بسیار خوب است و به طور گستردهای در زمینههای مختلف برای وظایف پیچیده کاربرد دارد؛ از اتصال خودکار به افزونه جستجوی بایدو پشتیبانی میکند تا اطلاعات پرسش و پاسخ به روز باشد. نسبت به ERNIE 4.0 در عملکرد بهتر است."
+ },
+ "ernie-char-8k": {
+ "description": "مدل زبان بزرگ با کاربرد خاص که توسط بایدو توسعه یافته است و برای کاربردهایی مانند NPCهای بازی، مکالمات خدمات مشتری، و نقشآفرینی در مکالمات مناسب است، سبک شخصیت آن واضحتر و یکدستتر است و توانایی پیروی از دستورات و عملکرد استدلال بهتری دارد."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "مدل زبان بزرگ با کاربرد خاص که توسط بایدو توسعه یافته است و برای کاربردهایی مانند NPCهای بازی، مکالمات خدمات مشتری، و نقشآفرینی در مکالمات مناسب است، سبک شخصیت آن واضحتر و یکدستتر است و توانایی پیروی از دستورات و عملکرد استدلال بهتری دارد."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite مدل زبان بزرگ سبک خود توسعه یافته توسط بایدو است که تعادل خوبی بین عملکرد مدل و عملکرد استدلال دارد و برای استفاده در کارتهای تسریع AI با توان محاسباتی پایین مناسب است."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "مدل زبان بزرگ سبک خود توسعه یافته توسط بایدو که تعادل خوبی بین عملکرد مدل و عملکرد استدلال دارد و عملکرد بهتری نسبت به ERNIE Lite دارد و برای استفاده در کارتهای تسریع AI با توان محاسباتی پایین مناسب است."
+ },
+ "ernie-novel-8k": {
+ "description": "مدل زبان بزرگ عمومی خود توسعه یافته توسط بایدو که در توانایی ادامه نوشتن رمان مزیت قابل توجهی دارد و همچنین میتواند در صحنههای کوتاهنمایش و فیلمها استفاده شود."
+ },
+ "ernie-speed-128k": {
+ "description": "مدل زبان بزرگ با عملکرد بالا که به تازگی در سال 2024 توسط بایدو منتشر شده است، دارای تواناییهای عمومی عالی است و برای تنظیم دقیق به عنوان مدل پایه مناسب است و میتواند به خوبی مسائل خاص را مدیریت کند و همچنین دارای عملکرد استدلال بسیار خوبی است."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "مدل زبان بزرگ با عملکرد بالا که به تازگی در سال 2024 توسط بایدو منتشر شده است، دارای تواناییهای عمومی عالی است و عملکرد بهتری نسبت به ERNIE Speed دارد و برای تنظیم دقیق به عنوان مدل پایه مناسب است و میتواند به خوبی مسائل خاص را مدیریت کند و همچنین دارای عملکرد استدلال بسیار خوبی است."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny مدل زبان بزرگ با عملکرد فوقالعاده بالا است که هزینههای استقرار و تنظیم آن در بین مدلهای سری Wenxin کمترین است."
+ },
+ "gemini-1.0-pro-001": {
+ "description": "Gemini 1.0 Pro 001 (تنظیم) عملکردی پایدار و قابل تنظیم ارائه میدهد و انتخابی ایدهآل برای راهحلهای وظایف پیچیده است."
+ },
+ "gemini-1.0-pro-002": {
+ "description": "جمینی 1.0 پرو 002 (تنظیم) پشتیبانی چندوجهی عالی ارائه میدهد و بر حل مؤثر وظایف پیچیده تمرکز دارد."
+ },
+ "gemini-1.0-pro-latest": {
+ "description": "Gemini 1.0 Pro مدل هوش مصنوعی با عملکرد بالای Google است که برای گسترش وظایف گسترده طراحی شده است."
+ },
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash جدیدترین مدل هوش مصنوعی چندوجهی گوگل است که دارای قابلیت پردازش سریع بوده و از ورودیهای متنی، تصویری و ویدیویی پشتیبانی میکند و برای گسترش کارآمد در انواع وظایف مناسب است."
+ },
+ "gemini-1.5-flash-001": {
+ "description": "جمینی 1.5 فلش 001 یک مدل چندوجهی کارآمد است که از گسترش کاربردهای گسترده پشتیبانی میکند."
+ },
+ "gemini-1.5-flash-002": {
+ "description": "جمینی 1.5 فلش 002 یک مدل چندوجهی کارآمد است که از گسترش کاربردهای گسترده پشتیبانی میکند."
+ },
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B یک مدل چندرسانهای کارآمد است که از گسترش کاربردهای وسیع پشتیبانی میکند."
+ },
+ "gemini-1.5-flash-8b-exp-0924": {
+ "description": "Gemini 1.5 Flash 8B 0924 جدیدترین مدل آزمایشی است که در موارد استفاده متنی و چندوجهی بهبود عملکرد قابل توجهی دارد."
+ },
+ "gemini-1.5-flash-exp-0827": {
+ "description": "Gemini 1.5 Flash 0827 دارای تواناییهای بهینهشده پردازش چندرسانهای است و مناسب برای انواع سناریوهای پیچیده است."
+ },
+ "gemini-1.5-flash-latest": {
+ "description": "Gemini 1.5 Flash جدیدترین مدل چندوجهی AI گوگل است که دارای قابلیت پردازش سریع بوده و از ورودیهای متن، تصویر و ویدئو پشتیبانی میکند و برای گسترش کارآمد در وظایف مختلف مناسب است."
+ },
+ "gemini-1.5-pro-001": {
+ "description": "Gemini 1.5 Pro 001 یک راهحل هوش مصنوعی چندوجهی قابل گسترش است که از طیف گستردهای از وظایف پیچیده پشتیبانی میکند."
+ },
+ "gemini-1.5-pro-002": {
+ "description": "Gemini 1.5 Pro 002 جدیدترین مدل آماده تولید است که خروجی با کیفیت بالاتری ارائه میدهد و به ویژه در زمینههای ریاضی، متنهای طولانی و وظایف بصری بهبود قابل توجهی دارد."
+ },
+ "gemini-1.5-pro-exp-0801": {
+ "description": "Gemini 1.5 Pro 0801 تواناییهای برجسته پردازش چندرسانهای را ارائه میدهد و انعطافپذیری بیشتری برای توسعه برنامهها به ارمغان میآورد."
+ },
+ "gemini-1.5-pro-exp-0827": {
+ "description": "Gemini 1.5 Pro 0827 با تکنولوژیهای بهینهسازی جدید ترکیب شده و توانایی پردازش دادههای چندرسانهای را بهینه میکند."
+ },
+ "gemini-1.5-pro-latest": {
+ "description": "Gemini 1.5 Pro از حداکثر ۲ میلیون توکن پشتیبانی میکند و انتخابی ایدهآل برای مدلهای چندوجهی متوسط است که برای پشتیبانی از وظایف پیچیده مناسب میباشد."
+ },
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash ویژگیها و بهبودهای نسل بعدی را ارائه میدهد، از جمله سرعت عالی، استفاده از ابزارهای بومی، تولید چندرسانهای و پنجره متن 1M توکن."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash ویژگیها و بهبودهای نسل بعدی را ارائه میدهد، از جمله سرعت عالی، استفاده از ابزارهای بومی، تولید چندرسانهای و پنجره متن 1M توکن."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "مدل متغیر Gemini 2.0 Flash برای بهینهسازی هزینه و تأخیر کم طراحی شده است."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "مدل متغیر Gemini 2.0 Flash برای بهینهسازی هزینه و تأخیر کم طراحی شده است."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "مدل Gemini 2.0 Flash که برای بهینهسازی هزینه و تأخیر کم طراحی شده است."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp جدیدترین مدل AI چندرسانهای آزمایشی گوگل است که دارای ویژگیهای نسل بعدی، سرعت فوقالعاده، فراخوانی ابزار بومی و تولید چندرسانهای است."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp جدیدترین مدل AI چندرسانهای آزمایشی گوگل است که دارای ویژگیهای نسل بعدی، سرعت فوقالعاده، فراخوانی ابزار بومی و تولید چندرسانهای است."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental جدیدترین مدل AI چندرسانهای آزمایشی گوگل است که نسبت به نسخههای قبلی خود بهبود کیفیت قابل توجهی داشته است، به ویژه در زمینه دانش جهانی، کد و متنهای طولانی."
+ },
+ "gemma-7b-it": {
+ "description": "Gemma 7B برای پردازش وظایف کوچک و متوسط مناسب است و از نظر هزینه مؤثر است."
+ },
+ "gemma2": {
+ "description": "Gemma 2 یک مدل کارآمد است که توسط Google ارائه شده و شامل طیف گستردهای از کاربردها از برنامههای کوچک تا پردازش دادههای پیچیده میباشد."
+ },
+ "gemma2-9b-it": {
+ "description": "Gemma 2 9B یک مدل بهینهسازی شده برای وظایف خاص و ادغام ابزارها است."
+ },
+ "gemma2:27b": {
+ "description": "Gemma 2 یک مدل کارآمد از Google است که طیف گستردهای از کاربردها را از برنامههای کوچک تا پردازش دادههای پیچیده پوشش میدهد."
+ },
+ "gemma2:2b": {
+ "description": "Gemma 2 یک مدل کارآمد است که توسط Google ارائه شده و شامل طیف گستردهای از کاربردها از برنامههای کوچک تا پردازش دادههای پیچیده میباشد."
+ },
+ "generalv3": {
+ "description": "Spark Pro یک مدل زبان بزرگ با عملکرد بالا است که برای حوزههای حرفهای بهینهسازی شده است و بر ریاضیات، برنامهنویسی، پزشکی، آموزش و سایر حوزهها تمرکز دارد. این مدل از جستجوی آنلاین و افزونههای داخلی مانند وضعیت آبوهوا و تاریخ پشتیبانی میکند. مدل بهینهشده آن در پرسش و پاسخهای پیچیده، درک زبان و تولید متون سطح بالا عملکرد برجسته و کارآمدی از خود نشان میدهد و انتخابی ایدهآل برای کاربردهای حرفهای است."
+ },
+ "generalv3.5": {
+ "description": "Spark Max جامعترین نسخه است که از جستجوی آنلاین و تعداد زیادی افزونه داخلی پشتیبانی میکند. قابلیتهای هستهای بهینهسازیشده و تنظیمات نقشهای سیستمی و عملکرد فراخوانی توابع، آن را در انواع سناریوهای پیچیده بسیار برجسته و کارآمد میسازد."
+ },
+ "glm-4": {
+ "description": "GLM-4 نسخه قدیمی پرچمدار است که در ژانویه 2024 منتشر شد و اکنون با نسخه قویتر GLM-4-0520 جایگزین شده است."
+ },
+ "glm-4-0520": {
+ "description": "GLM-4-0520 جدیدترین نسخه مدل است که برای وظایف بسیار پیچیده و متنوع طراحی شده و عملکردی عالی دارد."
+ },
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat در زمینههای معنایی، ریاضی، استدلال، کد و دانش عملکرد بالایی از خود نشان میدهد. همچنین دارای قابلیت مرور وب، اجرای کد، تماس با ابزارهای سفارشی و استدلال متنهای طولانی است. از 26 زبان از جمله ژاپنی، کرهای و آلمانی پشتیبانی میکند."
+ },
+ "glm-4-air": {
+ "description": "GLM-4-Air نسخهای با صرفه اقتصادی است که عملکردی نزدیک به GLM-4 دارد و سرعت بالا و قیمت مناسبی را ارائه میدهد."
+ },
+ "glm-4-airx": {
+ "description": "GLM-4-AirX نسخهای کارآمد از GLM-4-Air ارائه میدهد که سرعت استنتاج آن تا ۲.۶ برابر بیشتر است."
+ },
+ "glm-4-alltools": {
+ "description": "GLM-4-AllTools یک مدل چندمنظوره هوشمند است که برای پشتیبانی از برنامهریزی دستورات پیچیده و فراخوانی ابزارها بهینهسازی شده است، مانند مرور وب، تفسیر کد و تولید متن، و برای اجرای چندوظیفهای مناسب است."
+ },
+ "glm-4-flash": {
+ "description": "GLM-4-Flash انتخابی ایدهآل برای انجام وظایف ساده است، سریعترین و رایگان."
+ },
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX نسخه بهبود یافته Flash است که سرعت استنتاج فوقالعاده سریعی دارد."
+ },
+ "glm-4-long": {
+ "description": "GLM-4-Long از ورودیهای متنی بسیار طولانی پشتیبانی میکند و برای وظایف حافظهای و پردازش اسناد بزرگ مناسب است."
+ },
+ "glm-4-plus": {
+ "description": "GLM-4-Plus به عنوان پرچمدار هوشمند پیشرفته، دارای توانایی پردازش متون طولانی و وظایف پیچیده است و عملکرد آن به طور کامل بهبود یافته است."
+ },
+ "glm-4v": {
+ "description": "GLM-4V قابلیتهای قدرتمندی در درک و استدلال تصویری ارائه میدهد و از وظایف مختلف بصری پشتیبانی میکند."
+ },
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash بر روی درک کارآمد تصویر واحد تمرکز دارد و برای سناریوهای تحلیل سریع تصویر، مانند تحلیل تصویر در زمان واقعی یا پردازش دستهای تصاویر مناسب است."
+ },
+ "glm-4v-plus": {
+ "description": "GLM-4V-Plus توانایی درک محتوای ویدئویی و تصاویر متعدد را دارد و برای وظایف چندرسانهای مناسب است."
+ },
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview دارای تواناییهای پیچیده استدلال است و در زمینههای استدلال منطقی، ریاضیات، برنامهنویسی و غیره عملکرد عالی دارد."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash ویژگیها و بهبودهای نسل بعدی را ارائه میدهد، از جمله سرعت عالی، استفاده از ابزارهای بومی، تولید چندرسانهای و پنجره متن 1M توکن."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental جدیدترین مدل AI چندرسانهای آزمایشی گوگل است که نسبت به نسخههای قبلی خود بهبود کیفیت قابل توجهی داشته است، به ویژه در زمینه دانش جهانی، کد و متنهای طولانی."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash قابلیت پردازش چندوجهی بهینهشده را ارائه میدهد و برای انواع سناریوهای پیچیده مناسب است."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro با ترکیب آخرین فناوریهای بهینهسازی، توانایی پردازش دادههای چندحالته را با کارایی بالاتر ارائه میدهد."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 مدل کارآمدی است که توسط Google ارائه شده و شامل طیف وسیعی از کاربردها از برنامههای کوچک تا پردازش دادههای پیچیده است."
+ },
+ "google/gemma-2-27b-it": {
+ "description": "جمما ۲ ادامهدهندهی ایده طراحی سبک و کارآمد است."
+ },
+ "google/gemma-2-2b-it": {
+ "description": "مدل بهینهسازی دستورات سبک گوگل"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 مدل کارآمدی است که توسط Google ارائه شده و شامل طیف وسیعی از کاربردها از برنامههای کوچک تا پردازش دادههای پیچیده است."
+ },
+ "google/gemma-2-9b-it": {
+ "description": "Gemma 2 یک سری مدلهای متنی سبک و متنباز از Google است."
+ },
+ "google/gemma-2-9b-it:free": {
+ "description": "Gemma 2 یک سری مدلهای متن سبک و متنباز از Google است."
+ },
+ "google/gemma-2b-it": {
+ "description": "Gemma Instruct (2B) توانایی پردازش دستورات پایه را فراهم میکند و برای برنامههای سبک مناسب است."
+ },
+ "gpt-3.5-turbo": {
+ "description": "GPT 3.5 توربو، مناسب برای انواع وظایف تولید و درک متن، در حال حاضر به gpt-3.5-turbo-0125 اشاره میکند"
+ },
+ "gpt-3.5-turbo-0125": {
+ "description": "GPT 3.5 توربو، مناسب برای انواع وظایف تولید و درک متن، در حال حاضر به gpt-3.5-turbo-0125 اشاره میکند"
+ },
+ "gpt-3.5-turbo-1106": {
+ "description": "GPT 3.5 توربو، مناسب برای انواع وظایف تولید و درک متن، در حال حاضر به gpt-3.5-turbo-0125 اشاره میکند"
+ },
+ "gpt-3.5-turbo-instruct": {
+ "description": "GPT 3.5 توربو، مناسب برای انواع وظایف تولید و درک متن، در حال حاضر به gpt-3.5-turbo-0125 اشاره میکند"
+ },
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo، مدلی کارآمد از OpenAI، مناسب برای چت و وظایف تولید متن است و از فراخوانی توابع به صورت موازی پشتیبانی میکند."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k، مدل تولید متن با ظرفیت بالا، مناسب برای وظایف پیچیده است."
+ },
+ "gpt-4": {
+ "description": "GPT-4 یک پنجره متنی بزرگتر ارائه میدهد که قادر به پردازش ورودیهای متنی طولانیتر است و برای سناریوهایی که نیاز به ادغام گسترده اطلاعات و تحلیل دادهها دارند، مناسب است."
+ },
+ "gpt-4-0125-preview": {
+ "description": "جدیدترین مدل GPT-4 Turbo دارای قابلیتهای بصری است. اکنون درخواستهای بصری میتوانند از حالت JSON و فراخوانی توابع استفاده کنند. GPT-4 Turbo یک نسخه بهبود یافته است که پشتیبانی مقرونبهصرفهای برای وظایف چندوجهی ارائه میدهد. این مدل بین دقت و کارایی تعادل برقرار میکند و برای سناریوهای کاربردی که نیاز به تعاملات بلادرنگ دارند، مناسب است."
+ },
+ "gpt-4-0613": {
+ "description": "GPT-4 یک پنجره متنی بزرگتر ارائه میدهد که قادر به پردازش ورودیهای متنی طولانیتر است و برای سناریوهایی که نیاز به ادغام گسترده اطلاعات و تحلیل دادهها دارند، مناسب است."
+ },
+ "gpt-4-1106-preview": {
+ "description": "جدیدترین مدل GPT-4 Turbo دارای قابلیتهای بصری است. اکنون درخواستهای بصری میتوانند از حالت JSON و فراخوانی توابع استفاده کنند. GPT-4 Turbo یک نسخه بهبود یافته است که پشتیبانی مقرونبهصرفهای برای وظایف چندوجهی ارائه میدهد. این مدل بین دقت و کارایی تعادل برقرار میکند و برای سناریوهای کاربردی که نیاز به تعاملات بلادرنگ دارند، مناسب است."
+ },
+ "gpt-4-32k": {
+ "description": "GPT-4 یک پنجره متنی بزرگتر ارائه میدهد که قادر به پردازش ورودیهای متنی طولانیتر است و برای سناریوهایی که نیاز به ادغام گسترده اطلاعات و تحلیل دادهها دارند، مناسب است."
+ },
+ "gpt-4-32k-0613": {
+ "description": "GPT-4 یک پنجره متنی بزرگتر ارائه میدهد که قادر به پردازش ورودیهای متنی طولانیتر است و برای سناریوهایی که نیاز به ادغام گسترده اطلاعات و تحلیل دادهها دارند، مناسب است."
+ },
+ "gpt-4-turbo": {
+ "description": "جدیدترین مدل GPT-4 Turbo دارای قابلیتهای بصری است. اکنون درخواستهای بصری میتوانند از حالت JSON و فراخوانی توابع استفاده کنند. GPT-4 Turbo نسخهای بهبود یافته است که پشتیبانی مقرونبهصرفهای برای وظایف چندوجهی ارائه میدهد. این مدل بین دقت و کارایی تعادل برقرار میکند و برای سناریوهای کاربردی که نیاز به تعاملات بلادرنگ دارند، مناسب است."
+ },
+ "gpt-4-turbo-2024-04-09": {
+ "description": "جدیدترین مدل GPT-4 Turbo دارای قابلیتهای بصری است. اکنون درخواستهای بصری میتوانند از حالت JSON و فراخوانی توابع استفاده کنند. GPT-4 Turbo نسخهای بهبود یافته است که پشتیبانی مقرونبهصرفهای برای وظایف چندوجهی ارائه میدهد. این مدل تعادلی بین دقت و کارایی برقرار میکند و برای سناریوهای کاربردی که نیاز به تعاملات بلادرنگ دارند، مناسب است."
+ },
+ "gpt-4-turbo-preview": {
+ "description": "جدیدترین مدل GPT-4 Turbo دارای قابلیتهای بصری است. اکنون درخواستهای بصری میتوانند از حالت JSON و فراخوانی توابع استفاده کنند. GPT-4 Turbo یک نسخه بهبود یافته است که پشتیبانی مقرونبهصرفهای برای وظایف چندرسانهای ارائه میدهد. این مدل بین دقت و کارایی تعادل برقرار میکند و برای سناریوهای کاربردی که نیاز به تعاملات بلادرنگ دارند، مناسب است."
+ },
+ "gpt-4-vision-preview": {
+ "description": "جدیدترین مدل GPT-4 Turbo دارای قابلیتهای بصری است. اکنون درخواستهای بصری میتوانند از حالت JSON و فراخوانی توابع استفاده کنند. GPT-4 Turbo نسخهای پیشرفته است که پشتیبانی مقرونبهصرفهای برای وظایف چندوجهی ارائه میدهد. این مدل بین دقت و کارایی تعادل برقرار میکند و برای سناریوهای کاربردی که نیاز به تعاملات بلادرنگ دارند، مناسب است."
+ },
+ "gpt-4.5-preview": {
+ "description": "نسخه پیشنمایش تحقیقاتی GPT-4.5، بزرگترین و قدرتمندترین مدل GPT ما تا به امروز است. این مدل دارای دانش وسیع جهانی است و میتواند بهتر از قبل نیتهای کاربران را درک کند، که باعث میشود در وظایف خلاقانه و برنامهریزی مستقل عملکرد فوقالعادهای داشته باشد. GPT-4.5 قادر به پذیرش ورودیهای متنی و تصویری است و خروجیهای متنی (شامل خروجیهای ساختاریافته) تولید میکند. از ویژگیهای کلیدی توسعهدهندگان مانند فراخوانی توابع، API دستهای و خروجی جریانی پشتیبانی میکند. در وظایفی که نیاز به تفکر خلاق، تفکر باز و گفتگو دارند (مانند نوشتن، یادگیری یا کاوش ایدههای جدید)، GPT-4.5 بهویژه عملکرد خوبی دارد. تاریخ قطع دانش در اکتبر 2023 است."
+ },
+ "gpt-4o": {
+ "description": "پیشرفتهترین مدل چندوجهی در سری GPT-4 OpenAI که میتواند ورودیهای متنی و تصویری را پردازش کند."
+ },
+ "gpt-4o-2024-05-13": {
+ "description": "ChatGPT-4o یک مدل پویا است که بهصورت زنده بهروزرسانی میشود تا همیشه نسخهی جدید و بهروز باشد. این مدل ترکیبی از تواناییهای قوی در درک و تولید زبان است و برای کاربردهای گسترده مانند خدمات مشتری، آموزش و پشتیبانی فنی مناسب است."
+ },
+ "gpt-4o-2024-08-06": {
+ "description": "ChatGPT-4o یک مدل پویا است که بهصورت لحظهای بهروزرسانی میشود تا همیشه نسخهی جدید و بهروز باشد. این مدل ترکیبی از تواناییهای قوی در درک و تولید زبان است و برای کاربردهای گسترده مانند خدمات مشتری، آموزش و پشتیبانی فنی مناسب است."
+ },
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o یک مدل پویا است که به طور مداوم بهروز رسانی میشود تا نسخه فعلی و جدیدی را حفظ کند. این مدل قدرت فهم و تولید زبان را ترکیب کرده و مناسب برای کاربردهای مقیاس بزرگ مانند خدمات مشتری، آموزش و پشتیبانی فنی است."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "مدل صوتی GPT-4o، پشتیبانی از ورودی و خروجی صوتی."
+ },
+ "gpt-4o-mini": {
+ "description": "یک راهحل هوش مصنوعی مقرونبهصرفه که برای انواع وظایف متنی و تصویری مناسب است."
+ },
+ "gpt-4o-mini-realtime-preview": {
+ "description": "نسخه زنده GPT-4o-mini، پشتیبانی از ورودی و خروجی صوتی و متنی به صورت زنده."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "نسخه زنده GPT-4o، پشتیبانی از ورودی و خروجی صوتی و متنی به صورت زنده."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "نسخه زنده GPT-4o، پشتیبانی از ورودی و خروجی صوتی و متنی به صورت زنده."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "نسخه زنده GPT-4o، پشتیبانی از ورودی و خروجی صوتی و متنی به صورت زنده."
+ },
+ "grok-2-1212": {
+ "description": "این مدل در دقت، پیروی از دستورات و توانایی چند زبانه بهبود یافته است."
+ },
+ "grok-2-vision-1212": {
+ "description": "این مدل در دقت، پیروی از دستورات و توانایی چند زبانه بهبود یافته است."
+ },
+ "grok-beta": {
+ "description": "عملکردی معادل Grok 2 دارد، اما با کارایی، سرعت و قابلیتهای بالاتر."
+ },
+ "grok-vision-beta": {
+ "description": "جدیدترین مدل درک تصویر که میتواند انواع مختلف اطلاعات بصری از جمله اسناد، نمودارها، اسکرینشاتها و عکسها را پردازش کند."
+ },
+ "gryphe/mythomax-l2-13b": {
+ "description": "MythoMax l2 13B یک مدل زبانی است که خلاقیت و هوش را با ترکیب چندین مدل برتر به هم پیوند میدهد."
+ },
+ "hunyuan-code": {
+ "description": "مدل تولید کد جدید Hunyuan، که با استفاده از 200 میلیارد داده کد با کیفیت بالا آموزش داده شده است. این مدل پایه پس از شش ماه آموزش با دادههای SFT با کیفیت بالا بهروزرسانی شده است. طول پنجره متن به ۸ هزار کاراکتر افزایش یافته و در شاخصهای ارزیابی خودکار تولید کد در پنج زبان اصلی در رتبههای برتر قرار دارد. در ارزیابیهای دستی با کیفیت بالا برای ۱۰ معیار مختلف در پنج زبان اصلی، عملکرد این مدل در رده اول قرار دارد."
+ },
+ "hunyuan-functioncall": {
+ "description": "مدل FunctionCall با معماری MOE جدید Hunyuan، آموزشدیده با دادههای باکیفیت FunctionCall، با پنجره متنی تا 32K و پیشرو در چندین شاخص ارزیابی."
+ },
+ "hunyuan-large": {
+ "description": "مدل Hunyuan-large دارای مجموع پارامترها حدود 389B و پارامترهای فعال حدود 52B است، که بزرگترین و بهترین مدل MoE با ساختار Transformer در صنعت به شمار میرود."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "متخصص در پردازش وظایف متنی طولانی مانند خلاصهسازی اسناد و پرسش و پاسخ اسنادی، همچنین توانایی پردازش وظایف تولید متن عمومی را دارد. در تحلیل و تولید متنهای طولانی عملکرد فوقالعادهای دارد و میتواند بهطور مؤثر به نیازهای پیچیده و دقیق پردازش محتوای طولانی پاسخ دهد."
+ },
+ "hunyuan-lite": {
+ "description": "به ساختار MOE ارتقا یافته است، پنجره متنی 256k دارد و در چندین مجموعه ارزیابی در زمینههای NLP، کد، ریاضیات و صنایع از بسیاری از مدلهای متنباز پیشی گرفته است."
+ },
+ "hunyuan-lite-vision": {
+ "description": "مدل چندرسانهای 7B جدید Hunyuan، با پنجره زمینه 32K، از گفتگوی چندرسانهای در صحنههای چینی و انگلیسی، شناسایی اشیاء در تصاویر، درک جداول اسناد و ریاضیات چندرسانهای پشتیبانی میکند و در چندین بعد، معیارهای ارزیابی را نسبت به مدلهای رقیب 7B بهبود میبخشد."
+ },
+ "hunyuan-pro": {
+ "description": "مدل MOE-32K با مقیاس پارامتر تریلیونها. در انواع بنچمارکها به سطح پیشرو مطلق دست یافته است، توانایی پردازش دستورالعملها و استدلالهای پیچیده، دارای قابلیتهای ریاضی پیچیده، پشتیبانی از functioncall، و بهطور ویژه در حوزههای ترجمه چندزبانه، مالی، حقوقی و پزشکی بهینهسازی شده است."
+ },
+ "hunyuan-role": {
+ "description": "جدیدترین مدل نقشآفرینی HunYuan، مدل نقشآفرینی بهدقت تنظیمشده توسط تیم رسمی HunYuan، که بر اساس مدل HunYuan و با استفاده از مجموعه دادههای صحنههای نقشآفرینی آموزش بیشتری دیده است و در صحنههای نقشآفرینی عملکرد بهتری دارد."
+ },
+ "hunyuan-standard": {
+ "description": "استفاده از استراتژی مسیریابی بهینهتر، در حالی که مشکلات توازن بار و همگرایی متخصصان را کاهش میدهد. در زمینه متون طولانی، شاخص «یافتن سوزن در انبار کاه» به ۹۹.۹٪ میرسد. MOE-32K از نظر هزینه و عملکرد نسبتاً بهینهتر است و در عین حال که تعادل بین اثر و قیمت را حفظ میکند، میتواند پردازش ورودیهای متون طولانی را نیز انجام دهد."
+ },
+ "hunyuan-standard-256K": {
+ "description": "با استفاده از استراتژی مسیریابی بهینهتر، در عین حال مشکلات توازن بار و همگرایی کارشناسان را کاهش داده است. در زمینه متون طولانی، شاخص «یافتن سوزن در انبار کاه» به ۹۹.۹٪ رسیده است. MOE-256K در طول و عملکرد پیشرفت بیشتری داشته و به طور قابل توجهی طول ورودی قابل قبول را گسترش داده است."
+ },
+ "hunyuan-standard-vision": {
+ "description": "مدل چندرسانهای جدید Hunyuan، از پاسخگویی به چند زبان پشتیبانی میکند و تواناییهای چینی و انگلیسی را بهطور متوازن ارائه میدهد."
+ },
+ "hunyuan-translation": {
+ "description": "از ۱۵ زبان شامل چینی، انگلیسی، ژاپنی، فرانسوی، پرتغالی، اسپانیایی، ترکی، روسی، عربی، کرهای، ایتالیایی، آلمانی، ویتنامی، مالایی و اندونزیایی پشتیبانی میکند و به طور خودکار با استفاده از مجموعه ارزیابی ترجمه چند صحنهای، امتیاز COMET را ارزیابی میکند. در توانایی ترجمه متقابل در بیش از ده زبان رایج، به طور کلی از مدلهای هممقیاس در بازار برتر است."
+ },
+ "hunyuan-translation-lite": {
+ "description": "مدل ترجمه هویوان از ترجمه گفتگویی زبان طبیعی پشتیبانی میکند؛ از ۱۵ زبان شامل چینی، انگلیسی، ژاپنی، فرانسوی، پرتغالی، اسپانیایی، ترکی، روسی، عربی، کرهای، ایتالیایی، آلمانی، ویتنامی، مالایی و اندونزیایی پشتیبانی میکند."
+ },
+ "hunyuan-turbo": {
+ "description": "نسخه پیشنمایش مدل زبان بزرگ نسل جدید HunYuan که از ساختار مدل متخصص ترکیبی (MoE) جدید استفاده میکند. در مقایسه با hunyuan-pro، کارایی استنتاج سریعتر و عملکرد بهتری دارد."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "نسخه ثابت hunyuan-turbo 20 نوامبر 2024، نسخهای بین hunyuan-turbo و hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "بهینهسازیهای این نسخه: مقیاسدهی دستورات داده، بهطور قابل توجهی توانایی تعمیم عمومی مدل را افزایش میدهد؛ بهطور قابل توجهی تواناییهای ریاضی، کدنویسی و استدلال منطقی را بهبود میبخشد؛ بهینهسازی تواناییهای درک متن و کلمات مرتبط با آن؛ بهینهسازی کیفیت تولید محتوای خلق متن."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "بهینهسازی تجربه عمومی، شامل درک NLP، خلق متن، گپزنی، پرسش و پاسخ دانش، ترجمه و حوزههای مختلف؛ افزایش انساننمایی، بهینهسازی هوش عاطفی مدل؛ افزایش توانایی مدل در روشنسازی فعال زمانی که نیت مبهم است؛ افزایش توانایی پردازش مسائل مربوط به تجزیه و تحلیل کلمات؛ افزایش کیفیت و قابلیت تعامل در خلق محتوا؛ بهبود تجربه چند دور."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "مدل بزرگ زبان بصری نسل جدید Hunyuan، با استفاده از ساختار جدید مدلهای متخصص ترکیبی (MoE)، در تواناییهای مربوط به درک تصویر و متن، خلق محتوا، پرسش و پاسخ دانش و تحلیل استدلال نسبت به مدلهای نسل قبلی بهطور جامع بهبود یافته است."
+ },
+ "hunyuan-vision": {
+ "description": "جدیدترین مدل چندوجهی هونیوان، پشتیبانی از ورودی تصویر + متن برای تولید محتوای متنی."
+ },
+ "internlm/internlm2_5-20b-chat": {
+ "description": "مدل نوآورانه و متنباز InternLM2.5، با استفاده از پارامترهای بزرگ مقیاس، هوش مکالمه را بهبود بخشیده است."
+ },
+ "internlm/internlm2_5-7b-chat": {
+ "description": "InternLM2.5 راهحلهای گفتگوی هوشمند در چندین سناریو ارائه میدهد."
+ },
+ "internlm2-pro-chat": {
+ "description": "مدل قدیمی که هنوز در حال نگهداری است و گزینههای مختلفی از پارامترهای ۷B و ۲۰B را ارائه میدهد."
+ },
+ "internlm2.5-latest": {
+ "description": "جدیدترین سری مدلهای ما با عملکرد استدلال عالی، از طول متن ۱M پشتیبانی میکند و تواناییهای قویتری در پیروی از دستورات و فراخوانی ابزارها دارد."
+ },
+ "internlm3-latest": {
+ "description": "سری جدیدترین مدلهای ما با عملکرد استدلال برجسته، پیشتاز مدلهای متنباز در همان سطح هستند. به طور پیشفرض به جدیدترین مدلهای سری InternLM3 ما اشاره دارد."
+ },
+ "jina-deepsearch-v1": {
+ "description": "جستجوی عمیق ترکیبی از جستجوی اینترنتی، خواندن و استدلال است که میتواند تحقیقات جامع را انجام دهد. میتوانید آن را به عنوان یک نماینده در نظر بگیرید که وظایف تحقیق شما را میپذیرد - این نماینده جستجوی گستردهای انجام میدهد و پس از چندین بار تکرار، پاسخ را ارائه میدهد. این فرآیند شامل تحقیق مداوم، استدلال و حل مسئله از زوایای مختلف است. این با مدلهای بزرگ استاندارد که مستقیماً از دادههای پیشآموزش شده پاسخ تولید میکنند و سیستمهای RAG سنتی که به جستجوی سطحی یکباره وابستهاند، تفاوت اساسی دارد."
+ },
+ "kimi-latest": {
+ "description": "محصول دستیار هوشمند کیمی از جدیدترین مدل بزرگ کیمی استفاده میکند و ممکن است شامل ویژگیهای ناپایدار باشد. از درک تصویر پشتیبانی میکند و بهطور خودکار بر اساس طول متن درخواست، مدلهای 8k/32k/128k را بهعنوان مدل محاسبه انتخاب میکند."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM یک مدل زبانی تجربی و خاص برای وظایف است که برای مطابقت با اصول علم یادگیری آموزش دیده است و میتواند در سناریوهای آموزشی و یادگیری از دستورات سیستم پیروی کند و به عنوان مربی متخصص عمل کند."
+ },
+ "lite": {
+ "description": "Spark Lite یک مدل زبان بزرگ سبک است که دارای تأخیر بسیار کم و توانایی پردازش کارآمد میباشد. بهطور کامل رایگان و باز است و از قابلیت جستجوی آنلاین در زمان واقعی پشتیبانی میکند. ویژگی پاسخدهی سریع آن باعث میشود که در کاربردهای استنتاجی و تنظیم مدل در دستگاههای با توان محاسباتی پایین عملکرد برجستهای داشته باشد و تجربهای هوشمند و مقرونبهصرفه برای کاربران فراهم کند. بهویژه در زمینههای پرسش و پاسخ دانش، تولید محتوا و جستجو عملکرد خوبی دارد."
+ },
+ "llama-3.1-70b-versatile": {
+ "description": "لاما 3.1 70B توانایی استدلال هوش مصنوعی قویتری را ارائه میدهد، مناسب برای برنامههای پیچیده، پشتیبانی از پردازشهای محاسباتی فراوان و تضمین کارایی و دقت بالا."
+ },
+ "llama-3.1-8b-instant": {
+ "description": "Llama 3.1 8B یک مدل با کارایی بالا است که توانایی تولید سریع متن را فراهم میکند و برای کاربردهایی که به بهرهوری و صرفهجویی در هزینه در مقیاس بزرگ نیاز دارند، بسیار مناسب است."
+ },
+ "llama-3.2-11b-vision-instruct": {
+ "description": "توانایی استدلال تصویری عالی در تصاویر با وضوح بالا، مناسب برای برنامههای درک بصری."
+ },
+ "llama-3.2-11b-vision-preview": {
+ "description": "لاما 3.2 برای انجام وظایفی که شامل دادههای بصری و متنی هستند طراحی شده است. این مدل در وظایفی مانند توصیف تصویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "llama-3.2-90b-vision-instruct": {
+ "description": "قابلیتهای پیشرفته استدلال تصویری برای برنامههای نماینده درک بصری."
+ },
+ "llama-3.2-90b-vision-preview": {
+ "description": "لاما 3.2 برای انجام وظایفی که ترکیبی از دادههای بصری و متنی هستند طراحی شده است. این مدل در وظایفی مانند توصیف تصاویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 پیشرفتهترین مدل زبان چندزبانه و متنباز در سری Llama است که تجربهای با هزینه بسیار پایین مشابه عملکرد مدل 405B را ارائه میدهد. این مدل بر اساس ساختار Transformer طراحی شده و از طریق تنظیم دقیق نظارتی (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) بهبود کارایی و ایمنی یافته است. نسخه بهینهسازی شده آن برای مکالمات چندزبانه طراحی شده و در چندین معیار صنعتی از بسیاری از مدلهای چت متنباز و بسته بهتر عمل میکند. تاریخ قطع دانش آن دسامبر 2023 است."
+ },
+ "llama-3.3-70b-versatile": {
+ "description": "مدل زبان بزرگ چند زبانه Meta Llama 3.3 (LLM) یک مدل تولیدی پیشآموزش دیده و تنظیمشده در 70B (ورودی متن/خروجی متن) است. مدل متن خالص Llama 3.3 برای کاربردهای گفتگوی چند زبانه بهینهسازی شده و در معیارهای صنعتی معمول در مقایسه با بسیاری از مدلهای چت متنباز و بسته عملکرد بهتری دارد."
+ },
+ "llama3-70b-8192": {
+ "description": "متا لاما ۳ ۷۰B توانایی پردازش پیچیدگی بینظیری را ارائه میدهد و برای پروژههای با نیازهای بالا طراحی شده است."
+ },
+ "llama3-8b-8192": {
+ "description": "متا لاما ۳ ۸B عملکرد استدلالی با کیفیت بالا را ارائه میدهد و برای نیازهای کاربردی در چندین سناریو مناسب است."
+ },
+ "llama3-groq-70b-8192-tool-use-preview": {
+ "description": "Llama 3 Groq 70B Tool Use قابلیت فراخوانی ابزارهای قدرتمند را فراهم میکند و از پردازش کارهای پیچیده بهصورت کارآمد پشتیبانی میکند."
+ },
+ "llama3-groq-8b-8192-tool-use-preview": {
+ "description": "لاما 3 Groq 8B Tool Use مدلی است که برای استفاده بهینه از ابزارها طراحی شده و از محاسبات سریع و موازی پشتیبانی میکند."
+ },
+ "llama3.1": {
+ "description": "Llama 3.1 مدل پیشرو ارائه شده توسط Meta است که از حداکثر 405 میلیارد پارامتر پشتیبانی میکند و میتواند در زمینههای مکالمات پیچیده، ترجمه چندزبانه و تحلیل دادهها به کار گرفته شود."
+ },
+ "llama3.1:405b": {
+ "description": "Llama 3.1 مدل پیشرو ارائه شده توسط Meta است که از 405 میلیارد پارامتر پشتیبانی میکند و میتواند در زمینههای مکالمات پیچیده، ترجمه چندزبانه و تحلیل دادهها به کار گرفته شود."
+ },
+ "llama3.1:70b": {
+ "description": "لاما 3.1 مدل پیشرو ارائه شده توسط متا است که از حداکثر 405 میلیارد پارامتر پشتیبانی میکند و میتواند در زمینههای مکالمات پیچیده، ترجمه چندزبانه و تحلیل دادهها به کار گرفته شود."
+ },
+ "llava": {
+ "description": "LLaVA یک مدل چندوجهی است که رمزگذار بصری و Vicuna را برای درک قدرتمند زبان و تصویر ترکیب میکند."
+ },
+ "llava-v1.5-7b-4096-preview": {
+ "description": "LLaVA 1.5 7B قابلیت پردازش بصری را با هم ترکیب میکند و از طریق ورودی اطلاعات بصری خروجیهای پیچیده تولید میکند."
+ },
+ "llava:13b": {
+ "description": "LLaVA یک مدل چندوجهی است که رمزگذار بصری و Vicuna را برای درک قدرتمند زبان و تصویر ترکیب میکند."
+ },
+ "llava:34b": {
+ "description": "LLaVA یک مدل چندوجهی است که رمزگذار بصری و Vicuna را برای درک قدرتمند زبان و تصویر ترکیب میکند."
+ },
+ "mathstral": {
+ "description": "MathΣtral بهطور ویژه برای تحقیقات علمی و استدلالهای ریاضی طراحی شده است و توانایی محاسباتی مؤثر و تفسیر نتایج را ارائه میدهد."
+ },
+ "max-32k": {
+ "description": "Spark Max 32K با قابلیت پردازش متن با زمینه بزرگتر، توانایی درک و استدلال منطقی قویتری دارد و از ورودی متنی تا 32K توکن پشتیبانی میکند. مناسب برای خواندن اسناد طولانی، پرسش و پاسخ با دانش خصوصی و موارد مشابه."
+ },
+ "meta-llama-3-70b-instruct": {
+ "description": "یک مدل قدرتمند با ۷۰ میلیارد پارامتر که در استدلال، کدنویسی و کاربردهای گسترده زبانی عملکرد برجستهای دارد."
+ },
+ "meta-llama-3-8b-instruct": {
+ "description": "یک مدل چندمنظوره با ۸ میلیارد پارامتر که برای وظایف مکالمه و تولید متن بهینهسازی شده است."
+ },
+ "meta-llama-3.1-405b-instruct": {
+ "description": "مدل متنی Llama 3.1 که برای تنظیم دستورات بهینهسازی شده و برای موارد استفاده مکالمه چندزبانه بهینه شده است. در بسیاری از مدلهای چت منبع باز و بسته موجود، در معیارهای صنعتی رایج عملکرد برجستهای دارد."
+ },
+ "meta-llama-3.1-70b-instruct": {
+ "description": "مدل متنی Llama 3.1 با تنظیمات دستوری، بهینهسازی شده برای موارد استفاده در مکالمات چندزبانه، که در بسیاری از مدلهای چت منبع باز و بسته موجود، در معیارهای صنعتی رایج عملکرد برجستهای دارد."
+ },
+ "meta-llama-3.1-8b-instruct": {
+ "description": "مدل متنی Llama 3.1 که برای تنظیم دستورالعملها بهینهسازی شده و برای موارد استفاده مکالمه چندزبانه بهینه شده است. در بسیاری از مدلهای چت منبع باز و بسته موجود، در معیارهای صنعتی رایج عملکرد برجستهای دارد."
+ },
+ "meta-llama/Llama-2-13b-chat-hf": {
+ "description": "LLaMA-2 Chat (13B) تواناییهای پردازش زبان عالی و تجربه تعاملی بینظیری را ارائه میدهد."
+ },
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 تواناییهای پردازش زبان عالی و تجربه تعاملی بینظیری را ارائه میدهد."
+ },
+ "meta-llama/Llama-3-70b-chat-hf": {
+ "description": "Llama 3 70B Instruct Reference یک مدل چت قدرتمند است که از نیازهای پیچیده مکالمه پشتیبانی میکند."
+ },
+ "meta-llama/Llama-3-8b-chat-hf": {
+ "description": "Llama 3 8B Instruct Reference پشتیبانی چندزبانه ارائه میدهد و شامل دانش گستردهای در زمینههای مختلف است."
+ },
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 برای انجام وظایفی که ترکیبی از دادههای بصری و متنی هستند طراحی شده است. این مدل در وظایفی مانند توصیف تصویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 برای انجام وظایفی که ترکیبی از دادههای بصری و متنی هستند طراحی شده است. این مدل در وظایفی مانند توصیف تصویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 برای انجام وظایفی که ترکیبی از دادههای بصری و متنی هستند طراحی شده است. این مدل در وظایفی مانند توصیف تصویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 پیشرفتهترین مدل زبان بزرگ چند زبانه متن باز از سری Llama، با هزینه بسیار کم، تجربهای مشابه با عملکرد مدل 405B. بر پایه ساختار Transformer و با بهبود کارایی و ایمنی از طریق تنظیم دقیق نظارتی (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF). نسخه بهینهسازی شده برای دستورالعملها به طور خاص برای مکالمات چند زبانه بهینهسازی شده و در چندین معیار صنعتی بهتر از بسیاری از مدلهای چت متن باز و بسته عمل میکند. تاریخ قطع دانش تا دسامبر 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "مدل بزرگ زبان چند زبانه Meta Llama 3.3 (LLM) یک مدل تولیدی پیشآموزش و تنظیم دستوری در 70B (ورودی متن/خروجی متن) است. مدل تنظیم دستوری Llama 3.3 به طور خاص برای موارد استفاده مکالمه چند زبانه بهینهسازی شده و در معیارهای صنعتی رایج از بسیاری از مدلهای چت متنباز و بسته موجود بهتر عمل میکند."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 برای انجام وظایفی که ترکیبی از دادههای بصری و متنی هستند طراحی شده است. این مدل در وظایفی مانند توصیف تصویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
+ "description": "Llama 3 70B Instruct Lite مناسب برای محیطهایی که به عملکرد بالا و تأخیر کم نیاز دارند."
+ },
+ "meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
+ "description": "Llama 3 70B Instruct Turbo تواناییهای برجستهای در درک و تولید زبان ارائه میدهد و برای سختترین وظایف محاسباتی مناسب است."
+ },
+ "meta-llama/Meta-Llama-3-8B-Instruct-Lite": {
+ "description": "Llama 3 8B Instruct Lite برای محیطهای با منابع محدود مناسب است و عملکرد متعادلی را ارائه میدهد."
+ },
+ "meta-llama/Meta-Llama-3-8B-Instruct-Turbo": {
+ "description": "Llama 3 8B Instruct Turbo یک مدل زبان بزرگ با کارایی بالا است که از طیف گستردهای از کاربردها پشتیبانی میکند."
+ },
+ "meta-llama/Meta-Llama-3.1-405B-Instruct": {
+ "description": "مدل LLaMA 3.1 405B که برای تنظیمات دستوری بهینهسازی شده است، برای سناریوهای مکالمه چندزبانه بهینه شده است."
+ },
+ "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
+ "description": "مدل Llama 3.1 Turbo با ظرفیت 405B، پشتیبانی از زمینههای بسیار بزرگ برای پردازش دادههای عظیم را فراهم میکند و در کاربردهای هوش مصنوعی در مقیاس بسیار بزرگ عملکرد برجستهای دارد."
+ },
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 مدل پیشرو ارائه شده توسط Meta است که از حداکثر 405B پارامتر پشتیبانی میکند و میتواند در زمینههای گفتگوهای پیچیده، ترجمه چند زبانه و تحلیل دادهها استفاده شود."
+ },
+ "meta-llama/Meta-Llama-3.1-70B-Instruct": {
+ "description": "LLaMA 3.1 70B پشتیبانی کارآمد از مکالمات چندزبانه را ارائه میدهد."
+ },
+ "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
+ "description": "مدل Llama 3.1 70B بهطور دقیق تنظیم شده است و برای برنامههای با بار سنگین مناسب است. با کمیتسازی به FP8، توان محاسباتی و دقت بیشتری ارائه میدهد و عملکرد برتری را در سناریوهای پیچیده تضمین میکند."
+ },
+ "meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "LLaMA 3.1 پشتیبانی چندزبانه ارائه میدهد و یکی از مدلهای پیشرو در صنعت تولید محتوا است."
+ },
+ "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
+ "description": "مدل Llama 3.1 8B از کوانتیزاسیون FP8 استفاده میکند و از حداکثر 131,072 توکن متنی پشتیبانی میکند. این مدل یکی از بهترینها در میان مدلهای متنباز است و برای وظایف پیچیده مناسب بوده و در بسیاری از معیارهای صنعتی عملکرد برتری دارد."
+ },
+ "meta-llama/llama-3-70b-instruct": {
+ "description": "Llama 3 70B Instruct برای بهینهسازی در سناریوهای مکالمه با کیفیت بالا طراحی شده و در ارزیابیهای مختلف انسانی عملکرد برجستهای دارد."
+ },
+ "meta-llama/llama-3-8b-instruct": {
+ "description": "Llama 3 8B Instruct برای بهینهسازی سناریوهای مکالمه با کیفیت بالا طراحی شده و عملکردی بهتر از بسیاری از مدلهای بسته دارد."
+ },
+ "meta-llama/llama-3.1-70b-instruct": {
+ "description": "Llama 3.1 70B Instruct بهطور ویژه برای مکالمات با کیفیت بالا طراحی شده است و در ارزیابیهای انسانی عملکرد برجستهای دارد. این مدل بهویژه برای سناریوهای تعامل بالا مناسب است."
+ },
+ "meta-llama/llama-3.1-8b-instruct": {
+ "description": "Llama 3.1 8B Instruct جدیدترین نسخه ارائه شده توسط Meta است که برای بهینهسازی سناریوهای مکالمه با کیفیت بالا طراحی شده و عملکرد بهتری نسبت به بسیاری از مدلهای بسته پیشرو دارد."
+ },
+ "meta-llama/llama-3.1-8b-instruct:free": {
+ "description": "LLaMA 3.1 پشتیبانی چندزبانه ارائه میدهد و یکی از مدلهای پیشرو در صنعت تولید محتوا است."
+ },
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 برای انجام وظایفی که ترکیبی از دادههای بصری و متنی هستند طراحی شده است. این مدل در وظایفی مانند توصیف تصویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 برای انجام وظایفی طراحی شده است که دادههای بصری و متنی را با هم ترکیب میکند. این مدل در وظایفی مانند توصیف تصویر و پرسش و پاسخ بصری عملکرد بسیار خوبی دارد و فاصله بین تولید زبان و استدلال بصری را پر میکند."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 پیشرفتهترین مدل زبان چندزبانه و متنباز در سری Llama است که تجربهای با هزینه بسیار پایین مشابه عملکرد مدل 405B را ارائه میدهد. این مدل بر اساس ساختار Transformer طراحی شده و از طریق تنظیم دقیق نظارتی (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) بهبود کارایی و ایمنی یافته است. نسخه بهینهسازی شده آن برای مکالمات چندزبانه طراحی شده و در چندین معیار صنعتی از بسیاری از مدلهای چت متنباز و بسته بهتر عمل میکند. تاریخ قطع دانش آن دسامبر 2023 است."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 پیشرفتهترین مدل زبان چندزبانه و متنباز در سری Llama است که تجربهای با هزینه بسیار پایین مشابه عملکرد مدل 405B را ارائه میدهد. این مدل بر اساس ساختار Transformer طراحی شده و از طریق تنظیم دقیق نظارتی (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) بهبود کارایی و ایمنی یافته است. نسخه بهینهسازی شده آن برای مکالمات چندزبانه طراحی شده و در چندین معیار صنعتی از بسیاری از مدلهای چت متنباز و بسته بهتر عمل میکند. تاریخ قطع دانش آن دسامبر 2023 است."
+ },
+ "meta.llama3-1-405b-instruct-v1:0": {
+ "description": "Meta Llama 3.1 405B Instruct بزرگترین و قدرتمندترین مدل در میان مدلهای Llama 3.1 Instruct است. این یک مدل بسیار پیشرفته برای استدلال مکالمهای و تولید دادههای مصنوعی است و همچنین میتواند به عنوان پایهای برای پیشتمرین یا تنظیم دقیق مداوم در حوزههای خاص استفاده شود. Llama 3.1 مجموعهای از مدلهای زبان بزرگ چندزبانه (LLMs) است که از پیش آموزش دیده و برای دستورالعملها تنظیم شدهاند و شامل اندازههای 8B، 70B و 405B (ورودی/خروجی متنی) میباشد. مدلهای متنی تنظیمشده بر اساس دستورالعملهای Llama 3.1 (8B، 70B، 405B) بهطور خاص برای موارد استفاده مکالمه چندزبانه بهینهسازی شدهاند و در بسیاری از معیارهای استاندارد صنعتی از مدلهای چت منبع باز موجود پیشی گرفتهاند. Llama 3.1 برای استفادههای تجاری و تحقیقاتی در زبانهای مختلف طراحی شده است. مدلهای متنی تنظیمشده بر اساس دستورالعملها برای چتهای مشابه دستیار مناسب هستند، در حالی که مدلهای پیشآموزشدیده میتوانند برای انواع وظایف تولید زبان طبیعی سازگار شوند. مدلهای Llama 3.1 همچنین از خروجیهای خود برای بهبود سایر مدلها، از جمله تولید دادههای مصنوعی و پالایش، پشتیبانی میکنند. Llama 3.1 یک مدل زبان خودبازگشتی است که از معماری بهینهشده ترانسفورمر استفاده میکند. نسخههای تنظیمشده از تنظیم دقیق نظارتشده (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) برای تطابق با ترجیحات انسانی در مورد کمکرسانی و ایمنی استفاده میکنند."
+ },
+ "meta.llama3-1-70b-instruct-v1:0": {
+ "description": "نسخه بهروزرسانیشده Meta Llama 3.1 70B Instruct، شامل طول زمینه 128K توسعهیافته، چندزبانه بودن و بهبود توانایی استدلال. مدلهای زبان بزرگ چندزبانه (LLMs) ارائهشده توسط Llama 3.1 مجموعهای از مدلهای تولیدی پیشتمرینشده و تنظیمشده با دستورالعمل هستند که شامل اندازههای 8B، 70B و 405B (ورودی/خروجی متنی) میباشند. مدلهای متنی تنظیمشده با دستورالعمل Llama 3.1 (8B، 70B، 405B) بهطور خاص برای موارد استفاده مکالمه چندزبانه بهینهسازی شدهاند و در بسیاری از معیارهای استاندارد صنعتی از مدلهای چت منبعباز موجود پیشی گرفتهاند. Llama 3.1 برای استفادههای تجاری و تحقیقاتی در زبانهای مختلف طراحی شده است. مدلهای متنی تنظیمشده با دستورالعمل برای چتهای مشابه دستیار مناسب هستند، در حالی که مدلهای پیشتمرینشده میتوانند برای انواع وظایف تولید زبان طبیعی سازگار شوند. مدلهای Llama 3.1 همچنین از خروجیهای خود برای بهبود سایر مدلها، از جمله تولید دادههای مصنوعی و پالایش، پشتیبانی میکنند. Llama 3.1 یک مدل زبان خودبازگشتی است که از معماری بهینهشده ترانسفورمر استفاده میکند. نسخه تنظیمشده از تنظیم دقیق نظارتشده (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) برای همراستایی با ترجیحات انسانی در مورد کمکرسانی و ایمنی استفاده میکند."
+ },
+ "meta.llama3-1-8b-instruct-v1:0": {
+ "description": "نسخه بهروزرسانی شده Meta Llama 3.1 8B Instruct، شامل طول زمینه 128K توسعهیافته، چندزبانه بودن و بهبود توانایی استدلال. Llama 3.1 مدلهای زبانی بزرگ چندزبانه (LLMs) را ارائه میدهد که مجموعهای از مدلهای تولیدی پیشتمرینشده و تنظیمشده با دستورالعمل هستند و شامل اندازههای 8B، 70B و 405B (ورودی/خروجی متنی) میباشند. مدلهای متنی تنظیمشده با دستورالعمل Llama 3.1 (8B، 70B، 405B) بهطور خاص برای موارد استفاده مکالمه چندزبانه بهینهسازی شدهاند و در معیارهای صنعتی رایج از بسیاری از مدلهای چت متنباز موجود پیشی گرفتهاند. Llama 3.1 برای استفادههای تجاری و تحقیقاتی در زبانهای مختلف طراحی شده است. مدلهای متنی تنظیمشده با دستورالعمل برای چتهای مشابه دستیار مناسب هستند، در حالی که مدلهای پیشتمرینشده میتوانند برای انواع وظایف تولید زبان طبیعی سازگار شوند. مدلهای Llama 3.1 همچنین از خروجیهای خود برای بهبود سایر مدلها، از جمله تولید دادههای مصنوعی و پالایش، پشتیبانی میکنند. Llama 3.1 یک مدل زبانی خودبازگشتی است که از معماری بهینهشده ترانسفورمر استفاده میکند. نسخه تنظیمشده از تنظیم دقیق نظارتشده (SFT) و یادگیری تقویتی با بازخورد انسانی (RLHF) برای همراستا شدن با ترجیحات انسانی در مورد کمکرسانی و ایمنی استفاده میکند."
+ },
+ "meta.llama3-70b-instruct-v1:0": {
+ "description": "Meta Llama 3 یک مدل زبان بزرگ (LLM) باز برای توسعهدهندگان، پژوهشگران و شرکتها است که به آنها کمک میکند تا ایدههای هوش مصنوعی تولیدی خود را بسازند، آزمایش کنند و بهطور مسئولانه گسترش دهند. بهعنوان بخشی از سیستم پایه نوآوری جامعه جهانی، این مدل برای تولید محتوا، هوش مصنوعی مکالمهای، درک زبان، تحقیق و توسعه و کاربردهای شرکتی بسیار مناسب است."
+ },
+ "meta.llama3-8b-instruct-v1:0": {
+ "description": "Meta Llama 3 یک مدل زبان بزرگ باز (LLM) است که برای توسعهدهندگان، پژوهشگران و شرکتها طراحی شده است تا به آنها در ساخت، آزمایش و گسترش مسئولانه ایدههای هوش مصنوعی مولد کمک کند. به عنوان بخشی از سیستم پایه نوآوری جامعه جهانی، این مدل برای دستگاههای با توان محاسباتی و منابع محدود، دستگاههای لبه و زمانهای آموزش سریعتر بسیار مناسب است."
+ },
+ "meta/llama-3.1-405b-instruct": {
+ "description": "مدل LLM پیشرفته که از تولید دادههای ترکیبی، تقطیر دانش و استدلال پشتیبانی میکند و برای رباتهای چت، برنامهنویسی و وظایف خاص مناسب است."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "توانمندسازی گفتگوهای پیچیده با درک زمینهای عالی، توانایی استدلال و قابلیت تولید متن."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "مدل پیشرفته و پیشرفته که دارای درک زبان، توانایی استدلال عالی و قابلیت تولید متن است."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "مدل بینایی-زبان پیشرفته که در استدلال با کیفیت بالا از تصاویر مهارت دارد."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "مدل زبان کوچک پیشرفته و پیشرفته که دارای درک زبان، توانایی استدلال عالی و قابلیت تولید متن است."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "مدل زبان کوچک پیشرفته و پیشرفته که دارای درک زبان، توانایی استدلال عالی و قابلیت تولید متن است."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "مدل بینایی-زبان پیشرفته که در استدلال با کیفیت بالا از تصاویر مهارت دارد."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "مدل LLM پیشرفته که در استدلال، ریاضیات، دانش عمومی و فراخوانی توابع مهارت دارد."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 یک مدل زبانی است که توسط AI مایکروسافت ارائه شده و در زمینههای گفتگوی پیچیده، چند زبانه، استدلال و دستیار هوشمند به ویژه عملکرد خوبی دارد."
+ },
+ "microsoft/wizardlm-2-8x22b": {
+ "description": "WizardLM-2 8x22B پیشرفتهترین مدل Wizard از مایکروسافت AI است که عملکردی بسیار رقابتی از خود نشان میدهد."
+ },
+ "minicpm-v": {
+ "description": "MiniCPM-V نسل جدید مدل چندوجهی است که توسط OpenBMB ارائه شده و دارای تواناییهای برجسته در تشخیص OCR و درک چندوجهی است و از طیف گستردهای از کاربردها پشتیبانی میکند."
+ },
+ "ministral-3b-latest": {
+ "description": "Ministral 3B مدل پیشرفته و برتر Mistral در سطح جهانی است."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B یک مدل لبهای با صرفه اقتصادی بالا از Mistral است."
+ },
+ "mistral": {
+ "description": "Mistral یک مدل 7B است که توسط Mistral AI منتشر شده و برای نیازهای متنوع پردازش زبان مناسب است."
+ },
+ "mistral-large": {
+ "description": "Mixtral Large مدل پرچمدار Mistral است که توانایی تولید کد، ریاضیات و استدلال را ترکیب میکند و از پنجره متنی ۱۲۸k پشتیبانی میکند."
+ },
+ "mistral-large-latest": {
+ "description": "Mistral Large یک مدل بزرگ پرچمدار است که در انجام وظایف چندزبانه، استدلال پیچیده و تولید کد مهارت دارد و انتخابی ایدهآل برای کاربردهای سطح بالا است."
+ },
+ "mistral-nemo": {
+ "description": "Mistral Nemo توسط Mistral AI و NVIDIA بهطور مشترک عرضه شده است و یک مدل ۱۲ میلیاردی با کارایی بالا میباشد."
+ },
+ "mistral-small": {
+ "description": "Mistral Small میتواند برای هر وظیفهای که نیاز به کارایی بالا و تأخیر کم دارد، مبتنی بر زبان استفاده شود."
+ },
+ "mistral-small-latest": {
+ "description": "Mistral Small یک گزینه مقرونبهصرفه، سریع و قابلاعتماد است که برای موارد استفادهای مانند ترجمه، خلاصهسازی و تحلیل احساسات مناسب است."
+ },
+ "mistralai/Mistral-7B-Instruct-v0.1": {
+ "description": "Mistral (7B) Instruct به دلیل عملکرد بالا شناخته شده است و برای وظایف مختلف زبانی مناسب است."
+ },
+ "mistralai/Mistral-7B-Instruct-v0.2": {
+ "description": "مدل تنظیم دستور Mistral AI"
+ },
+ "mistralai/Mistral-7B-Instruct-v0.3": {
+ "description": "Mistral (7B) Instruct v0.3 توانایی محاسباتی بالا و درک زبان طبیعی را ارائه میدهد و برای کاربردهای گسترده مناسب است."
+ },
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B یک مدل فشرده اما با عملکرد بالا است که در پردازش دستهای و وظایف ساده مانند طبقهبندی و تولید متن مهارت دارد و دارای توانایی استدلال خوبی است."
+ },
+ "mistralai/Mixtral-8x22B-Instruct-v0.1": {
+ "description": "Mixtral-8x22B Instruct (141B) یک مدل زبان بسیار بزرگ است که از نیازهای پردازشی بسیار بالا پشتیبانی میکند."
+ },
+ "mistralai/Mixtral-8x7B-Instruct-v0.1": {
+ "description": "Mixtral-8x7B Instruct (46.7B) یک چارچوب محاسباتی با ظرفیت بالا ارائه میدهد که برای پردازش دادههای بزرگ مقیاس مناسب است."
+ },
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B یک مدل متخصص پراکنده است که با استفاده از پارامترهای متعدد سرعت استنتاج را افزایش میدهد و برای انجام وظایف چندزبانه و تولید کد مناسب است."
+ },
+ "mistralai/mistral-7b-instruct": {
+ "description": "Mistral 7B Instruct یک مدل استاندارد صنعتی با عملکرد بالا است که بهینهسازی سرعت و پشتیبانی از متن طولانی را ترکیب میکند."
+ },
+ "mistralai/mistral-nemo": {
+ "description": "Mistral Nemo یک مدل با 7.3 میلیارد پارامتر است که از برنامهنویسی با عملکرد بالا و پشتیبانی چندزبانه برخوردار است."
+ },
+ "mixtral": {
+ "description": "Mixtral مدل تخصصی Mistral AI است که دارای وزنهای متنباز بوده و در زمینه تولید کد و درک زبان پشتیبانی ارائه میدهد."
+ },
+ "mixtral-8x7b-32768": {
+ "description": "Mixtral 8x7B قابلیت محاسبات موازی با تحمل خطای بالا را ارائه میدهد و برای وظایف پیچیده مناسب است."
+ },
+ "mixtral:8x22b": {
+ "description": "Mixtral مدل تخصصی Mistral AI است که دارای وزنهای متنباز بوده و در تولید کد و درک زبان پشتیبانی ارائه میدهد."
+ },
+ "moonshot-v1-128k": {
+ "description": "Moonshot V1 128K یک مدل با قابلیت پردازش متن طولانی است که برای تولید متون بسیار طولانی مناسب است. این مدل میتواند تا 128,000 توکن را پردازش کند و برای کاربردهایی مانند پژوهش، علمی و تولید اسناد بزرگ بسیار مناسب است."
+ },
+ "moonshot-v1-128k-vision-preview": {
+ "description": "مدل بصری Kimi (شامل moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview و غیره) قادر به درک محتوای تصویر است، از جمله متن تصویر، رنگ تصویر و شکل اشیاء."
+ },
+ "moonshot-v1-32k": {
+ "description": "Moonshot V1 32K توانایی پردازش متن با طول متوسط را فراهم میکند و قادر به پردازش 32,768 توکن است. این مدل بهویژه برای تولید اسناد طولانی و مکالمات پیچیده مناسب است و در زمینههایی مانند تولید محتوا، ایجاد گزارش و سیستمهای مکالمه کاربرد دارد."
+ },
+ "moonshot-v1-32k-vision-preview": {
+ "description": "مدل بصری Kimi (شامل moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview و غیره) قادر به درک محتوای تصویر است، از جمله متن تصویر، رنگ تصویر و شکل اشیاء."
+ },
+ "moonshot-v1-8k": {
+ "description": "Moonshot V1 8K بهطور ویژه برای تولید متنهای کوتاه طراحی شده است و دارای عملکرد پردازشی کارآمدی است که میتواند ۸,۱۹۲ توکن را پردازش کند. این مدل برای مکالمات کوتاه، یادداشتبرداری سریع و تولید محتوای سریع بسیار مناسب است."
+ },
+ "moonshot-v1-8k-vision-preview": {
+ "description": "مدل بصری Kimi (شامل moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview و غیره) قادر به درک محتوای تصویر است، از جمله متن تصویر، رنگ تصویر و شکل اشیاء."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto میتواند بر اساس تعداد توکنهای اشغال شده در متن فعلی، مدل مناسب را انتخاب کند."
+ },
+ "nousresearch/hermes-2-pro-llama-3-8b": {
+ "description": "هرمس ۲ پرو لاما ۳ ۸B نسخه ارتقاء یافته Nous Hermes 2 است که شامل جدیدترین مجموعه دادههای توسعهیافته داخلی میباشد."
+ },
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B یک مدل زبانی بزرگ سفارشی شده توسط NVIDIA است که به منظور افزایش کمک به پاسخهای تولید شده توسط LLM برای پرسشهای کاربران طراحی شده است. این مدل در آزمونهای معیار مانند Arena Hard، AlpacaEval 2 LC و GPT-4-Turbo MT-Bench عملکرد عالی داشته و تا تاریخ 1 اکتبر 2024 در تمامی سه آزمون خودکار همراستایی در رتبه اول قرار دارد. این مدل با استفاده از RLHF (به ویژه REINFORCE)، Llama-3.1-Nemotron-70B-Reward و HelpSteer2-Preference در مدل Llama-3.1-70B-Instruct آموزش دیده است."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "مدل زبان منحصر به فرد که دقت و کارایی بینظیری را ارائه میدهد."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B یک مدل زبان بزرگ سفارشی از NVIDIA است که به منظور افزایش کمکپذیری پاسخهای تولید شده توسط LLM طراحی شده است."
+ },
+ "o1": {
+ "description": "متمرکز بر استدلال پیشرفته و حل مسائل پیچیده، از جمله وظایف ریاضی و علمی. بسیار مناسب برای برنامههایی که به درک عمیق زمینه و مدیریت جریانهای کاری نیاز دارند."
+ },
+ "o1-mini": {
+ "description": "کوچکتر و سریعتر از o1-preview، با ۸۰٪ هزینه کمتر، و عملکرد خوب در تولید کد و عملیات با زمینههای کوچک."
+ },
+ "o1-preview": {
+ "description": "تمرکز بر استدلال پیشرفته و حل مسائل پیچیده، از جمله وظایف ریاضی و علمی. بسیار مناسب برای برنامههایی که نیاز به درک عمیق از زمینه و جریان کاری خودمختار دارند."
+ },
+ "o3-mini": {
+ "description": "o3-mini جدیدترین مدل استنتاج کوچک ماست که هوش بالایی را با هزینه و هدف تأخیر مشابه o1-mini ارائه میدهد."
+ },
+ "open-codestral-mamba": {
+ "description": "Codestral Mamba یک مدل زبان Mamba 2 است که بر تولید کد تمرکز دارد و پشتیبانی قدرتمندی برای وظایف پیشرفته کدنویسی و استدلال ارائه میدهد."
+ },
+ "open-mistral-7b": {
+ "description": "Mistral 7B یک مدل فشرده اما با عملکرد بالا است که در پردازش دستهای و وظایف ساده مانند طبقهبندی و تولید متن مهارت دارد و دارای توانایی استدلال خوبی است."
+ },
+ "open-mistral-nemo": {
+ "description": "Mistral Nemo یک مدل 12 میلیاردی است که با همکاری Nvidia توسعه یافته و عملکرد عالی در استدلال و کدنویسی ارائه میدهد و به راحتی قابل ادغام و جایگزینی است."
+ },
+ "open-mixtral-8x22b": {
+ "description": "Mixtral 8x22B یک مدل تخصصی بزرگتر است که بر روی وظایف پیچیده تمرکز دارد و توانایی استدلال عالی و توان عملیاتی بالاتری را ارائه میدهد."
+ },
+ "open-mixtral-8x7b": {
+ "description": "Mixtral 8x7B یک مدل متخصص پراکنده است که با استفاده از پارامترهای متعدد سرعت استنتاج را افزایش میدهد و برای پردازش وظایف چندزبانه و تولید کد مناسب است."
+ },
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o یک مدل پویا است که بهصورت زنده بهروزرسانی میشود تا همیشه نسخهی جدید و بهروز باشد. این مدل ترکیبی از تواناییهای قدرتمند درک و تولید زبان را ارائه میدهد و برای کاربردهای گسترده مانند خدمات مشتری، آموزش و پشتیبانی فنی مناسب است."
+ },
+ "openai/gpt-4o-mini": {
+ "description": "GPT-4o mini جدیدترین مدل OpenAI است که پس از GPT-4 Omni عرضه شده و از ورودیهای تصویری و متنی پشتیبانی میکند و خروجی متنی ارائه میدهد. به عنوان پیشرفتهترین مدل کوچک آنها، این مدل بسیار ارزانتر از سایر مدلهای پیشرفته اخیر است و بیش از ۶۰٪ ارزانتر از GPT-3.5 Turbo میباشد. این مدل هوشمندی پیشرفته را حفظ کرده و در عین حال از نظر اقتصادی بسیار مقرون به صرفه است. GPT-4o mini در آزمون MMLU امتیاز ۸۲٪ را کسب کرده و در حال حاضر در ترجیحات چت بالاتر از GPT-4 رتبهبندی شده است."
+ },
+ "openai/o1-mini": {
+ "description": "o1-mini یک مدل استنتاج سریع و مقرونبهصرفه است که برای برنامهنویسی، ریاضیات و کاربردهای علمی طراحی شده است. این مدل دارای ۱۲۸ هزار بایت زمینه و تاریخ قطع دانش تا اکتبر ۲۰۲۳ میباشد."
+ },
+ "openai/o1-preview": {
+ "description": "o1 مدل جدید استنتاج OpenAI است که برای وظایف پیچیدهای که به دانش عمومی گسترده نیاز دارند، مناسب است. این مدل دارای 128K زمینه و تاریخ قطع دانش تا اکتبر 2023 است."
+ },
+ "openchat/openchat-7b": {
+ "description": "OpenChat 7B یک کتابخانه مدل زبان متنباز است که با استفاده از استراتژی «C-RLFT (تنظیم دقیق یادگیری تقویتی شرطی)» بهطور خاص تنظیم شده است."
+ },
+ "openrouter/auto": {
+ "description": "با توجه به طول متن، موضوع و پیچیدگی، درخواست شما به Llama 3 70B Instruct، Claude 3.5 Sonnet (تنظیم خودکار) یا GPT-4o ارسال خواهد شد."
+ },
+ "phi3": {
+ "description": "Phi-3 یک مدل سبک و باز از مایکروسافت است که برای یکپارچهسازی کارآمد و استدلال دانش در مقیاس بزرگ مناسب است."
+ },
+ "phi3:14b": {
+ "description": "Phi-3 یک مدل سبک و باز از مایکروسافت است که برای یکپارچهسازی کارآمد و استدلال دانش در مقیاس بزرگ طراحی شده است."
+ },
+ "pixtral-12b-2409": {
+ "description": "مدل Pixtral در وظایفی مانند نمودار و درک تصویر، پرسش و پاسخ اسناد، استدلال چندوجهی و پیروی از دستورات، تواناییهای قدرتمندی از خود نشان میدهد. این مدل قادر است تصاویر را با وضوح طبیعی و نسبت ابعاد دریافت کند و همچنین میتواند هر تعداد تصویری را در یک پنجره متنی طولانی تا ۱۲۸ هزار توکن پردازش کند."
+ },
+ "pixtral-large-latest": {
+ "description": "Pixtral Large یک مدل چندرسانهای متنباز با ۱۲۴۰ میلیارد پارامتر است که بر اساس Mistral Large 2 ساخته شده است. این دومین مدل در خانواده چندرسانهای ماست که تواناییهای پیشرفتهای در درک تصویر را به نمایش میگذارد."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K با قابلیت پردازش متن بسیار بزرگ، قادر به پردازش تا 128K اطلاعات متنی است. این ویژگی بهویژه برای تحلیل کامل و پردازش ارتباطات منطقی طولانیمدت در محتوای متنی طولانی مناسب است و میتواند در ارتباطات متنی پیچیده، پشتیبانی از منطق روان و یکپارچه و ارجاعات متنوع را فراهم کند."
+ },
+ "qvq-72b-preview": {
+ "description": "مدل QVQ یک مدل تحقیقاتی تجربی است که توسط تیم Qwen توسعه یافته و بر بهبود توانایی استدلال بصری، بهویژه در زمینه استدلال ریاضی تمرکز دارد."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "مدل کد Qwen با قابلیتهای جامع."
+ },
+ "qwen-coder-turbo-latest": {
+ "description": "مدل کدنویسی تونگی چیانون."
+ },
+ "qwen-long": {
+ "description": "مدل زبانی بسیار بزرگ Tongyi Qianwen که از متنهای طولانی و همچنین قابلیت مکالمه در چندین سناریو مانند اسناد طولانی و چندین سند پشتیبانی میکند."
+ },
+ "qwen-math-plus-latest": {
+ "description": "مدل ریاضی Qwen یک مدل زبانی است که به طور خاص برای حل مسائل ریاضی طراحی شده است."
+ },
+ "qwen-math-turbo-latest": {
+ "description": "مدل ریاضی Qwen Math Turbo یک مدل زبانی است که به طور خاص برای حل مسائل ریاضی طراحی شده است."
+ },
+ "qwen-max": {
+ "description": "مدل زبان بسیار بزرگ و با ظرفیت Qwen با توانایی پشتیبانی از ورودی زبانهای مختلف مانند چینی و انگلیسی، در حال حاضر مدل API پشت نسخه محصول Qwen 2.5 است."
+ },
+ "qwen-max-latest": {
+ "description": "مدل زبانی بسیار بزرگ با مقیاس میلیاردی تونگی چیانون، که از ورودیهای زبانهای مختلف مانند چینی، انگلیسی و غیره پشتیبانی میکند. مدل API پشت نسخه محصول تونگی چیانون 2.5 فعلی."
+ },
+ "qwen-omni-turbo-latest": {
+ "description": "مدلهای سری Qwen-Omni از ورودی دادههای چندگانه شامل ویدیو، صدا، تصویر و متن پشتیبانی میکنند و خروجیهای صوتی و متنی تولید میکنند."
+ },
+ "qwen-plus": {
+ "description": "مدل زبان بسیار بزرگ Qwen در نسخه تقویت شده، از ورودی زبانهای مختلف مانند چینی و انگلیسی پشتیبانی میکند."
+ },
+ "qwen-plus-latest": {
+ "description": "نسخه تقویتشده مدل زبانی بسیار بزرگ Tongyi Qianwen، پشتیبانی از ورودی به زبانهای چینی، انگلیسی و سایر زبانها."
+ },
+ "qwen-turbo": {
+ "description": "مدل زبان بسیار بزرگ Qwen، از ورودی زبانهای مختلف مانند چینی و انگلیسی پشتیبانی میکند."
+ },
+ "qwen-turbo-latest": {
+ "description": "مدل زبانی بسیار بزرگ Tongyi Qianwen که از ورودیهای زبانهای مختلف مانند چینی، انگلیسی و غیره پشتیبانی میکند."
+ },
+ "qwen-vl-chat-v1": {
+ "description": "مدل Qwen-VL از روشهای تعاملی انعطافپذیر پشتیبانی میکند، از جمله قابلیتهای چندتصویری، پرسش و پاسخ چندمرحلهای و خلاقیت."
+ },
+ "qwen-vl-max-latest": {
+ "description": "مدل زبان بصری فوقالعاده بزرگ Qwen-VL. در مقایسه با نسخه تقویتشده، توانایی استدلال بصری و پیروی از دستورات را دوباره بهبود میبخشد و سطح بالاتری از ادراک و شناخت بصری را ارائه میدهد."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "مدل OCR Qwen برای استخراج متن، بر روی توانایی استخراج متن از انواع تصاویر مانند اسناد، جداول، سوالات و متنهای دستنویس تمرکز دارد. این مدل قادر به شناسایی انواع مختلف متون است و زبانهای پشتیبانی شده شامل: چینی، انگلیسی، فرانسوی، ژاپنی، کرهای، آلمانی، روسی، ایتالیایی، ویتنامی و عربی میباشد."
+ },
+ "qwen-vl-plus-latest": {
+ "description": "نسخه تقویتشده مدل زبان تصویری بزرگ تونگی چیانون. بهبود قابل توجه در توانایی تشخیص جزئیات و شناسایی متن، پشتیبانی از وضوح بیش از یک میلیون پیکسل و تصاویر با هر نسبت طول به عرض."
+ },
+ "qwen-vl-v1": {
+ "description": "مدل زبان Qwen-7B با اضافه کردن مدل تصویر و وضوح ورودی تصویر 448، به عنوان یک مدل پیشآموزششده، اولیهسازی شده است."
+ },
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 یک سری جدید از مدلهای زبان بزرگ Qwen است. Qwen2 7B یک مدل مبتنی بر ترنسفورمر است که در درک زبان، قابلیتهای چند زبانه، برنامهنویسی، ریاضی و استدلال عملکرد عالی دارد."
+ },
+ "qwen/qwen-2-7b-instruct:free": {
+ "description": "Qwen2 یک سری جدید از مدلهای زبان بزرگ است که دارای تواناییهای درک و تولید قویتری میباشد."
+ },
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL جدیدترین نسخه از مدل Qwen-VL است که در آزمونهای معیار درک بصری به عملکرد پیشرفتهای دست یافته است، از جمله MathVista، DocVQA، RealWorldQA و MTVQA. Qwen2-VL قادر به درک ویدیوهای بیش از 20 دقیقه است و برای پرسش و پاسخ، گفتگو و تولید محتوا مبتنی بر ویدیو با کیفیت بالا استفاده میشود. این مدل همچنین دارای قابلیتهای پیچیده استدلال و تصمیمگیری است و میتواند با دستگاههای موبایل، رباتها و غیره ادغام شود و بر اساس محیط بصری و دستورات متنی به طور خودکار عمل کند. علاوه بر انگلیسی و چینی، Qwen2-VL اکنون از درک متنهای مختلف زبان در تصاویر نیز پشتیبانی میکند، از جمله بیشتر زبانهای اروپایی، ژاپنی، کرهای، عربی و ویتنامی."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct یکی از جدیدترین سری مدلهای زبان بزرگ منتشر شده توسط Alibaba Cloud است. این مدل 72B در زمینههای کدنویسی و ریاضی دارای قابلیتهای بهبود یافته قابل توجهی است. این مدل همچنین از چندین زبان پشتیبانی میکند و بیش از 29 زبان از جمله چینی و انگلیسی را پوشش میدهد. این مدل در پیروی از دستورات، درک دادههای ساختاری و تولید خروجیهای ساختاری (به ویژه JSON) بهبودهای قابل توجهی داشته است."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct یکی از جدیدترین سری مدلهای زبان بزرگ منتشر شده توسط Alibaba Cloud است. این مدل 32B در زمینههای کدنویسی و ریاضی دارای قابلیتهای بهبود یافته قابل توجهی است. این مدل از چندین زبان پشتیبانی میکند و بیش از 29 زبان از جمله چینی و انگلیسی را پوشش میدهد. این مدل در پیروی از دستورات، درک دادههای ساختاری و تولید خروجیهای ساختاری (به ویژه JSON) بهبودهای قابل توجهی داشته است."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "مدل LLM برای زبانهای چینی و انگلیسی که در زمینههای زبان، برنامهنویسی، ریاضیات و استدلال تخصص دارد."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "مدل LLM پیشرفته که از تولید کد، استدلال و اصلاح پشتیبانی میکند و شامل زبانهای برنامهنویسی اصلی است."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "مدل کد قدرتمند و متوسط که از طول زمینه 32K پشتیبانی میکند و در برنامهنویسی چند زبانه مهارت دارد."
+ },
+ "qwen2": {
+ "description": "Qwen2 مدل زبان بزرگ نسل جدید علیبابا است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwen2.5": {
+ "description": "Qwen2.5 نسل جدید مدل زبانی مقیاس بزرگ Alibaba است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwen2.5-14b-instruct": {
+ "description": "مدل 14B مقیاس Qwen 2.5 که به صورت منبع باز ارائه شده است."
+ },
+ "qwen2.5-14b-instruct-1m": {
+ "description": "مدل 72B مقیاس Qwen2.5 که به صورت متنباز ارائه شده است."
+ },
+ "qwen2.5-32b-instruct": {
+ "description": "مدل 32B مقیاس Qwen 2.5 که به صورت منبع باز ارائه شده است."
+ },
+ "qwen2.5-72b-instruct": {
+ "description": "مدل 72B مقیاس بازمتن Qwen 2.5 برای استفاده عمومی."
+ },
+ "qwen2.5-7b-instruct": {
+ "description": "مدل 7B متنباز Qwen 2.5 برای استفاده عمومی."
+ },
+ "qwen2.5-coder-1.5b-instruct": {
+ "description": "نسخه متنباز مدل کد Qwen."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "نسخه متن باز مدل کد Qwen."
+ },
+ "qwen2.5-coder-7b-instruct": {
+ "description": "نسخه متنباز مدل کدنویسی تونگی چیانون."
+ },
+ "qwen2.5-math-1.5b-instruct": {
+ "description": "مدل Qwen-Math دارای قابلیتهای قوی حل مسئله ریاضی است."
+ },
+ "qwen2.5-math-72b-instruct": {
+ "description": "مدل Qwen-Math دارای توانایی قوی در حل مسائل ریاضی است."
+ },
+ "qwen2.5-math-7b-instruct": {
+ "description": "مدل Qwen-Math دارای توانایی قوی در حل مسائل ریاضی است."
+ },
+ "qwen2.5-vl-72b-instruct": {
+ "description": "پیروی از دستورات، ریاضیات، حل مسائل، بهبود کلی کد، بهبود توانایی شناسایی همه چیز، پشتیبانی از فرمتهای مختلف برای شناسایی دقیق عناصر بصری، پشتیبانی از درک فایلهای ویدیویی طولانی (حداکثر 10 دقیقه) و شناسایی لحظات رویداد در سطح ثانیه، توانایی درک زمان و سرعت، بر اساس توانایی تجزیه و تحلیل و شناسایی، پشتیبانی از کنترل عاملهای OS یا Mobile، توانایی استخراج اطلاعات کلیدی و خروجی به فرمت Json قوی، این نسخه 72B است و قویترین نسخه در این سری است."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "پیروی از دستورات، ریاضیات، حل مسائل، بهبود کلی کد، بهبود توانایی شناسایی همه چیز، پشتیبانی از فرمتهای مختلف برای شناسایی دقیق عناصر بصری، پشتیبانی از درک فایلهای ویدیویی طولانی (حداکثر 10 دقیقه) و شناسایی لحظات رویداد در سطح ثانیه، توانایی درک زمان و سرعت، بر اساس توانایی تجزیه و تحلیل و شناسایی، پشتیبانی از کنترل عاملهای OS یا Mobile، توانایی استخراج اطلاعات کلیدی و خروجی به فرمت Json قوی، این نسخه 72B است و قویترین نسخه در این سری است."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 نسل جدید مدل زبانی مقیاس بزرگ Alibaba است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 نسل جدید مدل زبانی مقیاس بزرگ Alibaba است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 نسل جدید مدل زبانی مقیاس بزرگ Alibaba است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwen2:0.5b": {
+ "description": "Qwen2 مدل زبان بزرگ نسل جدید علیبابا است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwen2:1.5b": {
+ "description": "Qwen2 مدل زبان بزرگ نسل جدید علیبابا است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwen2:72b": {
+ "description": "Qwen2 مدل زبان بزرگ نسل جدید علیبابا است که با عملکرد عالی از نیازهای متنوع کاربردی پشتیبانی میکند."
+ },
+ "qwq": {
+ "description": "QwQ یک مدل تحقیقاتی تجربی است که بر بهبود توانایی استدلال AI تمرکز دارد."
+ },
+ "qwq-32b": {
+ "description": "مدل استنتاج QwQ مبتنی بر مدل Qwen2.5-32B است که از طریق یادگیری تقویتی به طور قابل توجهی توانایی استنتاج مدل را افزایش داده است. شاخصهای اصلی مدل مانند کد ریاضی (AIME 24/25، LiveCodeBench) و برخی از شاخصهای عمومی (IFEval، LiveBench و غیره) به سطح DeepSeek-R1 نسخه کامل رسیدهاند و تمامی شاخصها به طور قابل توجهی از DeepSeek-R1-Distill-Qwen-32B که نیز مبتنی بر Qwen2.5-32B است، پیشی گرفتهاند."
+ },
+ "qwq-32b-preview": {
+ "description": "مدل QwQ یک مدل تحقیقاتی تجربی است که توسط تیم Qwen توسعه یافته و بر تقویت توانایی استدلال AI تمرکز دارد."
+ },
+ "qwq-plus-latest": {
+ "description": "مدل استنتاج QwQ مبتنی بر مدل Qwen2.5 است که از طریق یادگیری تقویتی به طور قابل توجهی توانایی استنتاج مدل را افزایش داده است. شاخصهای اصلی مدل مانند کد ریاضی (AIME 24/25، LiveCodeBench) و برخی از شاخصهای عمومی (IFEval، LiveBench و غیره) به سطح DeepSeek-R1 نسخه کامل رسیدهاند."
+ },
+ "r1-1776": {
+ "description": "R1-1776 نسخهای از مدل DeepSeek R1 است که پس از آموزش مجدد، اطلاعات واقعی بدون سانسور و بدون تعصب را ارائه میدهد."
+ },
+ "solar-mini": {
+ "description": "Solar Mini یک LLM فشرده است که عملکردی بهتر از GPT-3.5 دارد و دارای تواناییهای چند زبانه قوی است و از انگلیسی و کرهای پشتیبانی میکند و راهحلهای کارآمد و کوچکی را ارائه میدهد."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) تواناییهای Solar Mini را گسترش میدهد و بر روی زبان ژاپنی تمرکز دارد و در استفاده از انگلیسی و کرهای نیز کارایی و عملکرد عالی را حفظ میکند."
+ },
+ "solar-pro": {
+ "description": "Solar Pro یک مدل هوش مصنوعی پیشرفته از Upstage است که بر توانایی پیروی از دستورات با استفاده از یک GPU تمرکز دارد و امتیاز IFEval بالای 80 را کسب کرده است. در حال حاضر از زبان انگلیسی پشتیبانی میکند و نسخه رسمی آن برای نوامبر 2024 برنامهریزی شده است که پشتیبانی از زبانهای بیشتر و طول زمینه را گسترش خواهد داد."
+ },
+ "sonar": {
+ "description": "محصول جستجوی سبک بر اساس زمینه جستجو که سریعتر و ارزانتر از Sonar Pro است."
+ },
+ "sonar-deep-research": {
+ "description": "تحقیق عمیق، تحقیقاتی جامع و تخصصی را انجام میدهد و آن را به گزارشهای قابل دسترسی و قابل استفاده تبدیل میکند."
+ },
+ "sonar-pro": {
+ "description": "محصول جستجوی پیشرفته که از جستجوی زمینه پشتیبانی میکند و قابلیتهای پیشرفتهای برای پرسش و پیگیری دارد."
+ },
+ "sonar-reasoning": {
+ "description": "محصول جدید API که توسط مدل استدلال DeepSeek پشتیبانی میشود."
+ },
+ "sonar-reasoning-pro": {
+ "description": "محصول جدید API که توسط مدل استدلال DeepSeek پشتیبانی میشود."
+ },
+ "step-1-128k": {
+ "description": "تعادل بین عملکرد و هزینه، مناسب برای سناریوهای عمومی."
+ },
+ "step-1-256k": {
+ "description": "دارای توانایی پردازش متن طولانی، بهویژه مناسب برای تحلیل اسناد بلند."
+ },
+ "step-1-32k": {
+ "description": "پشتیبانی از مکالمات با طول متوسط، مناسب برای انواع مختلف کاربردها."
+ },
+ "step-1-8k": {
+ "description": "مدل کوچک، مناسب برای وظایف سبک."
+ },
+ "step-1-flash": {
+ "description": "مدل پرسرعت، مناسب برای مکالمات در لحظه."
+ },
+ "step-1.5v-mini": {
+ "description": "این مدل دارای تواناییهای قوی در درک ویدیو است."
+ },
+ "step-1o-turbo-vision": {
+ "description": "این مدل دارای تواناییهای قوی در درک تصویر است و در زمینههای ریاضی و کدنویسی از 1o قویتر است. این مدل کوچکتر از 1o است و سرعت خروجی بیشتری دارد."
+ },
+ "step-1o-vision-32k": {
+ "description": "این مدل دارای تواناییهای قوی در درک تصویر است. در مقایسه با مدلهای سری step-1v، عملکرد بصری بهتری دارد."
+ },
+ "step-1v-32k": {
+ "description": "پشتیبانی از ورودی بصری، تقویت تجربه تعامل چندحالته."
+ },
+ "step-1v-8k": {
+ "description": "مدل بصری کوچک، مناسب برای وظایف پایهای تصویر و متن."
+ },
+ "step-2-16k": {
+ "description": "پشتیبانی از تعاملات متنی گسترده، مناسب برای سناریوهای مکالمه پیچیده."
+ },
+ "step-2-mini": {
+ "description": "مدل بزرگ فوقالعاده سریع مبتنی بر معماری توجه MFA که بهطور خودجوش توسعه یافته است، با هزینه بسیار کم به نتایجی مشابه با مرحله ۱ دست مییابد و در عین حال توانایی پردازش بالاتر و زمان پاسخ سریعتری را حفظ میکند. این مدل قادر به انجام وظایف عمومی است و در تواناییهای کدنویسی تخصص دارد."
+ },
+ "taichu_llm": {
+ "description": "Taichu 2.0 بر اساس حجم زیادی از دادههای با کیفیت بالا آموزش دیده است و دارای تواناییهای قویتری در درک متن، تولید محتوا، پرسش و پاسخ در مکالمه و غیره میباشد."
+ },
+ "taichu_vl": {
+ "description": "تواناییهای درک تصویر، انتقال دانش، و استدلال منطقی را ترکیب کرده و در زمینه پرسش و پاسخ تصویری و متنی عملکرد برجستهای دارد."
+ },
+ "text-embedding-3-large": {
+ "description": "قدرتمندترین مدل وکتور سازی، مناسب برای وظایف انگلیسی و غیرانگلیسی."
+ },
+ "text-embedding-3-small": {
+ "description": "مدل جدید و کارآمد Embedding، مناسب برای جستجوی دانش، کاربردهای RAG و سایر سناریوها."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "نسخه متن باز جدیدترین نسل مدلهای پیشآموزش GLM-4 منتشر شده توسط Zhizhu AI."
+ },
+ "togethercomputer/StripedHyena-Nous-7B": {
+ "description": "StripedHyena Nous (7B) با استفاده از استراتژیها و معماری مدل کارآمد، توان محاسباتی بهبودیافتهای را ارائه میدهد."
+ },
+ "tts-1": {
+ "description": "جدیدترین مدل تبدیل متن به گفتار، بهینهسازی شده برای سرعت در سناریوهای زنده."
+ },
+ "tts-1-hd": {
+ "description": "جدیدترین مدل تبدیل متن به گفتار، بهینهسازی شده برای کیفیت."
+ },
+ "upstage/SOLAR-10.7B-Instruct-v1.0": {
+ "description": "Upstage SOLAR Instruct v1 (11B) مناسب برای وظایف دقیق دستوری، ارائهدهنده تواناییهای برجسته در پردازش زبان."
+ },
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet استانداردهای صنعتی را ارتقا داده و عملکردی فراتر از مدلهای رقیب و Claude 3 Opus دارد و در ارزیابیهای گستردهای عملکرد عالی از خود نشان میدهد، در حالی که سرعت و هزینه مدلهای سطح متوسط ما را نیز داراست."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet سریعترین مدل نسل بعدی Anthropic است. در مقایسه با Claude 3 Haiku، Claude 3.7 Sonnet در تمام مهارتها بهبود یافته و در بسیاری از آزمونهای استاندارد هوش از بزرگترین مدل نسل قبلی، Claude 3 Opus، پیشی گرفته است."
+ },
+ "whisper-1": {
+ "description": "مدل شناسایی گفتار عمومی، پشتیبانی از شناسایی گفتار چند زبانه، ترجمه گفتار و شناسایی زبان."
+ },
+ "wizardlm2": {
+ "description": "WizardLM 2 یک مدل زبانی ارائه شده توسط هوش مصنوعی مایکروسافت است که در مکالمات پیچیده، چندزبانه، استدلال و دستیارهای هوشمند عملکرد برجستهای دارد."
+ },
+ "wizardlm2:8x22b": {
+ "description": "WizardLM 2 یک مدل زبانی ارائه شده توسط مایکروسافت AI است که در زمینههای مکالمات پیچیده، چندزبانه، استدلال و دستیارهای هوشمند عملکرد برجستهای دارد."
+ },
+ "yi-large": {
+ "description": "مدل جدید با میلیاردها پارامتر، ارائهدهنده تواناییهای فوقالعاده در پاسخگویی و تولید متن."
+ },
+ "yi-large-fc": {
+ "description": "بر اساس مدل yi-large، قابلیت استفاده از ابزارها را پشتیبانی و تقویت کرده است و برای انواع سناریوهای کسبوکاری که نیاز به ساخت agent یا workflow دارند، مناسب است."
+ },
+ "yi-large-preview": {
+ "description": "نسخه اولیه، توصیه میشود از yi-large (نسخه جدید) استفاده کنید."
+ },
+ "yi-large-rag": {
+ "description": "خدمات پیشرفته مبتنی بر مدل فوقالعاده yi-large، که با ترکیب فناوریهای جستجو و تولید، پاسخهای دقیقی ارائه میدهد و خدمات جستجوی اطلاعات در سراسر وب به صورت لحظهای فراهم میکند."
+ },
+ "yi-large-turbo": {
+ "description": "عملکرد عالی با صرفهجویی بالا. بهینهسازی دقت بالا با توجه به تعادل بین عملکرد، سرعت استنتاج و هزینه."
+ },
+ "yi-lightning": {
+ "description": "جدیدترین مدل با عملکرد بالا که ضمن تضمین خروجی با کیفیت بالا، سرعت استنتاج را به طور قابل توجهی افزایش میدهد."
+ },
+ "yi-lightning-lite": {
+ "description": "نسخه سبک، استفاده از yi-lightning توصیه میشود."
+ },
+ "yi-medium": {
+ "description": "ارتقاء مدل با اندازه متوسط، با تواناییهای متعادل و مقرونبهصرفه. بهینهسازی عمیق در توانایی پیروی از دستورات."
+ },
+ "yi-medium-200k": {
+ "description": "پنجره متنی بسیار طولانی ۲۰۰ هزار کلمهای، با قابلیت درک و تولید متون طولانی و پیچیده."
+ },
+ "yi-spark": {
+ "description": "کوچک و قدرتمند، مدلی سبک و فوقالعاده سریع. قابلیتهای تقویتشده برای محاسبات ریاضی و نوشتن کد ارائه میدهد."
+ },
+ "yi-vision": {
+ "description": "مدل وظایف پیچیده بینایی، ارائه دهنده قابلیتهای درک و تحلیل تصویر با عملکرد بالا."
+ },
+ "yi-vision-v2": {
+ "description": "مدلهای پیچیده بصری که قابلیتهای درک و تحلیل با عملکرد بالا را بر اساس چندین تصویر ارائه میدهند."
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/plugin.json b/DigitalHumanWeb/locales/fa-IR/plugin.json
new file mode 100644
index 0000000..0d1f1c0
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/plugin.json
@@ -0,0 +1,198 @@
+{
+ "debug": {
+ "arguments": "پارامترهای فراخوانی",
+ "function_call": "فراخوانی تابع",
+ "off": "غیرفعال کردن اشکالزدایی",
+ "on": "مشاهده اطلاعات فراخوانی افزونه",
+ "payload": "بار افزونه",
+ "response": "نتیجه بازگشتی",
+ "tool_call": "درخواست فراخوانی ابزار"
+ },
+ "detailModal": {
+ "info": {
+ "description": "توضیحات API",
+ "name": "نام API"
+ },
+ "tabs": {
+ "info": "قابلیتهای افزونه",
+ "manifest": "فایل نصب",
+ "settings": "تنظیمات"
+ },
+ "title": "جزئیات افزونه"
+ },
+ "dev": {
+ "confirmDeleteDevPlugin": "این افزونه محلی حذف خواهد شد و پس از حذف قابل بازیابی نخواهد بود. آیا میخواهید این افزونه را حذف کنید؟",
+ "customParams": {
+ "useProxy": {
+ "label": "نصب از طریق پروکسی (در صورت بروز خطای دسترسی متقابل، میتوانید این گزینه را فعال کرده و دوباره نصب کنید)"
+ }
+ },
+ "deleteSuccess": "افزونه با موفقیت حذف شد",
+ "manifest": {
+ "identifier": {
+ "desc": "شناسهی یکتای افزونه",
+ "label": "شناسه"
+ },
+ "mode": {
+ "local": "پیکربندی بصری",
+ "local-tooltip": "پیکربندی بصری در حال حاضر پشتیبانی نمیشود",
+ "url": "لینک آنلاین"
+ },
+ "name": {
+ "desc": "عنوان افزونه",
+ "label": "عنوان",
+ "placeholder": "موتور جستجو"
+ }
+ },
+ "meta": {
+ "author": {
+ "desc": "نویسنده افزونه",
+ "label": "نویسنده"
+ },
+ "avatar": {
+ "desc": "آیکون افزونه، میتوانید از ایموجی یا URL استفاده کنید",
+ "label": "آیکون"
+ },
+ "description": {
+ "desc": "توضیحات افزونه",
+ "label": "توضیحات",
+ "placeholder": "اطلاعات را از موتور جستجو دریافت کنید"
+ },
+ "formFieldRequired": "این فیلد الزامی است",
+ "homepage": {
+ "desc": "صفحه اصلی افزونه",
+ "label": "صفحه اصلی"
+ },
+ "identifier": {
+ "desc": "شناسهی یکتای افزونه که بهطور خودکار از manifest شناسایی میشود",
+ "errorDuplicate": "شناسه با افزونههای موجود تکراری است، لطفاً شناسه را تغییر دهید",
+ "label": "شناسه",
+ "pattenErrorMessage": "فقط میتوانید از حروف انگلیسی، اعداد، - و _ استفاده کنید"
+ },
+ "manifest": {
+ "desc": "{{appName}} از طریق این لینک افزونه را نصب خواهد کرد",
+ "label": "URL فایل توضیحات افزونه (Manifest)",
+ "preview": "پیشنمایش Manifest",
+ "refresh": "تازهسازی"
+ },
+ "title": {
+ "desc": "عنوان افزونه",
+ "label": "عنوان",
+ "placeholder": "موتور جستجو"
+ }
+ },
+ "metaConfig": "پیکربندی اطلاعات متا افزونه",
+ "modalDesc": "پس از افزودن افزونه سفارشی، میتوانید از آن برای تأیید توسعه افزونه استفاده کنید یا مستقیماً در مکالمهها از آن بهره ببرید. برای توسعه افزونه به <1>مستندات توسعه↗> مراجعه کنید.",
+ "openai": {
+ "importUrl": "وارد کردن از لینک URL",
+ "schema": "Schema"
+ },
+ "preview": {
+ "card": "پیشنمایش نمایش افزونه",
+ "desc": "پیشنمایش توضیحات افزونه",
+ "title": "پیشنمایش نام افزونه"
+ },
+ "save": "نصب افزونه",
+ "saveSuccess": "تنظیمات افزونه با موفقیت ذخیره شد",
+ "tabs": {
+ "manifest": "فهرست توضیحات عملکرد (Manifest)",
+ "meta": "اطلاعات متا افزونه"
+ },
+ "title": {
+ "create": "افزودن افزونه سفارشی",
+ "edit": "ویرایش افزونه سفارشی"
+ },
+ "type": {
+ "lobe": "افزونه {{appName}}",
+ "openai": "افزونه OpenAI"
+ },
+ "update": "بهروزرسانی",
+ "updateSuccess": "تنظیمات افزونه با موفقیت بهروزرسانی شد"
+ },
+ "error": {
+ "fetchError": "درخواست برای این لینک manifest ناموفق بود، لطفاً از معتبر بودن لینک اطمینان حاصل کنید و بررسی کنید که آیا لینک اجازه دسترسی بین دامنهای را میدهد.",
+ "installError": "نصب افزونه {{name}} ناموفق بود.",
+ "manifestInvalid": "manifest با استانداردها مطابقت ندارد، نتیجه بررسی: \n\n {{error}}",
+ "noManifest": "فایل توصیفی وجود ندارد.",
+ "openAPIInvalid": "تجزیه OpenAPI ناموفق بود، خطا: \n\n {{error}}",
+ "reinstallError": "بروزرسانی افزونه {{name}} ناموفق بود.",
+ "urlError": "این لینک محتوای JSON بازنگرداند، لطفاً از معتبر بودن لینک اطمینان حاصل کنید."
+ },
+ "inspector": {
+ "args": "مشاهده لیست پارامترها",
+ "pluginRender": "مشاهده رابط کاربری پلاگین"
+ },
+ "list": {
+ "item": {
+ "deprecated.title": "حذف شده",
+ "local.config": "پیکربندی",
+ "local.title": "سفارشی"
+ }
+ },
+ "loading": {
+ "content": "در حال فراخوانی افزونه...",
+ "plugin": "افزونه در حال اجرا..."
+ },
+ "pluginList": "فهرست افزونهها",
+ "search": {
+ "config": {
+ "addKey": "کلید را اضافه کنید",
+ "close": "حذف",
+ "confirm": "پیکربندی کامل و دوباره تلاش کنید"
+ },
+ "crawPages": {
+ "crawling": "در حال شناسایی لینک",
+ "detail": {
+ "preview": "پیشنمایش",
+ "raw": "متن اصلی",
+ "tooLong": "متن بسیار طولانی است، فقط {{characters}} کاراکتر اول در زمینه گفتگو حفظ میشود و بخشهای اضافی در زمینه گفتگو محاسبه نمیشوند"
+ },
+ "meta": {
+ "crawler": "مدل خزنده",
+ "words": "تعداد کاراکتر"
+ }
+ },
+ "searchxng": {
+ "baseURL": "لطفاً وارد کنید",
+ "description": "لطفاً آدرس وب SearchXNG را وارد کنید تا جستجوی آنلاین را شروع کنید",
+ "keyPlaceholder": "لطفاً کلید را وارد کنید",
+ "title": "پیکربندی موتور جستجوی SearchXNG",
+ "unconfiguredDesc": "لطفاً با مدیر تماس بگیرید تا پیکربندی موتور جستجوی SearchXNG را کامل کند و بتوانید جستجوی آنلاین را شروع کنید",
+ "unconfiguredTitle": "موتور جستجوی SearchXNG هنوز پیکربندی نشده است"
+ },
+ "title": "جستجوی آنلاین"
+ },
+ "setting": "تنظیمات افزونه",
+ "settings": {
+ "indexUrl": {
+ "title": "شاخص بازار",
+ "tooltip": "ویرایش آنلاین در حال حاضر پشتیبانی نمیشود، لطفاً از طریق متغیرهای محیطی در زمان استقرار تنظیم کنید"
+ },
+ "modalDesc": "پس از پیکربندی آدرس بازار افزونه، میتوانید از بازار افزونه سفارشی استفاده کنید",
+ "title": "تنظیمات بازار افزونه"
+ },
+ "showInPortal": "لطفاً جزئیات را در فضای کاری مشاهده کنید",
+ "store": {
+ "actions": {
+ "confirmUninstall": "در حال حذف این افزونه هستید. پس از حذف، تنظیمات افزونه پاک خواهد شد. لطفاً عملیات خود را تأیید کنید.",
+ "detail": "جزئیات",
+ "install": "نصب",
+ "manifest": "ویرایش فایل نصب",
+ "settings": "تنظیمات",
+ "uninstall": "حذف"
+ },
+ "communityPlugin": "افزونههای جامعه",
+ "customPlugin": "افزونه سفارشی",
+ "empty": "هیچ افزونهای نصب نشده است",
+ "installAllPlugins": "نصب همه",
+ "networkError": "دریافت فروشگاه افزونهها ناموفق بود. لطفاً اتصال شبکه خود را بررسی کرده و دوباره تلاش کنید.",
+ "placeholder": "نام افزونه، توضیحات یا کلمات کلیدی را جستجو کنید...",
+ "releasedAt": "منتشر شده در {{createdAt}}",
+ "tabs": {
+ "all": "همه",
+ "installed": "نصب شده"
+ },
+ "title": "فروشگاه افزونهها"
+ },
+ "unknownPlugin": "افزونه ناشناخته"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/portal.json b/DigitalHumanWeb/locales/fa-IR/portal.json
new file mode 100644
index 0000000..0ba3cfa
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/portal.json
@@ -0,0 +1,30 @@
+{
+ "Artifacts": "مصنوعات",
+ "FilePreview": {
+ "tabs": {
+ "chunk": "بخش",
+ "file": "فایل"
+ }
+ },
+ "Plugins": "افزونهها",
+ "artifacts": {
+ "display": {
+ "code": "کد",
+ "preview": "پیشنمایش"
+ },
+ "svg": {
+ "copyAsImage": "کپی به عنوان تصویر",
+ "copyFail": "کپی ناموفق بود، دلیل خطا: {{error}}",
+ "copySuccess": "تصویر با موفقیت کپی شد",
+ "download": {
+ "png": "دانلود به صورت PNG",
+ "svg": "دانلود به صورت SVG"
+ }
+ }
+ },
+ "emptyArtifactList": "لیست Artifacts در حال حاضر خالی است، لطفاً پس از استفاده از افزونهها در جلسه، دوباره بررسی کنید.",
+ "emptyKnowledgeList": "فهرست دانش فعلی خالی است",
+ "files": "فایلها",
+ "messageDetail": "جزئیات پیام",
+ "title": "فضای کاری"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/providers.json b/DigitalHumanWeb/locales/fa-IR/providers.json
new file mode 100644
index 0000000..ed02d86
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/providers.json
@@ -0,0 +1,146 @@
+{
+ "ai21": {
+ "description": "AI21 Labs مدلهای پایه و سیستمهای هوش مصنوعی را برای کسبوکارها ایجاد میکند و به تسریع کاربرد هوش مصنوعی تولیدی در تولید کمک میکند."
+ },
+ "ai360": {
+ "description": "360 AI پلتفرم مدلها و خدمات هوش مصنوعی شرکت 360 است که مدلهای پیشرفته پردازش زبان طبیعی متعددی از جمله 360GPT2 Pro، 360GPT Pro، 360GPT Turbo و 360GPT Turbo Responsibility 8K را ارائه میدهد. این مدلها با ترکیب پارامترهای بزرگمقیاس و قابلیتهای چندوجهی، به طور گسترده در زمینههای تولید متن، درک معنایی، سیستمهای مکالمه و تولید کد به کار میروند. با استفاده از استراتژیهای قیمتگذاری انعطافپذیر، 360 AI نیازهای متنوع کاربران را برآورده کرده و از یکپارچهسازی توسعهدهندگان پشتیبانی میکند و به نوآوری و توسعه کاربردهای هوشمند کمک میکند."
+ },
+ "anthropic": {
+ "description": "Anthropic یک شرکت متمرکز بر تحقیق و توسعه هوش مصنوعی است که مجموعهای از مدلهای پیشرفته زبان مانند Claude 3.5 Sonnet، Claude 3 Sonnet، Claude 3 Opus و Claude 3 Haiku را ارائه میدهد. این مدلها تعادلی ایدهآل بین هوشمندی، سرعت و هزینه برقرار میکنند و برای انواع کاربردها از بارهای کاری در سطح سازمانی تا پاسخهای سریع مناسب هستند. Claude 3.5 Sonnet به عنوان جدیدترین مدل آن، در ارزیابیهای متعدد عملکرد برجستهای داشته و در عین حال نسبت هزینه به عملکرد بالایی را حفظ کرده است."
+ },
+ "azure": {
+ "description": "Azure انواع مدلهای پیشرفته AI را ارائه میدهد، از جمله GPT-3.5 و جدیدترین سری GPT-4، که از انواع دادهها و وظایف پیچیده پشتیبانی میکند و به ارائه راهحلهای AI ایمن، قابل اعتماد و پایدار متعهد است."
+ },
+ "azureai": {
+ "description": "Azure مجموعهای از مدلهای پیشرفته AI را ارائه میدهد، از جمله GPT-3.5 و جدیدترین سری GPT-4، که از انواع مختلف دادهها و وظایف پیچیده پشتیبانی میکند و به دنبال راهحلهای AI ایمن، قابل اعتماد و پایدار است."
+ },
+ "baichuan": {
+ "description": "بایچوان هوش مصنوعی یک شرکت متمرکز بر توسعه مدلهای بزرگ هوش مصنوعی است. مدلهای این شرکت در وظایف چینی مانند دانشنامه، پردازش متون طولانی و تولید محتوا عملکرد برجستهای دارند و از مدلهای اصلی خارجی پیشی گرفتهاند. بایچوان هوش مصنوعی همچنین دارای تواناییهای چندوجهی پیشرو در صنعت است و در چندین ارزیابی معتبر عملکرد عالی داشته است. مدلهای آن شامل Baichuan 4، Baichuan 3 Turbo و Baichuan 3 Turbo 128k هستند که برای سناریوهای مختلف بهینهسازی شدهاند و راهحلهای مقرونبهصرفهای ارائه میدهند."
+ },
+ "bedrock": {
+ "description": "Bedrock یک سرویس ارائه شده توسط آمازون AWS است که بر ارائه مدلهای پیشرفته زبان AI و مدلهای بصری برای شرکتها تمرکز دارد. خانواده مدلهای آن شامل سری Claude از Anthropic، سری Llama 3.1 از Meta و غیره است که از مدلهای سبک تا مدلهای با عملکرد بالا را پوشش میدهد و از وظایفی مانند تولید متن، مکالمه و پردازش تصویر پشتیبانی میکند. این سرویس برای برنامههای شرکتی با مقیاسها و نیازهای مختلف مناسب است."
+ },
+ "cloudflare": {
+ "description": "مدلهای یادگیری ماشین مبتنی بر GPU بدون سرور را در شبکه جهانی Cloudflare اجرا کنید."
+ },
+ "deepseek": {
+ "description": "DeepSeek یک شرکت متمرکز بر تحقیق و کاربرد فناوری هوش مصنوعی است. مدل جدید آن، DeepSeek-V2.5، تواناییهای مکالمه عمومی و پردازش کد را ترکیب کرده و در زمینههایی مانند همترازی با ترجیحات انسانی، وظایف نوشتاری و پیروی از دستورات بهبود قابل توجهی داشته است."
+ },
+ "doubao": {
+ "description": "مدل بزرگ خودساخته شده توسط بایتدANCE. با تأیید در بیش از 50 سناریوی تجاری داخلی بایتدANCE، با استفاده روزانه از تریلیونها توکن، به طور مداوم بهبود یافته و تواناییهای چندگانهای را ارائه میدهد تا تجربههای تجاری غنی را با کیفیت مدل بالا برای شرکتها ایجاد کند."
+ },
+ "fireworksai": {
+ "description": "Fireworks AI یک ارائهدهنده پیشرو در خدمات مدلهای زبان پیشرفته است که بر فراخوانی توابع و پردازش چندوجهی تمرکز دارد. جدیدترین مدل آن، Firefunction V2، بر اساس Llama-3 ساخته شده و برای فراخوانی توابع، مکالمه و پیروی از دستورات بهینهسازی شده است. مدل زبان تصویری FireLLaVA-13B از ورودیهای ترکیبی تصویر و متن پشتیبانی میکند. سایر مدلهای قابل توجه شامل سری Llama و سری Mixtral هستند که پشتیبانی کارآمدی از پیروی دستورات چندزبانه و تولید ارائه میدهند."
+ },
+ "giteeai": {
+ "description": "API بی خدمتکار Gitee AI به توسعهکنندگان AI با یک از خدمت API بزرگ مدل آلودگی را از جعبه میدهد."
+ },
+ "github": {
+ "description": "با استفاده از مدل GitHub، توسعهدهندگان میتوانند به مهندسین هوش مصنوعی تبدیل شوند و با استفاده از مدلهای پیشرو در صنعت، ساخت و ساز کنند."
+ },
+ "google": {
+ "description": "سری Gemini گوگل پیشرفتهترین و عمومیترین مدل هوش مصنوعی آن است که توسط Google DeepMind ساخته شده و بهطور خاص برای چندوجهی طراحی شده است. این مدل از درک و پردازش بیوقفه متن، کد، تصویر، صدا و ویدئو پشتیبانی میکند. این مدل در محیطهای مختلف از مراکز داده تا دستگاههای همراه قابل استفاده است و بهطور قابل توجهی کارایی و گستردگی کاربرد مدلهای هوش مصنوعی را افزایش میدهد."
+ },
+ "groq": {
+ "description": "موتور استنتاج LPU شرکت Groq در آخرین آزمونهای معیار مدلهای زبانی بزرگ (LLM) مستقل عملکرد برجستهای داشته و با سرعت و کارایی شگفتانگیز خود، استانداردهای راهحلهای هوش مصنوعی را بازتعریف کرده است. Groq نمادی از سرعت استنتاج فوری است و در استقرارهای مبتنی بر ابر عملکرد خوبی از خود نشان داده است."
+ },
+ "higress": {
+ "description": "Higress یک دروازه API ابری است که برای حل مشکلات مربوط به بارگذاری مجدد Tengine در کسب و کارهای با اتصالات طولانی و همچنین کمبود قابلیتهای تعادل بار gRPC/Dubbo در داخل علی ایجاد شده است."
+ },
+ "huggingface": {
+ "description": "API استنتاج HuggingFace یک روش سریع و رایگان برای کاوش هزاران مدل برای وظایف مختلف ارائه میدهد. چه در حال طراحی نمونه اولیه برای یک برنامه جدید باشید و چه در حال آزمایش قابلیتهای یادگیری ماشین، این API به شما امکان دسترسی فوری به مدلهای با عملکرد بالا در چندین حوزه را میدهد."
+ },
+ "hunyuan": {
+ "description": "مدل زبان بزرگ توسعهیافته توسط تنسنت، با تواناییهای قدرتمند در خلق محتوای چینی، توانایی استدلال منطقی در زمینههای پیچیده، و قابلیت اجرای وظایف بهصورت قابل اعتماد"
+ },
+ "internlm": {
+ "description": "سازمان متن باز متعهد به تحقیق و توسعه ابزارهای مدلهای بزرگ. ارائه یک پلتفرم متن باز کارآمد و آسان برای تمام توسعهدهندگان هوش مصنوعی، تا جدیدترین مدلها و تکنیکهای الگوریتمی در دسترس باشد."
+ },
+ "jina": {
+ "description": "Jina AI در سال 2020 تأسیس شد و یک شرکت پیشرو در زمینه AI جستجو است. پلتفرم پایه جستجوی ما شامل مدلهای برداری، بازچینشگرها و مدلهای زبانی کوچک است که به کسبوکارها کمک میکند تا برنامههای جستجوی تولیدی و چندرسانهای قابل اعتماد و با کیفیت بالا بسازند."
+ },
+ "lmstudio": {
+ "description": "LM Studio یک برنامه دسکتاپ برای توسعه و آزمایش LLM ها بر روی رایانه شما است."
+ },
+ "minimax": {
+ "description": "MiniMax یک شرکت فناوری هوش مصنوعی عمومی است که در سال 2021 تأسیس شد و به همکاری با کاربران برای ایجاد هوش مصنوعی متعهد است. MiniMax بهطور مستقل مدلهای بزرگ عمومی چندگانهای را توسعه داده است، از جمله مدل متنی MoE با تریلیونها پارامتر، مدل صوتی و مدل تصویری. همچنین برنامههایی مانند حلزون AI را معرفی کرده است."
+ },
+ "mistral": {
+ "description": "Mistral مدلهای پیشرفته عمومی، تخصصی و پژوهشی را ارائه میدهد که به طور گسترده در زمینههای استدلال پیچیده، وظایف چندزبانه، تولید کد و غیره کاربرد دارند. از طریق رابط فراخوانی عملکرد، کاربران میتوانند قابلیتهای سفارشی را برای تحقق برنامههای خاص ادغام کنند."
+ },
+ "moonshot": {
+ "description": "Moonshot یک پلتفرم متنباز است که توسط شرکت فناوری Beijing Dark Side of the Moon ارائه شده است. این پلتفرم مدلهای مختلف پردازش زبان طبیعی را ارائه میدهد و در زمینههای گستردهای از جمله، اما نه محدود به، تولید محتوا، تحقیقات علمی، توصیههای هوشمند، تشخیص پزشکی و غیره کاربرد دارد و از پردازش متون طولانی و وظایف پیچیده تولید پشتیبانی میکند."
+ },
+ "novita": {
+ "description": "Novita AI یک پلتفرم ارائهدهنده خدمات API برای مدلهای بزرگ زبانی و تولید تصاویر هوش مصنوعی است که انعطافپذیر، قابلاعتماد و مقرونبهصرفه میباشد. این پلتفرم از جدیدترین مدلهای متنباز مانند Llama3 و Mistral پشتیبانی میکند و راهحلهای API جامع، کاربرپسند و خودکار برای توسعه برنامههای هوش مصنوعی مولد ارائه میدهد که مناسب رشد سریع استارتاپهای هوش مصنوعی است."
+ },
+ "nvidia": {
+ "description": "NVIDIA NIM™ کانتینرهایی را ارائه میدهد که میتوانند برای استنتاج میکروسرویسهای GPU تسریع شده خود میزبان استفاده شوند و از استقرار مدلهای AI پیشآموزشدیده و سفارشی در ابر، مراکز داده، رایانههای شخصی RTX™ AI و ایستگاههای کاری پشتیبانی میکند."
+ },
+ "ollama": {
+ "description": "مدلهای ارائهشده توسط Ollama طیف گستردهای از تولید کد، محاسبات ریاضی، پردازش چندزبانه و تعاملات گفتگویی را پوشش میدهند و از نیازهای متنوع استقرار در سطح سازمانی و محلی پشتیبانی میکنند."
+ },
+ "openai": {
+ "description": "OpenAI یک موسسه پیشرو در تحقیقات هوش مصنوعی در سطح جهان است که مدلهایی مانند سری GPT را توسعه داده و مرزهای پردازش زبان طبیعی را پیش برده است. OpenAI متعهد به تغییر صنایع مختلف از طریق راهحلهای نوآورانه و کارآمد هوش مصنوعی است. محصولات آنها دارای عملکرد برجسته و اقتصادی بوده و به طور گسترده در تحقیقات، تجارت و کاربردهای نوآورانه استفاده میشوند."
+ },
+ "openrouter": {
+ "description": "OpenRouter یک پلتفرم خدماتی است که رابطهای مدلهای پیشرفته مختلفی مانند OpenAI، Anthropic، LLaMA و بیشتر را ارائه میدهد و برای نیازهای متنوع توسعه و کاربرد مناسب است. کاربران میتوانند بر اساس نیازهای خود، بهترین مدل و قیمت را بهصورت انعطافپذیر انتخاب کنند و به بهبود تجربه AI کمک کنند."
+ },
+ "perplexity": {
+ "description": "Perplexity یک ارائهدهنده پیشرو در مدلهای تولید مکالمه است که انواع مدلهای پیشرفته Llama 3.1 را ارائه میدهد و از برنامههای آنلاین و آفلاین پشتیبانی میکند. این مدلها بهویژه برای وظایف پیچیده پردازش زبان طبیعی مناسب هستند."
+ },
+ "ppio": {
+ "description": "PPIO پایو کلود خدمات API مدلهای متن باز با ثبات و با قیمت مناسب را ارائه میدهد و از تمام سریهای DeepSeek، Llama، Qwen و سایر مدلهای بزرگ پیشرو در صنعت پشتیبانی میکند."
+ },
+ "qwen": {
+ "description": "چوان یی چیان ون یک مدل زبان بسیار بزرگ است که توسط علیکلود بهطور مستقل توسعه یافته و دارای تواناییهای قدرتمند درک و تولید زبان طبیعی است. این مدل میتواند به انواع سوالات پاسخ دهد، محتوای متنی خلق کند، نظرات و دیدگاهها را بیان کند، کد بنویسد و در حوزههای مختلف نقش ایفا کند."
+ },
+ "sambanova": {
+ "description": "SambaNova Cloud به توسعهدهندگان این امکان را میدهد که به راحتی از بهترین مدلهای متنباز استفاده کنند و از سریعترین سرعت استنتاج بهرهمند شوند."
+ },
+ "sensenova": {
+ "description": "سنسنووا، با تکیه بر زیرساختهای قوی سنستک، خدمات مدلهای بزرگ تمامپشتهای را بهصورت کارآمد و آسان ارائه میدهد."
+ },
+ "siliconcloud": {
+ "description": "SiliconCloud، یک سرویس ابری GenAI با کارایی بالا و مقرونبهصرفه بر اساس مدلهای منبعباز برجسته"
+ },
+ "spark": {
+ "description": "مدل بزرگ اسپارک iFLYTEK تواناییهای قدرتمند AI را در حوزههای مختلف و زبانهای متعدد ارائه میدهد و با استفاده از فناوری پیشرفته پردازش زبان طبیعی، برنامههای نوآورانهای را برای سختافزارهای هوشمند، بهداشت هوشمند، مالی هوشمند و سایر سناریوهای عمودی ایجاد میکند."
+ },
+ "stepfun": {
+ "description": "مدل بزرگ ستارهای طبقاتی دارای تواناییهای پیشرو در صنعت برای چندحالته و استدلال پیچیده است و از درک متون بسیار طولانی و قابلیت جستجوی خودکار قدرتمند پشتیبانی میکند."
+ },
+ "taichu": {
+ "description": "موسسه اتوماسیون آکادمی علوم چین و موسسه هوش مصنوعی ووهان نسل جدیدی از مدلهای چندوجهی را معرفی کردهاند که از پرسش و پاسخ چندمرحلهای، تولید متن، تولید تصویر، درک سهبعدی، تحلیل سیگنال و سایر وظایف جامع پرسش و پاسخ پشتیبانی میکند. این مدل دارای تواناییهای شناختی، درک و خلاقیت قویتری است و تجربه تعاملی جدیدی را به ارمغان میآورد."
+ },
+ "tencentcloud": {
+ "description": "قدرت اتمی موتور دانش (LLM Knowledge Engine Atomic Power) بر اساس موتور دانش توسعه یافته و قابلیت کامل پرسش و پاسخ را برای شرکتها و توسعهدهندگان ارائه میدهد. شما میتوانید با استفاده از چندین قدرت اتمی، خدمات مدل اختصاصی خود را بسازید و از خدماتی مانند تجزیه و تحلیل اسناد، تقسیم، جاسازی، بازنویسی چند دور و غیره برای سفارشیسازی کسب و کار هوش مصنوعی اختصاصی خود استفاده کنید."
+ },
+ "togetherai": {
+ "description": "Together AI متعهد به دستیابی به عملکرد پیشرو از طریق مدلهای نوآورانه هوش مصنوعی است و قابلیتهای سفارشیسازی گستردهای را ارائه میدهد، از جمله پشتیبانی از مقیاسپذیری سریع و فرآیندهای استقرار شهودی، که نیازهای مختلف شرکتها را برآورده میکند."
+ },
+ "upstage": {
+ "description": "Upstage بر توسعه مدلهای هوش مصنوعی برای نیازهای مختلف تجاری تمرکز دارد، از جمله Solar LLM و هوش مصنوعی اسناد، که هدف آن دستیابی به هوش عمومی مصنوعی (AGI) برای کار است. با استفاده از Chat API، میتوانید نمایندگان مکالمه ساده ایجاد کنید و از قابلیتهای فراخوانی عملکرد، ترجمه، تعبیه و کاربردهای خاص حوزه پشتیبانی کنید."
+ },
+ "vertexai": {
+ "description": "سری Gemini گوگل پیشرفتهترین و عمومیترین مدلهای هوش مصنوعی است که توسط Google DeepMind طراحی شده و بهطور خاص برای چندرسانهای طراحی شده است و از درک و پردازش بیوقفه متن، کد، تصویر، صدا و ویدیو پشتیبانی میکند. این مدلها برای محیطهای مختلف از مراکز داده تا دستگاههای همراه مناسب هستند و بهطور قابل توجهی کارایی و کاربردهای مدلهای هوش مصنوعی را افزایش میدهند."
+ },
+ "vllm": {
+ "description": "vLLM یک کتابخانه سریع و آسان برای استفاده است که برای استنتاج و خدمات LLM طراحی شده است."
+ },
+ "volcengine": {
+ "description": "پلتفرم توسعه خدمات مدلهای بزرگ که توسط بایتدANCE راهاندازی شده است، خدمات فراوان، ایمن و با قیمت رقابتی برای فراخوانی مدلها را ارائه میدهد. همچنین امکاناتی از جمله دادههای مدل، تنظیم دقیق، استنتاج و ارزیابی را به صورت end-to-end فراهم میکند و به طور جامع از توسعه و پیادهسازی برنامههای هوش مصنوعی شما حمایت میکند."
+ },
+ "wenxin": {
+ "description": "پلتفرم جامع توسعه و خدمات مدلهای بزرگ و برنامههای بومی هوش مصنوعی در سطح سازمانی، ارائهدهنده کاملترین و کاربرپسندترین زنجیره ابزارهای توسعه مدلهای هوش مصنوعی مولد و توسعه برنامهها"
+ },
+ "xai": {
+ "description": "xAI یک شرکت است که به ساخت هوش مصنوعی برای تسریع کشفیات علمی بشر اختصاص دارد. مأموریت ما پیشبرد درک مشترک ما از جهان است."
+ },
+ "zeroone": {
+ "description": "صفر و یک متعهد به پیشبرد انقلاب فناوری AI 2.0 با محوریت انسان است و هدف آن ایجاد ارزش اقتصادی و اجتماعی عظیم از طریق مدلهای زبانی بزرگ و همچنین ایجاد اکوسیستم جدید هوش مصنوعی و مدلهای تجاری است."
+ },
+ "zhipu": {
+ "description": "پلتفرم باز هوش مصنوعی Zhipu خدمات مدلهای چندرسانهای و زبانی را ارائه میدهد و از کاربردهای گستردهای در زمینههای مختلف هوش مصنوعی مانند پردازش متن، درک تصویر و کمک به برنامهنویسی پشتیبانی میکند."
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/ragEval.json b/DigitalHumanWeb/locales/fa-IR/ragEval.json
new file mode 100644
index 0000000..f621358
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/ragEval.json
@@ -0,0 +1,91 @@
+{
+ "addDataset": {
+ "confirm": "ایجاد جدید",
+ "description": {
+ "placeholder": "توضیحات مجموعه داده (اختیاری)"
+ },
+ "name": {
+ "placeholder": "نام مجموعه داده",
+ "required": "لطفاً نام مجموعه داده را وارد کنید"
+ },
+ "title": "افزودن مجموعه داده"
+ },
+ "dataset": {
+ "addNewButton": "ایجاد مجموعه داده",
+ "emptyGuide": "مجموعه داده فعلی خالی است، لطفاً یک مجموعه داده ایجاد کنید.",
+ "list": {
+ "table": {
+ "actions": {
+ "importData": "وارد کردن دادهها"
+ },
+ "columns": {
+ "actions": "عملیات",
+ "ideal": {
+ "title": "پاسخ مورد انتظار"
+ },
+ "question": {
+ "title": "سؤال"
+ },
+ "referenceFiles": {
+ "title": "فایلهای مرجع"
+ }
+ },
+ "notSelected": "لطفاً یک مجموعه داده از سمت چپ انتخاب کنید",
+ "title": "جزئیات مجموعه داده"
+ },
+ "title": "مجموعه داده"
+ }
+ },
+ "evaluation": {
+ "addEvaluation": {
+ "confirm": "ایجاد جدید",
+ "datasetId": {
+ "placeholder": "لطفاً مجموعه دادههای ارزیابی خود را انتخاب کنید",
+ "required": "لطفاً مجموعه دادههای ارزیابی را انتخاب کنید"
+ },
+ "description": {
+ "placeholder": "توضیحات وظیفه ارزیابی (اختیاری)"
+ },
+ "name": {
+ "placeholder": "نام وظیفه ارزیابی",
+ "required": "لطفاً نام وظیفه ارزیابی را وارد کنید"
+ },
+ "title": "افزودن وظیفه ارزیابی"
+ },
+ "addNewButton": "ایجاد ارزیابی",
+ "emptyGuide": "در حال حاضر هیچ وظیفه ارزیابی وجود ندارد، ایجاد ارزیابی را شروع کنید.",
+ "table": {
+ "columns": {
+ "actions": {
+ "checkStatus": "بررسی وضعیت",
+ "confirmDelete": "آیا این ارزیابی حذف شود؟",
+ "confirmRun": "آیا میخواهید اجرا را شروع کنید؟ پس از شروع، وظیفه ارزیابی به صورت غیرهمزمان در پسزمینه اجرا میشود و بستن صفحه بر اجرای وظیفه غیرهمزمان تأثیری نخواهد داشت.",
+ "downloadRecords": "دانلود ارزیابی",
+ "retry": "تلاش مجدد",
+ "run": "اجرا",
+ "title": "عملیات"
+ },
+ "datasetId": {
+ "title": "مجموعه داده"
+ },
+ "name": {
+ "title": "نام وظیفه ارزیابی"
+ },
+ "records": {
+ "title": "تعداد رکوردهای ارزیابی"
+ },
+ "referenceFiles": {
+ "title": "فایلهای مرجع"
+ },
+ "status": {
+ "error": "خطا در اجرا",
+ "pending": "در انتظار اجرا",
+ "processing": "در حال اجرا",
+ "success": "اجرای موفق",
+ "title": "وضعیت"
+ }
+ },
+ "title": "لیست وظایف ارزیابی"
+ }
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/setting.json b/DigitalHumanWeb/locales/fa-IR/setting.json
new file mode 100644
index 0000000..adf8fab
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/setting.json
@@ -0,0 +1,447 @@
+{
+ "about": {
+ "title": "درباره"
+ },
+ "agentTab": {
+ "chat": "ترجیحات گفتگو",
+ "meta": "اطلاعات دستیار",
+ "modal": "تنظیمات مدل",
+ "plugin": "تنظیمات افزونه",
+ "prompt": "تنظیمات شخصیت",
+ "tts": "خدمات صوتی"
+ },
+ "analytics": {
+ "telemetry": {
+ "desc": "با انتخاب ارسال دادههای تلهمتری، میتوانید به ما در بهبود تجربه کلی کاربری {{appName}} کمک کنید",
+ "title": "ارسال دادههای ناشناس استفاده"
+ },
+ "title": "آمار و دادهها"
+ },
+ "danger": {
+ "clear": {
+ "action": "پاکسازی فوری",
+ "confirm": "آیا از پاکسازی تمام دادههای گفتگو مطمئن هستید؟",
+ "desc": "تمام دادههای جلسه، از جمله دستیار، فایلها، پیامها، افزونهها و غیره پاک خواهد شد",
+ "success": "تمام پیامهای جلسه پاک شد",
+ "title": "پاکسازی تمام پیامهای جلسه"
+ },
+ "reset": {
+ "action": "بازنشانی فوری",
+ "confirm": "آیا از بازنشانی تمام تنظیمات مطمئن هستید؟",
+ "currentVersion": "نسخه فعلی",
+ "desc": "تمام تنظیمات بازنشانی شده و به مقادیر پیشفرض بازمیگردد",
+ "success": "تمام تنظیمات بازنشانی شد",
+ "title": "بازنشانی تمام تنظیمات"
+ }
+ },
+ "header": {
+ "desc": "ترجیحات و تنظیمات مدل",
+ "global": "تنظیمات کلی",
+ "session": "تنظیمات جلسه",
+ "sessionDesc": "تنظیمات نقش و ترجیحات جلسه",
+ "sessionWithName": "تنظیمات جلسه · {{name}}",
+ "title": "تنظیمات"
+ },
+ "llm": {
+ "aesGcm": "کلید و آدرس پروکسی شما با استفاده از الگوریتم رمزنگاری <1>AES-GCM1> رمزگذاری خواهد شد",
+ "apiKey": {
+ "desc": "لطفاً {{name}} API Key خود را وارد کنید",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "checker": {
+ "button": "بررسی",
+ "desc": "تست کنید که آیا Api Key و آدرس پروکسی به درستی وارد شدهاند",
+ "pass": "بررسی موفقیتآمیز",
+ "title": "بررسی اتصال"
+ },
+ "customModelCards": {
+ "addNew": "ایجاد و افزودن مدل {{id}}",
+ "config": "پیکربندی مدل",
+ "confirmDelete": "این مدل سفارشی در حال حذف است و پس از حذف قابل بازیابی نخواهد بود، لطفاً با دقت عمل کنید.",
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "فیلدی که در Azure OpenAI برای درخواست واقعی استفاده میشود",
+ "placeholder": "لطفاً نام استقرار مدل در Azure را وارد کنید",
+ "title": "نام استقرار مدل"
+ },
+ "displayName": {
+ "placeholder": "لطفاً نام نمایشی مدل را وارد کنید، مانند ChatGPT، GPT-4 و غیره",
+ "title": "نام نمایشی مدل"
+ },
+ "files": {
+ "extra": "پیادهسازی فعلی آپلود فایل تنها یک راهحل موقت است و فقط برای آزمایش شخصی است. قابلیت کامل آپلود فایل در آینده ارائه خواهد شد",
+ "title": "پشتیبانی از آپلود فایل"
+ },
+ "functionCall": {
+ "extra": "این پیکربندی تنها قابلیت فراخوانی توابع در برنامه را فعال میکند. پشتیبانی از فراخوانی توابع کاملاً به خود مدل بستگی دارد، لطفاً قابلیت فراخوانی توابع مدل را به صورت مستقل تست کنید",
+ "title": "پشتیبانی از فراخوانی توابع"
+ },
+ "id": {
+ "extra": "به عنوان برچسب مدل نمایش داده خواهد شد",
+ "placeholder": "لطفاً شناسه مدل را وارد کنید، مانند gpt-4-turbo-preview یا claude-2.1",
+ "title": "شناسه مدل"
+ },
+ "modalTitle": "پیکربندی مدل سفارشی",
+ "tokens": {
+ "title": "حداکثر تعداد توکنها"
+ },
+ "vision": {
+ "extra": "این پیکربندی تنها قابلیت آپلود تصویر در برنامه را فعال میکند. پشتیبانی از تشخیص تصویر کاملاً به خود مدل بستگی دارد، لطفاً قابلیت تشخیص تصویر مدل را به صورت مستقل تست کنید",
+ "title": "پشتیبانی از تشخیص تصویر"
+ }
+ }
+ },
+ "fetchOnClient": {
+ "desc": "حالت درخواست از سمت کلاینت، درخواستها را مستقیماً از مرورگر ارسال میکند و میتواند سرعت پاسخگویی را افزایش دهد",
+ "title": "استفاده از حالت درخواست از سمت کلاینت"
+ },
+ "fetcher": {
+ "clear": "پاک کردن مدلهای دریافت شده",
+ "fetch": "دریافت لیست مدلها",
+ "fetching": "در حال دریافت لیست مدلها...",
+ "latestTime": "آخرین زمان بهروزرسانی: {{time}}",
+ "noLatestTime": "هنوز لیستی دریافت نشده است"
+ },
+ "helpDoc": "راهنمای پیکربندی",
+ "modelList": {
+ "desc": "مدلهایی را که در جلسه نمایش داده میشوند انتخاب کنید. مدلهای انتخابشده در لیست مدلها نمایش داده خواهند شد",
+ "placeholder": "لطفاً مدلی را از لیست انتخاب کنید",
+ "title": "لیست مدلها",
+ "total": "در مجموع {{count}} مدل موجود است"
+ },
+ "proxyUrl": {
+ "desc": "باید شامل http(s):// باشد، به جز آدرس پیشفرض",
+ "title": "آدرس پروکسی API"
+ },
+ "waitingForMore": "مدلهای بیشتری در حال <1>برنامهریزی برای اضافه شدن1> هستند، لطفاً منتظر بمانید"
+ },
+ "plugin": {
+ "addTooltip": "افزودن افزونه سفارشی",
+ "clearDeprecated": "حذف افزونههای نامعتبر",
+ "empty": "هیچ افزونهای نصب نشده است، به <1>فروشگاه افزونهها1> بروید و کاوش کنید",
+ "installStatus": {
+ "deprecated": "حذف شده"
+ },
+ "settings": {
+ "hint": "لطفاً بر اساس توضیحات، تنظیمات زیر را پر کنید",
+ "title": "تنظیمات افزونه {{id}}",
+ "tooltip": "تنظیمات افزونه"
+ },
+ "store": "فروشگاه افزونهها"
+ },
+ "settingAgent": {
+ "avatar": {
+ "title": "آواتار"
+ },
+ "backgroundColor": {
+ "title": "رنگ پسزمینه"
+ },
+ "description": {
+ "placeholder": "لطفاً توضیحات دستیار را وارد کنید",
+ "title": "توضیحات دستیار"
+ },
+ "name": {
+ "placeholder": "لطفاً نام دستیار را وارد کنید",
+ "title": "نام"
+ },
+ "prompt": {
+ "placeholder": "لطفاً کلمات کلیدی نقش را وارد کنید",
+ "title": "تنظیمات نقش"
+ },
+ "tag": {
+ "placeholder": "لطفاً برچسبها را وارد کنید",
+ "title": "برچسب"
+ },
+ "title": "اطلاعات دستیار"
+ },
+ "settingChat": {
+ "autoCreateTopicThreshold": {
+ "desc": "پس از اینکه تعداد پیامهای فعلی از این مقدار بیشتر شود، بهطور خودکار موضوع ایجاد میشود",
+ "title": "آستانه تعداد پیامها"
+ },
+ "chatStyleType": {
+ "title": "سبک پنجره چت",
+ "type": {
+ "chat": "حالت گفتگو",
+ "docs": "حالت سند"
+ }
+ },
+ "compressThreshold": {
+ "desc": "وقتی تعداد پیامهای تاریخی فشردهنشده از این مقدار بیشتر شود، فشردهسازی انجام میشود",
+ "title": "آستانه فشردهسازی طول پیامهای تاریخی"
+ },
+ "enableAutoCreateTopic": {
+ "desc": "آیا در طول مکالمه بهطور خودکار موضوع ایجاد شود، فقط در موضوعات موقت اعمال میشود",
+ "title": "ایجاد خودکار موضوع"
+ },
+ "enableCompressHistory": {
+ "title": "فعالسازی خلاصهسازی خودکار تاریخچه پیامها"
+ },
+ "enableHistoryCount": {
+ "alias": "بدون محدودیت",
+ "limited": "فقط شامل {{number}} پیام مکالمه",
+ "setlimited": "استفاده از تعداد پیامهای تاریخی",
+ "title": "محدودیت تعداد پیامهای تاریخی",
+ "unlimited": "بدون محدودیت در تعداد پیامهای تاریخی"
+ },
+ "historyCount": {
+ "desc": "تعداد پیامهایی که در هر درخواست ارسال میشوند (شامل آخرین سوال نوشتهشده. هر سوال و پاسخ بهعنوان 1 محاسبه میشود)",
+ "title": "تعداد پیامهای همراه"
+ },
+ "inputTemplate": {
+ "desc": "آخرین پیام کاربر در این قالب پر میشود",
+ "placeholder": "قالب پیشپردازش {{text}} با اطلاعات ورودی لحظهای جایگزین میشود",
+ "title": "پیشپردازش ورودی کاربر"
+ },
+ "title": "تنظیمات چت"
+ },
+ "settingModel": {
+ "enableMaxTokens": {
+ "title": "فعالسازی محدودیت پاسخ"
+ },
+ "enableReasoningEffort": {
+ "title": "فعالسازی تنظیم شدت استدلال"
+ },
+ "frequencyPenalty": {
+ "desc": "هر چه مقدار بزرگتر باشد، واژگان متنوعتر و غنیتری استفاده میشود؛ هر چه مقدار کوچکتر باشد، واژگان سادهتر و عادیتر خواهند بود.",
+ "title": "تنوع واژگان"
+ },
+ "maxTokens": {
+ "desc": "حداکثر تعداد توکنهای استفادهشده در هر تعامل",
+ "title": "محدودیت پاسخ"
+ },
+ "model": {
+ "desc": "مدل {{provider}}",
+ "title": "مدل"
+ },
+ "params": {
+ "title": "پارامترهای پیشرفته"
+ },
+ "presencePenalty": {
+ "desc": "هر چه مقدار بزرگتر باشد، تمایل به استفاده از عبارات مختلف بیشتر میشود و از تکرار مفاهیم جلوگیری میکند؛ هر چه مقدار کوچکتر باشد، تمایل به استفاده از مفاهیم یا روایتهای تکراری بیشتر میشود و بیان یکدستتری خواهد داشت.",
+ "title": "گستردگی بیان"
+ },
+ "reasoningEffort": {
+ "desc": "هرچه مقدار بیشتر باشد، توانایی استدلال قویتر است، اما ممکن است زمان پاسخ و مصرف توکن را افزایش دهد",
+ "options": {
+ "high": "بالا",
+ "low": "پایین",
+ "medium": "متوسط"
+ },
+ "title": "شدت استدلال"
+ },
+ "temperature": {
+ "desc": "هر چه عدد بزرگتر باشد، پاسخها خلاقانهتر و تخیلیتر خواهند بود؛ هر چه عدد کوچکتر باشد، پاسخها دقیقتر خواهند بود",
+ "title": "فعالیت خلاقانه",
+ "warning": "اگر عدد فعالیت خلاقانه بیش از حد بزرگ باشد، خروجی ممکن است دچار اختلال شود"
+ },
+ "title": "تنظیمات مدل",
+ "topP": {
+ "desc": "چند احتمال را در نظر میگیرد، هر چه عدد بزرگتر باشد، پاسخهای بیشتری را میپذیرد؛ هر چه عدد کوچکتر باشد، تمایل به انتخاب پاسخهای محتملتر دارد. تغییر همزمان با فعالیت خلاقانه توصیه نمیشود",
+ "title": "باز بودن ذهن"
+ }
+ },
+ "settingPlugin": {
+ "title": "فهرست افزونهها"
+ },
+ "settingSystem": {
+ "accessCode": {
+ "desc": "مدیر دسترسی رمزگذاری شده را فعال کرده است",
+ "placeholder": "لطفاً رمز عبور دسترسی را وارد کنید",
+ "title": "رمز عبور دسترسی"
+ },
+ "oauth": {
+ "info": {
+ "desc": "وارد شدهاید",
+ "title": "اطلاعات حساب"
+ },
+ "signin": {
+ "action": "ورود",
+ "desc": "برای باز کردن قفل برنامه با SSO وارد شوید",
+ "title": "ورود به حساب"
+ },
+ "signout": {
+ "action": "خروج",
+ "confirm": "آیا از خروج مطمئن هستید؟",
+ "success": "خروج با موفقیت انجام شد"
+ }
+ },
+ "title": "تنظیمات سیستم"
+ },
+ "settingTTS": {
+ "openai": {
+ "sttModel": "مدل تشخیص گفتار OpenAI",
+ "title": "OpenAI",
+ "ttsModel": "مدل تبدیل متن به گفتار OpenAI"
+ },
+ "showAllLocaleVoice": {
+ "desc": "در صورت غیرفعال بودن، فقط منابع صوتی زبان فعلی نمایش داده میشود",
+ "title": "نمایش منابع صوتی همه زبانها"
+ },
+ "stt": "تنظیمات تشخیص گفتار",
+ "sttAutoStop": {
+ "desc": "در صورت غیرفعال بودن، تشخیص گفتار بهطور خودکار پایان نمییابد و باید بهصورت دستی دکمه پایان را فشار دهید",
+ "title": "پایان خودکار تشخیص گفتار"
+ },
+ "sttLocale": {
+ "desc": "زبان ورودی گفتار، این گزینه میتواند دقت تشخیص گفتار را افزایش دهد",
+ "title": "زبان تشخیص گفتار"
+ },
+ "sttService": {
+ "desc": "در این میان، browser به سرویس تشخیص گفتار بومی مرورگر اشاره دارد",
+ "title": "سرویس تشخیص گفتار"
+ },
+ "title": "سرویسهای گفتاری",
+ "tts": "تنظیمات تبدیل متن به گفتار",
+ "ttsService": {
+ "desc": "در صورت استفاده از سرویس تبدیل متن به گفتار OpenAI، باید اطمینان حاصل کنید که سرویس مدل OpenAI فعال است",
+ "title": "سرویس تبدیل متن به گفتار"
+ },
+ "voice": {
+ "desc": "برای دستیار فعلی یک صدا انتخاب کنید، منابع صوتی پشتیبانی شده توسط سرویسهای مختلف TTS متفاوت است",
+ "preview": "پیشنمایش منبع صوتی",
+ "title": "منبع صوتی تبدیل متن به گفتار"
+ }
+ },
+ "settingTheme": {
+ "avatar": {
+ "title": "آواتار"
+ },
+ "fontSize": {
+ "desc": "اندازه فونت محتوای چت",
+ "marks": {
+ "normal": "استاندارد"
+ },
+ "title": "اندازه فونت"
+ },
+ "lang": {
+ "autoMode": "دنبال کردن سیستم",
+ "title": "زبان"
+ },
+ "neutralColor": {
+ "desc": "سفارشیسازی طیف خاکستری با تمایلات رنگی مختلف",
+ "title": "رنگ خنثی"
+ },
+ "primaryColor": {
+ "desc": "سفارشیسازی رنگ اصلی",
+ "title": "رنگ اصلی"
+ },
+ "themeMode": {
+ "auto": "خودکار",
+ "dark": "تیره",
+ "light": "روشن",
+ "title": "حالت تم"
+ },
+ "title": "تنظیمات تم"
+ },
+ "submitAgentModal": {
+ "button": "ارسال دستیار",
+ "identifier": "شناسه دستیار",
+ "metaMiss": "لطفاً اطلاعات دستیار را تکمیل کنید و سپس ارسال نمایید. باید شامل نام، توضیحات و برچسبها باشد.",
+ "placeholder": "لطفاً شناسه دستیار را وارد کنید. باید منحصربهفرد باشد، مانند web-development",
+ "tooltips": "اشتراکگذاری در بازار دستیار"
+ },
+ "sync": {
+ "device": {
+ "deviceName": {
+ "hint": "برای شناسایی آسانتر، یک نام اضافه کنید",
+ "placeholder": "لطفاً نام دستگاه را وارد کنید",
+ "title": "نام دستگاه"
+ },
+ "title": "اطلاعات دستگاه",
+ "unknownBrowser": "مرورگر ناشناخته",
+ "unknownOS": "سیستم عامل ناشناخته"
+ },
+ "warning": {
+ "tip": "پس از یک دوره طولانی آزمایش عمومی در جامعه، ممکن است همگامسازی WebRTC نتواند بهطور پایدار نیازهای عمومی همگامسازی دادهها را برآورده کند. لطفاً پس از <1>راهاندازی سرور سیگنالدهی1>، از آن استفاده کنید."
+ },
+ "webrtc": {
+ "channelName": {
+ "desc": "WebRTC از این نام برای ایجاد کانال همگامسازی استفاده میکند، اطمینان حاصل کنید که نام کانال منحصربهفرد است",
+ "placeholder": "لطفاً نام کانال همگامسازی را وارد کنید",
+ "shuffle": "تولید تصادفی",
+ "title": "نام کانال همگامسازی"
+ },
+ "channelPassword": {
+ "desc": "برای اطمینان از خصوصی بودن کانال، رمز عبور اضافه کنید. فقط در صورت وارد کردن رمز عبور صحیح، دستگاه میتواند به کانال بپیوندد",
+ "placeholder": "لطفاً رمز عبور کانال همگامسازی را وارد کنید",
+ "title": "رمز عبور کانال همگامسازی"
+ },
+ "desc": "ارتباط دادهای همزمان و نقطهبهنقطه، دستگاهها باید همزمان آنلاین باشند تا همگامسازی انجام شود",
+ "enabled": {
+ "invalid": "لطفاً پس از وارد کردن سرور سیگنالدهی و نام کانال همگامسازی، آن را فعال کنید",
+ "title": "فعالسازی همگامسازی"
+ },
+ "signaling": {
+ "desc": "WebRTC از این آدرس برای همگامسازی استفاده میکند",
+ "placeholder": "لطفاً آدرس سرور سیگنالدهی را وارد کنید",
+ "title": "سرور سیگنالدهی"
+ },
+ "title": "همگامسازی WebRTC"
+ }
+ },
+ "systemAgent": {
+ "agentMeta": {
+ "label": "مدل تولید متادیتای دستیار",
+ "modelDesc": "مدلی که برای تولید نام، توضیحات، آواتار و برچسبهای دستیار استفاده میشود",
+ "title": "تولید خودکار اطلاعات دستیار"
+ },
+ "customPrompt": {
+ "addPrompt": "افزودن اعلان سفارشی",
+ "desc": "پس از پر کردن، دستیار سیستم از اعلان سفارشی برای تولید محتوا استفاده خواهد کرد",
+ "placeholder": "لطفاً اعلان سفارشی خود را وارد کنید",
+ "title": "اعلان سفارشی"
+ },
+ "historyCompress": {
+ "label": "مدل تاریخچه گفتگو",
+ "modelDesc": "مدلی که برای فشردهسازی تاریخچه گفتگو استفاده میشود",
+ "title": "خلاصهسازی خودکار تاریخچه گفتگو"
+ },
+ "queryRewrite": {
+ "label": "مدل بازنویسی پرسش",
+ "modelDesc": "مدلی که برای بهینهسازی پرسشهای کاربران استفاده میشود",
+ "title": "بازنویسی پرسشهای پایگاه دانش"
+ },
+ "thread": {
+ "label": "مدل نامگذاری زیرموضوع",
+ "modelDesc": "مدل مشخص شده برای تغییر نام خودکار زیرموضوعها",
+ "title": "نامگذاری خودکار زیرموضوع"
+ },
+ "title": "دستیار سیستم",
+ "topic": {
+ "label": "مدل نامگذاری موضوع",
+ "modelDesc": "مدلی که برای تغییر خودکار نام موضوعات استفاده میشود",
+ "title": "نامگذاری خودکار موضوع"
+ },
+ "translation": {
+ "label": "مدل ترجمه",
+ "modelDesc": "مدلی که برای ترجمه استفاده میشود",
+ "title": "ترجمه محتوای پیام"
+ }
+ },
+ "tab": {
+ "about": "درباره",
+ "agent": "دستیار پیشفرض",
+ "common": "تنظیمات عمومی",
+ "experiment": "آزمایش",
+ "llm": "مدل زبان",
+ "provider": "ارائه دهنده خدمات هوش مصنوعی",
+ "sync": "همگامسازی ابری",
+ "system-agent": "دستیار سیستم",
+ "tts": "خدمات صوتی"
+ },
+ "tools": {
+ "builtins": {
+ "groupName": "افزونههای داخلی"
+ },
+ "disabled": "مدل فعلی از فراخوانی توابع پشتیبانی نمیکند و نمیتوان از افزونهها استفاده کرد",
+ "plugins": {
+ "enabled": "{{num}} فعال شده است",
+ "groupName": "افزونههای شخص ثالث",
+ "noEnabled": "هیچ افزونه فعالی وجود ندارد",
+ "store": "فروشگاه افزونهها"
+ },
+ "title": "افزونههای گسترش"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/thread.json b/DigitalHumanWeb/locales/fa-IR/thread.json
new file mode 100644
index 0000000..cd9a216
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "شما در حال حذف این زیرموضوع هستید. پس از حذف، امکان بازیابی آن وجود نخواهد داشت. لطفاً با احتیاط عمل کنید."
+ },
+ "newPortalThread": {
+ "includeContext": "شامل زمینه موضوع",
+ "title": "باز کردن زیرموضوع جدید"
+ },
+ "notSupportMultiModals": "زیرموضوعها فعلاً از بارگذاری فایل/عکس پشتیبانی نمیکنند، در صورت نیاز، خوشحال میشویم که پیام بگذارید: <1>💬 بحثخانه1>"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/tool.json b/DigitalHumanWeb/locales/fa-IR/tool.json
new file mode 100644
index 0000000..f728c1c
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/tool.json
@@ -0,0 +1,28 @@
+{
+ "dalle": {
+ "autoGenerate": "تولید خودکار",
+ "downloading": "لینکهای تصاویر تولید شده توسط DallE3 فقط به مدت ۱ ساعت معتبر هستند، در حال ذخیرهسازی تصاویر به صورت محلی...",
+ "generate": "تولید",
+ "generating": "در حال تولید...",
+ "images": "تصاویر:",
+ "prompt": "کلمات کلیدی"
+ },
+ "search": {
+ "createNewSearch": "ایجاد جستجوی جدید",
+ "emptyResult": "نتیجهای یافت نشد، لطفاً کلمات کلیدی را تغییر داده و دوباره تلاش کنید",
+ "genAiMessage": "ایجاد پیام دستیار",
+ "includedTooltip": "نتایج جستجو فعلی در زمینه مکالمه قرار میگیرد",
+ "keywords": "کلمات کلیدی:",
+ "scoreTooltip": "امتیاز مرتبط بودن، هرچه این امتیاز بالاتر باشد، به کلمات کلیدی جستجو نزدیکتر است",
+ "searchBar": {
+ "button": "جستجو",
+ "placeholder": "کلمات کلیدی",
+ "tooltip": "نتایج جستجو دوباره دریافت خواهد شد و یک پیام خلاصه جدید ایجاد خواهد شد"
+ },
+ "searchEngine": "موتور جستجو:",
+ "searchResult": "تعداد جستجو:",
+ "summary": "خلاصه",
+ "summaryTooltip": "خلاصه محتوای فعلی",
+ "viewMoreResults": "مشاهده {{results}} نتیجه بیشتر"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/topic.json b/DigitalHumanWeb/locales/fa-IR/topic.json
new file mode 100644
index 0000000..5267efb
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "نامگذاری هوشمند",
+ "confirmRemoveAll": "در حال حذف تمام موضوعات، پس از حذف قابل بازیابی نخواهد بود، لطفاً با احتیاط عمل کنید.",
+ "confirmRemoveTopic": "در حال حذف این موضوع، پس از حذف قابل بازیابی نخواهد بود، لطفاً با احتیاط عمل کنید.",
+ "confirmRemoveUnstarred": "در حال حذف موضوعات بدون علامت، پس از حذف قابل بازیابی نخواهد بود، لطفاً با احتیاط عمل کنید.",
+ "duplicate": "ایجاد نسخه",
+ "export": "صادرات موضوع",
+ "removeAll": "حذف تمام موضوعات",
+ "removeUnstarred": "حذف موضوعات بدون علامت"
+ },
+ "defaultTitle": "موضوع پیشفرض",
+ "duplicateLoading": "در حال کپی موضوع...",
+ "duplicateSuccess": "کپی موضوع با موفقیت انجام شد",
+ "favorite": "علاقهمندی",
+ "groupMode": {
+ "ascMessages": "بر اساس تعداد پیامها به ترتیب صعودی",
+ "byTime": "بر اساس زمان گروهبندی",
+ "descMessages": "بر اساس تعداد پیامها به ترتیب نزولی",
+ "flat": "بدون گروهبندی"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "این ماه",
+ "today": "امروز",
+ "week": "این هفته",
+ "yesterday": "دیروز"
+ }
+ },
+ "guide": {
+ "desc": "برای ذخیره مکالمه فعلی به عنوان موضوع تاریخی و شروع یک دور جدید مکالمه، دکمه سمت چپ ارسال را کلیک کنید.",
+ "title": "لیست موضوعات"
+ },
+ "searchPlaceholder": "جستجوی موضوع...",
+ "searchResultEmpty": "نتیجهای برای جستجو یافت نشد",
+ "temp": "موقت",
+ "title": "موضوع"
+}
diff --git a/DigitalHumanWeb/locales/fa-IR/welcome.json b/DigitalHumanWeb/locales/fa-IR/welcome.json
new file mode 100644
index 0000000..9c43f44
--- /dev/null
+++ b/DigitalHumanWeb/locales/fa-IR/welcome.json
@@ -0,0 +1,45 @@
+{
+ "guide": {
+ "agents": {
+ "replaceBtn": "تغییر دسته",
+ "title": "دستیارهای جدید پیشنهادی:"
+ },
+ "defaultMessage": "من دستیار هوشمند شخصی شما {{appName}} هستم، چطور میتوانم به شما کمک کنم؟\nاگر به دستیارهای حرفهایتر یا سفارشی نیاز دارید، میتوانید با کلیک بر روی `+` یک دستیار سفارشی ایجاد کنید.",
+ "defaultMessageWithoutCreate": "من دستیار هوشمند شخصی شما {{appName}} هستم، چطور میتوانم به شما کمک کنم؟",
+ "qa": {
+ "q01": "LobeHub چیست؟",
+ "q02": "{{appName}} چیست؟",
+ "q03": "آیا {{appName}} پشتیبانی جامعه دارد؟",
+ "q04": "{{appName}} چه قابلیتهایی دارد؟",
+ "q05": "چگونه میتوان {{appName}} را مستقر و استفاده کرد؟",
+ "q06": "قیمتگذاری {{appName}} چگونه است؟",
+ "q07": "آیا {{appName}} رایگان است؟",
+ "q08": "آیا نسخه ابری وجود دارد؟",
+ "q09": "آیا از مدلهای زبانی محلی پشتیبانی میشود؟",
+ "q10": "آیا از تشخیص و تولید تصویر پشتیبانی میشود؟",
+ "q11": "آیا از تبدیل متن به گفتار و تشخیص گفتار پشتیبانی میشود؟",
+ "q12": "آیا از سیستم افزونهها پشتیبانی میشود؟",
+ "q13": "آیا بازار مخصوصی برای دریافت GPTها وجود دارد؟",
+ "q14": "آیا از چندین ارائهدهنده خدمات هوش مصنوعی پشتیبانی میشود؟",
+ "q15": "اگر در حین استفاده با مشکلی مواجه شدم، چه کاری باید انجام دهم؟"
+ },
+ "questions": {
+ "moreBtn": "بیشتر بدانید",
+ "title": "سوالات متداول:"
+ },
+ "welcome": {
+ "afternoon": "عصر بخیر",
+ "morning": "صبح بخیر",
+ "night": "شب بخیر",
+ "noon": "ظهر بخیر"
+ }
+ },
+ "header": "خوش آمدید به استفاده",
+ "pickAgent": "یا از الگوهای دستیار زیر انتخاب کنید",
+ "skip": "رد کردن ایجاد",
+ "slogan": {
+ "desc1": "خوشههای مغزی را فعال کنید و جرقههای تفکر را برانگیزید. دستیار هوشمند شما همیشه در کنار شماست.",
+ "desc2": "اولین دستیار خود را ایجاد کنید، بیایید شروع کنیم~",
+ "title": "یک مغز هوشمندتر برای خود داشته باشید"
+ }
+}
diff --git a/DigitalHumanWeb/locales/fr-FR/auth.json b/DigitalHumanWeb/locales/fr-FR/auth.json
index 9f51164..fa0b81a 100644
--- a/DigitalHumanWeb/locales/fr-FR/auth.json
+++ b/DigitalHumanWeb/locales/fr-FR/auth.json
@@ -1,8 +1,96 @@
{
- "login": "Connexion",
- "loginOrSignup": "Connexion / Inscription",
- "profile": "Profil",
- "security": "Sécurité",
- "signout": "Déconnexion",
- "signup": "Inscription"
+ "date": {
+ "prevMonth": "Le mois dernier",
+ "recent30Days": "Les 30 derniers jours"
+ },
+ "header": {
+ "desc": "Gérez les informations de votre compte.",
+ "title": "Compte"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Inactif",
+ "more": "Actif"
+ },
+ "months": {
+ "apr": "Avr",
+ "aug": "Août",
+ "dec": "Déc",
+ "feb": "Fév",
+ "jan": "Jan",
+ "jul": "Juil",
+ "jun": "Juin",
+ "mar": "Mar",
+ "may": "Mai",
+ "nov": "Nov",
+ "oct": "Oct",
+ "sep": "Sep"
+ },
+ "tooltip": "{{date}} a envoyé {{count}} messages ce jour-là",
+ "totalCount": "Un total de {{count}} messages envoyés au cours de l'année dernière"
+ },
+ "login": "Se connecter",
+ "loginOrSignup": "Se connecter / S'inscrire",
+ "profile": {
+ "avatar": "Avatar",
+ "email": "Adresse e-mail",
+ "sso": {
+ "loading": "Chargement des comptes tiers liés",
+ "providers": "Comptes connectés",
+ "unlink": {
+ "description": "Après la déconnexion, vous ne pourrez plus vous connecter avec le compte {{provider}} « {{providerAccountId}} ». Si vous avez besoin de rattacher le compte {{provider}} à votre compte actuel, assurez-vous que l'adresse e-mail du compte {{provider}} soit {{email}}. Nous procéderons automatiquement au rattachement lors de votre prochaine connexion.",
+ "forbidden": "Vous devez conserver au moins un compte tiers lié.",
+ "title": "Voulez-vous vraiment déconnecter ce compte tiers {{provider}} ?"
+ }
+ },
+ "username": "Nom d'utilisateur"
+ },
+ "signout": "Se déconnecter",
+ "signup": "S'inscrire",
+ "stats": {
+ "aiheatmaps": "Indice d'activité",
+ "assistants": "Assistants",
+ "assistantsRank": {
+ "left": "Assistant",
+ "right": "Sujets",
+ "title": "Classement d'utilisation des assistants"
+ },
+ "createdAt": "Inscrit le",
+ "days": "jours",
+ "empty": {
+ "desc": "Veuillez accumuler plus de données de chat pour voir",
+ "title": "Aucune donnée"
+ },
+ "lastYearActivity": "activité au cours de l'année dernière",
+ "loginGuide": {
+ "f1": "Obtenez un quota gratuit",
+ "f2": "Synchronisez les messages sur plusieurs appareils",
+ "f3": "Profitez d'un assistant riche",
+ "f4": "Explorez des plugins puissants",
+ "title": "Après vous être connecté, vous pouvez :"
+ },
+ "messages": "Messages",
+ "modelsRank": {
+ "left": "Modèle",
+ "right": "Messages",
+ "title": "Classement d'utilisation des modèles"
+ },
+ "share": {
+ "title": "Mon indice d'activité IA"
+ },
+ "topics": "Sujets",
+ "topicsRank": {
+ "left": "Sujet",
+ "right": "Messages",
+ "title": "Classement du contenu des sujets"
+ },
+ "updatedAt": "Mis à jour le",
+ "welcome": "{{username}}, c'est votre {{days}} jour avec {{appName}}",
+ "words": "Mots"
+ },
+ "tab": {
+ "profile": "Profil",
+ "security": "Sécurité",
+ "stats": "Statistiques"
+ }
}
diff --git a/DigitalHumanWeb/locales/fr-FR/changelog.json b/DigitalHumanWeb/locales/fr-FR/changelog.json
new file mode 100644
index 0000000..ecff38c
--- /dev/null
+++ b/DigitalHumanWeb/locales/fr-FR/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Suivez-nous sur X",
+ "subscribeToUpdates": "Abonnez-vous aux mises à jour",
+ "versions": "Détails de la version"
+ },
+ "addedWhileAway": "Nous avons ajouté de nouvelles fonctionnalités pendant votre absence.",
+ "allChangelog": "Voir tous les journaux de mise à jour",
+ "description": "Suivez en continu les nouvelles fonctionnalités et améliorations de {{appName}}",
+ "pagination": {
+ "next": "Page suivante",
+ "older": "Voir les modifications antérieures"
+ },
+ "readDetails": "Lire les détails",
+ "title": "Journal des mises à jour",
+ "versionDetails": "Détails de la version",
+ "welcomeBack": "Bienvenue de nouveau!"
+}
diff --git a/DigitalHumanWeb/locales/fr-FR/chat.json b/DigitalHumanWeb/locales/fr-FR/chat.json
index 27f4ff9..b8571ab 100644
--- a/DigitalHumanWeb/locales/fr-FR/chat.json
+++ b/DigitalHumanWeb/locales/fr-FR/chat.json
@@ -8,6 +8,7 @@
"agents": "Assistant",
"artifact": {
"generating": "Génération en cours",
+ "inThread": "Impossible de voir dans le sous-sujet, veuillez passer à la zone de discussion principale.",
"thinking": "En réflexion",
"thought": "Processus de pensée",
"unknownTitle": "Œuvre sans nom"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Copie",
"emptyAgent": "Aucun assistant disponible",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Le coût de génération d'une seule conversation peut être réduit de 90 % au maximum, avec une vitesse de réponse augmentée de 4 fois (<1>En savoir plus1>). Une fois activé, la limite du nombre de messages historiques sera automatiquement désactivée.",
+ "title": "Activer le cache de contexte"
+ },
+ "enableReasoning": {
+ "desc": "Basé sur les restrictions du mécanisme Claude Thinking (<1>En savoir plus1>), une fois activé, la limite du nombre de messages historiques sera automatiquement désactivée.",
+ "title": "Activer la réflexion approfondie"
+ },
+ "reasoningBudgetToken": {
+ "title": "Token de consommation de réflexion"
+ },
+ "title": "Fonctionnalités d'extension du modèle"
+ },
+ "history": {
+ "title": "L'assistant ne se souviendra que des {{count}} derniers messages"
+ },
"historyRange": "Plage d'historique",
+ "historySummary": "Résumé des messages historiques",
"inbox": {
"desc": "Débloquez le potentiel de votre esprit. Votre agent intelligent est là pour discuter avec vous de tout et de rien.",
"title": "Discutons un peu"
@@ -45,6 +64,9 @@
"stop": "Arrêter",
"warp": "Saut de ligne"
},
+ "intentUnderstanding": {
+ "title": "En train de comprendre et d'analyser votre intention..."
+ },
"knowledgeBase": {
"all": "Tout le contenu",
"allFiles": "Tous les fichiers",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Supprimer et régénérer",
+ "deleteDisabledByThreads": "Il existe des sous-sujets, la suppression n'est pas possible.",
"regenerate": "Régénérer"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Crédit",
+ "creditPricing": "Tarification",
+ "creditTooltip": "Pour faciliter le comptage, nous convertissons 1 $ en 1M de crédits, par exemple, 3 $/M tokens équivaut à 3 crédits/token",
+ "pricing": {
+ "inputCachedTokens": "Entrée mise en cache {{amount}}/crédit · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M caractères",
+ "inputMinutes": "${{amount}}/minute",
+ "inputTokens": "Entrée {{amount}}/crédit · ${{amount}}/M",
+ "outputTokens": "Sortie {{amount}}/crédit · ${{amount}}/M",
+ "writeCacheInputTokens": "Écriture de cache d'entrée {{amount}}/points · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Prix moyen",
+ "input": "Entrée",
+ "inputAudio": "Entrée audio",
+ "inputCached": "Entrée mise en cache",
+ "inputCitation": "Citation d'entrée",
+ "inputText": "Entrée texte",
+ "inputTitle": "Détails de l'entrée",
+ "inputUncached": "Entrée non mise en cache",
+ "inputWriteCached": "Écriture de cache d'entrée",
+ "output": "Sortie",
+ "outputAudio": "Sortie audio",
+ "outputText": "Sortie texte",
+ "outputTitle": "Détails de la sortie",
+ "reasoning": "Raisonnement approfondi",
+ "title": "Détails de génération",
+ "total": "Total consommé"
+ }
+ },
"newAgent": "Nouvel agent",
"pin": "Épingler",
"pinOff": "Désépingler",
@@ -81,6 +137,32 @@
},
"regenerate": "Regénérer",
"roleAndArchive": "Rôle et archivage",
+ "search": {
+ "grounding": {
+ "searchQueries": "Mots-clés de recherche",
+ "title": "{{count}} résultats trouvés"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Détermine intelligemment si une recherche est nécessaire en fonction du contenu de la conversation",
+ "title": "Connexion intelligente"
+ },
+ "off": {
+ "desc": "Utilise uniquement les connaissances de base du modèle, sans recherche en ligne",
+ "title": "Déconnexion"
+ },
+ "on": {
+ "desc": "Effectue en continu des recherches en ligne pour obtenir les informations les plus récentes",
+ "title": "Toujours connecté"
+ },
+ "useModelBuiltin": "Utiliser le moteur de recherche intégré du modèle"
+ },
+ "searchModel": {
+ "desc": "Le modèle actuel ne prend pas en charge les appels de fonction, il doit donc être associé à un modèle prenant en charge les appels de fonction pour effectuer une recherche en ligne",
+ "title": "Modèle d'assistance à la recherche"
+ },
+ "title": "Recherche en ligne"
+ },
"searchAgentPlaceholder": "Assistant de recherche...",
"sendPlaceholder": "Saisissez votre message...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Le nom du groupe doit comporter entre 1 et 20 caractères"
},
"shareModal": {
+ "copy": "Copier",
"download": "Télécharger la capture d'écran",
+ "downloadFile": "Télécharger le fichier",
+ "exportTitle": "Titre par défaut",
"imageType": "Type d'image",
+ "includeTool": "Inclure les messages de l'outil",
+ "includeUser": "Inclure les messages de l'utilisateur",
"screenshot": "Capture d'écran",
"settings": "Paramètres d'exportation",
- "shareToShareGPT": "Générer un lien de partage ShareGPT",
+ "text": "Texte",
"withBackground": "Avec image de fond",
"withFooter": "Avec pied de page",
"withPluginInfo": "Avec informations sur le plugin",
+ "withRole": "Inclure le rôle du message",
"withSystemRole": "Avec rôle de l'agent"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "En cours de reconnaissance...",
"prettifying": "En cours d'embellissement..."
},
- "temp": "Temporaire",
+ "thread": {
+ "divider": "Sous-sujet",
+ "threadMessageCount": "{{messageCount}} messages",
+ "title": "Sous-sujet"
+ },
"tokenDetails": {
"chats": "Messages de discussion",
+ "historySummary": "Résumé historique",
"rest": "Restant disponible",
"systemRole": "Rôle système",
"title": "Détails du jeton",
@@ -131,29 +224,10 @@
"used": "Utilisé"
},
"topic": {
- "actions": {
- "autoRename": "Renommer automatiquement",
- "duplicate": "Créer une copie",
- "export": "Exporter le sujet"
- },
"checkOpenNewTopic": "Voulez-vous ouvrir un nouveau sujet ?",
"checkSaveCurrentMessages": "Voulez-vous enregistrer la conversation actuelle en tant que sujet ?",
- "confirmRemoveAll": "Vous êtes sur le point de supprimer tous les sujets. Cette action est irréversible. Veuillez confirmer.",
- "confirmRemoveTopic": "Vous êtes sur le point de supprimer ce sujet. Cette action est irréversible. Veuillez confirmer.",
- "confirmRemoveUnstarred": "Vous êtes sur le point de supprimer les sujets non favoris. Cette action est irréversible. Veuillez confirmer.",
- "defaultTitle": "Sujet par défaut",
- "duplicateLoading": "Duplication du sujet en cours...",
- "duplicateSuccess": "Sujet dupliqué avec succès",
- "guide": {
- "desc": "Cliquez sur le bouton à gauche pour enregistrer la conversation actuelle comme un sujet historique et démarrer une nouvelle session.",
- "title": "Liste des sujets"
- },
"openNewTopic": "Ouvrir un nouveau sujet",
- "removeAll": "Supprimer tous les sujets",
- "removeUnstarred": "Supprimer les sujets non favoris",
- "saveCurrentMessages": "Enregistrer la conversation actuelle en tant que sujet",
- "searchPlaceholder": "Rechercher un sujet...",
- "title": "Liste des sujets"
+ "saveCurrentMessages": "Enregistrer la conversation actuelle en tant que sujet"
},
"translate": {
"action": "Traduire",
@@ -184,5 +258,6 @@
"processing": "Traitement du fichier..."
}
}
- }
+ },
+ "zenMode": "Mode de concentration"
}
diff --git a/DigitalHumanWeb/locales/fr-FR/common.json b/DigitalHumanWeb/locales/fr-FR/common.json
index f65b733..d4122f5 100644
--- a/DigitalHumanWeb/locales/fr-FR/common.json
+++ b/DigitalHumanWeb/locales/fr-FR/common.json
@@ -9,15 +9,79 @@
"title": "Bienvenue à {{name}}"
}
},
- "appInitializing": "L'application est en cours de démarrage...",
+ "appLoading": {
+ "appIdle": "Préparation du démarrage",
+ "appInitializing": "L'application se charge...",
+ "failed": "Désolé, l'initialisation de l'application a échoué. Veuillez consulter les détails pour résoudre le problème.",
+ "finished": "Initialisation de la base de données terminée",
+ "goToChat": "Chargement de la page de chat...",
+ "initAuth": "Initialisation du service d'authentification...",
+ "initUser": "Initialisation de l'état de l'utilisateur...",
+ "initializing": "Initialisation de la base de données PGlite...",
+ "loadingDependencies": "Chargement des dépendances...",
+ "loadingWasm": "Chargement du module WASM...",
+ "migrating": "Exécution de la migration des tables de données...",
+ "ready": "La base de données est prête",
+ "showDetail": "Voir les détails"
+ },
"autoGenerate": "Générer automatiquement",
"autoGenerateTooltip": "Générer automatiquement la description de l'agent basée sur les suggestions",
"autoGenerateTooltipDisabled": "Veuillez saisir un mot-clé avant d'activer la fonction de complétion automatique",
"back": "Retour",
"batchDelete": "Suppression en masse",
"blog": "Blog des produits",
+ "branching": "Créer un sous-sujet",
+ "branchingDisable": "La fonction « sous-sujet » n'est disponible que dans la version serveur. Si vous avez besoin de cette fonctionnalité, veuillez passer en mode de déploiement serveur ou utiliser LobeChat Cloud.",
"cancel": "Annuler",
"changelog": "Journal des modifications",
+ "clientDB": {
+ "autoInit": {
+ "title": "Initialisation de la base de données PGlite"
+ },
+ "error": {
+ "desc": "Nous sommes désolés, une erreur est survenue lors de l'initialisation de la base de données Pglite. Veuillez cliquer sur le bouton pour réessayer. Si l'erreur persiste après plusieurs tentatives, veuillez <1>soumettre un problème1>, nous vous aiderons à le résoudre dans les meilleurs délais.",
+ "detail": "Raison de l'erreur : [[{{type}}] {{message}}. Détails ci-dessous :",
+ "retry": "Réessayer",
+ "title": "Échec de l'initialisation de la base de données"
+ },
+ "initing": {
+ "error": "Une erreur s'est produite, veuillez réessayer",
+ "idle": "En attente d'initialisation...",
+ "initializing": "Initialisation en cours...",
+ "loadingDependencies": "Chargement des dépendances...",
+ "loadingWasmModule": "Chargement du module WASM...",
+ "migrating": "Exécution de la migration des tables de données...",
+ "ready": "Base de données prête"
+ },
+ "modal": {
+ "desc": "Activez la base de données client PGlite pour stocker de manière persistante les données de discussion dans votre navigateur et utiliser des fonctionnalités avancées telles que la base de connaissances.",
+ "enable": "Activer maintenant",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Consolidez votre base de connaissances personnelle et engagez facilement des conversations avec votre assistant (bientôt disponible)",
+ "title": "Support des conversations de base de connaissances, activez votre deuxième cerveau"
+ },
+ "localFirst": {
+ "desc": "Les données de chat sont entièrement stockées dans le navigateur, vos données sont toujours sous votre contrôle.",
+ "title": "Priorité locale, confidentialité avant tout"
+ },
+ "pglite": {
+ "desc": "Construit sur PGlite, prend en charge nativement les fonctionnalités avancées AI Native (recherche vectorielle)",
+ "title": "Nouvelle architecture de stockage client de nouvelle génération"
+ }
+ },
+ "init": {
+ "desc": "Initialisation de la base de données en cours, cela peut prendre de 5 à 30 secondes selon la connexion réseau.",
+ "title": "Initialisation de la base de données PGlite en cours"
+ },
+ "title": "Activer la base de données client"
+ },
+ "ready": {
+ "button": "Utiliser maintenant",
+ "desc": "Prêt à l'emploi",
+ "title": "Base de données PGlite prête"
+ }
+ },
"close": "Fermer",
"contact": "Nous contacter",
"copy": "Copier",
@@ -112,6 +176,7 @@
"en": "Anglais",
"en-US": "Anglais",
"es-ES": "Espagnol",
+ "fa-IR": "persan",
"fi-FI": "Finnois",
"fr-FR": "français",
"hi-IN": "Hindi",
@@ -153,6 +218,7 @@
"pinOff": "Désactiver l'épinglage",
"privacy": "Politique de confidentialité",
"regenerate": "Régénérer",
+ "releaseNotes": "Détails de la version",
"rename": "Renommer",
"reset": "Réinitialiser",
"retry": "Réessayer",
@@ -209,6 +275,7 @@
},
"temp": "Temporaire",
"terms": "Conditions de service",
+ "update": "Mise à jour",
"updateAgent": "Mettre à jour les informations de l'agent",
"upgradeVersion": {
"action": "Mettre à jour",
@@ -219,6 +286,7 @@
"anonymousNickName": "Utilisateur anonyme",
"billing": "Gestion de la facturation",
"cloud": "Découvrir {{name}}",
+ "community": "Version communautaire",
"data": "Stockage des données",
"defaultNickname": "Utilisateur de la version communautaire",
"discord": "Support de la communauté",
@@ -228,7 +296,6 @@
"help": "Centre d'aide",
"moveGuide": "Le bouton de configuration a été déplacé ici",
"plans": "Forfaits d'abonnement",
- "preview": "Aperçu",
"profile": "Gestion du compte",
"setting": "Paramètres de l'application",
"usages": "Statistiques d'utilisation"
diff --git a/DigitalHumanWeb/locales/fr-FR/components.json b/DigitalHumanWeb/locales/fr-FR/components.json
index 5c1c1c4..02641ec 100644
--- a/DigitalHumanWeb/locales/fr-FR/components.json
+++ b/DigitalHumanWeb/locales/fr-FR/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Découpage par lots",
"chunking": "Découpage",
"chunkingTooltip": "Divisez le fichier en plusieurs blocs de texte et vectorisez-les pour une recherche sémantique et un dialogue sur le fichier",
+ "chunkingUnsupported": "Ce fichier ne prend pas en charge le fractionnement",
"confirmDelete": "Vous allez supprimer ce fichier. Une fois supprimé, il ne pourra pas être récupéré. Veuillez confirmer votre action.",
"confirmDeleteMultiFiles": "Vous allez supprimer les {{count}} fichiers sélectionnés. Une fois supprimés, ils ne pourront pas être récupérés. Veuillez confirmer votre action.",
"confirmRemoveFromKnowledgeBase": "Vous allez retirer les {{count}} fichiers sélectionnés de la base de connaissances. Une fois retirés, les fichiers resteront visibles dans tous les fichiers. Veuillez confirmer votre action.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Retour"
},
+ "MaxTokenSlider": {
+ "unlimited": "Illimité"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Modèle personnalisé par défaut prenant en charge à la fois les appels de fonction et la reconnaissance visuelle. Veuillez vérifier la disponibilité de ces capacités en fonction de vos besoins réels.",
"file": "Ce modèle prend en charge la lecture et la reconnaissance de fichiers téléchargés.",
"functionCall": "Ce modèle prend en charge les appels de fonction.",
+ "reasoning": "Ce modèle prend en charge une réflexion approfondie",
+ "search": "Ce modèle prend en charge la recherche en ligne",
"tokens": "Ce modèle prend en charge jusqu'à {{tokens}} jetons par session.",
"vision": "Ce modèle prend en charge la reconnaissance visuelle."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Aucun modèle activé. Veuillez vous rendre dans les paramètres pour l'activer.",
+ "emptyProvider": "Aucun fournisseur activé, veuillez aller dans les paramètres pour l'activer",
+ "goToSettings": "Aller aux paramètres",
"provider": "Fournisseur"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "En raison des restrictions de sécurité des navigateurs, vous devez configurer les paramètres CORS pour utiliser Ollama correctement.",
+ "linux": {
+ "env": "Ajoutez `Environment` sous la section [Service], et ajoutez la variable d'environnement OLLAMA_ORIGINS :",
+ "reboot": "Rechargez systemd et redémarrez Ollama",
+ "systemd": "Appelez systemd pour éditer le service ollama :"
+ },
+ "macos": "Veuillez ouvrir l'application « Terminal », collez la commande suivante et appuyez sur Entrée pour l'exécuter",
+ "reboot": "Veuillez redémarrer le service Ollama après l'exécution",
+ "title": "Configurer Ollama pour autoriser l'accès CORS",
+ "windows": "Sous Windows, cliquez sur « Panneau de configuration », puis accédez à l'édition des variables d'environnement système. Créez une nouvelle variable d'environnement nommée « OLLAMA_ORIGINS » pour votre compte utilisateur, avec la valeur * , puis cliquez sur « OK/Appliquer » pour enregistrer"
+ },
+ "install": {
+ "description": "Veuillez vous assurer que vous avez démarré Ollama. Si vous n'avez pas téléchargé Ollama, veuillez vous rendre sur le site officiel <1>pour le télécharger1>",
+ "docker": "Si vous préférez utiliser Docker, Ollama propose également une image Docker officielle que vous pouvez tirer avec la commande suivante :",
+ "linux": {
+ "command": "Installez avec la commande suivante :",
+ "manual": "Ou, vous pouvez également consulter le <1>guide d'installation manuelle pour Linux1> pour l'installer vous-même"
+ },
+ "title": "Installer et démarrer l'application Ollama localement",
+ "windowsTab": "Windows (version préliminaire)"
+ }
+ },
+ "Thinking": {
+ "thinking": "En pleine réflexion...",
+ "thought": "Pensée approfondie (durée : {{duration}} secondes)",
+ "thoughtWithDuration": "Pensée approfondie"
}
}
diff --git a/DigitalHumanWeb/locales/fr-FR/discover.json b/DigitalHumanWeb/locales/fr-FR/discover.json
index 508b8d0..5fb3a75 100644
--- a/DigitalHumanWeb/locales/fr-FR/discover.json
+++ b/DigitalHumanWeb/locales/fr-FR/discover.json
@@ -126,6 +126,10 @@
"title": "Fraîcheur des sujets"
},
"range": "Plage",
+ "reasoning_effort": {
+ "desc": "Ce paramètre contrôle l'intensité de raisonnement du modèle avant de générer une réponse. Une faible intensité privilégie la rapidité de réponse et économise des tokens, tandis qu'une forte intensité offre un raisonnement plus complet, mais consomme plus de tokens et ralentit la réponse. La valeur par défaut est moyenne, équilibrant précision du raisonnement et rapidité de réponse.",
+ "title": "Intensité de raisonnement"
+ },
"temperature": {
"desc": "Ce paramètre influence la diversité des réponses du modèle. Des valeurs plus basses entraînent des réponses plus prévisibles et typiques, tandis que des valeurs plus élevées encouragent des réponses plus variées et moins courantes. Lorsque la valeur est fixée à 0, le modèle donne toujours la même réponse pour une entrée donnée.",
"title": "Aléatoire"
diff --git a/DigitalHumanWeb/locales/fr-FR/error.json b/DigitalHumanWeb/locales/fr-FR/error.json
index 5602d68..84c2d8c 100644
--- a/DigitalHumanWeb/locales/fr-FR/error.json
+++ b/DigitalHumanWeb/locales/fr-FR/error.json
@@ -12,8 +12,14 @@
"retry": "Recharger",
"title": "Un problème est survenu sur la page.."
},
- "fetchError": "Échec de la requête",
- "fetchErrorDetail": "Détails de l'erreur",
+ "fetchError": {
+ "detail": "Détails de l'erreur",
+ "title": "Échec de la requête"
+ },
+ "loginRequired": {
+ "desc": "Vous allez être redirigé vers la page de connexion",
+ "title": "Veuillez vous connecter pour utiliser cette fonctionnalité"
+ },
"notFound": {
"backHome": "Retour à la page d'accueil",
"check": "Veuillez vérifier si votre URL est correcte",
@@ -51,22 +57,34 @@
"431": "Désolé, les en-têtes de votre demande sont trop volumineux pour être traités par le serveur",
"451": "Désolé, pour des raisons légales, le serveur refuse de fournir cette ressource",
"500": "Désolé, le serveur semble rencontrer des difficultés et ne peut temporairement pas traiter votre requête. Veuillez réessayer plus tard",
+ "501": "Désolé, le serveur ne sait pas encore comment traiter cette demande, veuillez vérifier si votre opération est correcte.",
"502": "Désolé, le serveur semble perdu et ne peut temporairement pas fournir de service. Veuillez réessayer plus tard",
"503": "Désolé, le serveur ne peut actuellement pas traiter votre requête, probablement en raison d'une surcharge ou de travaux de maintenance. Veuillez réessayer plus tard",
"504": "Désolé, le serveur n'a pas reçu de réponse de la part du serveur amont. Veuillez réessayer plus tard",
+ "505": "Désolé, le serveur ne prend pas en charge la version HTTP que vous utilisez, veuillez mettre à jour et réessayer.",
+ "506": "Désolé, il y a un problème de configuration du serveur, veuillez contacter l'administrateur pour résoudre ce problème.",
+ "507": "Désolé, le serveur n'a pas suffisamment d'espace de stockage pour traiter votre demande, veuillez réessayer plus tard.",
+ "509": "Désolé, la bande passante du serveur est épuisée, veuillez réessayer plus tard.",
+ "510": "Désolé, le serveur ne prend pas en charge l'extension demandée, veuillez contacter l'administrateur.",
+ "524": "Désolé, le serveur a dépassé le délai d'attente en attendant une réponse, cela peut être dû à une réponse trop lente, veuillez réessayer plus tard.",
"AgentRuntimeError": "Erreur d'exécution du modèle linguistique Lobe, veuillez vérifier les informations ci-dessous ou réessayer",
+ "ConnectionCheckFailed": "La réponse est vide, veuillez vérifier si l'URL du proxy API se termine par `/v1`",
+ "ExceededContextWindow": "Le contenu de la demande actuelle dépasse la longueur que le modèle peut traiter. Veuillez réduire la quantité de contenu et réessayer.",
"FreePlanLimit": "Vous êtes actuellement un utilisateur gratuit et ne pouvez pas utiliser cette fonction. Veuillez passer à un plan payant pour continuer à l'utiliser.",
+ "InsufficientQuota": "Désolé, le quota de cette clé a atteint sa limite. Veuillez vérifier si le solde de votre compte est suffisant ou augmenter le quota de la clé avant de réessayer.",
"InvalidAccessCode": "Le mot de passe est incorrect ou vide. Veuillez saisir le mot de passe d'accès correct ou ajouter une clé API personnalisée.",
"InvalidBedrockCredentials": "L'authentification Bedrock a échoué, veuillez vérifier AccessKeyId/SecretAccessKey et réessayer",
"InvalidClerkUser": "Désolé, vous n'êtes pas actuellement connecté. Veuillez vous connecter ou vous inscrire avant de continuer.",
"InvalidGithubToken": "Le jeton d'accès personnel GitHub est incorrect ou vide. Veuillez vérifier le jeton d'accès personnel GitHub et réessayer.",
"InvalidOllamaArgs": "La configuration d'Ollama n'est pas valide, veuillez vérifier la configuration d'Ollama et réessayer",
"InvalidProviderAPIKey": "{{provider}} API Key incorrect or missing, please check {{provider}} API Key and try again",
+ "InvalidVertexCredentials": "L'authentification Vertex a échoué, veuillez vérifier vos informations d'authentification et réessayer",
"LocationNotSupportError": "Désolé, votre emplacement actuel ne prend pas en charge ce service de modèle, peut-être en raison de restrictions géographiques ou de services non disponibles. Veuillez vérifier si votre emplacement actuel prend en charge ce service ou essayer avec une autre localisation.",
+ "ModelNotFound": "Désolé, il n'est pas possible de demander le modèle correspondant, il se peut que le modèle n'existe pas ou que vous n'ayez pas les droits d'accès. Veuillez changer la clé API ou ajuster les droits d'accès, puis réessayez.",
"NoOpenAIAPIKey": "La clé API OpenAI est vide. Veuillez ajouter une clé API OpenAI personnalisée",
"OllamaBizError": "Erreur commerciale lors de la demande de service Ollama, veuillez vérifier les informations ci-dessous ou réessayer",
"OllamaServiceUnavailable": "Le service Ollama n'est pas disponible. Veuillez vérifier si Ollama fonctionne correctement ou si la configuration de la communication inter-domaines d'Ollama est correcte.",
- "OpenAIBizError": "Erreur de service OpenAI. Veuillez vérifier les informations suivantes ou réessayer.",
+ "PermissionDenied": "Désolé, vous n'avez pas la permission d'accéder à ce service. Veuillez vérifier si votre clé a les droits d'accès.",
"PluginApiNotFound": "Désolé, l'API spécifiée n'existe pas dans le manifeste du plugin. Veuillez vérifier que votre méthode de requête correspond à l'API du manifeste du plugin",
"PluginApiParamsError": "Désolé, la validation des paramètres d'entrée de la requête de ce plugin a échoué. Veuillez vérifier que les paramètres d'entrée correspondent aux informations de l'API",
"PluginFailToTransformArguments": "Désolé, échec de la transformation des arguments de l'appel du plugin. Veuillez essayer de régénérer le message d'assistance ou de changer de modèle d'IA avec une capacité d'appel d'outils plus puissante, puis réessayer.",
@@ -81,8 +99,11 @@
"PluginServerError": "Erreur de réponse du serveur du plugin. Veuillez vérifier le fichier de description du plugin, la configuration du plugin ou la mise en œuvre côté serveur en fonction des informations d'erreur ci-dessous",
"PluginSettingsInvalid": "Ce plugin doit être correctement configuré avant de pouvoir être utilisé. Veuillez vérifier votre configuration",
"ProviderBizError": "Erreur de service {{provider}}. Veuillez vérifier les informations suivantes ou réessayer.",
+ "QuotaLimitReached": "Désolé, l'utilisation actuelle des tokens ou le nombre de requêtes a atteint la limite de quota de cette clé. Veuillez augmenter le quota de cette clé ou réessayer plus tard.",
"StreamChunkError": "Erreur de parsing du bloc de message de la requête en streaming. Veuillez vérifier si l'API actuelle respecte les normes ou contacter votre fournisseur d'API pour des conseils.",
- "SubscriptionPlanLimit": "Vous avez atteint votre limite d'abonnement et ne pouvez pas utiliser cette fonction. Veuillez passer à un plan supérieur ou acheter un pack de ressources pour continuer à l'utiliser.",
+ "SubscriptionKeyMismatch": "Nous sommes désolés, en raison d'une défaillance système occasionnelle, l'utilisation actuelle de l'abonnement est temporairement inactive. Veuillez cliquer sur le bouton ci-dessous pour rétablir votre abonnement ou nous contacter par e-mail pour obtenir de l'aide.",
+ "SubscriptionPlanLimit": "Votre quota d'abonnement est épuisé, vous ne pouvez pas utiliser cette fonctionnalité. Veuillez passer à un plan supérieur ou configurer l'API du modèle personnalisé pour continuer à l'utiliser.",
+ "SystemTimeNotMatchError": "Désolé, l'heure de votre système ne correspond pas à celle du serveur. Veuillez vérifier l'heure de votre système et réessayer.",
"UnknownChatFetchError": "Désolé, une erreur de requête inconnue s'est produite. Veuillez vérifier les informations ci-dessous ou réessayer."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/fr-FR/metadata.json b/DigitalHumanWeb/locales/fr-FR/metadata.json
index ca1d976..b53a646 100644
--- a/DigitalHumanWeb/locales/fr-FR/metadata.json
+++ b/DigitalHumanWeb/locales/fr-FR/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Suivez les nouvelles fonctionnalités et améliorations de {{appName}}",
+ "title": "Journal des mises à jour"
+ },
"chat": {
"description": "{{appName}} vous offre la meilleure expérience d'utilisation de ChatGPT, Claude, Gemini et OLLaMA WebUI",
"title": "{{appName}} : un outil d'efficacité personnelle en IA pour vous donner un cerveau plus intelligent"
diff --git a/DigitalHumanWeb/locales/fr-FR/modelProvider.json b/DigitalHumanWeb/locales/fr-FR/modelProvider.json
index 87e1045..2ec73f5 100644
--- a/DigitalHumanWeb/locales/fr-FR/modelProvider.json
+++ b/DigitalHumanWeb/locales/fr-FR/modelProvider.json
@@ -19,6 +19,24 @@
"title": "Clé API"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Version de l'API Azure, au format YYYY-MM-DD. Consultez la [dernière version](https://learn.microsoft.com/fr-fr/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Obtenir la liste",
+ "title": "Version de l'API Azure"
+ },
+ "endpoint": {
+ "desc": "Trouvez le point de terminaison d'inférence du modèle Azure AI dans l'aperçu du projet Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Point de terminaison Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Trouvez la clé API dans l'aperçu du projet Azure AI",
+ "placeholder": "Clé Azure",
+ "title": "Clé"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Saisissez l'ID de clé d'accès AWS",
@@ -51,6 +69,58 @@
"title": "Utiliser des informations d'authentification Bedrock personnalisées"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Veuillez remplir l'Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Saisir l'ID de compte Cloudflare ou l'adresse API personnalisée",
+ "placeholder": "ID de compte Cloudflare / URL API personnalisée",
+ "title": "ID de compte Cloudflare / adresse API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Veuillez entrer votre clé API",
+ "title": "Clé API"
+ },
+ "basicTitle": "Informations de base",
+ "configTitle": "Informations de configuration",
+ "confirm": "Créer",
+ "createSuccess": "Création réussie",
+ "description": {
+ "placeholder": "Description du fournisseur (facultatif)",
+ "title": "Description du fournisseur"
+ },
+ "id": {
+ "desc": "Identifiant unique du fournisseur de services, qui ne peut pas être modifié après sa création",
+ "format": "Ne peut contenir que des chiffres, des lettres minuscules, des tirets (-) et des underscores (_) ",
+ "placeholder": "Utilisez uniquement des lettres minuscules, par exemple openai, non modifiable après création",
+ "required": "Veuillez entrer l'ID du fournisseur",
+ "title": "ID du fournisseur"
+ },
+ "logo": {
+ "required": "Veuillez télécharger un logo valide pour le fournisseur",
+ "title": "Logo du fournisseur"
+ },
+ "name": {
+ "placeholder": "Veuillez entrer le nom d'affichage du fournisseur",
+ "required": "Veuillez entrer le nom du fournisseur",
+ "title": "Nom du fournisseur"
+ },
+ "proxyUrl": {
+ "required": "Veuillez remplir l'adresse du proxy",
+ "title": "Adresse du proxy"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Veuillez sélectionner le type de SDK",
+ "title": "Format de requête"
+ },
+ "title": "Créer un fournisseur AI personnalisé"
+ },
"github": {
"personalAccessToken": {
"desc": "Entrez votre PAT GitHub, cliquez [ici](https://github.com/settings/tokens) pour en créer un.",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Entrez votre jeton HuggingFace, cliquez [ici](https://huggingface.co/settings/tokens) pour en créer un",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "Jeton HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Fournisseur non activé",
+ "enabled": "Fournisseur activé"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Ajouter un fournisseur personnalisé",
+ "all": "Tout",
+ "list": {
+ "disabled": "Non activé",
+ "enabled": "Activé"
+ },
+ "notFound": "Aucun résultat trouvé",
+ "searchProviders": "Rechercher des fournisseurs...",
+ "sort": "Tri personnalisé"
+ },
"ollama": {
"checker": {
"desc": "Vérifiez si l'adresse du proxy est correctement saisie",
@@ -69,47 +163,173 @@
"title": "Nom du modèle personnalisé"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. The download will resume from where it left off if interrupted.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama est en train de télécharger ce modèle, veuillez essayer de ne pas fermer cette page. Le téléchargement reprendra à l'endroit où il a été interrompu.",
+ "remainingTime": "Temps restant",
+ "speed": "Vitesse de téléchargement",
+ "title": "Téléchargement du modèle {{model}} en cours"
},
"endpoint": {
- "desc": "Saisissez l'adresse du proxy Ollama, laissez vide si non spécifié localement",
+ "desc": "Doit inclure http(s)://, peut rester vide si non spécifié localement",
"title": "Adresse du proxy"
},
- "setup": {
- "cors": {
- "description": "Due to browser security restrictions, you need to configure cross-origin settings for Ollama to function properly.",
- "linux": {
- "env": "Add `Environment` under [Service] section, and set the OLLAMA_ORIGINS environment variable:",
- "reboot": "Reload systemd and restart Ollama.",
- "systemd": "Invoke systemd to edit the ollama service:"
- },
- "macos": "Open the Terminal application, paste the following command, and press Enter.",
- "reboot": "Restart the Ollama service after the execution is complete.",
- "title": "Configure Ollama for Cross-Origin Access",
- "windows": "On Windows, go to 'Control Panel' and edit system environment variables. Create a new environment variable named 'OLLAMA_ORIGINS' for your user account, set the value to '*', and click 'OK/Apply' to save."
- },
- "install": {
- "description": "Veuillez vous assurer que vous avez activé Ollama. Si vous n'avez pas encore téléchargé Ollama, veuillez vous rendre sur le site officiel pour le <1>télécharger1>.",
- "docker": "If you prefer using Docker, Ollama also provides an official Docker image. You can pull it using the following command:",
- "linux": {
- "command": "Install using the following command:",
- "manual": "Alternatively, you can refer to the <1>Linux Manual Installation Guide1> for manual installation."
- },
- "title": "Install and Start Ollama Locally",
- "windowsTab": "Windows (Preview)"
- }
- },
"title": "Ollama",
"unlock": {
- "cancel": "Cancel Download",
- "confirm": "Download",
- "description": "Enter your Ollama model tag to continue the session",
+ "cancel": "Annuler le téléchargement",
+ "confirm": "Télécharger",
+ "description": "Entrez l'étiquette de votre modèle Ollama pour continuer la session.",
"downloaded": "{{completed}} / {{total}}",
- "starting": "Starting download...",
- "title": "Download specified Ollama model"
+ "starting": "Début du téléchargement...",
+ "title": "Télécharger le modèle Ollama spécifié"
+ }
+ },
+ "providerModels": {
+ "config": {
+ "aesGcm": "Votre clé et votre adresse de proxy seront chiffrées à l'aide de l'algorithme de chiffrement <1>AES-GCM1>",
+ "apiKey": {
+ "desc": "Veuillez entrer votre {{name}} clé API",
+ "placeholder": "{{name}} clé API",
+ "title": "Clé API"
+ },
+ "baseURL": {
+ "desc": "Doit inclure http(s)://",
+ "invalid": "Veuillez entrer une URL valide",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "Adresse du proxy API"
+ },
+ "checker": {
+ "button": "Vérifier",
+ "desc": "Tester si la clé API et l'adresse de proxy sont correctement renseignées",
+ "pass": "Vérification réussie",
+ "title": "Vérification de connectivité"
+ },
+ "fetchOnClient": {
+ "desc": "Le mode de requête client lancera directement la requête de session depuis le navigateur, ce qui peut améliorer la vitesse de réponse",
+ "title": "Utiliser le mode de requête client"
+ },
+ "helpDoc": "Guide de configuration",
+ "waitingForMore": "D'autres modèles sont en <1>planification d'intégration1>, restez à l'écoute"
+ },
+ "createNew": {
+ "title": "Créer un modèle AI personnalisé"
+ },
+ "item": {
+ "config": "Configurer le modèle",
+ "customModelCards": {
+ "addNew": "Créer et ajouter le modèle {{id}}",
+ "confirmDelete": "Vous allez supprimer ce modèle personnalisé, une fois supprimé, il ne pourra pas être récupéré, veuillez agir avec prudence."
+ },
+ "delete": {
+ "confirm": "Confirmer la suppression du modèle {{displayName}} ?",
+ "success": "Suppression réussie",
+ "title": "Supprimer le modèle"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Champ utilisé pour la demande réelle dans Azure OpenAI",
+ "placeholder": "Veuillez entrer le nom de déploiement du modèle dans Azure",
+ "title": "Nom de déploiement du modèle"
+ },
+ "deployName": {
+ "extra": "Ce champ sera utilisé comme ID de modèle lors de l'envoi de la demande",
+ "placeholder": "Veuillez entrer le nom ou l'ID de déploiement réel du modèle",
+ "title": "Nom de déploiement du modèle"
+ },
+ "displayName": {
+ "placeholder": "Veuillez entrer le nom d'affichage du modèle, par exemple ChatGPT, GPT-4, etc.",
+ "title": "Nom d'affichage du modèle"
+ },
+ "files": {
+ "extra": "La mise en œuvre actuelle du téléchargement de fichiers n'est qu'une solution de contournement, à essayer à vos risques et périls. Veuillez attendre la mise en œuvre complète des capacités de téléchargement de fichiers.",
+ "title": "Téléchargement de fichiers pris en charge"
+ },
+ "functionCall": {
+ "extra": "Cette configuration activera uniquement la capacité du modèle à utiliser des outils, permettant ainsi d'ajouter des plugins de type outil au modèle. Cependant, la prise en charge de l'utilisation réelle des outils dépend entièrement du modèle lui-même, veuillez tester la disponibilité par vous-même.",
+ "title": "Support de l'utilisation des outils"
+ },
+ "id": {
+ "extra": "Une fois créé, il ne peut pas être modifié et sera utilisé comme identifiant du modèle lors de l'appel à l'IA",
+ "placeholder": "Veuillez entrer l'identifiant du modèle, par exemple gpt-4o ou claude-3.5-sonnet",
+ "title": "ID du modèle"
+ },
+ "modalTitle": "Configuration du modèle personnalisé",
+ "reasoning": {
+ "extra": "Cette configuration activera uniquement la capacité de réflexion approfondie du modèle. Les résultats dépendent entièrement du modèle lui-même, veuillez tester si ce modèle possède une capacité de réflexion approfondie utilisable.",
+ "title": "Support de la réflexion approfondie"
+ },
+ "tokens": {
+ "extra": "Définir le nombre maximal de tokens pris en charge par le modèle",
+ "title": "Fenêtre de contexte maximale",
+ "unlimited": "Illimité"
+ },
+ "vision": {
+ "extra": "Cette configuration n'activera que la configuration de téléchargement d'images dans l'application, la prise en charge de la reconnaissance dépend entièrement du modèle lui-même, veuillez tester la disponibilité des capacités de reconnaissance visuelle de ce modèle.",
+ "title": "Reconnaissance visuelle prise en charge"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/image",
+ "inputCharts": "${{amount}}/M caractères",
+ "inputMinutes": "${{amount}}/minutes",
+ "inputTokens": "Entrée ${{amount}}/M",
+ "outputTokens": "Sortie ${{amount}}/M"
+ },
+ "releasedAt": "Publié le {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Ajouter un modèle",
+ "disabled": "Non activé",
+ "disabledActions": {
+ "showMore": "Afficher tout"
+ },
+ "empty": {
+ "desc": "Veuillez créer un modèle personnalisé ou importer un modèle pour commencer à l'utiliser.",
+ "title": "Aucun modèle disponible"
+ },
+ "enabled": "Activé",
+ "enabledActions": {
+ "disableAll": "Désactiver tout",
+ "enableAll": "Activer tout",
+ "sort": "Trier les modèles personnalisés"
+ },
+ "enabledEmpty": "Aucun modèle activé pour le moment, veuillez activer vos modèles préférés dans la liste ci-dessous~",
+ "fetcher": {
+ "clear": "Effacer les modèles récupérés",
+ "fetch": "Récupérer la liste des modèles",
+ "fetching": "Récupération de la liste des modèles en cours...",
+ "latestTime": "Dernière mise à jour : {{time}}",
+ "noLatestTime": "Aucune liste récupérée pour le moment"
+ },
+ "resetAll": {
+ "conform": "Êtes-vous sûr de vouloir réinitialiser toutes les modifications du modèle actuel ? Après la réinitialisation, la liste des modèles actuels reviendra à l'état par défaut",
+ "success": "Réinitialisation réussie",
+ "title": "Réinitialiser toutes les modifications"
+ },
+ "search": "Rechercher des modèles...",
+ "searchResult": "Trouvé {{count}} modèle(s)",
+ "title": "Liste des modèles",
+ "total": "Un total de {{count}} modèles disponibles"
+ },
+ "searchNotFound": "Aucun résultat trouvé"
+ },
+ "sortModal": {
+ "success": "Mise à jour du tri réussie",
+ "title": "Tri personnalisé",
+ "update": "Mettre à jour"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Vous allez supprimer ce fournisseur AI, une fois supprimé, il ne pourra pas être récupéré, confirmez-vous la suppression ?",
+ "deleteSuccess": "Suppression réussie",
+ "tooltip": "Mettre à jour la configuration de base du fournisseur",
+ "updateSuccess": "Mise à jour réussie"
+ },
+ "updateCustomAiProvider": {
+ "title": "Mettre à jour la configuration du fournisseur de services AI personnalisé"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Entrez vos clés Vertex AI",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Clés Vertex AI"
}
},
"zeroone": {
diff --git a/DigitalHumanWeb/locales/fr-FR/models.json b/DigitalHumanWeb/locales/fr-FR/models.json
index 73147b2..022d0db 100644
--- a/DigitalHumanWeb/locales/fr-FR/models.json
+++ b/DigitalHumanWeb/locales/fr-FR/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, avec un ensemble d'échantillons d'entraînement riche, offre des performances supérieures dans les applications sectorielles."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat est une variante de la série Yi-1.5, appartenant aux modèles de chat open source. Yi-1.5 est une version améliorée de Yi, pré-entraînée sur 500B de corpus de haute qualité et ajustée sur plus de 3M d'échantillons diversifiés. Comparé à Yi, Yi-1.5 montre de meilleures performances en codage, mathématiques, raisonnement et suivi des instructions, tout en maintenant d'excellentes capacités de compréhension du langage, de raisonnement de bon sens et de compréhension de lecture. Ce modèle propose des versions avec des longueurs de contexte de 4K, 16K et 32K, avec un total de pré-entraînement atteignant 3.6T de tokens."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B supporte 16K Tokens, offrant une capacité de génération de langage efficace et fluide."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Everything, le dernier modèle de fine-tuning open source, avec 34 milliards de paramètres, prend en charge divers scénarios de dialogue, avec des données d'entraînement de haute qualité, alignées sur les préférences humaines."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Everything, le dernier modèle de fine-tuning open source, avec 9 milliards de paramètres, prend en charge divers scénarios de dialogue, avec des données d'entraînement de haute qualité, alignées sur les préférences humaines."
+ },
"360gpt-pro": {
"description": "360GPT Pro, en tant que membre important de la série de modèles AI de 360, répond à des applications variées de traitement de texte avec une efficacité élevée, supportant la compréhension de longs textes et les dialogues multi-tours."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K met l'accent sur la sécurité sémantique et l'orientation vers la responsabilité, conçu pour des scénarios d'application exigeant une sécurité de contenu élevée, garantissant l'exactitude et la robustesse de l'expérience utilisateur."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 utilise une recherche arborescente pour construire des chaînes de pensée et introduit un mécanisme de réflexion, entraîné par apprentissage par renforcement, permettant au modèle d'avoir des capacités d'auto-réflexion et de correction."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro est un modèle avancé de traitement du langage naturel lancé par la société 360, offrant d'excellentes capacités de génération et de compréhension de texte, en particulier dans le domaine de la création et de la génération."
},
+ "360zhinao2-o1": {
+ "description": "Le modèle 360zhinao2-o1 utilise une recherche arborescente pour construire une chaîne de pensée et introduit un mécanisme de réflexion, formé par apprentissage par renforcement, permettant au modèle d'avoir la capacité de réflexion et de correction autonome."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra est la version la plus puissante de la série de grands modèles Xinghuo, améliorant la compréhension et la capacité de résumé du contenu textuel tout en mettant à jour le lien de recherche en ligne. C'est une solution complète pour améliorer la productivité au bureau et répondre avec précision aux besoins, représentant un produit intelligent de premier plan dans l'industrie."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Le modèle est le meilleur en Chine, surpassant les modèles étrangers dans des tâches en chinois telles que l'encyclopédie, les longs textes et la création. Il possède également des capacités multimodales de pointe, avec d'excellentes performances dans plusieurs évaluations de référence."
},
+ "Baichuan4-Air": {
+ "description": "Le modèle le plus performant en Chine, surpassant les modèles dominants étrangers dans les tâches en chinois telles que les encyclopédies, les longs textes et la création. Il possède également des capacités multimodales de pointe, avec d'excellentes performances dans plusieurs évaluations de référence."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Le modèle le plus performant en Chine, surpassant les modèles dominants étrangers dans les tâches en chinois telles que les encyclopédies, les longs textes et la création. Il possède également des capacités multimodales de pointe, avec d'excellentes performances dans plusieurs évaluations de référence."
+ },
+ "DeepSeek-R1": {
+ "description": "LLM efficace à la pointe de la technologie, spécialisé dans le raisonnement, les mathématiques et la programmation."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 - un modèle plus grand et plus intelligent dans la suite DeepSeek - a été distillé dans l'architecture Llama 70B. Basé sur des tests de référence et des évaluations humaines, ce modèle est plus intelligent que le Llama 70B d'origine, en particulier dans les tâches nécessitant des mathématiques et une précision factuelle."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Le modèle distillé DeepSeek-R1 basé sur Qwen2.5-Math-1.5B optimise les performances d'inférence grâce à l'apprentissage par renforcement et aux données de démarrage à froid, rafraîchissant les références multi-tâches des modèles open source."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Le modèle distillé DeepSeek-R1 basé sur Qwen2.5-14B optimise les performances d'inférence grâce à l'apprentissage par renforcement et aux données de démarrage à froid, rafraîchissant les références multi-tâches des modèles open source."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "La série DeepSeek-R1 optimise les performances d'inférence grâce à l'apprentissage par renforcement et aux données de démarrage à froid, rafraîchissant les références multi-tâches des modèles open source, dépassant le niveau d'OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Le modèle distillé DeepSeek-R1 basé sur Qwen2.5-Math-7B optimise les performances d'inférence grâce à l'apprentissage par renforcement et aux données de démarrage à froid, rafraîchissant les références multi-tâches des modèles open source."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro est un modèle multimodal de grande taille récemment mis à jour, prenant en charge la reconnaissance d'images à toute résolution et avec des rapports d'aspect extrêmes, améliorant les capacités de raisonnement visuel, de reconnaissance de documents, de compréhension des informations détaillées et de suivi des instructions."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite présente une rapidité de réponse exceptionnelle et un excellent rapport qualité-prix, offrant des choix plus flexibles pour différents scénarios clients. Prend en charge le raisonnement et le réglage fin avec une fenêtre de contexte de 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite présente une rapidité de réponse exceptionnelle et un excellent rapport qualité-prix, offrant des choix plus flexibles pour différents scénarios clients. Prend en charge le raisonnement et le réglage fin avec une fenêtre de contexte de 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite présente une rapidité de réponse exceptionnelle et un excellent rapport qualité-prix, offrant des choix plus flexibles pour différents scénarios clients. Prend en charge le raisonnement et le réglage fin avec une fenêtre de contexte de 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "Le modèle principal offrant les meilleures performances, adapté aux tâches complexes, avec de bons résultats dans des scénarios tels que le question-réponse, le résumé, la création, la classification de texte et le jeu de rôle. Prend en charge le raisonnement et le réglage fin avec une fenêtre de contexte de 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "Le modèle phare avec les meilleures performances, adapté au traitement de tâches complexes, offrant de bons résultats dans des scénarios tels que les questions-réponses de référence, les résumés, la création, la classification de texte et le jeu de rôle. Prend en charge le raisonnement et le réglage fin avec une fenêtre contextuelle de 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "Le modèle principal offrant les meilleures performances, adapté aux tâches complexes, avec de bons résultats dans des scénarios tels que le question-réponse, le résumé, la création, la classification de texte et le jeu de rôle. Prend en charge le raisonnement et le réglage fin avec une fenêtre de contexte de 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "Le modèle principal offrant les meilleures performances, adapté aux tâches complexes, avec de bons résultats dans des scénarios tels que le question-réponse, le résumé, la création, la classification de texte et le jeu de rôle. Prend en charge le raisonnement et le réglage fin avec une fenêtre de contexte de 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Le modèle Doubao-vision est un modèle multimodal lancé par Doubao, doté de puissantes capacités de compréhension et de raisonnement d'images, ainsi que d'une compréhension précise des instructions. Le modèle a démontré de solides performances dans l'extraction d'informations textuelles à partir d'images et dans des tâches de raisonnement basées sur des images, pouvant être appliqué à des tâches de questions-réponses visuelles plus complexes et variées."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Le modèle Doubao-vision est un modèle multimodal lancé par Doubao, doté de puissantes capacités de compréhension et de raisonnement d'images, ainsi que d'une compréhension précise des instructions. Le modèle a démontré de solides performances dans l'extraction d'informations textuelles à partir d'images et dans des tâches de raisonnement basées sur des images, pouvant être appliqué à des tâches de questions-réponses visuelles plus complexes et variées."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Modèle de langage à grande échelle de pointe développé par Baidu, couvrant une vaste quantité de corpus en chinois et en anglais, avec de puissantes capacités générales, capable de répondre à la plupart des exigences en matière de dialogue, de questions-réponses, de création de contenu et d'applications de plugins ; prend en charge l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Modèle de langage à grande échelle de pointe développé par Baidu, couvrant une vaste quantité de corpus en chinois et en anglais, avec de puissantes capacités générales, capable de répondre à la plupart des exigences en matière de dialogue, de questions-réponses, de création de contenu et d'applications de plugins ; prend en charge l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Modèle de langage à grande échelle de pointe développé par Baidu, couvrant une vaste quantité de corpus en chinois et en anglais, avec de puissantes capacités générales, capable de répondre à la plupart des exigences en matière de dialogue, de questions-réponses, de création de contenu et d'applications de plugins ; prend en charge l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Modèle de langage ultra-large de premier plan développé par Baidu, ayant réalisé une mise à niveau complète des capacités par rapport à ERNIE 3.5, largement applicable à des scénarios de tâches complexes dans divers domaines ; prend en charge l'intégration automatique avec le plugin de recherche Baidu, garantissant l'actualité des informations de réponse."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Modèle de langage ultra-large de premier plan développé par Baidu, ayant réalisé une mise à niveau complète des capacités par rapport à ERNIE 3.5, largement applicable à des scénarios de tâches complexes dans divers domaines ; prend en charge l'intégration automatique avec le plugin de recherche Baidu, garantissant l'actualité des informations de réponse."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Modèle linguistique ultramoderne et de grande taille auto-développé par Baidu, avec d'excellentes performances générales, largement applicable à divers scénarios de tâches complexes ; prend en charge la connexion automatique aux plugins de recherche Baidu pour assurer la pertinence des informations de réponse. Par rapport à ERNIE 4.0, il affiche de meilleures performances."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Modèle de langage ultra-large de premier plan développé par Baidu, offrant d'excellentes performances globales, largement applicable à des scénarios de tâches complexes dans divers domaines ; prend en charge l'intégration automatique avec le plugin de recherche Baidu, garantissant l'actualité des informations de réponse. Par rapport à ERNIE 4.0, il offre de meilleures performances."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Modèle de langage pour scénarios verticaux développé par Baidu, adapté aux applications telles que les NPC de jeux, les dialogues de service client, et les jeux de rôle, avec des styles de personnages plus distincts et cohérents, une meilleure capacité à suivre les instructions et des performances d'inférence supérieures."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Modèle de langage léger développé par Baidu, alliant d'excellentes performances du modèle et efficacité d'inférence, offrant de meilleures performances que ERNIE Lite, adapté à l'inférence sur des cartes d'accélération AI à faible puissance de calcul."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Modèle de langage haute performance développé par Baidu, publié en 2024, avec d'excellentes capacités générales, adapté comme modèle de base pour un ajustement fin, permettant de mieux traiter les problèmes de scénarios spécifiques, tout en offrant d'excellentes performances d'inférence."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Modèle de langage haute performance développé par Baidu, publié en 2024, avec d'excellentes capacités générales, offrant de meilleures performances que ERNIE Speed, adapté comme modèle de base pour un ajustement fin, permettant de mieux traiter les problèmes de scénarios spécifiques, tout en offrant d'excellentes performances d'inférence."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) est un modèle innovant, adapté à des applications dans plusieurs domaines et à des tâches complexes."
},
- "Max-32k": {
- "description": "Spark Max 32K est équipé d'une grande capacité de traitement de contexte, offrant une meilleure compréhension du contexte et des capacités de raisonnement logique, prenant en charge des entrées textuelles de 32K tokens, adapté à la lecture de longs documents, aux questions-réponses sur des connaissances privées et à d'autres scénarios."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B est un puissant modèle de langage visuel, prenant en charge le traitement multimodal d'images et de textes, capable de reconnaître avec précision le contenu des images et de générer des descriptions ou des réponses pertinentes."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B est un puissant modèle de langage visuel, prenant en charge le traitement multimodal d'images et de textes, capable de reconnaître avec précision le contenu des images et de générer des descriptions ou des réponses pertinentes."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Excellentes capacités de raisonnement d'image sur des images haute résolution, adaptées aux applications de compréhension visuelle."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Capacités avancées de raisonnement d'image adaptées aux applications d'agents de compréhension visuelle."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct est l'un des derniers modèles de langage à grande échelle publiés par Alibaba Cloud. Ce modèle 72B présente des capacités considérablement améliorées dans des domaines tels que le codage et les mathématiques. Le modèle offre également un support multilingue, couvrant plus de 29 langues, y compris le chinois et l'anglais. Il a montré des améliorations significatives dans le suivi des instructions, la compréhension des données structurées et la génération de sorties structurées (en particulier JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct est l'un des derniers modèles de langage à grande échelle publiés par Alibaba Cloud. Ce modèle 7B présente des capacités considérablement améliorées dans des domaines tels que le codage et les mathématiques. Le modèle offre également un support multilingue, couvrant plus de 29 langues, y compris le chinois et l'anglais. Il a montré des améliorations significatives dans le suivi des instructions, la compréhension des données structurées et la génération de sorties structurées (en particulier JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Modèle de texte optimisé pour les instructions de Llama 3.1, conçu pour des cas d'utilisation de dialogue multilingue, qui se distingue dans de nombreux modèles de chat open source et fermés sur des benchmarks industriels courants."
+ },
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Modèle de texte optimisé pour les instructions de Llama 3.1, conçu pour des cas d'utilisation de dialogue multilingue, qui se distingue dans de nombreux modèles de chat open source et fermés sur des benchmarks industriels courants."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO est une fusion de modèles hautement flexible, visant à offrir une expérience créative exceptionnelle."
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Modèle de texte optimisé pour les instructions de Llama 3.1, conçu pour des cas d'utilisation de dialogue multilingue, qui se distingue dans de nombreux modèles de chat open source et fermés sur des benchmarks industriels courants."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Modèle de langage de petite taille à la pointe de la technologie, doté de compétences en compréhension linguistique, d'excellentes capacités de raisonnement et de génération de texte."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Modèle de langage de petite taille à la pointe de la technologie, doté de compétences en compréhension linguistique, d'excellentes capacités de raisonnement et de génération de texte."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 est le modèle de langage open source multilingue le plus avancé de la série Llama, offrant des performances comparables à celles d'un modèle de 405B à un coût très faible. Basé sur une architecture Transformer, il a été amélioré en utilité et en sécurité grâce à un ajustement supervisé (SFT) et à un apprentissage par renforcement avec retour humain (RLHF). Sa version optimisée pour les instructions est spécialement conçue pour les dialogues multilingues et surpasse de nombreux modèles de chat open source et fermés sur plusieurs benchmarks industriels. La date limite des connaissances est décembre 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "Dans la série de modèles MiniMax-01, nous avons réalisé une innovation audacieuse : la première mise en œuvre à grande échelle d'un mécanisme d'attention linéaire, rendant l'architecture Transformer traditionnelle non plus le seul choix. Ce modèle possède un nombre de paramètres atteignant 456 milliards, avec 45,9 milliards d'activations par instance. Les performances globales du modèle rivalisent avec celles des meilleurs modèles étrangers, tout en étant capable de traiter efficacement un contexte mondial de 4 millions de tokens, soit 32 fois celui de GPT-4o et 20 fois celui de Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) est un modèle d'instructions de haute précision, adapté aux calculs complexes."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) offre une sortie linguistique optimisée et des possibilités d'application diversifiées."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Rafraîchissement du modèle Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 a démontré des performances exceptionnelles sur diverses tâches de langage visuel, y compris la compréhension de documents et de graphiques, la compréhension de texte de scène, l'OCR, ainsi que la résolution de problèmes scientifiques et mathématiques."
},
"Phi-3-medium-128k-instruct": {
"description": "Même modèle Phi-3-medium, mais avec une taille de contexte plus grande pour RAG ou un prompt à quelques exemples."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Un modèle de 7 milliards de paramètres, prouvant une meilleure qualité que Phi-3-mini, avec un accent sur des données denses en raisonnement de haute qualité."
},
- "Pro-128k": {
- "description": "Spark Pro-128K est configuré avec une capacité de traitement de contexte exceptionnel, capable de gérer jusqu'à 128K d'informations contextuelles, particulièrement adapté pour l'analyse complète et le traitement des relations logiques à long terme dans des contenus longs, offrant une logique fluide et cohérente ainsi qu'un support varié pour les références dans des communications textuelles complexes."
+ "Phi-3.5-mini-instruct": {
+ "description": "Version améliorée du modèle Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Version améliorée du modèle Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 a démontré des performances exceptionnelles sur diverses tâches de langage visuel, y compris la compréhension de documents et de graphiques, la compréhension de texte de scène, l'OCR, ainsi que la résolution de problèmes scientifiques et mathématiques."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct est un modèle de langage à grande échelle de la série Qwen2, avec une taille de paramètre de 1.5B. Ce modèle est basé sur l'architecture Transformer, utilisant des fonctions d'activation SwiGLU, des biais d'attention QKV et des techniques d'attention par groupe. Il excelle dans la compréhension du langage, la génération, les capacités multilingues, le codage, les mathématiques et le raisonnement dans plusieurs tests de référence, surpassant la plupart des modèles open source. Comparé à Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct montre des améliorations de performance significatives dans des tests tels que MMLU, HumanEval, GSM8K, C-Eval et IFEval, bien que le nombre de paramètres soit légèrement inférieur."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct est un modèle de langage à grande échelle de la série Qwen2, avec une taille de paramètre de 7B. Ce modèle est basé sur l'architecture Transformer, utilisant des fonctions d'activation SwiGLU, des biais d'attention QKV et des techniques d'attention par groupe. Il est capable de traiter de grandes entrées. Ce modèle excelle dans la compréhension du langage, la génération, les capacités multilingues, le codage, les mathématiques et le raisonnement dans plusieurs tests de référence, surpassant la plupart des modèles open source et montrant une compétitivité comparable à celle des modèles propriétaires dans certaines tâches. Qwen2-7B-Instruct a montré des performances significativement meilleures que Qwen1.5-7B-Chat dans plusieurs évaluations."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL est la dernière itération du modèle Qwen-VL, atteignant des performances de pointe dans les tests de référence de compréhension visuelle."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct est l'un des derniers modèles de langage à grande échelle publiés par Alibaba Cloud. Ce modèle 7B présente des capacités considérablement améliorées dans des domaines tels que le codage et les mathématiques. Le modèle offre également un support multilingue, couvrant plus de 29 langues, y compris le chinois et l'anglais. Il a montré des améliorations significatives dans le suivi des instructions, la compréhension des données structurées et la génération de sorties structurées (en particulier JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct est la dernière version de la série de modèles de langage à grande échelle spécifique au code publiée par Alibaba Cloud. Ce modèle, basé sur Qwen2.5, a été formé avec 55 trillions de tokens, améliorant considérablement les capacités de génération, de raisonnement et de correction de code. Il renforce non seulement les capacités de codage, mais maintient également des avantages en mathématiques et en compétences générales. Le modèle fournit une base plus complète pour des applications pratiques telles que les agents de code."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat est la version open source de la série de modèles pré-entraînés GLM-4 lancée par Zhipu AI. Ce modèle excelle dans plusieurs domaines tels que la sémantique, les mathématiques, le raisonnement, le code et les connaissances. En plus de prendre en charge des dialogues multi-tours, GLM-4-9B-Chat dispose également de fonctionnalités avancées telles que la navigation sur le web, l'exécution de code, l'appel d'outils personnalisés (Function Call) et le raisonnement sur de longs textes. Le modèle prend en charge 26 langues, y compris le chinois, l'anglais, le japonais, le coréen et l'allemand. Dans plusieurs tests de référence, GLM-4-9B-Chat a montré d'excellentes performances, comme AlignBench-v2, MT-Bench, MMLU et C-Eval. Ce modèle prend en charge une longueur de contexte maximale de 128K, adapté à la recherche académique et aux applications commerciales."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 est un modèle d'inférence piloté par l'apprentissage par renforcement (RL), qui résout les problèmes de répétition et de lisibilité dans le modèle. Avant le RL, DeepSeek-R1 a introduit des données de démarrage à froid, optimisant encore les performances d'inférence. Il se compare à OpenAI-o1 dans les tâches mathématiques, de code et d'inférence, et améliore l'ensemble des performances grâce à des méthodes d'entraînement soigneusement conçues."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 est un modèle de langage à experts mixtes (MoE) avec 671 milliards de paramètres, utilisant une attention potentielle multi-tête (MLA) et une architecture DeepSeekMoE, combinant une stratégie d'équilibrage de charge sans perte auxiliaire pour optimiser l'efficacité d'inférence et d'entraînement. Pré-entraîné sur 14,8 billions de tokens de haute qualité, et affiné par supervision et apprentissage par renforcement, DeepSeek-V3 surpasse d'autres modèles open source et se rapproche des modèles fermés de premier plan."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma est l'une des séries de modèles open source légers et avancés développés par Google. C'est un modèle de langage à grande échelle uniquement décodeur, prenant en charge l'anglais, offrant des poids ouverts, des variantes pré-entraînées et des variantes d'ajustement d'instructions. Le modèle Gemma est adapté à diverses tâches de génération de texte, y compris les questions-réponses, les résumés et le raisonnement. Ce modèle 9B a été formé avec 80 trillions de tokens. Sa taille relativement petite permet de le déployer dans des environnements à ressources limitées, tels que des ordinateurs portables, des ordinateurs de bureau ou votre propre infrastructure cloud, rendant ainsi les modèles d'IA de pointe plus accessibles et favorisant l'innovation."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 est une famille de modèles de langage à grande échelle multilingues développée par Meta, comprenant des variantes pré-entraînées et d'ajustement d'instructions de tailles de paramètres de 8B, 70B et 405B. Ce modèle d'ajustement d'instructions 8B est optimisé pour des scénarios de dialogue multilingue, montrant d'excellentes performances dans plusieurs tests de référence de l'industrie. L'entraînement du modèle a utilisé plus de 150 trillions de tokens de données publiques, et des techniques telles que l'ajustement supervisé et l'apprentissage par renforcement basé sur les retours humains ont été appliquées pour améliorer l'utilité et la sécurité du modèle. Llama 3.1 prend en charge la génération de texte et de code, avec une date limite de connaissances fixée à décembre 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview est un modèle de traitement du langage naturel innovant, capable de gérer efficacement des tâches complexes de génération de dialogues et de compréhension contextuelle."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview est un modèle de recherche développé par l'équipe Qwen, axé sur les capacités de raisonnement visuel, qui possède des avantages uniques dans la compréhension de scènes complexes et la résolution de problèmes mathématiques liés à la vision."
+ },
+ "Qwen/QwQ-32B": {
+ "description": "QwQ est le modèle d'inférence de la série Qwen. Comparé aux modèles d'optimisation d'instructions traditionnels, QwQ possède des capacités de réflexion et de raisonnement, permettant d'obtenir des performances nettement améliorées dans les tâches en aval, en particulier pour résoudre des problèmes difficiles. QwQ-32B est un modèle d'inférence de taille moyenne, capable d'obtenir des performances compétitives par rapport aux modèles d'inférence les plus avancés (comme DeepSeek-R1, o1-mini). Ce modèle utilise des techniques telles que RoPE, SwiGLU, RMSNorm et Attention QKV bias, avec une architecture de réseau de 64 couches et 40 têtes d'attention Q (dans l'architecture GQA, KV est de 8)."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "En tant que version bêta de Qwen2, Qwen1.5 utilise des données à grande échelle pour réaliser des fonctionnalités de dialogue plus précises."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview est le dernier modèle de recherche expérimental de Qwen, axé sur l'amélioration des capacités de raisonnement de l'IA. En explorant des mécanismes complexes tels que le mélange de langues et le raisonnement récursif, ses principaux avantages incluent de puissantes capacités d'analyse de raisonnement, ainsi que des compétences en mathématiques et en programmation. Cependant, il existe également des problèmes de changement de langue, des cycles de raisonnement, des considérations de sécurité et des différences dans d'autres capacités."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) offre des réponses rapides et des capacités de dialogue naturel, adapté aux environnements multilingues."
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct est un modèle de langage à grande échelle de la série Qwen2, avec une taille de paramètre de 1.5B. Ce modèle est basé sur l'architecture Transformer, utilisant des fonctions d'activation SwiGLU, des biais d'attention QKV et des techniques d'attention par groupe. Il excelle dans la compréhension du langage, la génération, les capacités multilingues, le codage, les mathématiques et le raisonnement dans plusieurs tests de référence, surpassant la plupart des modèles open source. Comparé à Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct montre des améliorations de performance significatives dans des tests tels que MMLU, HumanEval, GSM8K, C-Eval et IFEval, bien que le nombre de paramètres soit légèrement inférieur."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 est un modèle de langage général avancé, prenant en charge divers types d'instructions."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct est un modèle de langage à grande échelle de la série Qwen2, avec une taille de paramètre de 72B. Ce modèle est basé sur l'architecture Transformer, utilisant des fonctions d'activation SwiGLU, des biais d'attention QKV et des techniques d'attention par groupe. Il est capable de traiter de grandes entrées. Ce modèle excelle dans la compréhension du langage, la génération, les capacités multilingues, le codage, les mathématiques et le raisonnement dans plusieurs tests de référence, surpassant la plupart des modèles open source et montrant une compétitivité comparable à celle des modèles propriétaires dans certaines tâches."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL est la dernière itération du modèle Qwen-VL, atteignant des performances de pointe dans les tests de référence de compréhension visuelle."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 est une toute nouvelle série de modèles de langage à grande échelle, conçue pour optimiser le traitement des tâches d'instruction."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 est une toute nouvelle série de modèles de langage à grande échelle, conçue pour optimiser le traitement des tâches d'instruction."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 est une toute nouvelle série de modèles de langage à grande échelle, avec une capacité de compréhension et de génération améliorée."
+ "description": "Un grand modèle de langage développé par l'équipe Tongyi Qianwen d'Alibaba Cloud"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 est une toute nouvelle série de modèles de langage de grande taille avec des capacités de compréhension et de génération améliorées."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 est une toute nouvelle série de modèles de langage de grande taille, conçue pour optimiser le traitement des tâches d'instruction."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 est une toute nouvelle série de modèles de langage à grande échelle, conçue pour optimiser le traitement des tâches d'instruction."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 est une toute nouvelle série de modèles de langage de grande taille, conçue pour optimiser le traitement des tâches d'instruction."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder se concentre sur la rédaction de code."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math se concentre sur la résolution de problèmes dans le domaine des mathématiques, fournissant des réponses professionnelles pour des questions de haute difficulté."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct est la dernière version de la série de modèles de langage à grande échelle spécifique au code publiée par Alibaba Cloud. Ce modèle, basé sur Qwen2.5, a été formé avec 55 trillions de tokens, améliorant considérablement les capacités de génération, de raisonnement et de correction de code. Il renforce non seulement les capacités de codage, mais maintient également des avantages en mathématiques et en compétences générales. Le modèle fournit une base plus complète pour des applications pratiques telles que les agents de code."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 est la dernière série du modèle Qwen, prenant en charge un contexte de 128k. Comparé aux meilleurs modèles open source actuels, Qwen2-72B surpasse de manière significative les modèles leaders dans des domaines tels que la compréhension du langage naturel, les connaissances, le code, les mathématiques et le multilinguisme."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 est la dernière série du modèle Qwen, capable de surpasser les meilleurs modèles open source de taille équivalente, voire de plus grande taille. Qwen2 7B a obtenu des résultats significatifs dans plusieurs évaluations, en particulier en ce qui concerne la compréhension du code et du chinois."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B est un puissant modèle de langage visuel, prenant en charge le traitement multimodal d'images et de textes, capable de reconnaître avec précision le contenu des images et de générer des descriptions ou des réponses pertinentes."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct est un grand modèle de langage de 14 milliards de paramètres, offrant d'excellentes performances, optimisé pour les scénarios en chinois et multilingues, prenant en charge des applications telles que les questions-réponses intelligentes et la génération de contenu."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct est un grand modèle de langage de 32 milliards de paramètres, offrant des performances équilibrées, optimisé pour les scénarios en chinois et multilingues, prenant en charge des applications telles que les questions-réponses intelligentes et la génération de contenu."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct prend en charge un contexte de 16k, générant des textes longs de plus de 8K. Il permet des appels de fonction et une interaction transparente avec des systèmes externes, augmentant considérablement la flexibilité et l'évolutivité. Les connaissances du modèle ont considérablement augmenté, et ses capacités en codage et en mathématiques ont été grandement améliorées, avec un support multilingue dépassant 29 langues."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct est un grand modèle de langage de 7 milliards de paramètres, prenant en charge les appels de fonction et l'interaction transparente avec des systèmes externes, améliorant considérablement la flexibilité et l'évolutivité. Optimisé pour les scénarios en chinois et multilingues, il prend en charge des applications telles que les questions-réponses intelligentes et la génération de contenu."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct est un modèle d'instructions de programmation basé sur un pré-entraînement à grande échelle, doté d'une puissante capacité de compréhension et de génération de code, capable de traiter efficacement diverses tâches de programmation, particulièrement adapté à la rédaction de code intelligent, à la génération de scripts automatisés et à la résolution de problèmes de programmation."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct est un grand modèle de langage conçu pour la génération de code, la compréhension de code et les scénarios de développement efficaces, avec une échelle de 32 milliards de paramètres, répondant à des besoins de programmation variés."
+ },
+ "SenseChat": {
+ "description": "Modèle de version de base (V4), longueur de contexte de 4K, avec de puissantes capacités générales."
+ },
+ "SenseChat-128K": {
+ "description": "Modèle de version de base (V4), longueur de contexte de 128K, excellent dans les tâches de compréhension et de génération de longs textes."
+ },
+ "SenseChat-32K": {
+ "description": "Modèle de version de base (V4), longueur de contexte de 32K, appliqué de manière flexible à divers scénarios."
+ },
+ "SenseChat-5": {
+ "description": "Modèle de dernière version (V5.5), longueur de contexte de 128K, avec des capacités significativement améliorées dans le raisonnement mathématique, les dialogues en anglais, le suivi d'instructions et la compréhension de longs textes, rivalisant avec GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "C'est la dernière version basée sur V5.5, qui présente des améliorations significatives par rapport à la version précédente dans plusieurs dimensions telles que les capacités de base en chinois et en anglais, la conversation, les connaissances en sciences, les connaissances en lettres, l'écriture, la logique mathématique et le contrôle du nombre de mots."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Longueur de contexte de 32K, surpassant GPT-4 dans la compréhension des dialogues en cantonais, rivalisant avec GPT-4 Turbo dans plusieurs domaines tels que les connaissances, le raisonnement, les mathématiques et la rédaction de code."
+ },
+ "SenseChat-Character": {
+ "description": "Modèle standard, longueur de contexte de 8K, avec une grande rapidité de réponse."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Modèle avancé, longueur de contexte de 32K, avec des capacités globalement améliorées, prenant en charge les dialogues en chinois et en anglais."
+ },
+ "SenseChat-Turbo": {
+ "description": "Conçu pour des questions-réponses rapides et des scénarios de micro-ajustement du modèle."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "C'est le dernier modèle léger, atteignant plus de 90 % des capacités du modèle complet, tout en réduisant considérablement le coût d'inférence."
+ },
+ "SenseChat-Vision": {
+ "description": "Le dernier modèle (V5.5) prend en charge l'entrée de plusieurs images, optimisant les capacités de base du modèle, avec des améliorations significatives dans la reconnaissance des attributs d'objets, les relations spatiales, la reconnaissance d'événements d'action, la compréhension de scènes, la reconnaissance des émotions, le raisonnement de bon sens logique et la compréhension et génération de texte."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Le modèle de deuxième génération Skylark (Skylark2-lite) présente une grande rapidité de réponse, adapté à des scénarios nécessitant une réactivité élevée, sensible aux coûts, avec des exigences de précision de modèle moins élevées, avec une longueur de fenêtre de contexte de 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Le modèle de deuxième génération Skylark (Skylark2-pro) offre une précision élevée, adapté à des scénarios de génération de texte plus complexes tels que la création de contenu dans des domaines professionnels, la rédaction de romans et les traductions de haute qualité, avec une longueur de fenêtre de contexte de 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Le modèle de deuxième génération Skylark (Skylark2-pro) offre une précision élevée, adapté à des scénarios de génération de texte plus complexes tels que la création de contenu dans des domaines professionnels, la rédaction de romans et les traductions de haute qualité, avec une longueur de fenêtre de contexte de 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Le modèle de deuxième génération Skylark (Skylark2-pro-character) possède d'excellentes capacités de jeu de rôle et de chat, capable d'interagir suivant les instructions des utilisateurs, avec un style de personnage distinct et un contenu de dialogue fluide. Il est approprié pour construire des chatbots, des assistants virtuels et des services clients en ligne, avec une grande rapidité de réponse."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Le modèle de deuxième génération Skylark (Skylark2-pro-turbo-8k) offre un raisonnement plus rapide et un coût réduit, avec une longueur de fenêtre de contexte de 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B est un modèle open source de la série ChatGLM, développé par Zhipu AI. Ce modèle conserve les excellentes caractéristiques de son prédécesseur, telles que la fluidité des dialogues et un faible seuil de déploiement, tout en introduisant de nouvelles fonctionnalités. Il utilise des données d'entraînement plus variées, un nombre d'étapes d'entraînement plus élevé et une stratégie d'entraînement plus raisonnable, se distinguant parmi les modèles pré-entraînés de moins de 10B. ChatGLM3-6B prend en charge des dialogues multi-tours, des appels d'outils, l'exécution de code et des tâches d'agent dans des scénarios complexes. En plus du modèle de dialogue, les modèles de base ChatGLM-6B-Base et le modèle de dialogue long ChatGLM3-6B-32K sont également open source. Ce modèle est entièrement ouvert à la recherche académique et permet également une utilisation commerciale gratuite après enregistrement."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B est une version open source, offrant une expérience de dialogue optimisée pour les applications de conversation."
},
+ "TeleAI/TeleChat2": {
+ "description": "Le grand modèle TeleChat2 est un modèle sémantique génératif développé de manière autonome par China Telecom, prenant en charge des fonctionnalités telles que les questions-réponses encyclopédiques, la génération de code et la génération de longs textes, fournissant des services de consultation par dialogue aux utilisateurs, capable d'interagir avec les utilisateurs, de répondre à des questions, d'assister à la création, et d'aider efficacement et commodément les utilisateurs à obtenir des informations, des connaissances et de l'inspiration. Le modèle montre de bonnes performances sur des problèmes d'hallucination, la génération de longs textes et la compréhension logique."
+ },
+ "TeleAI/TeleMM": {
+ "description": "Le grand modèle multimodal TeleMM est un modèle de compréhension multimodale développé de manière autonome par China Telecom, capable de traiter des entrées multimodales telles que du texte et des images, prenant en charge des fonctionnalités telles que la compréhension d'images et l'analyse de graphiques, fournissant des services de compréhension intermodale aux utilisateurs. Le modèle peut interagir avec les utilisateurs de manière multimodale, comprendre avec précision le contenu d'entrée, répondre à des questions, assister à la création, et fournir efficacement des informations et un soutien d'inspiration multimodale. Il excelle dans des tâches multimodales telles que la perception fine et le raisonnement logique."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct est l'un des derniers modèles de langage à grande échelle publiés par Alibaba Cloud. Ce modèle 72B présente des capacités considérablement améliorées dans des domaines tels que le codage et les mathématiques. Le modèle offre également un support multilingue, couvrant plus de 29 langues, y compris le chinois et l'anglais. Il a montré des améliorations significatives dans le suivi des instructions, la compréhension des données structurées et la génération de sorties structurées (en particulier JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, tout en maintenant les excellentes capacités linguistiques générales de la série originale, a considérablement amélioré ses compétences en logique mathématique et en codage grâce à un entraînement incrémental sur 500 milliards de tokens de haute qualité."
+ },
"abab5.5-chat": {
"description": "Orienté vers des scénarios de productivité, prenant en charge le traitement de tâches complexes et la génération de texte efficace, adapté aux applications professionnelles."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Optimisé pour des scénarios de dialogue en chinois, offrant une capacité de génération de dialogues fluide et conforme aux habitudes d'expression en chinois."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Le modèle d'appel de fonction open source de Fireworks offre d'excellentes capacités d'exécution d'instructions et des caractéristiques personnalisables."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2, récemment lancé par Fireworks, est un modèle d'appel de fonction performant, développé sur la base de Llama-3 et optimisé pour des scénarios tels que les appels de fonction, les dialogues et le suivi d'instructions."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b est un modèle de langage visuel capable de recevoir simultanément des entrées d'images et de texte, entraîné sur des données de haute qualité, adapté aux tâches multimodales."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 est un modèle de langage de grande taille à la pointe de la technologie, optimisé par apprentissage renforcé et données de démarrage à froid, offrant d'excellentes performances en raisonnement, mathématiques et programmation."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Le modèle d'instructions Gemma 2 9B, basé sur la technologie antérieure de Google, est adapté à diverses tâches de génération de texte telles que la réponse aux questions, le résumé et le raisonnement."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Modèle de langage puissant de Deepseek basé sur un mélange d'experts (MoE), avec un total de 671B de paramètres, activant 37B de paramètres par jeton."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Le modèle d'instructions Llama 3 70B est optimisé pour les dialogues multilingues et la compréhension du langage naturel, surpassant la plupart des modèles concurrents."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Le modèle d'instructions Llama 3 70B (version HF) est conforme aux résultats de l'implémentation officielle, adapté aux tâches de suivi d'instructions de haute qualité."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Le modèle d'instructions Llama 3 8B est optimisé pour les dialogues et les tâches multilingues, offrant des performances exceptionnelles et efficaces."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Le modèle d'instructions Llama 3.1 8B est optimisé pour les dialogues multilingues, capable de surpasser la plupart des modèles open source et fermés sur des benchmarks industriels courants."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Modèle d'inférence d'image ajusté par instructions de Meta avec 11B paramètres. Ce modèle est optimisé pour la reconnaissance visuelle, l'inférence d'image, la description d'image et pour répondre à des questions générales sur l'image. Il est capable de comprendre des données visuelles, comme des graphiques et des diagrammes, et de combler le fossé entre la vision et le langage en générant des descriptions textuelles des détails de l'image."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Le modèle d'instructions Llama 3.2 3B est un modèle multilingue léger lancé par Meta. Ce modèle vise à améliorer l'efficacité, offrant des améliorations significatives en matière de latence et de coût par rapport aux modèles plus grands. Les cas d'utilisation incluent les requêtes, la réécriture de prompts et l'assistance à l'écriture."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Modèle d'inférence d'image ajusté par instructions de Meta avec 90B paramètres. Ce modèle est optimisé pour la reconnaissance visuelle, l'inférence d'image, la description d'image et pour répondre à des questions générales sur l'image. Il est capable de comprendre des données visuelles, comme des graphiques et des diagrammes, et de combler le fossé entre la vision et le langage en générant des descriptions textuelles des détails de l'image."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct est la version mise à jour de Llama 3.1 70B de décembre. Ce modèle a été amélioré par rapport à Llama 3.1 70B (publié en juillet 2024), renforçant les appels d'outils, le support multilingue, ainsi que les capacités en mathématiques et en programmation. Ce modèle atteint des niveaux de performance de pointe dans le raisonnement, les mathématiques et le respect des instructions, tout en offrant des performances similaires à celles du 3.1 405B, avec des avantages significatifs en termes de vitesse et de coût."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Modèle de 24B paramètres, doté de capacités de pointe comparables à celles de modèles plus grands."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Le modèle d'instructions Mixtral MoE 8x22B, avec des paramètres à grande échelle et une architecture multi-experts, prend en charge efficacement le traitement de tâches complexes."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Le modèle d'instructions Mixtral MoE 8x7B, avec une architecture multi-experts, offre un suivi et une exécution d'instructions efficaces."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Le modèle d'instructions Mixtral MoE 8x7B (version HF) offre des performances conformes à l'implémentation officielle, adapté à divers scénarios de tâches efficaces."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "Le modèle MythoMax L2 13B, combinant des techniques de fusion novatrices, excelle dans la narration et le jeu de rôle."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Le modèle d'instructions Phi 3 Vision est un modèle multimodal léger, capable de traiter des informations visuelles et textuelles complexes, avec une forte capacité de raisonnement."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "Le modèle StarCoder 15.5B prend en charge des tâches de programmation avancées, avec des capacités multilingues améliorées, adapté à la génération et à la compréhension de code complexes."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Le modèle QwQ est un modèle de recherche expérimental développé par l'équipe Qwen, axé sur l'amélioration des capacités de raisonnement de l'IA."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "Le modèle StarCoder 7B est entraîné sur plus de 80 langages de programmation, offrant d'excellentes capacités de complétion de code et de compréhension contextuelle."
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "La version 72B du modèle Qwen-VL est le fruit de la dernière itération d'Alibaba, représentant près d'un an d'innovation."
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 est une série de modèles de langage à décodage uniquement développée par l'équipe Qwen d'Alibaba Cloud. Ces modèles sont offerts en différentes tailles, y compris 0.5B, 1.5B, 3B, 7B, 14B, 32B et 72B, avec des variantes de base (base) et d'instruction (instruct)."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct est la dernière version de la série de modèles de langage à grande échelle spécifique au code publiée par Alibaba Cloud. Ce modèle, basé sur Qwen2.5, a été formé avec 55 trillions de tokens, améliorant considérablement les capacités de génération, de raisonnement et de correction de code. Il renforce non seulement les capacités de codage, mais maintient également des avantages en mathématiques et en compétences générales. Le modèle fournit une base plus complète pour des applications pratiques telles que les agents de code."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Le modèle Yi-Large offre d'excellentes capacités de traitement multilingue, adapté à diverses tâches de génération et de compréhension de langage."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Un modèle multilingue de 52 milliards de paramètres (12 milliards actifs), offrant une fenêtre de contexte longue de 256K, des appels de fonction, une sortie structurée et une génération ancrée."
},
- "ai21-jamba-instruct": {
- "description": "Un modèle LLM basé sur Mamba de qualité production pour atteindre des performances, une qualité et une efficacité de coût de premier ordre."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet élève les normes de l'industrie, surpassant les modèles concurrents et Claude 3 Opus, avec d'excellentes performances dans une large gamme d'évaluations, tout en offrant la vitesse et le coût de nos modèles de niveau intermédiaire."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet a élevé les normes de l'industrie, surpassant les modèles concurrents et Claude 3 Opus, tout en affichant d'excellentes performances dans une large gamme d'évaluations, tout en conservant la vitesse et le coût de nos modèles de niveau intermédiaire."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku est le modèle le plus rapide et le plus compact d'Anthropic, offrant une vitesse de réponse quasi instantanée. Il peut répondre rapidement à des requêtes et demandes simples. Les clients pourront construire une expérience AI transparente imitant l'interaction humaine. Claude 3 Haiku peut traiter des images et retourner des sorties textuelles, avec une fenêtre contextuelle de 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus est le modèle le plus puissant d'Anthropic pour traiter des tâches hautement complexes. Il excelle en termes de performance, d'intelligence, de fluidité et de compréhension."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku est le modèle de nouvelle génération le plus rapide d'Anthropic. Par rapport à Claude 3 Haiku, Claude 3.5 Haiku présente des améliorations dans toutes les compétences et surpasse le plus grand modèle de la génération précédente, Claude 3 Opus, dans de nombreux tests de référence intellectuels."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet offre des capacités supérieures à celles d'Opus et une vitesse plus rapide que Sonnet, tout en maintenant le même prix que Sonnet. Sonnet excelle particulièrement dans la programmation, la science des données, le traitement visuel et les tâches d'agent."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet est le modèle le plus intelligent d'Anthropic à ce jour, et le premier modèle de raisonnement hybride sur le marché. Claude 3.7 Sonnet peut produire des réponses quasi instantanées ou un raisonnement prolongé, permettant aux utilisateurs de voir clairement ces processus. Sonnet excelle particulièrement dans la programmation, la science des données, le traitement visuel et les tâches d'agent."
+ },
"aya": {
"description": "Aya 23 est un modèle multilingue lancé par Cohere, prenant en charge 23 langues, facilitant les applications linguistiques diversifiées."
},
"aya:35b": {
"description": "Aya 23 est un modèle multilingue lancé par Cohere, prenant en charge 23 langues, facilitant les applications linguistiques diversifiées."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B est un modèle de langage open source et commercialisable développé par Baichuan Intelligence, contenant 13 milliards de paramètres, qui a obtenu les meilleurs résultats dans des benchmarks chinois et anglais de référence."
+ },
"charglm-3": {
"description": "CharGLM-3 est conçu pour le jeu de rôle et l'accompagnement émotionnel, prenant en charge une mémoire multi-tours ultra-longue et des dialogues personnalisés, avec des applications variées."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 offre des avancées clés pour les entreprises, y compris un contexte de 200K jetons, une réduction significative du taux d'illusion du modèle, des invites système et une nouvelle fonctionnalité de test : l'appel d'outils."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku est le modèle de prochaine génération le plus rapide d'Anthropic. Par rapport à Claude 3 Haiku, Claude 3.5 Haiku a amélioré ses compétences dans tous les domaines et a surpassé le plus grand modèle de la génération précédente, Claude 3 Opus, dans de nombreux tests de référence intellectuels."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet offre des capacités dépassant celles d'Opus et une vitesse plus rapide que Sonnet, tout en maintenant le même prix que Sonnet. Sonnet excelle particulièrement dans la programmation, la science des données, le traitement visuel et les tâches d'agent."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet offre des capacités dépassant celles d'Opus et une vitesse supérieure à celle de Sonnet, tout en maintenant le même tarif que Sonnet. Sonnet excelle particulièrement dans la programmation, la science des données, le traitement visuel et les tâches d'agent."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet élève les normes de l'industrie, surpassant les modèles concurrents et Claude 3 Opus, avec d'excellentes performances dans une large gamme d'évaluations, tout en offrant la vitesse et le coût de nos modèles de niveau intermédiaire."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku est le modèle le plus rapide et le plus compact d'Anthropic, conçu pour des réponses quasi instantanées. Il présente des performances directionnelles rapides et précises."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet offre un équilibre idéal entre intelligence et vitesse pour les charges de travail d'entreprise. Il fournit une utilité maximale à un coût inférieur, fiable et adapté à un déploiement à grande échelle."
},
- "claude-instant-1.2": {
- "description": "Le modèle d'Anthropic est conçu pour une génération de texte à faible latence et à haut débit, prenant en charge la génération de centaines de pages de texte."
- },
"codegeex-4": {
"description": "CodeGeeX-4 est un puissant assistant de programmation AI, prenant en charge des questions intelligentes et l'achèvement de code dans divers langages de programmation, améliorant l'efficacité du développement."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B est un modèle de génération de code multilingue, offrant des fonctionnalités complètes, y compris la complétion et la génération de code, un interpréteur de code, une recherche sur le web, des appels de fonction et des questions-réponses sur le code au niveau des dépôts, couvrant divers scénarios de développement logiciel. C'est un modèle de génération de code de premier plan avec moins de 10B de paramètres."
+ },
"codegemma": {
"description": "CodeGemma est un modèle de langage léger dédié à différentes tâches de programmation, prenant en charge une itération et une intégration rapides."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama est un LLM axé sur la génération et la discussion de code, combinant un large support de langages de programmation, adapté aux environnements de développement."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama est un LLM axé sur la génération et la discussion de code, combinant un large support de langages de programmation, adapté aux environnements de développement."
+ },
"codellama:13b": {
"description": "Code Llama est un LLM axé sur la génération et la discussion de code, combinant un large support de langages de programmation, adapté aux environnements de développement."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ est un modèle de langage de grande taille à haute performance, conçu pour des scénarios d'entreprise réels et des applications complexes."
},
+ "dall-e-2": {
+ "description": "Le deuxième modèle DALL·E, prenant en charge la génération d'images plus réalistes et précises, avec une résolution quatre fois supérieure à celle de la première génération."
+ },
+ "dall-e-3": {
+ "description": "Le dernier modèle DALL·E, publié en novembre 2023. Prend en charge la génération d'images plus réalistes et précises, avec une meilleure expressivité des détails."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct offre des capacités de traitement d'instructions hautement fiables, prenant en charge des applications dans divers secteurs."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 est un modèle d'inférence alimenté par l'apprentissage par renforcement (RL), qui résout les problèmes de répétitivité et de lisibilité dans le modèle. Avant le RL, DeepSeek-R1 a introduit des données de démarrage à froid, optimisant ainsi les performances d'inférence. Il se compare à OpenAI-o1 en matière de tâches mathématiques, de code et d'inférence, et améliore l'efficacité globale grâce à des méthodes d'entraînement soigneusement conçues."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "Le modèle distillé DeepSeek-R1 optimise les performances d'inférence grâce à l'apprentissage par renforcement et aux données de démarrage à froid, rafraîchissant les références multi-tâches des modèles open source."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B est un modèle distillé basé sur Llama-3.1-8B. Ce modèle a été affiné avec des échantillons générés par DeepSeek-R1, montrant d'excellentes capacités d'inférence. Il a bien performé dans plusieurs tests de référence, atteignant 89,1 % de précision dans MATH-500, 50,4 % de taux de réussite dans AIME 2024, et un score de 1205 sur CodeForces, démontrant de fortes capacités en mathématiques et en programmation pour un modèle de 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Le modèle distillé DeepSeek-R1 optimise les performances d'inférence grâce à l'apprentissage par renforcement et aux données de démarrage à froid, rafraîchissant les références multi-tâches des modèles open source."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Le modèle distillé DeepSeek-R1 optimise les performances d'inférence grâce à l'apprentissage par renforcement et aux données de démarrage à froid, rafraîchissant les références multi-tâches des modèles open source."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B est un modèle obtenu par distillation de Qwen2.5-32B. Ce modèle a été affiné avec 800 000 échantillons sélectionnés générés par DeepSeek-R1, montrant des performances exceptionnelles dans plusieurs domaines tels que les mathématiques, la programmation et le raisonnement. Il a obtenu d'excellents résultats dans plusieurs tests de référence, atteignant 94,3 % de précision dans MATH-500, démontrant une forte capacité de raisonnement mathématique."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B est un modèle obtenu par distillation de Qwen2.5-Math-7B. Ce modèle a été affiné avec 800 000 échantillons sélectionnés générés par DeepSeek-R1, montrant d'excellentes capacités d'inférence. Il a obtenu d'excellents résultats dans plusieurs tests de référence, atteignant 92,8 % de précision dans MATH-500, 55,5 % de taux de réussite dans AIME 2024, et un score de 1189 sur CodeForces, démontrant de fortes capacités en mathématiques et en programmation pour un modèle de 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 intègre les excellentes caractéristiques des versions précédentes, renforçant les capacités générales et de codage."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 est un modèle de langage à experts mixtes (MoE) avec 6710 milliards de paramètres, utilisant une attention potentielle multi-tête (MLA) et l'architecture DeepSeekMoE, combinée à une stratégie d'équilibrage de charge sans perte auxiliaire, optimisant ainsi l'efficacité d'inférence et d'entraînement. En pré-entraînant sur 14,8 billions de tokens de haute qualité, suivi d'un ajustement supervisé et d'apprentissage par renforcement, DeepSeek-V3 surpasse les autres modèles open source en termes de performance, se rapprochant des modèles fermés de premier plan."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B est un modèle avancé formé pour des dialogues de haute complexité."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "LLM avancé et efficace, spécialisé dans le raisonnement, les mathématiques et la programmation."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 est un modèle de langage visuel à experts mixtes (MoE) développé sur la base de DeepSeekMoE-27B, utilisant une architecture MoE à activation sparse, réalisant des performances exceptionnelles tout en n'activant que 4,5 milliards de paramètres. Ce modèle excelle dans plusieurs tâches telles que la question-réponse visuelle, la reconnaissance optique de caractères, la compréhension de documents/tableaux/graphes et le positionnement visuel."
+ },
"deepseek-chat": {
"description": "Un nouveau modèle open source qui fusionne des capacités générales et de code, conservant non seulement la capacité de dialogue général du modèle Chat d'origine et la puissante capacité de traitement de code du modèle Coder, mais s'alignant également mieux sur les préférences humaines. De plus, DeepSeek-V2.5 a réalisé des améliorations significatives dans plusieurs domaines tels que les tâches d'écriture et le suivi des instructions."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B est un modèle de langage de code, entraîné sur 20 trillions de données, dont 87 % sont du code et 13 % des langues chinoise et anglaise. Le modèle introduit une taille de fenêtre de 16K et des tâches de remplissage, offrant des fonctionnalités de complétion de code et de remplissage de fragments au niveau des projets."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 est un modèle de code open source de type expert mixte, performant dans les tâches de code, rivalisant avec GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 est un modèle de code open source de type expert mixte, performant dans les tâches de code, rivalisant avec GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 est un modèle d'inférence alimenté par l'apprentissage par renforcement (RL), qui résout les problèmes de répétitivité et de lisibilité dans le modèle. Avant le RL, DeepSeek-R1 a introduit des données de démarrage à froid, optimisant ainsi les performances d'inférence. Il se compare à OpenAI-o1 en matière de tâches mathématiques, de code et d'inférence, et améliore l'efficacité globale grâce à des méthodes d'entraînement soigneusement conçues."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 — le modèle plus grand et plus intelligent de la suite DeepSeek — a été distillé dans l'architecture Llama 70B. Basé sur des tests de référence et des évaluations humaines, ce modèle est plus intelligent que le Llama 70B d'origine, en particulier dans les tâches nécessitant précision mathématique et factuelle."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Le modèle de la série DeepSeek-R1-Distill est obtenu par la technique de distillation des connaissances, en ajustant les échantillons générés par DeepSeek-R1 sur des modèles open source tels que Qwen et Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Le modèle de la série DeepSeek-R1-Distill est obtenu par la technique de distillation des connaissances, en ajustant les échantillons générés par DeepSeek-R1 sur des modèles open source tels que Qwen et Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Le modèle de la série DeepSeek-R1-Distill est obtenu par la technique de distillation des connaissances, en ajustant les échantillons générés par DeepSeek-R1 sur des modèles open source tels que Qwen et Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Le modèle de la série DeepSeek-R1-Distill est obtenu par la technique de distillation des connaissances, en ajustant les échantillons générés par DeepSeek-R1 sur des modèles open source tels que Qwen et Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Le modèle de la série DeepSeek-R1-Distill est obtenu par la technique de distillation des connaissances, en ajustant les échantillons générés par DeepSeek-R1 sur des modèles open source tels que Qwen et Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "Modèle d'inférence proposé par DeepSeek. Avant de fournir la réponse finale, le modèle génère d'abord une chaîne de pensée pour améliorer l'exactitude de la réponse finale."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 est un modèle de langage Mixture-of-Experts efficace, adapté aux besoins de traitement économique."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B est le modèle de code de conception de DeepSeek, offrant de puissantes capacités de génération de code."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 est un modèle MoE développé par la société Hangzhou DeepSeek AI Technology Research Co., Ltd., avec des performances exceptionnelles dans plusieurs évaluations, se classant au premier rang des modèles open source dans les classements principaux. Par rapport au modèle V2.5, la vitesse de génération a été multipliée par 3, offrant aux utilisateurs une expérience d'utilisation plus rapide et fluide."
+ },
"deepseek/deepseek-chat": {
"description": "Un nouveau modèle open source fusionnant des capacités générales et de codage, qui non seulement conserve les capacités de dialogue général du modèle Chat d'origine et la puissante capacité de traitement de code du modèle Coder, mais s'aligne également mieux sur les préférences humaines. De plus, DeepSeek-V2.5 a également réalisé des améliorations significatives dans plusieurs domaines tels que les tâches d'écriture et le suivi d'instructions."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 améliore considérablement les capacités de raisonnement du modèle avec très peu de données annotées. Avant de fournir la réponse finale, le modèle génère d'abord une chaîne de pensée pour améliorer l'exactitude de la réponse finale."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B est un modèle de langage de grande taille basé sur Llama3.3 70B, qui utilise le fine-tuning des sorties de DeepSeek R1 pour atteindre des performances compétitives comparables aux grands modèles de pointe."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B est un modèle de langage distillé basé sur Llama-3.1-8B-Instruct, entraîné en utilisant les sorties de DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B est un modèle de langage distillé basé sur Qwen 2.5 14B, entraîné en utilisant les sorties de DeepSeek R1. Ce modèle a surpassé l'o1-mini d'OpenAI dans plusieurs benchmarks, atteignant des résultats de pointe pour les modèles denses. Voici quelques résultats de benchmarks :\nAIME 2024 pass@1 : 69.7\nMATH-500 pass@1 : 93.9\nCodeForces Rating : 1481\nCe modèle, affiné à partir des sorties de DeepSeek R1, démontre des performances compétitives comparables à celles de modèles de pointe de plus grande taille."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B est un modèle de langage distillé basé sur Qwen 2.5 32B, entraîné en utilisant les sorties de DeepSeek R1. Ce modèle a surpassé l'o1-mini d'OpenAI dans plusieurs benchmarks, atteignant des résultats de pointe pour les modèles denses. Voici quelques résultats de benchmarks :\nAIME 2024 pass@1 : 72.6\nMATH-500 pass@1 : 94.3\nCodeForces Rating : 1691\nCe modèle, affiné à partir des sorties de DeepSeek R1, démontre des performances compétitives comparables à celles de modèles de pointe de plus grande taille."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 est le dernier modèle open source publié par l'équipe DeepSeek, offrant des performances d'inférence très puissantes, atteignant des niveaux comparables à ceux du modèle o1 d'OpenAI, en particulier dans les tâches de mathématiques, de programmation et de raisonnement."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 améliore considérablement les capacités de raisonnement du modèle avec très peu de données annotées. Avant de fournir la réponse finale, le modèle génère d'abord une chaîne de pensée pour améliorer l'exactitude de la réponse finale."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 a réalisé une percée majeure en termes de vitesse d'inférence par rapport aux modèles précédents. Il se classe au premier rang des modèles open source et peut rivaliser avec les modèles fermés les plus avancés au monde. DeepSeek-V3 utilise une architecture d'attention multi-tête (MLA) et DeepSeekMoE, qui ont été entièrement validées dans DeepSeek-V2. De plus, DeepSeek-V3 a introduit une stratégie auxiliaire sans perte pour l'équilibrage de charge et a établi des objectifs d'entraînement de prédiction multi-étiquettes pour obtenir de meilleures performances."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 a réalisé une percée majeure en termes de vitesse d'inférence par rapport aux modèles précédents. Il se classe au premier rang des modèles open source et peut rivaliser avec les modèles fermés les plus avancés au monde. DeepSeek-V3 utilise une architecture d'attention multi-tête (MLA) et DeepSeekMoE, qui ont été entièrement validées dans DeepSeek-V2. De plus, DeepSeek-V3 a introduit une stratégie auxiliaire sans perte pour l'équilibrage de charge et a établi des objectifs d'entraînement de prédiction multi-étiquettes pour obtenir de meilleures performances."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite est un modèle léger de nouvelle génération, offrant une vitesse de réponse extrême, avec des performances et des délais atteignant des niveaux de classe mondiale."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k est une version améliorée de Doubao-1.5-Pro, offrant une amélioration globale de 10%. Il prend en charge le raisonnement avec une fenêtre contextuelle de 256k et une longueur de sortie maximale de 12k tokens. Performances supérieures, plus grande fenêtre, rapport qualité-prix exceptionnel, adapté à un large éventail de scénarios d'application."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro est un modèle phare de nouvelle génération, avec des performances entièrement améliorées, se distinguant dans les domaines de la connaissance, du code, du raisonnement, etc."
+ },
"emohaa": {
"description": "Emohaa est un modèle psychologique, doté de compétences de conseil professionnel, aidant les utilisateurs à comprendre les problèmes émotionnels."
},
+ "ernie-3.5-128k": {
+ "description": "Le modèle de langage de grande taille phare développé par Baidu, couvrant une vaste quantité de corpus en chinois et en anglais, avec de puissantes capacités générales, capable de répondre à la plupart des exigences en matière de questions-réponses, de génération créative et d'applications de plugins ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ernie-3.5-8k": {
+ "description": "Le modèle de langage de grande taille phare développé par Baidu, couvrant une vaste quantité de corpus en chinois et en anglais, avec de puissantes capacités générales, capable de répondre à la plupart des exigences en matière de questions-réponses, de génération créative et d'applications de plugins ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Le modèle de langage de grande taille phare développé par Baidu, couvrant une vaste quantité de corpus en chinois et en anglais, avec de puissantes capacités générales, capable de répondre à la plupart des exigences en matière de questions-réponses, de génération créative et d'applications de plugins ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Le modèle de langage de très grande taille phare développé par Baidu, par rapport à ERNIE 3.5, a réalisé une mise à niveau complète des capacités du modèle, largement applicable à des scénarios de tâches complexes dans divers domaines ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Le modèle de langage de très grande taille phare développé par Baidu, par rapport à ERNIE 3.5, a réalisé une mise à niveau complète des capacités du modèle, largement applicable à des scénarios de tâches complexes dans divers domaines ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Le modèle de langage de très grande taille phare développé par Baidu, avec d'excellentes performances globales, largement applicable à des scénarios de tâches complexes dans divers domaines ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse. Par rapport à ERNIE 4.0, il offre de meilleures performances."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Le modèle de langage de très grande taille phare développé par Baidu, avec d'excellentes performances globales, largement applicable à des scénarios de tâches complexes dans divers domaines ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse. Par rapport à ERNIE 4.0, il offre de meilleures performances."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Le modèle de langage de très grande taille phare développé par Baidu, avec d'excellentes performances globales, largement applicable à des scénarios de tâches complexes dans divers domaines ; supporte l'intégration automatique avec le plugin de recherche Baidu, garantissant la pertinence des informations de réponse. Par rapport à ERNIE 4.0, il offre de meilleures performances."
+ },
+ "ernie-char-8k": {
+ "description": "Le modèle de langage pour des scénarios verticaux développé par Baidu, adapté aux dialogues de NPC de jeux, aux dialogues de service client, aux jeux de rôle, avec un style de personnage plus distinct et cohérent, une meilleure capacité de suivi des instructions et des performances d'inférence supérieures."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Le modèle de langage pour des scénarios verticaux développé par Baidu, adapté aux dialogues de NPC de jeux, aux dialogues de service client, aux jeux de rôle, avec un style de personnage plus distinct et cohérent, une meilleure capacité de suivi des instructions et des performances d'inférence supérieures."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite est un modèle de langage léger développé par Baidu, alliant d'excellentes performances du modèle et performances d'inférence, adapté à une utilisation sur des cartes d'accélération AI à faible puissance."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Un modèle de langage léger développé par Baidu, alliant d'excellentes performances du modèle et performances d'inférence, avec des résultats supérieurs à ceux d'ERNIE Lite, adapté à une utilisation sur des cartes d'accélération AI à faible puissance."
+ },
+ "ernie-novel-8k": {
+ "description": "Le modèle de langage général développé par Baidu, avec un avantage évident dans la capacité de continuation de romans, également applicable à des scénarios de courtes pièces, de films, etc."
+ },
+ "ernie-speed-128k": {
+ "description": "Le modèle de langage haute performance développé par Baidu, publié en 2024, avec d'excellentes capacités générales, adapté comme modèle de base pour un affinage, permettant de mieux traiter des problèmes spécifiques, tout en offrant d'excellentes performances d'inférence."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Le modèle de langage haute performance développé par Baidu, publié en 2024, avec d'excellentes capacités générales, offrant de meilleures performances que l'ERNIE Speed, adapté comme modèle de base pour un affinage, permettant de mieux traiter des problèmes spécifiques, tout en offrant d'excellentes performances d'inférence."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny est un modèle de langage à très haute performance développé par Baidu, avec les coûts de déploiement et d'affinage les plus bas parmi les modèles de la série Wenxin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Ajustement) offre des performances stables et ajustables, ce qui en fait un choix idéal pour des solutions de tâches complexes."
},
@@ -329,14 +791,17 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro est le modèle d'IA haute performance de Google, conçu pour une large extension des tâches."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash est le dernier modèle d'IA multimodale de Google, doté d'une capacité de traitement rapide, prenant en charge les entrées de texte, d'images et de vidéos, et adapté à une extension efficace pour diverses tâches."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 est un modèle multimodal efficace, prenant en charge l'extension d'applications variées."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 est un modèle multimodal efficace, prenant en charge une large gamme d'applications."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 est conçu pour traiter des scénarios de tâches à grande échelle, offrant une vitesse de traitement inégalée."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B est un modèle multimodal efficace, prenant en charge une large gamme d'applications."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 est le dernier modèle expérimental, offrant des améliorations significatives en termes de performance dans les cas d'utilisation textuels et multimodaux."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002 est le dernier modèle prêt pour la production, offrant une qualité de sortie supérieure, avec des améliorations notables dans les domaines des mathématiques, des contextes longs et des tâches visuelles."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 offre d'excellentes capacités de traitement multimodal, apportant une plus grande flexibilité au développement d'applications."
+ "description": "Gemini 1.5 Pro 0801 offre d'excellentes capacités de traitement multimodal, apportant plus de flexibilité au développement d'applications."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 combine les dernières technologies d'optimisation, offrant une capacité de traitement de données multimodales plus efficace."
+ "description": "Gemini 1.5 Pro 0827 combine les dernières technologies d'optimisation pour offrir des capacités de traitement de données multimodales plus efficaces."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro prend en charge jusqu'à 2 millions de tokens, ce qui en fait un choix idéal pour un modèle multimodal de taille moyenne, adapté à un soutien polyvalent pour des tâches complexes."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash propose des fonctionnalités et des améliorations de nouvelle génération, y compris une vitesse exceptionnelle, l'utilisation d'outils natifs, la génération multimodale et une fenêtre de contexte de 1M tokens."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash propose des fonctionnalités et des améliorations de nouvelle génération, y compris une vitesse exceptionnelle, l'utilisation d'outils natifs, la génération multimodale et une fenêtre de contexte de 1M tokens."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Une variante du modèle Gemini 2.0 Flash, optimisée pour des objectifs tels que le rapport coût-efficacité et la faible latence."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Une variante du modèle Gemini 2.0 Flash, optimisée pour des objectifs tels que le rapport coût-efficacité et la faible latence."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Un modèle Gemini 2.0 Flash optimisé pour des objectifs de rentabilité et de faible latence."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp est le dernier modèle d'IA multimodal expérimental de Google, doté de caractéristiques de nouvelle génération, d'une vitesse exceptionnelle, d'appels d'outils natifs et de génération multimodale."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp est le dernier modèle d'IA multimodal expérimental de Google, doté de caractéristiques de nouvelle génération, d'une vitesse exceptionnelle, d'appels d'outils natifs et de génération multimodale."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental est le dernier modèle AI multimodal expérimental de Google, offrant une amélioration de la qualité par rapport aux versions précédentes, en particulier pour les connaissances générales, le code et les longs contextes."
+ },
"gemma-7b-it": {
"description": "Gemma 7B est adapté au traitement de tâches de taille moyenne, alliant coût et efficacité."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 est un modèle efficace lancé par Google, couvrant une variété de scénarios d'application allant des petites applications au traitement de données complexes."
},
- "general": {
- "description": "Spark Lite est un modèle de langage léger, offrant une latence extrêmement faible et une capacité de traitement efficace, entièrement gratuit et ouvert, supportant une fonction de recherche en temps réel. Sa rapidité de réponse le rend exceptionnel dans les applications d'inférence sur des appareils à faible puissance de calcul et dans l'ajustement des modèles, offrant aux utilisateurs un excellent rapport coût-efficacité et une expérience intelligente, en particulier dans les scénarios de questions-réponses, de génération de contenu et de recherche."
- },
"generalv3": {
"description": "Spark Pro est un modèle de langage de haute performance optimisé pour des domaines professionnels, se concentrant sur les mathématiques, la programmation, la médecine, l'éducation, etc., et supportant la recherche en ligne ainsi que des plugins intégrés pour la météo, la date, etc. Son modèle optimisé affiche d'excellentes performances et une efficacité dans des tâches complexes de questions-réponses, de compréhension linguistique et de création de textes de haut niveau, en faisant un choix idéal pour des applications professionnelles."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 est la dernière version du modèle, conçue pour des tâches hautement complexes et diversifiées, avec des performances exceptionnelles."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat affiche de bonnes performances dans divers domaines tels que la sémantique, les mathématiques, le raisonnement, le code et les connaissances. Il dispose également de fonctionnalités de navigation sur le web, d'exécution de code, d'appels d'outils personnalisés et de raisonnement sur de longs textes. Il prend en charge 26 langues, y compris le japonais, le coréen et l'allemand."
+ },
"glm-4-air": {
"description": "GLM-4-Air est une version économique, offrant des performances proches de GLM-4, avec une rapidité et un prix abordable."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash est le choix idéal pour traiter des tâches simples, avec la vitesse la plus rapide et le prix le plus avantageux."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX est une version améliorée de Flash, offrant une vitesse d'inférence ultra-rapide."
+ },
"glm-4-long": {
"description": "GLM-4-Long prend en charge des entrées de texte ultra-longues, adapté aux tâches de mémoire et au traitement de documents à grande échelle."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V offre de puissantes capacités de compréhension et de raisonnement d'image, prenant en charge diverses tâches visuelles."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash se concentre sur la compréhension efficace d'une seule image, adapté aux scénarios d'analyse d'image rapide, tels que l'analyse d'image en temps réel ou le traitement d'images en lot."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus possède la capacité de comprendre le contenu vidéo et plusieurs images, adapté aux tâches multimodales."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 offre des capacités de traitement multimodal optimisées, adaptées à divers scénarios de tâches complexes."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview possède de puissantes capacités de raisonnement complexe, se distinguant dans les domaines du raisonnement logique, des mathématiques et de la programmation."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 combine les dernières technologies d'optimisation pour offrir des capacités de traitement de données multimodales plus efficaces."
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash propose des fonctionnalités et des améliorations de nouvelle génération, y compris une vitesse exceptionnelle, l'utilisation d'outils natifs, la génération multimodale et une fenêtre de contexte de 1M tokens."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental est le dernier modèle AI multimodal expérimental de Google, offrant une amélioration de la qualité par rapport aux versions précédentes, en particulier pour les connaissances générales, le code et les longs contextes."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash propose des capacités de traitement multimodal optimisées, adaptées à divers scénarios de tâches complexes."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro combine les dernières technologies d'optimisation pour offrir une capacité de traitement de données multimodales plus efficace."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 est un modèle efficace lancé par Google, couvrant une variété de scénarios d'application allant des petites applications au traitement de données complexes."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 poursuit le concept de conception légère et efficace."
},
+ "google/gemma-2-2b-it": {
+ "description": "Modèle d'optimisation des instructions léger de Google."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 est un modèle efficace lancé par Google, couvrant une variété de scénarios d'application allant des petites applications au traitement de données complexes."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 est une série de modèles de texte open source allégés de Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, adapté à diverses tâches de génération et de compréhension de texte, pointe actuellement vers gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo, un modèle efficace proposé par OpenAI, adapté aux tâches de chat et de génération de texte, prenant en charge les appels de fonction en parallèle."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k, un modèle de génération de texte à haute capacité, adapté aux tâches complexes."
+ },
"gpt-4": {
"description": "GPT-4 offre une fenêtre contextuelle plus grande, capable de traiter des entrées textuelles plus longues, adapté aux scénarios nécessitant une intégration d'informations étendue et une analyse de données."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "Le dernier modèle GPT-4 Turbo dispose de fonctionnalités visuelles. Désormais, les requêtes visuelles peuvent être effectuées en utilisant le mode JSON et les appels de fonction. GPT-4 Turbo est une version améliorée, offrant un soutien rentable pour les tâches multimodales. Il trouve un équilibre entre précision et efficacité, adapté aux applications nécessitant des interactions en temps réel."
},
- "gpt-4-1106-vision-preview": {
- "description": "Le dernier modèle GPT-4 Turbo dispose de fonctionnalités visuelles. Désormais, les requêtes visuelles peuvent être effectuées en utilisant le mode JSON et les appels de fonction. GPT-4 Turbo est une version améliorée, offrant un soutien rentable pour les tâches multimodales. Il trouve un équilibre entre précision et efficacité, adapté aux applications nécessitant des interactions en temps réel."
- },
"gpt-4-32k": {
"description": "GPT-4 offre une fenêtre contextuelle plus grande, capable de traiter des entrées textuelles plus longues, adapté aux scénarios nécessitant une intégration d'informations étendue et une analyse de données."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "Le dernier modèle GPT-4 Turbo dispose de fonctionnalités visuelles. Désormais, les requêtes visuelles peuvent être effectuées en utilisant le mode JSON et les appels de fonction. GPT-4 Turbo est une version améliorée, offrant un soutien rentable pour les tâches multimodales. Il trouve un équilibre entre précision et efficacité, adapté aux applications nécessitant des interactions en temps réel."
},
+ "gpt-4.5-preview": {
+ "description": "La version de recherche préliminaire de GPT-4.5, qui est notre modèle GPT le plus grand et le plus puissant à ce jour. Il possède une vaste connaissance du monde et comprend mieux les intentions des utilisateurs, ce qui le rend exceptionnel dans les tâches créatives et la planification autonome. GPT-4.5 accepte les entrées textuelles et visuelles et génère des sorties textuelles (y compris des sorties structurées). Il prend en charge des fonctionnalités clés pour les développeurs, telles que les appels de fonctions, l'API par lots et les sorties en continu. GPT-4.5 excelle particulièrement dans les tâches nécessitant créativité, pensée ouverte et dialogue (comme l'écriture, l'apprentissage ou l'exploration de nouvelles idées). La date limite des connaissances est fixée à octobre 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o est un modèle dynamique, mis à jour en temps réel pour rester à jour avec la dernière version. Il combine une compréhension et une génération de langage puissantes, adapté à des scénarios d'application à grande échelle, y compris le service client, l'éducation et le support technique."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o est un modèle dynamique, mis à jour en temps réel pour rester à jour avec la dernière version. Il combine une compréhension et une génération de langage puissantes, adapté à des scénarios d'application à grande échelle, y compris le service client, l'éducation et le support technique."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o est un modèle dynamique, mis à jour en temps réel pour rester à jour avec la dernière version. Il combine une compréhension linguistique puissante et des capacités de génération, adapté aux scénarios d'application à grande échelle, y compris le service client, l'éducation et le support technique."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Modèle audio GPT-4o, prenant en charge les entrées et sorties audio."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini est le dernier modèle lancé par OpenAI après le GPT-4 Omni, prenant en charge les entrées multimodales et produisant des sorties textuelles. En tant que leur modèle compact le plus avancé, il est beaucoup moins cher que d'autres modèles de pointe récents et coûte plus de 60 % de moins que le GPT-3.5 Turbo. Il maintient une intelligence de pointe tout en offrant un rapport qualité-prix significatif. Le GPT-4o mini a obtenu un score de 82 % au test MMLU et se classe actuellement au-dessus du GPT-4 en termes de préférences de chat."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Version mini en temps réel de GPT-4o, prenant en charge les entrées et sorties audio et textuelles en temps réel."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Version en temps réel de GPT-4o, prenant en charge les entrées et sorties audio et textuelles en temps réel."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Version en temps réel de GPT-4o, prenant en charge les entrées et sorties audio et textuelles en temps réel."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Version en temps réel de GPT-4o, prenant en charge les entrées et sorties audio et textuelles en temps réel."
+ },
+ "grok-2-1212": {
+ "description": "Ce modèle a été amélioré en termes de précision, de respect des instructions et de capacités multilingues."
+ },
+ "grok-2-vision-1212": {
+ "description": "Ce modèle a été amélioré en termes de précision, de respect des instructions et de capacités multilingues."
+ },
+ "grok-beta": {
+ "description": "Offre des performances comparables à Grok 2, mais avec une efficacité, une vitesse et des fonctionnalités supérieures."
+ },
+ "grok-vision-beta": {
+ "description": "Le dernier modèle de compréhension d'image, capable de traiter une variété d'informations visuelles, y compris des documents, des graphiques, des captures d'écran et des photos."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B est un modèle linguistique combinant créativité et intelligence, intégrant plusieurs modèles de pointe."
},
+ "hunyuan-code": {
+ "description": "Dernier modèle de génération de code Hunyuan, formé sur un modèle de base avec 200B de données de code de haute qualité, entraîné pendant six mois avec des données SFT de haute qualité, avec une longueur de fenêtre contextuelle augmentée à 8K, se classant parmi les meilleurs sur les indicateurs d'évaluation automatique de génération de code dans cinq langages ; en première ligne des évaluations de qualité humaine sur dix aspects de tâches de code dans cinq langages."
+ },
+ "hunyuan-functioncall": {
+ "description": "Dernier modèle FunctionCall de l'architecture MOE Hunyuan, formé sur des données FunctionCall de haute qualité, avec une fenêtre contextuelle atteignant 32K, se classant parmi les meilleurs sur plusieurs dimensions d'évaluation."
+ },
+ "hunyuan-large": {
+ "description": "Le modèle Hunyuan-large a un nombre total de paramètres d'environ 389B, avec environ 52B de paramètres activés, ce qui en fait le modèle MoE open source de l'architecture Transformer avec le plus grand nombre de paramètres et les meilleures performances dans l'industrie."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Expert dans le traitement des tâches de longs documents telles que le résumé de documents et les questions-réponses sur des documents, tout en ayant également la capacité de traiter des tâches de génération de texte général. Il excelle dans l'analyse et la génération de longs textes, capable de répondre efficacement aux besoins de traitement de contenus longs complexes et détaillés."
+ },
+ "hunyuan-lite": {
+ "description": "Mise à niveau vers une structure MOE, avec une fenêtre contextuelle de 256k, en tête de nombreux modèles open source dans les évaluations NLP, code, mathématiques, industrie, etc."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Le dernier modèle multimodal 7B de Hunyuan, avec une fenêtre contextuelle de 32K, prend en charge les dialogues multimodaux en chinois et en anglais, la reconnaissance d'objets d'images, la compréhension de documents et de tableaux, ainsi que les mathématiques multimodales, surpassant les modèles concurrents de 7B sur plusieurs dimensions d'évaluation."
+ },
+ "hunyuan-pro": {
+ "description": "Modèle de long texte MOE-32K avec un milliard de paramètres. Atteint un niveau de performance absolument supérieur sur divers benchmarks, capable de traiter des instructions complexes et de raisonner, avec des capacités mathématiques avancées, prenant en charge les appels de fonction, optimisé pour des domaines tels que la traduction multilingue, le droit financier et médical."
+ },
+ "hunyuan-role": {
+ "description": "Dernier modèle de jeu de rôle Hunyuan, un modèle de jeu de rôle affiné et formé par l'équipe officielle de Hunyuan, basé sur le modèle Hunyuan et des ensembles de données de scénarios de jeu de rôle, offrant de meilleures performances de base dans les scénarios de jeu de rôle."
+ },
+ "hunyuan-standard": {
+ "description": "Utilise une stratégie de routage améliorée tout en atténuant les problèmes d'équilibrage de charge et de convergence des experts. Pour les longs textes, l'indice de recherche atteint 99,9 %. MOE-32K offre un meilleur rapport qualité-prix, équilibrant efficacité et coût tout en permettant le traitement des entrées de longs textes."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Utilise une stratégie de routage améliorée tout en atténuant les problèmes d'équilibrage de charge et de convergence des experts. Pour les longs textes, l'indice de recherche atteint 99,9 %. MOE-256K franchit de nouvelles étapes en termes de longueur et d'efficacité, élargissant considérablement la longueur d'entrée possible."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Le dernier modèle multimodal de Hunyuan, prenant en charge les réponses multilingues, avec des capacités équilibrées en chinois et en anglais."
+ },
+ "hunyuan-translation": {
+ "description": "Supporte la traduction entre le chinois et l'anglais, le japonais, le français, le portugais, l'espagnol, le turc, le russe, l'arabe, le coréen, l'italien, l'allemand, le vietnamien, le malais et l'indonésien, soit 15 langues au total, avec une évaluation automatisée basée sur le score COMET à partir d'un ensemble d'évaluation de traduction multi-scénarios, montrant une capacité de traduction globale supérieure à celle des modèles de taille similaire sur le marché."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Le modèle de traduction Hunyuan prend en charge la traduction en dialogue naturel ; il supporte la traduction entre le chinois et l'anglais, le japonais, le français, le portugais, l'espagnol, le turc, le russe, l'arabe, le coréen, l'italien, l'allemand, le vietnamien, le malais et l'indonésien, soit 15 langues au total."
+ },
+ "hunyuan-turbo": {
+ "description": "Version préliminaire du nouveau modèle de langage de génération Hunyuan, utilisant une nouvelle structure de modèle d'experts mixtes (MoE), offrant une efficacité d'inférence plus rapide et de meilleures performances par rapport à Hunyuan-Pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Version fixe de hunyuan-turbo du 20 novembre 2024, une version intermédiaire entre hunyuan-turbo et hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Optimisations de cette version : mise à l'échelle des instructions de données, augmentation significative de la capacité de généralisation du modèle ; amélioration significative des capacités en mathématiques, en code et en raisonnement logique ; optimisation des capacités de compréhension des mots dans le texte ; optimisation de la qualité de génération de contenu dans la création de texte."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Optimisation de l'expérience générale, y compris la compréhension NLP, la création de texte, les conversations informelles, les questions-réponses, la traduction, et les domaines spécifiques ; amélioration de l'humanité simulée, optimisation de l'intelligence émotionnelle du modèle ; amélioration de la capacité du modèle à clarifier activement en cas d'ambiguïté d'intention ; amélioration de la capacité à traiter les questions de décomposition de mots ; amélioration de la qualité et de l'interactivité de la création ; amélioration de l'expérience multi-tours."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Le nouveau modèle phare de langage visuel de Hunyuan de nouvelle génération, utilisant une toute nouvelle structure de modèle d'experts hybrides (MoE), avec des améliorations complètes par rapport à la génération précédente dans les capacités de reconnaissance de base, de création de contenu, de questions-réponses, et d'analyse et de raisonnement liés à la compréhension d'images et de textes."
+ },
+ "hunyuan-vision": {
+ "description": "Dernier modèle multimodal Hunyuan, prenant en charge l'entrée d'images et de textes pour générer du contenu textuel."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Le modèle open source innovant InternLM2.5 améliore l'intelligence des dialogues grâce à un grand nombre de paramètres."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 fournit des solutions de dialogue intelligent dans divers scénarios."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Le modèle Llama 3.1 70B Instruct, avec 70B de paramètres, offre des performances exceptionnelles dans la génération de texte et les tâches d'instructions."
+ "internlm2-pro-chat": {
+ "description": "Une ancienne version du modèle que nous maintenons encore, avec des options de paramètres de 7B et 20B disponibles."
+ },
+ "internlm2.5-latest": {
+ "description": "Notre dernière série de modèles, offrant des performances d'inférence exceptionnelles, prenant en charge une longueur de contexte de 1M et des capacités améliorées de suivi des instructions et d'appel d'outils."
+ },
+ "internlm3-latest": {
+ "description": "Notre dernière série de modèles, avec des performances d'inférence exceptionnelles, en tête des modèles open source de même niveau. Par défaut, elle pointe vers notre dernière version du modèle InternLM3."
+ },
+ "jina-deepsearch-v1": {
+ "description": "La recherche approfondie combine la recherche sur le web, la lecture et le raisonnement pour mener des enquêtes complètes. Vous pouvez la considérer comme un agent qui prend en charge vos tâches de recherche - elle effectuera une recherche approfondie et itérative avant de fournir une réponse. Ce processus implique une recherche continue, un raisonnement et une résolution de problèmes sous différents angles. Cela diffère fondamentalement des grands modèles standard qui génèrent des réponses directement à partir de données pré-entraînées et des systèmes RAG traditionnels qui dépendent d'une recherche superficielle unique."
+ },
+ "kimi-latest": {
+ "description": "Le produit d'assistant intelligent Kimi utilise le dernier modèle Kimi, qui peut inclure des fonctionnalités encore instables. Il prend en charge la compréhension des images et choisit automatiquement le modèle de facturation 8k/32k/128k en fonction de la longueur du contexte de la demande."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM est un modèle de langage expérimental, spécifique à des tâches, formé pour respecter les principes des sciences de l'apprentissage, capable de suivre des instructions systématiques dans des contextes d'enseignement et d'apprentissage, agissant comme un mentor expert, entre autres."
+ },
+ "lite": {
+ "description": "Spark Lite est un modèle de langage léger, offrant une latence extrêmement faible et une capacité de traitement efficace, entièrement gratuit et ouvert, prenant en charge la recherche en temps réel. Sa capacité de réponse rapide le rend exceptionnel pour les applications d'inférence sur des appareils à faible puissance de calcul et pour le réglage des modèles, offrant aux utilisateurs un excellent rapport coût-efficacité et une expérience intelligente, en particulier dans les scénarios de questions-réponses, de génération de contenu et de recherche."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B offre une capacité de raisonnement AI plus puissante, adaptée aux applications complexes, prenant en charge un traitement de calcul intensif tout en garantissant efficacité et précision."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B est un modèle à haute performance, offrant une capacité de génération de texte rapide, particulièrement adapté aux scénarios d'application nécessitant une efficacité à grande échelle et un rapport coût-efficacité."
},
- "llama-3.1-8b-instruct": {
- "description": "Le modèle Llama 3.1 8B Instruct, avec 8B de paramètres, prend en charge l'exécution efficace des tâches d'instructions visuelles, offrant d'excellentes capacités de génération de texte."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Capacités d'inférence d'image exceptionnelles sur des images haute résolution, adaptées aux applications de compréhension visuelle."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Le modèle Llama 3.1 Sonar Huge Online, avec 405B de paramètres, prend en charge une longueur de contexte d'environ 127 000 jetons, conçu pour des applications de chat en ligne complexes."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 est conçu pour traiter des tâches combinant des données visuelles et textuelles. Il excelle dans des tâches telles que la description d'images et les questions-réponses visuelles, comblant le fossé entre la génération de langage et le raisonnement visuel."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Le modèle Llama 3.1 Sonar Large Chat, avec 70B de paramètres, prend en charge une longueur de contexte d'environ 127 000 jetons, adapté aux tâches de chat hors ligne complexes."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Capacités d'inférence d'image avancées pour les applications d'agents de compréhension visuelle."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Le modèle Llama 3.1 Sonar Large Online, avec 70B de paramètres, prend en charge une longueur de contexte d'environ 127 000 jetons, adapté aux tâches de chat à haute capacité et diversifiées."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 est conçu pour traiter des tâches combinant des données visuelles et textuelles. Il excelle dans des tâches telles que la description d'images et les questions-réponses visuelles, comblant le fossé entre la génération de langage et le raisonnement visuel."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Le modèle Llama 3.1 Sonar Small Chat, avec 8B de paramètres, est conçu pour le chat hors ligne, prenant en charge une longueur de contexte d'environ 127 000 jetons."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 est le modèle de langage open source multilingue le plus avancé de la série Llama, offrant des performances comparables à celles du modèle 405B à un coût très bas. Basé sur une architecture Transformer, il améliore son utilité et sa sécurité grâce à un ajustement supervisé (SFT) et un apprentissage par renforcement avec retour humain (RLHF). Sa version optimisée pour les instructions est spécialement conçue pour les dialogues multilingues et surpasse de nombreux modèles de chat open source et fermés sur plusieurs benchmarks industriels. La date limite des connaissances est décembre 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Le modèle Llama 3.1 Sonar Small Online, avec 8B de paramètres, prend en charge une longueur de contexte d'environ 127 000 jetons, conçu pour le chat en ligne, capable de traiter efficacement diverses interactions textuelles."
+ "llama-3.3-70b-versatile": {
+ "description": "Le modèle de langage multilingue Llama 3.3 de Meta (LLM) est un modèle génératif pré-entraîné et affiné par instructions avec 70B (entrée/sortie de texte). Le modèle Llama 3.3 affiné par instructions est optimisé pour les cas d'utilisation de dialogue multilingue et surpasse de nombreux modèles de chat open-source et fermés disponibles sur des benchmarks industriels courants."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B offre une capacité de traitement de complexité inégalée, sur mesure pour des projets exigeants."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral est conçu pour la recherche scientifique et le raisonnement mathématique, offrant des capacités de calcul efficaces et des interprétations de résultats."
},
+ "max-32k": {
+ "description": "Spark Max 32K est équipé d'une grande capacité de traitement de contexte, avec une compréhension contextuelle et des capacités de raisonnement logique renforcées, prenant en charge des entrées textuelles de 32K tokens, adapté à la lecture de documents longs, aux questions-réponses privées et à d'autres scénarios."
+ },
"meta-llama-3-70b-instruct": {
"description": "Un puissant modèle de 70 milliards de paramètres excelling dans le raisonnement, le codage et les applications linguistiques larges."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) offre d'excellentes capacités de traitement du langage et une expérience interactive exceptionnelle."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 offre d'excellentes capacités de traitement du langage et une expérience d'interaction exceptionnelle."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) est un modèle de chat puissant, prenant en charge des besoins de dialogue complexes."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) offre un support multilingue, couvrant un large éventail de connaissances."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 est conçu pour traiter des tâches qui combinent des données visuelles et textuelles. Il excelle dans des tâches comme la description d'image et le questionnement visuel, comblant le fossé entre génération de langage et raisonnement visuel."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 est conçu pour traiter des tâches qui combinent des données visuelles et textuelles. Il excelle dans des tâches comme la description d'image et le questionnement visuel, comblant le fossé entre génération de langage et raisonnement visuel."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 est conçu pour traiter des tâches qui combinent des données visuelles et textuelles. Il excelle dans des tâches comme la description d'image et le questionnement visuel, comblant le fossé entre génération de langage et raisonnement visuel."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 est le modèle de langage open source multilingue le plus avancé de la série Llama, offrant une expérience comparable aux performances du modèle 405B à un coût très bas. Basé sur une architecture Transformer, il améliore l'utilité et la sécurité grâce à un ajustement supervisé (SFT) et un apprentissage par renforcement avec retour humain (RLHF). Sa version optimisée pour les instructions est spécialement conçue pour les dialogues multilingues, surpassant de nombreux modèles de chat open source et fermés sur plusieurs benchmarks industriels. Date limite de connaissance : décembre 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Le modèle de langage multilingue Meta Llama 3.3 (LLM) est un modèle génératif pré-entraîné et ajusté par instruction de 70B (entrée/sortie de texte). Le modèle de texte pur ajusté par instruction Llama 3.3 est optimisé pour les cas d'utilisation de dialogue multilingue et surpasse de nombreux modèles de chat open source et fermés sur des benchmarks industriels courants."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 est conçu pour traiter des tâches qui combinent des données visuelles et textuelles. Il excelle dans des tâches comme la description d'image et le questionnement visuel, comblant le fossé entre génération de langage et raisonnement visuel."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite est adapté aux environnements nécessitant une haute performance et une faible latence."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "Le modèle Llama 3.1 Turbo 405B offre un support de contexte de très grande capacité pour le traitement de grandes données, se distinguant dans les applications d'intelligence artificielle à très grande échelle."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 est le modèle de pointe lancé par Meta, prenant en charge jusqu'à 405B de paramètres, applicable aux dialogues complexes, à la traduction multilingue et à l'analyse de données."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B offre un support de dialogue efficace en plusieurs langues."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct optimise les scénarios de dialogue de haute qualité, avec des performances supérieures à de nombreux modèles fermés."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct est la dernière version lancée par Meta, optimisée pour générer des dialogues de haute qualité, surpassant de nombreux modèles fermés de premier plan."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct est conçu pour des dialogues de haute qualité, se distinguant dans les évaluations humaines, particulièrement adapté aux scénarios d'interaction élevée."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 offre un support multilingue et est l'un des modèles génératifs les plus avancés de l'industrie."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 est conçu pour traiter des tâches combinant des données visuelles et textuelles. Il excelle dans des tâches telles que la description d'images et les questions-réponses visuelles, comblant le fossé entre la génération de langage et le raisonnement visuel."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 est conçu pour traiter des tâches combinant des données visuelles et textuelles. Il excelle dans des tâches telles que la description d'images et les questions-réponses visuelles, comblant le fossé entre la génération de langage et le raisonnement visuel."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 est le modèle de langage open source multilingue le plus avancé de la série Llama, offrant des performances comparables à celles du modèle 405B à un coût très bas. Basé sur une architecture Transformer, il améliore son utilité et sa sécurité grâce à un ajustement supervisé (SFT) et un apprentissage par renforcement avec retour humain (RLHF). Sa version optimisée pour les instructions est spécialement conçue pour les dialogues multilingues et surpasse de nombreux modèles de chat open source et fermés sur plusieurs benchmarks industriels. La date limite des connaissances est décembre 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 est le modèle de langage open source multilingue le plus avancé de la série Llama, offrant des performances comparables à celles du modèle 405B à un coût très bas. Basé sur une architecture Transformer, il améliore son utilité et sa sécurité grâce à un ajustement supervisé (SFT) et un apprentissage par renforcement avec retour humain (RLHF). Sa version optimisée pour les instructions est spécialement conçue pour les dialogues multilingues et surpasse de nombreux modèles de chat open source et fermés sur plusieurs benchmarks industriels. La date limite des connaissances est décembre 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct est le modèle le plus grand et le plus puissant du modèle Llama 3.1 Instruct. C'est un modèle de génération de données de dialogue et de raisonnement hautement avancé, qui peut également servir de base pour un pré-entraînement ou un ajustement fin spécialisé dans des domaines spécifiques. Les modèles de langage multilingues (LLMs) fournis par Llama 3.1 sont un ensemble de modèles génératifs pré-entraînés et ajustés par instructions, comprenant des tailles de 8B, 70B et 405B (entrée/sortie de texte). Les modèles de texte ajustés par instructions de Llama 3.1 (8B, 70B, 405B) sont optimisés pour des cas d'utilisation de dialogue multilingue et ont surpassé de nombreux modèles de chat open source disponibles dans des benchmarks industriels courants. Llama 3.1 est conçu pour des usages commerciaux et de recherche dans plusieurs langues. Les modèles de texte ajustés par instructions conviennent aux chats de type assistant, tandis que les modèles pré-entraînés peuvent s'adapter à diverses tâches de génération de langage naturel. Le modèle Llama 3.1 prend également en charge l'amélioration d'autres modèles en utilisant sa sortie, y compris la génération de données synthétiques et le raffinement. Llama 3.1 est un modèle de langage autoregressif utilisant une architecture de transformateur optimisée. Les versions ajustées utilisent un ajustement fin supervisé (SFT) et un apprentissage par renforcement avec retour humain (RLHF) pour répondre aux préférences humaines en matière d'utilité et de sécurité."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 est un modèle de langage ouvert (LLM) destiné aux développeurs, chercheurs et entreprises, conçu pour les aider à construire, expérimenter et étendre de manière responsable leurs idées d'IA générative. En tant que partie intégrante d'un système de base pour l'innovation de la communauté mondiale, il est particulièrement adapté aux appareils à capacité de calcul et de ressources limitées, ainsi qu'à des temps d'entraînement plus rapides."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B est le dernier modèle léger et rapide de Microsoft AI, offrant des performances proches de dix fois celles des modèles leaders open source existants."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "LLM avancé, prenant en charge la génération de données synthétiques, la distillation de connaissances et le raisonnement, adapté aux chatbots, à la programmation et aux tâches spécifiques."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Permet des dialogues complexes, avec une excellente compréhension du contexte, des capacités de raisonnement et de génération de texte."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Modèle de pointe avancé, doté de compréhension linguistique, d'excellentes capacités de raisonnement et de génération de texte."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Modèle visuel-linguistique de pointe, spécialisé dans le raisonnement de haute qualité à partir d'images."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Modèle de langage de pointe de petite taille, doté de compréhension linguistique, d'excellentes capacités de raisonnement et de génération de texte."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Modèle de langage de pointe de petite taille, doté de compréhension linguistique, d'excellentes capacités de raisonnement et de génération de texte."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Modèle visuel-linguistique de pointe, spécialisé dans le raisonnement de haute qualité à partir d'images."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "LLM avancé, spécialisé dans le raisonnement, les mathématiques, le bon sens et les appels de fonction."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 est un modèle de langage proposé par Microsoft AI, qui excelle dans les domaines des dialogues complexes, du multilinguisme, du raisonnement et des assistants intelligents."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B est le modèle Wizard le plus avancé de Microsoft AI, montrant des performances extrêmement compétitives."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V est un nouveau modèle multimodal de nouvelle génération lancé par OpenBMB, offrant d'excellentes capacités de reconnaissance OCR et de compréhension multimodale, prenant en charge une large gamme d'applications."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B est le modèle de pointe de Mistral sur le marché."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B est un modèle à excellent rapport qualité-prix de Mistral."
+ },
"mistral": {
"description": "Mistral est le modèle 7B lancé par Mistral AI, adapté aux besoins variés de traitement du langage."
},
"mistral-large": {
"description": "Mixtral Large est le modèle phare de Mistral, combinant des capacités de génération de code, de mathématiques et de raisonnement, prenant en charge une fenêtre de contexte de 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) est un modèle de langage avancé (LLM) avec des capacités de raisonnement, de connaissance et de codage à la pointe de la technologie."
- },
"mistral-large-latest": {
"description": "Mistral Large est le modèle phare, excellent pour les tâches multilingues, le raisonnement complexe et la génération de code, idéal pour des applications haut de gamme."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 offre une capacité de calcul efficace et une compréhension du langage naturel, adapté à un large éventail d'applications."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B est un modèle compact mais performant, excellent pour le traitement par lot et les tâches simples, comme la classification et la génération de texte, avec de bonnes capacités d'inférence."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) est un super grand modèle de langage, prenant en charge des besoins de traitement extrêmement élevés."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B est un modèle de mélange d'experts pré-entraîné, utilisé pour des tâches textuelles générales."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B est un modèle d'experts clairsemés qui utilise de multiples paramètres pour améliorer la vitesse d'inférence, adapté au traitement des tâches multilingues et de génération de code."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct est un modèle standard de l'industrie, alliant optimisation de la vitesse et support de longs contextes."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K est un modèle doté d'une capacité de traitement de contexte ultra-long, adapté à la génération de textes très longs, répondant aux besoins de tâches de génération complexes, capable de traiter jusqu'à 128 000 tokens, idéal pour la recherche, l'académie et la génération de documents volumineux."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Le modèle visuel Kimi (y compris moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) est capable de comprendre le contenu des images, y compris le texte des images, les couleurs des images et les formes des objets."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K offre une capacité de traitement de contexte de longueur moyenne, capable de traiter 32 768 tokens, particulièrement adapté à la génération de divers documents longs et de dialogues complexes, utilisé dans la création de contenu, la génération de rapports et les systèmes de dialogue."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Le modèle visuel Kimi (y compris moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) est capable de comprendre le contenu des images, y compris le texte des images, les couleurs des images et les formes des objets."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K est conçu pour des tâches de génération de courts textes, avec des performances de traitement efficaces, capable de traiter 8 192 tokens, idéal pour des dialogues courts, des prises de notes et une génération rapide de contenu."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Le modèle visuel Kimi (y compris moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) est capable de comprendre le contenu des images, y compris le texte des images, les couleurs des images et les formes des objets."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto peut choisir le modèle approprié en fonction du nombre de tokens utilisés dans le contexte actuel."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B est une version améliorée de Nous Hermes 2, intégrant les derniers ensembles de données développés en interne."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B est un modèle de langage à grande échelle personnalisé par NVIDIA, conçu pour améliorer l'aide fournie par les réponses générées par LLM aux requêtes des utilisateurs. Ce modèle a excellé dans des tests de référence tels que Arena Hard, AlpacaEval 2 LC et GPT-4-Turbo MT-Bench, se classant premier dans les trois tests d'alignement automatique au 1er octobre 2024. Le modèle utilise RLHF (en particulier REINFORCE), Llama-3.1-Nemotron-70B-Reward et HelpSteer2-Preference pour l'entraînement sur la base du modèle Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Modèle de langage unique, offrant une précision et une efficacité inégalées."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct est un modèle de langage de grande taille personnalisé par NVIDIA, conçu pour améliorer l'utilité des réponses générées par LLM."
+ },
+ "o1": {
+ "description": "Axé sur le raisonnement avancé et la résolution de problèmes complexes, y compris les tâches mathématiques et scientifiques. Idéal pour les applications nécessitant une compréhension approfondie du contexte et des flux de travail d'agent."
+ },
"o1-mini": {
"description": "o1-mini est un modèle de raisonnement rapide et économique conçu pour les applications de programmation, de mathématiques et de sciences. Ce modèle dispose d'un contexte de 128K et d'une date limite de connaissance en octobre 2023."
},
"o1-preview": {
"description": "o1 est le nouveau modèle de raisonnement d'OpenAI, adapté aux tâches complexes nécessitant une vaste connaissance générale. Ce modèle dispose d'un contexte de 128K et d'une date limite de connaissance en octobre 2023."
},
+ "o3-mini": {
+ "description": "o3-mini est notre dernier modèle d'inférence compact, offrant une grande intelligence avec les mêmes objectifs de coût et de latence que o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba est un modèle de langage Mamba 2 axé sur la génération de code, offrant un soutien puissant pour des tâches avancées de codage et de raisonnement."
},
@@ -745,7 +1466,7 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B est un modèle d'expert épars, utilisant plusieurs paramètres pour améliorer la vitesse de raisonnement, adapté au traitement de tâches multilingues et de génération de code."
},
- "openai/gpt-4o-2024-08-06": {
+ "openai/gpt-4o": {
"description": "ChatGPT-4o est un modèle dynamique, mis à jour en temps réel pour rester à jour avec la dernière version. Il combine une compréhension et une génération de langage puissantes, adapté à des scénarios d'application à grande échelle, y compris le service client, l'éducation et le support technique."
},
"openai/gpt-4o-mini": {
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Le modèle Pixtral montre de puissantes capacités dans des tâches telles que la compréhension des graphiques et des images, le questionnement de documents, le raisonnement multimodal et le respect des instructions, capable d'ingérer des images à résolution naturelle et à rapport d'aspect, tout en traitant un nombre quelconque d'images dans une fenêtre de contexte longue allant jusqu'à 128K tokens."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large est un modèle multimodal open source avec 124 milliards de paramètres, basé sur Mistral Large 2. C'est notre deuxième modèle de la famille multimodale, démontrant des capacités de compréhension d'image à la pointe de la technologie."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K est doté d'une capacité de traitement de contexte très étendue, capable de gérer jusqu'à 128K d'informations contextuelles, particulièrement adapté pour l'analyse complète et le traitement des relations logiques à long terme dans des contenus longs, offrant une logique fluide et cohérente ainsi qu'un soutien varié pour les références dans des communications textuelles complexes."
+ },
+ "qvq-72b-preview": {
+ "description": "Le modèle QVQ est un modèle de recherche expérimental développé par l'équipe Qwen, axé sur l'amélioration des capacités de raisonnement visuel, en particulier dans le domaine du raisonnement mathématique."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Modèle de code Qwen universel."
+ },
"qwen-coder-turbo-latest": {
"description": "Le modèle de code Tongyi Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Le modèle de langage Tongyi Qwen pour les mathématiques, spécialement conçu pour résoudre des problèmes mathématiques."
},
+ "qwen-max": {
+ "description": "Modèle de langage à grande échelle de niveau milliard Qwen, prenant en charge des entrées dans différentes langues telles que le chinois et l'anglais, représentant actuellement le modèle API derrière la version 2.5 de Qwen."
+ },
"qwen-max-latest": {
"description": "Le modèle de langage à grande échelle Tongyi Qwen de niveau milliard, prenant en charge des entrées en chinois, en anglais et dans d'autres langues, actuellement le modèle API derrière la version produit Tongyi Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "La série de modèles Qwen-Omni prend en charge l'entrée de données multimodales, y compris vidéo, audio, images et texte, et produit des sorties audio et textuelles."
+ },
+ "qwen-plus": {
+ "description": "Version améliorée du modèle de langage à grande échelle Qwen, prenant en charge des entrées dans différentes langues telles que le chinois et l'anglais."
+ },
"qwen-plus-latest": {
"description": "La version améliorée du modèle de langage à grande échelle Tongyi Qwen, prenant en charge des entrées en chinois, en anglais et dans d'autres langues."
},
+ "qwen-turbo": {
+ "description": "Le modèle de langage à grande échelle Qwen, prenant en charge des entrées dans différentes langues telles que le chinois et l'anglais."
+ },
"qwen-turbo-latest": {
"description": "Le modèle de langage à grande échelle Tongyi Qwen, prenant en charge des entrées en chinois, en anglais et dans d'autres langues."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL prend en charge des modes d'interaction flexibles, y compris la capacité de poser des questions à plusieurs images, des dialogues multi-tours, et plus encore."
},
- "qwen-vl-max": {
- "description": "Qwen est un modèle de langage visuel à grande échelle. Par rapport à la version améliorée, elle améliore encore la capacité de raisonnement visuel et de suivi des instructions, offrant un niveau de perception et de cognition visuelle plus élevé."
+ "qwen-vl-max-latest": {
+ "description": "Modèle de langage visuel à très grande échelle Tongyi Qianwen. Par rapport à la version améliorée, il améliore encore les capacités de raisonnement visuel et de suivi des instructions, offrant un niveau de perception visuelle et de cognition plus élevé."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Le modèle OCR Qwen est un modèle spécialisé dans l'extraction de texte, se concentrant sur la capacité d'extraction de texte à partir d'images de documents, tableaux, questions d'examen, écriture manuscrite, etc. Il peut reconnaître plusieurs langues, actuellement supportées : chinois, anglais, français, japonais, coréen, allemand, russe, italien, vietnamien, arabe."
},
- "qwen-vl-plus": {
- "description": "Qwen est une version améliorée du modèle de langage visuel à grande échelle. Elle améliore considérablement la capacité de reconnaissance des détails et de reconnaissance de texte, prenant en charge des images avec une résolution de plus d'un million de pixels et des spécifications de rapport d'aspect arbitraire."
+ "qwen-vl-plus-latest": {
+ "description": "Version améliorée du modèle de langage visuel à grande échelle Tongyi Qianwen. Amélioration significative des capacités de reconnaissance des détails et de reconnaissance de texte, prenant en charge des résolutions d'image de plus d'un million de pixels et des rapports d'aspect de n'importe quelle taille."
},
"qwen-vl-v1": {
"description": "Initialisé avec le modèle de langage Qwen-7B, ajoutant un modèle d'image, un modèle pré-entraîné avec une résolution d'entrée d'image de 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 est la toute nouvelle série de modèles de langage de grande taille Qwen. Qwen2 7B est un modèle basé sur le transformateur, qui excelle dans la compréhension du langage, les capacités multilingues, la programmation, les mathématiques et le raisonnement."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 est une toute nouvelle série de modèles de langage de grande taille, offrant des capacités de compréhension et de génération plus puissantes."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL est la dernière version itérée du modèle Qwen-VL, atteignant des performances de pointe dans les benchmarks de compréhension visuelle, y compris MathVista, DocVQA, RealWorldQA et MTVQA. Qwen2-VL peut comprendre des vidéos de plus de 20 minutes pour des questions-réponses, des dialogues et de la création de contenu de haute qualité basés sur la vidéo. Il possède également des capacités de raisonnement et de décision complexes, pouvant être intégré à des appareils mobiles, des robots, etc., pour des opérations automatiques basées sur l'environnement visuel et des instructions textuelles. En plus de l'anglais et du chinois, Qwen2-VL prend désormais en charge la compréhension du texte dans différentes langues dans les images, y compris la plupart des langues européennes, le japonais, le coréen, l'arabe et le vietnamien."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct est l'un des derniers modèles de langage de grande taille publiés par Alibaba Cloud. Ce modèle de 72B présente des capacités significativement améliorées dans des domaines tels que le codage et les mathématiques. Le modèle offre également un support multilingue, couvrant plus de 29 langues, y compris le chinois et l'anglais. Il a montré des améliorations significatives dans le suivi des instructions, la compréhension des données structurées et la génération de sorties structurées (en particulier JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct est l'un des derniers modèles de langage de grande taille publiés par Alibaba Cloud. Ce modèle de 32B présente des capacités significativement améliorées dans des domaines tels que le codage et les mathématiques. Le modèle offre un support multilingue, couvrant plus de 29 langues, y compris le chinois et l'anglais. Il a montré des améliorations significatives dans le suivi des instructions, la compréhension des données structurées et la génération de sorties structurées (en particulier JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM orienté vers le chinois et l'anglais, ciblant des domaines tels que la langue, la programmation, les mathématiques et le raisonnement."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "LLM avancé, prenant en charge la génération de code, le raisonnement et la correction, couvrant les langages de programmation courants."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Modèle de code puissant de taille moyenne, prenant en charge une longueur de contexte de 32K, spécialisé dans la programmation multilingue."
+ },
"qwen2": {
"description": "Qwen2 est le nouveau modèle de langage à grande échelle d'Alibaba, offrant d'excellentes performances pour des besoins d'application diversifiés."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 est le nouveau modèle de langage à grande échelle de Alibaba, offrant d'excellentes performances pour répondre à des besoins d'application diversifiés."
+ },
"qwen2.5-14b-instruct": {
"description": "Le modèle de 14B de Tongyi Qwen 2.5, open source."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Le modèle de 72B de Qwen2.5 est ouvert au public."
+ },
"qwen2.5-32b-instruct": {
"description": "Le modèle de 32B de Tongyi Qwen 2.5, open source."
},
@@ -824,7 +1599,10 @@
"description": "Le modèle de 7B de Tongyi Qwen 2.5, open source."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "Version open source du modèle de code Tongyi Qwen."
+ "description": "Version open-source du modèle de code Qwen."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Version open source du modèle de code Qwen universel."
},
"qwen2.5-coder-7b-instruct": {
"description": "Version open source du modèle de code Tongyi Qwen."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Le modèle Qwen-Math possède de puissantes capacités de résolution de problèmes mathématiques."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Amélioration globale des capacités de suivi des instructions, mathématiques, résolution de problèmes et code, amélioration des capacités de reconnaissance, support de divers formats pour un positionnement précis des éléments visuels, compréhension de fichiers vidéo longs (jusqu'à 10 minutes) et localisation d'événements en temps réel, capable de comprendre l'ordre temporel et la vitesse, supportant le contrôle d'agents OS ou Mobile basé sur des capacités d'analyse et de localisation, avec une forte capacité d'extraction d'informations clés et de sortie au format Json. Cette version est la version 72B, la plus puissante de cette série."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Amélioration globale des capacités de suivi des instructions, mathématiques, résolution de problèmes et code, amélioration des capacités de reconnaissance, support de divers formats pour un positionnement précis des éléments visuels, compréhension de fichiers vidéo longs (jusqu'à 10 minutes) et localisation d'événements en temps réel, capable de comprendre l'ordre temporel et la vitesse, supportant le contrôle d'agents OS ou Mobile basé sur des capacités d'analyse et de localisation, avec une forte capacité d'extraction d'informations clés et de sortie au format Json. Cette version est la version 72B, la plus puissante de cette série."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 est le nouveau modèle de langage à grande échelle de Alibaba, offrant d'excellentes performances pour répondre à des besoins d'application diversifiés."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 est le nouveau modèle de langage à grande échelle de Alibaba, offrant d'excellentes performances pour répondre à des besoins d'application diversifiés."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 est le nouveau modèle de langage à grande échelle de Alibaba, offrant d'excellentes performances pour répondre à des besoins d'application diversifiés."
+ },
"qwen2:0.5b": {
"description": "Qwen2 est le nouveau modèle de langage à grande échelle d'Alibaba, offrant d'excellentes performances pour des besoins d'application diversifiés."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 est le nouveau modèle de langage à grande échelle d'Alibaba, offrant d'excellentes performances pour des besoins d'application diversifiés."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini est un LLM compact, surpassant GPT-3.5, avec de puissantes capacités multilingues, supportant l'anglais et le coréen, offrant une solution efficace et compacte."
+ "qwq": {
+ "description": "QwQ est un modèle de recherche expérimental, axé sur l'amélioration des capacités de raisonnement de l'IA."
+ },
+ "qwq-32b": {
+ "description": "Le modèle d'inférence QwQ, entraîné sur le modèle Qwen2.5-32B, a considérablement amélioré ses capacités d'inférence grâce à l'apprentissage par renforcement. Les indicateurs clés du modèle, tels que le code mathématique (AIME 24/25, LiveCodeBench) ainsi que certains indicateurs généraux (IFEval, LiveBench, etc.), atteignent le niveau de la version complète de DeepSeek-R1, avec des performances nettement supérieures à celles de DeepSeek-R1-Distill-Qwen-32B, également basé sur Qwen2.5-32B."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) étend les capacités de Solar Mini, se concentrant sur le japonais tout en maintenant une efficacité et des performances exceptionnelles en anglais et en coréen."
+ "qwq-32b-preview": {
+ "description": "Le modèle QwQ est un modèle de recherche expérimental développé par l'équipe Qwen, axé sur l'amélioration des capacités de raisonnement de l'IA."
+ },
+ "qwq-plus-latest": {
+ "description": "Le modèle d'inférence QwQ, entraîné sur le modèle Qwen2.5, a considérablement amélioré ses capacités d'inférence grâce à l'apprentissage par renforcement. Les indicateurs clés du modèle, tels que le code mathématique (AIME 24/25, LiveCodeBench) ainsi que certains indicateurs généraux (IFEval, LiveBench, etc.), atteignent le niveau de la version complète de DeepSeek-R1."
+ },
+ "r1-1776": {
+ "description": "R1-1776 est une version du modèle DeepSeek R1, après un entraînement supplémentaire, fournissant des informations factuelles non filtrées et impartiales."
+ },
+ "solar-mini": {
+ "description": "Solar Mini est un LLM compact, offrant des performances supérieures à celles de GPT-3.5, avec de puissantes capacités multilingues, prenant en charge l'anglais et le coréen, et fournissant une solution efficace et compacte."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) étend les capacités de Solar Mini, se concentrant sur le japonais tout en maintenant une efficacité et des performances exceptionnelles dans l'utilisation de l'anglais et du coréen."
},
"solar-pro": {
"description": "Solar Pro est un LLM hautement intelligent lancé par Upstage, axé sur la capacité de suivi des instructions sur un seul GPU, avec un score IFEval supérieur à 80. Actuellement, il supporte l'anglais, et la version officielle est prévue pour novembre 2024, avec une extension du support linguistique et de la longueur du contexte."
},
+ "sonar": {
+ "description": "Produit de recherche léger basé sur le contexte de recherche, plus rapide et moins cher que Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research effectue des recherches approfondies de niveau expert et les synthétise en rapports accessibles et exploitables."
+ },
+ "sonar-pro": {
+ "description": "Produit de recherche avancé prenant en charge le contexte de recherche, avec des requêtes avancées et un suivi."
+ },
+ "sonar-reasoning": {
+ "description": "Nouveau produit API soutenu par le modèle de raisonnement DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Nouveau produit API soutenu par le modèle de raisonnement DeepSeek."
+ },
"step-1-128k": {
"description": "Équilibre entre performance et coût, adapté à des scénarios généraux."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Modèle à haute vitesse, adapté aux dialogues en temps réel."
},
+ "step-1.5v-mini": {
+ "description": "Ce modèle possède de puissantes capacités de compréhension vidéo."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Ce modèle possède de puissantes capacités de compréhension d'image, surpassant le 1o dans les domaines mathématiques et de codage. Le modèle est plus petit que le 1o et offre une vitesse de sortie plus rapide."
+ },
+ "step-1o-vision-32k": {
+ "description": "Ce modèle possède de puissantes capacités de compréhension d'image. Par rapport à la série de modèles step-1v, il offre des performances visuelles supérieures."
+ },
"step-1v-32k": {
"description": "Prend en charge les entrées visuelles, améliorant l'expérience d'interaction multimodale."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Prend en charge des interactions contextuelles à grande échelle, adapté aux scénarios de dialogue complexes."
},
+ "step-2-mini": {
+ "description": "Un modèle de grande taille ultra-rapide basé sur la nouvelle architecture d'attention auto-développée MFA, atteignant des résultats similaires à ceux de step1 à un coût très bas, tout en maintenant un débit plus élevé et un temps de réponse plus rapide. Capable de traiter des tâches générales, avec des compétences particulières en matière de codage."
+ },
"taichu_llm": {
"description": "Le modèle de langage Taichu Zidong possède une forte capacité de compréhension linguistique ainsi que des compétences en création de texte, questions-réponses, programmation, calcul mathématique, raisonnement logique, analyse des sentiments, et résumé de texte. Il combine de manière innovante le pré-entraînement sur de grandes données avec des connaissances riches provenant de multiples sources, en perfectionnant continuellement la technologie algorithmique et en intégrant de nouvelles connaissances sur le vocabulaire, la structure, la grammaire et le sens à partir de vastes ensembles de données textuelles, offrant aux utilisateurs des informations et des services plus pratiques ainsi qu'une expérience plus intelligente."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V intègre des capacités de compréhension d'image, de transfert de connaissances et d'attribution logique, se distinguant dans le domaine des questions-réponses textuelles et visuelles."
+ "taichu_vl": {
+ "description": "Intègre des capacités de compréhension d'image, de transfert de connaissances et de raisonnement logique, se distinguant dans le domaine des questions-réponses textuelles et visuelles."
+ },
+ "text-embedding-3-large": {
+ "description": "Le modèle de vectorisation le plus puissant, adapté aux tâches en anglais et non-anglais."
+ },
+ "text-embedding-3-small": {
+ "description": "Un modèle d'Embedding de nouvelle génération, efficace et économique, adapté à la recherche de connaissances, aux applications RAG, etc."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Version open source de la dernière génération de modèles pré-entraînés de la série GLM-4 publiée par Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) offre une capacité de calcul améliorée grâce à des stratégies et une architecture de modèle efficaces."
},
+ "tts-1": {
+ "description": "Le dernier modèle de synthèse vocale, optimisé pour la vitesse dans des scénarios en temps réel."
+ },
+ "tts-1-hd": {
+ "description": "Le dernier modèle de synthèse vocale, optimisé pour la qualité."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) est adapté aux tâches d'instructions détaillées, offrant d'excellentes capacités de traitement du langage."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet élève les normes de l'industrie, surpassant les modèles concurrents et Claude 3 Opus, avec d'excellentes performances dans une large gamme d'évaluations, tout en offrant la vitesse et le coût de nos modèles de niveau intermédiaire."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet est le modèle de prochaine génération le plus rapide d'Anthropic. Par rapport à Claude 3 Haiku, Claude 3.7 Sonnet a amélioré ses compétences dans divers domaines et a surpassé le plus grand modèle de la génération précédente, Claude 3 Opus, dans de nombreux tests de référence intellectuels."
+ },
+ "whisper-1": {
+ "description": "Modèle de reconnaissance vocale général, prenant en charge la reconnaissance vocale multilingue, la traduction vocale et la reconnaissance de langue."
+ },
"wizardlm2": {
"description": "WizardLM 2 est un modèle de langage proposé par Microsoft AI, particulièrement performant dans les domaines des dialogues complexes, du multilinguisme, du raisonnement et des assistants intelligents."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Un excellent rapport qualité-prix avec des performances exceptionnelles. Optimisé pour un équilibre de haute précision en fonction des performances, de la vitesse de raisonnement et des coûts."
},
+ "yi-lightning": {
+ "description": "Modèle haute performance dernier cri, garantissant une sortie de haute qualité tout en améliorant considérablement la vitesse d'inférence."
+ },
+ "yi-lightning-lite": {
+ "description": "Version allégée, l'utilisation de yi-lightning est recommandée."
+ },
"yi-medium": {
"description": "Modèle de taille moyenne, optimisé et ajusté, offrant un équilibre de capacités et un bon rapport qualité-prix. Optimisation approfondie des capacités de suivi des instructions."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Modèle pour des tâches visuelles complexes, offrant des capacités de compréhension et d'analyse d'images de haute performance."
+ },
+ "yi-vision-v2": {
+ "description": "Modèle pour des tâches visuelles complexes, offrant des capacités de compréhension et d'analyse de haute performance basées sur plusieurs images."
}
}
diff --git a/DigitalHumanWeb/locales/fr-FR/plugin.json b/DigitalHumanWeb/locales/fr-FR/plugin.json
index 9e52584..b8e59e4 100644
--- a/DigitalHumanWeb/locales/fr-FR/plugin.json
+++ b/DigitalHumanWeb/locales/fr-FR/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Échec de la mise à jour du plugin {{name}}",
"urlError": "Ce lien ne renvoie pas de contenu au format JSON. Veuillez vous assurer qu'il s'agit d'un lien valide."
},
+ "inspector": {
+ "args": "Voir la liste des paramètres",
+ "pluginRender": "Voir l'interface du plugin"
+ },
"list": {
"item": {
"deprecated.title": "Obsolète",
@@ -130,6 +134,34 @@
"plugin": "Exécution du plugin en cours..."
},
"pluginList": "Liste des plugins",
+ "search": {
+ "config": {
+ "addKey": "Ajouter une clé",
+ "close": "Supprimer",
+ "confirm": "Configuration terminée, veuillez réessayer"
+ },
+ "crawPages": {
+ "crawling": "Identification des liens en cours",
+ "detail": {
+ "preview": "Aperçu",
+ "raw": "Texte brut",
+ "tooLong": "Le contenu du texte est trop long, le contexte de la conversation ne conserve que les {{characters}} premiers caractères, la partie excédentaire n'est pas prise en compte dans le contexte de la conversation"
+ },
+ "meta": {
+ "crawler": "Mode de collecte",
+ "words": "Nombre de caractères"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Veuillez entrer",
+ "description": "Veuillez entrer l'URL de SearchXNG pour commencer la recherche en ligne",
+ "keyPlaceholder": "Veuillez entrer la clé",
+ "title": "Configurer le moteur de recherche SearchXNG",
+ "unconfiguredDesc": "Veuillez contacter l'administrateur pour compléter la configuration du moteur de recherche SearchXNG afin de commencer la recherche en ligne",
+ "unconfiguredTitle": "Moteur de recherche SearchXNG non configuré"
+ },
+ "title": "Recherche en ligne"
+ },
"setting": "Paramètres des plugins",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/fr-FR/portal.json b/DigitalHumanWeb/locales/fr-FR/portal.json
index 9c92513..94c4f6a 100644
--- a/DigitalHumanWeb/locales/fr-FR/portal.json
+++ b/DigitalHumanWeb/locales/fr-FR/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Plugins",
- "actions": {
- "genAiMessage": "Créer un message d'assistant",
- "summary": "Résumé",
- "summaryTooltip": "Résumé du contenu actuel"
- },
"artifacts": {
"display": {
"code": "Code",
diff --git a/DigitalHumanWeb/locales/fr-FR/providers.json b/DigitalHumanWeb/locales/fr-FR/providers.json
index 60e26b6..e8e4fbe 100644
--- a/DigitalHumanWeb/locales/fr-FR/providers.json
+++ b/DigitalHumanWeb/locales/fr-FR/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs construit des modèles de base et des systèmes d'intelligence artificielle pour les entreprises, accélérant l'application de l'intelligence artificielle générative en production."
+ },
"ai360": {
"description": "360 AI est une plateforme de modèles et de services IA lancée par la société 360, offrant divers modèles avancés de traitement du langage naturel, y compris 360GPT2 Pro, 360GPT Pro, 360GPT Turbo et 360GPT Turbo Responsibility 8K. Ces modèles combinent de grands paramètres et des capacités multimodales, largement utilisés dans la génération de texte, la compréhension sémantique, les systèmes de dialogue et la génération de code. Grâce à une stratégie de tarification flexible, 360 AI répond à des besoins variés des utilisateurs, soutenant l'intégration des développeurs et favorisant l'innovation et le développement des applications intelligentes."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure propose une variété de modèles IA avancés, y compris GPT-3.5 et la dernière série GPT-4, prenant en charge divers types de données et tâches complexes, tout en s'engageant à fournir des solutions IA sécurisées, fiables et durables."
},
+ "azureai": {
+ "description": "Azure propose une variété de modèles d'IA avancés, y compris GPT-3.5 et la dernière série GPT-4, prenant en charge divers types de données et des tâches complexes, s'engageant à fournir des solutions d'IA sécurisées, fiables et durables."
+ },
"baichuan": {
"description": "Baichuan Intelligent est une entreprise spécialisée dans le développement de grands modèles d'intelligence artificielle, dont les modèles excellent dans les tâches en chinois telles que l'encyclopédie de connaissances, le traitement de longs textes et la création, surpassant les modèles dominants étrangers. Baichuan Intelligent possède également des capacités multimodales de premier plan, se distinguant dans plusieurs évaluations autorisées. Ses modèles incluent Baichuan 4, Baichuan 3 Turbo et Baichuan 3 Turbo 128k, chacun optimisé pour différents scénarios d'application, offrant des solutions à bon rapport qualité-prix."
},
"bedrock": {
"description": "Bedrock est un service proposé par Amazon AWS, axé sur la fourniture de modèles linguistiques et visuels avancés pour les entreprises. Sa famille de modèles comprend la série Claude d'Anthropic, la série Llama 3.1 de Meta, etc., offrant une variété d'options allant des modèles légers aux modèles haute performance, prenant en charge des tâches telles que la génération de texte, les dialogues et le traitement d'images, adaptées aux applications d'entreprise de différentes tailles et besoins."
},
+ "cloudflare": {
+ "description": "Exécutez des modèles d'apprentissage automatique alimentés par GPU sans serveur sur le réseau mondial de Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek est une entreprise spécialisée dans la recherche et l'application des technologies d'intelligence artificielle, dont le dernier modèle, DeepSeek-V2.5, combine des capacités de dialogue général et de traitement de code, réalisant des améliorations significatives dans l'alignement des préférences humaines, les tâches d'écriture et le suivi des instructions."
},
+ "doubao": {
+ "description": "Un grand modèle développé en interne par ByteDance. Validé par la pratique dans plus de 50 scénarios d'affaires au sein de ByteDance, avec un volume d'utilisation quotidien de plusieurs trillions de tokens, il offre diverses capacités multimodales, créant ainsi une expérience commerciale riche grâce à des performances de modèle de haute qualité."
+ },
"fireworksai": {
"description": "Fireworks AI est un fournisseur de services de modèles linguistiques avancés, axé sur les appels de fonction et le traitement multimodal. Son dernier modèle, Firefunction V2, basé sur Llama-3, est optimisé pour les appels de fonction, les dialogues et le suivi des instructions. Le modèle de langage visuel FireLLaVA-13B prend en charge les entrées mixtes d'images et de texte. D'autres modèles notables incluent la série Llama et la série Mixtral, offrant un support efficace pour le suivi et la génération d'instructions multilingues."
},
+ "giteeai": {
+ "description": "L'API serverless de gitee ai fournit aux développeurs d'IA un service d'api d'inférence grand modèle prêt à l'emploi."
+ },
"github": {
"description": "Avec les modèles GitHub, les développeurs peuvent devenir des ingénieurs en IA et créer avec les modèles d'IA les plus avancés de l'industrie."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Le moteur d'inférence LPU de Groq a excellé dans les derniers tests de référence des grands modèles de langage (LLM), redéfinissant les normes des solutions IA grâce à sa vitesse et son efficacité impressionnantes. Groq représente une vitesse d'inférence instantanée, montrant de bonnes performances dans les déploiements basés sur le cloud."
},
+ "higress": {
+ "description": "Higress est une passerelle API cloud-native, née au sein d'Alibaba pour résoudre les problèmes de rechargement de Tengine affectant les connexions persistantes, ainsi que le manque de capacités d'équilibrage de charge pour gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "L'API d'inférence HuggingFace offre un moyen rapide et gratuit d'explorer des milliers de modèles adaptés à diverses tâches. Que vous soyez en train de prototyper une nouvelle application ou d'expérimenter les capacités de l'apprentissage automatique, cette API vous permet d'accéder instantanément à des modèles performants dans de nombreux domaines."
+ },
+ "hunyuan": {
+ "description": "Un modèle de langage développé par Tencent, doté d'une puissante capacité de création en chinois, d'une capacité de raisonnement logique dans des contextes complexes, ainsi que d'une capacité fiable d'exécution des tâches."
+ },
+ "internlm": {
+ "description": "Organisation open source dédiée à la recherche et au développement d'outils pour les grands modèles. Fournit à tous les développeurs d'IA une plateforme open source efficace et facile à utiliser, rendant les technologies de pointe en matière de grands modèles et d'algorithmes accessibles."
+ },
+ "jina": {
+ "description": "Jina AI, fondée en 2020, est une entreprise leader dans le domaine de l'IA de recherche. Notre plateforme de recherche de base comprend des modèles vectoriels, des réarrangeurs et de petits modèles de langage, aidant les entreprises à construire des applications de recherche génératives et multimodales fiables et de haute qualité."
+ },
+ "lmstudio": {
+ "description": "LM Studio est une application de bureau pour développer et expérimenter des LLM sur votre ordinateur."
+ },
"minimax": {
"description": "MiniMax est une entreprise de technologie d'intelligence artificielle générale fondée en 2021, dédiée à la co-création d'intelligence avec les utilisateurs. MiniMax a développé de manière autonome différents modèles de grande taille, y compris un modèle de texte MoE à un trillion de paramètres, un modèle vocal et un modèle d'image. Elle a également lancé des applications telles que Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI est une plateforme offrant des services API pour divers grands modèles de langage et la génération d'images IA, flexible, fiable et rentable. Elle prend en charge les derniers modèles open source tels que Llama3, Mistral, et fournit des solutions API complètes, conviviales et évolutives pour le développement d'applications IA, adaptées à la croissance rapide des startups IA."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ fournit des conteneurs pour l'inférence de microservices accélérés par GPU auto-hébergés, prenant en charge le déploiement de modèles d'IA pré-entraînés et personnalisés dans le cloud, les centres de données, les PC personnels RTX™ AI et les stations de travail."
+ },
"ollama": {
"description": "Les modèles proposés par Ollama couvrent largement des domaines tels que la génération de code, les calculs mathématiques, le traitement multilingue et les interactions conversationnelles, répondant à des besoins diversifiés pour le déploiement en entreprise et la localisation."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity est un fournisseur de modèles de génération de dialogue de premier plan, offrant divers modèles avancés Llama 3.1, prenant en charge les applications en ligne et hors ligne, particulièrement adaptés aux tâches complexes de traitement du langage naturel."
},
+ "ppio": {
+ "description": "PPIO Paiouyun offre des services API de modèles open source stables et rentables, prenant en charge toute la gamme DeepSeek, Llama, Qwen et d'autres grands modèles de pointe dans l'industrie."
+ },
"qwen": {
"description": "Tongyi Qianwen est un modèle de langage à grande échelle développé de manière autonome par Alibaba Cloud, doté de puissantes capacités de compréhension et de génération du langage naturel. Il peut répondre à diverses questions, créer du contenu écrit, exprimer des opinions, rédiger du code, etc., jouant un rôle dans plusieurs domaines."
},
+ "sambanova": {
+ "description": "SambaNova Cloud permet aux développeurs d'utiliser facilement les meilleurs modèles open source et de bénéficier de la vitesse d'inférence la plus rapide."
+ },
+ "sensenova": {
+ "description": "SenseNova, soutenue par la puissante infrastructure de SenseTime, offre des services de modèles de grande taille complets, efficaces et faciles à utiliser."
+ },
"siliconcloud": {
"description": "SiliconFlow s'engage à accélérer l'AGI pour le bénéfice de l'humanité, en améliorant l'efficacité de l'IA à grande échelle grâce à une pile GenAI facile à utiliser et à faible coût."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "L'Institut d'automatisation de l'Académie chinoise des sciences et l'Institut de recherche en intelligence artificielle de Wuhan ont lancé une nouvelle génération de grands modèles multimodaux, prenant en charge des tâches de questions-réponses complètes, de création de texte, de génération d'images, de compréhension 3D, d'analyse de signaux, avec des capacités cognitives, de compréhension et de création renforcées, offrant une toute nouvelle expérience interactive."
},
+ "tencentcloud": {
+ "description": "La capacité atomique du moteur de connaissance (LLM Knowledge Engine Atomic Power) est une capacité de question-réponse complète développée sur la base du moteur de connaissance, destinée aux entreprises et aux développeurs. Elle offre la possibilité de créer et de développer des applications de modèles de manière flexible. Vous pouvez assembler votre service de modèle exclusif en utilisant plusieurs capacités atomiques, en appelant des services tels que l'analyse de documents, la séparation, l'embedding, la réécriture multi-tours, etc., pour personnaliser les affaires AI spécifiques à votre entreprise."
+ },
"togetherai": {
"description": "Together AI s'engage à réaliser des performances de pointe grâce à des modèles IA innovants, offrant une large capacité de personnalisation, y compris un support d'évolutivité rapide et un processus de déploiement intuitif, répondant à divers besoins d'entreprise."
},
"upstage": {
"description": "Upstage se concentre sur le développement de modèles IA pour divers besoins commerciaux, y compris Solar LLM et Document AI, visant à réaliser une intelligence générale artificielle (AGI) pour le travail. Créez des agents de dialogue simples via l'API Chat, et prenez en charge les appels de fonction, la traduction, l'intégration et les applications spécifiques à un domaine."
},
+ "vertexai": {
+ "description": "La série Gemini de Google est son modèle d'IA le plus avancé et polyvalent, développé par Google DeepMind, conçu pour être multimodal, prenant en charge la compréhension et le traitement sans couture de texte, de code, d'images, d'audio et de vidéo. Adapté à divers environnements, des centres de données aux appareils mobiles, il améliore considérablement l'efficacité et l'applicabilité des modèles d'IA."
+ },
+ "vllm": {
+ "description": "vLLM est une bibliothèque rapide et facile à utiliser pour l'inférence et les services LLM."
+ },
+ "volcengine": {
+ "description": "La plateforme de développement des services de grands modèles lancée par ByteDance, offrant des services d'appel de modèles riches en fonctionnalités, sécurisés et compétitifs en termes de prix. Elle propose également des fonctionnalités de bout en bout telles que les données de modèle, le réglage fin, l'inférence et l'évaluation, garantissant ainsi le succès de votre développement d'applications AI."
+ },
+ "wenxin": {
+ "description": "Plateforme de développement et de services d'applications AI natives et de modèles de grande envergure, tout-en-un pour les entreprises, offrant la chaîne d'outils la plus complète et facile à utiliser pour le développement de modèles d'intelligence artificielle générative et le développement d'applications."
+ },
+ "xai": {
+ "description": "xAI est une entreprise dédiée à la construction d'intelligences artificielles pour accélérer les découvertes scientifiques humaines. Notre mission est de promouvoir notre compréhension commune de l'univers."
+ },
"zeroone": {
"description": "01.AI se concentre sur les technologies d'intelligence artificielle de l'ère IA 2.0, promouvant activement l'innovation et l'application de \"l'homme + l'intelligence artificielle\", utilisant des modèles puissants et des technologies IA avancées pour améliorer la productivité humaine et réaliser l'autonomisation technologique."
},
diff --git a/DigitalHumanWeb/locales/fr-FR/setting.json b/DigitalHumanWeb/locales/fr-FR/setting.json
index 3d73f22..a988ba7 100644
--- a/DigitalHumanWeb/locales/fr-FR/setting.json
+++ b/DigitalHumanWeb/locales/fr-FR/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Configuration du modèle personnalisé",
"tokens": {
- "title": "Nombre maximal de jetons",
- "unlimited": "illimité"
+ "title": "Nombre maximal de jetons"
},
"vision": {
"extra": "Cette configuration n'activera que la configuration de téléchargement d'images dans l'application. La prise en charge de la reconnaissance dépend entièrement du modèle lui-même, veuillez tester la disponibilité des capacités de reconnaissance visuelle de ce modèle.",
@@ -98,6 +97,7 @@
"title": "Utiliser le mode de requête client"
},
"fetcher": {
+ "clear": "Effacer le modèle récupéré",
"fetch": "Obtenir la liste des modèles",
"fetching": "Récupération de la liste des modèles en cours...",
"latestTime": "Dernière mise à jour : {{time}}",
@@ -175,8 +175,8 @@
"desc": "Activer la création automatique de sujets pendant la conversation, uniquement valable pour les sujets temporaires",
"title": "Activer la création automatique de sujets"
},
- "enableCompressThreshold": {
- "title": "Activer le seuil de compression de la longueur des messages"
+ "enableCompressHistory": {
+ "title": "Activer le résumé automatique des messages historiques"
},
"enableHistoryCount": {
"alias": "Illimité",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Activer la limite de tokens par réponse"
},
+ "enableReasoningEffort": {
+ "title": "Activer l'ajustement de l'intensité de raisonnement"
+ },
"frequencyPenalty": {
- "desc": "Plus la valeur est élevée, plus il est probable de réduire les mots répétés",
- "title": "Pénalité de fréquence"
+ "desc": "Plus la valeur est élevée, plus le vocabulaire est riche et varié ; plus la valeur est basse, plus le vocabulaire est simple et direct",
+ "title": "Richesse du vocabulaire"
},
"maxTokens": {
"desc": "Nombre maximal de tokens utilisés par interaction",
@@ -212,19 +215,31 @@
"desc": "Modèle {{provider}}",
"title": "Modèle"
},
+ "params": {
+ "title": "Paramètres avancés"
+ },
"presencePenalty": {
- "desc": "Plus la valeur est élevée, plus il est probable d'explorer de nouveaux sujets",
- "title": "Pénalité de présence"
+ "desc": "Plus la valeur est élevée, plus il y a tendance à utiliser des expressions différentes, évitant la répétition des concepts ; plus la valeur est basse, plus il y a tendance à utiliser des concepts ou des narrations répétitifs, rendant l'expression plus cohérente",
+ "title": "Diversité de l'expression"
+ },
+ "reasoningEffort": {
+ "desc": "Plus la valeur est élevée, plus la capacité de raisonnement est forte, mais cela peut augmenter le temps de réponse et la consommation de jetons",
+ "options": {
+ "high": "Élevé",
+ "low": "Bas",
+ "medium": "Moyen"
+ },
+ "title": "Intensité de raisonnement"
},
"temperature": {
- "desc": "Plus la valeur est élevée, plus la réponse est aléatoire",
- "title": "Aléatoire",
- "titleWithValue": "Aléatoire {{value}}"
+ "desc": "Plus la valeur est élevée, plus les réponses sont créatives et imaginatives ; plus la valeur est basse, plus les réponses sont rigoureuses",
+ "title": "Niveau de créativité",
+ "warning": "Une valeur de créativité trop élevée peut entraîner des sorties illisibles"
},
"title": "Paramètres du modèle",
"topP": {
- "desc": "Similaire à l'aléatoire, mais ne doit pas être modifié en même temps que l'aléatoire",
- "title": "Échantillonnage topP"
+ "desc": "Considère combien de possibilités, plus la valeur est élevée, plus il accepte de réponses possibles ; plus la valeur est basse, plus il a tendance à choisir la réponse la plus probable. Il n'est pas recommandé de modifier cela en même temps que le niveau de créativité",
+ "title": "Ouverture d'esprit"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Modèle spécifié pour générer le nom, la description, l'avatar et les balises de l'assistant",
"title": "Génération automatique des informations de l'assistant"
},
+ "customPrompt": {
+ "addPrompt": "Ajouter un prompt personnalisé",
+ "desc": "Une fois rempli, l'assistant système utilisera le prompt personnalisé lors de la génération de contenu",
+ "placeholder": "Veuillez entrer le mot-clé personnalisé",
+ "title": "Mot-clé personnalisé"
+ },
+ "historyCompress": {
+ "label": "Modèle d'historique de conversation",
+ "modelDesc": "Modèle utilisé pour compresser l'historique des conversations",
+ "title": "Résumé automatique de l'historique des conversations"
+ },
"queryRewrite": {
"label": "Modèle de reformulation des questions",
"modelDesc": "Modèle utilisé pour optimiser les questions des utilisateurs",
- "title": "Base de connaissances"
+ "title": "Réécriture de la question de la base de connaissances"
+ },
+ "thread": {
+ "label": "Modèle de nomination de sous-thème",
+ "modelDesc": "Modèle utilisé pour le renommage automatique des sous-thèmes",
+ "title": "Nommer automatiquement les sous-thèmes"
},
"title": "Agent système",
"topic": {
@@ -395,6 +426,7 @@
"common": "Paramètres généraux",
"experiment": "Expérience",
"llm": "Modèle de langue",
+ "provider": "Fournisseur de services d'IA",
"sync": "Synchronisation cloud",
"system-agent": "Agent système",
"tts": "Service vocal"
diff --git a/DigitalHumanWeb/locales/fr-FR/thread.json b/DigitalHumanWeb/locales/fr-FR/thread.json
new file mode 100644
index 0000000..49e16d9
--- /dev/null
+++ b/DigitalHumanWeb/locales/fr-FR/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Vous allez supprimer ce sous-sujet. Une fois supprimé, il ne pourra pas être récupéré. Veuillez agir avec prudence."
+ },
+ "newPortalThread": {
+ "includeContext": "Inclure le contexte du sujet",
+ "title": "Ouvrir un nouveau sous-sujet"
+ },
+ "notSupportMultiModals": "Les sous-sujets ne prennent pas encore en charge le téléchargement de fichiers/images. Si besoin, n'hésitez pas à laisser un message : <1>💬 Forum de discussion1>"
+}
diff --git a/DigitalHumanWeb/locales/fr-FR/tool.json b/DigitalHumanWeb/locales/fr-FR/tool.json
index ed373d0..3aa6bf3 100644
--- a/DigitalHumanWeb/locales/fr-FR/tool.json
+++ b/DigitalHumanWeb/locales/fr-FR/tool.json
@@ -6,5 +6,23 @@
"generating": "En cours de génération...",
"images": "Images :",
"prompt": "Mot de rappel"
+ },
+ "search": {
+ "createNewSearch": "Créer un nouvel enregistrement de recherche",
+ "emptyResult": "Aucun résultat trouvé, veuillez modifier les mots-clés et réessayer",
+ "genAiMessage": "Créer un message d'assistant",
+ "includedTooltip": "Les résultats de recherche actuels seront intégrés dans le contexte de la conversation",
+ "keywords": "Mots-clés :",
+ "scoreTooltip": "Score de pertinence, plus ce score est élevé, plus il est pertinent par rapport aux mots-clés de la requête",
+ "searchBar": {
+ "button": "Rechercher",
+ "placeholder": "Mots-clés",
+ "tooltip": "Cela va récupérer à nouveau les résultats de recherche et créer un nouveau message de résumé"
+ },
+ "searchEngine": "Moteur de recherche :",
+ "searchResult": "Nombre de recherches :",
+ "summary": "Résumé",
+ "summaryTooltip": "Résumer le contenu actuel",
+ "viewMoreResults": "Voir {{results}} résultats supplémentaires"
}
}
diff --git a/DigitalHumanWeb/locales/fr-FR/topic.json b/DigitalHumanWeb/locales/fr-FR/topic.json
new file mode 100644
index 0000000..1eee84f
--- /dev/null
+++ b/DigitalHumanWeb/locales/fr-FR/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Renommage intelligent",
+ "confirmRemoveAll": "Vous allez supprimer tous les sujets. Cette action est irréversible, veuillez agir avec prudence.",
+ "confirmRemoveTopic": "Vous allez supprimer ce sujet. Cette action est irréversible, veuillez agir avec prudence.",
+ "confirmRemoveUnstarred": "Vous allez supprimer les sujets non favoris. Cette action est irréversible, veuillez agir avec prudence.",
+ "duplicate": "Créer une copie",
+ "export": "Exporter le sujet",
+ "removeAll": "Supprimer tous les sujets",
+ "removeUnstarred": "Supprimer les sujets non favoris"
+ },
+ "defaultTitle": "Sujet par défaut",
+ "duplicateLoading": "Copie du sujet en cours...",
+ "duplicateSuccess": "Copie du sujet réussie",
+ "favorite": "Favori",
+ "groupMode": {
+ "ascMessages": "Par ordre croissant du nombre de messages",
+ "byTime": "Groupé par temps",
+ "descMessages": "Par ordre décroissant du nombre de messages",
+ "flat": "Non groupé"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Ce mois-ci",
+ "today": "Aujourd'hui",
+ "week": "Cette semaine",
+ "yesterday": "Hier"
+ }
+ },
+ "guide": {
+ "desc": "Cliquez sur le bouton à gauche pour enregistrer la conversation actuelle en tant que sujet historique et commencer une nouvelle conversation.",
+ "title": "Liste des sujets"
+ },
+ "searchPlaceholder": "Rechercher des sujets...",
+ "searchResultEmpty": "Aucun résultat de recherche disponible",
+ "temp": "Temporaire",
+ "title": "Sujet"
+}
diff --git a/DigitalHumanWeb/locales/fr-FR/welcome.json b/DigitalHumanWeb/locales/fr-FR/welcome.json
index ebc3cff..dad8794 100644
--- a/DigitalHumanWeb/locales/fr-FR/welcome.json
+++ b/DigitalHumanWeb/locales/fr-FR/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Importer la configuration",
- "market": "Parcourir le marché",
- "start": "Démarrer maintenant"
- },
"guide": {
"agents": {
"replaceBtn": "Remplacer",
diff --git a/DigitalHumanWeb/locales/it-IT/auth.json b/DigitalHumanWeb/locales/it-IT/auth.json
index da60291..01d5d99 100644
--- a/DigitalHumanWeb/locales/it-IT/auth.json
+++ b/DigitalHumanWeb/locales/it-IT/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Mese Scorso",
+ "recent30Days": "Ultimi 30 Giorni"
+ },
+ "header": {
+ "desc": "Gestisci le informazioni del tuo account.",
+ "title": "Account"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Inattivo",
+ "more": "Attivo"
+ },
+ "months": {
+ "apr": "Apr",
+ "aug": "Ago",
+ "dec": "Dic",
+ "feb": "Feb",
+ "jan": "Gen",
+ "jul": "Lug",
+ "jun": "Giu",
+ "mar": "Mar",
+ "may": "Mag",
+ "nov": "Nov",
+ "oct": "Ott",
+ "sep": "Set"
+ },
+ "tooltip": "{{date}} ha inviato {{count}} messaggi quel giorno",
+ "totalCount": "Un totale di {{count}} messaggi inviati nell'ultimo anno"
+ },
"login": "Accedi",
"loginOrSignup": "Accedi / Registrati",
- "profile": "Profilo",
- "security": "Sicurezza",
- "signout": "Esci",
- "signup": "Registrati"
+ "profile": {
+ "avatar": "Avatar",
+ "email": "Indirizzo Email",
+ "sso": {
+ "loading": "Caricamento degli account di terze parti collegati",
+ "providers": "Account collegati",
+ "unlink": {
+ "description": "Dopo la disconnessione, non potrai più accedere con l'account {{provider}} “{{providerAccountId}}”. Se desideri ricollegare l'account {{provider}} a questo account, assicurati che l'indirizzo email dell'account {{provider}} sia {{email}}, e lo collegheremo automaticamente all'account attualmente in uso al momento dell'accesso.",
+ "forbidden": "Devi mantenere almeno un account di terze parti collegato.",
+ "title": "Vuoi disconnettere questo account di terze parti {{provider}}?"
+ }
+ },
+ "username": "Nome Utente"
+ },
+ "signout": "Disconnetti",
+ "signup": "Registrati",
+ "stats": {
+ "aiheatmaps": "Indice di Attività",
+ "assistants": "Assistenti",
+ "assistantsRank": {
+ "left": "Assistente",
+ "right": "Argomenti",
+ "title": "Classifica Utilizzo Assistente"
+ },
+ "createdAt": "Registrato il",
+ "days": "giorni",
+ "empty": {
+ "desc": "Accumula più dati di chat per visualizzare",
+ "title": "Nessun Dato"
+ },
+ "lastYearActivity": "attività nell'ultimo anno",
+ "loginGuide": {
+ "f1": "Ottieni un utilizzo gratuito",
+ "f2": "Sincronizza i messaggi su più dispositivi",
+ "f3": "Accedi a un ricco assistente",
+ "f4": "Esplora potenti plugin",
+ "title": "Dopo il login puoi:"
+ },
+ "messages": "Messaggi",
+ "modelsRank": {
+ "left": "Modello",
+ "right": "Messaggi",
+ "title": "Classifica Utilizzo Modello"
+ },
+ "share": {
+ "title": "Il Mio Indice di Attività AI"
+ },
+ "topics": "Argomenti",
+ "topicsRank": {
+ "left": "Argomento",
+ "right": "Messaggi",
+ "title": "Classifica Contenuti Argomento"
+ },
+ "updatedAt": "Aggiornato il",
+ "welcome": "{{username}}, questo è il tuo {{days}} giorno con {{appName}}",
+ "words": "Parole"
+ },
+ "tab": {
+ "profile": "Profilo",
+ "security": "Sicurezza",
+ "stats": "Statistiche"
+ }
}
diff --git a/DigitalHumanWeb/locales/it-IT/changelog.json b/DigitalHumanWeb/locales/it-IT/changelog.json
new file mode 100644
index 0000000..fa7ed31
--- /dev/null
+++ b/DigitalHumanWeb/locales/it-IT/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Seguici su X",
+ "subscribeToUpdates": "Iscriviti agli aggiornamenti",
+ "versions": "Dettagli versione"
+ },
+ "addedWhileAway": "Abbiamo introdotto nuove funzionalità mentre eri via.",
+ "allChangelog": "Visualizza tutti i registri delle modifiche",
+ "description": "Tieni traccia delle nuove funzionalità e miglioramenti di {{appName}}",
+ "pagination": {
+ "next": "Pagina successiva",
+ "older": "Visualizza le modifiche precedenti"
+ },
+ "readDetails": "Leggi i dettagli",
+ "title": "Registro delle modifiche",
+ "versionDetails": "Dettagli versione",
+ "welcomeBack": "Bentornato!"
+}
diff --git a/DigitalHumanWeb/locales/it-IT/chat.json b/DigitalHumanWeb/locales/it-IT/chat.json
index 8c166b8..95b9959 100644
--- a/DigitalHumanWeb/locales/it-IT/chat.json
+++ b/DigitalHumanWeb/locales/it-IT/chat.json
@@ -8,6 +8,7 @@
"agents": "Assistente",
"artifact": {
"generating": "Generazione in corso",
+ "inThread": "Non è possibile visualizzare nei sottoargomenti, passare all'area di discussione principale per aprire",
"thinking": "In fase di riflessione",
"thought": "Processo di pensiero",
"unknownTitle": "Opera non nominata"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Copia",
"emptyAgent": "Nessun assistente disponibile",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Il costo di generazione di una singola conversazione può essere ridotto fino al 90%, con una velocità di risposta aumentata di 4 volte (<1>Scopri di più1>). Attivando questa opzione, verrà disabilitato automaticamente il limite sul numero di messaggi storici.",
+ "title": "Attiva la cache del contesto"
+ },
+ "enableReasoning": {
+ "desc": "Limitazioni basate sul meccanismo di pensiero di Claude (<1>Scopri di più1>), attivando questa opzione verrà disabilitato automaticamente il limite sul numero di messaggi storici.",
+ "title": "Attiva il pensiero profondo"
+ },
+ "reasoningBudgetToken": {
+ "title": "Token di consumo del pensiero"
+ },
+ "title": "Funzionalità di estensione del modello"
+ },
+ "history": {
+ "title": "L'assistente ricorderà solo gli ultimi {{count}} messaggi"
+ },
"historyRange": "Intervallo cronologico",
+ "historySummary": "Riepilogo della storia",
"inbox": {
"desc": "Attiva il cluster cerebrale, accendi la scintilla del pensiero. Il tuo assistente intelligente, qui per comunicare con te su tutto.",
"title": "Chiacchierata casuale"
@@ -45,6 +64,9 @@
"stop": "Ferma",
"warp": "A capo"
},
+ "intentUnderstanding": {
+ "title": "Stiamo comprendendo e analizzando la tua intenzione..."
+ },
"knowledgeBase": {
"all": "Tutti i contenuti",
"allFiles": "Tutti i file",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Elimina e rigenera",
+ "deleteDisabledByThreads": "Esistono sottoargomenti, non è possibile eliminare",
"regenerate": "Rigenera"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Crediti",
+ "creditPricing": "Prezzo",
+ "creditTooltip": "Per facilitare il conteggio, consideriamo 1$ equivalente a 1M crediti, ad esempio $3/M token equivalgono a 3 crediti/token",
+ "pricing": {
+ "inputCachedTokens": "Input memorizzato {{amount}}/crediti · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M caratteri",
+ "inputMinutes": "${{amount}}/minuto",
+ "inputTokens": "Input {{amount}}/crediti · ${{amount}}/M",
+ "outputTokens": "Output {{amount}}/crediti · ${{amount}}/M",
+ "writeCacheInputTokens": "Scrittura cache input {{amount}}/crediti · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Prezzo medio",
+ "input": "Input",
+ "inputAudio": "Input audio",
+ "inputCached": "Input memorizzato",
+ "inputCitation": "Citazione input",
+ "inputText": "Input testo",
+ "inputTitle": "Dettagli input",
+ "inputUncached": "Input non memorizzato",
+ "inputWriteCached": "Scrittura cache input",
+ "output": "Output",
+ "outputAudio": "Output audio",
+ "outputText": "Output testo",
+ "outputTitle": "Dettagli output",
+ "reasoning": "Ragionamento profondo",
+ "title": "Dettagli generati",
+ "total": "Totale consumato"
+ }
+ },
"newAgent": "Nuovo assistente",
"pin": "Fissa in alto",
"pinOff": "Annulla fissaggio in alto",
@@ -81,6 +137,32 @@
},
"regenerate": "Rigenera",
"roleAndArchive": "Ruolo e archivio",
+ "search": {
+ "grounding": {
+ "searchQueries": "Parole chiave di ricerca",
+ "title": "Trovati {{count}} risultati"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Determina intelligentemente se è necessario cercare in base al contenuto della conversazione",
+ "title": "Collegamento intelligente"
+ },
+ "off": {
+ "desc": "Utilizza solo la conoscenza di base del modello, senza effettuare ricerche online",
+ "title": "Disattiva collegamento"
+ },
+ "on": {
+ "desc": "Esegue continuamente ricerche online per ottenere le informazioni più recenti",
+ "title": "Collegamento sempre attivo"
+ },
+ "useModelBuiltin": "Utilizza il motore di ricerca integrato del modello"
+ },
+ "searchModel": {
+ "desc": "Il modello attuale non supporta le chiamate di funzione, quindi è necessario utilizzarlo insieme a un modello che supporti le chiamate di funzione per cercare online",
+ "title": "Modello di ricerca assistita"
+ },
+ "title": "Ricerca online"
+ },
"searchAgentPlaceholder": "Assistente di ricerca...",
"sendPlaceholder": "Inserisci il testo della chat...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Il nome del gruppo deve essere lungo 1-20 caratteri"
},
"shareModal": {
+ "copy": "Copia",
"download": "Scarica screenshot",
+ "downloadFile": "Scarica file",
+ "exportTitle": "Titolo predefinito",
"imageType": "Tipo di immagine",
+ "includeTool": "Includi messaggio dello strumento",
+ "includeUser": "Includi messaggio dell'utente",
"screenshot": "Screenshot",
"settings": "Impostazioni di esportazione",
- "shareToShareGPT": "Genera link di condivisione ShareGPT",
+ "text": "Testo",
"withBackground": "Con immagine di sfondo",
"withFooter": "Con piè di pagina",
"withPluginInfo": "Con informazioni sul plugin",
+ "withRole": "Includi ruolo del messaggio",
"withSystemRole": "Con impostazione del ruolo dell'assistente"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Riconoscimento in corso...",
"prettifying": "Miglioramento in corso..."
},
- "temp": "Temporaneo",
+ "thread": {
+ "divider": "Sottoargomento",
+ "threadMessageCount": "{{messageCount}} messaggi",
+ "title": "Sottoargomento"
+ },
"tokenDetails": {
"chats": "Chat",
+ "historySummary": "Riepilogo storico",
"rest": "Rimanenti",
"systemRole": "Ruolo di sistema",
"title": "Dettagli del Token",
@@ -131,29 +224,10 @@
"used": "Utilizzati"
},
"topic": {
- "actions": {
- "autoRename": "Rinomina automaticamente",
- "duplicate": "Crea copia",
- "export": "Esporta argomento"
- },
"checkOpenNewTopic": "Abilitare un nuovo argomento?",
"checkSaveCurrentMessages": "Vuoi salvare la conversazione attuale come argomento?",
- "confirmRemoveAll": "Stai per rimuovere tutti gli argomenti, questa operazione non potrà essere annullata. Procedere con cautela.",
- "confirmRemoveTopic": "Stai per rimuovere questo argomento, l'operazione non potrà essere annullata. Procedere con cautela.",
- "confirmRemoveUnstarred": "Stai per rimuovere gli argomenti non contrassegnati, questa operazione non potrà essere annullata. Procedere con cautela.",
- "defaultTitle": "Argomento predefinito",
- "duplicateLoading": "Duplicazione dell'argomento in corso...",
- "duplicateSuccess": "Argomento duplicato con successo",
- "guide": {
- "desc": "Fare clic sul pulsante a sinistra per salvare l'attuale sessione come argomento storico e avviare una nuova sessione",
- "title": "Elenco argomenti"
- },
"openNewTopic": "Apri nuovo argomento",
- "removeAll": "Rimuovi tutti gli argomenti",
- "removeUnstarred": "Rimuovi argomenti non contrassegnati",
- "saveCurrentMessages": "Salva la conversazione attuale come argomento",
- "searchPlaceholder": "Cerca argomenti...",
- "title": "Elenco argomenti"
+ "saveCurrentMessages": "Salva la conversazione attuale come argomento"
},
"translate": {
"action": "Traduci",
@@ -184,5 +258,6 @@
"processing": "Elaborazione del file..."
}
}
- }
+ },
+ "zenMode": "Modalità di concentrazione"
}
diff --git a/DigitalHumanWeb/locales/it-IT/common.json b/DigitalHumanWeb/locales/it-IT/common.json
index fe0f0c3..437462d 100644
--- a/DigitalHumanWeb/locales/it-IT/common.json
+++ b/DigitalHumanWeb/locales/it-IT/common.json
@@ -9,15 +9,79 @@
"title": "Benvenuto a {{name}}"
}
},
- "appInitializing": "Applicazione in fase di avvio...",
+ "appLoading": {
+ "appIdle": "Pronto per avviare",
+ "appInitializing": "Avvio dell'app in corso...",
+ "failed": "Ci dispiace, l'inizializzazione dell'applicazione è fallita. Si prega di controllare i dettagli per la risoluzione.",
+ "finished": "Inizializzazione del database completata",
+ "goToChat": "Caricamento della pagina di chat in corso...",
+ "initAuth": "Inizializzazione del servizio di autenticazione...",
+ "initUser": "Inizializzazione dello stato utente...",
+ "initializing": "Inizializzazione del database PGlite...",
+ "loadingDependencies": "Inizializzazione delle dipendenze...",
+ "loadingWasm": "Caricamento del modulo WASM...",
+ "migrating": "Esecuzione della migrazione delle tabelle dati...",
+ "ready": "Database pronto",
+ "showDetail": "Mostra dettagli"
+ },
"autoGenerate": "Generazione automatica",
"autoGenerateTooltip": "Completamento automatico basato su suggerimenti",
"autoGenerateTooltipDisabled": "Si prega di compilare il campo suggerimento per abilitare la funzione di completamento automatico",
"back": "Indietro",
"batchDelete": "Elimina in batch",
"blog": "Blog sui prodotti",
+ "branching": "Crea un sottotema",
+ "branchingDisable": "La funzione «sottotema» è disponibile solo nella versione server. Se desideri utilizzare questa funzione, passa alla modalità di distribuzione server o utilizza LobeChat Cloud.",
"cancel": "Annulla",
"changelog": "Registro modifiche",
+ "clientDB": {
+ "autoInit": {
+ "title": "Inizializzazione del database PGlite"
+ },
+ "error": {
+ "desc": "Ci scusiamo, si è verificato un errore durante il processo di inizializzazione del database Pglite. Clicca sul pulsante per riprovare. Se l'errore persiste dopo vari tentativi, per favore <1>invia un problema1> e noi ci occuperemo di risolverlo il prima possibile",
+ "detail": "Motivo dell'errore: [{{type}}] {{message}}. Dettagli come segue:",
+ "retry": "Riprova",
+ "title": "Inizializzazione del database fallita"
+ },
+ "initing": {
+ "error": "Si è verificato un errore, si prega di riprovare",
+ "idle": "In attesa di inizializzazione...",
+ "initializing": "In fase di inizializzazione...",
+ "loadingDependencies": "Caricamento delle dipendenze in corso...",
+ "loadingWasmModule": "Caricamento del modulo WASM in corso...",
+ "migrating": "Esecuzione della migrazione della tabella dati...",
+ "ready": "Database pronto"
+ },
+ "modal": {
+ "desc": "Abilita il database client PGlite per memorizzare in modo persistente i dati della chat nel tuo browser e utilizzare funzionalità avanzate come la knowledge base",
+ "enable": "Abilita ora",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Conserva il tuo archivio personale di conoscenze e avvia facilmente conversazioni con il tuo assistente (in arrivo)",
+ "title": "Supporto per conversazioni sull'archivio di conoscenze, attiva il tuo secondo cervello"
+ },
+ "localFirst": {
+ "desc": "I dati delle chat sono completamente memorizzati nel browser, i tuoi dati sono sempre sotto il tuo controllo.",
+ "title": "Locale prima, privacy al primo posto"
+ },
+ "pglite": {
+ "desc": "Costruito su PGlite, supporta nativamente le funzionalità avanzate AI Native (ricerca vettoriale)",
+ "title": "Nuova generazione di architettura di archiviazione client"
+ }
+ },
+ "init": {
+ "desc": "In fase di inizializzazione del database, il tempo necessario può variare da 5 a 30 secondi a seconda della rete",
+ "title": "Inizializzazione del database PGlite in corso"
+ },
+ "title": "Attiva il database client"
+ },
+ "ready": {
+ "button": "Usa ora",
+ "desc": "Inizia subito",
+ "title": "Database PGlite pronto"
+ }
+ },
"close": "Chiudi",
"contact": "Contattaci",
"copy": "Copia",
@@ -112,6 +176,7 @@
"en": "Inglese",
"en-US": "Inglese",
"es-ES": "Spagnolo",
+ "fa-IR": "persiano",
"fi-FI": "Finlandese",
"fr-FR": "Francese",
"hi-IN": "Hindi",
@@ -153,6 +218,7 @@
"pinOff": "Annulla fissaggio",
"privacy": "Informativa sulla privacy",
"regenerate": "Rigenera",
+ "releaseNotes": "Dettagli della versione",
"rename": "Rinomina",
"reset": "Ripristina",
"retry": "Riprova",
@@ -209,6 +275,7 @@
},
"temp": "Temporaneo",
"terms": "Termini di servizio",
+ "update": "Aggiornamento",
"updateAgent": "Aggiorna informazioni agente",
"upgradeVersion": {
"action": "Aggiorna",
@@ -219,6 +286,7 @@
"anonymousNickName": "Utente Anonimo",
"billing": "Gestione fatturazione",
"cloud": "Prova {{name}}",
+ "community": "Versione comunitaria",
"data": "Archiviazione dati",
"defaultNickname": "Utente Community",
"discord": "Supporto della community",
@@ -228,7 +296,6 @@
"help": "Centro assistenza",
"moveGuide": "Il pulsante delle impostazioni è stato spostato qui",
"plans": "Piani di abbonamento",
- "preview": "Anteprima",
"profile": "Gestione account",
"setting": "Impostazioni app",
"usages": "Statistiche di utilizzo"
diff --git a/DigitalHumanWeb/locales/it-IT/components.json b/DigitalHumanWeb/locales/it-IT/components.json
index ef6e808..0721e20 100644
--- a/DigitalHumanWeb/locales/it-IT/components.json
+++ b/DigitalHumanWeb/locales/it-IT/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Suddivisione in batch",
"chunking": "Suddivisione",
"chunkingTooltip": "Dividi il file in più blocchi di testo e vettorizzali, utilizzabili per la ricerca semantica e il dialogo sui file",
+ "chunkingUnsupported": "Questo file non supporta il frazionamento",
"confirmDelete": "Stai per eliminare questo file. Una volta eliminato, non sarà possibile recuperarlo. Ti preghiamo di confermare l'operazione.",
"confirmDeleteMultiFiles": "Stai per eliminare i {{count}} file selezionati. Una volta eliminati, non sarà possibile recuperarli. Ti preghiamo di confermare l'operazione.",
"confirmRemoveFromKnowledgeBase": "Stai per rimuovere i {{count}} file selezionati dalla base di conoscenza. I file rimarranno visibili in tutti i file. Ti preghiamo di confermare l'operazione.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Indietro"
},
+ "MaxTokenSlider": {
+ "unlimited": "Illimitato"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Modello personalizzato: di default supporta sia la chiamata di funzioni che il riconoscimento visivo. Verifica l'effettiva disponibilità di tali funzionalità.",
"file": "Questo modello supporta il caricamento e il riconoscimento di file.",
"functionCall": "Questo modello supporta la chiamata di funzioni.",
+ "reasoning": "Questo modello supporta un pensiero profondo",
+ "search": "Questo modello supporta la ricerca online",
"tokens": "Questo modello supporta un massimo di {{tokens}} token per sessione.",
"vision": "Questo modello supporta il riconoscimento visivo."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Nessun modello attivo. Vai alle impostazioni per attivarne uno.",
+ "emptyProvider": "Nessun fornitore attivo, vai alle impostazioni per attivarlo",
+ "goToSettings": "Vai alle impostazioni",
"provider": "Provider"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "A causa delle restrizioni di sicurezza del browser, è necessario configurare il cross-origin per utilizzare Ollama correttamente.",
+ "linux": {
+ "env": "Aggiungi `Environment` nella sezione [Service] e aggiungi la variabile d'ambiente OLLAMA_ORIGINS:",
+ "reboot": "Ricarica systemd e riavvia Ollama",
+ "systemd": "Usa systemd per modificare il servizio ollama:"
+ },
+ "macos": "Apri l'applicazione 'Terminale', incolla il seguente comando e premi invio per eseguirlo",
+ "reboot": "Riavvia il servizio Ollama dopo il completamento dell'esecuzione",
+ "title": "Configura Ollama per consentire l'accesso cross-origin",
+ "windows": "Su Windows, fai clic su 'Pannello di controllo' e accedi alla modifica delle variabili d'ambiente di sistema. Crea una nuova variabile d'ambiente chiamata 'OLLAMA_ORIGINS' per il tuo account utente, con valore *, quindi fai clic su 'OK/Applica' per salvare"
+ },
+ "install": {
+ "description": "Assicurati di aver avviato Ollama. Se non hai scaricato Ollama, visita il sito ufficiale <1>per scaricare1>",
+ "docker": "Se preferisci utilizzare Docker, Ollama offre anche un'immagine Docker ufficiale, puoi scaricarla con il seguente comando:",
+ "linux": {
+ "command": "Installa con il seguente comando:",
+ "manual": "In alternativa, puoi fare riferimento alla <1>guida all'installazione manuale di Linux1> per installare manualmente"
+ },
+ "title": "Installa e avvia l'app Ollama localmente",
+ "windowsTab": "Windows (versione anteprima)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Pensando profondamente...",
+ "thought": "Ho riflettuto a lungo (tempo impiegato {{duration}} secondi)",
+ "thoughtWithDuration": "Ho riflettuto a lungo"
}
}
diff --git a/DigitalHumanWeb/locales/it-IT/discover.json b/DigitalHumanWeb/locales/it-IT/discover.json
index ac7805a..e59f6cd 100644
--- a/DigitalHumanWeb/locales/it-IT/discover.json
+++ b/DigitalHumanWeb/locales/it-IT/discover.json
@@ -126,6 +126,10 @@
"title": "Freschezza del tema"
},
"range": "Intervallo",
+ "reasoning_effort": {
+ "desc": "Questa impostazione controlla l'intensità del ragionamento del modello prima di generare una risposta. Un'intensità bassa privilegia la velocità di risposta e risparmia Token, mentre un'intensità alta fornisce un ragionamento più completo, ma consuma più Token e riduce la velocità di risposta. Il valore predefinito è medio, bilanciando l'accuratezza del ragionamento e la velocità di risposta.",
+ "title": "Intensità del ragionamento"
+ },
"temperature": {
"desc": "Questa impostazione influisce sulla diversità delle risposte del modello. Valori più bassi portano a risposte più prevedibili e tipiche, mentre valori più alti incoraggiano risposte più varie e insolite. Quando il valore è impostato a 0, il modello fornisce sempre la stessa risposta per un dato input.",
"title": "Casualità"
diff --git a/DigitalHumanWeb/locales/it-IT/error.json b/DigitalHumanWeb/locales/it-IT/error.json
index add5dbd..dd7ab81 100644
--- a/DigitalHumanWeb/locales/it-IT/error.json
+++ b/DigitalHumanWeb/locales/it-IT/error.json
@@ -12,8 +12,14 @@
"retry": "Ricarica",
"title": "La pagina ha riscontrato un problema.."
},
- "fetchError": "Errore di richiesta",
- "fetchErrorDetail": "Dettagli dell'errore",
+ "fetchError": {
+ "detail": "Dettagli errore",
+ "title": "Richiesta fallita"
+ },
+ "loginRequired": {
+ "desc": "Verrai reindirizzato automaticamente alla pagina di accesso",
+ "title": "Accedi per utilizzare questa funzione"
+ },
"notFound": {
"backHome": "Torna alla homepage",
"check": "Controlla se l'URL è corretto",
@@ -51,22 +57,34 @@
"431": "Spiacenti, le intestazioni della tua richiesta sono troppo grandi per il server da gestire",
"451": "Spiacenti, per motivi legali, il server rifiuta di fornire questa risorsa",
"500": "Spiacenti, il server sembra avere qualche difficoltà al momento e non può completare la tua richiesta. Riprova più tardi",
+ "501": "Ci dispiace, il server non sa ancora come gestire questa richiesta, per favore verifica che la tua operazione sia corretta",
"502": "Spiacenti, il server sembra smarrito e non può fornire servizio al momento. Riprova più tardi",
"503": "Spiacenti, il server non può elaborare la tua richiesta al momento, probabilmente a causa di sovraccarico o manutenzione in corso. Riprova più tardi",
"504": "Spiacenti, il server non ha ricevuto risposta dal server upstream. Riprova più tardi",
+ "505": "Ci dispiace, il server non supporta la versione HTTP che stai utilizzando, per favore aggiorna e riprova",
+ "506": "Ci dispiace, c'è un problema di configurazione del server, contatta l'amministratore per risolverlo",
+ "507": "Ci dispiace, lo spazio di archiviazione del server è insufficiente per elaborare la tua richiesta, per favore riprova più tardi",
+ "509": "Ci dispiace, la larghezza di banda del server è esaurita, per favore riprova più tardi",
+ "510": "Ci dispiace, il server non supporta le funzionalità di estensione richieste, contatta l'amministratore",
+ "524": "Ci dispiace, il server ha superato il timeout in attesa di una risposta, potrebbe essere a causa di una risposta troppo lenta, per favore riprova più tardi",
"AgentRuntimeError": "Errore di esecuzione del modello linguistico Lobe, controlla le informazioni seguenti o riprova",
+ "ConnectionCheckFailed": "La risposta è vuota, controlla se l'indirizzo del proxy API termina con `/v1`",
+ "ExceededContextWindow": "Il contenuto della richiesta attuale supera la lunghezza che il modello può gestire. Si prega di ridurre la quantità di contenuto e riprovare.",
"FreePlanLimit": "Attualmente sei un utente gratuito e non puoi utilizzare questa funzione. Per favore, passa a un piano a pagamento per continuare.",
+ "InsufficientQuota": "Ci dispiace, la quota per questa chiave ha raggiunto il limite. Si prega di controllare il saldo dell'account o di aumentare la quota della chiave e riprovare.",
"InvalidAccessCode": "Password incorrect or empty, please enter the correct access password, or add a custom API Key",
"InvalidBedrockCredentials": "Autenticazione Bedrock non riuscita, controlla AccessKeyId/SecretAccessKey e riprova",
"InvalidClerkUser": "Spiacenti, al momento non hai effettuato l'accesso. Per favore, effettua l'accesso o registrati prima di continuare.",
"InvalidGithubToken": "Il token di accesso personale di Github non è corretto o è vuoto. Controlla il token di accesso personale di Github e riprova.",
"InvalidOllamaArgs": "Configurazione Ollama non valida, controllare la configurazione di Ollama e riprovare",
"InvalidProviderAPIKey": "{{provider}} Chiave API non valida o vuota, controlla la Chiave API di {{provider}} e riprova",
+ "InvalidVertexCredentials": "Autenticazione Vertex non riuscita, controlla le credenziali di autenticazione e riprova",
"LocationNotSupportError": "Spiacenti, la tua posizione attuale non supporta questo servizio modello, potrebbe essere a causa di restrizioni geografiche o servizi non attivati. Verifica se la posizione attuale supporta l'uso di questo servizio o prova a utilizzare un'altra posizione.",
+ "ModelNotFound": "Ci dispiace, non è possibile richiedere il modello corrispondente, potrebbe essere che il modello non esista o che non si disponga dei diritti di accesso. Si prega di cambiare la chiave API o di modificare i diritti di accesso e riprovare.",
"NoOpenAIAPIKey": "La chiave API OpenAI è vuota. Aggiungi una chiave API personalizzata OpenAI",
"OllamaBizError": "Errore di servizio Ollama, controllare le informazioni seguenti o riprovare",
"OllamaServiceUnavailable": "Servizio Ollama non disponibile: controllare che Ollama sia in esecuzione correttamente o che la configurazione di cross-origin di Ollama sia corretta",
- "OpenAIBizError": "Errore di business di OpenAI. Si prega di controllare le informazioni seguenti o riprovare.",
+ "PermissionDenied": "Ci dispiace, non hai il permesso di accedere a questo servizio. Controlla se la tua chiave ha i diritti di accesso.",
"PluginApiNotFound": "Spiacenti, l'API specificata non esiste nel manifesto del plugin. Verifica che il metodo di richiesta corrisponda all'API del manifesto del plugin",
"PluginApiParamsError": "Spiacenti, la convalida dei parametri di input della richiesta del plugin non è riuscita. Verifica che i parametri di input corrispondano alle informazioni dell'API",
"PluginFailToTransformArguments": "Spiacenti, la trasformazione degli argomenti della chiamata al plugin non è riuscita. Si prega di provare a rigenerare il messaggio dell'assistente o riprovare dopo aver cambiato il modello AI di Tools Calling con capacità più avanzate.",
@@ -81,8 +99,11 @@
"PluginServerError": "Errore nella risposta del server del plugin. Verifica il file descrittivo del plugin, la configurazione del plugin o l'implementazione del server",
"PluginSettingsInvalid": "Il plugin deve essere configurato correttamente prima di poter essere utilizzato. Verifica che la tua configurazione sia corretta",
"ProviderBizError": "Errore di business del fornitore {{provider}}. Si prega di controllare le informazioni seguenti o riprovare.",
+ "QuotaLimitReached": "Ci dispiace, l'uso attuale dei token o il numero di richieste ha raggiunto il limite di quota per questa chiave. Si prega di aumentare la quota di questa chiave o riprovare più tardi.",
"StreamChunkError": "Erro di analisi del blocco di messaggi della richiesta in streaming. Controlla se l'interfaccia API attuale è conforme agli standard o contatta il tuo fornitore di API per ulteriori informazioni.",
- "SubscriptionPlanLimit": "Il tuo piano di abbonamento ha raggiunto il limite e non puoi utilizzare questa funzione. Per favore, passa a un piano superiore o acquista un pacchetto di risorse per continuare.",
+ "SubscriptionKeyMismatch": "Ci scusiamo, ma a causa di un'imprevista anomalia di sistema, l'attuale utilizzo dell'abbonamento è temporaneamente non valido. Si prega di fare clic sul pulsante qui sotto per ripristinare l'abbonamento o contattarci via email per ricevere supporto.",
+ "SubscriptionPlanLimit": "I tuoi punti di abbonamento sono esauriti, non puoi utilizzare questa funzione. Ti preghiamo di passare a un piano superiore o di configurare un modello API personalizzato per continuare a utilizzare.",
+ "SystemTimeNotMatchError": "Ci dispiace, l'orario del sistema non corrisponde a quello del server. Si prega di controllare l'orario del sistema e riprovare.",
"UnknownChatFetchError": "Ci scusiamo, si è verificato un errore di richiesta sconosciuto. Si prega di controllare le informazioni seguenti o riprovare."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/it-IT/metadata.json b/DigitalHumanWeb/locales/it-IT/metadata.json
index 31549cc..327cf6c 100644
--- a/DigitalHumanWeb/locales/it-IT/metadata.json
+++ b/DigitalHumanWeb/locales/it-IT/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Segui le nuove funzionalità e i miglioramenti di {{appName}}",
+ "title": "Registro delle modifiche"
+ },
"chat": {
"description": "{{appName}} ti offre la migliore esperienza con ChatGPT, Claude, Gemini e OLLaMA WebUI",
"title": "{{appName}}: strumento di efficienza personale AI, per darti un cervello più intelligente"
diff --git a/DigitalHumanWeb/locales/it-IT/modelProvider.json b/DigitalHumanWeb/locales/it-IT/modelProvider.json
index c4a52d7..cdf90f7 100644
--- a/DigitalHumanWeb/locales/it-IT/modelProvider.json
+++ b/DigitalHumanWeb/locales/it-IT/modelProvider.json
@@ -19,6 +19,24 @@
"title": "Chiave API"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Versione API di Azure, seguendo il formato YYYY-MM-DD, consulta [l'ultima versione](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Ottieni elenco",
+ "title": "Versione API di Azure"
+ },
+ "endpoint": {
+ "desc": "Trova l'endpoint di inferenza del modello Azure AI nella panoramica del progetto Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Endpoint di Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Trova la chiave API nella panoramica del progetto Azure AI",
+ "placeholder": "Chiave Azure",
+ "title": "Chiave"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Inserisci l'ID chiave di accesso AWS",
@@ -51,6 +69,58 @@
"title": "Usa le informazioni di autenticazione Bedrock personalizzate"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Compila l'Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Inserisci l'ID dell'account Cloudflare o l'indirizzo API personalizzato",
+ "placeholder": "ID account Cloudflare / URL API personalizzato",
+ "title": "ID account Cloudflare / indirizzo API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Inserisci la tua API Key",
+ "title": "API Key"
+ },
+ "basicTitle": "Informazioni di base",
+ "configTitle": "Informazioni di configurazione",
+ "confirm": "Crea",
+ "createSuccess": "Creazione avvenuta con successo",
+ "description": {
+ "placeholder": "Descrizione del fornitore (opzionale)",
+ "title": "Descrizione del fornitore"
+ },
+ "id": {
+ "desc": "Identificatore unico del fornitore di servizi, non modificabile dopo la creazione",
+ "format": "Può contenere solo numeri, lettere minuscole, trattini (-) e underscore (_) ",
+ "placeholder": "Si consiglia di utilizzare solo lettere minuscole, ad esempio openai, non modificabile dopo la creazione",
+ "required": "Inserisci l'ID del fornitore",
+ "title": "ID del fornitore"
+ },
+ "logo": {
+ "required": "Carica un logo del fornitore valido",
+ "title": "Logo del fornitore"
+ },
+ "name": {
+ "placeholder": "Inserisci il nome visualizzato del fornitore",
+ "required": "Inserisci il nome del fornitore",
+ "title": "Nome del fornitore"
+ },
+ "proxyUrl": {
+ "required": "Inserisci l'indirizzo del proxy",
+ "title": "Indirizzo proxy"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Seleziona il tipo di SDK",
+ "title": "Formato della richiesta"
+ },
+ "title": "Crea fornitore AI personalizzato"
+ },
"github": {
"personalAccessToken": {
"desc": "Inserisci il tuo PAT di Github, clicca [qui](https://github.com/settings/tokens) per crearne uno",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Inserisci il tuo token HuggingFace, clicca [qui](https://huggingface.co/settings/tokens) per crearne uno",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "Token HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Fornitore non attivato",
+ "enabled": "Fornitore attivato"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Aggiungi fornitore personalizzato",
+ "all": "Tutti",
+ "list": {
+ "disabled": "Non attivato",
+ "enabled": "Attivato"
+ },
+ "notFound": "Nessun risultato trovato",
+ "searchProviders": "Cerca fornitori...",
+ "sort": "Ordinamento personalizzato"
+ },
"ollama": {
"checker": {
"desc": "Verifica se l'indirizzo del proxy è stato compilato correttamente",
@@ -75,33 +169,9 @@
"title": "Download del modello in corso {{model}}"
},
"endpoint": {
- "desc": "Inserisci l'indirizzo del proxy dell'interfaccia Ollama. Lascia vuoto se non specificato localmente",
+ "desc": "Deve includere http(s)://, può rimanere vuoto se non specificato localmente",
"title": "Indirizzo del proxy dell'interfaccia"
},
- "setup": {
- "cors": {
- "description": "A causa delle restrizioni di sicurezza del browser, è necessario configurare il cross-origin resource sharing (CORS) per consentire l'utilizzo di Ollama.",
- "linux": {
- "env": "Nella sezione [Service], aggiungi `Environment` e inserisci la variabile di ambiente OLLAMA_ORIGINS:",
- "reboot": "Dopo aver completato l'esecuzione, riavvia il servizio Ollama.",
- "systemd": "Per modificare il servizio ollama, chiama systemd:"
- },
- "macos": "Apri l'applicazione 'Terminale', incolla il comando seguente e premi Invio per eseguirlo",
- "reboot": "Riavvia il servizio Ollama una volta completata l'esecuzione",
- "title": "Configura Ollama per consentire l'accesso cross-origin",
- "windows": "Su Windows, fai clic su 'Pannello di controllo', accedi alle variabili di ambiente di sistema. Crea una nuova variabile di ambiente chiamata 'OLLAMA_ORIGINS' per il tuo account utente, con valore *, quindi fai clic su 'OK/Applica' per salvare le modifiche"
- },
- "install": {
- "description": "Assicurati di aver avviato Ollama. Se non l'hai ancora scaricato, visita il sito ufficiale per <1>scaricarlo1>",
- "docker": "Se preferisci utilizzare Docker, Ollama fornisce anche un'immagine Docker ufficiale che puoi scaricare tramite il seguente comando:",
- "linux": {
- "command": "Per installare, utilizza il seguente comando:",
- "manual": "Oppure, puoi consultare la <1>Guida all'installazione manuale di Linux1> per installare manualmente"
- },
- "title": "Installa e avvia l'applicazione Ollama localmente",
- "windowsTab": "Windows (Versione di anteprima)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Annulla download",
@@ -112,6 +182,156 @@
"title": "Scarica il modello Ollama specificato"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "La tua chiave e l'indirizzo proxy saranno crittografati utilizzando l'algoritmo di crittografia <1>AES-GCM1>",
+ "apiKey": {
+ "desc": "Inserisci la tua {{name}} API Key",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "Deve contenere http(s)://",
+ "invalid": "Inserisci un URL valido",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "Indirizzo proxy API"
+ },
+ "checker": {
+ "button": "Controlla",
+ "desc": "Verifica se l'API Key e l'indirizzo proxy sono stati inseriti correttamente",
+ "pass": "Controllo superato",
+ "title": "Verifica connettività"
+ },
+ "fetchOnClient": {
+ "desc": "La modalità di richiesta client avvierà direttamente la richiesta di sessione dal browser, migliorando la velocità di risposta",
+ "title": "Utilizza la modalità di richiesta client"
+ },
+ "helpDoc": "Guida alla configurazione",
+ "waitingForMore": "Altri modelli sono in fase di <1>implementazione1>, resta sintonizzato"
+ },
+ "createNew": {
+ "title": "Crea modello AI personalizzato"
+ },
+ "item": {
+ "config": "Configura modello",
+ "customModelCards": {
+ "addNew": "Crea e aggiungi modello {{id}}",
+ "confirmDelete": "Stai per eliminare questo modello personalizzato, una volta eliminato non sarà recuperabile, procedi con cautela."
+ },
+ "delete": {
+ "confirm": "Confermi di voler eliminare il modello {{displayName}}?",
+ "success": "Eliminazione avvenuta con successo",
+ "title": "Elimina modello"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Campo effettivamente richiesto in Azure OpenAI",
+ "placeholder": "Inserisci il nome di distribuzione del modello in Azure",
+ "title": "Nome di distribuzione del modello"
+ },
+ "deployName": {
+ "extra": "Questo campo verrà utilizzato come ID del modello quando si invia la richiesta",
+ "placeholder": "Inserisci il nome o l'ID effettivo del modello distribuito",
+ "title": "Nome di distribuzione del modello"
+ },
+ "displayName": {
+ "placeholder": "Inserisci il nome visualizzato del modello, ad esempio ChatGPT, GPT-4, ecc.",
+ "title": "Nome visualizzato del modello"
+ },
+ "files": {
+ "extra": "L'attuale implementazione del caricamento file è solo una soluzione temporanea, limitata a tentativi personali. Attendere implementazioni complete per il caricamento file.",
+ "title": "Supporto per il caricamento file"
+ },
+ "functionCall": {
+ "extra": "Questa configurazione abiliterà solo la capacità del modello di utilizzare strumenti, consentendo così di aggiungere plugin di tipo strumento al modello. Tuttavia, se il modello supporta realmente l'uso degli strumenti dipende interamente dal modello stesso; si prega di testarne l'usabilità",
+ "title": "Supporto all'uso degli strumenti"
+ },
+ "id": {
+ "extra": "Non modificabile dopo la creazione, verrà utilizzato come ID del modello durante la chiamata all'AI",
+ "placeholder": "Inserisci l'ID del modello, ad esempio gpt-4o o claude-3.5-sonnet",
+ "title": "ID del modello"
+ },
+ "modalTitle": "Configurazione modello personalizzato",
+ "reasoning": {
+ "extra": "Questa configurazione attiverà solo la capacità di pensiero profondo del modello; l'effetto specifico dipende interamente dal modello stesso. Si prega di testare autonomamente se il modello possiede una capacità di pensiero profondo utilizzabile.",
+ "title": "Supporto per il pensiero profondo"
+ },
+ "tokens": {
+ "extra": "Imposta il numero massimo di token supportati dal modello",
+ "title": "Finestra di contesto massima",
+ "unlimited": "Illimitato"
+ },
+ "vision": {
+ "extra": "Questa configurazione abiliterà solo la configurazione di caricamento immagini nell'app, la disponibilità di riconoscimento dipende interamente dal modello stesso, testare autonomamente la disponibilità di riconoscimento visivo di questo modello.",
+ "title": "Supporto per riconoscimento visivo"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/Immagine",
+ "inputCharts": "${{amount}}/M caratteri",
+ "inputMinutes": "${{amount}}/minuti",
+ "inputTokens": "Ingresso ${{amount}}/M",
+ "outputTokens": "Uscita ${{amount}}/M"
+ },
+ "releasedAt": "Rilasciato il {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Aggiungi modello",
+ "disabled": "Non attivato",
+ "disabledActions": {
+ "showMore": "Mostra tutto"
+ },
+ "empty": {
+ "desc": "Si prega di creare un modello personalizzato o di importare un modello per iniziare a utilizzarlo",
+ "title": "Nessun modello disponibile"
+ },
+ "enabled": "Attivato",
+ "enabledActions": {
+ "disableAll": "Disattiva tutto",
+ "enableAll": "Attiva tutto",
+ "sort": "Ordinamento modelli personalizzato"
+ },
+ "enabledEmpty": "Nessun modello attivato, attiva i modelli desiderati dall'elenco qui sotto~",
+ "fetcher": {
+ "clear": "Cancella i modelli recuperati",
+ "fetch": "Recupera l'elenco dei modelli",
+ "fetching": "Recupero dell'elenco dei modelli in corso...",
+ "latestTime": "Ultimo aggiornamento: {{time}}",
+ "noLatestTime": "Nessun elenco recuperato finora"
+ },
+ "resetAll": {
+ "conform": "Sei sicuro di voler ripristinare tutte le modifiche al modello corrente? Dopo il ripristino, l'elenco dei modelli correnti tornerà allo stato predefinito",
+ "success": "Ripristino avvenuto con successo",
+ "title": "Ripristina tutte le modifiche"
+ },
+ "search": "Cerca modelli...",
+ "searchResult": "Trovati {{count}} modelli",
+ "title": "Elenco dei modelli",
+ "total": "Totale di {{count}} modelli disponibili"
+ },
+ "searchNotFound": "Nessun risultato trovato"
+ },
+ "sortModal": {
+ "success": "Ordinamento aggiornato con successo",
+ "title": "Ordinamento personalizzato",
+ "update": "Aggiorna"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Stai per eliminare questo fornitore AI, una volta eliminato non sarà recuperabile, confermi di voler eliminare?",
+ "deleteSuccess": "Eliminazione avvenuta con successo",
+ "tooltip": "Aggiorna la configurazione di base del fornitore",
+ "updateSuccess": "Aggiornamento avvenuto con successo"
+ },
+ "updateCustomAiProvider": {
+ "title": "Aggiorna la configurazione del fornitore di AI personalizzato"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Inserisci le tue chiavi Vertex AI",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Chiavi Vertex AI"
+ }
+ },
"zeroone": {
"title": "01.AI ZeroOne"
},
diff --git a/DigitalHumanWeb/locales/it-IT/models.json b/DigitalHumanWeb/locales/it-IT/models.json
index bc45405..b120d72 100644
--- a/DigitalHumanWeb/locales/it-IT/models.json
+++ b/DigitalHumanWeb/locales/it-IT/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, con un ricco campione di addestramento, offre prestazioni superiori nelle applicazioni di settore."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat è una variante della serie Yi-1.5, appartenente ai modelli di chat open source. Yi-1.5 è una versione aggiornata di Yi, addestrata su 500B di dati di alta qualità e rifinita su oltre 3M di campioni diversificati. Rispetto a Yi, Yi-1.5 mostra prestazioni superiori in codifica, matematica, ragionamento e capacità di seguire istruzioni, mantenendo al contempo eccellenti capacità di comprensione linguistica, ragionamento di buon senso e comprensione della lettura. Questo modello è disponibile in versioni con lunghezze di contesto di 4K, 16K e 32K, con un totale di pre-addestramento di 3.6T token."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B supporta 16K Tokens, offrendo capacità di generazione linguistica efficienti e fluide."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Everything, il più recente modello open source fine-tuned, con 34 miliardi di parametri, supporta vari scenari di dialogo, con dati di addestramento di alta qualità, allineati alle preferenze umane."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Everything, il più recente modello open source fine-tuned, con 9 miliardi di parametri, supporta vari scenari di dialogo, con dati di addestramento di alta qualità, allineati alle preferenze umane."
+ },
"360gpt-pro": {
"description": "360GPT Pro, come membro importante della serie di modelli AI di 360, soddisfa le diverse applicazioni del linguaggio naturale con un'efficace capacità di elaborazione del testo, supportando la comprensione di testi lunghi e conversazioni a più turni."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K enfatizza la sicurezza semantica e l'orientamento alla responsabilità, progettato specificamente per scenari applicativi con elevati requisiti di sicurezza dei contenuti, garantendo l'accuratezza e la robustezza dell'esperienza utente."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 utilizza la ricerca ad albero per costruire catene di pensiero e introduce un meccanismo di riflessione, addestrato tramite apprendimento rinforzato, dotando il modello della capacità di auto-riflessione e correzione degli errori."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro è un modello avanzato di elaborazione del linguaggio naturale lanciato da 360, con eccellenti capacità di generazione e comprensione del testo, in particolare nel campo della generazione e creazione, capace di gestire compiti complessi di conversione linguistica e interpretazione di ruoli."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 utilizza la ricerca ad albero per costruire catene di pensiero e introduce un meccanismo di riflessione, addestrato tramite apprendimento rinforzato, dotando il modello della capacità di auto-riflessione e correzione degli errori."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra è la versione più potente della serie di modelli Spark, migliorando la comprensione e la sintesi del contenuto testuale mentre aggiorna il collegamento alla ricerca online. È una soluzione completa per migliorare la produttività lavorativa e rispondere con precisione alle esigenze, rappresentando un prodotto intelligente all'avanguardia nel settore."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Il modello ha la migliore capacità in Cina, superando i modelli mainstream esteri in compiti cinesi come enciclopedie, testi lunghi e creazione di contenuti. Ha anche capacità multimodali leader nel settore, con prestazioni eccellenti in vari benchmark di valutazione."
},
+ "Baichuan4-Air": {
+ "description": "Il modello con le migliori capacità in patria, supera i modelli principali esteri in compiti cinesi come enciclopedie, testi lunghi e creazione di contenuti. Possiede anche capacità multimodali leader del settore, con prestazioni eccellenti in vari benchmark di valutazione."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Il modello con le migliori capacità in patria, supera i modelli principali esteri in compiti cinesi come enciclopedie, testi lunghi e creazione di contenuti. Possiede anche capacità multimodali leader del settore, con prestazioni eccellenti in vari benchmark di valutazione."
+ },
+ "DeepSeek-R1": {
+ "description": "LLM avanzato ed efficiente, specializzato in ragionamento, matematica e programmazione."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1—il modello più grande e intelligente del pacchetto DeepSeek—è stato distillato nell'architettura Llama 70B. Basato su benchmark e valutazioni umane, questo modello è più intelligente del Llama 70B originale, eccellendo in particolare in compiti che richiedono precisione matematica e fattuale."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Il modello di distillazione DeepSeek-R1 basato su Qwen2.5-Math-1.5B ottimizza le prestazioni di inferenza attraverso l'apprendimento rinforzato e dati di avvio a freddo, aggiornando il benchmark multi-task del modello open source."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Il modello di distillazione DeepSeek-R1 basato su Qwen2.5-14B ottimizza le prestazioni di inferenza attraverso l'apprendimento rinforzato e dati di avvio a freddo, aggiornando il benchmark multi-task del modello open source."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "La serie DeepSeek-R1 ottimizza le prestazioni di inferenza attraverso l'apprendimento rinforzato e dati di avvio a freddo, aggiornando il benchmark multi-task del modello open source, superando il livello di OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Il modello di distillazione DeepSeek-R1 basato su Qwen2.5-Math-7B ottimizza le prestazioni di inferenza attraverso l'apprendimento rinforzato e dati di avvio a freddo, aggiornando il benchmark multi-task del modello open source."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro è un modello multimodale aggiornato, che supporta il riconoscimento di immagini con qualsiasi risoluzione e rapporti di aspetto estremi, migliorando le capacità di ragionamento visivo, riconoscimento di documenti, comprensione delle informazioni dettagliate e capacità di seguire istruzioni."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite offre un'estrema velocità di risposta, un miglior rapporto qualità-prezzo e opzioni più flessibili per diversi scenari dei clienti. Supporta inferenze e fine-tuning con una finestra di contesto di 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite offre un'estrema velocità di risposta, un miglior rapporto qualità-prezzo e opzioni più flessibili per diversi scenari dei clienti. Supporta inferenze e fine-tuning con una finestra di contesto di 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite offre un'estrema velocità di risposta, un miglior rapporto qualità-prezzo e opzioni più flessibili per diversi scenari dei clienti. Supporta inferenze e fine-tuning con una finestra di contesto di 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "Il modello principale presenta le migliori prestazioni, adatto per compiti complessi, con risultati eccellenti in scenari di domanda di riferimento, sintesi, creazione, classificazione del testo, e role-playing. Supporta inferenze e fine-tuning con una finestra di contesto di 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "Il modello principale con le migliori prestazioni, adatto a gestire compiti complessi, con ottimi risultati in scenari di domande e risposte, riassunti, creazione, classificazione del testo e interpretazione di ruoli. Supporta il ragionamento e il fine-tuning con una finestra di contesto di 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "Il modello principale presenta le migliori prestazioni, adatto per compiti complessi, con risultati eccellenti in scenari di domanda di riferimento, sintesi, creazione, classificazione del testo, e role-playing. Supporta inferenze e fine-tuning con una finestra di contesto di 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "Il modello principale presenta le migliori prestazioni, adatto per compiti complessi, con risultati eccellenti in scenari di domanda di riferimento, sintesi, creazione, classificazione del testo, e role-playing. Supporta inferenze e fine-tuning con una finestra di contesto di 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Il modello Doubao-vision è un modello multimodale lanciato da Doubao, dotato di potenti capacità di comprensione e ragionamento delle immagini, nonché di una precisa comprensione delle istruzioni. Il modello ha dimostrato prestazioni eccezionali nell'estrazione di informazioni testuali da immagini e in compiti di ragionamento basati su immagini, applicabile a compiti di domanda e risposta visiva più complessi e ampi."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Il modello Doubao-vision è un modello multimodale lanciato da Doubao, dotato di potenti capacità di comprensione e ragionamento delle immagini, nonché di una precisa comprensione delle istruzioni. Il modello ha dimostrato prestazioni eccezionali nell'estrazione di informazioni testuali da immagini e in compiti di ragionamento basati su immagini, applicabile a compiti di domanda e risposta visiva più complessi e ampi."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Modello di linguaggio di grande scala di punta sviluppato da Baidu, che copre un'enorme quantità di dati in cinese e inglese, con potenti capacità generali, in grado di soddisfare la maggior parte delle esigenze di domande e risposte, generazione creativa e scenari di applicazione dei plugin; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Modello di linguaggio di grande scala di punta sviluppato da Baidu, che copre un'enorme quantità di dati in cinese e inglese, con potenti capacità generali, in grado di soddisfare la maggior parte delle esigenze di domande e risposte, generazione creativa e scenari di applicazione dei plugin; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Modello di linguaggio di grande scala di punta sviluppato da Baidu, che copre un'enorme quantità di dati in cinese e inglese, con potenti capacità generali, in grado di soddisfare la maggior parte delle esigenze di domande e risposte, generazione creativa e scenari di applicazione dei plugin; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Modello di linguaggio di grande scala ultra avanzato sviluppato da Baidu, che rispetto a ERNIE 3.5 ha subito un aggiornamento completo delle capacità del modello, ampiamente applicabile a scenari di compiti complessi in vari settori; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Modello di linguaggio di grande scala ultra avanzato sviluppato da Baidu, che rispetto a ERNIE 3.5 ha subito un aggiornamento completo delle capacità del modello, ampiamente applicabile a scenari di compiti complessi in vari settori; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Il modello linguistico ultra grande di Baidu, auto-sviluppato, offre eccellenti prestazioni generali, ampiamente utilizzabile in scenari complessi di vari settori; supporta l'integrazione automatica dei plugin di ricerca di Baidu, garantendo l'attualità delle informazioni nelle risposte. Rispetto a ERNIE 4.0, offre prestazioni superiori."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Modello di linguaggio di grande scala ultra avanzato sviluppato da Baidu, con prestazioni complessive eccezionali, ampiamente applicabile a scenari di compiti complessi in vari settori; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte. Rispetto a ERNIE 4.0, offre prestazioni superiori."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Modello di linguaggio verticale sviluppato da Baidu, adatto per applicazioni come NPC nei giochi, dialoghi di assistenza clienti, e interpretazione di ruoli nei dialoghi, con uno stile di personaggio più distintivo e coerente, capacità di seguire le istruzioni più forte e prestazioni di inferenza superiori."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Modello di linguaggio leggero sviluppato da Baidu, che combina prestazioni eccellenti del modello con prestazioni di inferenza, con risultati migliori rispetto a ERNIE Lite, adatto per l'uso in schede di accelerazione AI a bassa potenza."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Modello di linguaggio ad alte prestazioni sviluppato da Baidu, lanciato nel 2024, con capacità generali eccellenti, adatto come modello di base per il fine-tuning, per gestire meglio le problematiche di scenari specifici, mantenendo al contempo prestazioni di inferenza eccezionali."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Modello di linguaggio ad alte prestazioni sviluppato da Baidu, lanciato nel 2024, con capacità generali eccellenti, risultati migliori rispetto a ERNIE Speed, adatto come modello di base per il fine-tuning, per gestire meglio le problematiche di scenari specifici, mantenendo al contempo prestazioni di inferenza eccezionali."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) è un modello innovativo, adatto per applicazioni in più settori e compiti complessi."
},
- "Max-32k": {
- "description": "Spark Max 32K è dotato di una grande capacità di elaborazione del contesto, con una comprensione e un ragionamento logico più potenti, supporta l'input di testo fino a 32K token, adatto per la lettura di documenti lunghi, domande e risposte su conoscenze private e altri scenari."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B è un potente modello linguistico visivo, supporta l'elaborazione multimodale di immagini e testo, in grado di riconoscere con precisione il contenuto delle immagini e generare descrizioni o risposte correlate."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B è un potente modello linguistico visivo, supporta l'elaborazione multimodale di immagini e testo, in grado di riconoscere con precisione il contenuto delle immagini e generare descrizioni o risposte correlate."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Eccellenti capacità di ragionamento visivo su immagini ad alta risoluzione, adatte per applicazioni di comprensione visiva."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Capacità avanzate di ragionamento visivo per applicazioni di agenti di comprensione visiva."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct è uno dei più recenti modelli linguistici di grandi dimensioni rilasciati da Alibaba Cloud. Questo modello da 72B ha capacità notevolmente migliorate in codifica e matematica. Il modello offre anche supporto multilingue, coprendo oltre 29 lingue, tra cui cinese e inglese. Ha mostrato miglioramenti significativi nel seguire istruzioni, comprendere dati strutturati e generare output strutturati (soprattutto JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct è uno dei più recenti modelli linguistici di grandi dimensioni rilasciati da Alibaba Cloud. Questo modello da 7B ha capacità notevolmente migliorate in codifica e matematica. Il modello offre anche supporto multilingue, coprendo oltre 29 lingue, tra cui cinese e inglese. Ha mostrato miglioramenti significativi nel seguire istruzioni, comprendere dati strutturati e generare output strutturati (soprattutto JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Modello di testo ottimizzato per le istruzioni di Llama 3.1, progettato per casi d'uso di dialogo multilingue, che si distingue in molti modelli di chat open source e chiusi in benchmark di settore comuni."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO è un modello altamente flessibile, progettato per offrire un'esperienza creativa eccezionale."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Modello di testo ottimizzato per le istruzioni di Llama 3.1, progettato per casi d'uso di dialogo multilingue, che si distingue in molti modelli di chat open source e chiusi in benchmark di settore comuni."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Modello di testo ottimizzato per le istruzioni di Llama 3.1, progettato per casi d'uso di dialogo multilingue, che si distingue in molti modelli di chat open source e chiusi in benchmark di settore comuni."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Modello di linguaggio di piccole dimensioni all'avanguardia, dotato di comprensione linguistica, eccellenti capacità di ragionamento e generazione di testo."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Modello di linguaggio di piccole dimensioni all'avanguardia, dotato di comprensione linguistica, eccellenti capacità di ragionamento e generazione di testo."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 è il modello di linguaggio open source multilingue più avanzato della serie Llama, che offre prestazioni paragonabili a un modello da 405B a un costo estremamente ridotto. Basato su una struttura Transformer e migliorato tramite fine-tuning supervisionato (SFT) e apprendimento rinforzato con feedback umano (RLHF) per aumentarne l'utilità e la sicurezza. La sua versione ottimizzata per le istruzioni è progettata per dialoghi multilingue, superando molti modelli di chat open source e chiusi in vari benchmark di settore. La data di conoscenza è dicembre 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "Nella serie di modelli MiniMax-01, abbiamo fatto un'innovazione audace: per la prima volta abbiamo implementato su larga scala un meccanismo di attenzione lineare, rendendo l'architettura Transformer tradizionale non più l'unica opzione. Questo modello ha un numero di parametri che raggiunge i 456 miliardi, con un'attivazione singola di 45,9 miliardi. Le prestazioni complessive del modello sono paragonabili a quelle dei migliori modelli internazionali, mentre è in grado di gestire in modo efficiente contesti globali lunghi fino a 4 milioni di token, 32 volte rispetto a GPT-4o e 20 volte rispetto a Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) è un modello di istruzioni ad alta precisione, adatto per calcoli complessi."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) offre output linguistici ottimizzati e possibilità di applicazione diversificate."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Aggiornamento del modello Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 ha dimostrato prestazioni eccezionali in una varietà di compiti visivi linguistici, tra cui comprensione di documenti e grafici, comprensione di testo in scena, OCR, risoluzione di problemi scientifici e matematici."
},
"Phi-3-medium-128k-instruct": {
"description": "Stesso modello Phi-3-medium, ma con una dimensione di contesto più grande per RAG o prompting a pochi colpi."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Un modello con 7 miliardi di parametri, dimostra una qualità migliore rispetto a Phi-3-mini, con un focus su dati densi di ragionamento di alta qualità."
},
- "Pro-128k": {
- "description": "Spark Pro-128K è dotato di capacità di elaborazione del contesto eccezionalmente grandi, in grado di gestire fino a 128K di informazioni contestuali, particolarmente adatto per contenuti lunghi che richiedono analisi complete e gestione di associazioni logiche a lungo termine, fornendo logica fluida e coerenza in comunicazioni testuali complesse e supporto per citazioni varie."
+ "Phi-3.5-mini-instruct": {
+ "description": "Versione aggiornata del modello Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Versione aggiornata del modello Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 ha dimostrato prestazioni eccezionali in una varietà di compiti visivi linguistici, tra cui comprensione di documenti e grafici, comprensione di testo in scena, OCR, risoluzione di problemi scientifici e matematici."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct è un modello linguistico di grandi dimensioni con fine-tuning per istruzioni nella serie Qwen2, con una dimensione di 1.5B parametri. Questo modello si basa sull'architettura Transformer, utilizzando funzioni di attivazione SwiGLU, bias QKV di attenzione e attenzione a query di gruppo. Ha dimostrato prestazioni eccellenti in comprensione linguistica, generazione, capacità multilingue, codifica, matematica e ragionamento in vari benchmark, superando la maggior parte dei modelli open source. Rispetto a Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct ha mostrato miglioramenti significativi nei test MMLU, HumanEval, GSM8K, C-Eval e IFEval, nonostante un numero di parametri leggermente inferiore."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct è un modello linguistico di grandi dimensioni con fine-tuning per istruzioni nella serie Qwen2, con una dimensione di 7B parametri. Questo modello si basa sull'architettura Transformer, utilizzando funzioni di attivazione SwiGLU, bias QKV di attenzione e attenzione a query di gruppo. È in grado di gestire input di grandi dimensioni. Ha dimostrato prestazioni eccellenti in comprensione linguistica, generazione, capacità multilingue, codifica, matematica e ragionamento in vari benchmark, superando la maggior parte dei modelli open source e mostrando competitività paragonabile a modelli proprietari in alcuni compiti. Qwen2-7B-Instruct ha mostrato miglioramenti significativi in vari test rispetto a Qwen1.5-7B-Chat."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL è l'ultima iterazione del modello Qwen-VL, che ha raggiunto prestazioni all'avanguardia nei benchmark di comprensione visiva."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct è uno dei più recenti modelli linguistici di grandi dimensioni rilasciati da Alibaba Cloud. Questo modello da 7B ha capacità notevolmente migliorate in codifica e matematica. Il modello offre anche supporto multilingue, coprendo oltre 29 lingue, tra cui cinese e inglese. Ha mostrato miglioramenti significativi nel seguire istruzioni, comprendere dati strutturati e generare output strutturati (soprattutto JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct è l'ultima versione della serie di modelli linguistici di grandi dimensioni specifici per il codice rilasciata da Alibaba Cloud. Questo modello, basato su Qwen2.5, ha migliorato significativamente le capacità di generazione, ragionamento e riparazione del codice grazie all'addestramento su 55 trilioni di token. Ha potenziato non solo le capacità di codifica, ma ha anche mantenuto i vantaggi nelle abilità matematiche e generali. Il modello fornisce una base più completa per applicazioni pratiche come agenti di codice."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat è la versione open source del modello pre-addestrato GLM-4 della serie sviluppata da Zhipu AI. Questo modello ha dimostrato prestazioni eccellenti in vari aspetti, tra cui semantica, matematica, ragionamento, codice e conoscenza. Oltre a supportare conversazioni multi-turno, GLM-4-9B-Chat offre anche funzionalità avanzate come navigazione web, esecuzione di codice, chiamate a strumenti personalizzati (Function Call) e ragionamento su testi lunghi. Il modello supporta 26 lingue, tra cui cinese, inglese, giapponese, coreano e tedesco. Ha mostrato prestazioni eccellenti in vari benchmark, come AlignBench-v2, MT-Bench, MMLU e C-Eval. Questo modello supporta una lunghezza di contesto massima di 128K, rendendolo adatto per ricerche accademiche e applicazioni commerciali."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 è un modello di inferenza guidato dall'apprendimento per rinforzo (RL) che affronta i problemi di ripetitività e leggibilità nel modello. Prima dell'RL, DeepSeek-R1 ha introdotto dati di cold start, ottimizzando ulteriormente le prestazioni di inferenza. Si comporta in modo comparabile a OpenAI-o1 in compiti matematici, di codifica e di inferenza, e migliora l'efficacia complessiva grazie a metodi di addestramento ben progettati."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 è un modello di linguaggio con 6710 miliardi di parametri, basato su un'architettura di esperti misti (MoE) che utilizza attenzione multilivello (MLA) e la strategia di bilanciamento del carico senza perdite ausiliarie, ottimizzando l'efficienza di inferenza e addestramento. Pre-addestrato su 14,8 trilioni di token di alta qualità e successivamente affinato tramite supervisione e apprendimento per rinforzo, DeepSeek-V3 supera altri modelli open source, avvicinandosi ai modelli chiusi di punta."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma è una delle serie di modelli open source leggeri e all'avanguardia sviluppati da Google. È un modello linguistico di grandi dimensioni con solo decoder, supporta l'inglese e offre pesi aperti, varianti pre-addestrate e varianti con fine-tuning per istruzioni. Il modello Gemma è adatto per vari compiti di generazione di testi, tra cui domande e risposte, riassunti e ragionamento. Questo modello da 9B è stato addestrato su 80 trilioni di token. La sua dimensione relativamente ridotta consente di implementarlo in ambienti con risorse limitate, come laptop, desktop o la propria infrastruttura cloud, rendendo così accessibili modelli AI all'avanguardia a un pubblico più ampio e promuovendo l'innovazione."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 è una famiglia di modelli linguistici di grandi dimensioni multilingue sviluppata da Meta, che include varianti pre-addestrate e con fine-tuning per istruzioni con dimensioni di 8B, 70B e 405B. Questo modello di fine-tuning per istruzioni da 8B è ottimizzato per scenari di dialogo multilingue e ha dimostrato prestazioni eccellenti in vari benchmark di settore. L'addestramento del modello ha utilizzato oltre 150 trilioni di token di dati pubblici e ha impiegato tecniche come il fine-tuning supervisionato e l'apprendimento per rinforzo basato su feedback umano per migliorare l'utilità e la sicurezza del modello. Llama 3.1 supporta la generazione di testi e di codice, con una data di scadenza delle conoscenze fissata a dicembre 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview è un modello di elaborazione del linguaggio naturale innovativo, in grado di gestire in modo efficiente compiti complessi di generazione di dialoghi e comprensione del contesto."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview è un modello di ricerca sviluppato dal team Qwen, focalizzato sulle capacità di inferenza visiva, con vantaggi unici nella comprensione di scenari complessi e nella risoluzione di problemi matematici legati alla visione."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Come versione beta di Qwen2, Qwen1.5 utilizza dati su larga scala per realizzare funzionalità di dialogo più precise."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ è il modello di inferenza della serie Qwen. Rispetto ai tradizionali modelli di ottimizzazione delle istruzioni, QwQ possiede capacità di pensiero e ragionamento, consentendo prestazioni significativamente migliorate nei compiti downstream, specialmente nella risoluzione di problemi complessi. QwQ-32B è un modello di inferenza di medie dimensioni, in grado di ottenere prestazioni competitive rispetto ai modelli di inferenza all'avanguardia (come DeepSeek-R1, o1-mini). Questo modello utilizza tecnologie come RoPE, SwiGLU, RMSNorm e Attention QKV bias, con una struttura di rete a 64 strati e 40 teste di attenzione Q (nel GQA, KV è 8)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) offre risposte rapide e capacità di dialogo naturale, adatto per ambienti multilingue."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview è l'ultimo modello di ricerca sperimentale di Qwen, focalizzato sul miglioramento delle capacità di ragionamento dell'IA. Esplorando meccanismi complessi come la mescolanza linguistica e il ragionamento ricorsivo, i principali vantaggi includono potenti capacità di analisi del ragionamento, abilità matematiche e di programmazione. Tuttavia, ci sono anche problemi di cambio linguistico, cicli di ragionamento, considerazioni di sicurezza e differenze in altre capacità."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct è un modello linguistico di grandi dimensioni con fine-tuning per istruzioni nella serie Qwen2, con una dimensione di 1.5B parametri. Questo modello si basa sull'architettura Transformer, utilizzando funzioni di attivazione SwiGLU, bias QKV di attenzione e attenzione a query di gruppo. Ha dimostrato prestazioni eccellenti in comprensione linguistica, generazione, capacità multilingue, codifica, matematica e ragionamento in vari benchmark, superando la maggior parte dei modelli open source. Rispetto a Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct ha mostrato miglioramenti significativi nei test MMLU, HumanEval, GSM8K, C-Eval e IFEval, nonostante un numero di parametri leggermente inferiore."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 è un modello di linguaggio universale avanzato, supportando vari tipi di istruzioni."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct è un modello linguistico di grandi dimensioni con fine-tuning per istruzioni nella serie Qwen2, con una dimensione di 72B parametri. Questo modello si basa sull'architettura Transformer, utilizzando funzioni di attivazione SwiGLU, bias QKV di attenzione e attenzione a query di gruppo. È in grado di gestire input di grandi dimensioni. Ha dimostrato prestazioni eccellenti in comprensione linguistica, generazione, capacità multilingue, codifica, matematica e ragionamento in vari benchmark, superando la maggior parte dei modelli open source e mostrando competitività paragonabile a modelli proprietari in alcuni compiti."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL è l'ultima iterazione del modello Qwen-VL, che ha raggiunto prestazioni all'avanguardia nei benchmark di comprensione visiva."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 è una nuova serie di modelli di linguaggio di grandi dimensioni, progettata per ottimizzare l'elaborazione di compiti istruzionali."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 è una nuova serie di modelli di linguaggio di grandi dimensioni, progettata per ottimizzare l'elaborazione di compiti istruzionali."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 è una nuova serie di modelli di linguaggio di grandi dimensioni, con capacità di comprensione e generazione superiori."
+ "description": "Un grande modello linguistico sviluppato dal team di Alibaba Cloud Tongyi Qianwen"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 è una nuova serie di modelli linguistici di grandi dimensioni, con una maggiore capacità di comprensione e generazione."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 è una nuova serie di modelli linguistici di grandi dimensioni, progettata per ottimizzare l'elaborazione dei compiti istruzionali."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 è una nuova serie di modelli di linguaggio di grandi dimensioni, progettata per ottimizzare l'elaborazione di compiti istruzionali."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 è una nuova serie di modelli linguistici di grandi dimensioni, progettata per ottimizzare l'elaborazione dei compiti istruzionali."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder si concentra sulla scrittura di codice."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math si concentra sulla risoluzione di problemi nel campo della matematica, fornendo risposte professionali a domande di alta difficoltà."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct è l'ultima versione della serie di modelli linguistici di grandi dimensioni specifici per il codice rilasciata da Alibaba Cloud. Questo modello, basato su Qwen2.5, ha migliorato significativamente le capacità di generazione, ragionamento e riparazione del codice grazie all'addestramento su 55 trilioni di token. Ha potenziato non solo le capacità di codifica, ma ha anche mantenuto i vantaggi nelle abilità matematiche e generali. Il modello fornisce una base più completa per applicazioni pratiche come agenti di codice."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 è l'ultima serie del modello Qwen, supporta un contesto di 128k, e rispetto ai modelli open source attualmente migliori, Qwen2-72B supera significativamente i modelli leader attuali in comprensione del linguaggio naturale, conoscenza, codice, matematica e capacità multilingue."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 è l'ultima serie del modello Qwen, in grado di superare i modelli open source ottimali di dimensioni simili e anche modelli di dimensioni maggiori. Qwen2 7B ha ottenuto vantaggi significativi in vari test, in particolare nella comprensione del codice e del cinese."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B è un potente modello di linguaggio visivo, supporta l'elaborazione multimodale di immagini e testo, in grado di riconoscere con precisione il contenuto delle immagini e generare descrizioni o risposte correlate."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct è un grande modello linguistico con 14 miliardi di parametri, con prestazioni eccellenti, ottimizzato per scenari in cinese e multilingue, supporta applicazioni di domande e risposte intelligenti, generazione di contenuti e altro."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct è un grande modello linguistico con 32 miliardi di parametri, con prestazioni equilibrate, ottimizzato per scenari in cinese e multilingue, supporta applicazioni di domande e risposte intelligenti, generazione di contenuti e altro."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct supporta un contesto di 16k, generando testi lunghi oltre 8K. Supporta chiamate di funzione e interazioni senza soluzione di continuità con sistemi esterni, aumentando notevolmente flessibilità e scalabilità. La conoscenza del modello è notevolmente aumentata e ha migliorato significativamente le capacità di codifica e matematica, con supporto per oltre 29 lingue."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct è un grande modello linguistico con 7 miliardi di parametri, supporta chiamate di funzione e interazioni senza soluzione di continuità con sistemi esterni, aumentando notevolmente flessibilità e scalabilità. Ottimizzato per scenari in cinese e multilingue, supporta applicazioni di domande e risposte intelligenti, generazione di contenuti e altro."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct è un modello di istruzioni per la programmazione basato su un pre-addestramento su larga scala, con potenti capacità di comprensione e generazione del codice, in grado di gestire in modo efficiente vari compiti di programmazione, particolarmente adatto per la scrittura intelligente di codice, la generazione di script automatizzati e la risoluzione di problemi di programmazione."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct è un grande modello linguistico progettato per la generazione di codice, la comprensione del codice e scenari di sviluppo efficienti, con una scala di 32 miliardi di parametri all'avanguardia nel settore, in grado di soddisfare esigenze di programmazione diversificate."
+ },
+ "SenseChat": {
+ "description": "Modello di base (V4), lunghezza del contesto di 4K, con potenti capacità generali."
+ },
+ "SenseChat-128K": {
+ "description": "Modello di base (V4), lunghezza del contesto di 128K, si distingue in compiti di comprensione e generazione di testi lunghi."
+ },
+ "SenseChat-32K": {
+ "description": "Modello di base (V4), lunghezza del contesto di 32K, applicabile in vari scenari."
+ },
+ "SenseChat-5": {
+ "description": "Modello dell'ultima versione (V5.5), lunghezza del contesto di 128K, con capacità significativamente migliorate in ragionamento matematico, conversazioni in inglese, seguire istruzioni e comprensione di testi lunghi, paragonabile a GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "È l'ultima versione basata su V5.5, con miglioramenti significativi rispetto alla versione precedente nelle capacità di base in cinese e inglese, chat, conoscenze scientifiche, conoscenze umanistiche, scrittura, logica matematica e controllo del numero di parole."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Lunghezza del contesto di 32K, supera GPT-4 nella comprensione delle conversazioni in cantonese, paragonabile a GPT-4 Turbo in vari ambiti come conoscenza, ragionamento, matematica e scrittura di codice."
+ },
+ "SenseChat-Character": {
+ "description": "Modello standard, lunghezza del contesto di 8K, alta velocità di risposta."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Modello avanzato, lunghezza del contesto di 32K, capacità complessivamente migliorate, supporta conversazioni in cinese/inglese."
+ },
+ "SenseChat-Turbo": {
+ "description": "Adatto per domande e risposte rapide, scenari di micro-ottimizzazione del modello."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "È l'ultima versione leggera del modello, raggiungendo oltre il 90% delle capacità del modello completo, riducendo significativamente i costi di inferenza."
+ },
+ "SenseChat-Vision": {
+ "description": "L'ultima versione del modello (V5.5) supporta l'input di più immagini, ottimizzando le capacità di base del modello, con notevoli miglioramenti nel riconoscimento delle proprietà degli oggetti, nelle relazioni spaziali, nel riconoscimento degli eventi, nella comprensione delle scene, nel riconoscimento delle emozioni, nel ragionamento logico e nella comprensione e generazione del testo."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Il modello di seconda generazione Skylark (Skylark2-lite) ha un'elevata velocità di risposta, adatto per scenari in cui sono richieste elevate prestazioni in tempo reale, attento ai costi e con requisiti di precisione del modello non elevati, con una lunghezza della finestra di contesto di 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Il modello di seconda generazione Skylark (Skylark2-pro) offre una maggiore precisione, adatto per scenari complessi di generazione di testi, come la scrittura di contenuti in ambito professionale, narrativa e traduzioni di alta qualità, con una lunghezza della finestra di contesto di 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Il modello di seconda generazione Skylark (Skylark2-pro) offre una maggiore precisione, adatto per scenari complessi di generazione di testi, come la scrittura di contenuti in ambito professionale, narrativa e traduzioni di alta qualità, con una lunghezza della finestra di contesto di 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Il modello di seconda generazione Skylark (Skylark2-pro-character) presenta eccellenti capacità di role-playing e chat, specializzandosi nel recitare diversi ruoli in base alle richieste dell'utente e nel portare avanti conversazioni naturali e fluide. È adatto per la creazione di chatbot, assistenti virtuali e customer service online, con elevate velocità di risposta."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Il modello di seconda generazione Skylark (Skylark2-pro-turbo-8k) è più veloce nell'inferenza e più economico, con una lunghezza della finestra di contesto di 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B è un modello open source della serie ChatGLM, sviluppato da Zhipu AI. Questo modello conserva le eccellenti caratteristiche dei modelli precedenti, come la fluidità del dialogo e la bassa soglia di implementazione, introducendo al contempo nuove funzionalità. Utilizza dati di addestramento più diversificati, un numero maggiore di passi di addestramento e strategie di addestramento più ragionevoli, dimostrando prestazioni eccellenti tra i modelli pre-addestrati sotto i 10B. ChatGLM3-6B supporta scenari complessi come conversazioni multi-turno, chiamate a strumenti, esecuzione di codice e compiti di agente. Oltre al modello di dialogo, sono stati rilasciati anche il modello di base ChatGLM-6B-Base e il modello di dialogo su testi lunghi ChatGLM3-6B-32K. Questo modello è completamente aperto per la ricerca accademica e consente anche un uso commerciale gratuito dopo la registrazione."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B è una versione open source, progettata per fornire un'esperienza di dialogo ottimizzata per applicazioni conversazionali."
},
+ "TeleAI/TeleChat2": {
+ "description": "Il grande modello TeleChat2 è un modello semantico generativo sviluppato autonomamente da China Telecom, che supporta funzioni come domande e risposte enciclopediche, generazione di codice e generazione di testi lunghi, fornendo servizi di consulenza dialogica agli utenti, in grado di interagire con gli utenti, rispondere a domande e assistere nella creazione, aiutando gli utenti a ottenere informazioni, conoscenze e ispirazione in modo efficiente e conveniente. Il modello ha mostrato prestazioni eccellenti in problemi di illusione, generazione di testi lunghi e comprensione logica."
+ },
+ "TeleAI/TeleMM": {
+ "description": "Il grande modello multimodale TeleMM è un modello di comprensione multimodale sviluppato autonomamente da China Telecom, in grado di gestire input di diverse modalità, come testo e immagini, supportando funzioni di comprensione delle immagini e analisi dei grafici, fornendo servizi di comprensione multimodale agli utenti. Il modello è in grado di interagire con gli utenti in modo multimodale, comprendere accuratamente il contenuto dell'input, rispondere a domande, assistere nella creazione e fornire in modo efficiente supporto informativo e ispirazione multimodale. Ha mostrato prestazioni eccellenti in compiti multimodali come percezione fine e ragionamento logico."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct è uno dei più recenti modelli linguistici di grandi dimensioni rilasciati da Alibaba Cloud. Questo modello da 72B ha capacità notevolmente migliorate in codifica e matematica. Il modello offre anche supporto multilingue, coprendo oltre 29 lingue, tra cui cinese e inglese. Ha mostrato miglioramenti significativi nel seguire istruzioni, comprendere dati strutturati e generare output strutturati (soprattutto JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, mantenendo le eccellenti capacità linguistiche generali della serie originale, ha notevolmente migliorato la logica matematica e le capacità di codifica attraverso un addestramento incrementale su 500 miliardi di token di alta qualità."
+ },
"abab5.5-chat": {
"description": "Focalizzato su scenari di produttività, supporta l'elaborazione di compiti complessi e la generazione di testo efficiente, adatto per applicazioni professionali."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Ottimizzato per scenari di dialogo con personaggi cinesi, offre capacità di generazione di dialoghi fluida e conforme alle espressioni cinesi."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Il modello open source di chiamata di funzione di Fireworks offre capacità di esecuzione di istruzioni eccezionali e caratteristiche personalizzabili."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2, l'ultima offerta di Fireworks, è un modello di chiamata di funzione ad alte prestazioni, sviluppato su Llama-3 e ottimizzato per scenari come chiamate di funzione, dialogo e seguimento di istruzioni."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b è un modello di linguaggio visivo in grado di ricevere input sia visivi che testuali, addestrato su dati di alta qualità, adatto per compiti multimodali."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 è un modello linguistico di grandi dimensioni all'avanguardia, ottimizzato tramite apprendimento rinforzato e dati di cold start, con prestazioni eccezionali nel ragionamento, nella matematica e nella programmazione."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Il modello di istruzioni Gemma 2 9B, basato sulla tecnologia Google precedente, è adatto per rispondere a domande, riassumere e generare testi in vari contesti."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Un potente modello linguistico Mixture-of-Experts (MoE) fornito da Deepseek, con un totale di 671B di parametri, attivando 37B di parametri per ogni token."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Il modello di istruzioni Llama 3 70B è ottimizzato per dialoghi multilingue e comprensione del linguaggio naturale, superando le prestazioni della maggior parte dei modelli concorrenti."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Il modello di istruzioni Llama 3 70B (versione HF) è allineato con i risultati dell'implementazione ufficiale, adatto per compiti di seguimento di istruzioni di alta qualità."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Il modello di istruzioni Llama 3 8B è ottimizzato per dialoghi e compiti multilingue, offrendo prestazioni eccellenti e alta efficienza."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Il modello di istruzioni Llama 3.1 8B è ottimizzato per dialoghi multilingue, in grado di superare la maggior parte dei modelli open e closed source su benchmark di settore comuni."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Modello di ragionamento visivo di Meta con 11 miliardi di parametri. Questo modello è ottimizzato per il riconoscimento visivo, il ragionamento visivo, la descrizione delle immagini e la risposta a domande generali riguardanti le immagini. Questo modello è in grado di comprendere dati visivi, come grafici e tabelle, e colmare il divario tra visione e linguaggio generando descrizioni testuali dei dettagli delle immagini."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Il modello di istruzioni Llama 3.2 3B è un modello multilingue leggero lanciato da Meta. Questo modello è progettato per migliorare l'efficienza, offrendo miglioramenti significativi in termini di latenza e costi rispetto a modelli più grandi. I casi d'uso esemplari di questo modello includono query e riscrittura di suggerimenti, nonché supporto alla scrittura."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Modello di ragionamento visivo di Meta con 90 miliardi di parametri. Questo modello è ottimizzato per il riconoscimento visivo, il ragionamento visivo, la descrizione delle immagini e la risposta a domande generali riguardanti le immagini. Questo modello è in grado di comprendere dati visivi, come grafici e tabelle, e colmare il divario tra visione e linguaggio generando descrizioni testuali dei dettagli delle immagini."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct è la versione aggiornata di dicembre di Llama 3.1 70B. Questo modello è stato migliorato rispetto a Llama 3.1 70B (rilasciato a luglio 2024), potenziando le capacità di chiamata degli strumenti, il supporto per testi multilingue, le abilità matematiche e di programmazione. Il modello raggiunge livelli di eccellenza nel ragionamento, nella matematica e nel rispetto delle istruzioni, offrendo prestazioni simili a quelle di 3.1 405B, con vantaggi significativi in termini di velocità e costi."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Modello con 24B di parametri, dotato di capacità all'avanguardia comparabili a modelli di dimensioni maggiori."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Il modello di istruzioni Mixtral MoE 8x22B, con parametri su larga scala e architettura multi-esperto, supporta in modo completo l'elaborazione efficiente di compiti complessi."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Il modello di istruzioni Mixtral MoE 8x7B, con architettura multi-esperto, offre un'elevata efficienza nel seguire e eseguire istruzioni."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Il modello di istruzioni Mixtral MoE 8x7B (versione HF) ha prestazioni coerenti con l'implementazione ufficiale, adatto per vari scenari di compiti efficienti."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "Il modello MythoMax L2 13B combina tecnologie di fusione innovative, specializzandosi in narrazione e interpretazione di ruoli."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Il modello di istruzioni Phi 3 Vision è un modello multimodale leggero, in grado di gestire informazioni visive e testuali complesse, con forti capacità di ragionamento."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "Il modello StarCoder 15.5B supporta compiti di programmazione avanzati, con capacità multilingue potenziate, adatto per la generazione e comprensione di codice complesso."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Il modello QwQ è un modello di ricerca sperimentale sviluppato dal team Qwen, focalizzato sul potenziamento delle capacità di ragionamento dell'IA."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "La versione 72B del modello Qwen-VL è il risultato dell'ultima iterazione di Alibaba, rappresentando quasi un anno di innovazione."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "Il modello StarCoder 7B è addestrato su oltre 80 linguaggi di programmazione, con eccellenti capacità di completamento del codice e comprensione del contesto."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 è una serie di modelli linguistici solo decoder sviluppata dal team Qwen di Alibaba Cloud. Questi modelli offrono dimensioni diverse, tra cui 0.5B, 1.5B, 3B, 7B, 14B, 32B e 72B, e ci sono varianti base e di istruzione."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct è l'ultima versione della serie di modelli linguistici di grandi dimensioni specifici per il codice rilasciata da Alibaba Cloud. Questo modello, basato su Qwen2.5, ha migliorato significativamente le capacità di generazione, ragionamento e riparazione del codice grazie all'addestramento su 55 trilioni di token. Ha potenziato non solo le capacità di codifica, ma ha anche mantenuto i vantaggi nelle abilità matematiche e generali. Il modello fornisce una base più completa per applicazioni pratiche come agenti di codice."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Il modello Yi-Large offre capacità eccezionali di elaborazione multilingue, utilizzabile per vari compiti di generazione e comprensione del linguaggio."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Un modello multilingue con 52 miliardi di parametri (12 miliardi attivi), offre una finestra di contesto lunga 256K, chiamata di funzione, output strutturato e generazione ancorata."
},
- "ai21-jamba-instruct": {
- "description": "Un modello LLM basato su Mamba di grado di produzione per ottenere prestazioni, qualità e efficienza dei costi di prim'ordine."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet ha elevato gli standard del settore, superando i modelli concorrenti e Claude 3 Opus, dimostrando prestazioni eccezionali in una vasta gamma di valutazioni, mantenendo la velocità e i costi dei nostri modelli di livello medio."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet ha elevato gli standard del settore, superando le prestazioni dei modelli concorrenti e di Claude 3 Opus, dimostrando eccellenza in una vasta gamma di valutazioni, mantenendo al contempo la velocità e i costi dei nostri modelli di livello medio."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku è il modello più veloce e compatto di Anthropic, offrendo una velocità di risposta quasi istantanea. Può rispondere rapidamente a query e richieste semplici. I clienti saranno in grado di costruire un'esperienza AI senza soluzione di continuità che imita l'interazione umana. Claude 3 Haiku può gestire immagini e restituire output testuali, con una finestra di contesto di 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus è il modello più potente di Anthropic per gestire compiti altamente complessi. Eccelle in prestazioni, intelligenza, fluidità e comprensione."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku è il modello di nuova generazione più veloce di Anthropic. Rispetto a Claude 3 Haiku, Claude 3.5 Haiku ha migliorato le proprie capacità e ha superato il modello più grande della generazione precedente, Claude 3 Opus, in molti test di intelligenza."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet offre capacità superiori rispetto a Opus e una velocità maggiore rispetto a Sonnet, mantenendo lo stesso prezzo di Sonnet. Sonnet è particolarmente abile in programmazione, scienza dei dati, elaborazione visiva e compiti di agenzia."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet è il modello più intelligente di Anthropic fino ad oggi ed è il primo modello di ragionamento ibrido sul mercato. Claude 3.7 Sonnet può generare risposte quasi istantanee o pensieri prolungati e graduali, consentendo agli utenti di vedere chiaramente questi processi. Sonnet è particolarmente abile nella programmazione, nella scienza dei dati, nell'elaborazione visiva e nei compiti di agenzia."
+ },
"aya": {
"description": "Aya 23 è un modello multilingue lanciato da Cohere, supporta 23 lingue, facilitando applicazioni linguistiche diversificate."
},
"aya:35b": {
"description": "Aya 23 è un modello multilingue lanciato da Cohere, supporta 23 lingue, facilitando applicazioni linguistiche diversificate."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B è un modello di linguaggio open source sviluppato da Baichuan Intelligence, con 13 miliardi di parametri, che ha ottenuto i migliori risultati nella sua categoria in benchmark autorevoli sia in cinese che in inglese."
+ },
"charglm-3": {
"description": "CharGLM-3 è progettato per il gioco di ruolo e la compagnia emotiva, supporta una memoria multi-turno ultra-lunga e dialoghi personalizzati, con ampie applicazioni."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 offre progressi nelle capacità chiave per le aziende, inclusi contesti leader del settore fino a 200K token, riduzione significativa della frequenza di allucinazioni del modello, suggerimenti di sistema e una nuova funzionalità di test: chiamate di strumenti."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku è il modello di prossima generazione più veloce di Anthropic. Rispetto a Claude 3 Haiku, Claude 3.5 Haiku ha migliorato le proprie capacità in vari ambiti e ha superato il modello di generazione precedente, Claude 3 Opus, in molti test di intelligenza."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet offre capacità superiori a Opus e velocità più elevate rispetto a Sonnet, mantenendo lo stesso prezzo. Sonnet è particolarmente abile in programmazione, scienza dei dati, elaborazione visiva e compiti di agenti."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet offre capacità superiori a Opus e velocità maggiore rispetto a Sonnet, mantenendo lo stesso prezzo di Sonnet. Sonnet è particolarmente abile nella programmazione, nella scienza dei dati, nell'elaborazione visiva e nei compiti di agenzia."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet è il modello più recente di Anthropic, con prestazioni all'avanguardia in una vasta gamma di valutazioni, superando i modelli concorrenti e Claude 3.5 Sonnet, dimostrando eccellenza in una vasta gamma di valutazioni, mantenendo al contempo la velocità e i costi dei nostri modelli di livello medio."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku è il modello più veloce e compatto di Anthropic, progettato per risposte quasi istantanee. Ha prestazioni di orientamento rapide e accurate."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet offre un equilibrio ideale tra intelligenza e velocità per i carichi di lavoro aziendali. Fornisce la massima utilità a un prezzo inferiore, affidabile e adatto per distribuzioni su larga scala."
},
- "claude-instant-1.2": {
- "description": "Il modello di Anthropic è progettato per generazione di testi a bassa latenza e alta capacità, supportando la generazione di centinaia di pagine di testo."
- },
"codegeex-4": {
"description": "CodeGeeX-4 è un potente assistente di programmazione AI, supporta domande intelligenti e completamento del codice in vari linguaggi di programmazione, migliorando l'efficienza dello sviluppo."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B è un modello di generazione di codice multilingue, supporta funzionalità complete tra cui completamento e generazione di codice, interprete di codice, ricerca in rete, chiamate di funzione e domande e risposte sul codice a livello di repository, coprendo vari scenari di sviluppo software. È un modello di generazione di codice di punta con meno di 10B di parametri."
+ },
"codegemma": {
"description": "CodeGemma è un modello linguistico leggero dedicato a vari compiti di programmazione, supporta iterazioni rapide e integrazione."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama è un LLM focalizzato sulla generazione e discussione di codice, combinando un ampio supporto per i linguaggi di programmazione, adatto per ambienti di sviluppo."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama è un LLM focalizzato sulla generazione e discussione di codice, con un ampio supporto per diversi linguaggi di programmazione, adatto per ambienti di sviluppo."
+ },
"codellama:13b": {
"description": "Code Llama è un LLM focalizzato sulla generazione e discussione di codice, combinando un ampio supporto per i linguaggi di programmazione, adatto per ambienti di sviluppo."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ è un modello di linguaggio di grandi dimensioni ad alte prestazioni, progettato per scenari aziendali reali e applicazioni complesse."
},
+ "dall-e-2": {
+ "description": "Seconda generazione del modello DALL·E, supporta la generazione di immagini più realistiche e accurate, con una risoluzione quattro volte superiore rispetto alla prima generazione."
+ },
+ "dall-e-3": {
+ "description": "L'ultimo modello DALL·E, rilasciato a novembre 2023. Supporta la generazione di immagini più realistiche e accurate, con una maggiore capacità di dettaglio."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct offre capacità di elaborazione di istruzioni altamente affidabili, supportando applicazioni in vari settori."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 è un modello di inferenza guidato da apprendimento rinforzato (RL) che affronta i problemi di ripetitività e leggibilità nel modello. Prima dell'RL, DeepSeek-R1 ha introdotto dati di cold start, ottimizzando ulteriormente le prestazioni di inferenza. Si comporta in modo comparabile a OpenAI-o1 in compiti matematici, di codifica e di inferenza, e migliora l'efficacia complessiva attraverso metodi di addestramento accuratamente progettati."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "Il modello di distillazione DeepSeek-R1 ottimizza le prestazioni di inferenza attraverso l'apprendimento rinforzato e dati di avvio a freddo, aggiornando il benchmark multi-task del modello open source."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B è un modello di distillazione sviluppato sulla base di Llama-3.1-8B. Questo modello è stato messo a punto utilizzando campioni generati da DeepSeek-R1, mostrando eccellenti capacità di inferenza. Ha ottenuto buoni risultati in vari test di benchmark, raggiungendo un'accuratezza dell'89,1% in MATH-500, una percentuale di passaggio del 50,4% in AIME 2024 e un punteggio di 1205 su CodeForces, dimostrando forti capacità matematiche e di programmazione come modello di dimensioni 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Il modello di distillazione DeepSeek-R1 ottimizza le prestazioni di inferenza attraverso l'apprendimento rinforzato e dati di avvio a freddo, aggiornando il benchmark multi-task del modello open source."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Il modello di distillazione DeepSeek-R1 ottimizza le prestazioni di inferenza attraverso l'apprendimento rinforzato e dati di avvio a freddo, aggiornando il benchmark multi-task del modello open source."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B è un modello ottenuto tramite distillazione della conoscenza basato su Qwen2.5-32B. Questo modello è stato messo a punto utilizzando 800.000 campioni selezionati generati da DeepSeek-R1, mostrando prestazioni eccezionali in vari campi come matematica, programmazione e ragionamento. Ha ottenuto risultati eccellenti in vari test di benchmark, raggiungendo un'accuratezza del 94,3% in MATH-500, dimostrando una forte capacità di ragionamento matematico."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B è un modello ottenuto tramite distillazione della conoscenza basato su Qwen2.5-Math-7B. Questo modello è stato messo a punto utilizzando 800.000 campioni selezionati generati da DeepSeek-R1, mostrando eccellenti capacità di inferenza. Ha ottenuto risultati eccezionali in vari test di benchmark, raggiungendo un'accuratezza del 92,8% in MATH-500, una percentuale di passaggio del 55,5% in AIME 2024 e un punteggio di 1189 su CodeForces, dimostrando forti capacità matematiche e di programmazione come modello di dimensioni 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 combina le eccellenti caratteristiche delle versioni precedenti, migliorando le capacità generali e di codifica."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 è un modello linguistico a esperti misti (MoE) con 6710 miliardi di parametri, che utilizza attenzione latente multi-testa (MLA) e architettura DeepSeekMoE, combinando strategie di bilanciamento del carico senza perdite ausiliarie per ottimizzare l'efficienza di inferenza e addestramento. Pre-addestrato su 14,8 trilioni di token di alta qualità e successivamente affinato supervisionato e tramite apprendimento rinforzato, DeepSeek-V3 supera le prestazioni di altri modelli open source, avvicinandosi ai modelli closed source leader."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B è un modello avanzato addestrato per dialoghi ad alta complessità."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "LLM altamente efficiente, specializzato in ragionamento, matematica e programmazione."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 è un modello linguistico visivo a esperti misti (MoE) sviluppato sulla base di DeepSeekMoE-27B, che utilizza un'architettura MoE con attivazione sparsa, raggiungendo prestazioni eccezionali attivando solo 4,5 miliardi di parametri. Questo modello eccelle in vari compiti, tra cui domande visive, riconoscimento ottico dei caratteri, comprensione di documenti/tabelle/grafici e localizzazione visiva."
+ },
"deepseek-chat": {
"description": "Un nuovo modello open source che integra capacità generali e di codifica, mantenendo non solo le capacità conversazionali generali del modello Chat originale, ma anche la potente capacità di elaborazione del codice del modello Coder, allineandosi meglio alle preferenze umane. Inoltre, DeepSeek-V2.5 ha ottenuto notevoli miglioramenti in vari aspetti, come i compiti di scrittura e il rispetto delle istruzioni."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B è un modello di linguaggio per codice, addestrato su 20 trilioni di dati, di cui l'87% è codice e il 13% è in cinese e inglese. Il modello introduce una dimensione della finestra di 16K e compiti di completamento, fornendo funzionalità di completamento del codice e riempimento di frammenti a livello di progetto."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 è un modello di codice open source di esperti misti, eccelle nei compiti di codice, paragonabile a GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 è un modello di codice open source di esperti misti, eccelle nei compiti di codice, paragonabile a GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 è un modello di inferenza guidato da apprendimento rinforzato (RL) che affronta i problemi di ripetitività e leggibilità nel modello. Prima dell'RL, DeepSeek-R1 ha introdotto dati di cold start, ottimizzando ulteriormente le prestazioni di inferenza. Si comporta in modo comparabile a OpenAI-o1 in compiti matematici, di codifica e di inferenza, e migliora l'efficacia complessiva attraverso metodi di addestramento accuratamente progettati."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - il modello più grande e intelligente del pacchetto DeepSeek - è stato distillato nell'architettura Llama 70B. Basato su test di benchmark e valutazioni umane, questo modello è più intelligente del Llama 70B originale, mostrando prestazioni eccezionali in compiti che richiedono precisione matematica e fattuale."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Il modello della serie DeepSeek-R1-Distill è stato ottenuto tramite la tecnologia di distillazione della conoscenza, ottimizzando i campioni generati da DeepSeek-R1 su modelli open source come Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Il modello della serie DeepSeek-R1-Distill è stato ottenuto tramite la tecnologia di distillazione della conoscenza, ottimizzando i campioni generati da DeepSeek-R1 su modelli open source come Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Il modello della serie DeepSeek-R1-Distill è stato ottenuto tramite la tecnologia di distillazione della conoscenza, ottimizzando i campioni generati da DeepSeek-R1 su modelli open source come Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Il modello della serie DeepSeek-R1-Distill è stato ottenuto tramite la tecnologia di distillazione della conoscenza, ottimizzando i campioni generati da DeepSeek-R1 su modelli open source come Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Il modello della serie DeepSeek-R1-Distill è stato ottenuto tramite la tecnologia di distillazione della conoscenza, ottimizzando i campioni generati da DeepSeek-R1 su modelli open source come Qwen e Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "Modello di ragionamento lanciato da DeepSeek. Prima di fornire la risposta finale, il modello genera una catena di pensiero per migliorare l'accuratezza della risposta finale."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 è un modello di linguaggio Mixture-of-Experts efficiente, adatto per esigenze di elaborazione economica."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B è il modello di codice progettato di DeepSeek, offre potenti capacità di generazione di codice."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 è un modello MoE sviluppato internamente da Hangzhou DeepSeek Artificial Intelligence Technology Research Co., Ltd., con risultati eccezionali in molteplici valutazioni, posizionandosi al primo posto tra i modelli open source nelle classifiche principali. Rispetto al modello V2.5, la velocità di generazione è aumentata di 3 volte, offrendo un'esperienza utente più rapida e fluida."
+ },
"deepseek/deepseek-chat": {
"description": "Un nuovo modello open source che integra capacità generali e di codice, mantenendo non solo le capacità di dialogo generali del modello Chat originale e la potente capacità di elaborazione del codice del modello Coder, ma allineandosi anche meglio alle preferenze umane. Inoltre, DeepSeek-V2.5 ha ottenuto notevoli miglioramenti in vari aspetti, come compiti di scrittura e seguire istruzioni."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 ha notevolmente migliorato le capacità di ragionamento del modello con pochissimi dati etichettati. Prima di fornire la risposta finale, il modello genera una catena di pensiero per migliorare l'accuratezza della risposta finale."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B è un grande modello di linguaggio basato su Llama3.3 70B, che utilizza il fine-tuning dell'output di DeepSeek R1 per raggiungere prestazioni competitive paragonabili a quelle dei modelli all'avanguardia di grandi dimensioni."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B è un modello di linguaggio distillato basato su Llama-3.1-8B-Instruct, addestrato utilizzando l'output di DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B è un modello di linguaggio distillato basato su Qwen 2.5 14B, addestrato utilizzando l'output di DeepSeek R1. Questo modello ha superato OpenAI's o1-mini in diversi benchmark, raggiungendo risultati all'avanguardia per i modelli densi. Ecco alcuni risultati dei benchmark:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nQuesto modello, attraverso il fine-tuning dell'output di DeepSeek R1, ha dimostrato prestazioni competitive paragonabili a modelli all'avanguardia di dimensioni maggiori."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B è un modello di linguaggio distillato basato su Qwen 2.5 32B, addestrato utilizzando l'output di DeepSeek R1. Questo modello ha superato OpenAI's o1-mini in diversi benchmark, raggiungendo risultati all'avanguardia per i modelli densi. Ecco alcuni risultati dei benchmark:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nQuesto modello, attraverso il fine-tuning dell'output di DeepSeek R1, ha dimostrato prestazioni competitive paragonabili a modelli all'avanguardia di dimensioni maggiori."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 è l'ultimo modello open source rilasciato dal team di DeepSeek, con prestazioni di inferenza eccezionali, in particolare nei compiti di matematica, programmazione e ragionamento, raggiungendo livelli comparabili a quelli del modello o1 di OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 ha notevolmente migliorato le capacità di ragionamento del modello con pochissimi dati etichettati. Prima di fornire la risposta finale, il modello genera una catena di pensiero per migliorare l'accuratezza della risposta finale."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 ha realizzato un significativo progresso nella velocità di inferenza rispetto ai modelli precedenti. Si posiziona al primo posto tra i modelli open source e può competere con i modelli closed source più avanzati al mondo. DeepSeek-V3 utilizza l'architettura Multi-Head Latent Attention (MLA) e DeepSeekMoE, che sono state ampiamente validate in DeepSeek-V2. Inoltre, DeepSeek-V3 ha introdotto una strategia ausiliaria senza perdita per il bilanciamento del carico e ha stabilito obiettivi di addestramento per la previsione multi-etichetta per ottenere prestazioni superiori."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 ha realizzato un significativo progresso nella velocità di inferenza rispetto ai modelli precedenti. Si posiziona al primo posto tra i modelli open source e può competere con i modelli closed source più avanzati al mondo. DeepSeek-V3 utilizza l'architettura Multi-Head Latent Attention (MLA) e DeepSeekMoE, che sono state ampiamente validate in DeepSeek-V2. Inoltre, DeepSeek-V3 ha introdotto una strategia ausiliaria senza perdita per il bilanciamento del carico e ha stabilito obiettivi di addestramento per la previsione multi-etichetta per ottenere prestazioni superiori."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite è un modello leggero di nuova generazione, con una velocità di risposta eccezionale, raggiungendo standard di livello mondiale sia in termini di prestazioni che di latenza."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k è una versione completamente aggiornata di Doubao-1.5-Pro, con un miglioramento complessivo delle prestazioni del 10%. Supporta il ragionamento con una finestra di contesto di 256k e una lunghezza di output massima di 12k token. Maggiore prestazioni, finestra più ampia e un eccellente rapporto qualità-prezzo, adatto a una gamma più ampia di scenari applicativi."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro è un modello di nuova generazione, con prestazioni completamente aggiornate, eccellente in conoscenza, codice, ragionamento e altro."
+ },
"emohaa": {
"description": "Emohaa è un modello psicologico, con capacità di consulenza professionale, aiuta gli utenti a comprendere i problemi emotivi."
},
+ "ernie-3.5-128k": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, coprendo un'enorme quantità di dati in cinese e inglese, con forti capacità generali, in grado di soddisfare la maggior parte delle esigenze di domande e risposte, generazione creativa e scenari di applicazione di plugin; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ernie-3.5-8k": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, coprendo un'enorme quantità di dati in cinese e inglese, con forti capacità generali, in grado di soddisfare la maggior parte delle esigenze di domande e risposte, generazione creativa e scenari di applicazione di plugin; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, coprendo un'enorme quantità di dati in cinese e inglese, con forti capacità generali, in grado di soddisfare la maggior parte delle esigenze di domande e risposte, generazione creativa e scenari di applicazione di plugin; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, con un aggiornamento completo delle capacità rispetto a ERNIE 3.5, ampiamente applicabile a scenari di compiti complessi in vari campi; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, con un aggiornamento completo delle capacità rispetto a ERNIE 3.5, ampiamente applicabile a scenari di compiti complessi in vari campi; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, con prestazioni complessive eccezionali, ampiamente applicabile a scenari di compiti complessi in vari campi; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte. Rispetto a ERNIE 4.0, offre prestazioni migliori."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, con prestazioni complessive eccezionali, ampiamente applicabile a scenari di compiti complessi in vari campi; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte. Rispetto a ERNIE 4.0, offre prestazioni migliori."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Il modello di linguaggio di grandi dimensioni di punta sviluppato internamente da Baidu, con prestazioni complessive eccezionali, ampiamente applicabile a scenari di compiti complessi in vari campi; supporta l'integrazione automatica con il plugin di ricerca di Baidu, garantendo l'aggiornamento delle informazioni nelle risposte. Rispetto a ERNIE 4.0, offre prestazioni migliori."
+ },
+ "ernie-char-8k": {
+ "description": "Un modello di linguaggio di grandi dimensioni sviluppato internamente da Baidu, adatto per scenari di applicazione come NPC nei giochi, dialoghi di assistenza clienti e interpretazione di ruoli nei dialoghi, con uno stile di personaggio più distintivo e coerente, capacità di seguire istruzioni più forti e prestazioni di inferenza migliori."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Un modello di linguaggio di grandi dimensioni sviluppato internamente da Baidu, adatto per scenari di applicazione come NPC nei giochi, dialoghi di assistenza clienti e interpretazione di ruoli nei dialoghi, con uno stile di personaggio più distintivo e coerente, capacità di seguire istruzioni più forti e prestazioni di inferenza migliori."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite è un modello di linguaggio di grandi dimensioni sviluppato internamente da Baidu, che bilancia prestazioni eccellenti del modello e prestazioni di inferenza, adatto per l'uso con schede di accelerazione AI a bassa potenza."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Un modello di linguaggio di grandi dimensioni leggero sviluppato internamente da Baidu, che bilancia prestazioni eccellenti del modello e prestazioni di inferenza, con risultati migliori rispetto a ERNIE Lite, adatto per l'uso con schede di accelerazione AI a bassa potenza."
+ },
+ "ernie-novel-8k": {
+ "description": "Un modello di linguaggio di grandi dimensioni sviluppato internamente da Baidu, con un evidente vantaggio nella capacità di continuare romanzi, utilizzabile anche in scenari come cortometraggi e film."
+ },
+ "ernie-speed-128k": {
+ "description": "Il modello di linguaggio di grandi dimensioni ad alte prestazioni sviluppato internamente da Baidu, rilasciato nel 2024, con capacità generali eccellenti, adatto come modello di base per la messa a punto, per affrontare meglio i problemi specifici, mantenendo eccellenti prestazioni di inferenza."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Il modello di linguaggio di grandi dimensioni ad alte prestazioni sviluppato internamente da Baidu, rilasciato nel 2024, con capacità generali eccellenti, con risultati migliori rispetto a ERNIE Speed, adatto come modello di base per la messa a punto, per affrontare meglio i problemi specifici, mantenendo eccellenti prestazioni di inferenza."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny è un modello di linguaggio di grandi dimensioni ad alte prestazioni sviluppato internamente da Baidu, con i costi di distribuzione e messa a punto più bassi della serie Wencin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) offre prestazioni stabili e ottimizzabili, è la scelta ideale per soluzioni a compiti complessi."
},
@@ -329,14 +791,17 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro è il modello AI ad alte prestazioni di Google, progettato per l'espansione su una vasta gamma di compiti."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash è il più recente modello AI multimodale di Google, dotato di capacità di elaborazione rapida, supporta input di testo, immagini e video, ed è adatto per un'efficiente scalabilità in vari compiti."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 è un modello multimodale efficiente, supporta l'espansione per applicazioni ampie."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 è un modello multimodale altamente efficiente, che supporta un'ampia gamma di applicazioni."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 è progettato per gestire scenari di compiti su larga scala, offrendo una velocità di elaborazione senza pari."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B è un modello multimodale altamente efficiente, che supporta un'ampia gamma di applicazioni."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 è il modello sperimentale più recente, con miglioramenti significativi nelle prestazioni sia nei casi d'uso testuali che multimodali."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002 è il modello più recente pronto per la produzione, che offre output di qualità superiore, con miglioramenti significativi in particolare in matematica, contesti lunghi e compiti visivi."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 offre eccellenti capacità di elaborazione multimodale, fornendo maggiore flessibilità per lo sviluppo delle applicazioni."
+ "description": "Gemini 1.5 Pro 0801 offre eccellenti capacità di elaborazione multimodale, offrendo maggiore flessibilità nello sviluppo di applicazioni."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 combina le più recenti tecnologie ottimizzate, offrendo una capacità di elaborazione dei dati multimodali più efficiente."
+ "description": "Gemini 1.5 Pro 0827 integra le tecnologie di ottimizzazione più recenti, offrendo capacità di elaborazione dei dati multimodali più efficienti."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro supporta fino a 2 milioni di token, è la scelta ideale per modelli multimodali di medie dimensioni, adatta a un supporto multifunzionale per compiti complessi."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash offre funzionalità e miglioramenti di nuova generazione, tra cui velocità eccezionale, utilizzo di strumenti nativi, generazione multimodale e una finestra di contesto di 1M token."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash offre funzionalità e miglioramenti di nuova generazione, tra cui velocità eccezionale, utilizzo di strumenti nativi, generazione multimodale e una finestra di contesto di 1M token."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash è una variante del modello Flash, ottimizzata per obiettivi come il rapporto costo-efficacia e la bassa latenza."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash è una variante del modello Flash, ottimizzata per obiettivi come il rapporto costo-efficacia e la bassa latenza."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Un modello Gemini 2.0 Flash ottimizzato per obiettivi di costo-efficacia e bassa latenza."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp è il più recente modello AI multimodale sperimentale di Google, dotato di caratteristiche di nuova generazione, velocità eccezionale, chiamate a strumenti nativi e generazione multimodale."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp è il più recente modello AI multimodale sperimentale di Google, dotato di caratteristiche di nuova generazione, velocità eccezionale, chiamate a strumenti nativi e generazione multimodale."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental è il più recente modello AI multimodale sperimentale di Google, con un miglioramento della qualità rispetto alle versioni precedenti, in particolare per quanto riguarda la conoscenza del mondo, il codice e i contesti lunghi."
+ },
"gemma-7b-it": {
"description": "Gemma 7B è adatto per l'elaborazione di compiti di piccole e medie dimensioni, combinando efficienza dei costi."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 è un modello efficiente lanciato da Google, coprendo una vasta gamma di scenari applicativi, da applicazioni di piccole dimensioni a elaborazioni di dati complesse."
},
- "general": {
- "description": "Spark Lite è un modello linguistico di grandi dimensioni leggero, con latenza estremamente bassa e capacità di elaborazione efficiente, completamente gratuito e aperto, supportando funzionalità di ricerca online in tempo reale. La sua caratteristica di risposta rapida lo rende eccellente per applicazioni di inferenza su dispositivi a bassa potenza e per il fine-tuning del modello, offrendo un ottimo rapporto costo-efficacia e un'esperienza intelligente, in particolare in scenari di domande e risposte, generazione di contenuti e ricerca."
- },
"generalv3": {
"description": "Spark Pro è un modello linguistico di grandi dimensioni ad alte prestazioni, ottimizzato per settori professionali, focalizzandosi su matematica, programmazione, medicina, educazione e altro, supportando la ricerca online e plugin integrati per meteo, data e altro. Il modello ottimizzato mostra prestazioni eccellenti e alta efficienza in domande e risposte complesse, comprensione del linguaggio e creazione di testi di alto livello, rendendolo una scelta ideale per scenari di applicazione professionale."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 è l'ultima versione del modello, progettata per compiti altamente complessi e diversificati, con prestazioni eccezionali."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat mostra elevate prestazioni in vari aspetti come semantica, matematica, ragionamento, codice e conoscenza. Ha anche la capacità di navigare in rete, eseguire codice, chiamare strumenti personalizzati e inferire testi lunghi. Supporta 26 lingue, tra cui giapponese, coreano e tedesco."
+ },
"glm-4-air": {
"description": "GLM-4-Air è una versione economica, con prestazioni simili a GLM-4, che offre velocità elevate a un prezzo accessibile."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash è l'ideale per compiti semplici, con la massima velocità e il prezzo più conveniente."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX è una versione potenziata di Flash, con una velocità di inferenza super veloce."
+ },
"glm-4-long": {
"description": "GLM-4-Long supporta input di testo ultra-lunghi, adatto per compiti di memoria e gestione di documenti su larga scala."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V offre potenti capacità di comprensione e ragionamento visivo, supportando vari compiti visivi."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash si concentra sulla comprensione efficiente di un'unica immagine, adatta a scenari di analisi rapida delle immagini, come l'analisi delle immagini in tempo reale o l'elaborazione di immagini in batch."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus ha la capacità di comprendere contenuti video e più immagini, adatto per compiti multimodali."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 offre capacità di elaborazione multimodale ottimizzate, adatte a vari scenari di compiti complessi."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview possiede potenti capacità di ragionamento complesso, eccellendo nei campi del ragionamento logico, della matematica e della programmazione."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 combina le più recenti tecnologie di ottimizzazione, offrendo capacità di elaborazione dei dati multimodali più efficienti."
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash offre funzionalità e miglioramenti di nuova generazione, tra cui velocità eccezionale, utilizzo di strumenti nativi, generazione multimodale e una finestra di contesto di 1M token."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental è il più recente modello AI multimodale sperimentale di Google, con un miglioramento della qualità rispetto alle versioni precedenti, in particolare per quanto riguarda la conoscenza del mondo, il codice e i contesti lunghi."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash offre capacità di elaborazione multimodale ottimizzate, adatte a vari scenari di compiti complessi."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro combina le più recenti tecnologie di ottimizzazione, offrendo una capacità di elaborazione dei dati multimodali più efficiente."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 è un modello efficiente lanciato da Google, coprendo una varietà di scenari applicativi, dalle piccole applicazioni all'elaborazione di dati complessi."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 continua il concetto di design leggero ed efficiente."
},
+ "google/gemma-2-2b-it": {
+ "description": "Modello di ottimizzazione delle istruzioni leggero di Google"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 è un modello efficiente lanciato da Google, coprendo una varietà di scenari applicativi, dalle piccole applicazioni all'elaborazione di dati complessi."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 è una serie di modelli di testo open source leggeri di Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, adatto a una varietà di compiti di generazione e comprensione del testo, attualmente punta a gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo è un modello efficiente fornito da OpenAI, adatto per chat e generazione di testo, che supporta chiamate di funzione parallele."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k è un modello di generazione di testo ad alta capacità, adatto per compiti complessi."
+ },
"gpt-4": {
"description": "GPT-4 offre una finestra di contesto più ampia, in grado di gestire input testuali più lunghi, adatta a scenari che richiedono un'integrazione ampia delle informazioni e analisi dei dati."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "L'ultimo modello GPT-4 Turbo ha funzionalità visive. Ora, le richieste visive possono essere effettuate utilizzando il formato JSON e le chiamate di funzione. GPT-4 Turbo è una versione potenziata che offre supporto economico per compiti multimodali. Trova un equilibrio tra accuratezza ed efficienza, adatta a scenari di applicazione che richiedono interazioni in tempo reale."
},
- "gpt-4-1106-vision-preview": {
- "description": "L'ultimo modello GPT-4 Turbo ha funzionalità visive. Ora, le richieste visive possono essere effettuate utilizzando il formato JSON e le chiamate di funzione. GPT-4 Turbo è una versione potenziata che offre supporto economico per compiti multimodali. Trova un equilibrio tra accuratezza ed efficienza, adatta a scenari di applicazione che richiedono interazioni in tempo reale."
- },
"gpt-4-32k": {
"description": "GPT-4 offre una finestra di contesto più ampia, in grado di gestire input testuali più lunghi, adatta a scenari che richiedono un'integrazione ampia delle informazioni e analisi dei dati."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "L'ultimo modello GPT-4 Turbo ha funzionalità visive. Ora, le richieste visive possono essere effettuate utilizzando il formato JSON e le chiamate di funzione. GPT-4 Turbo è una versione potenziata che offre supporto economico per compiti multimodali. Trova un equilibrio tra accuratezza ed efficienza, adatta a scenari di applicazione che richiedono interazioni in tempo reale."
},
+ "gpt-4.5-preview": {
+ "description": "Anteprima di ricerca di GPT-4.5, il nostro modello GPT più grande e potente fino ad oggi. Possiede una vasta conoscenza del mondo e comprende meglio le intenzioni degli utenti, eccellendo in compiti creativi e nella pianificazione autonoma. GPT-4.5 accetta input testuali e visivi e genera output testuali (inclusi output strutturati). Supporta funzionalità chiave per gli sviluppatori, come chiamate di funzione, API in batch e output in streaming. GPT-4.5 si distingue particolarmente in compiti che richiedono pensiero creativo, aperto e dialogo (come scrittura, apprendimento o esplorazione di nuove idee). La data di scadenza delle conoscenze è ottobre 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o è un modello dinamico, aggiornato in tempo reale per mantenere la versione più recente. Combina una potente comprensione e generazione del linguaggio, adatta a scenari di applicazione su larga scala, inclusi servizi clienti, educazione e supporto tecnico."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o è un modello dinamico, aggiornato in tempo reale per mantenere la versione più recente. Combina una potente comprensione e generazione del linguaggio, adatta a scenari di applicazione su larga scala, inclusi servizi clienti, educazione e supporto tecnico."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o è un modello dinamico che si aggiorna in tempo reale per mantenere sempre l'ultima versione. Combina una potente comprensione del linguaggio e capacità di generazione, rendendolo adatto a scenari di applicazione su larga scala, inclusi assistenza clienti, istruzione e supporto tecnico."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Modello GPT-4o Audio, supporta input e output audio."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini è il modello più recente lanciato da OpenAI dopo il GPT-4 Omni, supporta input visivi e testuali e produce output testuali. Come il loro modello di punta in formato ridotto, è molto più economico rispetto ad altri modelli all'avanguardia recenti e costa oltre il 60% in meno rispetto a GPT-3.5 Turbo. Mantiene un'intelligenza all'avanguardia, offrendo un rapporto qualità-prezzo significativo. GPT-4o mini ha ottenuto un punteggio dell'82% nel test MMLU e attualmente è classificato più in alto di GPT-4 per preferenze di chat."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Versione in tempo reale di GPT-4o-mini, supporta input e output audio e testuali in tempo reale."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Versione in tempo reale di GPT-4o, supporta input e output audio e testuali in tempo reale."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Versione in tempo reale di GPT-4o, supporta input e output audio e testuali in tempo reale."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Versione in tempo reale di GPT-4o, supporta input e output audio e testuali in tempo reale."
+ },
+ "grok-2-1212": {
+ "description": "Questo modello ha migliorato l'accuratezza, il rispetto delle istruzioni e le capacità multilingue."
+ },
+ "grok-2-vision-1212": {
+ "description": "Questo modello ha migliorato l'accuratezza, il rispetto delle istruzioni e le capacità multilingue."
+ },
+ "grok-beta": {
+ "description": "Offre prestazioni comparabili a Grok 2, ma con maggiore efficienza, velocità e funzionalità."
+ },
+ "grok-vision-beta": {
+ "description": "L'ultimo modello di comprensione delle immagini, in grado di gestire una vasta gamma di informazioni visive, tra cui documenti, grafici, screenshot e fotografie."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B è un modello linguistico che combina creatività e intelligenza, unendo diversi modelli di punta."
},
+ "hunyuan-code": {
+ "description": "Ultimo modello di generazione di codice di Hunyuan, addestrato su un modello di base con 200B di dati di codice di alta qualità, con sei mesi di addestramento su dati SFT di alta qualità, la lunghezza della finestra di contesto è aumentata a 8K, e si posiziona tra i primi in cinque indicatori di valutazione automatica della generazione di codice; nelle valutazioni di alta qualità su dieci aspetti di codice in cinque lingue, le prestazioni sono nella prima fascia."
+ },
+ "hunyuan-functioncall": {
+ "description": "Ultimo modello FunctionCall con architettura MOE di Hunyuan, addestrato su dati di alta qualità per le chiamate di funzione, con una finestra di contesto di 32K, è in testa in vari indicatori di valutazione."
+ },
+ "hunyuan-large": {
+ "description": "Il modello Hunyuan-large ha un numero totale di parametri di circa 389B, con circa 52B di parametri attivati, ed è il modello MoE open source con la più grande scala di parametri e le migliori prestazioni nel settore, basato su architettura Transformer."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Specializzato nel gestire compiti di testi lunghi come riassunti di documenti e domande e risposte sui documenti, possiede anche capacità di generazione di testi generali. Eccelle nell'analisi e nella generazione di testi lunghi, in grado di affrontare efficacemente esigenze complesse e dettagliate di elaborazione di contenuti lunghi."
+ },
+ "hunyuan-lite": {
+ "description": "Aggiornato a una struttura MOE, con una finestra di contesto di 256k, è in testa a molti modelli open source in vari set di valutazione su NLP, codice, matematica e settori."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Il modello multimodale Hunyuan più recente da 7B, con una finestra contestuale di 32K, supporta dialoghi multimodali in cinese e inglese, riconoscimento di oggetti nelle immagini, comprensione di documenti e tabelle, matematica multimodale, e supera i modelli concorrenti da 7B in vari indicatori di valutazione."
+ },
+ "hunyuan-pro": {
+ "description": "Modello di testo lungo MOE-32K con un miliardo di parametri. Raggiunge livelli di eccellenza in vari benchmark, con capacità di istruzioni complesse e ragionamento, supporta le chiamate di funzione, ottimizzato per traduzione multilingue, finanza, diritto e medicina."
+ },
+ "hunyuan-role": {
+ "description": "Ultimo modello di ruolo di Hunyuan, un modello di ruolo fine-tuned ufficialmente rilasciato da Hunyuan, addestrato su un dataset di scenari di ruolo, con migliori prestazioni di base in scenari di ruolo."
+ },
+ "hunyuan-standard": {
+ "description": "Utilizza una strategia di routing migliore, alleviando i problemi di bilanciamento del carico e convergenza degli esperti. Per i testi lunghi, l'indice di recupero è del 99,9%. MOE-32K offre un buon rapporto qualità-prezzo, bilanciando efficacia e costo, e gestisce l'input di testi lunghi."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Utilizza una strategia di routing migliore, alleviando i problemi di bilanciamento del carico e convergenza degli esperti. Per i testi lunghi, l'indice di recupero è del 99,9%. MOE-256K supera ulteriormente in lunghezza ed efficacia, ampliando notevolmente la lunghezza massima di input."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Il modello multimodale più recente di Hunyuan, supporta risposte in più lingue, con capacità equilibrate in cinese e inglese."
+ },
+ "hunyuan-translation": {
+ "description": "Supporta la traduzione tra cinese e inglese, giapponese, francese, portoghese, spagnolo, turco, russo, arabo, coreano, italiano, tedesco, vietnamita, malese e indonesiano, per un totale di 15 lingue, con valutazione automatica basata su un set di valutazione di traduzione multi-scenario e punteggio COMET, mostrando complessivamente prestazioni superiori rispetto ai modelli di dimensioni simili sul mercato in termini di capacità di traduzione reciproca tra le lingue più comuni."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Il modello di traduzione Hunyuan supporta la traduzione in modo conversazionale in linguaggio naturale; supporta la traduzione tra cinese e inglese, giapponese, francese, portoghese, spagnolo, turco, russo, arabo, coreano, italiano, tedesco, vietnamita, malese e indonesiano, per un totale di 15 lingue."
+ },
+ "hunyuan-turbo": {
+ "description": "Anteprima della nuova generazione di modelli di linguaggio di Hunyuan, utilizza una nuova struttura di modello ibrido di esperti (MoE), con una maggiore efficienza di inferenza e prestazioni superiori rispetto a hunyuan-pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Versione fissa di hunyuan-turbo del 20 novembre 2024, una versione intermedia tra hunyuan-turbo e hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Ottimizzazione di questa versione: scaling delle istruzioni sui dati, notevole aumento della capacità di generalizzazione del modello; notevole miglioramento delle capacità matematiche, di codifica e di ragionamento logico; ottimizzazione delle capacità di comprensione del testo e delle parole; ottimizzazione della qualità della generazione dei contenuti di creazione del testo."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Ottimizzazione dell'esperienza generale, inclusi comprensione NLP, creazione di testi, conversazione, domande e risposte, traduzione, e altro; miglioramento dell'umanizzazione, ottimizzazione dell'intelligenza emotiva del modello; potenziamento della capacità del modello di chiarire attivamente in caso di ambiguità; miglioramento della gestione di problemi di analisi di parole e frasi; aumento della qualità e dell'interattività della creazione; miglioramento dell'esperienza multi-turno."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Il nuovo modello di punta di linguaggio visivo di Hunyuan, adotta una nuova struttura di modello esperto misto (MoE), con miglioramenti complessivi nelle capacità di riconoscimento di base, creazione di contenuti, domande e risposte, analisi e ragionamento rispetto alla generazione precedente."
+ },
+ "hunyuan-vision": {
+ "description": "Ultimo modello multimodale di Hunyuan, supporta l'input di immagini e testo per generare contenuti testuali."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Il modello open source innovativo InternLM2.5, con un gran numero di parametri, migliora l'intelligenza del dialogo."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 offre soluzioni di dialogo intelligente in vari scenari."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Il modello Llama 3.1 70B Instruct, con 70B parametri, offre prestazioni eccezionali in generazione di testi di grandi dimensioni e compiti di istruzione."
+ "internlm2-pro-chat": {
+ "description": "Un modello della vecchia versione che stiamo ancora mantenendo, disponibile in diverse dimensioni di parametri: 7B e 20B."
+ },
+ "internlm2.5-latest": {
+ "description": "La nostra ultima serie di modelli, con prestazioni di ragionamento eccezionali, supporta una lunghezza di contesto di 1M e offre una migliore capacità di seguire istruzioni e chiamare strumenti."
+ },
+ "internlm3-latest": {
+ "description": "La nostra ultima serie di modelli, con prestazioni di inferenza eccezionali, è leader tra i modelli open source della stessa classe. Punta di default ai modelli della serie InternLM3 appena rilasciati."
+ },
+ "jina-deepsearch-v1": {
+ "description": "La ricerca approfondita combina la ricerca online, la lettura e il ragionamento, consentendo indagini complete. Puoi considerarlo come un agente che accetta il tuo compito di ricerca - eseguirà una ricerca approfondita e iterativa prima di fornire una risposta. Questo processo implica una continua ricerca, ragionamento e risoluzione dei problemi da diverse angolazioni. Questo è fondamentalmente diverso dai modelli di grandi dimensioni standard che generano risposte direttamente dai dati pre-addestrati e dai tradizionali sistemi RAG che si basano su ricerche superficiali una tantum."
+ },
+ "kimi-latest": {
+ "description": "Il prodotto Kimi Smart Assistant utilizza il più recente modello Kimi, che potrebbe includere funzionalità non ancora stabili. Supporta la comprensione delle immagini e selezionerà automaticamente il modello di fatturazione 8k/32k/128k in base alla lunghezza del contesto della richiesta."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM è un modello linguistico sperimentale, specifico per compiti, addestrato per rispettare i principi della scienza dell'apprendimento, in grado di seguire istruzioni sistematiche in contesti di insegnamento e apprendimento, fungendo da tutor esperto."
+ },
+ "lite": {
+ "description": "Spark Lite è un modello di linguaggio di grandi dimensioni leggero, con latenza estremamente bassa e capacità di elaborazione efficiente, completamente gratuito e aperto, supporta funzionalità di ricerca online in tempo reale. La sua caratteristica di risposta rapida lo rende eccellente per applicazioni di inferenza su dispositivi a bassa potenza e per il fine-tuning dei modelli, offrendo agli utenti un'ottima efficienza dei costi e un'esperienza intelligente, soprattutto nei contesti di domande e risposte, generazione di contenuti e ricerca."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B offre capacità di ragionamento AI più potenti, adatto per applicazioni complesse, supporta un'elaborazione computazionale elevata garantendo efficienza e precisione."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B è un modello ad alte prestazioni, offre capacità di generazione di testo rapida, particolarmente adatto per scenari applicativi che richiedono efficienza su larga scala e costi contenuti."
},
- "llama-3.1-8b-instruct": {
- "description": "Il modello Llama 3.1 8B Instruct, con 8B parametri, supporta l'esecuzione efficiente di compiti di istruzione, offrendo capacità di generazione testuale di alta qualità."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Eccellenti capacità di ragionamento visivo su immagini ad alta risoluzione, adatte ad applicazioni di comprensione visiva."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Il modello Llama 3.1 Sonar Huge Online, con 405B parametri, supporta una lunghezza di contesto di circa 127.000 token, progettato per applicazioni di chat online complesse."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Eccelle in compiti come la descrizione delle immagini e le domande visive, colmando il divario tra generazione del linguaggio e ragionamento visivo."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Il modello Llama 3.1 Sonar Large Chat, con 70B parametri, supporta una lunghezza di contesto di circa 127.000 token, adatto per compiti di chat offline complessi."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Capacità avanzate di ragionamento visivo per applicazioni di agenti di comprensione visiva."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Il modello Llama 3.1 Sonar Large Online, con 70B parametri, supporta una lunghezza di contesto di circa 127.000 token, adatto per compiti di chat ad alta capacità e diversificati."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Eccelle in compiti come la descrizione delle immagini e le domande visive, colmando il divario tra generazione del linguaggio e ragionamento visivo."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Il modello Llama 3.1 Sonar Small Chat, con 8B parametri, è progettato per chat offline, supportando una lunghezza di contesto di circa 127.000 token."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 è il modello di linguaggio open source multilingue più avanzato della serie Llama, che offre prestazioni paragonabili a un modello da 405B a un costo estremamente ridotto. Basato su una struttura Transformer, migliora l'utilità e la sicurezza attraverso il fine-tuning supervisionato (SFT) e l'apprendimento per rinforzo con feedback umano (RLHF). La sua versione ottimizzata per le istruzioni è progettata per dialoghi multilingue e supera molti modelli di chat open source e chiusi in vari benchmark di settore. La data di scadenza delle conoscenze è dicembre 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Il modello Llama 3.1 Sonar Small Online, con 8B parametri, supporta una lunghezza di contesto di circa 127.000 token, progettato per chat online, in grado di gestire interazioni testuali in modo efficiente."
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 è un modello linguistico di grandi dimensioni multilingue (LLM) da 70B (input/output testuale) con pre-addestramento e aggiustamento delle istruzioni. Il modello di testo puro di Llama 3.3 è ottimizzato per casi d'uso di dialogo multilingue e supera molti modelli di chat open-source e chiusi nei benchmark di settore comuni."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B offre capacità di elaborazione della complessità senza pari, progettato su misura per progetti ad alta richiesta."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral è progettato per la ricerca scientifica e il ragionamento matematico, offre capacità di calcolo efficaci e interpretazione dei risultati."
},
+ "max-32k": {
+ "description": "Spark Max 32K è dotato di una grande capacità di elaborazione del contesto, con una comprensione del contesto e capacità di ragionamento logico superiori, supporta input testuali fino a 32K token, adatto per la lettura di documenti lunghi, domande e risposte su conoscenze private e altri scenari."
+ },
"meta-llama-3-70b-instruct": {
"description": "Un potente modello con 70 miliardi di parametri che eccelle nel ragionamento, nella codifica e nelle ampie applicazioni linguistiche."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) offre eccellenti capacità di elaborazione linguistica e un'interazione di alta qualità."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 offre eccellenti capacità di elaborazione del linguaggio e un'esperienza interattiva di alta qualità."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) è un potente modello di chat, in grado di gestire esigenze di dialogo complesse."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) offre supporto multilingue, coprendo una vasta gamma di conoscenze di dominio."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Eccelle in compiti come la descrizione di immagini e le domande visive, colmando il divario tra generazione del linguaggio e ragionamento visivo."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Eccelle in compiti come la descrizione di immagini e le domande visive, colmando il divario tra generazione del linguaggio e ragionamento visivo."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Eccelle in compiti come la descrizione di immagini e le domande visive, colmando il divario tra generazione del linguaggio e ragionamento visivo."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 è il modello di linguaggio open source multilingue più avanzato della serie Llama, che offre prestazioni paragonabili a un modello da 405B a costi molto bassi. Basato su architettura Transformer, migliorato tramite fine-tuning supervisionato (SFT) e apprendimento rinforzato con feedback umano (RLHF) per aumentarne l'utilità e la sicurezza. La sua versione ottimizzata per le istruzioni è progettata per dialoghi multilingue, superando molti modelli di chat open source e chiusi in vari benchmark di settore. Data di scadenza delle conoscenze: dicembre 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Il modello di linguaggio di grandi dimensioni multilingue Meta Llama 3.3 (LLM) è un modello generativo pre-addestrato e regolato per istruzioni da 70B (input/output di testo). Il modello di testo puro di Llama 3.3 regolato per istruzioni è ottimizzato per casi d'uso di dialogo multilingue e supera molti modelli di chat open source e chiusi disponibili su benchmark di settore comuni."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Eccelle in compiti come la descrizione di immagini e le domande visive, colmando il divario tra generazione del linguaggio e ragionamento visivo."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite è adatto per ambienti che richiedono alta efficienza e bassa latenza."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "Il modello Llama 3.1 Turbo 405B offre un supporto di contesto di capacità estremamente grande per l'elaborazione di big data, eccellendo nelle applicazioni di intelligenza artificiale su larga scala."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 è il modello leader lanciato da Meta, supporta fino a 405B parametri, applicabile a conversazioni complesse, traduzione multilingue e analisi dei dati."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B offre supporto per dialoghi multilingue ad alta efficienza."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct è ottimizzato per scenari di dialogo di alta qualità, con prestazioni superiori a molti modelli chiusi."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct è l'ultima versione rilasciata da Meta, ottimizzata per generare dialoghi di alta qualità, superando molti modelli chiusi di punta."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct è progettato per dialoghi di alta qualità, con prestazioni eccezionali nelle valutazioni umane, particolarmente adatto per scenari ad alta interazione."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 offre supporto multilingue ed è uno dei modelli generativi leader nel settore."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Si distingue in compiti come la descrizione delle immagini e il question answering visivo, colmando il divario tra generazione del linguaggio e ragionamento visivo."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 è progettato per gestire compiti che combinano dati visivi e testuali. Si distingue in compiti come la descrizione delle immagini e il question answering visivo, colmando il divario tra generazione del linguaggio e ragionamento visivo."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 è il modello di linguaggio open source multilingue più avanzato della serie Llama, che offre prestazioni paragonabili a un modello da 405B a un costo estremamente ridotto. Basato su una struttura Transformer, migliora l'utilità e la sicurezza attraverso il fine-tuning supervisionato (SFT) e l'apprendimento per rinforzo con feedback umano (RLHF). La sua versione ottimizzata per le istruzioni è progettata per dialoghi multilingue e supera molti modelli di chat open source e chiusi in vari benchmark di settore. La data di scadenza delle conoscenze è dicembre 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 è il modello di linguaggio open source multilingue più avanzato della serie Llama, che offre prestazioni paragonabili a un modello da 405B a un costo estremamente ridotto. Basato su una struttura Transformer, migliora l'utilità e la sicurezza attraverso il fine-tuning supervisionato (SFT) e l'apprendimento per rinforzo con feedback umano (RLHF). La sua versione ottimizzata per le istruzioni è progettata per dialoghi multilingue e supera molti modelli di chat open source e chiusi in vari benchmark di settore. La data di scadenza delle conoscenze è dicembre 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct è il modello più grande e potente della serie Llama 3.1 Instruct, un modello avanzato per la generazione di dati e il ragionamento conversazionale, utilizzabile anche come base per un pre-addestramento o un fine-tuning specializzato in determinati settori. I modelli di linguaggio di grandi dimensioni (LLMs) multilingue forniti da Llama 3.1 sono un insieme di modelli generativi pre-addestrati e ottimizzati per le istruzioni, che includono dimensioni di 8B, 70B e 405B (input/output di testo). I modelli di testo ottimizzati per le istruzioni di Llama 3.1 (8B, 70B, 405B) sono stati progettati per casi d'uso conversazionali multilingue e hanno superato molti modelli di chat open source disponibili in benchmark di settore comuni. Llama 3.1 è progettato per usi commerciali e di ricerca in diverse lingue. I modelli di testo ottimizzati per le istruzioni sono adatti a chat simili a assistenti, mentre i modelli pre-addestrati possono adattarsi a vari compiti di generazione di linguaggio naturale. I modelli Llama 3.1 supportano anche l'uso della loro output per migliorare altri modelli, inclusa la generazione di dati sintetici e il raffinamento. Llama 3.1 è un modello di linguaggio autoregressivo basato su un'architettura di trasformatore ottimizzata. Le versioni ottimizzate utilizzano il fine-tuning supervisionato (SFT) e l'apprendimento per rinforzo con feedback umano (RLHF) per allinearsi alle preferenze umane in termini di utilità e sicurezza."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 è un modello di linguaggio di grandi dimensioni (LLM) open source progettato per sviluppatori, ricercatori e aziende, per aiutarli a costruire, sperimentare e scalare responsabilmente le loro idee di AI generativa. Come parte di un sistema di base per l'innovazione della comunità globale, è particolarmente adatto per dispositivi a bassa potenza e risorse limitate, oltre a garantire tempi di addestramento più rapidi."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B è il modello leggero e veloce più recente di Microsoft AI, con prestazioni vicine a quelle dei modelli leader open source esistenti."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "LLM avanzato, supporta la generazione di dati sintetici, la distillazione della conoscenza e il ragionamento, adatto per chatbot, programmazione e compiti specifici."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Abilita conversazioni complesse, con eccellenti capacità di comprensione del contesto, ragionamento e generazione di testo."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Modello all'avanguardia, dotato di comprensione del linguaggio, eccellenti capacità di ragionamento e generazione di testo."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Modello visivo-linguistico all'avanguardia, specializzato nel ragionamento di alta qualità a partire dalle immagini."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Modello linguistico all'avanguardia di piccole dimensioni, dotato di comprensione del linguaggio, eccellenti capacità di ragionamento e generazione di testo."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Modello linguistico all'avanguardia di piccole dimensioni, dotato di comprensione del linguaggio, eccellenti capacità di ragionamento e generazione di testo."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Modello visivo-linguistico all'avanguardia, specializzato nel ragionamento di alta qualità a partire dalle immagini."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "LLM avanzato, specializzato in ragionamento, matematica, conoscenze generali e chiamate di funzione."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 è un modello linguistico fornito da Microsoft AI, particolarmente efficace in conversazioni complesse, multilingue, ragionamento e assistenti intelligenti."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B è il modello Wizard più avanzato di Microsoft AI, mostrando prestazioni estremamente competitive."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V è la nuova generazione di modelli multimodali lanciata da OpenBMB, dotata di eccellenti capacità di riconoscimento OCR e comprensione multimodale, supportando una vasta gamma di scenari applicativi."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B è il modello di punta di Mistral per edge computing."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B è un modello edge ad alto rapporto qualità-prezzo di Mistral."
+ },
"mistral": {
"description": "Mistral è un modello da 7B lanciato da Mistral AI, adatto per esigenze di elaborazione linguistica variabili."
},
"mistral-large": {
"description": "Mixtral Large è il modello di punta di Mistral, combinando capacità di generazione di codice, matematica e ragionamento, supporta una finestra di contesto di 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) è un modello di linguaggio avanzato (LLM) con capacità di ragionamento, conoscenza e codifica all'avanguardia."
- },
"mistral-large-latest": {
"description": "Mistral Large è il modello di punta, specializzato in compiti multilingue, ragionamento complesso e generazione di codice, è la scelta ideale per applicazioni di alta gamma."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 offre capacità computazionali efficienti e comprensione del linguaggio naturale, adatta per una vasta gamma di applicazioni."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B è un modello compatto ma ad alte prestazioni, specializzato nell'elaborazione batch e in compiti semplici come classificazione e generazione di testo, con buone capacità di ragionamento."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) è un super modello di linguaggio, supportando esigenze di elaborazione estremamente elevate."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B è un modello di esperti misti pre-addestrato, utilizzato per compiti testuali generali."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B è un modello di esperti sparsi che utilizza più parametri per migliorare la velocità di ragionamento, adatto a compiti di generazione multilingue e di codice."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct è un modello standard di settore ad alte prestazioni, ottimizzato per velocità e supporto di contesti lunghi."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K è un modello con capacità di elaborazione di contesti ultra lunghi, adatto per generare testi molto lunghi, soddisfacendo le esigenze di compiti complessi, in grado di gestire contenuti fino a 128.000 token, particolarmente adatto per applicazioni di ricerca, accademiche e generazione di documenti di grandi dimensioni."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Il modello visivo Kimi (inclusi moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, ecc.) è in grado di comprendere il contenuto delle immagini, inclusi testo, colori e forme degli oggetti."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K offre capacità di elaborazione di contesti di lunghezza media, in grado di gestire 32.768 token, particolarmente adatto per generare vari documenti lunghi e dialoghi complessi, utilizzato in creazione di contenuti, generazione di report e sistemi di dialogo."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Il modello visivo Kimi (inclusi moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, ecc.) è in grado di comprendere il contenuto delle immagini, inclusi testo, colori e forme degli oggetti."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K è progettato per generare compiti di testo brevi, con prestazioni di elaborazione efficienti, in grado di gestire 8.192 token, particolarmente adatto per dialoghi brevi, appunti e generazione rapida di contenuti."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Il modello visivo Kimi (inclusi moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, ecc.) è in grado di comprendere il contenuto delle immagini, inclusi testo, colori e forme degli oggetti."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto può selezionare il modello appropriato in base al numero di token utilizzati nel contesto attuale."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B è una versione aggiornata di Nous Hermes 2, contenente i più recenti dataset sviluppati internamente."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B è un modello linguistico di grandi dimensioni personalizzato da NVIDIA, progettato per migliorare l'utilità delle risposte generate dai LLM alle domande degli utenti. Questo modello ha ottenuto risultati eccellenti nei benchmark come Arena Hard, AlpacaEval 2 LC e GPT-4-Turbo MT-Bench, classificandosi al primo posto in tutti e tre i benchmark di allineamento automatico fino al 1 ottobre 2024. Il modello è stato addestrato utilizzando RLHF (in particolare REINFORCE), Llama-3.1-Nemotron-70B-Reward e HelpSteer2-Preference come suggerimenti, basandosi sul modello Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Modello linguistico unico, offre prestazioni di accuratezza ed efficienza senza pari."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct è un modello linguistico di grandi dimensioni personalizzato da NVIDIA, progettato per migliorare l'utilità delle risposte generate da LLM."
+ },
+ "o1": {
+ "description": "Focalizzato su inferenze avanzate e risoluzione di problemi complessi, inclusi compiti matematici e scientifici. È particolarmente adatto per applicazioni che richiedono una comprensione profonda del contesto e flussi di lavoro agenti."
+ },
"o1-mini": {
"description": "o1-mini è un modello di inferenza rapido ed economico progettato per applicazioni di programmazione, matematica e scienza. Questo modello ha un contesto di 128K e una data di cutoff della conoscenza di ottobre 2023."
},
"o1-preview": {
"description": "o1 è il nuovo modello di inferenza di OpenAI, adatto a compiti complessi che richiedono una vasta conoscenza generale. Questo modello ha un contesto di 128K e una data di cutoff della conoscenza di ottobre 2023."
},
+ "o3-mini": {
+ "description": "o3-mini è il nostro ultimo modello di inferenza compatto, che offre un'intelligenza elevata con gli stessi obiettivi di costo e latenza di o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba è un modello linguistico Mamba 2 focalizzato sulla generazione di codice, offre un forte supporto per compiti avanzati di codifica e ragionamento."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B è un modello di esperti sparsi, che utilizza più parametri per aumentare la velocità di ragionamento, adatto per gestire compiti di generazione di linguaggio e codice multilingue."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o è un modello dinamico, aggiornato in tempo reale per mantenere la versione più recente. Combina potenti capacità di comprensione e generazione del linguaggio, adatto a scenari applicativi su larga scala, inclusi servizi clienti, educazione e supporto tecnico."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o è un modello dinamico, aggiornato in tempo reale per mantenere la versione più recente. Combina potenti capacità di comprensione e generazione del linguaggio, adatto a scenari di applicazione su larga scala, tra cui assistenza clienti, istruzione e supporto tecnico."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini è il modello più recente di OpenAI, lanciato dopo GPT-4 Omni, che supporta input visivi e testuali e produce output testuali. Come il loro modello di piccole dimensioni più avanzato, è molto più economico rispetto ad altri modelli all'avanguardia recenti e costa oltre il 60% in meno rispetto a GPT-3.5 Turbo. Mantiene un'intelligenza all'avanguardia, offrendo un notevole rapporto qualità-prezzo. GPT-4o mini ha ottenuto un punteggio dell'82% nel test MMLU e attualmente è classificato più in alto di GPT-4 per preferenze di chat."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Il modello Pixtral dimostra potenti capacità in compiti di comprensione di grafici e immagini, domande e risposte su documenti, ragionamento multimodale e rispetto delle istruzioni, in grado di elaborare immagini a risoluzione naturale e proporzioni, e di gestire un numero arbitrario di immagini in una finestra di contesto lunga fino a 128K token."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large è un modello multimodale open source con 124 miliardi di parametri, costruito su Mistral Large 2. Questo è il nostro secondo modello nella famiglia multimodale, che mostra capacità di comprensione delle immagini a livello all'avanguardia."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K è dotato di una capacità di elaborazione del contesto eccezionale, in grado di gestire fino a 128K di informazioni contestuali, particolarmente adatto per l'analisi completa e la gestione di associazioni logiche a lungo termine in contenuti lunghi, fornendo una logica fluida e coerente e un supporto variegato per le citazioni in comunicazioni testuali complesse."
+ },
+ "qvq-72b-preview": {
+ "description": "Il modello QVQ è un modello di ricerca sperimentale sviluppato dal team Qwen, focalizzato sul miglioramento delle capacità di ragionamento visivo, in particolare nel campo del ragionamento matematico."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Modello di codice Qwen di Tongyi."
+ },
"qwen-coder-turbo-latest": {
"description": "Modello di codice Tongyi Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Il modello matematico Tongyi Qwen è progettato specificamente per la risoluzione di problemi matematici."
},
+ "qwen-max": {
+ "description": "Qwen Max è un modello linguistico di grandi dimensioni con trilioni di parametri, supporta input in diverse lingue, tra cui cinese e inglese e attualmente è il modello API dietro la versione 2.5 di Qwen."
+ },
"qwen-max-latest": {
"description": "Modello linguistico su larga scala Tongyi Qwen con miliardi di parametri, supporta input in diverse lingue tra cui cinese e inglese, attualmente il modello API dietro la versione del prodotto Tongyi Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "La serie di modelli Qwen-Omni supporta l'input di dati in diverse modalità, inclusi video, audio, immagini e testo, e produce output audio e testuale."
+ },
+ "qwen-plus": {
+ "description": "Qwen Plus è una versione potenziata del modello linguistico di grandi dimensioni, che supporta input in diverse lingue, tra cui cinese e inglese."
+ },
"qwen-plus-latest": {
"description": "Versione potenziata del modello linguistico su larga scala Tongyi Qwen, supporta input in diverse lingue tra cui cinese e inglese."
},
+ "qwen-turbo": {
+ "description": "Qwen è un modello linguistico di grandi dimensioni che supporta input in diverse lingue, tra cui cinese e inglese."
+ },
"qwen-turbo-latest": {
"description": "Il modello linguistico su larga scala Tongyi Qwen, supporta input in diverse lingue tra cui cinese e inglese."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL supporta modalità di interazione flessibili, inclusi modelli di domande e risposte multipli e creativi."
},
- "qwen-vl-max": {
- "description": "Qwen è un modello di linguaggio visivo su larga scala. Rispetto alla versione potenziata, migliora ulteriormente le capacità di ragionamento visivo e di aderenza alle istruzioni, offrendo un livello superiore di percezione e cognizione visiva."
+ "qwen-vl-max-latest": {
+ "description": "Modello di linguaggio visivo Qwen di grande scala. Rispetto alla versione potenziata, migliora ulteriormente la capacità di ragionamento visivo e di aderenza alle istruzioni, offrendo un livello superiore di percezione visiva e cognizione."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Qwen OCR è un modello specializzato nell'estrazione di testo, focalizzato sulla capacità di estrazione di testo da immagini di documenti, tabelle, domande d'esame, scrittura a mano, ecc. È in grado di riconoscere vari testi, supportando attualmente le seguenti lingue: cinese, inglese, francese, giapponese, coreano, tedesco, russo, italiano, vietnamita, arabo."
},
- "qwen-vl-plus": {
- "description": "Qwen è una versione potenziata del modello di linguaggio visivo su larga scala. Migliora notevolmente le capacità di riconoscimento dei dettagli e di riconoscimento del testo, supportando immagini con risoluzione superiore a un milione di pixel e proporzioni di qualsiasi dimensione."
+ "qwen-vl-plus-latest": {
+ "description": "Versione potenziata del modello di linguaggio visivo Qwen. Migliora notevolmente la capacità di riconoscimento dei dettagli e di riconoscimento del testo, supportando risoluzioni superiori a un milione di pixel e immagini di qualsiasi rapporto di aspetto."
},
"qwen-vl-v1": {
"description": "Inizializzato con il modello di linguaggio Qwen-7B, aggiunge un modello di immagine, con una risoluzione di input dell'immagine di 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 è la nuova serie di modelli di linguaggio Qwen. Qwen2 7B è un modello basato su transformer, che mostra prestazioni eccezionali nella comprensione del linguaggio, nelle capacità multilingue, nella programmazione, nella matematica e nel ragionamento."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 è una nuova serie di modelli di linguaggio di grandi dimensioni, con capacità di comprensione e generazione più forti."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL è l'ultima iterazione del modello Qwen-VL, raggiungendo prestazioni all'avanguardia nei benchmark di comprensione visiva, inclusi MathVista, DocVQA, RealWorldQA e MTVQA. Qwen2-VL è in grado di comprendere video di oltre 20 minuti, per domande e risposte, dialoghi e creazione di contenuti di alta qualità basati su video. Ha anche capacità di ragionamento e decisione complesse, che possono essere integrate con dispositivi mobili, robot e altro, per operazioni automatiche basate su ambienti visivi e istruzioni testuali. Oltre all'inglese e al cinese, Qwen2-VL ora supporta anche la comprensione di testi in diverse lingue all'interno delle immagini, comprese la maggior parte delle lingue europee, giapponese, coreano, arabo e vietnamita."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct è uno dei più recenti modelli di linguaggio rilasciati da Alibaba Cloud. Questo modello da 72B ha capacità notevolmente migliorate in campi come la codifica e la matematica. Il modello offre anche supporto multilingue, coprendo oltre 29 lingue, tra cui cinese e inglese. Ha mostrato miglioramenti significativi nel seguire istruzioni, comprendere dati strutturati e generare output strutturati (in particolare JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct è uno dei più recenti modelli di linguaggio rilasciati da Alibaba Cloud. Questo modello da 32B ha capacità notevolmente migliorate in campi come la codifica e la matematica. Il modello offre anche supporto multilingue, coprendo oltre 29 lingue, tra cui cinese e inglese. Ha mostrato miglioramenti significativi nel seguire istruzioni, comprendere dati strutturati e generare output strutturati (in particolare JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM orientato al cinese e all'inglese, focalizzato su linguaggio, programmazione, matematica, ragionamento e altro."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "LLM avanzato, supporta la generazione di codice, il ragionamento e la correzione, coprendo i linguaggi di programmazione più diffusi."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Potente modello di codice di medie dimensioni, supporta una lunghezza di contesto di 32K, specializzato in programmazione multilingue."
+ },
"qwen2": {
"description": "Qwen2 è la nuova generazione di modelli di linguaggio su larga scala di Alibaba, supporta prestazioni eccellenti per esigenze applicative diversificate."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 è la nuova generazione di modelli linguistici su larga scala di Alibaba, che supporta esigenze applicative diversificate con prestazioni eccellenti."
+ },
"qwen2.5-14b-instruct": {
"description": "Modello da 14B di Tongyi Qwen 2.5, open source."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Il modello da 72B di Qwen2.5 è open source."
+ },
"qwen2.5-32b-instruct": {
"description": "Modello da 32B di Tongyi Qwen 2.5, open source."
},
@@ -824,7 +1599,10 @@
"description": "Modello da 7B di Tongyi Qwen 2.5, open source."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "Versione open source del modello di codice Tongyi Qwen."
+ "description": "Versione open-source del modello di codice Qwen."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Versione open source del modello di codice Qwen di Tongyi."
},
"qwen2.5-coder-7b-instruct": {
"description": "Versione open source del modello di codice Tongyi Qwen."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Il modello Qwen-Math ha potenti capacità di risoluzione di problemi matematici."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Miglioramento complessivo nella seguire istruzioni, matematica, risoluzione di problemi e codice, con capacità di riconoscimento universale migliorate, supporto per formati diversi per il posizionamento preciso degli elementi visivi, comprensione di file video lunghi (fino a 10 minuti) e localizzazione di eventi in tempo reale, capacità di comprendere sequenze temporali e velocità, supporto per il controllo di agenti OS o Mobile basato su capacità di analisi e localizzazione, forte capacità di estrazione di informazioni chiave e output in formato Json, questa versione è la 72B, la versione più potente della serie."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Miglioramento complessivo nella seguire istruzioni, matematica, risoluzione di problemi e codice, con capacità di riconoscimento universale migliorate, supporto per formati diversi per il posizionamento preciso degli elementi visivi, comprensione di file video lunghi (fino a 10 minuti) e localizzazione di eventi in tempo reale, capacità di comprendere sequenze temporali e velocità, supporto per il controllo di agenti OS o Mobile basato su capacità di analisi e localizzazione, forte capacità di estrazione di informazioni chiave e output in formato Json, questa versione è la 72B, la versione più potente della serie."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 è la nuova generazione di modelli linguistici su larga scala di Alibaba, che supporta esigenze applicative diversificate con prestazioni eccellenti."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 è la nuova generazione di modelli linguistici su larga scala di Alibaba, che supporta esigenze applicative diversificate con prestazioni eccellenti."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 è la nuova generazione di modelli linguistici su larga scala di Alibaba, che supporta esigenze applicative diversificate con prestazioni eccellenti."
+ },
"qwen2:0.5b": {
"description": "Qwen2 è la nuova generazione di modelli di linguaggio su larga scala di Alibaba, supporta prestazioni eccellenti per esigenze applicative diversificate."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 è la nuova generazione di modelli di linguaggio su larga scala di Alibaba, supporta prestazioni eccellenti per esigenze applicative diversificate."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini è un LLM compatto, con prestazioni superiori a GPT-3.5, dotato di forti capacità multilingue, supportando inglese e coreano, offrendo soluzioni efficienti e compatte."
+ "qwq": {
+ "description": "QwQ è un modello di ricerca sperimentale, focalizzato sul miglioramento delle capacità di ragionamento dell'IA."
+ },
+ "qwq-32b": {
+ "description": "Il modello di inferenza QwQ, addestrato sul modello Qwen2.5-32B, ha notevolmente migliorato le capacità di inferenza del modello attraverso l'apprendimento rinforzato. I principali indicatori core (AIME 24/25, LiveCodeBench) e alcuni indicatori generali (IFEval, LiveBench, ecc.) raggiungono il livello della versione completa di DeepSeek-R1, con tutti gli indicatori che superano significativamente il DeepSeek-R1-Distill-Qwen-32B, anch'esso basato su Qwen2.5-32B."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) espande le capacità di Solar Mini, focalizzandosi sul giapponese, mantenendo al contempo prestazioni elevate e un uso efficiente in inglese e coreano."
+ "qwq-32b-preview": {
+ "description": "Il modello QwQ è un modello di ricerca sperimentale sviluppato dal team Qwen, focalizzato sul potenziamento delle capacità di ragionamento dell'IA."
+ },
+ "qwq-plus-latest": {
+ "description": "Il modello di inferenza QwQ, addestrato sul modello Qwen2.5, ha notevolmente migliorato le capacità di inferenza del modello attraverso l'apprendimento rinforzato. I principali indicatori core (AIME 24/25, LiveCodeBench) e alcuni indicatori generali (IFEval, LiveBench, ecc.) raggiungono il livello della versione completa di DeepSeek-R1."
+ },
+ "r1-1776": {
+ "description": "R1-1776 è una versione del modello DeepSeek R1, addestrata successivamente per fornire informazioni fattuali non verificate e prive di pregiudizi."
+ },
+ "solar-mini": {
+ "description": "Solar Mini è un LLM compatto, con prestazioni superiori a GPT-3.5, dotato di potenti capacità multilingue, supporta inglese e coreano, offrendo soluzioni efficienti e compatte."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) espande le capacità di Solar Mini, concentrandosi sul giapponese, mantenendo al contempo prestazioni elevate ed efficienti nell'uso dell'inglese e del coreano."
},
"solar-pro": {
"description": "Solar Pro è un LLM altamente intelligente lanciato da Upstage, focalizzato sulla capacità di seguire istruzioni su singolo GPU, con un punteggio IFEval superiore a 80. Attualmente supporta l'inglese, con una versione ufficiale prevista per novembre 2024, che espanderà il supporto linguistico e la lunghezza del contesto."
},
+ "sonar": {
+ "description": "Prodotto di ricerca leggero basato sul contesto di ricerca, più veloce e più economico rispetto a Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research conduce ricerche complete a livello esperto e le sintetizza in rapporti accessibili e utilizzabili."
+ },
+ "sonar-pro": {
+ "description": "Prodotto di ricerca avanzata che supporta il contesto di ricerca, query avanzate e follow-up."
+ },
+ "sonar-reasoning": {
+ "description": "Nuovo prodotto API supportato dal modello di ragionamento DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Nuovo prodotto API supportato dal modello di ragionamento DeepSeek."
+ },
"step-1-128k": {
"description": "Equilibrio tra prestazioni e costi, adatto per scenari generali."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Modello ad alta velocità, adatto per dialoghi in tempo reale."
},
+ "step-1.5v-mini": {
+ "description": "Questo modello possiede potenti capacità di comprensione video."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Questo modello ha potenti capacità di comprensione delle immagini, superando 1o nei campi matematici e di codifica. Il modello è più piccolo di 1o e offre una velocità di output più rapida."
+ },
+ "step-1o-vision-32k": {
+ "description": "Questo modello possiede una potente capacità di comprensione delle immagini. Rispetto ai modelli della serie step-1v, offre prestazioni visive superiori."
+ },
"step-1v-32k": {
"description": "Supporta input visivi, migliorando l'esperienza di interazione multimodale."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Supporta interazioni di contesto su larga scala, adatto per scenari di dialogo complessi."
},
+ "step-2-mini": {
+ "description": "Un modello di grandi dimensioni ad alta velocità basato sulla nuova architettura di attenzione auto-sviluppata MFA, in grado di raggiungere risultati simili a quelli di step1 a un costo molto basso, mantenendo al contempo una maggiore capacità di elaborazione e tempi di risposta più rapidi. È in grado di gestire compiti generali, con competenze particolari nella programmazione."
+ },
"taichu_llm": {
"description": "Il modello linguistico Taichu di Zīdōng ha una straordinaria capacità di comprensione del linguaggio e abilità in creazione di testi, domande di conoscenza, programmazione, calcoli matematici, ragionamento logico, analisi del sentimento e sintesi di testi. Combina in modo innovativo il pre-addestramento su grandi dati con una ricca conoscenza multi-sorgente, affinando continuamente la tecnologia degli algoritmi e assorbendo costantemente nuove conoscenze da dati testuali massivi, migliorando continuamente le prestazioni del modello. Fornisce agli utenti informazioni e servizi più convenienti e un'esperienza più intelligente."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V integra capacità di comprensione delle immagini, trasferimento di conoscenze e attribuzione logica, eccellendo nel campo delle domande e risposte basate su testo e immagini."
+ "taichu_vl": {
+ "description": "Integra capacità di comprensione delle immagini, trasferimento di conoscenze e attribuzione logica, mostrando prestazioni eccezionali nel campo delle domande e risposte basate su testo e immagini."
+ },
+ "text-embedding-3-large": {
+ "description": "Il modello di vettorizzazione più potente, adatto per compiti in inglese e non inglese."
+ },
+ "text-embedding-3-small": {
+ "description": "Modello di Embedding di nuova generazione, efficiente ed economico, adatto per la ricerca di conoscenza, applicazioni RAG e altri scenari."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "La versione open source dell'ultima generazione del modello pre-addestrato GLM-4 rilasciato da Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) offre capacità di calcolo potenziate attraverso strategie e architetture di modelli efficienti."
},
+ "tts-1": {
+ "description": "L'ultimo modello di sintesi vocale, ottimizzato per la velocità in scenari in tempo reale."
+ },
+ "tts-1-hd": {
+ "description": "L'ultimo modello di sintesi vocale, ottimizzato per la qualità."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) è adatto per compiti di istruzione dettagliati, offrendo eccellenti capacità di elaborazione linguistica."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet ha elevato gli standard del settore, superando le prestazioni dei modelli concorrenti e di Claude 3 Opus, dimostrando eccellenza in una vasta gamma di valutazioni, mantenendo al contempo la velocità e i costi dei nostri modelli di livello medio."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet è il modello di prossima generazione più veloce di Anthropic. Rispetto a Claude 3 Haiku, Claude 3.7 Sonnet ha migliorato le sue capacità in vari ambiti e ha superato il modello di generazione precedente, Claude 3 Opus, in molti test di intelligenza."
+ },
+ "whisper-1": {
+ "description": "Modello di riconoscimento vocale universale, supporta il riconoscimento vocale multilingue, la traduzione vocale e il riconoscimento linguistico."
+ },
"wizardlm2": {
"description": "WizardLM 2 è un modello di linguaggio fornito da Microsoft AI, particolarmente efficace in dialoghi complessi, multilingue, ragionamento e assistenti intelligenti."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Eccellente rapporto qualità-prezzo e prestazioni superiori. Ottimizzazione ad alta precisione in base a prestazioni, velocità di inferenza e costi."
},
+ "yi-lightning": {
+ "description": "Il modello di ultima generazione ad alte prestazioni, che garantisce output di alta qualità e migliora notevolmente la velocità di ragionamento."
+ },
+ "yi-lightning-lite": {
+ "description": "Versione leggera, si consiglia di utilizzare yi-lightning."
+ },
"yi-medium": {
"description": "Modello di dimensioni medie aggiornato e ottimizzato, con capacità bilanciate e un buon rapporto qualità-prezzo. Ottimizzazione profonda delle capacità di seguire istruzioni."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Modello per compiti visivi complessi, offre elevate prestazioni nella comprensione e analisi delle immagini."
+ },
+ "yi-vision-v2": {
+ "description": "Modello per compiti visivi complessi, che offre capacità di comprensione e analisi ad alte prestazioni basate su più immagini."
}
}
diff --git a/DigitalHumanWeb/locales/it-IT/plugin.json b/DigitalHumanWeb/locales/it-IT/plugin.json
index 01b1861..fcd5ddf 100644
--- a/DigitalHumanWeb/locales/it-IT/plugin.json
+++ b/DigitalHumanWeb/locales/it-IT/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Ricaricamento del plugin {{name}} fallito",
"urlError": "Il collegamento non restituisce contenuti nel formato JSON. Assicurati che il collegamento sia valido"
},
+ "inspector": {
+ "args": "Visualizza l'elenco dei parametri",
+ "pluginRender": "Visualizza l'interfaccia del plugin"
+ },
"list": {
"item": {
"deprecated.title": "Deprecato",
@@ -130,6 +134,34 @@
"plugin": "Esecuzione del plugin in corso..."
},
"pluginList": "Elenco dei plugin",
+ "search": {
+ "config": {
+ "addKey": "Aggiungi chiave",
+ "close": "Rimuovi",
+ "confirm": "Configurazione completata, riprovare"
+ },
+ "crawPages": {
+ "crawling": "Riconoscimento del link in corso",
+ "detail": {
+ "preview": "Anteprima",
+ "raw": "Testo originale",
+ "tooLong": "Il contenuto del testo è troppo lungo, il contesto della conversazione manterrà solo i primi {{characters}} caratteri, la parte in eccesso non verrà considerata nel contesto della conversazione"
+ },
+ "meta": {
+ "crawler": "Modalità di scansione",
+ "words": "Numero di caratteri"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Inserisci",
+ "description": "Inserisci l'URL di SearchXNG per iniziare la ricerca online",
+ "keyPlaceholder": "Inserisci chiave",
+ "title": "Configura il motore di ricerca SearchXNG",
+ "unconfiguredDesc": "Contatta l'amministratore per completare la configurazione del motore di ricerca SearchXNG e iniziare la ricerca online",
+ "unconfiguredTitle": "Motore di ricerca SearchXNG non configurato"
+ },
+ "title": "Ricerca online"
+ },
"setting": "Impostazioni del plugin",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/it-IT/portal.json b/DigitalHumanWeb/locales/it-IT/portal.json
index 151d67f..be9efc3 100644
--- a/DigitalHumanWeb/locales/it-IT/portal.json
+++ b/DigitalHumanWeb/locales/it-IT/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Plugin",
- "actions": {
- "genAiMessage": "Genera messaggio AI",
- "summary": "Sommario",
- "summaryTooltip": "Sommario del contenuto attuale"
- },
"artifacts": {
"display": {
"code": "Codice",
diff --git a/DigitalHumanWeb/locales/it-IT/providers.json b/DigitalHumanWeb/locales/it-IT/providers.json
index f965aba..b2deb58 100644
--- a/DigitalHumanWeb/locales/it-IT/providers.json
+++ b/DigitalHumanWeb/locales/it-IT/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs costruisce modelli di base e sistemi di intelligenza artificiale per le imprese, accelerando l'adozione dell'intelligenza artificiale generativa in produzione."
+ },
"ai360": {
"description": "360 AI è una piattaforma di modelli e servizi AI lanciata da 360 Company, che offre vari modelli avanzati di elaborazione del linguaggio naturale, tra cui 360GPT2 Pro, 360GPT Pro, 360GPT Turbo e 360GPT Turbo Responsibility 8K. Questi modelli combinano parametri su larga scala e capacità multimodali, trovando ampio utilizzo in generazione di testo, comprensione semantica, sistemi di dialogo e generazione di codice. Con strategie di prezzo flessibili, 360 AI soddisfa le esigenze diversificate degli utenti, supportando l'integrazione degli sviluppatori e promuovendo l'innovazione e lo sviluppo delle applicazioni intelligenti."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure offre una varietà di modelli AI avanzati, tra cui GPT-3.5 e l'ultima serie GPT-4, supportando diversi tipi di dati e compiti complessi, con un impegno per soluzioni AI sicure, affidabili e sostenibili."
},
+ "azureai": {
+ "description": "Azure offre una varietà di modelli AI avanzati, tra cui GPT-3.5 e l'ultima serie GPT-4, supportando diversi tipi di dati e compiti complessi, impegnandosi per soluzioni AI sicure, affidabili e sostenibili."
+ },
"baichuan": {
"description": "Baichuan Intelligence è un'azienda focalizzata sulla ricerca e sviluppo di modelli di intelligenza artificiale di grandi dimensioni, i cui modelli eccellono in compiti in cinese come enciclopedie di conoscenza, elaborazione di testi lunghi e creazione di contenuti, superando i modelli mainstream esteri. Baichuan Intelligence ha anche capacità multimodali leader nel settore, mostrando prestazioni eccezionali in diverse valutazioni autorevoli. I suoi modelli includono Baichuan 4, Baichuan 3 Turbo e Baichuan 3 Turbo 128k, ottimizzati per diversi scenari applicativi, offrendo soluzioni ad alto rapporto qualità-prezzo."
},
"bedrock": {
"description": "Bedrock è un servizio offerto da Amazon AWS, focalizzato sulla fornitura di modelli linguistici e visivi AI avanzati per le aziende. La sua famiglia di modelli include la serie Claude di Anthropic, la serie Llama 3.1 di Meta e altro, coprendo una varietà di opzioni da leggere a ad alte prestazioni, supportando generazione di testo, dialogo, elaborazione di immagini e altro, adatta a diverse applicazioni aziendali di varie dimensioni e necessità."
},
+ "cloudflare": {
+ "description": "Esegui modelli di machine learning alimentati da GPU serverless sulla rete globale di Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek è un'azienda focalizzata sulla ricerca e applicazione della tecnologia AI, il cui ultimo modello DeepSeek-V2.5 combina capacità di dialogo generico e elaborazione del codice, realizzando miglioramenti significativi nell'allineamento delle preferenze umane, nei compiti di scrittura e nel rispetto delle istruzioni."
},
+ "doubao": {
+ "description": "Il grande modello sviluppato internamente da ByteDance. Validato attraverso oltre 50 scenari aziendali interni, con un utilizzo quotidiano di trilioni di token che affinano continuamente il modello, offre diverse capacità multimodali, creando esperienze aziendali ricche con risultati di alta qualità."
+ },
"fireworksai": {
"description": "Fireworks AI è un fornitore leader di servizi di modelli linguistici avanzati, focalizzato su chiamate funzionali e elaborazione multimodale. Il suo ultimo modello Firefunction V2, basato su Llama-3, è ottimizzato per chiamate di funzione, dialogo e rispetto delle istruzioni. Il modello di linguaggio visivo FireLLaVA-13B supporta input misti di immagini e testo. Altri modelli notevoli includono la serie Llama e la serie Mixtral, offrendo supporto efficiente per il rispetto e la generazione di istruzioni multilingue."
},
+ "giteeai": {
+ "description": "L'API Serverless di Gitee AI fornisce agli sviluppatori di AI un servizio API di inferenza di modelli di grandi dimensioni fuori dagli schemi."
+ },
"github": {
"description": "Con i modelli di GitHub, gli sviluppatori possono diventare ingegneri AI e costruire con i modelli AI leader del settore."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Il motore di inferenza LPU di Groq ha mostrato prestazioni eccezionali nei recenti benchmark indipendenti sui modelli di linguaggio di grandi dimensioni (LLM), ridefinendo gli standard delle soluzioni AI con la sua incredibile velocità ed efficienza. Groq rappresenta una velocità di inferenza istantanea, mostrando buone prestazioni nelle implementazioni basate su cloud."
},
+ "higress": {
+ "description": "Higress è un gateway API cloud-native, nato all'interno di Alibaba per risolvere i problemi causati dal ricaricamento di Tengine sulle connessioni persistenti e per migliorare le capacità di bilanciamento del carico di gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "L'API di Inferenza di HuggingFace offre un modo rapido e gratuito per esplorare migliaia di modelli per una varietà di compiti. Che tu stia prototipando una nuova applicazione o cercando di sperimentare le funzionalità del machine learning, questa API ti consente di accedere immediatamente a modelli ad alte prestazioni in diversi ambiti."
+ },
+ "hunyuan": {
+ "description": "Un modello di linguaggio sviluppato da Tencent, dotato di potenti capacità di creazione in cinese, abilità di ragionamento logico in contesti complessi e capacità affidabili di esecuzione dei compiti."
+ },
+ "internlm": {
+ "description": "Un'organizzazione open source dedicata alla ricerca e allo sviluppo di strumenti per modelli di grandi dimensioni. Fornisce a tutti gli sviluppatori di AI una piattaforma open source efficiente e facile da usare, rendendo le tecnologie e gli algoritmi all'avanguardia accessibili a tutti."
+ },
+ "jina": {
+ "description": "Jina AI, fondata nel 2020, è una delle principali aziende di ricerca AI. La nostra piattaforma di base per la ricerca include modelli vettoriali, riordinatori e piccoli modelli linguistici, per aiutare le aziende a costruire applicazioni di ricerca generativa e multimodale affidabili e di alta qualità."
+ },
+ "lmstudio": {
+ "description": "LM Studio è un'applicazione desktop per sviluppare e sperimentare LLM sul tuo computer."
+ },
"minimax": {
"description": "MiniMax è un'azienda di tecnologia dell'intelligenza artificiale generale fondata nel 2021, dedicata alla co-creazione di intelligenza con gli utenti. MiniMax ha sviluppato modelli generali di diverse modalità, tra cui un modello di testo MoE con trilioni di parametri, un modello vocale e un modello visivo. Ha anche lanciato applicazioni come Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI è una piattaforma che offre API per vari modelli di linguaggio di grandi dimensioni e generazione di immagini AI, flessibile, affidabile e conveniente. Supporta i più recenti modelli open source come Llama3 e Mistral, fornendo soluzioni API complete, user-friendly e scalabili per lo sviluppo di applicazioni AI, adatte alla rapida crescita delle startup AI."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ fornisce contenitori per l'inferenza di microservizi accelerati da GPU self-hosted, supportando il deployment di modelli AI pre-addestrati e personalizzati su cloud, data center, PC RTX™ AI e workstation."
+ },
"ollama": {
"description": "I modelli forniti da Ollama coprono ampiamente aree come generazione di codice, operazioni matematiche, elaborazione multilingue e interazioni conversazionali, supportando esigenze diversificate per implementazioni aziendali e localizzate."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity è un fornitore leader di modelli di generazione di dialogo, offrendo vari modelli avanzati Llama 3.1, supportando applicazioni online e offline, particolarmente adatti per compiti complessi di elaborazione del linguaggio naturale."
},
+ "ppio": {
+ "description": "PPIO Paeou Cloud offre servizi API per modelli open source stabili e ad alto rapporto qualità-prezzo, supportando l'intera gamma di DeepSeek, Llama, Qwen e altri modelli di grandi dimensioni leader del settore."
+ },
"qwen": {
"description": "Qwen è un modello di linguaggio di grande scala sviluppato autonomamente da Alibaba Cloud, con potenti capacità di comprensione e generazione del linguaggio naturale. Può rispondere a varie domande, creare contenuti testuali, esprimere opinioni e scrivere codice, svolgendo un ruolo in vari settori."
},
+ "sambanova": {
+ "description": "SambaNova Cloud consente agli sviluppatori di utilizzare facilmente i migliori modelli open source e di godere della velocità di inferenza più rapida."
+ },
+ "sensenova": {
+ "description": "SenseTime offre servizi di modelli di grandi dimensioni full-stack, supportati dalla potente infrastruttura di SenseTime."
+ },
"siliconcloud": {
"description": "SiliconFlow si impegna ad accelerare l'AGI per il bene dell'umanità, migliorando l'efficienza dell'AI su larga scala attraverso stack GenAI facili da usare e a basso costo."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "L'Istituto di Automazione dell'Accademia Cinese delle Scienze e l'Istituto di Ricerca sull'Intelligenza Artificiale di Wuhan hanno lanciato una nuova generazione di modelli di grandi dimensioni multimodali, supportando domande e risposte a più turni, creazione di testi, generazione di immagini, comprensione 3D, analisi dei segnali e altre attività di domanda e risposta complete, con capacità cognitive, di comprensione e di creazione più forti, offrendo un'esperienza interattiva completamente nuova."
},
+ "tencentcloud": {
+ "description": "La potenza atomica del motore di conoscenza (LLM Knowledge Engine Atomic Power) è una capacità completa di domande e risposte sviluppata sulla base del motore di conoscenza, rivolta a imprese e sviluppatori, che offre la possibilità di costruire e sviluppare applicazioni modello in modo flessibile. Puoi assemblare il tuo servizio modello esclusivo utilizzando diverse capacità atomiche, richiamando servizi di analisi documentale, suddivisione, embedding, riscrittura multipla e altro, per personalizzare il tuo business AI esclusivo."
+ },
"togetherai": {
"description": "Together AI si impegna a raggiungere prestazioni leader attraverso modelli AI innovativi, offrendo ampie capacità di personalizzazione, inclusi supporto per scalabilità rapida e processi di distribuzione intuitivi, per soddisfare le varie esigenze aziendali."
},
"upstage": {
"description": "Upstage si concentra sullo sviluppo di modelli AI per varie esigenze commerciali, inclusi Solar LLM e document AI, con l'obiettivo di realizzare un'intelligenza artificiale generale artificiale (AGI) per il lavoro. Crea semplici agenti di dialogo tramite Chat API e supporta chiamate funzionali, traduzioni, embedding e applicazioni specifiche del settore."
},
+ "vertexai": {
+ "description": "La serie Gemini di Google è il suo modello AI più avanzato e versatile, sviluppato da Google DeepMind, progettato per essere multimodale e supportare la comprensione e l'elaborazione senza soluzione di continuità di testo, codice, immagini, audio e video. Adatta a una varietà di ambienti, dai data center ai dispositivi mobili, migliora notevolmente l'efficienza e l'ampia applicabilità dei modelli AI."
+ },
+ "vllm": {
+ "description": "vLLM è una libreria veloce e facile da usare per l'inferenza e i servizi LLM."
+ },
+ "volcengine": {
+ "description": "La piattaforma di sviluppo dei servizi di modelli di grandi dimensioni lanciata da ByteDance, offre servizi di invocazione di modelli ricchi di funzionalità, sicuri e competitivi in termini di prezzo, fornendo anche dati sui modelli, messa a punto, inferenza, valutazione e altre funzionalità end-to-end, garantendo in modo completo lo sviluppo e l'implementazione delle vostre applicazioni AI."
+ },
+ "wenxin": {
+ "description": "Piattaforma di sviluppo e servizi per modelli di grandi dimensioni e applicazioni AI native, a livello aziendale, che offre la catena di strumenti completa e facile da usare per lo sviluppo di modelli di intelligenza artificiale generativa e per l'intero processo di sviluppo delle applicazioni."
+ },
+ "xai": {
+ "description": "xAI è un'azienda dedicata alla costruzione di intelligenza artificiale per accelerare le scoperte scientifiche umane. La nostra missione è promuovere la nostra comprensione collettiva dell'universo."
+ },
"zeroone": {
"description": "01.AI si concentra sulla tecnologia AI dell'era 2.0, promuovendo attivamente l'innovazione e l'applicazione di \"uomo + intelligenza artificiale\", utilizzando modelli potenti e tecnologie AI avanzate per migliorare la produttività umana e realizzare l'abilitazione tecnologica."
},
diff --git a/DigitalHumanWeb/locales/it-IT/setting.json b/DigitalHumanWeb/locales/it-IT/setting.json
index 03dfa64..8916372 100644
--- a/DigitalHumanWeb/locales/it-IT/setting.json
+++ b/DigitalHumanWeb/locales/it-IT/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Configurazione del modello personalizzato",
"tokens": {
- "title": "Numero massimo di token",
- "unlimited": "illimitato"
+ "title": "Numero massimo di token"
},
"vision": {
"extra": "Questa configurazione attiverà solo la capacità di caricamento delle immagini nell'app, se il riconoscimento è supportato dipende interamente dal modello stesso, ti invitiamo a testare l'usabilità del riconoscimento visivo di questo modello.",
@@ -98,6 +97,7 @@
"title": "Utilizzo del modo di richiesta del client"
},
"fetcher": {
+ "clear": "Cancella il modello ottenuto",
"fetch": "Ottenere l'elenco dei modelli",
"fetching": "Recupero dell'elenco dei modelli in corso...",
"latestTime": "Ultimo aggiornamento: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Se creare automaticamente un argomento durante la conversazione, valido solo per le conversazioni temporanee",
"title": "Abilita la creazione automatica di argomenti"
},
- "enableCompressThreshold": {
- "title": "Abilita la soglia di compressione della lunghezza dei messaggi storici"
+ "enableCompressHistory": {
+ "title": "Attiva il riassunto automatico della cronologia dei messaggi"
},
"enableHistoryCount": {
"alias": "Illimitato",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Abilita limite di risposta singola"
},
+ "enableReasoningEffort": {
+ "title": "Attiva la regolazione dell'intensità del ragionamento"
+ },
"frequencyPenalty": {
- "desc": "Più alto è il valore, più probabile è la riduzione delle parole ripetute",
- "title": "Penalità di frequenza"
+ "desc": "Maggiore è il valore, più ricca e varia sarà la scelta delle parole; minore è il valore, più semplici e dirette saranno le parole",
+ "title": "Ricchezza del vocabolario"
},
"maxTokens": {
"desc": "Numero massimo di token utilizzati per interazione singola",
@@ -212,19 +215,31 @@
"desc": "Modello {{provider}}",
"title": "Modello"
},
+ "params": {
+ "title": "Parametri avanzati"
+ },
"presencePenalty": {
- "desc": "Più alto è il valore, più probabile è l'estensione a nuovi argomenti",
- "title": "Freschezza dell'argomento"
+ "desc": "Maggiore è il valore, maggiore sarà la tendenza a esprimere in modi diversi, evitando ripetizioni; minore è il valore, maggiore sarà la tendenza a utilizzare concetti o narrazioni ripetute, rendendo l'espressione più coerente",
+ "title": "Divergenza espressiva"
+ },
+ "reasoningEffort": {
+ "desc": "Maggiore è il valore, più forte è la capacità di ragionamento, ma potrebbe aumentare il tempo di risposta e il consumo di Token",
+ "options": {
+ "high": "Alto",
+ "low": "Basso",
+ "medium": "Medio"
+ },
+ "title": "Intensità del ragionamento"
},
"temperature": {
- "desc": "Più alto è il valore, più casuale è la risposta",
- "title": "Casualità",
- "titleWithValue": "Casualità {{value}}"
+ "desc": "Maggiore è il valore, più creativi e fantasiosi saranno le risposte; minore è il valore, più rigorose saranno le risposte",
+ "title": "Attività Creativa",
+ "warning": "Un valore troppo alto per l'attività creativa potrebbe generare output illeggibili"
},
- "title": "Impostazioni del modello",
+ "title": "Impostazioni del Modello",
"topP": {
- "desc": "Simile alla casualità, ma non modificare insieme alla casualità",
- "title": "Campionamento principale"
+ "desc": "Considera quante possibilità, maggiore è il valore, più risposte potenziali vengono accettate; minore è il valore, più si tende a scegliere la risposta più probabile. Non si consiglia di modificarlo insieme all'attività creativa",
+ "title": "Apertura Mentale"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Modello specificato per generare nome, descrizione, avatar e etichetta dell'assistente",
"title": "Genera automaticamente informazioni sull'assistente"
},
+ "customPrompt": {
+ "addPrompt": "Aggiungi suggerimento personalizzato",
+ "desc": "Una volta compilato, l'assistente di sistema utilizzerà il suggerimento personalizzato nella generazione dei contenuti",
+ "placeholder": "Inserisci il suggerimento personalizzato",
+ "title": "Suggerimento personalizzato"
+ },
+ "historyCompress": {
+ "label": "Modello di storia delle conversazioni",
+ "modelDesc": "Specifica il modello utilizzato per comprimere la storia delle conversazioni",
+ "title": "Riepilogo automatico della storia delle conversazioni"
+ },
"queryRewrite": {
"label": "Modello di riscrittura delle domande",
"modelDesc": "Modello specificato per ottimizzare le domande degli utenti",
- "title": "Banca dati"
+ "title": "Riscrittura delle domande del knowledge base"
+ },
+ "thread": {
+ "label": "Modello di denominazione dei sottoargomenti",
+ "modelDesc": "Modello designato per la rinominazione automatica dei sottoargomenti",
+ "title": "Rinominazione automatica dei sottoargomenti"
},
"title": "Assistente di sistema",
"topic": {
@@ -395,6 +426,7 @@
"common": "Impostazioni comuni",
"experiment": "实验",
"llm": "Modello linguistico",
+ "provider": "Fornitore di servizi AI",
"sync": "云端同步",
"system-agent": "Assistente di sistema",
"tts": "Servizio vocale"
diff --git a/DigitalHumanWeb/locales/it-IT/thread.json b/DigitalHumanWeb/locales/it-IT/thread.json
new file mode 100644
index 0000000..e658990
--- /dev/null
+++ b/DigitalHumanWeb/locales/it-IT/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Stai per eliminare questo sottoargomento. Una volta eliminato, non potrà essere ripristinato. Ti preghiamo di procedere con cautela."
+ },
+ "newPortalThread": {
+ "includeContext": "Includi il contesto della discussione",
+ "title": "Avvia un nuovo sottoargomento"
+ },
+ "notSupportMultiModals": "Attualmente i sottoargomenti non supportano il caricamento di file/immagini. Se hai bisogno, sentiti libero di lasciare un messaggio: <1>💬 Discussione1>"
+}
diff --git a/DigitalHumanWeb/locales/it-IT/tool.json b/DigitalHumanWeb/locales/it-IT/tool.json
index 3ec2f38..12339bb 100644
--- a/DigitalHumanWeb/locales/it-IT/tool.json
+++ b/DigitalHumanWeb/locales/it-IT/tool.json
@@ -6,5 +6,23 @@
"generating": "Generazione in corso...",
"images": "Immagini:",
"prompt": "parola chiave"
+ },
+ "search": {
+ "createNewSearch": "Crea una nuova registrazione di ricerca",
+ "emptyResult": "Nessun risultato trovato, per favore modifica le parole chiave e riprova",
+ "genAiMessage": "Crea messaggio assistente",
+ "includedTooltip": "I risultati della ricerca attuale entreranno nel contesto della conversazione",
+ "keywords": "Parole chiave:",
+ "scoreTooltip": "Punteggio di rilevanza, un punteggio più alto indica una maggiore pertinenza rispetto alle parole chiave di ricerca",
+ "searchBar": {
+ "button": "Cerca",
+ "placeholder": "Parole chiave",
+ "tooltip": "Ricaricherà i risultati di ricerca e creerà un nuovo messaggio di sintesi"
+ },
+ "searchEngine": "Motore di ricerca:",
+ "searchResult": "Numero di ricerche:",
+ "summary": "Riepilogo",
+ "summaryTooltip": "Riepiloga il contenuto attuale",
+ "viewMoreResults": "Visualizza altri {{results}} risultati"
}
}
diff --git a/DigitalHumanWeb/locales/it-IT/topic.json b/DigitalHumanWeb/locales/it-IT/topic.json
new file mode 100644
index 0000000..947bcab
--- /dev/null
+++ b/DigitalHumanWeb/locales/it-IT/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Rinomina automaticamente",
+ "confirmRemoveAll": "Stai per eliminare tutti i temi. Dopo l'eliminazione, non sarà possibile recuperarli. Procedi con cautela.",
+ "confirmRemoveTopic": "Stai per eliminare questo tema. Dopo l'eliminazione, non sarà possibile recuperarlo. Procedi con cautela.",
+ "confirmRemoveUnstarred": "Stai per eliminare i temi non contrassegnati. Dopo l'eliminazione, non sarà possibile recuperarli. Procedi con cautela.",
+ "duplicate": "Crea una copia",
+ "export": "Esporta il tema",
+ "removeAll": "Elimina tutti i temi",
+ "removeUnstarred": "Elimina i temi non contrassegnati"
+ },
+ "defaultTitle": "Tema predefinito",
+ "duplicateLoading": "Copia del tema in corso...",
+ "duplicateSuccess": "Copia del tema riuscita",
+ "favorite": "Preferito",
+ "groupMode": {
+ "ascMessages": "In ordine crescente per numero di messaggi",
+ "byTime": "Raggruppa per tempo",
+ "descMessages": "In ordine decrescente per numero di messaggi",
+ "flat": "Non raggruppare"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Questo mese",
+ "today": "Oggi",
+ "week": "Questa settimana",
+ "yesterday": "Ieri"
+ }
+ },
+ "guide": {
+ "desc": "Clicca sul pulsante a sinistra per salvare la conversazione attuale come tema storico e avviare una nuova conversazione.",
+ "title": "Elenco dei temi"
+ },
+ "searchPlaceholder": "Cerca temi...",
+ "searchResultEmpty": "Nessun risultato trovato",
+ "temp": "Temporaneo",
+ "title": "Tema"
+}
diff --git a/DigitalHumanWeb/locales/it-IT/welcome.json b/DigitalHumanWeb/locales/it-IT/welcome.json
index 4f7a727..7f9aca5 100644
--- a/DigitalHumanWeb/locales/it-IT/welcome.json
+++ b/DigitalHumanWeb/locales/it-IT/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Importa configurazione",
- "market": "Esplora il mercato",
- "start": "Inizia subito"
- },
"guide": {
"agents": {
"replaceBtn": "Cambia gruppo",
diff --git a/DigitalHumanWeb/locales/ja-JP/auth.json b/DigitalHumanWeb/locales/ja-JP/auth.json
index 0caf556..a018830 100644
--- a/DigitalHumanWeb/locales/ja-JP/auth.json
+++ b/DigitalHumanWeb/locales/ja-JP/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "先月",
+ "recent30Days": "過去30日間"
+ },
+ "header": {
+ "desc": "アカウント情報を管理します。",
+ "title": "アカウント"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "非アクティブ",
+ "more": "アクティブ"
+ },
+ "months": {
+ "apr": "4月",
+ "aug": "8月",
+ "dec": "12月",
+ "feb": "2月",
+ "jan": "1月",
+ "jul": "7月",
+ "jun": "6月",
+ "mar": "3月",
+ "may": "5月",
+ "nov": "11月",
+ "oct": "10月",
+ "sep": "9月"
+ },
+ "tooltip": "{{date}} に {{count}} 件のメッセージを送信しました",
+ "totalCount": "過去1年間に送信されたメッセージは合計で {{count}} 件です"
+ },
"login": "ログイン",
- "loginOrSignup": "ログイン / 登録",
- "profile": "プロフィール",
- "security": "セキュリティ",
+ "loginOrSignup": "ログイン / サインアップ",
+ "profile": {
+ "avatar": "アバター",
+ "email": "メールアドレス",
+ "sso": {
+ "loading": "リンクされたサードパーティアカウントを読み込み中",
+ "providers": "接続されたアカウント",
+ "unlink": {
+ "description": "解除すると、{{provider}} アカウント「{{providerAccountId}}」を使用してログインできなくなります。現在のアカウントに{{provider}} アカウントを再度リンクする必要がある場合は、{{provider}} アカウントのメールアドレスが {{email}} であることを確認してください。ログイン時に自動的に現在のログインアカウントにリンクされます。",
+ "forbidden": "少なくとも1つのサードパーティアカウントをリンクしておく必要があります。",
+ "title": "サードパーティアカウント {{provider}} を解除しますか?"
+ }
+ },
+ "username": "ユーザー名"
+ },
"signout": "ログアウト",
- "signup": "サインアップ"
+ "signup": "サインアップ",
+ "stats": {
+ "aiheatmaps": "アクティビティインデックス",
+ "assistants": "アシスタント",
+ "assistantsRank": {
+ "left": "アシスタント",
+ "right": "トピック",
+ "title": "アシスタント使用ランク"
+ },
+ "createdAt": "登録日",
+ "days": "日",
+ "empty": {
+ "desc": "チャットデータをもっと蓄積してください",
+ "title": "データなし"
+ },
+ "lastYearActivity": "過去1年間のアクティビティ",
+ "loginGuide": {
+ "f1": "無料の使用量を取得する",
+ "f2": "複数デバイスでメッセージを同期する",
+ "f3": "豊富なアシスタントを持つ",
+ "f4": "強力なプラグインを探索する",
+ "title": "ログイン後にできること:"
+ },
+ "messages": "メッセージ",
+ "modelsRank": {
+ "left": "モデル",
+ "right": "メッセージ",
+ "title": "モデル使用ランク"
+ },
+ "share": {
+ "title": "私のAIアクティビティインデックス"
+ },
+ "topics": "トピック",
+ "topicsRank": {
+ "left": "トピック",
+ "right": "メッセージ",
+ "title": "トピックコンテンツランク"
+ },
+ "updatedAt": "更新日",
+ "welcome": "{{username}}さん、これはあなたの {{days}} 日目の {{appName}} です",
+ "words": "単語"
+ },
+ "tab": {
+ "profile": "プロフィール",
+ "security": "セキュリティ",
+ "stats": "統計"
+ }
}
diff --git a/DigitalHumanWeb/locales/ja-JP/changelog.json b/DigitalHumanWeb/locales/ja-JP/changelog.json
new file mode 100644
index 0000000..f8106c0
--- /dev/null
+++ b/DigitalHumanWeb/locales/ja-JP/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Xで私たちをフォロー",
+ "subscribeToUpdates": "更新を購読",
+ "versions": "バージョンの詳細"
+ },
+ "addedWhileAway": "あなたが離れている間に、新しい機能を追加しました。",
+ "allChangelog": "すべての更新ログを見る",
+ "description": "{{appName}}の新機能と改善を継続的に追跡",
+ "pagination": {
+ "next": "次のページ",
+ "older": "履歴の変更を表示"
+ },
+ "readDetails": "詳細を読む",
+ "title": "更新ログ",
+ "versionDetails": "バージョンの詳細",
+ "welcomeBack": "お帰りなさい!"
+}
diff --git a/DigitalHumanWeb/locales/ja-JP/chat.json b/DigitalHumanWeb/locales/ja-JP/chat.json
index fafb0c2..9d6c878 100644
--- a/DigitalHumanWeb/locales/ja-JP/chat.json
+++ b/DigitalHumanWeb/locales/ja-JP/chat.json
@@ -8,6 +8,7 @@
"agents": "エージェント",
"artifact": {
"generating": "生成中",
+ "inThread": "サブトピックでは表示できません。メインの対話エリアに切り替えてください。",
"thinking": "思考中",
"thought": "思考過程",
"unknownTitle": "未命名の作品"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} のコピー",
"emptyAgent": "エージェントがいません",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "単一の対話生成コストは最大90%削減され、応答速度は4倍向上します(<1>詳細はこちら1>)。有効にすると、過去のメッセージ数制限が自動的に無効になります。",
+ "title": "コンテキストキャッシュを有効にする"
+ },
+ "enableReasoning": {
+ "desc": "Claude Thinkingメカニズムに基づく制限(<1>詳細はこちら1>)により、有効にすると過去のメッセージ数制限が自動的に無効になります。",
+ "title": "深い思考を有効にする"
+ },
+ "reasoningBudgetToken": {
+ "title": "思考消費トークン"
+ },
+ "title": "モデル拡張機能"
+ },
+ "history": {
+ "title": "アシスタントは最後の{{count}}件のメッセージのみを記憶します"
+ },
"historyRange": "履歴範囲",
+ "historySummary": "履歴メッセージの要約",
"inbox": {
"desc": "脳のクラスターを起動し、創造性を引き出しましょう。あなたのスマートアシスタントは、あなたとすべてのことについてここでコミュニケーションします。",
"title": "気軽におしゃべり"
@@ -45,6 +64,9 @@
"stop": "停止",
"warp": "改行"
},
+ "intentUnderstanding": {
+ "title": "あなたの意図を理解し、分析しています..."
+ },
"knowledgeBase": {
"all": "すべてのコンテンツ",
"allFiles": "すべてのファイル",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "削除して再生成",
+ "deleteDisabledByThreads": "サブトピックが存在するため、削除できません。",
"regenerate": "再生成"
},
+ "messages": {
+ "modelCard": {
+ "credit": "クレジット",
+ "creditPricing": "価格設定",
+ "creditTooltip": "カウントを容易にするために、1ドルを1Mクレジットに換算します。例えば、$3/Mトークンは3クレジット/トークンに相当します。",
+ "pricing": {
+ "inputCachedTokens": "キャッシュ入力 {{amount}}/クレジット · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M 文字",
+ "inputMinutes": "${{amount}}/分",
+ "inputTokens": "入力 {{amount}}/クレジット · ${{amount}}/M",
+ "outputTokens": "出力 {{amount}}/クレジット · ${{amount}}/M",
+ "writeCacheInputTokens": "キャッシュ入力の書き込み {{amount}}/ポイント · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "平均単価",
+ "input": "入力",
+ "inputAudio": "音声入力",
+ "inputCached": "キャッシュ入力",
+ "inputCitation": "引用入力",
+ "inputText": "テキスト入力",
+ "inputTitle": "入力の詳細",
+ "inputUncached": "未キャッシュ入力",
+ "inputWriteCached": "入力キャッシュ書き込み",
+ "output": "出力",
+ "outputAudio": "音声出力",
+ "outputText": "テキスト出力",
+ "outputTitle": "出力の詳細",
+ "reasoning": "深い思考",
+ "title": "生成の詳細",
+ "total": "合計消費"
+ }
+ },
"newAgent": "新しいエージェント",
"pin": "ピン留め",
"pinOff": "ピン留め解除",
@@ -81,6 +137,32 @@
},
"regenerate": "再生成",
"roleAndArchive": "役割とアーカイブ",
+ "search": {
+ "grounding": {
+ "searchQueries": "検索キーワード",
+ "title": "検索結果が {{count}} 件見つかりました"
+ },
+ "mode": {
+ "auto": {
+ "desc": "会話の内容に基づいて、検索が必要かどうかを自動的に判断します",
+ "title": "インテリジェント接続"
+ },
+ "off": {
+ "desc": "モデルの基本知識のみを使用し、ネット検索は行いません",
+ "title": "接続をオフ"
+ },
+ "on": {
+ "desc": "最新情報を取得するために継続的にネット検索を行います",
+ "title": "常に接続"
+ },
+ "useModelBuiltin": "モデル内蔵の検索エンジンを使用"
+ },
+ "searchModel": {
+ "desc": "現在のモデルは関数呼び出しをサポートしていないため、関数呼び出しをサポートするモデルと組み合わせてネット検索を行う必要があります",
+ "title": "検索補助モデル"
+ },
+ "title": "ネット接続検索"
+ },
"searchAgentPlaceholder": "検索アシスタント...",
"sendPlaceholder": "チャット内容を入力してください...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "グループ名は1〜20文字で入力してください"
},
"shareModal": {
+ "copy": "コピー",
"download": "スクリーンショットをダウンロード",
+ "downloadFile": "ファイルをダウンロード",
+ "exportTitle": "デフォルトタイトル",
"imageType": "画像形式",
+ "includeTool": "ツールメッセージを含める",
+ "includeUser": "ユーザーメッセージを含める",
"screenshot": "スクリーンショット",
"settings": "エクスポート設定",
- "shareToShareGPT": "ShareGPT 共有リンクを生成",
+ "text": "テキスト",
"withBackground": "背景画像を含む",
"withFooter": "フッターを含む",
"withPluginInfo": "プラグイン情報を含む",
+ "withRole": "メッセージの役割を含める",
"withSystemRole": "エージェントの役割を含む"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "認識中...",
"prettifying": "整形中..."
},
- "temp": "一時的",
+ "thread": {
+ "divider": "サブトピック",
+ "threadMessageCount": "{{messageCount}} 件のメッセージ",
+ "title": "サブトピック"
+ },
"tokenDetails": {
"chats": "チャットメッセージ",
+ "historySummary": "履歴の要約",
"rest": "残り利用可能",
"systemRole": "システムロール設定",
"title": "コンテキストの詳細",
@@ -131,29 +224,10 @@
"used": "使用済み"
},
"topic": {
- "actions": {
- "autoRename": "自動リネーム",
- "duplicate": "コピーを作成",
- "export": "トピックをエクスポート"
- },
"checkOpenNewTopic": "新しいトピックを開始しますか?",
"checkSaveCurrentMessages": "現在の会話をトピックとして保存しますか?",
- "confirmRemoveAll": "すべてのトピックを削除します。削除した後は元に戻すことはできません。注意して操作してください。",
- "confirmRemoveTopic": "このトピックを削除します。削除した後は元に戻すことはできません。注意して操作してください。",
- "confirmRemoveUnstarred": "スターをつけていないトピックを削除します。削除した後は元に戻すことはできません。注意して操作してください。",
- "defaultTitle": "デフォルトトピック",
- "duplicateLoading": "トピックを複製中...",
- "duplicateSuccess": "トピックの複製に成功しました",
- "guide": {
- "desc": "左側のボタンをクリックして、現在の会話を保存し、新しい会話を開始できます",
- "title": "トピックリスト"
- },
"openNewTopic": "新しいトピックを開く",
- "removeAll": "すべてのトピックを削除",
- "removeUnstarred": "スターをつけていないトピックを削除",
- "saveCurrentMessages": "現在の会話をトピックとして保存",
- "searchPlaceholder": "トピックを検索...",
- "title": "トピックリスト"
+ "saveCurrentMessages": "現在の会話をトピックとして保存"
},
"translate": {
"action": "翻訳",
@@ -184,5 +258,6 @@
"processing": "ファイル処理中..."
}
}
- }
+ },
+ "zenMode": "集中モード"
}
diff --git a/DigitalHumanWeb/locales/ja-JP/common.json b/DigitalHumanWeb/locales/ja-JP/common.json
index 119b4df..0beea19 100644
--- a/DigitalHumanWeb/locales/ja-JP/common.json
+++ b/DigitalHumanWeb/locales/ja-JP/common.json
@@ -9,15 +9,79 @@
"title": "{{name}} を体験してみてください"
}
},
- "appInitializing": "アプリケーションを初期化しています...",
+ "appLoading": {
+ "appIdle": "起動準備中",
+ "appInitializing": "アプリケーションを起動しています...",
+ "failed": "申し訳ありませんが、アプリの初期化に失敗しました。詳細を確認して問題を調査してください。",
+ "finished": "データベースの初期化が完了しました",
+ "goToChat": "チャットページを読み込んでいます...",
+ "initAuth": "認証サービスを初期化しています...",
+ "initUser": "ユーザー状態を初期化しています...",
+ "initializing": "PGliteデータベースを初期化しています...",
+ "loadingDependencies": "依存関係を初期化しています...",
+ "loadingWasm": "WASM モジュールを読み込んでいます...",
+ "migrating": "データテーブルの移行を実行しています...",
+ "ready": "データベースは準備完了です",
+ "showDetail": "詳細を見る"
+ },
"autoGenerate": "自動生成",
"autoGenerateTooltip": "ヒントに基づいてエージェントの説明を自動生成します",
"autoGenerateTooltipDisabled": "ツールチップを入力してから自動生成機能を使用してください",
"back": "戻る",
"batchDelete": "バッチ削除",
"blog": "製品ブログ",
+ "branching": "サブトピックを作成",
+ "branchingDisable": "「サブトピック」機能はサーバー版のみで利用可能です。この機能が必要な場合は、サーバー展開モードに切り替えるか、LobeChat Cloudを使用してください。",
"cancel": "キャンセル",
"changelog": "変更履歴",
+ "clientDB": {
+ "autoInit": {
+ "title": "PGlite データベースの初期化"
+ },
+ "error": {
+ "desc": "申し訳ありませんが、Pglite データベースの初期化中にエラーが発生しました。ボタンをクリックして再試行してください。それでも何度もエラーが発生する場合は、<1>問題を報告1>してください。すぐに調査いたします。",
+ "detail": "エラーの原因:[{{type}}] {{message}}、詳細は以下の通りです:",
+ "retry": "再試行",
+ "title": "データベースの初期化に失敗しました"
+ },
+ "initing": {
+ "error": "エラーが発生しました。再試行してください。",
+ "idle": "初期化を待っています...",
+ "initializing": "初期化中...",
+ "loadingDependencies": "依存関係を読み込んでいます...",
+ "loadingWasmModule": "WASM モジュールを読み込んでいます...",
+ "migrating": "データテーブルの移行を実行しています...",
+ "ready": "データベースは準備完了です"
+ },
+ "modal": {
+ "desc": "PGlite クライアントデータベースを有効にし、ブラウザにチャットデータを永続的に保存し、ナレッジベースなどの高度な機能を使用します。",
+ "enable": "今すぐ有効にする",
+ "features": {
+ "knowledgeBase": {
+ "desc": "あなたの個人的な知識ベースを蓄積し、アシスタントと簡単に知識ベースの対話を開始できます(近日公開)",
+ "title": "知識ベースの対話をサポートし、第二の脳を開放する"
+ },
+ "localFirst": {
+ "desc": "チャットデータは完全にブラウザに保存され、あなたのデータは常にあなたの手の中にあります。",
+ "title": "ローカルファースト、プライバシー最優先"
+ },
+ "pglite": {
+ "desc": "PGliteに基づいて構築され、AIネイティブの高度な機能(ベクトル検索)をネイティブにサポートします。",
+ "title": "次世代クライアントストレージアーキテクチャ"
+ }
+ },
+ "init": {
+ "desc": "データベースを初期化中です。ネットワークの状況により、5〜30秒かかる場合があります。",
+ "title": "PGlite データベースを初期化中"
+ },
+ "title": "クライアントデータベースを有効にする"
+ },
+ "ready": {
+ "button": "今すぐ使用",
+ "desc": "すぐに使用したい",
+ "title": "PGlite データベースは準備完了です"
+ }
+ },
"close": "閉じる",
"contact": "お問い合わせ",
"copy": "コピー",
@@ -112,6 +176,7 @@
"en": "英語",
"en-US": "英語",
"es-ES": "スペイン語",
+ "fa-IR": "ペルシャ語",
"fi-FI": "フィンランド語",
"fr-FR": "フランス語",
"hi-IN": "ヒンディー語",
@@ -153,6 +218,7 @@
"pinOff": "ピン留め解除",
"privacy": "プライバシーポリシー",
"regenerate": "再生成",
+ "releaseNotes": "リリースノート",
"rename": "名前を変更",
"reset": "リセット",
"retry": "再試行",
@@ -209,6 +275,7 @@
},
"temp": "一時的",
"terms": "利用規約",
+ "update": "更新",
"updateAgent": "エージェント情報を更新",
"upgradeVersion": {
"action": "アップグレード",
@@ -219,6 +286,7 @@
"anonymousNickName": "匿名ユーザー",
"billing": "請求管理",
"cloud": "{{name}} を体験",
+ "community": "コミュニティ版",
"data": "データストレージ",
"defaultNickname": "コミュニティユーザー",
"discord": "コミュニティサポート",
@@ -228,7 +296,6 @@
"help": "ヘルプセンター",
"moveGuide": "設定ボタンがこちらに移動しました",
"plans": "サブスクリプションプラン",
- "preview": "プレビュー",
"profile": "アカウント管理",
"setting": "アプリ設定",
"usages": "利用量統計"
diff --git a/DigitalHumanWeb/locales/ja-JP/components.json b/DigitalHumanWeb/locales/ja-JP/components.json
index d438757..0a7f2a4 100644
--- a/DigitalHumanWeb/locales/ja-JP/components.json
+++ b/DigitalHumanWeb/locales/ja-JP/components.json
@@ -12,6 +12,7 @@
"batchChunking": "バッチ分割",
"chunking": "分割",
"chunkingTooltip": "ファイルを複数のテキストブロックに分割し、ベクトル化した後、意味検索やファイル対話に使用できます",
+ "chunkingUnsupported": "このファイルはチャンク分割をサポートしていません",
"confirmDelete": "このファイルを削除しようとしています。削除後は復元できませんので、操作を確認してください",
"confirmDeleteMultiFiles": "選択した {{count}} 個のファイルを削除しようとしています。削除後は復元できませんので、操作を確認してください",
"confirmRemoveFromKnowledgeBase": "選択した {{count}} 個のファイルを知識ベースから削除しようとしています。削除後もファイルはすべてのファイルで表示できますので、操作を確認してください",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "戻る"
},
+ "MaxTokenSlider": {
+ "unlimited": "無制限"
+ },
"ModelSelect": {
"featureTag": {
"custom": "カスタムモデル、デフォルトでは関数呼び出しとビジョン認識の両方をサポートしています。上記機能の有効性を確認してください。",
"file": "このモデルはファイルのアップロードと認識をサポートしています。",
"functionCall": "このモデルは関数呼び出し(Function Call)をサポートしています。",
+ "reasoning": "このモデルは深い思考をサポートしています",
+ "search": "このモデルはオンライン検索をサポートしています",
"tokens": "このモデルは1つのセッションあたり最大{{tokens}}トークンをサポートしています。",
"vision": "このモデルはビジョン認識をサポートしています。"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "有効なモデルがありません。設定に移動して有効にしてください。",
+ "emptyProvider": "有効なサービスプロバイダーがありません。設定に移動して有効にしてください。",
+ "goToSettings": "設定に移動",
"provider": "プロバイダー"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "ブラウザのセキュリティ制限により、Ollamaを正常に使用するにはクロスオリジン設定が必要です。",
+ "linux": {
+ "env": "[Service] セクションに `Environment` を追加し、OLLAMA_ORIGINS 環境変数を設定します:",
+ "reboot": "systemdをリロードし、Ollamaを再起動します",
+ "systemd": "systemdを呼び出してollamaサービスを編集します:"
+ },
+ "macos": "「ターミナル」アプリを開き、以下のコマンドを貼り付けてEnterを押して実行します",
+ "reboot": "実行が完了したらOllamaサービスを再起動してください",
+ "title": "Ollamaのクロスオリジンアクセスを許可する設定",
+ "windows": "Windowsでは、「コントロールパネル」をクリックし、システム環境変数を編集します。ユーザーアカウント用に「OLLAMA_ORIGINS」という名前の環境変数を新規作成し、値を * に設定して「OK/適用」をクリックして保存します"
+ },
+ "install": {
+ "description": "Ollamaが起動していることを確認してください。まだOllamaをダウンロードしていない場合は、公式サイト<1>からダウンロード1>してください。",
+ "docker": "Dockerを使用することを好む場合、Ollamaは公式のDockerイメージも提供しています。以下のコマンドでプルできます:",
+ "linux": {
+ "command": "以下のコマンドでインストールします:",
+ "manual": "または、<1>Linux手動インストールガイド1>を参照して自分でインストールすることもできます。"
+ },
+ "title": "ローカルにOllamaアプリをインストールして起動する",
+ "windowsTab": "Windows(プレビュー版)"
+ }
+ },
+ "Thinking": {
+ "thinking": "深く考えています...",
+ "thought": "深く考えました(所要時間 {{duration}} 秒)",
+ "thoughtWithDuration": "深く考えました"
}
}
diff --git a/DigitalHumanWeb/locales/ja-JP/discover.json b/DigitalHumanWeb/locales/ja-JP/discover.json
index c7bb66f..291122a 100644
--- a/DigitalHumanWeb/locales/ja-JP/discover.json
+++ b/DigitalHumanWeb/locales/ja-JP/discover.json
@@ -126,6 +126,10 @@
"title": "トピックの新鮮さ"
},
"range": "範囲",
+ "reasoning_effort": {
+ "desc": "この設定は、モデルが回答を生成する前の推論の強度を制御するために使用されます。低強度は応答速度を優先し、トークンを節約しますが、高強度はより完全な推論を提供しますが、より多くのトークンを消費し、応答速度が低下します。デフォルト値は中で、推論の正確性と応答速度のバランスを取ります。",
+ "title": "推論強度"
+ },
"temperature": {
"desc": "この設定は、モデルの応答の多様性に影響を与えます。低い値はより予測可能で典型的な応答をもたらし、高い値はより多様で珍しい応答を奨励します。値が0に設定されると、モデルは与えられた入力に対して常に同じ応答を返します。",
"title": "ランダム性"
diff --git a/DigitalHumanWeb/locales/ja-JP/error.json b/DigitalHumanWeb/locales/ja-JP/error.json
index f2b1627..aedd5ef 100644
--- a/DigitalHumanWeb/locales/ja-JP/error.json
+++ b/DigitalHumanWeb/locales/ja-JP/error.json
@@ -12,8 +12,14 @@
"retry": "再読み込み",
"title": "ページに問題が発生しました.."
},
- "fetchError": "リクエストが失敗しました",
- "fetchErrorDetail": "エラーの詳細",
+ "fetchError": {
+ "detail": "エラーの詳細",
+ "title": "リクエストに失敗しました"
+ },
+ "loginRequired": {
+ "desc": "自動的にログインページにリダイレクトされます",
+ "title": "この機能を使用するにはログインしてください"
+ },
"notFound": {
"backHome": "ホームに戻る",
"check": "URLが正しいかどうかを確認してください",
@@ -51,22 +57,34 @@
"431": "申し訳ありませんが、リクエストヘッダーフィールドが大きすぎてサーバーが処理できません",
"451": "申し訳ありませんが、法的な理由により、サーバーはこのリソースの提供を拒否しています",
"500": "申し訳ありませんが、サーバーに一時的な問題が発生し、リクエストを完了できません。しばらくしてから再試行してください",
+ "501": "申し訳ありませんが、サーバーはこのリクエストを処理する方法をまだ知りません。操作が正しいか確認してください。",
"502": "申し訳ありませんが、サーバーは一時的にサービスを提供できません。しばらくしてから再試行してください",
"503": "申し訳ありませんが、サーバーは現在、リクエストを処理できません。オーバーロードまたはメンテナンス中の可能性があります。しばらくしてから再試行してください",
"504": "申し訳ありませんが、サーバーは上位サーバーからの応答を待っていません。しばらくしてから再試行してください",
+ "505": "申し訳ありませんが、サーバーは使用しているHTTPバージョンをサポートしていません。更新して再試行してください。",
+ "506": "申し訳ありませんが、サーバーの設定に問題が発生しました。管理者に連絡して解決してください。",
+ "507": "申し訳ありませんが、サーバーのストレージスペースが不足しており、リクエストを処理できません。後でもう一度お試しください。",
+ "509": "申し訳ありませんが、サーバーの帯域幅が使い果たされました。後でもう一度お試しください。",
+ "510": "申し訳ありませんが、サーバーはリクエストされた拡張機能をサポートしていません。管理者に連絡してください。",
+ "524": "申し訳ありませんが、サーバーは応答を待っている間にタイムアウトしました。応答が遅すぎる可能性があります。後でもう一度お試しください。",
"AgentRuntimeError": "Lobe言語モデルの実行時にエラーが発生しました。以下の情報に基づいてトラブルシューティングを行うか、再試行してください。",
+ "ConnectionCheckFailed": "リクエストの返答が空です。API プロキシのアドレスの末尾に `/v1` が含まれているか確認してください。",
+ "ExceededContextWindow": "現在のリクエスト内容がモデルが処理できる長さを超えています。内容量を減らして再試行してください。",
"FreePlanLimit": "現在は無料ユーザーですので、この機能を使用することはできません。有料プランにアップグレードして継続してください。",
+ "InsufficientQuota": "申し訳ありませんが、そのキーのクォータが上限に達しました。アカウントの残高を確認するか、キーのクォータを増やしてから再試行してください。",
"InvalidAccessCode": "パスワードが正しくないか空です。正しいアクセスパスワードを入力するか、カスタムAPIキーを追加してください",
"InvalidBedrockCredentials": "Bedrockの認証に失敗しました。AccessKeyId/SecretAccessKeyを確認してから再試行してください。",
"InvalidClerkUser": "申し訳ありませんが、現在ログインしていません。続行するにはログインまたはアカウント登録を行ってください",
"InvalidGithubToken": "Githubのパーソナルアクセストークンが無効または空です。Githubのパーソナルアクセストークンを確認してから、再試行してください。",
"InvalidOllamaArgs": "Ollamaの設定が正しくありません。Ollamaの設定を確認してからもう一度お試しください",
"InvalidProviderAPIKey": "{{provider}} APIキーが正しくないか空です。{{provider}} APIキーを確認して再試行してください。",
+ "InvalidVertexCredentials": "Vertexの認証に失敗しました。認証情報を確認して再試行してください",
"LocationNotSupportError": "申し訳ありませんが、お住まいの地域ではこのモデルサービスをサポートしていません。地域制限またはサービスが利用できない可能性があります。現在の位置がこのサービスをサポートしているかどうかを確認するか、他の位置情報を使用してみてください。",
+ "ModelNotFound": "申し訳ありませんが、該当するモデルをリクエストできませんでした。モデルが存在しないか、アクセス権がない可能性があります。APIキーを変更するか、アクセス権を調整して再試行してください。",
"NoOpenAIAPIKey": "OpenAI APIキーが空です。カスタムOpenAI APIキーを追加してください。",
"OllamaBizError": "Ollamaサービスのリクエストでエラーが発生しました。以下の情報に基づいてトラブルシューティングを行うか、再度お試しください",
"OllamaServiceUnavailable": "Ollamaサービスが利用できません。Ollamaが正常に動作しているか、またはOllamaのクロスオリジン設定が正しく行われているかを確認してください",
- "OpenAIBizError": "リクエスト OpenAI サービスでエラーが発生しました。以下の情報を確認して再試行してください。",
+ "PermissionDenied": "申し訳ありませんが、このサービスにアクセスする権限がありません。あなたのキーにアクセス権があるかどうかを確認してください。",
"PluginApiNotFound": "申し訳ありませんが、プラグインのマニフェストに指定されたAPIが見つかりませんでした。リクエストメソッドとプラグインのマニフェストのAPIが一致しているかどうかを確認してください",
"PluginApiParamsError": "申し訳ありませんが、プラグインのリクエストパラメータの検証に失敗しました。パラメータとAPIの説明が一致しているかどうか確認してください",
"PluginFailToTransformArguments": "申し訳ありませんが、プラグインの引数変換に失敗しました。助手メッセージを再生成するか、より強力な Tools Calling 機能を持つAIモデルに切り替えて再試行してください",
@@ -81,8 +99,11 @@
"PluginServerError": "プラグインサーバーのリクエストエラーが発生しました。以下のエラーメッセージを参考に、プラグインのマニフェストファイル、設定、サーバー実装を確認してください",
"PluginSettingsInvalid": "このプラグインを使用するには、正しい設定が必要です。設定が正しいかどうか確認してください",
"ProviderBizError": "リクエスト {{provider}} サービスでエラーが発生しました。以下の情報を確認して再試行してください。",
+ "QuotaLimitReached": "申し訳ありませんが、現在のトークン使用量またはリクエスト回数がこのキーのクォータ上限に達しました。キーのクォータを増やすか、後でもう一度お試しください。",
"StreamChunkError": "ストリーミングリクエストのメッセージブロック解析エラーです。現在のAPIインターフェースが標準仕様に準拠しているか確認するか、APIプロバイダーにお問い合わせください。",
- "SubscriptionPlanLimit": "ご契約のクォータが使い切られましたので、この機能を使用することはできません。より高いプランにアップグレードするか、リソースパッケージを購入して継続してください。",
+ "SubscriptionKeyMismatch": "申し訳ありませんが、システムの一時的な障害により、現在のサブスクリプションの使用量が一時的に無効になっています。下のボタンをクリックしてサブスクリプションを復元するか、サポートを受けるためにメールでお問い合わせください。",
+ "SubscriptionPlanLimit": "あなたのサブスクリプションポイントは使い果たされました。この機能を使用することはできません。より高いプランにアップグレードするか、カスタムモデルAPIを設定して引き続き使用してください。",
+ "SystemTimeNotMatchError": "申し訳ありませんが、システムの時間がサーバーと一致していません。システムの時間を確認して再試行してください。",
"UnknownChatFetchError": "申し訳ありませんが、未知のリクエストエラーが発生しました。以下の情報をもとに確認するか、再試行してください。"
},
"stt": {
diff --git a/DigitalHumanWeb/locales/ja-JP/metadata.json b/DigitalHumanWeb/locales/ja-JP/metadata.json
index fbc4bcf..45ae6d8 100644
--- a/DigitalHumanWeb/locales/ja-JP/metadata.json
+++ b/DigitalHumanWeb/locales/ja-JP/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "{{appName}} の新機能と改善を継続的に追跡する",
+ "title": "更新履歴"
+ },
"chat": {
"description": "{{appName}}が提供する最高のChatGPT、Claude、Gemini、OLLaMA WebUIの体験",
"title": "{{appName}}:個人AI効率ツール、より賢い脳を手に入れよう"
diff --git a/DigitalHumanWeb/locales/ja-JP/modelProvider.json b/DigitalHumanWeb/locales/ja-JP/modelProvider.json
index 6ca08bc..9630d6e 100644
--- a/DigitalHumanWeb/locales/ja-JP/modelProvider.json
+++ b/DigitalHumanWeb/locales/ja-JP/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "AzureのAPIバージョン。YYYY-MM-DD形式に従い、[最新バージョン](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)を参照してください。",
+ "fetch": "リストを取得",
+ "title": "Azure APIバージョン"
+ },
+ "endpoint": {
+ "desc": "Azure AIプロジェクトの概要からAzure AIモデル推論エンドポイントを見つけます。",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AIエンドポイント"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Azure AIプロジェクトの概要からAPIキーを見つけます。",
+ "placeholder": "Azureキー",
+ "title": "キー"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "AWS Access Key Id を入力してください",
@@ -51,6 +69,58 @@
"title": "使用カスタム Bedrock 認証情報"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Cloudflare API Key を入力してください",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Cloudflare アカウント ID またはカスタム API アドレスを入力してください。",
+ "placeholder": "Cloudflare アカウント ID / カスタム API URL",
+ "title": "Cloudflare アカウント ID / API アドレス"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "あなたの API キーを入力してください",
+ "title": "API キー"
+ },
+ "basicTitle": "基本情報",
+ "configTitle": "設定情報",
+ "confirm": "新規作成",
+ "createSuccess": "新規作成に成功しました",
+ "description": {
+ "placeholder": "サービスプロバイダーの紹介(任意)",
+ "title": "サービスプロバイダーの紹介"
+ },
+ "id": {
+ "desc": "サービスプロバイダーの一意の識別子であり、作成後は変更できません",
+ "format": "数字、小文字のアルファベット、ハイフン(-)、およびアンダースコア(_)のみを含むことができます",
+ "placeholder": "小文字で入力してください(例: openai)。作成後は変更できません",
+ "required": "サービスプロバイダー ID を入力してください",
+ "title": "サービスプロバイダー ID"
+ },
+ "logo": {
+ "required": "正しいサービスプロバイダーのロゴをアップロードしてください",
+ "title": "サービスプロバイダーのロゴ"
+ },
+ "name": {
+ "placeholder": "サービスプロバイダーの表示名を入力してください",
+ "required": "サービスプロバイダー名を入力してください",
+ "title": "サービスプロバイダー名"
+ },
+ "proxyUrl": {
+ "required": "プロキシURLを入力してください",
+ "title": "プロキシアドレス"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "SDK タイプを選択してください",
+ "title": "リクエスト形式"
+ },
+ "title": "カスタム AI サービスプロバイダーの作成"
+ },
"github": {
"personalAccessToken": {
"desc": "あなたのGithub PATを入力してください。[こちら](https://github.com/settings/tokens)をクリックして作成します",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "あなたの HuggingFace トークンを入力してください。 [こちら](https://huggingface.co/settings/tokens) をクリックして作成します。",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace トークン"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "サービスプロバイダーは無効です",
+ "enabled": "サービスプロバイダーは有効です"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "カスタムサービスプロバイダーを追加",
+ "all": "すべて",
+ "list": {
+ "disabled": "未使用",
+ "enabled": "使用中"
+ },
+ "notFound": "検索結果が見つかりません",
+ "searchProviders": "サービスプロバイダーを検索...",
+ "sort": "カスタムソート"
+ },
"ollama": {
"checker": {
"desc": "プロキシアドレスが正しく入力されているかをテストします",
@@ -69,47 +163,173 @@
"title": "カスタムモデル名"
},
"download": {
- "desc": "Ollama is currently downloading the model. Please try not to close this page. The download will resume from where it left off if interrupted.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollamaはこのモデルをダウンロードしています。このページを閉じないでください。再ダウンロードすると中断したところから再開されます。",
+ "remainingTime": "残り時間",
+ "speed": "ダウンロード速度",
+ "title": "モデル{{model}}をダウンロード中"
},
"endpoint": {
- "desc": "Ollamaプロキシインターフェースアドレスを入力してください。ローカルで追加の指定がない場合は空白のままにしてください",
+ "desc": "http(s)://を含める必要があります。ローカルで特に指定がない場合は空白のままで構いません",
"title": "プロキシインターフェースアドレス"
},
- "setup": {
- "cors": {
- "description": "ブラウザのセキュリティ制限により、Ollama を正常に使用するにはクロスオリジンリクエストを許可する必要があります。",
- "linux": {
- "env": "[Service] セクションに `Environment` を追加し、OLLAMA_ORIGINS 環境変数を設定してください:",
- "reboot": "systemd を再読み込みして Ollama を再起動します。",
- "systemd": "systemd を呼び出して ollama サービスを編集します:"
- },
- "macos": "「ターミナル」アプリを開き、以下のコマンドを貼り付けて実行し、Enter キーを押してください",
- "reboot": "Ollama サービスを再起動するには、実行後に再起動してください",
- "title": "Ollama の CORS アクセスを許可する設定",
- "windows": "Windows 上では、「コントロールパネル」をクリックしてシステム環境変数を編集します。ユーザーアカウントに「OLLAMA_ORIGINS」という名前の環境変数を作成し、値を * に設定し、「OK/適用」をクリックして保存します"
- },
- "install": {
- "description": "Ollamaを有効にしていることを確認してください。Ollamaをまだダウンロードしていない場合は、公式サイト<1>からダウンロード1>してください。",
- "docker": "もしDockerを使用することを好む場合、Ollamaは公式Dockerイメージも提供しています。以下のコマンドを使用して取得できます:",
- "linux": {
- "command": "以下のコマンドを使用してインストール:",
- "manual": "または、<1>Linuxマニュアルインストールガイド1>を参照して手動でインストールすることもできます"
- },
- "title": "ローカルでOllamaアプリをインストールして起動する",
- "windowsTab": "Windows(プレビュー版)"
- }
- },
"title": "Ollama",
"unlock": {
- "cancel": "Cancel Download",
- "confirm": "Download",
- "description": "Enter your Ollama model tag to continue the session",
+ "cancel": "ダウンロードをキャンセル",
+ "confirm": "ダウンロード",
+ "description": "Ollamaモデルのラベルを入力して、セッションを続行してください。",
"downloaded": "{{completed}} / {{total}}",
- "starting": "Starting download...",
- "title": "Download specified Ollama model"
+ "starting": "ダウンロードを開始しています...",
+ "title": "指定されたOllamaモデルをダウンロード"
+ }
+ },
+ "providerModels": {
+ "config": {
+ "aesGcm": "あなたのキーとプロキシアドレスなどは <1>AES-GCM1> 暗号化アルゴリズムを使用して暗号化されます",
+ "apiKey": {
+ "desc": "あなたの {{name}} API キーを入力してください",
+ "placeholder": "{{name}} API キー",
+ "title": "API キー"
+ },
+ "baseURL": {
+ "desc": "http(s):// を含める必要があります",
+ "invalid": "有効なURLを入力してください",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API プロキシアドレス"
+ },
+ "checker": {
+ "button": "チェック",
+ "desc": "API キーとプロキシアドレスが正しく入力されているかテストします",
+ "pass": "チェックに合格しました",
+ "title": "接続性チェック"
+ },
+ "fetchOnClient": {
+ "desc": "クライアントリクエストモードはブラウザから直接セッションリクエストを発起し、応答速度を向上させます",
+ "title": "クライアントリクエストモードを使用"
+ },
+ "helpDoc": "設定ガイド",
+ "waitingForMore": "さらに多くのモデルが <1>接続予定1> です。お楽しみに"
+ },
+ "createNew": {
+ "title": "カスタム AI モデルの作成"
+ },
+ "item": {
+ "config": "モデルを設定",
+ "customModelCards": {
+ "addNew": "{{id}} モデルを作成して追加",
+ "confirmDelete": "このカスタムモデルを削除しようとしています。削除後は復元できませんので、慎重に操作してください。"
+ },
+ "delete": {
+ "confirm": "モデル {{displayName}} を削除してもよろしいですか?",
+ "success": "削除に成功しました",
+ "title": "モデルを削除"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Azure OpenAI で実際にリクエストされるフィールド",
+ "placeholder": "Azure でのモデルデプロイ名を入力してください",
+ "title": "モデルデプロイ名"
+ },
+ "deployName": {
+ "extra": "リクエストを送信する際に、このフィールドがモデルIDとして使用されます。",
+ "placeholder": "モデルの実際のデプロイ名またはIDを入力してください。",
+ "title": "モデルデプロイ名"
+ },
+ "displayName": {
+ "placeholder": "モデルの表示名を入力してください(例: ChatGPT、GPT-4 など)",
+ "title": "モデル表示名"
+ },
+ "files": {
+ "extra": "現在のファイルアップロード実装は一つのハック手法に過ぎず、自己責任での試行に限られます。完全なファイルアップロード機能は今後の実装をお待ちください",
+ "title": "ファイルアップロードをサポート"
+ },
+ "functionCall": {
+ "extra": "この設定は、モデルがツールを使用する機能を有効にし、モデルにツールタイプのプラグインを追加できるようにします。ただし、実際にツールを使用できるかどうかはモデル自体に依存するため、使用可能性を自分でテストしてください",
+ "title": "ツール使用のサポート"
+ },
+ "id": {
+ "extra": "作成後は変更できません。AIを呼び出す際にモデルIDとして使用されます。",
+ "placeholder": "モデルIDを入力してください。例:gpt-4o または claude-3.5-sonnet",
+ "title": "モデル ID"
+ },
+ "modalTitle": "カスタムモデル設定",
+ "reasoning": {
+ "extra": "この設定は、モデルの深い思考能力を有効にするだけです。具体的な効果はモデル自体に依存しますので、このモデルが利用可能な深い思考能力を持っているかどうかはご自身でテストしてください。",
+ "title": "深い思考をサポート"
+ },
+ "tokens": {
+ "extra": "モデルがサポートする最大トークン数を設定する",
+ "title": "最大コンテキストウィンドウ",
+ "unlimited": "無制限"
+ },
+ "vision": {
+ "extra": "この設定はアプリ内の画像アップロード設定のみを有効にします。認識のサポートはモデル自体に依存しますので、そのモデルの視覚認識機能の可用性を自分でテストしてください",
+ "title": "視覚認識をサポート"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/画像",
+ "inputCharts": "${{amount}}/M 文字",
+ "inputMinutes": "${{amount}}/分",
+ "inputTokens": "入力 ${{amount}}/M",
+ "outputTokens": "出力 ${{amount}}/M"
+ },
+ "releasedAt": "リリース日: {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "モデルを追加",
+ "disabled": "無効",
+ "disabledActions": {
+ "showMore": "すべて表示"
+ },
+ "empty": {
+ "desc": "カスタムモデルを作成するか、モデルを取得してから使用を開始してください",
+ "title": "利用可能なモデルはありません"
+ },
+ "enabled": "有効",
+ "enabledActions": {
+ "disableAll": "すべて無効にする",
+ "enableAll": "すべて有効にする",
+ "sort": "カスタムモデルの並べ替え"
+ },
+ "enabledEmpty": "有効なモデルはありません。下のリストからお気に入りのモデルを有効にしてください〜",
+ "fetcher": {
+ "clear": "取得したモデルをクリア",
+ "fetch": "モデルリストを取得",
+ "fetching": "モデルリストを取得中...",
+ "latestTime": "最終更新日時:{{time}}",
+ "noLatestTime": "まだリストを取得していません"
+ },
+ "resetAll": {
+ "conform": "現在のモデルのすべての変更をリセットしてもよろしいですか?リセット後、現在のモデルリストはデフォルトの状態に戻ります",
+ "success": "リセットに成功しました",
+ "title": "すべての変更をリセット"
+ },
+ "search": "モデルを検索...",
+ "searchResult": "{{count}} 個のモデルが見つかりました",
+ "title": "モデルリスト",
+ "total": "利用可能なモデルは合計 {{count}} 件です"
+ },
+ "searchNotFound": "検索結果が見つかりませんでした"
+ },
+ "sortModal": {
+ "success": "ソートが更新されました",
+ "title": "カスタムソート",
+ "update": "更新"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "この AI サービスプロバイダーを削除しようとしています。削除後は復元できません。削除してもよろしいですか?",
+ "deleteSuccess": "削除に成功しました",
+ "tooltip": "サービスプロバイダーの基本設定を更新",
+ "updateSuccess": "更新に成功しました"
+ },
+ "updateCustomAiProvider": {
+ "title": "カスタム AI プロバイダー設定の更新"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "あなたの Vertex AI キーを入力してください",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI キー"
}
},
"zeroone": {
diff --git a/DigitalHumanWeb/locales/ja-JP/models.json b/DigitalHumanWeb/locales/ja-JP/models.json
index c1a5c3f..826a597 100644
--- a/DigitalHumanWeb/locales/ja-JP/models.json
+++ b/DigitalHumanWeb/locales/ja-JP/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34Bは豊富な訓練サンプルを用いて業界アプリケーションで優れたパフォーマンスを提供します。"
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-ChatはYi-1.5シリーズの変種で、オープンソースのチャットモデルに属します。Yi-1.5はYiのアップグレード版で、500Bの高品質コーパスで継続的に事前訓練され、3Mの多様な微調整サンプルで微調整されています。Yiと比較して、Yi-1.5はコーディング、数学、推論、指示遵守能力においてより強力な性能を示し、優れた言語理解、常識推論、読解能力を維持しています。このモデルは4K、16K、32Kのコンテキスト長バージョンを持ち、事前訓練の総量は3.6Tトークンに達します。"
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9Bは16Kトークンをサポートし、高効率でスムーズな言語生成能力を提供します。"
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "零一万物、最新のオープンソース微調整モデル、340億パラメータ、微調整は多様な対話シーンをサポートし、高品質なトレーニングデータで人間の好みに合わせています。"
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "零一万物、最新のオープンソース微調整モデル、90億パラメータ、微調整は多様な対話シーンをサポートし、高品質なトレーニングデータで人間の好みに合わせています。"
+ },
"360gpt-pro": {
"description": "360GPT Proは360 AIモデルシリーズの重要なメンバーであり、高効率なテキスト処理能力を持ち、多様な自然言語アプリケーションシーンに対応し、長文理解や多輪対話などの機能をサポートします。"
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8Kは意味の安全性と責任指向を強調し、コンテンツの安全性に高い要求を持つアプリケーションシーンのために設計されており、ユーザー体験の正確性と堅牢性を確保します。"
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1は、ツリーサーチを使用して思考の連鎖を構築し、反省メカニズムを導入し、強化学習で訓練されたモデルであり、自己反省と誤り訂正の能力を備えています。"
+ },
"360gpt2-pro": {
"description": "360GPT2 Proは360社が発表した高級自然言語処理モデルで、卓越したテキスト生成と理解能力を備え、特に生成と創作の分野で優れたパフォーマンスを発揮し、複雑な言語変換や役割演技タスクを処理できます。"
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1は、木探索を使用して思考の連鎖を構築し、反省メカニズムを導入し、強化学習で訓練され、自己反省と誤り訂正の能力を備えています。"
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultraは星火大モデルシリーズの中で最も強力なバージョンで、ネットワーク検索のリンクをアップグレードし、テキストコンテンツの理解と要約能力を向上させています。これは、オフィスの生産性を向上させ、要求に正確に応えるための全方位のソリューションであり、業界をリードするインテリジェントな製品です。"
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "モデル能力は国内でトップであり、知識百科、長文、生成創作などの中国語タスクで海外の主流モデルを超えています。また、業界をリードするマルチモーダル能力を備え、複数の権威ある評価基準で優れたパフォーマンスを示しています。"
},
+ "Baichuan4-Air": {
+ "description": "モデル能力は国内で第一であり、知識百科、長文、生成創作などの中国語タスクで海外の主流モデルを超えています。また、業界をリードするマルチモーダル能力を持ち、多くの権威ある評価基準で優れたパフォーマンスを示しています。"
+ },
+ "Baichuan4-Turbo": {
+ "description": "モデル能力は国内で第一であり、知識百科、長文、生成創作などの中国語タスクで海外の主流モデルを超えています。また、業界をリードするマルチモーダル能力を持ち、多くの権威ある評価基準で優れたパフォーマンスを示しています。"
+ },
+ "DeepSeek-R1": {
+ "description": "最先端の効率的なLLMで、推論、数学、プログラミングに優れています。"
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1——DeepSeekスイートの中でより大きく、より賢いモデル——がLlama 70Bアーキテクチャに蒸留されました。ベンチマークテストと人間の評価に基づき、このモデルは元のLlama 70Bよりも賢く、特に数学と事実の正確性が求められるタスクで優れた性能を発揮します。"
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Qwen2.5-Math-1.5Bに基づくDeepSeek-R1蒸留モデルで、強化学習とコールドスタートデータを通じて推論性能を最適化し、オープンソースモデルがマルチタスクの基準を刷新しました。"
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Qwen2.5-14Bに基づくDeepSeek-R1蒸留モデルで、強化学習とコールドスタートデータを通じて推論性能を最適化し、オープンソースモデルがマルチタスクの基準を刷新しました。"
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1シリーズは、強化学習とコールドスタートデータを通じて推論性能を最適化し、オープンソースモデルがマルチタスクの基準を刷新し、OpenAI-o1-miniのレベルを超えました。"
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Qwen2.5-Math-7Bに基づくDeepSeek-R1蒸留モデルで、強化学習とコールドスタートデータを通じて推論性能を最適化し、オープンソースモデルがマルチタスクの基準を刷新しました。"
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-proは全く新しいアップグレード版のマルチモーダル大モデルで、任意の解像度と極端なアスペクト比の画像認識をサポートし、視覚推論、文書認識、詳細情報の理解、指示遵守能力を強化しています。"
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-liteは、極めて高速な応答速度と優れたコストパフォーマンスを備え、顧客のさまざまなシーンに柔軟な選択肢を提供します。128kコンテキストウィンドウの推論と微調整をサポートしています。"
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-liteは、極めて高速な応答速度と優れたコストパフォーマンスを備え、顧客のさまざまなシーンに柔軟な選択肢を提供します。32kコンテキストウィンドウの推論と微調整をサポートしています。"
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-liteは、極めて高速な応答速度と優れたコストパフォーマンスを備え、顧客のさまざまなシーンに柔軟な選択肢を提供します。4kコンテキストウィンドウの推論と微調整をサポートしています。"
+ },
+ "Doubao-pro-128k": {
+ "description": "最も効果的な主力モデルで、複雑なタスクの処理に適しており、参考質問応答、要約、創作、テキスト分類、ロールプレイングなどのシーンで素晴らしい結果を出します。128kコンテキストウィンドウの推論と微調整をサポートしています。"
+ },
+ "Doubao-pro-256k": {
+ "description": "最も効果的な主力モデルで、複雑なタスクの処理に適しており、参考質問応答、要約、創作、テキスト分類、ロールプレイなどのシーンで優れた効果を発揮します。256kのコンテキストウィンドウでの推論とファインチューニングをサポートします。"
+ },
+ "Doubao-pro-32k": {
+ "description": "最も効果的な主力モデルで、複雑なタスクの処理に適しており、参考質問応答、要約、創作、テキスト分類、ロールプレイングなどのシーンで素晴らしい結果を出します。32kコンテキストウィンドウの推論と微調整をサポートしています。"
+ },
+ "Doubao-pro-4k": {
+ "description": "最も効果的な主力モデルで、複雑なタスクの処理に適しており、参考質問応答、要約、創作、テキスト分類、ロールプレイングなどのシーンで素晴らしい結果を出します。4kコンテキストウィンドウの推論と微調整をサポートしています。"
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Doubao-visionモデルは豆包が提供するマルチモーダル大モデルで、強力な画像理解と推論能力、正確な指示理解能力を備えています。モデルは画像テキスト情報の抽出や画像に基づく推論タスクで強力な性能を発揮し、より複雑で広範な視覚的質問応答タスクに応用できます。"
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Doubao-visionモデルは豆包が提供するマルチモーダル大モデルで、強力な画像理解と推論能力、正確な指示理解能力を備えています。モデルは画像テキスト情報の抽出や画像に基づく推論タスクで強力な性能を発揮し、より複雑で広範な視覚的質問応答タスクに応用できます。"
+ },
+ "ERNIE-3.5-128K": {
+ "description": "百度が独自に開発したフラッグシップの大規模言語モデルで、膨大な中英語のコーパスをカバーし、強力な汎用能力を持っています。ほとんどの対話型質問応答、創作生成、プラグインアプリケーションの要件を満たすことができます。また、百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ERNIE-3.5-8K": {
+ "description": "百度が独自に開発したフラッグシップの大規模言語モデルで、膨大な中英語のコーパスをカバーし、強力な汎用能力を持っています。ほとんどの対話型質問応答、創作生成、プラグインアプリケーションの要件を満たすことができます。また、百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "百度が独自に開発したフラッグシップの大規模言語モデルで、膨大な中英語のコーパスをカバーし、強力な汎用能力を持っています。ほとんどの対話型質問応答、創作生成、プラグインアプリケーションの要件を満たすことができます。また、百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、ERNIE 3.5に比べてモデル能力が全面的にアップグレードされ、さまざまな分野の複雑なタスクシナリオに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、ERNIE 3.5に比べてモデル能力が全面的にアップグレードされ、さまざまな分野の複雑なタスクシナリオに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "百度が自主開発したフラッグシップの超大規模な言語モデルで、総合的なパフォーマンスが優れており、各分野の複雑なタスクシナリオに広く適応します;百度検索プラグインとの自動連携をサポートし、質問応答情報のタイムリーさを保証します。ERNIE 4.0に比べてパフォーマンスが向上しています。"
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、総合的なパフォーマンスが優れており、さまざまな分野の複雑なタスクシナリオに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。ERNIE 4.0に比べてパフォーマンスがさらに優れています。"
+ },
+ "ERNIE-Character-8K": {
+ "description": "百度が独自に開発した垂直シナリオ向けの大規模言語モデルで、ゲームのNPC、カスタマーサービスの対話、対話型キャラクターの役割演技などのアプリケーションシナリオに適しており、キャラクターのスタイルがより鮮明で一貫性があり、指示に従う能力が強化され、推論性能が向上しています。"
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "百度が独自に開発した軽量大規模言語モデルで、優れたモデル効果と推論性能を兼ね備え、ERNIE Liteよりも効果が優れており、低計算能力のAIアクセラレータカードでの推論使用に適しています。"
+ },
+ "ERNIE-Speed-128K": {
+ "description": "百度が2024年に最新リリースした独自開発の高性能大規模言語モデルで、汎用能力が優れており、基盤モデルとして微調整に適しており、特定のシナリオの問題をより良く処理し、優れた推論性能を持っています。"
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "百度が2024年に最新リリースした独自開発の高性能大規模言語モデルで、汎用能力が優れており、ERNIE Speedよりも効果が優れており、基盤モデルとして微調整に適しており、特定のシナリオの問題をより良く処理し、優れた推論性能を持っています。"
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B)は、革新的なモデルであり、多分野のアプリケーションや複雑なタスクに適しています。"
},
- "Max-32k": {
- "description": "Spark Max 32Kは、大規模なコンテキスト処理能力を備え、より強力なコンテキスト理解と論理推論能力を持ち、32Kトークンのテキスト入力をサポートします。長文書の読解やプライベートな知識に基づく質問応答などのシーンに適しています。"
+ "InternVL2-8B": {
+ "description": "InternVL2-8Bは、強力な視覚言語モデルで、画像とテキストのマルチモーダル処理をサポートし、画像内容を正確に認識し、関連する説明や回答を生成することができます。"
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26Bは、強力な視覚言語モデルで、画像とテキストのマルチモーダル処理をサポートし、画像内容を正確に認識し、関連する説明や回答を生成することができます。"
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "高解像度画像で優れた画像推論能力を発揮し、視覚理解アプリケーションに適しています。"
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "視覚理解エージェントアプリケーションに適した高度な画像推論能力を備えています。"
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-InstructはAlibaba Cloudが発表した最新の大規模言語モデルシリーズの一つです。この72Bモデルはコーディングや数学などの分野で顕著な能力の改善を持っています。このモデルは29以上の言語をカバーする多言語サポートも提供しており、中国語、英語などが含まれています。モデルは指示の遵守、構造化データの理解、特にJSONのような構造化出力の生成において顕著な向上を示しています。"
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-InstructはAlibaba Cloudが発表した最新の大規模言語モデルシリーズの一つです。この7Bモデルはコーディングや数学などの分野で顕著な能力の改善を持っています。このモデルは29以上の言語をカバーする多言語サポートも提供しており、中国語、英語などが含まれています。モデルは指示の遵守、構造化データの理解、特にJSONのような構造化出力の生成において顕著な向上を示しています。"
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Llama 3.1の指示調整されたテキストモデルで、多言語対話のユースケースに最適化されており、多くの利用可能なオープンソースおよびクローズドチャットモデルの中で、一般的な業界ベンチマークで優れた性能を発揮します。"
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPOは非常に柔軟なマルチモデル統合で、卓越した創造的体験を提供することを目的としています。"
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Llama 3.1の指示調整されたテキストモデルで、多言語対話のユースケースに最適化されており、多くの利用可能なオープンソースおよびクローズドチャットモデルの中で、一般的な業界ベンチマークで優れた性能を発揮します。"
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Llama 3.1の指示調整されたテキストモデルで、多言語対話のユースケースに最適化されており、多くの利用可能なオープンソースおよびクローズドチャットモデルの中で、一般的な業界ベンチマークで優れた性能を発揮します。"
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "最先端の小型言語モデルで、言語理解、優れた推論能力、テキスト生成能力を備えています。"
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "最先端の小型言語モデルで、言語理解、優れた推論能力、テキスト生成能力を備えています。"
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3は、Llamaシリーズの最先端の多言語オープンソース大規模言語モデルで、非常に低コストで405Bモデルに匹敵する性能を体験できます。Transformer構造に基づき、監視付き微調整(SFT)と人間のフィードバックによる強化学習(RLHF)を通じて有用性と安全性を向上させています。その指示調整バージョンは多言語対話に最適化されており、さまざまな業界のベンチマークで多くのオープンソースおよびクローズドチャットモデルを上回る性能を発揮します。知識のカットオフ日は2023年12月です。"
+ },
+ "MiniMax-Text-01": {
+ "description": "MiniMax-01シリーズモデルでは、大胆な革新を行いました:初めて大規模に線形注意メカニズムを実現し、従来のTransformerアーキテクチャが唯一の選択肢ではなくなりました。このモデルのパラメータ数は4560億に達し、単回のアクティベーションは459億です。モデルの総合性能は海外のトップモデルに匹敵し、世界最長の400万トークンのコンテキストを効率的に処理でき、GPT-4oの32倍、Claude-3.5-Sonnetの20倍です。"
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B)は、高精度の指示モデルであり、複雑な計算に適しています。"
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B)は、最適化された言語出力と多様なアプリケーションの可能性を提供します。"
- },
- "Phi-3-5-mini-instruct": {
- "description": "Phi-3-miniモデルのリフレッシュ版です。"
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2はさまざまな視覚と言語タスクで卓越した性能を発揮しており、文書や図表の理解、シーンテキストの理解、OCR、科学および数学の問題解決などを含みます。"
},
"Phi-3-medium-128k-instruct": {
"description": "同じPhi-3-mediumモデルですが、RAGまたは少数ショットプロンプティング用により大きなコンテキストサイズを持っています。"
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "7Bパラメータのモデルで、Phi-3-miniよりも高品質で、質の高い推論密度のデータに焦点を当てています。"
},
- "Pro-128k": {
- "description": "Spark Pro-128Kは特大のコンテキスト処理能力を備え、最大128Kのコンテキスト情報を処理でき、特に全体分析や長期的な論理関連処理が必要な長文コンテンツに適しており、複雑なテキストコミュニケーションにおいて流暢で一貫した論理と多様な引用サポートを提供します。"
+ "Phi-3.5-mini-instruct": {
+ "description": "Phi-3-miniモデルの更新版です。"
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Phi-3-visionモデルの更新版です。"
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2はさまざまな視覚と言語タスクで卓越した性能を発揮しており、文書や図表の理解、シーンテキストの理解、OCR、科学および数学の問題解決などを含みます。"
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-InstructはQwen2シリーズの指示微調整大規模言語モデルで、パラメータ規模は1.5Bです。このモデルはTransformerアーキテクチャに基づき、SwiGLU活性化関数、注意QKVバイアス、グループクエリ注意などの技術を採用しています。言語理解、生成、多言語能力、コーディング、数学、推論などの複数のベンチマークテストで優れたパフォーマンスを示し、ほとんどのオープンソースモデルを超えています。Qwen1.5-1.8B-Chatと比較して、Qwen2-1.5B-InstructはMMLU、HumanEval、GSM8K、C-Eval、IFEvalなどのテストで顕著な性能向上を示していますが、パラメータ数はわずかに少ないです。"
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-InstructはQwen2シリーズの指示微調整大規模言語モデルで、パラメータ規模は7Bです。このモデルはTransformerアーキテクチャに基づき、SwiGLU活性化関数、注意QKVバイアス、グループクエリ注意などの技術を採用しています。大規模な入力を処理することができます。このモデルは言語理解、生成、多言語能力、コーディング、数学、推論などの複数のベンチマークテストで優れたパフォーマンスを示し、ほとんどのオープンソースモデルを超え、特定のタスクでは専有モデルと同等の競争力を示しています。Qwen2-7B-Instructは多くの評価でQwen1.5-7B-Chatを上回り、顕著な性能向上を示しています。"
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VLはQwen-VLモデルの最新のイテレーションで、視覚理解のベンチマークテストで最先端の性能を達成しました。"
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-InstructはAlibaba Cloudが発表した最新の大規模言語モデルシリーズの一つです。この7Bモデルはコーディングや数学などの分野で顕著な能力の改善を持っています。このモデルは29以上の言語をカバーする多言語サポートも提供しており、中国語、英語などが含まれています。モデルは指示の遵守、構造化データの理解、特にJSONのような構造化出力の生成において顕著な向上を示しています。"
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-InstructはAlibaba Cloudが発表したコード特化型大規模言語モデルシリーズの最新バージョンです。このモデルはQwen2.5を基に、55兆トークンの訓練を通じて、コード生成、推論、修正能力を大幅に向上させました。コーディング能力を強化するだけでなく、数学および一般的な能力の利点も維持しています。このモデルはコードエージェントなどの実際のアプリケーションに対して、より包括的な基盤を提供します。"
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chatは智譜AIが提供するGLM-4シリーズの事前訓練モデルのオープンバージョンです。このモデルは意味、数学、推論、コード、知識などの複数の側面で優れたパフォーマンスを示します。多輪対話をサポートするだけでなく、GLM-4-9B-Chatはウェブブラウジング、コード実行、カスタムツール呼び出し(Function Call)、長文推論などの高度な機能も備えています。モデルは中国語、英語、日本語、韓国語、ドイツ語など26の言語をサポートしています。多くのベンチマークテストで、GLM-4-9B-Chatは優れた性能を示し、AlignBench-v2、MT-Bench、MMLU、C-Evalなどでの評価が行われています。このモデルは最大128Kのコンテキスト長をサポートし、学術研究や商業アプリケーションに適しています。"
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1は、強化学習(RL)駆動の推論モデルで、モデル内の繰り返しと可読性の問題を解決します。RLの前に、DeepSeek-R1はコールドスタートデータを導入し、推論性能をさらに最適化しました。数学、コード、推論タスクにおいてOpenAI-o1と同等の性能を発揮し、精巧に設計されたトレーニング手法によって全体的な効果を向上させています。"
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3は、6710億パラメータを持つ混合専門家(MoE)言語モデルで、多頭潜在注意力(MLA)とDeepSeekMoEアーキテクチャを採用し、無補助損失の負荷バランス戦略を組み合わせて推論とトレーニングの効率を最適化しています。14.8兆の高品質トークンで事前トレーニングを行い、監視付き微調整と強化学習を経て、DeepSeek-V3は他のオープンソースモデルを超え、先進的なクローズドモデルに近づいています。"
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "GemmaはGoogleが開発した軽量で最先端のオープンモデルシリーズの一つです。これはデコーダーのみの大規模言語モデルで、英語をサポートし、オープンウェイト、事前訓練バリアント、指示微調整バリアントを提供します。Gemmaモデルは質問応答、要約、推論などのさまざまなテキスト生成タスクに適しています。この9Bモデルは8兆トークンで訓練されました。その比較的小さな規模により、リソースが限られた環境(ノートパソコン、デスクトップ、または自分のクラウドインフラストラクチャなど)でのデプロイが可能になり、より多くの人々が最先端のAIモデルにアクセスできるようになり、革新を促進します。"
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1はMetaが開発した多言語大規模言語モデルファミリーで、8B、70B、405Bの3つのパラメータ規模の事前訓練および指示微調整バリアントを含みます。この8B指示微調整モデルは多言語対話シーンに最適化されており、複数の業界ベンチマークテストで優れたパフォーマンスを示しています。モデルの訓練には150兆トークン以上の公開データが使用され、監視微調整や人間のフィードバック強化学習などの技術が採用され、モデルの有用性と安全性が向上しています。Llama 3.1はテキスト生成とコード生成をサポートし、知識のカットオフ日は2023年12月です。"
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Previewは、複雑な対話生成と文脈理解タスクを効率的に処理できる革新的な自然言語処理モデルです。"
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Previewは、Qwenチームによって開発された視覚推論能力に特化した研究モデルであり、複雑なシーン理解と視覚関連の数学問題を解決する上で独自の利点を持っています。"
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Qwen2のテスト版として、Qwen1.5は大規模データを使用してより正確な対話機能を実現しました。"
+ "Qwen/QwQ-32B": {
+ "description": "QwQはQwenシリーズの推論モデルです。従来の指示調整モデルと比較して、QwQは思考と推論能力を備えており、特に困難な問題を解決する際に、下流タスクでのパフォーマンスを大幅に向上させることができます。QwQ-32Bは中型の推論モデルであり、最先端の推論モデル(DeepSeek-R1、o1-miniなど)との比較において競争力のあるパフォーマンスを発揮します。このモデルはRoPE、SwiGLU、RMSNorm、Attention QKVバイアスなどの技術を採用しており、64層のネットワーク構造と40のQアテンションヘッド(GQAアーキテクチャではKVは8個)を持っています。"
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B)は、迅速な応答と自然な対話能力を提供し、多言語環境に適しています。"
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-PreviewはQwenの最新の実験的研究モデルで、AIの推論能力を向上させることに特化しています。言語の混合、再帰的推論などの複雑なメカニズムを探求することで、主な利点は強力な推論分析能力、数学およびプログラミング能力です。同時に、言語切り替えの問題、推論のループ、安全性の考慮、その他の能力の違いも存在します。"
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-InstructはQwen2シリーズの指示微調整大規模言語モデルで、パラメータ規模は1.5Bです。このモデルはTransformerアーキテクチャに基づき、SwiGLU活性化関数、注意QKVバイアス、グループクエリ注意などの技術を採用しています。言語理解、生成、多言語能力、コーディング、数学、推論などの複数のベンチマークテストで優れたパフォーマンスを示し、ほとんどのオープンソースモデルを超えています。Qwen1.5-1.8B-Chatと比較して、Qwen2-1.5B-InstructはMMLU、HumanEval、GSM8K、C-Eval、IFEvalなどのテストで顕著な性能向上を示していますが、パラメータ数はわずかに少ないです。"
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2は、先進的な汎用言語モデルであり、さまざまな指示タイプをサポートします。"
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-InstructはQwen2シリーズの指示微調整大規模言語モデルで、パラメータ規模は72Bです。このモデルはTransformerアーキテクチャに基づき、SwiGLU活性化関数、注意QKVバイアス、グループクエリ注意などの技術を採用しています。大規模な入力を処理することができます。このモデルは言語理解、生成、多言語能力、コーディング、数学、推論などの複数のベンチマークテストで優れたパフォーマンスを示し、ほとんどのオープンソースモデルを超え、特定のタスクでは専有モデルと同等の競争力を示しています。"
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VLはQwen-VLモデルの最新のイテレーションで、視覚理解のベンチマークテストで最先端の性能を達成しました。"
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5は、新しい大型言語モデルシリーズで、指示型タスクの処理を最適化することを目的としています。"
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5は、新しい大型言語モデルシリーズで、指示型タスクの処理を最適化することを目的としています。"
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5は、新しい大型言語モデルシリーズで、より強力な理解と生成能力を持っています。"
+ "description": "アリババクラウドの通義千問チームが開発した大規模言語モデル"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5は新しい大型言語モデルシリーズで、より強力な理解と生成能力を持っています。"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5は新しい大型言語モデルシリーズで、指示タスクの処理を最適化することを目的としています。"
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5は、新しい大型言語モデルシリーズで、指示型タスクの処理を最適化することを目的としています。"
},
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5は新しい大型言語モデルシリーズで、指示タスクの処理を最適化することを目的としています。"
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coderはコード作成に特化しています。"
+ },
"Qwen/Qwen2.5-Coder-7B-Instruct": {
- "description": "Qwen2.5-Coderは、コード作成に特化しています。"
+ "description": "Qwen2.5-Coder-7B-InstructはAlibaba Cloudが発表したコード特化型大規模言語モデルシリーズの最新バージョンです。このモデルはQwen2.5を基に、55兆トークンの訓練を通じて、コード生成、推論、修正能力を大幅に向上させました。コーディング能力を強化するだけでなく、数学および一般的な能力の利点も維持しています。このモデルはコードエージェントなどの実際のアプリケーションに対して、より包括的な基盤を提供します。"
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2はQwenモデルの最新シリーズで、128kのコンテキストをサポートしています。現在の最適なオープンソースモデルと比較して、Qwen2-72Bは自然言語理解、知識、コード、数学、そして多言語などの能力において、現在のリーディングモデルを大幅に上回っています。"
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2はQwenモデルの最新シリーズで、同等の規模の最適なオープンソースモデルやそれ以上の規模のモデルを超えることができ、Qwen2 7Bは複数の評価で顕著な優位性を示し、特にコードと中国語理解において優れています。"
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72Bは、強力な視覚言語モデルであり、画像とテキストのマルチモーダル処理をサポートし、画像の内容を正確に認識し、関連する説明や回答を生成できます。"
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instructは、140億パラメータの大規模言語モデルで、優れたパフォーマンスを発揮し、中国語と多言語シーンを最適化し、インテリジェントQ&A、コンテンツ生成などのアプリケーションをサポートします。"
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instructは、320億パラメータの大規模言語モデルで、パフォーマンスが均衡しており、中国語と多言語シーンを最適化し、インテリジェントQ&A、コンテンツ生成などのアプリケーションをサポートします。"
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instructは、16kのコンテキストをサポートし、8Kを超える長文を生成します。関数呼び出しと外部システムとのシームレスなインタラクションをサポートし、柔軟性と拡張性を大幅に向上させました。モデルの知識は明らかに増加し、コーディングと数学の能力が大幅に向上し、29以上の言語をサポートしています。"
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instructは、70億パラメータの大規模言語モデルで、関数呼び出しと外部システムとのシームレスなインタラクションをサポートし、柔軟性と拡張性を大幅に向上させます。中国語と多言語シーンを最適化し、インテリジェントQ&A、コンテンツ生成などのアプリケーションをサポートします。"
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instructは、大規模な事前学習に基づくプログラミング指示モデルであり、強力なコード理解と生成能力を持ち、さまざまなプログラミングタスクを効率的に処理でき、特にスマートコード作成、自動化スクリプト生成、プログラミング問題の解決に適しています。"
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instructは、コード生成、コード理解、効率的な開発シーンのために設計された大規模言語モデルで、業界をリードする32Bパラメータ規模を採用しており、多様なプログラミングニーズに応えます。"
+ },
+ "SenseChat": {
+ "description": "基本バージョンのモデル (V4)、4Kのコンテキスト長で、汎用能力が強力です。"
+ },
+ "SenseChat-128K": {
+ "description": "基本バージョンのモデル (V4)、128Kのコンテキスト長で、長文理解や生成などのタスクで優れたパフォーマンスを発揮します。"
+ },
+ "SenseChat-32K": {
+ "description": "基本バージョンのモデル (V4)、32Kのコンテキスト長で、さまざまなシーンに柔軟に適用できます。"
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Mathは、数学分野の問題解決に特化しており、高難度の問題に対して専門的な解答を提供します。"
+ "SenseChat-5": {
+ "description": "最新バージョンのモデル (V5.5)、128Kのコンテキスト長で、数学的推論、英語の対話、指示のフォロー、長文理解などの分野での能力が大幅に向上し、GPT-4oに匹敵します。"
+ },
+ "SenseChat-5-1202": {
+ "description": "V5.5に基づく最新バージョンで、前のバージョンに比べて中国語と英語の基本能力、チャット、理系知識、人文系知識、ライティング、数理論理、文字数制御などのいくつかの次元でのパフォーマンスが大幅に向上しています。"
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "32Kのコンテキスト長で、広東語の対話理解においてGPT-4を超え、知識、推論、数学、コード作成などの複数の分野でGPT-4 Turboに匹敵します。"
+ },
+ "SenseChat-Character": {
+ "description": "スタンダード版モデル、8Kのコンテキスト長で、高速な応答速度を持っています。"
+ },
+ "SenseChat-Character-Pro": {
+ "description": "ハイエンド版モデル、32Kのコンテキスト長で、能力が全面的に向上し、中国語/英語の対話をサポートしています。"
+ },
+ "SenseChat-Turbo": {
+ "description": "迅速な質問応答やモデルの微調整シーンに適しています。"
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "最新の軽量バージョンモデルで、フルモデルの90%以上の能力を達成し、推論コストを大幅に削減しています。"
+ },
+ "SenseChat-Vision": {
+ "description": "最新バージョンモデル (V5.5) で、複数の画像入力をサポートし、モデルの基本能力の最適化を全面的に実現し、オブジェクト属性認識、空間関係、動作イベント認識、シーン理解、感情認識、論理常識推論、テキスト理解生成において大幅な向上を実現しました。"
+ },
+ "Skylark2-lite-8k": {
+ "description": "雲雀(Skylark)第2世代モデル、Skylark2-liteモデルは高い応答速度を持ち、リアルタイム性が求められ、コストに敏感で、モデルの精度要求がそれほど高くないシーンに適しています。コンテキストウィンドウ長は8kです。"
+ },
+ "Skylark2-pro-32k": {
+ "description": "雲雀(Skylark)第2世代モデル、Skylark2-proバージョンは高いモデル精度を持ち、専門分野の文書生成、小説創作、高品質翻訳などの複雑なテキスト生成シーンに適しています。コンテキストウィンドウ長は32kです。"
+ },
+ "Skylark2-pro-4k": {
+ "description": "雲雀(Skylark)第2世代モデル、Skylark2-proモデルは高いモデル精度を持ち、専門分野の文書生成、小説創作、高品質翻訳などの複雑なテキスト生成シーンに適しています。コンテキストウィンドウ長は4kです。"
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "雲雀(Skylark)第2世代モデル、Skylark2-pro-characterモデルは、優れたロールプレイングとチャット能力を持ち、ユーザーのプロンプト要件に基づいて異なるキャラクターを演じながらチャットを行うのが得意です。キャラクターのスタイルが際立ち、対話の内容は自然で流暢です。チャットボット、仮想アシスタント、オンラインカスタマーサービスなどのシーンに適しており、高速な応答を実現します。"
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "雲雀(Skylark)第2世代モデル、Skylark2-pro-turbo-8kは、推論がより速く、コストが低く、コンテキストウィンドウ長は8kです。"
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6BはChatGLMシリーズのオープンモデルで、智譜AIによって開発されました。このモデルは前の世代の優れた特性を保持し、対話の流暢さとデプロイのハードルの低さを維持しつつ、新しい特性を導入しています。より多様な訓練データ、より十分な訓練ステップ、より合理的な訓練戦略を採用し、10B未満の事前訓練モデルの中で優れたパフォーマンスを示しています。ChatGLM3-6Bは多輪対話、ツール呼び出し、コード実行、エージェントタスクなどの複雑なシーンをサポートしています。対話モデルの他に、基礎モデルChatGLM-6B-Baseと長文対話モデルChatGLM3-6B-32Kもオープンソースとして提供されています。このモデルは学術研究に完全にオープンで、登録後は無料の商業利用も許可されています。"
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9Bはオープンソース版で、会話アプリケーションに最適化された対話体験を提供します。"
},
+ "TeleAI/TeleChat2": {
+ "description": "TeleChat2大モデルは中国電信が0から1まで自主開発した生成的意味大モデルで、百科問答、コード生成、長文生成などの機能をサポートし、ユーザーに対話相談サービスを提供します。ユーザーと対話し、質問に答え、創作を支援し、効率的かつ便利に情報、知識、インスピレーションを取得する手助けをします。モデルは幻覚問題、長文生成、論理理解などの面で優れたパフォーマンスを示しています。"
+ },
+ "TeleAI/TeleMM": {
+ "description": "TeleMM多モーダル大モデルは中国電信が自主開発した多モーダル理解大モデルで、テキスト、画像などの多様なモーダル入力を処理し、画像理解、グラフ分析などの機能をサポートし、ユーザーにクロスモーダルの理解サービスを提供します。モデルはユーザーと多モーダルでインタラクションし、入力内容を正確に理解し、質問に答え、創作を支援し、効率的に多モーダル情報とインスピレーションのサポートを提供します。細粒度の認識、論理推論などの多モーダルタスクで優れたパフォーマンスを示しています。"
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-InstructはAlibaba Cloudが発表した最新の大規模言語モデルシリーズの一つです。この72Bモデルはコーディングや数学などの分野で顕著な能力の改善を持っています。このモデルは29以上の言語をカバーする多言語サポートも提供しており、中国語、英語などが含まれています。モデルは指示の遵守、構造化データの理解、特にJSONのような構造化出力の生成において顕著な向上を示しています。"
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34Bは、元のシリーズモデルの優れた汎用言語能力を維持しつつ、5000億の高品質トークンを増分トレーニングすることで、数学的論理とコーディング能力を大幅に向上させました。"
+ },
"abab5.5-chat": {
"description": "生産性シーン向けであり、複雑なタスク処理と効率的なテキスト生成をサポートし、専門分野のアプリケーションに適しています。"
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "中国語のキャラクター対話シーンに最適化されており、流暢で中国語の表現習慣に合った対話生成能力を提供します。"
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworksのオープンソース関数呼び出しモデルは、卓越した指示実行能力とオープンでカスタマイズ可能な特性を提供します。"
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Fireworks社の最新のFirefunction-v2は、Llama-3を基に開発された高性能な関数呼び出しモデルであり、多くの最適化を経て、特に関数呼び出し、対話、指示のフォローなどのシナリオに適しています。"
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1は、強化学習とコールドスタートデータの最適化を経た最先端の大規模言語モデルで、優れた推論、数学、プログラミング性能を持っています。"
},
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13bは、画像とテキストの入力を同時に受け取ることができる視覚言語モデルであり、高品質なデータで訓練されており、多モーダルタスクに適しています。"
- },
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B指示モデルは、以前のGoogle技術に基づいており、質問応答、要約、推論などのさまざまなテキスト生成タスクに適しています。"
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Deepseekが提供する強力なMixture-of-Experts (MoE)言語モデルで、総パラメータ数は671Bであり、各トークンは37Bのパラメータを活性化します。"
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Llama 3 70B指示モデルは、多言語対話と自然言語理解に最適化されており、ほとんどの競合モデルを上回る性能を持っています。"
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B指示モデル(HFバージョン)は、公式実装結果と一致し、高品質な指示フォロータスクに適しています。"
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Llama 3 8B指示モデルは、対話や多言語タスクに最適化されており、卓越した効率を発揮します。"
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Llama 3.1 8B指示モデルは、多言語対話の最適化のために設計されており、一般的な業界ベンチマークを超える性能を発揮します。"
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Metaの11Bパラメータ指示調整画像推論モデルです。このモデルは視覚認識、画像推論、画像説明、および画像に関する一般的な質問への回答に最適化されています。このモデルは、グラフや図表などの視覚データを理解し、画像の詳細をテキストで記述することで、視覚と言語の間のギャップを埋めることができます。"
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Llama 3.2 3B指示モデルはMetaが発表した軽量な多言語モデルです。このモデルは効率を向上させることを目的としており、より大規模なモデルと比較して遅延とコストの面で大きな改善を提供します。このモデルの使用例には、問い合わせやプロンプトのリライト、執筆支援が含まれます。"
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Metaの90Bパラメータ指示調整画像推論モデルです。このモデルは視覚認識、画像推論、画像説明、および画像に関する一般的な質問への回答に最適化されています。このモデルは、グラフや図表などの視覚データを理解し、画像の詳細をテキストで記述することで、視覚と言語の間のギャップを埋めることができます。"
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instructは、Llama 3.1 70Bの12月の更新版です。このモデルは、2024年7月にリリースされたLlama 3.1 70Bを基に改良され、ツール呼び出し、多言語テキストサポート、数学およびプログラミング能力が強化されています。このモデルは、推論、数学、指示遵守の面で業界の最前線に達しており、3.1 405Bと同等の性能を提供しつつ、速度とコストにおいて顕著な利点を持っています。"
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "24Bパラメータモデルで、より大規模なモデルと同等の最先端の能力を備えています。"
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B指示モデルは、大規模なパラメータと多専門家アーキテクチャを持ち、複雑なタスクの高効率処理を全方位でサポートします。"
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B指示モデルは、多専門家アーキテクチャを提供し、高効率の指示フォローと実行をサポートします。"
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B指示モデル(HFバージョン)は、公式実装と一致し、さまざまな高効率タスクシナリオに適しています。"
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "MythoMax L2 13Bモデルは、新しい統合技術を組み合わせており、物語やキャラクターの役割に優れています。"
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision指示モデルは、軽量の多モーダルモデルであり、複雑な視覚とテキスト情報を処理でき、強力な推論能力を持っています。"
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5Bモデルは、高度なプログラミングタスクをサポートし、多言語能力を強化し、複雑なコード生成と理解に適しています。"
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "QwQモデルはQwenチームによって開発された実験的な研究モデルで、AIの推論能力を強化することに焦点を当てています。"
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Qwen-VLモデルの72Bバージョンは、アリババの最新のイテレーションの成果であり、近年の革新を代表しています。"
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5はAlibaba Cloud Qwenチームによって開発された一連のデコーダーのみを含む言語モデルです。これらのモデルは、0.5B、1.5B、3B、7B、14B、32B、72Bなど、さまざまなサイズを提供し、ベース版と指示版の2種類のバリエーションがあります。"
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7Bモデルは、80以上のプログラミング言語に特化して訓練されており、優れたプログラミング補完能力と文脈理解を持っています。"
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B InstructはAlibaba Cloudが発表したコード特化型大規模言語モデルシリーズの最新バージョンです。このモデルはQwen2.5を基に、55兆トークンの訓練を通じて、コード生成、推論、修正能力を大幅に向上させました。コーディング能力を強化するだけでなく、数学および一般的な能力の利点も維持しています。このモデルはコードエージェントなどの実際のアプリケーションに対して、より包括的な基盤を提供します。"
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Yi-Largeモデルは、卓越した多言語処理能力を持ち、さまざまな言語生成と理解タスクに使用できます。"
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "52Bパラメータ(12Bアクティブ)の多言語モデルで、256Kの長いコンテキストウィンドウ、関数呼び出し、構造化出力、基盤生成を提供します。"
},
- "ai21-jamba-instruct": {
- "description": "最高のパフォーマンス、品質、コスト効率を実現するための生産グレードのMambaベースのLLMモデルです。"
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnetは業界標準を向上させ、競合モデルやClaude 3 Opusを超える性能を持ち、広範な評価で優れたパフォーマンスを示し、私たちの中程度のモデルの速度とコストを兼ね備えています。"
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnetは業界標準を引き上げ、競合モデルやClaude 3 Opusを上回る性能を発揮し、広範な評価で優れた結果を示しています。また、中程度のレベルのモデルと同等の速度とコストを持っています。"
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 HaikuはAnthropicの最も速く、最もコンパクトなモデルで、ほぼ瞬時の応答速度を提供します。簡単なクエリやリクエストに迅速に回答できます。顧客は人間のインタラクションを模倣するシームレスなAI体験を構築できるようになります。Claude 3 Haikuは画像を処理し、テキスト出力を返すことができ、200Kのコンテキストウィンドウを持っています。"
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opusは、Anthropicが高度に複雑なタスクを処理するために開発した最も強力なモデルです。性能、知能、流暢さ、理解力において卓越したパフォーマンスを発揮します。"
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haikuは、Anthropicの最も高速な次世代モデルです。Claude 3 Haikuと比較して、Claude 3.5 Haikuはすべてのスキルで向上しており、多くの知能ベンチマークテストで前世代の最大モデルClaude 3 Opusを超えています。"
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 SonnetはOpusを超える能力を提供し、Sonnetよりも速い速度を持ちながら、Sonnetと同じ価格を維持します。Sonnetは特にプログラミング、データサイエンス、視覚処理、代理タスクに優れています。"
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnetは、Anthropicがこれまでに開発した最も知能の高いモデルであり、市場で初めての混合推論モデルです。Claude 3.7 Sonnetは、ほぼ瞬時の応答や段階的な思考を生成することができ、ユーザーはこれらのプロセスを明確に見ることができます。Sonnetは特にプログラミング、データサイエンス、視覚処理、代理タスクに優れています。"
+ },
"aya": {
"description": "Aya 23は、Cohereが提供する多言語モデルであり、23の言語をサポートし、多様な言語アプリケーションを便利にします。"
},
"aya:35b": {
"description": "Aya 23は、Cohereが提供する多言語モデルであり、23の言語をサポートし、多様な言語アプリケーションを便利にします。"
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13Bは百川智能が開発した130億パラメータを持つオープンソースの商用大規模言語モデルで、権威ある中国語と英語のベンチマークで同サイズの中で最良の結果を達成しています。"
+ },
"charglm-3": {
"description": "CharGLM-3はキャラクター演技と感情的な伴侶のために設計されており、超長期の多段階記憶と個別化された対話をサポートし、幅広い用途に適しています。"
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2は、業界をリードする200Kトークンのコンテキスト、モデルの幻覚の発生率を大幅に低下させる、システムプロンプト、および新しいテスト機能:ツール呼び出しを含む、企業にとって重要な能力の進歩を提供します。"
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haikuは、Anthropicの最も高速な次世代モデルです。Claude 3 Haikuと比較して、Claude 3.5 Haikuはすべてのスキルで向上しており、多くの知能ベンチマークテストで前の世代の最大モデルであるClaude 3 Opusを超えています。"
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnetは、Opusを超える能力とSonnetよりも速い速度を提供し、Sonnetと同じ価格を維持します。Sonnetは特にプログラミング、データサイエンス、視覚処理、エージェントタスクに優れています。"
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnetは、Opusを超える能力とSonnetよりも速い速度を提供しつつ、Sonnetと同じ価格を維持します。Sonnetは特にプログラミング、データサイエンス、視覚処理、代理タスクに優れています。"
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnetは、競合他社よりも低価格で最大の効用を提供し、信頼性が高く耐久性のある主力機として設計されています。スケール化されたAIデプロイメントに適しています。Claude 3.7 Sonnetは画像を処理し、テキスト出力を返すことができ、200Kのコンテキストウィンドウを持っています。"
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haikuは、Anthropicの最も速く、最もコンパクトなモデルであり、ほぼ瞬時の応答を実現することを目的としています。迅速かつ正確な指向性能を持っています。"
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnetは、企業のワークロードに理想的なバランスを提供し、より低価格で最大の効用を提供し、信頼性が高く、大規模な展開に適しています。"
},
- "claude-instant-1.2": {
- "description": "Anthropicのモデルは、低遅延、高スループットのテキスト生成に使用され、数百ページのテキストを生成することをサポートします。"
- },
"codegeex-4": {
"description": "CodeGeeX-4は強力なAIプログラミングアシスタントで、さまざまなプログラミング言語のインテリジェントな質問応答とコード補完をサポートし、開発効率を向上させます。"
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9Bは、多言語コード生成モデルで、コード補完と生成、コードインタープリター、ウェブ検索、関数呼び出し、リポジトリレベルのコードQ&Aを含む包括的な機能をサポートし、ソフトウェア開発のさまざまなシーンをカバーしています。パラメータが10B未満のトップクラスのコード生成モデルです。"
+ },
"codegemma": {
"description": "CodeGemmaは、さまざまなプログラミングタスクに特化した軽量言語モデルであり、迅速な反復と統合をサポートします。"
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llamaは、コード生成と議論に特化したLLMであり、広範なプログラミング言語のサポートを組み合わせて、開発者環境に適しています。"
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llamaはコード生成と議論に特化したLLMで、幅広いプログラミング言語のサポートを組み合わせて、開発者環境に適しています。"
+ },
"codellama:13b": {
"description": "Code Llamaは、コード生成と議論に特化したLLMであり、広範なプログラミング言語のサポートを組み合わせて、開発者環境に適しています。"
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+は、リアルな企業シーンと複雑なアプリケーションのために設計された高性能な大規模言語モデルです。"
},
+ "dall-e-2": {
+ "description": "第二世代DALL·Eモデル、よりリアルで正確な画像生成をサポートし、解像度は第一世代の4倍です"
+ },
+ "dall-e-3": {
+ "description": "最新のDALL·Eモデル、2023年11月にリリース。よりリアルで正確な画像生成をサポートし、詳細表現力が向上しています"
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instructは、高い信頼性の指示処理能力を提供し、多業界アプリケーションをサポートします。"
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1は、強化学習(RL)駆動の推論モデルであり、モデル内の繰り返しと可読性の問題を解決します。RLの前に、DeepSeek-R1はコールドスタートデータを導入し、推論性能をさらに最適化しました。数学、コード、推論タスクにおいてOpenAI-o1と同等のパフォーマンスを発揮し、精巧に設計されたトレーニング手法によって全体的な効果を向上させました。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek-R1蒸留モデルで、強化学習とコールドスタートデータを通じて推論性能を最適化し、オープンソースモデルがマルチタスクの基準を刷新しました。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8Bは、Llama-3.1-8Bに基づいて開発された蒸留モデルです。このモデルは、DeepSeek-R1が生成したサンプルを使用して微調整され、優れた推論能力を示しています。複数のベンチマークテストで良好なパフォーマンスを示し、特にMATH-500では89.1%の正確性を達成し、AIME 2024では50.4%の合格率を達成し、CodeForcesでは1205のスコアを獲得し、8B規模のモデルとして強力な数学とプログラミング能力を示しています。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1蒸留モデルで、強化学習とコールドスタートデータを通じて推論性能を最適化し、オープンソースモデルがマルチタスクの基準を刷新しました。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1蒸留モデルで、強化学習とコールドスタートデータを通じて推論性能を最適化し、オープンソースモデルがマルチタスクの基準を刷新しました。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32Bは、Qwen2.5-32Bに基づいて知識蒸留によって得られたモデルです。このモデルは、DeepSeek-R1が生成した80万の選りすぐりのサンプルを使用して微調整され、数学、プログラミング、推論などの複数の分野で卓越した性能を示しています。AIME 2024、MATH-500、GPQA Diamondなどの複数のベンチマークテストで優れた成績を収めており、特にMATH-500では94.3%の正確性を達成し、強力な数学的推論能力を示しています。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7Bは、Qwen2.5-Math-7Bに基づいて知識蒸留によって得られたモデルです。このモデルは、DeepSeek-R1が生成した80万の選りすぐりのサンプルを使用して微調整され、優れた推論能力を示しています。複数のベンチマークテストで優れた成績を収めており、特にMATH-500では92.8%の正確性を達成し、AIME 2024では55.5%の合格率を達成し、CodeForcesでは1189のスコアを獲得し、7B規模のモデルとして強力な数学とプログラミング能力を示しています。"
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5は以前のバージョンの優れた特徴を集約し、汎用性とコーディング能力を強化しました。"
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3は、6710億パラメータを持つ混合専門家(MoE)言語モデルであり、多頭潜在注意(MLA)とDeepSeekMoEアーキテクチャを採用し、補助損失なしの負荷バランス戦略を組み合わせて、推論とトレーニングの効率を最適化します。14.8兆の高品質トークンで事前トレーニングを行い、監視微調整と強化学習を経て、DeepSeek-V3は他のオープンソースモデルを超え、先進的なクローズドソースモデルに近づきました。"
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67Bは、高い複雑性の対話のために訓練された先進的なモデルです。"
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "最先端の効率的なLLMで、推論、数学、プログラミングに優れています。"
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2は、DeepSeekMoE-27Bに基づいて開発された混合専門家(MoE)視覚言語モデルであり、スパースアクティベーションのMoEアーキテクチャを採用し、わずか4.5Bパラメータを活性化することで卓越した性能を実現しています。このモデルは、視覚的質問応答、光学文字認識、文書/表/グラフ理解、視覚的定位などの複数のタスクで優れたパフォーマンスを発揮します。"
+ },
"deepseek-chat": {
"description": "一般的な対話能力と強力なコード処理能力を兼ね備えた新しいオープンソースモデルであり、元のChatモデルの対話能力とCoderモデルのコード処理能力を保持しつつ、人間の好みにより良く整合しています。さらに、DeepSeek-V2.5は、執筆タスクや指示に従う能力など、さまざまな面で大幅な向上を実現しました。"
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33Bは、2兆のデータを基にトレーニングされたコード言語モデルで、そのうち87%がコード、13%が中英語です。モデルは16Kのウィンドウサイズと穴埋めタスクを導入し、プロジェクトレベルのコード補完とスニペット埋め機能を提供します。"
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2は、オープンソースの混合エキスパートコードモデルであり、コードタスクにおいて優れた性能を発揮し、GPT4-Turboに匹敵します。"
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2は、オープンソースの混合エキスパートコードモデルであり、コードタスクにおいて優れた性能を発揮し、GPT4-Turboに匹敵します。"
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1は、強化学習(RL)駆動の推論モデルであり、モデル内の繰り返しと可読性の問題を解決します。RLの前に、DeepSeek-R1はコールドスタートデータを導入し、推論性能をさらに最適化しました。数学、コード、推論タスクにおいてOpenAI-o1と同等のパフォーマンスを発揮し、精巧に設計されたトレーニング手法によって全体的な効果を向上させました。"
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1——DeepSeekスイートの中でより大きく、より賢いモデル——がLlama 70Bアーキテクチャに蒸留されました。ベンチマークテストと人間評価に基づき、このモデルは元のLlama 70Bよりも賢く、特に数学と事実の正確性が求められるタスクで優れたパフォーマンスを示します。"
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek-R1-Distillシリーズモデルは、知識蒸留技術を通じて、DeepSeek-R1が生成したサンプルをQwen、Llamaなどのオープンソースモデルに微調整して得られたものです。"
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "DeepSeek-R1-Distillシリーズモデルは、知識蒸留技術を通じて、DeepSeek-R1が生成したサンプルをQwen、Llamaなどのオープンソースモデルに微調整して得られたものです。"
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek-R1-Distillシリーズモデルは、知識蒸留技術を通じて、DeepSeek-R1が生成したサンプルをQwen、Llamaなどのオープンソースモデルに微調整して得られたものです。"
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek-R1-Distillシリーズモデルは、知識蒸留技術を通じて、DeepSeek-R1が生成したサンプルをQwen、Llamaなどのオープンソースモデルに微調整して得られたものです。"
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "DeepSeek-R1-Distillシリーズモデルは、知識蒸留技術を通じて、DeepSeek-R1が生成したサンプルをQwen、Llamaなどのオープンソースモデルに微調整して得られたものです。"
+ },
+ "deepseek-reasoner": {
+ "description": "DeepSeekが提供する推論モデルです。最終的な回答を出力する前に、モデルは思考の連鎖を出力し、最終的な答えの正確性を高めます。"
+ },
"deepseek-v2": {
"description": "DeepSeek V2は、高効率なMixture-of-Experts言語モデルであり、経済的な処理ニーズに適しています。"
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236Bは、DeepSeekの設計コードモデルであり、強力なコード生成能力を提供します。"
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3は、杭州深度求索人工知能基礎技術研究有限公司が独自に開発したMoEモデルで、複数の評価で優れた成績を収め、主流のランキングでオープンソースモデルの首位に立っています。V3はV2.5モデルに比べて生成速度が3倍向上し、ユーザーにより迅速でスムーズな使用体験を提供します。"
+ },
"deepseek/deepseek-chat": {
"description": "汎用性とコード能力を融合させた新しいオープンソースモデルで、元のChatモデルの汎用対話能力とCoderモデルの強力なコード処理能力を保持しつつ、人間の好みにより良く整合しています。さらに、DeepSeek-V2.5は執筆タスク、指示の遵守などの多くの面で大幅な向上を実現しました。"
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1は、わずかなラベル付きデータしかない状況で、モデルの推論能力を大幅に向上させました。最終的な回答を出力する前に、モデルは思考の連鎖を出力し、最終的な答えの正確性を向上させます。"
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70BはLlama3.3 70Bに基づく大規模言語モデルで、DeepSeek R1の出力を微調整に利用し、大規模な最前線モデルと同等の競争力のある性能を実現しています。"
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8BはLlama-3.1-8B-Instructに基づく蒸留大言語モデルで、DeepSeek R1の出力を使用してトレーニングされています。"
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14BはQwen 2.5 14Bに基づく蒸留大言語モデルで、DeepSeek R1の出力を使用してトレーニングされています。このモデルは複数のベンチマークテストでOpenAIのo1-miniを超え、密なモデル(dense models)の最新技術の成果を達成しました。以下は一部のベンチマークテストの結果です:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nこのモデルはDeepSeek R1の出力から微調整を行い、より大規模な最前線モデルと同等の競争力のある性能を示しています。"
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32BはQwen 2.5 32Bに基づく蒸留大言語モデルで、DeepSeek R1の出力を使用してトレーニングされています。このモデルは複数のベンチマークテストでOpenAIのo1-miniを超え、密なモデル(dense models)の最新技術の成果を達成しました。以下は一部のベンチマークテストの結果です:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nこのモデルはDeepSeek R1の出力から微調整を行い、より大規模な最前線モデルと同等の競争力のある性能を示しています。"
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1はDeepSeekチームが発表した最新のオープンソースモデルで、特に数学、プログラミング、推論タスクにおいてOpenAIのo1モデルと同等の推論性能を持っています。"
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1は、わずかなラベル付きデータしかない状況で、モデルの推論能力を大幅に向上させました。最終的な回答を出力する前に、モデルは思考の連鎖を出力し、最終的な答えの正確性を向上させます。"
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3は推論速度において前のモデルに比べて大きなブレークスルーを達成しました。オープンソースモデルの中で1位にランクインし、世界の最先端のクローズドモデルと肩を並べることができます。DeepSeek-V3はマルチヘッド潜在注意(MLA)とDeepSeekMoEアーキテクチャを採用しており、これらのアーキテクチャはDeepSeek-V2で完全に検証されています。さらに、DeepSeek-V3は負荷分散のための補助的な非損失戦略を開発し、より強力な性能を得るためにマルチラベル予測トレーニング目標を設定しました。"
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3は推論速度において前のモデルに比べて大きなブレークスルーを達成しました。オープンソースモデルの中で1位にランクインし、世界の最先端のクローズドモデルと肩を並べることができます。DeepSeek-V3はマルチヘッド潜在注意(MLA)とDeepSeekMoEアーキテクチャを採用しており、これらのアーキテクチャはDeepSeek-V2で完全に検証されています。さらに、DeepSeek-V3は負荷分散のための補助的な非損失戦略を開発し、より強力な性能を得るためにマルチラベル予測トレーニング目標を設定しました。"
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-liteは全く新しい世代の軽量版モデルで、極限の応答速度を実現し、効果と遅延の両方で世界トップレベルに達しています。"
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256kはDoubao-1.5-Proの全面的なアップグレード版で、全体的な効果が10%大幅に向上しました。256kのコンテキストウィンドウでの推論をサポートし、出力長は最大12kトークンをサポートします。より高い性能、より大きなウィンドウ、超高コストパフォーマンスで、より広範なアプリケーションシーンに適しています。"
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-proは全く新しい世代の主力モデルで、性能が全面的にアップグレードされ、知識、コード、推論などの面で卓越したパフォーマンスを発揮します。"
+ },
"emohaa": {
"description": "Emohaaは心理モデルで、専門的な相談能力を持ち、ユーザーが感情問題を理解するのを助けます。"
},
+ "ernie-3.5-128k": {
+ "description": "百度が独自に開発したフラッグシップの大規模言語モデルで、膨大な中英文コーパスをカバーし、強力な汎用能力を持ち、ほとんどの対話質問応答、創作生成、プラグインアプリケーションシーンの要求を満たすことができます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ernie-3.5-8k": {
+ "description": "百度が独自に開発したフラッグシップの大規模言語モデルで、膨大な中英文コーパスをカバーし、強力な汎用能力を持ち、ほとんどの対話質問応答、創作生成、プラグインアプリケーションシーンの要求を満たすことができます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "百度が独自に開発したフラッグシップの大規模言語モデルで、膨大な中英文コーパスをカバーし、強力な汎用能力を持ち、ほとんどの対話質問応答、創作生成、プラグインアプリケーションシーンの要求を満たすことができます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、ERNIE 3.5に比べてモデル能力が全面的にアップグレードされ、さまざまな分野の複雑なタスクシーンに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、ERNIE 3.5に比べてモデル能力が全面的にアップグレードされ、さまざまな分野の複雑なタスクシーンに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。"
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、総合的なパフォーマンスが優れており、さまざまな分野の複雑なタスクシーンに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。ERNIE 4.0に比べてパフォーマンスがさらに優れています。"
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、総合的なパフォーマンスが優れており、さまざまな分野の複雑なタスクシーンに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。ERNIE 4.0に比べてパフォーマンスがさらに優れています。"
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "百度が独自に開発したフラッグシップの超大規模言語モデルで、総合的なパフォーマンスが優れており、さまざまな分野の複雑なタスクシーンに広く適用されます。百度検索プラグインとの自動接続をサポートし、質問応答情報のタイムリーさを保証します。ERNIE 4.0に比べてパフォーマンスがさらに優れています。"
+ },
+ "ernie-char-8k": {
+ "description": "百度が独自に開発した垂直シーン向けの大規模言語モデルで、ゲームのNPC、カスタマーサービスの対話、対話キャラクターの役割演技などのアプリケーションシーンに適しており、キャラクターのスタイルがより鮮明で一貫しており、指示に従う能力が強く、推論性能が優れています。"
+ },
+ "ernie-char-fiction-8k": {
+ "description": "百度が独自に開発した垂直シーン向けの大規模言語モデルで、ゲームのNPC、カスタマーサービスの対話、対話キャラクターの役割演技などのアプリケーションシーンに適しており、キャラクターのスタイルがより鮮明で一貫しており、指示に従う能力が強く、推論性能が優れています。"
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Liteは、百度が独自に開発した軽量級の大規模言語モデルで、優れたモデル効果と推論性能を兼ね備え、低計算能力のAIアクセラレータカードでの推論使用に適しています。"
+ },
+ "ernie-lite-pro-128k": {
+ "description": "百度が独自に開発した軽量級の大規模言語モデルで、優れたモデル効果と推論性能を兼ね備え、ERNIE Liteよりも優れた効果を持ち、低計算能力のAIアクセラレータカードでの推論使用に適しています。"
+ },
+ "ernie-novel-8k": {
+ "description": "百度が独自に開発した汎用大規模言語モデルで、小説の続編作成能力に明らかな優位性があり、短編劇や映画などのシーンにも使用できます。"
+ },
+ "ernie-speed-128k": {
+ "description": "百度が2024年に最新リリースした自社開発の高性能大規模言語モデルで、汎用能力が優れており、基盤モデルとして微調整に適しており、特定のシーンの問題をより良く処理し、優れた推論性能を持っています。"
+ },
+ "ernie-speed-pro-128k": {
+ "description": "百度が2024年に最新リリースした自社開発の高性能大規模言語モデルで、汎用能力が優れており、ERNIE Speedよりも優れた効果を持ち、基盤モデルとして微調整に適しており、特定のシーンの問題をより良く処理し、優れた推論性能を持っています。"
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tinyは、百度が独自に開発した超高性能の大規模言語モデルで、文心シリーズモデルの中でデプロイと微調整コストが最も低いです。"
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001(チューニング)は、安定した調整可能な性能を提供し、複雑なタスクのソリューションに理想的な選択肢です。"
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Proは、Googleの高性能AIモデルであり、幅広いタスクの拡張に特化しています。"
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flashは、Googleの最新のマルチモーダルAIモデルで、高速処理能力を備え、テキスト、画像、動画の入力をサポートし、さまざまなタスクに対して効率的に拡張できます。"
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001は、効率的なマルチモーダルモデルであり、幅広いアプリケーションの拡張をサポートします。"
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002は効率的なマルチモーダルモデルで、幅広いアプリケーションの拡張をサポートしています。"
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827は、大規模なタスクシナリオの処理のために設計されており、比類のない処理速度を提供します。"
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8Bは、高効率のマルチモーダルモデルで、幅広いアプリケーションの拡張をサポートしています。"
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924は最新の実験モデルで、テキストおよびマルチモーダルのユースケースにおいて顕著な性能向上を実現しています。"
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827は、最適化されたマルチモーダル処理能力を提供し、さまざまな複雑なタスクシナリオに適用できます。"
+ "description": "Gemini 1.5 Flash 0827は、最適化されたマルチモーダル処理能力を提供し、多様な複雑なタスクシナリオに適用可能です。"
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flashは、Googleの最新のマルチモーダルAIモデルであり、高速処理能力を備え、テキスト、画像、動画の入力をサポートし、さまざまなタスクの効率的な拡張に適しています。"
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002は最新の生産準備モデルで、特に数学、長いコンテキスト、視覚タスクにおいて質の高い出力を提供し、顕著な向上を見せています。"
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801は、優れたマルチモーダル処理能力を提供し、アプリケーション開発における柔軟性を高めます。"
+ "description": "Gemini 1.5 Pro 0801は、優れたマルチモーダル処理能力を提供し、アプリケーション開発により大きな柔軟性をもたらします。"
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827は、最新の最適化技術を組み合わせて、より効率的なマルチモーダルデータ処理能力を提供します。"
+ "description": "Gemini 1.5 Pro 0827は、最新の最適化技術を組み合わせ、より効率的なマルチモーダルデータ処理能力をもたらします。"
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Proは、最大200万トークンをサポートする中型マルチモーダルモデルの理想的な選択肢であり、複雑なタスクに対する多面的なサポートを提供します。"
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flashは、卓越した速度、ネイティブツールの使用、マルチモーダル生成、1Mトークンのコンテキストウィンドウを含む次世代の機能と改善を提供します。"
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flashは、卓越した速度、ネイティブツールの使用、マルチモーダル生成、1Mトークンのコンテキストウィンドウを含む次世代の機能と改善を提供します。"
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flashモデルのバリアントで、コスト効率と低遅延などの目標に最適化されています。"
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flashモデルのバリアントで、コスト効率と低遅延などの目標に最適化されています。"
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "コスト効率と低遅延を目指して最適化されたGemini 2.0 Flashモデルです。"
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Expは、Googleの最新の実験的なマルチモーダルAIモデルであり、次世代の機能、卓越した速度、ネイティブツールの呼び出し、マルチモーダル生成を備えています。"
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Expは、Googleの最新の実験的なマルチモーダルAIモデルであり、次世代の機能、卓越した速度、ネイティブツールの呼び出し、マルチモーダル生成を備えています。"
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimentalは、Googleの最新の実験的なマルチモーダルAIモデルで、歴史的なバージョンと比較して品質が向上しています。特に、世界の知識、コード、長いコンテキストにおいて顕著です。"
+ },
"gemma-7b-it": {
"description": "Gemma 7Bは、中小規模のタスク処理に適しており、コスト効果を兼ね備えています。"
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2は、Googleが提供する高効率モデルであり、小型アプリケーションから複雑なデータ処理まで、さまざまなアプリケーションシーンをカバーしています。"
},
- "general": {
- "description": "Spark Liteは軽量な大言語モデルで、極めて低い遅延と高効率な処理能力を備え、完全に無料でオープンに提供され、リアルタイムのオンライン検索機能をサポートします。その迅速な応答特性により、低算力デバイスでの推論アプリケーションやモデル微調整において優れたパフォーマンスを発揮し、ユーザーに優れたコスト効果とインテリジェントな体験を提供し、特に知識問答、コンテンツ生成、検索シーンでのパフォーマンスが優れています。"
- },
"generalv3": {
"description": "Spark Proは専門分野に最適化された高性能な大言語モデルで、数学、プログラミング、医療、教育などの複数の分野に特化し、ネットワーク検索や内蔵の天気、日付などのプラグインをサポートします。最適化されたモデルは、複雑な知識問答、言語理解、高度なテキスト創作において優れたパフォーマンスと高効率を示し、専門的なアプリケーションシーンに最適な選択肢です。"
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520は最新のモデルバージョンで、高度に複雑で多様なタスクのために設計され、優れたパフォーマンスを発揮します。"
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chatは、意味、数学、推論、コード、知識などの多方面で高い性能を示しています。また、ウェブブラウジング、コード実行、カスタムツール呼び出し、長文推論を備えています。日本語、韓国語、ドイツ語を含む26の言語をサポートしています。"
+ },
"glm-4-air": {
"description": "GLM-4-Airはコストパフォーマンスが高いバージョンで、GLM-4に近い性能を提供し、高速かつ手頃な価格です。"
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flashはシンプルなタスクを処理するのに理想的な選択肢で、最も速く、最も手頃な価格です。"
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashXはFlashの強化版で、超高速の推論速度を誇ります。"
+ },
"glm-4-long": {
"description": "GLM-4-Longは超長文入力をサポートし、記憶型タスクや大規模文書処理に適しています。"
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4Vは強力な画像理解と推論能力を提供し、さまざまな視覚タスクをサポートします。"
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flashは、高効率の単一画像理解に特化しており、リアルタイム画像分析やバッチ画像処理などの迅速な画像解析のシーンに適しています。"
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plusは動画コンテンツや複数の画像を理解する能力を持ち、マルチモーダルタスクに適しています。"
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827は、最適化されたマルチモーダル処理能力を提供し、さまざまな複雑なタスクシーンに適用可能です。"
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Previewは、強力な複雑な推論能力を備え、論理推論、数学、プログラミングなどの分野で優れたパフォーマンスを発揮します。"
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flashは、卓越した速度、ネイティブツールの使用、マルチモーダル生成、1Mトークンのコンテキストウィンドウを含む次世代の機能と改善を提供します。"
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimentalは、Googleの最新の実験的なマルチモーダルAIモデルで、歴史的なバージョンと比較して品質が向上しています。特に、世界の知識、コード、長いコンテキストにおいて顕著です。"
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827は、最新の最適化技術を組み合わせて、より効率的なマルチモーダルデータ処理能力を提供します。"
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flashは、最適化されたマルチモーダル処理能力を提供し、さまざまな複雑なタスクシナリオに適しています。"
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Proは、最新の最適化技術を組み合わせて、より効率的なマルチモーダルデータ処理能力を実現します。"
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2はGoogleが提供する効率的なモデルで、小型アプリケーションから複雑なデータ処理まで、さまざまなアプリケーションシナリオをカバーしています。"
},
"google/gemma-2-27b-it": {
"description": "Gemma 2は、軽量化と高効率のデザイン理念を継承しています。"
},
+ "google/gemma-2-2b-it": {
+ "description": "Googleの軽量指示調整モデル"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2はGoogleが提供する効率的なモデルで、小型アプリケーションから複雑なデータ処理まで、さまざまなアプリケーションシナリオをカバーしています。"
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2は、Googleの軽量オープンソーステキストモデルシリーズです。"
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turboは、さまざまなテキスト生成と理解タスクに適しており、現在はgpt-3.5-turbo-0125を指しています。"
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turboは、OpenAIが提供する効率的なモデルで、チャットやテキスト生成タスクに適しており、並行関数呼び出しをサポートしています。"
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16kは、高容量のテキスト生成モデルで、複雑なタスクに適しています。"
+ },
"gpt-4": {
"description": "GPT-4は、より大きなコンテキストウィンドウを提供し、より長いテキスト入力を処理できるため、広範な情報統合やデータ分析が必要なシナリオに適しています。"
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "最新のGPT-4 Turboモデルは視覚機能を備えています。現在、視覚リクエストはJSON形式と関数呼び出しを使用して行うことができます。GPT-4 Turboは、マルチモーダルタスクに対してコスト効率の高いサポートを提供する強化版です。正確性と効率のバランスを取り、リアルタイムのインタラクションが必要なアプリケーションシナリオに適しています。"
},
- "gpt-4-1106-vision-preview": {
- "description": "最新のGPT-4 Turboモデルは視覚機能を備えています。現在、視覚リクエストはJSON形式と関数呼び出しを使用して行うことができます。GPT-4 Turboは、マルチモーダルタスクに対してコスト効率の高いサポートを提供する強化版です。正確性と効率のバランスを取り、リアルタイムのインタラクションが必要なアプリケーションシナリオに適しています。"
- },
"gpt-4-32k": {
"description": "GPT-4は、より大きなコンテキストウィンドウを提供し、より長いテキスト入力を処理できるため、広範な情報統合やデータ分析が必要なシナリオに適しています。"
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "最新のGPT-4 Turboモデルは視覚機能を備えています。現在、視覚リクエストはJSON形式と関数呼び出しを使用して行うことができます。GPT-4 Turboは、マルチモーダルタスクに対してコスト効率の高いサポートを提供する強化版です。正確性と効率のバランスを取り、リアルタイムのインタラクションが必要なアプリケーションシナリオに適しています。"
},
+ "gpt-4.5-preview": {
+ "description": "GPT-4.5の研究プレビュー版で、これまでで最大かつ最強のGPTモデルです。広範な世界知識を持ち、ユーザーの意図をよりよく理解することができるため、創造的なタスクや自律的な計画において優れたパフォーマンスを発揮します。GPT-4.5はテキストと画像の入力を受け付け、テキスト出力(構造化出力を含む)を生成します。関数呼び出し、バッチAPI、ストリーミング出力など、重要な開発者機能をサポートしています。創造的でオープンな思考や対話が求められるタスク(執筆、学習、新しいアイデアの探求など)において、GPT-4.5は特に優れた性能を発揮します。知識のカットオフ日は2023年10月です。"
+ },
"gpt-4o": {
"description": "ChatGPT-4oは、リアルタイムで更新される動的モデルで、常に最新のバージョンを維持します。強力な言語理解と生成能力を組み合わせており、顧客サービス、教育、技術サポートなどの大規模なアプリケーションシナリオに適しています。"
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4oは、リアルタイムで更新される動的モデルで、常に最新のバージョンを維持します。強力な言語理解と生成能力を組み合わせており、顧客サービス、教育、技術サポートなどの大規模なアプリケーションシナリオに適しています。"
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4oは動的モデルで、リアルタイムで更新され、常に最新バージョンを保持します。 powerfulな言語理解と生成能力を組み合わせており、カスタマーサービス、教育、技術サポートなどの大規模なアプリケーションに適しています。"
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o Audio モデル、音声の入力と出力をサポート"
+ },
"gpt-4o-mini": {
"description": "GPT-4o miniは、OpenAIがGPT-4 Omniの後に発表した最新のモデルで、画像とテキストの入力をサポートし、テキストを出力します。最先端の小型モデルとして、最近の他の先進モデルよりもはるかに安価で、GPT-3.5 Turboよりも60%以上安価です。最先端の知能を維持しつつ、コストパフォーマンスが大幅に向上しています。GPT-4o miniはMMLUテストで82%のスコアを獲得し、現在チャットの好みではGPT-4よりも高い評価を得ています。"
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "GPT-4o-miniリアルタイムバージョン、音声とテキストのリアルタイム入力と出力をサポート"
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "GPT-4oリアルタイムバージョン、音声とテキストのリアルタイム入力と出力をサポート"
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "GPT-4oリアルタイムバージョン、音声とテキストのリアルタイム入力と出力をサポート"
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "GPT-4oリアルタイムバージョン、音声とテキストのリアルタイム入力と出力をサポート"
+ },
+ "grok-2-1212": {
+ "description": "このモデルは、精度、指示の遵守、そして多言語能力において改善されています。"
+ },
+ "grok-2-vision-1212": {
+ "description": "このモデルは、精度、指示の遵守、そして多言語能力において改善されています。"
+ },
+ "grok-beta": {
+ "description": "Grok 2と同等の性能を持ちながら、より高い効率、速度、機能を備えています。"
+ },
+ "grok-vision-beta": {
+ "description": "最新の画像理解モデルで、文書、グラフ、スクリーンショット、写真など、さまざまな視覚情報を処理できます。"
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13Bは複数のトップモデルを統合した創造性と知性を兼ね備えた言語モデルです。"
},
+ "hunyuan-code": {
+ "description": "混元の最新のコード生成モデルで、200Bの高品質コードデータで基盤モデルを増強し、半年間の高品質SFTデータトレーニングを経て、コンテキストウィンドウの長さが8Kに増加しました。5つの主要言語のコード生成自動評価指標で上位に位置し、5つの言語における10項目の総合コードタスクの人工高品質評価で、パフォーマンスは第一梯隊にあります。"
+ },
+ "hunyuan-functioncall": {
+ "description": "混元の最新のMOEアーキテクチャFunctionCallモデルで、高品質のFunctionCallデータトレーニングを経て、コンテキストウィンドウは32Kに達し、複数の次元の評価指標でリーダーシップを発揮しています。"
+ },
+ "hunyuan-large": {
+ "description": "Hunyuan-largeモデルの総パラメータ数は約389B、活性化パラメータ数は約52Bで、現在業界で最大のパラメータ規模を持ち、最も優れた効果を持つTransformerアーキテクチャのオープンソースMoEモデル。"
+ },
+ "hunyuan-large-longcontext": {
+ "description": "文書要約や文書問答などの長文タスクを得意とし、一般的なテキスト生成タスクの処理能力も備えている。長文の分析と生成において優れたパフォーマンスを発揮し、複雑で詳細な長文内容の処理要求に効果的に対応できる。"
+ },
+ "hunyuan-lite": {
+ "description": "MOE構造にアップグレードされ、コンテキストウィンドウは256kで、NLP、コード、数学、業界などの多くの評価セットで多くのオープンソースモデルをリードしています。"
+ },
+ "hunyuan-lite-vision": {
+ "description": "混元最新の7Bマルチモーダルモデル、コンテキストウィンドウ32K、中英文シーンのマルチモーダル対話、画像物体認識、文書表理解、マルチモーダル数学などをサポートし、複数の次元で評価指標が7B競合モデルを上回る。"
+ },
+ "hunyuan-pro": {
+ "description": "万億規模のパラメータを持つMOE-32K長文モデルです。さまざまなベンチマークで絶対的なリーダーシップを達成し、複雑な指示や推論、複雑な数学能力を備え、functioncallをサポートし、多言語翻訳、金融、法律、医療などの分野で重点的に最適化されています。"
+ },
+ "hunyuan-role": {
+ "description": "混元の最新のロールプレイングモデルで、混元公式の精緻なトレーニングによって開発されたロールプレイングモデルで、混元モデルとロールプレイングシナリオデータセットを組み合わせて増強され、ロールプレイングシナリオにおいてより良い基本的な効果を持っています。"
+ },
+ "hunyuan-standard": {
+ "description": "より優れたルーティング戦略を採用し、負荷分散と専門家の収束の問題を緩和しました。長文に関しては、大海捞針指標が99.9%に達しています。MOE-32Kはコストパフォーマンスが相対的に高く、効果と価格のバランスを取りながら、長文入力の処理を実現します。"
+ },
+ "hunyuan-standard-256K": {
+ "description": "より優れたルーティング戦略を採用し、負荷分散と専門家の収束の問題を緩和しました。長文に関しては、大海捞針指標が99.9%に達しています。MOE-256Kは長さと効果の面でさらに突破し、入力可能な長さを大幅に拡張しました。"
+ },
+ "hunyuan-standard-vision": {
+ "description": "混元最新のマルチモーダルモデルで、多言語での応答をサポートし、中英文能力が均衡している。"
+ },
+ "hunyuan-translation": {
+ "description": "中国語、英語、日本語、フランス語、ポルトガル語、スペイン語、トルコ語、ロシア語、アラビア語、韓国語、イタリア語、ドイツ語、ベトナム語、マレー語、インドネシア語の15言語の相互翻訳をサポートし、多シーン翻訳評価セットに基づく自動評価COMETスコアを使用して、十数の一般的な言語間の翻訳能力が市場の同規模モデルを全体的に上回っています。"
+ },
+ "hunyuan-translation-lite": {
+ "description": "混元翻訳モデルは自然言語の対話式翻訳をサポートし、中国語、英語、日本語、フランス語、ポルトガル語、スペイン語、トルコ語、ロシア語、アラビア語、韓国語、イタリア語、ドイツ語、ベトナム語、マレー語、インドネシア語の15言語の相互翻訳をサポートしています。"
+ },
+ "hunyuan-turbo": {
+ "description": "混元の新世代大規模言語モデルのプレビュー版で、全く新しい混合専門家モデル(MoE)構造を採用し、hunyuan-proに比べて推論効率が向上し、パフォーマンスも強化されています。"
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "hunyuan-turbo 2024年11月20日の固定バージョンで、hunyuan-turboとhunyuan-turbo-latestの間に位置するバージョン。"
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "このバージョンの最適化:データ指令のスケーリングにより、モデルの汎用的な一般化能力を大幅に向上;数学、コード、論理推論能力を大幅に向上;テキスト理解と語彙理解に関連する能力を最適化;テキスト作成の内容生成の質を最適化。"
+ },
+ "hunyuan-turbo-latest": {
+ "description": "汎用体験の最適化、NLP理解、テキスト作成、雑談、知識問答、翻訳、分野などを含む;擬人性を向上させ、モデルの感情知能を最適化;意図が曖昧な時のモデルの能動的な明確化能力を向上;語彙解析に関する問題の処理能力を向上;創作の質とインタラクティブ性を向上;多段階体験を向上。"
+ },
+ "hunyuan-turbo-vision": {
+ "description": "混元の次世代視覚言語フラッグシップ大モデルで、全く新しい混合専門家モデル(MoE)構造を採用し、画像とテキストの理解に関連する基礎認識、コンテンツ作成、知識問答、分析推論などの能力が前世代モデルに比べて全面的に向上。"
+ },
+ "hunyuan-vision": {
+ "description": "混元の最新のマルチモーダルモデルで、画像とテキストの入力をサポートし、テキストコンテンツを生成します。"
+ },
"internlm/internlm2_5-20b-chat": {
"description": "革新的なオープンソースモデルInternLM2.5は、大規模なパラメータを通じて対話のインテリジェンスを向上させました。"
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5は多様なシーンでのインテリジェントな対話ソリューションを提供します。"
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instructモデルは、70Bパラメータを持ち、大規模なテキスト生成と指示タスクで卓越した性能を提供します。"
+ "internlm2-pro-chat": {
+ "description": "私たちがまだ維持している旧バージョンのモデルで、7B、20Bのさまざまなモデルパラメータ量が選択可能です。"
+ },
+ "internlm2.5-latest": {
+ "description": "私たちの最新のモデルシリーズで、卓越した推論性能を持ち、1Mのコンテキスト長をサポートし、より強力な指示追従とツール呼び出し能力を備えています。"
+ },
+ "internlm3-latest": {
+ "description": "私たちの最新のモデルシリーズは、卓越した推論性能を持ち、同等のオープンソースモデルの中でリーダーシップを発揮しています。デフォルトで最新のInternLM3シリーズモデルを指します。"
+ },
+ "jina-deepsearch-v1": {
+ "description": "深層検索は、ウェブ検索、読解、推論を組み合わせて、包括的な調査を行います。これは、あなたの研究タスクを受け入れる代理人として考えることができ、広範な検索を行い、何度も反復してから答えを提供します。このプロセスには、継続的な研究、推論、さまざまな視点からの問題解決が含まれます。これは、事前に訓練されたデータから直接答えを生成する標準的な大規模モデルや、一度きりの表面的な検索に依存する従来のRAGシステムとは根本的に異なります。"
+ },
+ "kimi-latest": {
+ "description": "Kimi スマートアシスタント製品は最新の Kimi 大モデルを使用しており、まだ安定していない機能が含まれている可能性があります。画像理解をサポートし、リクエストのコンテキストの長さに応じて 8k/32k/128k モデルを請求モデルとして自動的に選択します。"
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLMは、学習科学の原則に従って訓練された実験的なタスク特化型言語モデルで、教育や学習のシーンでシステムの指示に従い、専門的なメンターとして機能します。"
+ },
+ "lite": {
+ "description": "Spark Liteは軽量な大規模言語モデルで、非常に低い遅延と高い処理能力を備えています。完全に無料でオープンであり、リアルタイムのオンライン検索機能をサポートしています。その迅速な応答特性により、低算力デバイスでの推論アプリケーションやモデルの微調整において優れたパフォーマンスを発揮し、特に知識問答、コンテンツ生成、検索シーンにおいて優れたコストパフォーマンスとインテリジェントな体験を提供します。"
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70Bは、より強力なAI推論能力を提供し、複雑なアプリケーションに適しており、非常に多くの計算処理をサポートし、高効率と精度を保証します。"
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8Bは、高効率モデルであり、迅速なテキスト生成能力を提供し、大規模な効率とコスト効果が求められるアプリケーションシナリオに非常に適しています。"
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instructモデルは、8Bパラメータを持ち、画面指示タスクの高効率な実行をサポートし、優れたテキスト生成能力を提供します。"
+ "llama-3.2-11b-vision-instruct": {
+ "description": "高解像度画像で優れた画像推論能力を発揮し、視覚理解アプリケーションに適しています。"
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Onlineモデルは、405Bパラメータを持ち、約127,000トークンのコンテキスト長をサポートし、複雑なオンラインチャットアプリケーション用に設計されています。"
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2は、視覚データとテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的質問応答などのタスクで優れたパフォーマンスを発揮し、言語生成と視覚推論の間のギャップを埋めます。"
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chatモデルは、70Bパラメータを持ち、約127,000トークンのコンテキスト長をサポートし、複雑なオフラインチャットタスクに適しています。"
+ "llama-3.2-90b-vision-instruct": {
+ "description": "視覚理解エージェントアプリケーション向けの高度な画像推論能力を提供します。"
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Onlineモデルは、70Bパラメータを持ち、約127,000トークンのコンテキスト長をサポートし、高容量で多様なチャットタスクに適しています。"
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2は、視覚データとテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的質問応答などのタスクで優れたパフォーマンスを発揮し、言語生成と視覚推論の間のギャップを埋めます。"
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chatモデルは、8Bパラメータを持ち、オフラインチャット用に設計されており、約127,000トークンのコンテキスト長をサポートします。"
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3は、Llamaシリーズの最先端の多言語オープンソース大規模言語モデルで、非常に低コストで405Bモデルに匹敵する性能を体験できます。Transformer構造に基づき、監視付き微調整(SFT)と人間のフィードバックによる強化学習(RLHF)を通じて有用性と安全性を向上させています。その指示調整バージョンは多言語対話に最適化されており、複数の業界ベンチマークで多くのオープンソースおよびクローズドチャットモデルを上回る性能を発揮します。知識のカットオフ日は2023年12月です。"
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Onlineモデルは、8Bパラメータを持ち、約127,000トークンのコンテキスト長をサポートし、オンラインチャット用に設計されており、さまざまなテキストインタラクションを効率的に処理できます。"
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3は、70B(テキスト入力/テキスト出力)の事前学習と指示調整による生成モデルを持つ多言語大規模言語モデル(LLM)です。Llama 3.3の指示調整済みのプレーンテキストモデルは、多言語の対話ユースケースに最適化されており、一般的な業界ベンチマークで多くの利用可能なオープンソースおよびクローズドチャットモデルを上回っています。"
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70Bは、比類のない複雑性処理能力を提供し、高要求プロジェクトに特化しています。"
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtralは、科学研究と数学推論のために設計されており、効果的な計算能力と結果の解釈を提供します。"
},
+ "max-32k": {
+ "description": "Spark Max 32Kは大規模なコンテキスト処理能力を備え、より強力なコンテキスト理解と論理推論能力を持ち、32Kトークンのテキスト入力をサポートします。長文書の読解やプライベートな知識問答などのシーンに適しています。"
+ },
"meta-llama-3-70b-instruct": {
"description": "推論、コーディング、広範な言語アプリケーションに優れた70億パラメータの強力なモデルです。"
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B)は、優れた言語処理能力と素晴らしいインタラクション体験を提供します。"
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2は優れた言語処理能力と素晴らしいインタラクティブ体験を提供します。"
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B)は、強力なチャットモデルであり、複雑な対話ニーズをサポートします。"
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B)は、多言語サポートを提供し、豊富な分野知識をカバーしています。"
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2は視覚データとテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的質問応答などのタスクで優れた性能を発揮し、言語生成と視覚推論の間のギャップを埋めます。"
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2は視覚データとテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的質問応答などのタスクで優れた性能を発揮し、言語生成と視覚推論の間のギャップを埋めます。"
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2は視覚データとテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的質問応答などのタスクで優れた性能を発揮し、言語生成と視覚推論の間のギャップを埋めます。"
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3はLlamaシリーズの最先端の多言語オープンソース大規模言語モデルで、非常に低コストで405Bモデルに匹敵する性能を体験できます。Transformer構造に基づき、監視付き微調整(SFT)と人間のフィードバック強化学習(RLHF)を通じて有用性と安全性を向上させています。その指示調整バージョンは多言語対話に最適化されており、複数の業界ベンチマークで多くのオープンソースおよびクローズドチャットモデルを上回る性能を発揮します。知識のカットオフ日は2023年12月です"
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3の多言語大規模言語モデル(LLM)は、70B(テキスト入力/テキスト出力)の事前訓練と指示調整生成モデルです。Llama 3.3の指示調整された純粋なテキストモデルは、多言語対話のユースケースに最適化されており、一般的な業界ベンチマークで多くの利用可能なオープンソースおよびクローズドチャットモデルを上回っています。"
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2は視覚データとテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的質問応答などのタスクで優れた性能を発揮し、言語生成と視覚推論の間のギャップを埋めます。"
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Liteは、高効率と低遅延が求められる環境に適しています。"
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "405BのLlama 3.1 Turboモデルは、大規模データ処理のために超大容量のコンテキストサポートを提供し、超大規模な人工知能アプリケーションで優れたパフォーマンスを発揮します。"
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1はMetaが提供する先進的なモデルで、最大405Bのパラメータをサポートし、複雑な対話、多言語翻訳、データ分析の分野で利用できます。"
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70Bは多言語の高効率な対話サポートを提供します。"
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instructは高品質な対話シーンに最適化されており、多くのクローズドソースモデルよりも優れた性能を持っています。"
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B InstructはMetaが最新にリリースしたバージョンで、高品質な対話生成に最適化されており、多くのリーダーのクローズドソースモデルを超えています。"
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instructは高品質な対話のために設計されており、人間の評価において優れたパフォーマンスを示し、高いインタラクションシーンに特に適しています。"
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1は多言語サポートを提供し、業界をリードする生成モデルの一つです。"
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2は、視覚とテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的な質問応答などのタスクで優れたパフォーマンスを発揮し、言語生成と視覚推論の間のギャップを超えています。"
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2は、視覚とテキストデータを組み合わせたタスクを処理することを目的としています。画像の説明や視覚的な質問応答などのタスクで優れたパフォーマンスを発揮し、言語生成と視覚推論の間のギャップを超えています。"
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3は、Llamaシリーズの最先端の多言語オープンソース大規模言語モデルで、非常に低コストで405Bモデルに匹敵する性能を体験できます。Transformer構造に基づき、監視付き微調整(SFT)と人間のフィードバックによる強化学習(RLHF)を通じて有用性と安全性を向上させています。その指示調整バージョンは多言語対話に最適化されており、複数の業界ベンチマークで多くのオープンソースおよびクローズドチャットモデルを上回る性能を発揮します。知識のカットオフ日は2023年12月です。"
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3は、Llamaシリーズの最先端の多言語オープンソース大規模言語モデルで、非常に低コストで405Bモデルに匹敵する性能を体験できます。Transformer構造に基づき、監視付き微調整(SFT)と人間のフィードバックによる強化学習(RLHF)を通じて有用性と安全性を向上させています。その指示調整バージョンは多言語対話に最適化されており、複数の業界ベンチマークで多くのオープンソースおよびクローズドチャットモデルを上回る性能を発揮します。知識のカットオフ日は2023年12月です。"
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instructは、Llama 3.1 Instructモデルの中で最大かつ最も強力なモデルであり、高度に進化した対話推論および合成データ生成モデルです。また、特定の分野での専門的な継続的な事前トレーニングや微調整の基盤としても使用できます。Llama 3.1が提供する多言語大規模言語モデル(LLMs)は、8B、70B、405Bのサイズ(テキスト入力/出力)を含む、事前トレーニングされた指示調整された生成モデルのセットです。Llama 3.1の指示調整されたテキストモデル(8B、70B、405B)は、多言語対話のユースケースに最適化されており、一般的な業界ベンチマークテストで多くの利用可能なオープンソースチャットモデルを上回っています。Llama 3.1は、さまざまな言語の商業および研究用途に使用されることを目的としています。指示調整されたテキストモデルは、アシスタントのようなチャットに適しており、事前トレーニングモデルはさまざまな自然言語生成タスクに適応できます。Llama 3.1モデルは、他のモデルを改善するためにその出力を利用することもサポートしており、合成データ生成や洗練にも対応しています。Llama 3.1は、最適化されたトランスフォーマーアーキテクチャを使用した自己回帰型言語モデルです。調整されたバージョンは、監視付き微調整(SFT)と人間のフィードバックを伴う強化学習(RLHF)を使用して、人間の助けや安全性に対する好みに適合させています。"
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3は、開発者、研究者、企業向けのオープンな大規模言語モデル(LLM)であり、生成AIのアイデアを構築、実験、責任を持って拡張するのを支援することを目的としています。世界的なコミュニティの革新の基盤システムの一部として、計算能力とリソースが限られたエッジデバイスや、より迅速なトレーニング時間に非常に適しています。"
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7BはMicrosoft AIの最新の高速軽量モデルで、既存のオープンソースリーダーモデルの10倍に近い性能を持っています。"
+ "meta/llama-3.1-405b-instruct": {
+ "description": "高度なLLMで、合成データ生成、知識蒸留、推論をサポートし、チャットボット、プログラミング、特定の分野のタスクに適しています。"
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "複雑な対話を可能にし、卓越した文脈理解、推論能力、テキスト生成能力を備えています。"
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "高度な最先端モデルで、言語理解、卓越した推論能力、テキスト生成能力を備えています。"
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "最先端の視覚-言語モデルで、画像から高品質な推論を行うのが得意です。"
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "最先端の小型言語モデルで、言語理解、卓越した推論能力、テキスト生成能力を備えています。"
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "最先端の小型言語モデルで、言語理解、卓越した推論能力、テキスト生成能力を備えています。"
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "最先端の視覚-言語モデルで、画像から高品質な推論を行うのが得意です。"
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "高度なLLMで、推論、数学、常識、関数呼び出しに優れています。"
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2はMicrosoft AIが提供する言語モデルで、複雑な対話、多言語、推論、インテリジェントアシスタントの分野で特に優れた性能を発揮します。"
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22Bは、Microsoftの最先端AI Wizardモデルであり、非常に競争力のあるパフォーマンスを示しています。"
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-VはOpenBMBが発表した次世代のマルチモーダル大モデルで、優れたOCR認識能力とマルチモーダル理解能力を備え、幅広いアプリケーションシーンをサポートします。"
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3BはMistralの世界トップクラスのエッジモデルです。"
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8BはMistralのコストパフォーマンスに優れたエッジモデルです。"
+ },
"mistral": {
"description": "Mistralは、Mistral AIがリリースした7Bモデルであり、多様な言語処理ニーズに適しています。"
},
"mistral-large": {
"description": "Mixtral Largeは、Mistralのフラッグシップモデルであり、コード生成、数学、推論の能力を組み合わせ、128kのコンテキストウィンドウをサポートします。"
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407)は、最先端の推論、知識、コーディング能力を持つ高度な大規模言語モデル(LLM)です。"
- },
"mistral-large-latest": {
"description": "Mistral Largeは、フラッグシップの大モデルであり、多言語タスク、複雑な推論、コード生成に優れ、高端アプリケーションに理想的な選択肢です。"
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3は、高効率の計算能力と自然言語理解を提供し、幅広いアプリケーションに適しています。"
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7Bはコンパクトで高性能なモデルで、バッチ処理や分類、テキスト生成などの簡単なタスクに優れた推論能力を持っています。"
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B)は、超大規模な言語モデルであり、非常に高い処理要求をサポートします。"
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7Bは、一般的なテキストタスクに使用される事前訓練されたスパースミックス専門家モデルです。"
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7Bはスパースエキスパートモデルで、複数のパラメータを利用して推論速度を向上させ、多言語処理やコード生成タスクに適しています。"
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instructは速度最適化と長いコンテキストサポートを兼ね備えた高性能な業界標準モデルです。"
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128Kは、超長いコンテキスト処理能力を持つモデルであり、超長文の生成に適しており、複雑な生成タスクのニーズを満たし、最大128,000トークンの内容を処理でき、研究、学術、大型文書生成などのアプリケーションシーンに非常に適しています。"
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Kimi視覚モデル(moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-previewなどを含む)は、画像の内容を理解でき、画像の文字、色、物体の形状などを含みます。"
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32Kは、中程度の長さのコンテキスト処理能力を提供し、32,768トークンを処理でき、さまざまな長文や複雑な対話の生成に特に適しており、コンテンツ作成、報告書生成、対話システムなどの分野で使用されます。"
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Kimi視覚モデル(moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-previewなどを含む)は、画像の内容を理解でき、画像の文字、色、物体の形状などを含みます。"
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8Kは、短文生成タスクのために設計されており、高効率な処理性能を持ち、8,192トークンを処理でき、短い対話、速記、迅速なコンテンツ生成に非常に適しています。"
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Kimi視覚モデル(moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-previewなどを含む)は、画像の内容を理解でき、画像の文字、色、物体の形状などを含みます。"
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto は、現在のコンテキストで使用されているトークンの数に基づいて適切なモデルを選択できます。"
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8BはNous Hermes 2のアップグレード版で、最新の内部開発データセットを含んでいます。"
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70BはNVIDIAによってカスタマイズされた大規模言語モデルで、LLMが生成する応答がユーザーのクエリにどれだけ役立つかを向上させることを目的としています。このモデルはArena Hard、AlpacaEval 2 LC、GPT-4-Turbo MT-Benchなどのベンチマークテストで優れたパフォーマンスを示し、2024年10月1日現在、すべての自動整合ベンチマークテストで1位にランクされています。このモデルはRLHF(特にREINFORCE)、Llama-3.1-Nemotron-70B-Reward、HelpSteer2-Preferenceプロンプトを使用してLlama-3.1-70B-Instructモデルの基盤の上で訓練されています。"
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "独自の言語モデルで、比類のない精度と効率を提供します。"
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instructは、NVIDIAがカスタマイズした大規模言語モデルで、LLMが生成する応答の有用性を向上させることを目的としています。"
+ },
+ "o1": {
+ "description": "高度な推論と複雑な問題の解決に焦点を当てており、数学や科学のタスクを含みます。深いコンテキスト理解とエージェントワークフローを必要とするアプリケーションに非常に適しています。"
+ },
"o1-mini": {
"description": "o1-miniは、プログラミング、数学、科学のアプリケーションシーンに特化して設計された迅速で経済的な推論モデルです。このモデルは128Kのコンテキストを持ち、2023年10月の知識のカットオフがあります。"
},
"o1-preview": {
"description": "o1はOpenAIの新しい推論モデルで、広範な一般知識を必要とする複雑なタスクに適しています。このモデルは128Kのコンテキストを持ち、2023年10月の知識のカットオフがあります。"
},
+ "o3-mini": {
+ "description": "o3-miniは、o1-miniと同じコストと遅延目標で高い知能を提供する最新の小型推論モデルです。"
+ },
"open-codestral-mamba": {
"description": "Codestral Mambaは、コード生成に特化したMamba 2言語モデルであり、高度なコードおよび推論タスクを強力にサポートします。"
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7Bは、スパースエキスパートモデルであり、複数のパラメータを利用して推論速度を向上させ、多言語およびコード生成タスクの処理に適しています。"
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4oは動的モデルで、リアルタイムで最新バージョンを維持します。強力な言語理解と生成能力を組み合わせており、顧客サービス、教育、技術サポートなどの大規模なアプリケーションシーンに適しています。"
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4oは動的モデルで、最新のバージョンを維持するためにリアルタイムで更新されます。強力な言語理解と生成能力を組み合わせており、顧客サービス、教育、技術サポートなどの大規模なアプリケーションシナリオに適しています。"
},
"openai/gpt-4o-mini": {
"description": "GPT-4o miniはOpenAIがGPT-4 Omniの後に発表した最新モデルで、画像とテキストの入力をサポートし、テキストを出力します。彼らの最先端の小型モデルとして、最近の他の最前線モデルよりもはるかに安価で、GPT-3.5 Turboよりも60%以上安価です。最先端の知能を維持しつつ、顕著なコストパフォーマンスを誇ります。GPT-4o miniはMMLUテストで82%のスコアを獲得し、現在チャットの好みでGPT-4よりも高い評価を得ています。"
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Pixtralモデルは、グラフと画像理解、文書質問応答、多モーダル推論、指示遵守などのタスクで強力な能力を発揮し、自然な解像度とアスペクト比で画像を取り込み、最大128Kトークンの長いコンテキストウィンドウで任意の数の画像を処理できます。"
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Largeは、1240億のパラメータを持つオープンソースのマルチモーダルモデルで、Mistral Large 2に基づいて構築されています。これは私たちのマルチモーダルファミリーの中で2番目のモデルであり、最先端の画像理解能力を示しています。"
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128Kは特大のコンテキスト処理能力を備え、最大128Kのコンテキスト情報を処理できます。特に、全体を通じての分析や長期的な論理的関連性の処理が必要な長文コンテンツに適しており、複雑なテキストコミュニケーションにおいて滑らかで一貫した論理と多様な引用サポートを提供します。"
+ },
+ "qvq-72b-preview": {
+ "description": "QVQモデルはQwenチームによって開発された実験的研究モデルで、視覚推論能力の向上に特化しており、特に数学推論の分野で優れた性能を発揮。"
+ },
+ "qwen-coder-plus-latest": {
+ "description": "通義千問コードモデル。"
+ },
"qwen-coder-turbo-latest": {
"description": "通義千問のコードモデルです。"
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "通義千問の数学モデルは、数学の問題解決に特化した言語モデルです。"
},
+ "qwen-max": {
+ "description": "通義千問の千億レベルの超大規模言語モデルで、中国語、英語などさまざまな言語の入力をサポートしています。現在、通義千問2.5製品バージョンの背後にあるAPIモデルです。"
+ },
"qwen-max-latest": {
"description": "通義千問の千億レベルの超大規模言語モデルで、中国語、英語などの異なる言語入力をサポートし、現在の通義千問2.5製品バージョンの背後にあるAPIモデルです。"
},
+ "qwen-omni-turbo-latest": {
+ "description": "Qwen-Omniシリーズモデルは、動画、音声、画像、テキストなどのさまざまなモダリティのデータを入力し、音声とテキストを出力することをサポートしています。"
+ },
+ "qwen-plus": {
+ "description": "通義千問の超大規模言語モデルの強化版で、中国語、英語などさまざまな言語の入力をサポートしています。"
+ },
"qwen-plus-latest": {
"description": "通義千問の超大規模言語モデルの強化版で、中国語、英語などの異なる言語入力をサポートしています。"
},
+ "qwen-turbo": {
+ "description": "通義千問の超大規模言語モデルで、中国語、英語などさまざまな言語の入力をサポートしています。"
+ },
"qwen-turbo-latest": {
"description": "通義千問の超大規模言語モデルで、中国語、英語などの異なる言語入力をサポートしています。"
},
"qwen-vl-chat-v1": {
"description": "通義千問VLは、複数の画像、多段階の質問応答、創作などの柔軟なインタラクション方式をサポートするモデルです。"
},
- "qwen-vl-max": {
- "description": "通義千問超大規模視覚言語モデル。強化版に比べて、視覚推論能力と指示遵守能力をさらに向上させ、高い視覚認識と認知レベルを提供します。"
+ "qwen-vl-max-latest": {
+ "description": "通義千問の超大規模視覚言語モデル。強化版に比べて、視覚推論能力と指示遵守能力をさらに向上させ、より高い視覚認識と認知レベルを提供します。"
},
- "qwen-vl-plus": {
- "description": "通義千問大規模視覚言語モデルの強化版。詳細認識能力と文字認識能力を大幅に向上させ、超百万ピクセル解像度と任意のアスペクト比の画像をサポートします。"
+ "qwen-vl-ocr-latest": {
+ "description": "通義千問OCRは、文書、表、試験問題、手書き文字などの画像から文字を抽出する専用モデルです。多様な文字を認識でき、現在サポートされている言語は中国語、英語、フランス語、日本語、韓国語、ドイツ語、ロシア語、イタリア語、ベトナム語、アラビア語です。"
+ },
+ "qwen-vl-plus-latest": {
+ "description": "通義千問の大規模視覚言語モデルの強化版。詳細認識能力と文字認識能力を大幅に向上させ、100万ピクセル以上の解像度と任意のアスペクト比の画像をサポートします。"
},
"qwen-vl-v1": {
"description": "Qwen-7B言語モデルを初期化し、画像モデルを追加した、画像入力解像度448の事前トレーニングモデルです。"
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2は全く新しいQwen大規模言語モデルシリーズです。Qwen2 7Bはトランスフォーマーに基づくモデルで、言語理解、多言語能力、プログラミング、数学、推論において優れた性能を示しています。"
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2は全く新しい大型言語モデルシリーズで、より強力な理解と生成能力を備えています。"
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VLはQwen-VLモデルの最新のイテレーションで、MathVista、DocVQA、RealWorldQA、MTVQAなどの視覚理解ベンチマークテストで最先端の性能を達成しました。Qwen2-VLは20分以上のビデオを理解し、高品質なビデオベースの質問応答、対話、コンテンツ作成を行うことができます。また、複雑な推論と意思決定能力を備えており、モバイルデバイスやロボットなどと統合し、視覚環境とテキスト指示に基づいて自動操作を行うことができます。英語と中国語に加えて、Qwen2-VLは現在、ほとんどのヨーロッパ言語、日本語、韓国語、アラビア語、ベトナム語など、異なる言語のテキストを画像内で理解することもサポートしています。"
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instructはアリババクラウドが発表した最新の大言語モデルシリーズの一つです。この72Bモデルはコーディングや数学などの分野で顕著な能力の向上を示しています。このモデルは29以上の言語をカバーする多言語サポートも提供しており、中国語、英語などが含まれています。モデルは指示の追従、構造化データの理解、構造化出力(特にJSON)の生成においても顕著な向上を示しています。"
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instructはアリババクラウドが発表した最新の大言語モデルシリーズの一つです。この32Bモデルはコーディングや数学などの分野で顕著な能力の向上を示しています。このモデルは29以上の言語をカバーする多言語サポートも提供しており、中国語、英語などが含まれています。モデルは指示の追従、構造化データの理解、構造化出力(特にJSON)の生成においても顕著な向上を示しています。"
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "中国語と英語に対応したLLMで、言語、プログラミング、数学、推論などの分野に特化しています。"
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "高度なLLMで、コード生成、推論、修正をサポートし、主流のプログラミング言語をカバーしています。"
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "強力な中型コードモデルで、32Kのコンテキスト長をサポートし、多言語プログラミングに優れています。"
+ },
"qwen2": {
"description": "Qwen2は、Alibabaの新世代大規模言語モデルであり、優れた性能で多様なアプリケーションニーズをサポートします。"
},
+ "qwen2.5": {
+ "description": "Qwen2.5はAlibabaの次世代大規模言語モデルで、優れた性能を持ち、多様なアプリケーションのニーズをサポートします。"
+ },
"qwen2.5-14b-instruct": {
"description": "通義千問2.5の対外オープンソースの14B規模のモデルです。"
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "通義千問2.5が公開した72B規模のモデルです。"
+ },
"qwen2.5-32b-instruct": {
"description": "通義千問2.5の対外オープンソースの32B規模のモデルです。"
},
@@ -824,13 +1599,16 @@
"description": "通義千問2.5の対外オープンソースの7B規模のモデルです。"
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "通義千問のコードモデルのオープンソース版です。"
+ "description": "通義千問コードモデルのオープンソース版です。"
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "通義千問コードモデルのオープンソース版。"
},
"qwen2.5-coder-7b-instruct": {
"description": "通義千問のコードモデルのオープンソース版です。"
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Qwen-Mathモデルは、強力な数学の問題解決能力を持っています。"
+ "description": "Qwen-Mathモデルは、強力な数学的問題解決能力を備えています。"
},
"qwen2.5-math-72b-instruct": {
"description": "Qwen-Mathモデルは、強力な数学の問題解決能力を持っています。"
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Qwen-Mathモデルは、強力な数学の問題解決能力を持っています。"
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "指示に従い、数学、問題解決、コード全体の向上、万物認識能力の向上を実現し、多様な形式で視覚要素を直接的に正確に特定し、長い動画ファイル(最大10分)を理解し、秒単位のイベント時刻を特定でき、時間の前後や速さを理解し、解析と特定能力に基づいてOSやモバイルのエージェントを操作し、重要な情報抽出能力とJson形式出力能力が強化されています。このバージョンは72Bバージョンで、本シリーズの中で最も強力なバージョンです。"
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "指示に従い、数学、問題解決、コード全体の向上、万物認識能力の向上を実現し、多様な形式で視覚要素を直接的に正確に特定し、長い動画ファイル(最大10分)を理解し、秒単位のイベント時刻を特定でき、時間の前後や速さを理解し、解析と特定能力に基づいてOSやモバイルのエージェントを操作し、重要な情報抽出能力とJson形式出力能力が強化されています。このバージョンは72Bバージョンで、本シリーズの中で最も強力なバージョンです。"
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5はAlibabaの次世代大規模言語モデルで、優れた性能を持ち、多様なアプリケーションのニーズをサポートします。"
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5はAlibabaの次世代大規模言語モデルで、優れた性能を持ち、多様なアプリケーションのニーズをサポートします。"
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5はAlibabaの次世代大規模言語モデルで、優れた性能を持ち、多様なアプリケーションのニーズをサポートします。"
+ },
"qwen2:0.5b": {
"description": "Qwen2は、Alibabaの新世代大規模言語モデルであり、優れた性能で多様なアプリケーションニーズをサポートします。"
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2は、Alibabaの新世代大規模言語モデルであり、優れた性能で多様なアプリケーションニーズをサポートします。"
},
- "solar-1-mini-chat": {
+ "qwq": {
+ "description": "QwQはAIの推論能力を向上させることに特化した実験的研究モデルです。"
+ },
+ "qwq-32b": {
+ "description": "Qwen2.5-32Bモデルに基づいて訓練されたQwQ推論モデルは、強化学習を通じてモデルの推論能力を大幅に向上させました。モデルの数学コードなどのコア指標(AIME 24/25、LiveCodeBench)および一部の一般的な指標(IFEval、LiveBenchなど)は、DeepSeek-R1のフルバージョンに達しており、すべての指標は同じくQwen2.5-32Bに基づくDeepSeek-R1-Distill-Qwen-32Bを大幅に上回っています。"
+ },
+ "qwq-32b-preview": {
+ "description": "QwQモデルはQwenチームによって開発された実験的な研究モデルで、AIの推論能力を強化することに焦点を当てています。"
+ },
+ "qwq-plus-latest": {
+ "description": "Qwen2.5モデルに基づいて訓練されたQwQ推論モデルは、強化学習を通じてモデルの推論能力を大幅に向上させました。モデルの数学コードなどのコア指標(AIME 24/25、LiveCodeBench)および一部の一般的な指標(IFEval、LiveBenchなど)は、DeepSeek-R1のフルバージョンに達しています。"
+ },
+ "r1-1776": {
+ "description": "R1-1776は、DeepSeek R1モデルの一つのバージョンで、後処理を経て、検閲されていない偏りのない事実情報を提供します。"
+ },
+ "solar-mini": {
"description": "Solar MiniはコンパクトなLLMで、GPT-3.5を上回る性能を持ち、強力な多言語能力を備え、英語と韓国語をサポートし、高効率でコンパクトなソリューションを提供します。"
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja)はSolar Miniの能力を拡張し、日本語に特化しつつ、英語と韓国語の使用においても高効率で卓越した性能を維持します。"
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) はSolar Miniの能力を拡張し、日本語に特化しながら、英語と韓国語の使用においても高効率で卓越した性能を維持しています。"
},
"solar-pro": {
"description": "Solar ProはUpstageが発表した高インテリジェンスLLMで、単一GPUの指示追従能力に特化しており、IFEvalスコアは80以上です。現在は英語をサポートしており、正式版は2024年11月にリリース予定で、言語サポートとコンテキスト長を拡張します。"
},
+ "sonar": {
+ "description": "検索コンテキストに基づく軽量検索製品で、Sonar Proよりも速く、安価です。"
+ },
+ "sonar-deep-research": {
+ "description": "Deep Researchは、専門家による包括的な研究を行い、それをアクセス可能で実行可能なレポートにまとめます。"
+ },
+ "sonar-pro": {
+ "description": "検索コンテキストをサポートする高度な検索製品で、高度なクエリとフォローアップをサポートします。"
+ },
+ "sonar-reasoning": {
+ "description": "DeepSeek推論モデルによってサポートされる新しいAPI製品です。"
+ },
+ "sonar-reasoning-pro": {
+ "description": "DeepSeek推論モデルによってサポートされる新しいAPI製品。"
+ },
"step-1-128k": {
"description": "性能とコストのバランスを取り、一般的なシナリオに適しています。"
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "高速モデルであり、リアルタイムの対話に適しています。"
},
+ "step-1.5v-mini": {
+ "description": "このモデルは、強力なビデオ理解能力を備えています。"
+ },
+ "step-1o-turbo-vision": {
+ "description": "このモデルは強力な画像理解能力を持ち、数理、コード分野で1oより優れています。モデルは1oよりも小さく、出力速度が速くなっています。"
+ },
+ "step-1o-vision-32k": {
+ "description": "このモデルは強力な画像理解能力を持っています。step-1vシリーズモデルと比較して、より優れた視覚性能を発揮します。"
+ },
"step-1v-32k": {
"description": "視覚入力をサポートし、多モーダルインタラクション体験を強化します。"
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "大規模なコンテキストインタラクションをサポートし、複雑な対話シナリオに適しています。"
},
+ "step-2-mini": {
+ "description": "新世代の自社開発のAttentionアーキテクチャMFAに基づく超高速大モデルで、非常に低コストでstep1と同様の効果を達成しつつ、より高いスループットと迅速な応答遅延を維持しています。一般的なタスクを処理でき、コード能力において特長を持っています。"
+ },
"taichu_llm": {
"description": "紫東太初言語大モデルは、強力な言語理解能力とテキスト創作、知識問答、コードプログラミング、数学計算、論理推論、感情分析、テキスト要約などの能力を備えています。革新的に大データの事前学習と多源の豊富な知識を組み合わせ、アルゴリズム技術を継続的に磨き、膨大なテキストデータから語彙、構造、文法、意味などの新しい知識を吸収し、モデルの効果を進化させています。ユーザーにより便利な情報とサービス、よりインテリジェントな体験を提供します。"
},
- "taichu_vqa": {
- "description": "Taichu 2.0Vは画像理解、知識移転、論理的帰納などの能力を融合させており、テキストと画像の質問応答分野で優れたパフォーマンスを発揮しています。"
+ "taichu_vl": {
+ "description": "画像理解、知識移転、論理帰納などの能力を融合し、画像とテキストの質問応答分野で優れたパフォーマンスを発揮します。"
+ },
+ "text-embedding-3-large": {
+ "description": "最も強力なベクトル化モデル、英語および非英語のタスクに適しています"
+ },
+ "text-embedding-3-small": {
+ "description": "効率的で経済的な次世代埋め込みモデル、知識検索やRAGアプリケーションなどのシーンに適しています"
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "智谱AIが発表したGLM-4シリーズの最新世代の事前トレーニングモデルのオープンソース版です。"
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B)は、高効率の戦略とモデルアーキテクチャを通じて、強化された計算能力を提供します。"
},
+ "tts-1": {
+ "description": "最新のテキスト音声合成モデル、リアルタイムシーン向けに速度を最適化"
+ },
+ "tts-1-hd": {
+ "description": "最新のテキスト音声合成モデル、品質を最適化"
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B)は、精密な指示タスクに適しており、優れた言語処理能力を提供します。"
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnetは業界標準を向上させ、競合モデルやClaude 3 Opusを超える性能を持ち、広範な評価で優れた結果を示し、我々の中程度のモデルの速度とコストを兼ね備えています。"
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 Sonnetは、Anthropicの最も高速な次世代モデルです。Claude 3 Haikuと比較して、Claude 3.7 Sonnetはすべてのスキルで向上しており、多くの知能ベンチマークテストで前世代の最大モデルClaude 3 Opusを超えています。"
+ },
+ "whisper-1": {
+ "description": "汎用音声認識モデル、多言語音声認識、音声翻訳、言語認識をサポート"
+ },
"wizardlm2": {
"description": "WizardLM 2は、Microsoft AIが提供する言語モデルであり、複雑な対話、多言語、推論、インテリジェントアシスタントの分野で特に優れた性能を発揮します。"
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "超高コストパフォーマンス、卓越した性能。性能と推論速度、コストに基づいて、高精度のバランス調整を行います。"
},
+ "yi-lightning": {
+ "description": "最新の高性能モデルで、高品質な出力を保証しつつ、推論速度が大幅に向上しています。"
+ },
+ "yi-lightning-lite": {
+ "description": "軽量版で、yi-lightningの使用を推奨します。"
+ },
"yi-medium": {
"description": "中型サイズモデルのアップグレード微調整であり、能力が均衡しており、コストパフォーマンスが高いです。指示遵守能力を深く最適化しています。"
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "複雑な視覚タスクモデルであり、高性能な画像理解と分析能力を提供します。"
+ },
+ "yi-vision-v2": {
+ "description": "複雑な視覚タスクモデルで、複数の画像に基づく高性能な理解と分析能力を提供します。"
}
}
diff --git a/DigitalHumanWeb/locales/ja-JP/plugin.json b/DigitalHumanWeb/locales/ja-JP/plugin.json
index 1edb807..3bebb58 100644
--- a/DigitalHumanWeb/locales/ja-JP/plugin.json
+++ b/DigitalHumanWeb/locales/ja-JP/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "プラグイン{{name}}の再インストールに失敗しました",
"urlError": "このリンクはJSON形式のコンテンツを返していません。有効なリンクであることを確認してください"
},
+ "inspector": {
+ "args": "パラメーターリストを表示",
+ "pluginRender": "プラグインインターフェースを表示"
+ },
"list": {
"item": {
"deprecated.title": "削除済み",
@@ -130,6 +134,34 @@
"plugin": "プラグインの実行中..."
},
"pluginList": "プラグインリスト",
+ "search": {
+ "config": {
+ "addKey": "キーを追加",
+ "close": "削除",
+ "confirm": "設定が完了し、再試行しました"
+ },
+ "crawPages": {
+ "crawling": "リンクを識別中",
+ "detail": {
+ "preview": "プレビュー",
+ "raw": "原文",
+ "tooLong": "テキストが長すぎます。会話のコンテキストには最初の {{characters}} 文字のみが保持され、それを超える部分は会話のコンテキストには含まれません"
+ },
+ "meta": {
+ "crawler": "クローリングモード",
+ "words": "文字数"
+ }
+ },
+ "searchxng": {
+ "baseURL": "入力してください",
+ "description": "SearchXNG の URL を入力すると、ネット検索を開始できます",
+ "keyPlaceholder": "キーを入力してください",
+ "title": "SearchXNG 検索エンジンの設定",
+ "unconfiguredDesc": "ネット検索を開始するには、管理者に連絡して SearchXNG 検索エンジンの設定を完了してください",
+ "unconfiguredTitle": "SearchXNG 検索エンジンはまだ設定されていません"
+ },
+ "title": "ネット検索"
+ },
"setting": "プラグインの設定",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/ja-JP/portal.json b/DigitalHumanWeb/locales/ja-JP/portal.json
index ba3b4b3..acdd1e0 100644
--- a/DigitalHumanWeb/locales/ja-JP/portal.json
+++ b/DigitalHumanWeb/locales/ja-JP/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "プラグイン",
- "actions": {
- "genAiMessage": "AIメッセージを生成",
- "summary": "サマリー",
- "summaryTooltip": "現在の内容を要約"
- },
"artifacts": {
"display": {
"code": "コード",
diff --git a/DigitalHumanWeb/locales/ja-JP/providers.json b/DigitalHumanWeb/locales/ja-JP/providers.json
index b0b5343..943c39a 100644
--- a/DigitalHumanWeb/locales/ja-JP/providers.json
+++ b/DigitalHumanWeb/locales/ja-JP/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labsは企業向けに基盤モデルと人工知能システムを構築し、生成的人工知能の生産への応用を加速します。"
+ },
"ai360": {
"description": "360 AIは、360社が提供するAIモデルとサービスプラットフォームであり、360GPT2 Pro、360GPT Pro、360GPT Turbo、360GPT Turbo Responsibility 8Kなど、さまざまな先進的な自然言語処理モデルを提供しています。これらのモデルは、大規模なパラメータと多モーダル能力を組み合わせており、テキスト生成、意味理解、対話システム、コード生成などの分野で広く使用されています。柔軟な価格戦略を通じて、360 AIは多様なユーザーのニーズに応え、開発者の統合をサポートし、スマートアプリケーションの革新と発展を促進します。"
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azureは、GPT-3.5や最新のGPT-4シリーズを含む多様な先進AIモデルを提供し、さまざまなデータタイプや複雑なタスクをサポートし、安全で信頼性が高く持続可能なAIソリューションに取り組んでいます。"
},
+ "azureai": {
+ "description": "Azureは、GPT-3.5や最新のGPT-4シリーズを含む多様な先進的AIモデルを提供し、さまざまなデータタイプや複雑なタスクをサポートし、安全で信頼性が高く持続可能なAIソリューションに取り組んでいます。"
+ },
"baichuan": {
"description": "百川智能は、人工知能大モデルの研究開発に特化した企業であり、そのモデルは国内の知識百科、長文処理、生成創作などの中国語タスクで卓越したパフォーマンスを示し、海外の主流モデルを超えています。百川智能は、業界をリードする多モーダル能力を持ち、複数の権威ある評価で優れたパフォーマンスを示しています。そのモデルには、Baichuan 4、Baichuan 3 Turbo、Baichuan 3 Turbo 128kなどが含まれ、異なるアプリケーションシーンに最適化され、高コストパフォーマンスのソリューションを提供しています。"
},
"bedrock": {
"description": "Bedrockは、Amazon AWSが提供するサービスで、企業に先進的なAI言語モデルと視覚モデルを提供することに特化しています。そのモデルファミリーには、AnthropicのClaudeシリーズやMetaのLlama 3.1シリーズなどが含まれ、軽量から高性能までのさまざまな選択肢を提供し、テキスト生成、対話、画像処理などの多様なタスクをサポートし、異なる規模とニーズの企業アプリケーションに適しています。"
},
+ "cloudflare": {
+ "description": "Cloudflareのグローバルネットワーク上で、サーバーレスGPUによって駆動される機械学習モデルを実行します。"
+ },
"deepseek": {
"description": "DeepSeekは、人工知能技術の研究と応用に特化した企業であり、最新のモデルDeepSeek-V2.5は、汎用対話とコード処理能力を融合させ、人間の好みの整合、ライティングタスク、指示の遵守などの面で顕著な向上を実現しています。"
},
+ "doubao": {
+ "description": "バイトダンスが開発した独自の大規模モデルです。バイトダンス内部の50以上のビジネスシーンでの実践を通じて検証され、毎日数兆トークンの大規模な使用量で磨かれ、多様なモーダル能力を提供し、高品質なモデル効果で企業に豊かなビジネス体験を提供します。"
+ },
"fireworksai": {
"description": "Fireworks AIは、先進的な言語モデルサービスのリーダーであり、機能呼び出しと多モーダル処理に特化しています。最新のモデルFirefunction V2はLlama-3に基づいており、関数呼び出し、対話、指示の遵守に最適化されています。視覚言語モデルFireLLaVA-13Bは、画像とテキストの混合入力をサポートしています。他の注目すべきモデルには、LlamaシリーズやMixtralシリーズがあり、高効率の多言語指示遵守と生成サポートを提供しています。"
},
+ "giteeai": {
+ "description": "Gitee AIのServerless APIは、AI開発者に開梱即使用の大モデル推論APIサービスを提供する。"
+ },
"github": {
"description": "GitHubモデルを使用することで、開発者はAIエンジニアになり、業界をリードするAIモデルを使って構築できます。"
},
@@ -30,6 +44,24 @@
"groq": {
"description": "GroqのLPU推論エンジンは、最新の独立した大規模言語モデル(LLM)ベンチマークテストで卓越したパフォーマンスを示し、その驚異的な速度と効率でAIソリューションの基準を再定義しています。Groqは、即時推論速度の代表であり、クラウドベースの展開で良好なパフォーマンスを発揮しています。"
},
+ "higress": {
+ "description": "Higressは、阿里内部でTengineのリロードが長期接続のビジネスに悪影響を及ぼすことや、gRPC/Dubboの負荷分散能力が不足している問題を解決するために生まれた、クラウドネイティブなAPIゲートウェイです。"
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference APIは、数千のモデルをさまざまなタスクに対して探索するための迅速かつ無料の方法を提供します。新しいアプリケーションのプロトタイプを作成している場合でも、機械学習の機能を試している場合でも、このAPIは複数の分野の高性能モデルに即座にアクセスできるようにします。"
+ },
+ "hunyuan": {
+ "description": "テンセントが開発した大規模言語モデルであり、強力な中国語の創作能力、複雑な文脈における論理的推論能力、そして信頼性の高いタスク実行能力を備えています。"
+ },
+ "internlm": {
+ "description": "大規模モデルの研究と開発ツールチェーンに特化したオープンソース組織です。すべてのAI開発者に対して、高効率で使いやすいオープンプラットフォームを提供し、最先端の大規模モデルとアルゴリズム技術を身近に感じられるようにします。"
+ },
+ "jina": {
+ "description": "Jina AIは2020年に設立され、検索AIのリーディングカンパニーです。私たちの検索基盤プラットフォームには、ベクトルモデル、リランキングモデル、小型言語モデルが含まれており、企業が信頼性が高く高品質な生成AIおよびマルチモーダル検索アプリケーションを構築するのを支援します。"
+ },
+ "lmstudio": {
+ "description": "LM Studioは、あなたのコンピュータ上でLLMを開発し、実験するためのデスクトップアプリケーションです。"
+ },
"minimax": {
"description": "MiniMaxは2021年に設立された汎用人工知能テクノロジー企業であり、ユーザーと共に知能を共創することに取り組んでいます。MiniMaxは、さまざまなモードの汎用大モデルを独自に開発しており、トリリオンパラメータのMoEテキスト大モデル、音声大モデル、画像大モデルを含んでいます。また、海螺AIなどのアプリケーションも展開しています。"
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AIは、さまざまな大規模言語モデルとAI画像生成のAPIサービスを提供するプラットフォームであり、柔軟で信頼性が高く、コスト効率に優れています。Llama3、Mistralなどの最新のオープンソースモデルをサポートし、生成的AIアプリケーションの開発に向けた包括的でユーザーフレンドリーかつ自動スケーリングのAPIソリューションを提供し、AIスタートアップの急成長を支援します。"
},
+ "nvidia": {
+ "description": "NVIDIA NIM™は、自己ホスティングのGPU加速推論マイクロサービスに使用できるコンテナを提供し、クラウド、データセンター、RTX™ AIパーソナルコンピュータ、ワークステーション上で事前トレーニング済みおよびカスタムAIモデルを展開することをサポートします。"
+ },
"ollama": {
"description": "Ollamaが提供するモデルは、コード生成、数学演算、多言語処理、対話インタラクションなどの分野を広くカバーし、企業向けおよびローカライズされた展開の多様なニーズに対応しています。"
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexityは、先進的な対話生成モデルの提供者であり、さまざまなLlama 3.1モデルを提供し、オンラインおよびオフラインアプリケーションをサポートし、特に複雑な自然言語処理タスクに適しています。"
},
+ "ppio": {
+ "description": "PPIO パイオ云は、安定した高コストパフォーマンスのオープンソースモデル API サービスを提供し、DeepSeek の全シリーズ、Llama、Qwen などの業界をリードする大規模モデルをサポートしています。"
+ },
"qwen": {
"description": "通義千問は、アリババクラウドが独自に開発した超大規模言語モデルであり、強力な自然言語理解と生成能力を持っています。さまざまな質問に答えたり、文章を創作したり、意見を表現したり、コードを執筆したりすることができ、さまざまな分野で活躍しています。"
},
+ "sambanova": {
+ "description": "SambaNova Cloudは、開発者が最高のオープンソースモデルを簡単に利用でき、最速の推論速度を享受できるようにします。"
+ },
+ "sensenova": {
+ "description": "商湯日日新は、商湯の強力な基盤支援に基づき、高効率で使いやすい全スタックの大規模モデルサービスを提供します。"
+ },
"siliconcloud": {
"description": "SiliconFlowは、AGIを加速させ、人類に利益をもたらすことを目指し、使いやすくコスト効率の高いGenAIスタックを通じて大規模AIの効率を向上させることに取り組んでいます。"
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "中科院自動化研究所と武漢人工知能研究院が新世代の多モーダル大モデルを発表し、多輪問答、テキスト創作、画像生成、3D理解、信号分析などの包括的な問答タスクをサポートし、より強力な認知、理解、創作能力を持ち、新しいインタラクティブな体験を提供します。"
},
+ "tencentcloud": {
+ "description": "知識エンジン原子能力(LLM Knowledge Engine Atomic Power)は、知識エンジンに基づいて開発された知識問答の全体的な能力であり、企業や開発者向けに、柔軟にモデルアプリケーションを構築・開発する能力を提供します。複数の原子能力を使用して、専用のモデルサービスを構築し、文書解析、分割、埋め込み、多段階の書き換えなどのサービスを組み合わせて、企業専用のAIビジネスをカスタマイズできます。"
+ },
"togetherai": {
"description": "Together AIは、革新的なAIモデルを通じて先進的な性能を実現することに取り組んでおり、迅速なスケーリングサポートや直感的な展開プロセスを含む広範なカスタマイズ能力を提供し、企業のさまざまなニーズに応えています。"
},
"upstage": {
"description": "Upstageは、さまざまなビジネスニーズに応じたAIモデルの開発に特化しており、Solar LLMや文書AIを含み、人造一般知能(AGI)の実現を目指しています。Chat APIを通じてシンプルな対話エージェントを作成し、機能呼び出し、翻訳、埋め込み、特定分野のアプリケーションをサポートします。"
},
+ "vertexai": {
+ "description": "GoogleのGeminiシリーズは、Google DeepMindによって開発された最先端の汎用AIモデルであり、マルチモーダル設計に特化しています。テキスト、コード、画像、音声、動画のシームレスな理解と処理をサポートし、データセンターからモバイルデバイスまでのさまざまな環境で使用できます。AIモデルの効率と適用範囲を大幅に向上させます。"
+ },
+ "vllm": {
+ "description": "vLLMは、LLM推論とサービスのための迅速で使いやすいライブラリです。"
+ },
+ "volcengine": {
+ "description": "バイトダンスが提供する大規模モデルサービスの開発プラットフォームで、機能が豊富で安全性が高く、価格競争力のあるモデル呼び出しサービスを提供します。また、モデルデータ、ファインチューニング、推論、評価などのエンドツーエンド機能を提供し、AIアプリケーションの開発を全面的にサポートします。"
+ },
+ "wenxin": {
+ "description": "企業向けのワンストップ大規模モデルとAIネイティブアプリケーションの開発およびサービスプラットフォームで、最も包括的で使いやすい生成的人工知能モデルの開発とアプリケーション開発の全プロセスツールチェーンを提供します。"
+ },
+ "xai": {
+ "description": "xAIは、人類の科学的発見を加速するための人工知能を構築することに専念している企業です。私たちの使命は、宇宙に対する共通の理解を促進することです。"
+ },
"zeroone": {
"description": "01.AIは、AI 2.0時代の人工知能技術に特化し、「人+人工知能」の革新と応用を推進し、超強力なモデルと先進的なAI技術を用いて人類の生産性を向上させ、技術の力を実現します。"
},
diff --git a/DigitalHumanWeb/locales/ja-JP/setting.json b/DigitalHumanWeb/locales/ja-JP/setting.json
index de7cf53..42722a8 100644
--- a/DigitalHumanWeb/locales/ja-JP/setting.json
+++ b/DigitalHumanWeb/locales/ja-JP/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "カスタムモデルの設定",
"tokens": {
- "title": "最大トークン数",
- "unlimited": "無制限"
+ "title": "最大トークン数"
},
"vision": {
"extra": "この設定はアプリ内の画像アップロード機能のみを有効にします。認識のサポートはモデル自体に依存するため、モデルの視覚認識機能の有効性を自分でテストしてください。",
@@ -98,6 +97,7 @@
"title": "クライアントサイドリクエストモードの使用"
},
"fetcher": {
+ "clear": "取得したモデルをクリア",
"fetch": "モデルリストを取得する",
"fetching": "モデルリストを取得中...",
"latestTime": "最終更新時間:{{time}}",
@@ -175,8 +175,8 @@
"desc": "会話中に自動的にトピックを作成するかどうか。一時的なトピックのみ有効です",
"title": "自動的にトピックを作成する"
},
- "enableCompressThreshold": {
- "title": "過去メッセージの長さの圧縮閾値を有効にする"
+ "enableCompressHistory": {
+ "title": "履歴メッセージの自動要約を有効にする"
},
"enableHistoryCount": {
"alias": "制限なし",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "単一応答制限を有効にする"
},
+ "enableReasoningEffort": {
+ "title": "推論強度調整を有効にする"
+ },
"frequencyPenalty": {
- "desc": "値が大きいほど、単語の繰り返しを減らす可能性が高くなります",
- "title": "頻度ペナルティ"
+ "desc": "値が大きいほど、言葉がより豊かで多様になります。値が小さいほど、言葉はより素朴でシンプルになります。",
+ "title": "語彙の豊かさ"
},
"maxTokens": {
"desc": "1 回の対話で使用される最大トークン数",
@@ -212,19 +215,31 @@
"desc": "{{provider}}モデル",
"title": "モデル"
},
+ "params": {
+ "title": "高度なパラメータ"
+ },
"presencePenalty": {
- "desc": "値が大きいほど、新しいトピックに拡張する可能性が高くなります",
- "title": "トピックの新鮮度"
+ "desc": "値が大きいほど、異なる表現方法を好み、概念の繰り返しを避けます。値が小さいほど、繰り返しの概念や表現を使用する傾向が強く、一貫性のある表現になります。",
+ "title": "表現の多様性"
+ },
+ "reasoningEffort": {
+ "desc": "値が大きいほど推論能力が高まりますが、応答時間とトークン消費が増加する可能性があります",
+ "options": {
+ "high": "高",
+ "low": "低",
+ "medium": "中"
+ },
+ "title": "推論強度"
},
"temperature": {
- "desc": "値が大きいほど、応答がよりランダムになります",
- "title": "ランダム性",
- "titleWithValue": "ランダム性 {{value}}"
+ "desc": "数値が大きいほど、回答はより創造的で想像力に富む;数値が小さいほど、回答はより厳密になる",
+ "title": "創造性の活性度",
+ "warning": "創造性の活性度が高すぎると、出力に乱れが生じる可能性があります"
},
"title": "モデル設定",
"topP": {
- "desc": "ランダム性と同様ですが、ランダム性と一緒に変更しないでください",
- "title": "トップ P サンプリング"
+ "desc": "どれだけの可能性を考慮するか。値が大きいほど、より多くの可能な回答を受け入れる;値が小さいほど、最も可能性の高い回答を選ぶ傾向がある。創造性の活性度と一緒に変更することは推奨しません",
+ "title": "思考の開放度"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "アシスタントの名前、説明、アバター、ラベルを生成するために指定されたモデル",
"title": "アシスタント情報の自動生成"
},
+ "customPrompt": {
+ "addPrompt": "カスタムプロンプトを追加",
+ "desc": "入力後、システムアシスタントは生成するコンテンツにカスタムプロンプトを使用します",
+ "placeholder": "カスタムプロンプトを入力してください",
+ "title": "カスタムプロンプト"
+ },
+ "historyCompress": {
+ "label": "会話履歴モデル",
+ "modelDesc": "会話履歴を圧縮するために指定されたモデル",
+ "title": "会話履歴の自動要約"
+ },
"queryRewrite": {
"label": "質問リライトモデル",
"modelDesc": "ユーザーの質問を最適化するために指定されたモデル",
- "title": "知識ベース"
+ "title": "知識ベースの質問の書き換え"
+ },
+ "thread": {
+ "label": "サブトピック命名モデル",
+ "modelDesc": "サブトピックの自動命名に使用されるモデルを指定します",
+ "title": "サブトピックの自動命名"
},
"title": "システムアシスタント",
"topic": {
@@ -395,6 +426,7 @@
"common": "一般設定",
"experiment": "実験",
"llm": "言語モデル",
+ "provider": "AIサービスプロバイダー",
"sync": "クラウド同期",
"system-agent": "システムアシスタント",
"tts": "音声サービス"
diff --git a/DigitalHumanWeb/locales/ja-JP/thread.json b/DigitalHumanWeb/locales/ja-JP/thread.json
new file mode 100644
index 0000000..21a1c42
--- /dev/null
+++ b/DigitalHumanWeb/locales/ja-JP/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "このスレッドを削除しようとしています。削除後は復元できませんので、慎重に操作してください。"
+ },
+ "newPortalThread": {
+ "includeContext": "トピックのコンテキストを含める",
+ "title": "新しいサブトピックを開始する"
+ },
+ "notSupportMultiModals": "サブトピックではファイルや画像のアップロードはサポートされていません。必要があれば、コメントを残してください:<1>💬 ディスカッションエリア1>"
+}
diff --git a/DigitalHumanWeb/locales/ja-JP/tool.json b/DigitalHumanWeb/locales/ja-JP/tool.json
index 15f3716..30804a8 100644
--- a/DigitalHumanWeb/locales/ja-JP/tool.json
+++ b/DigitalHumanWeb/locales/ja-JP/tool.json
@@ -6,5 +6,23 @@
"generating": "生成中...",
"images": "画像:",
"prompt": "プロンプト"
+ },
+ "search": {
+ "createNewSearch": "新しい検索記録を作成",
+ "emptyResult": "結果が見つかりませんでした。キーワードを変更して再試行してください",
+ "genAiMessage": "アシスタントメッセージを作成",
+ "includedTooltip": "現在の検索結果は会話の文脈に含まれます",
+ "keywords": "キーワード:",
+ "scoreTooltip": "関連性スコア。このスコアが高いほど、クエリキーワードとの関連性が高くなります",
+ "searchBar": {
+ "button": "検索",
+ "placeholder": "キーワード",
+ "tooltip": "検索結果を再取得し、新しい要約メッセージを作成します"
+ },
+ "searchEngine": "検索エンジン:",
+ "searchResult": "検索結果の数:",
+ "summary": "要約",
+ "summaryTooltip": "現在の内容を要約",
+ "viewMoreResults": "さらに {{results}} 件の結果を見る"
}
}
diff --git a/DigitalHumanWeb/locales/ja-JP/topic.json b/DigitalHumanWeb/locales/ja-JP/topic.json
new file mode 100644
index 0000000..5e259d3
--- /dev/null
+++ b/DigitalHumanWeb/locales/ja-JP/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "自動リネーム",
+ "confirmRemoveAll": "すべてのトピックを削除しようとしています。削除後は復元できませんので、慎重に操作してください。",
+ "confirmRemoveTopic": "このトピックを削除しようとしています。削除後は復元できませんので、慎重に操作してください。",
+ "confirmRemoveUnstarred": "未お気に入りのトピックを削除しようとしています。削除後は復元できませんので、慎重に操作してください。",
+ "duplicate": "コピーを作成",
+ "export": "トピックをエクスポート",
+ "removeAll": "すべてのトピックを削除",
+ "removeUnstarred": "未お気に入りのトピックを削除"
+ },
+ "defaultTitle": "デフォルトトピック",
+ "duplicateLoading": "トピックをコピー中...",
+ "duplicateSuccess": "トピックのコピーに成功しました",
+ "favorite": "お気に入り",
+ "groupMode": {
+ "ascMessages": "メッセージ総数順",
+ "byTime": "時間順にグループ化",
+ "descMessages": "メッセージ総数逆順",
+ "flat": "グループ化しない"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "今月",
+ "today": "今日",
+ "week": "今週",
+ "yesterday": "昨日"
+ }
+ },
+ "guide": {
+ "desc": "左側の送信ボタンをクリックすると、現在の会話を履歴トピックとして保存し、新しい会話を開始します。",
+ "title": "トピックリスト"
+ },
+ "searchPlaceholder": "トピックを検索...",
+ "searchResultEmpty": "検索結果はありません",
+ "temp": "一時的",
+ "title": "トピック"
+}
diff --git a/DigitalHumanWeb/locales/ja-JP/welcome.json b/DigitalHumanWeb/locales/ja-JP/welcome.json
index 43c6d37..8b71657 100644
--- a/DigitalHumanWeb/locales/ja-JP/welcome.json
+++ b/DigitalHumanWeb/locales/ja-JP/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "設定をインポート",
- "market": "市場を見る",
- "start": "すぐに開始"
- },
"guide": {
"agents": {
"replaceBtn": "別のグループ",
diff --git a/DigitalHumanWeb/locales/ko-KR/auth.json b/DigitalHumanWeb/locales/ko-KR/auth.json
index 78e9446..3bd9ee9 100644
--- a/DigitalHumanWeb/locales/ko-KR/auth.json
+++ b/DigitalHumanWeb/locales/ko-KR/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "지난 달",
+ "recent30Days": "최근 30일"
+ },
+ "header": {
+ "desc": "계정 정보를 관리하세요.",
+ "title": "계정"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "비활성",
+ "more": "활성"
+ },
+ "months": {
+ "apr": "4월",
+ "aug": "8월",
+ "dec": "12월",
+ "feb": "2월",
+ "jan": "1월",
+ "jul": "7월",
+ "jun": "6월",
+ "mar": "3월",
+ "may": "5월",
+ "nov": "11월",
+ "oct": "10월",
+ "sep": "9월"
+ },
+ "tooltip": "{{date}}에 {{count}}개의 메시지를 보냈습니다.",
+ "totalCount": "지난 1년 동안 총 {{count}}개의 메시지가 전송되었습니다."
+ },
"login": "로그인",
"loginOrSignup": "로그인 / 가입",
- "profile": "프로필",
- "security": "보안",
+ "profile": {
+ "avatar": "아바타",
+ "email": "이메일 주소",
+ "sso": {
+ "loading": "연결된 제3자 계정을 로드 중입니다",
+ "providers": "연결된 계정",
+ "unlink": {
+ "description": "연결을 해제하면 {{provider}} 계정“{{providerAccountId}}”으로 로그인할 수 없습니다. 현재 계정에 {{provider}} 계정을 다시 연결해야 하는 경우, {{provider}} 계정의 이메일 주소가 {{email}}인지 확인하십시오. 로그인 시 자동으로 현재 로그인 계정에 연결됩니다.",
+ "forbidden": "최소한 하나의 제3자 계정 연결을 유지해야 합니다.",
+ "title": "이 제3자 계정 {{provider}} 를 연결 해제하시겠습니까?"
+ }
+ },
+ "username": "사용자 이름"
+ },
"signout": "로그아웃",
- "signup": "가입"
+ "signup": "가입",
+ "stats": {
+ "aiheatmaps": "활동 지수",
+ "assistants": "어시스턴트",
+ "assistantsRank": {
+ "left": "어시스턴트",
+ "right": "주제",
+ "title": "어시스턴트 사용 순위"
+ },
+ "createdAt": "등록일",
+ "days": "일",
+ "empty": {
+ "desc": "더 많은 채팅 데이터를 축적하여 보세요.",
+ "title": "데이터 없음"
+ },
+ "lastYearActivity": "지난 1년간의 활동",
+ "loginGuide": {
+ "f1": "무료 사용량 받기",
+ "f2": "다양한 기기에서 메시지 동기화",
+ "f3": "풍부한 도우미 기능 제공",
+ "f4": "강력한 플러그인 탐색",
+ "title": "로그인 후 할 수 있는 것:"
+ },
+ "messages": "메시지",
+ "modelsRank": {
+ "left": "모델",
+ "right": "메시지",
+ "title": "모델 사용 순위"
+ },
+ "share": {
+ "title": "내 AI 활동 지수"
+ },
+ "topics": "주제",
+ "topicsRank": {
+ "left": "주제",
+ "right": "메시지",
+ "title": "주제 내용 순위"
+ },
+ "updatedAt": "업데이트 일",
+ "welcome": "{{username}}, {{appName}}와 함께한 {{days}}일입니다.",
+ "words": "단어"
+ },
+ "tab": {
+ "profile": "프로필",
+ "security": "보안",
+ "stats": "통계"
+ }
}
diff --git a/DigitalHumanWeb/locales/ko-KR/changelog.json b/DigitalHumanWeb/locales/ko-KR/changelog.json
new file mode 100644
index 0000000..08dc722
--- /dev/null
+++ b/DigitalHumanWeb/locales/ko-KR/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "X에서 저희를 팔로우하세요",
+ "subscribeToUpdates": "업데이트 구독하기",
+ "versions": "버전 세부정보"
+ },
+ "addedWhileAway": "귀하가 떠나 있는 동안 새로운 기능이 추가되었습니다.",
+ "allChangelog": "모든 업데이트 로그 보기",
+ "description": "{{appName}}의 새로운 기능과 개선 사항을 지속적으로 추적하세요",
+ "pagination": {
+ "next": "다음 페이지",
+ "older": "이전 변경 사항 보기"
+ },
+ "readDetails": "자세히 읽기",
+ "title": "업데이트 로그",
+ "versionDetails": "버전 세부정보",
+ "welcomeBack": "다시 오신 것을 환영합니다!"
+}
diff --git a/DigitalHumanWeb/locales/ko-KR/chat.json b/DigitalHumanWeb/locales/ko-KR/chat.json
index 09cb0b0..613be77 100644
--- a/DigitalHumanWeb/locales/ko-KR/chat.json
+++ b/DigitalHumanWeb/locales/ko-KR/chat.json
@@ -8,6 +8,7 @@
"agents": "도우미",
"artifact": {
"generating": "생성 중",
+ "inThread": "하위 주제에서는 볼 수 없습니다. 주 대화 영역으로 전환하여 열어주세요.",
"thinking": "생각 중",
"thought": "사고 과정",
"unknownTitle": "제목 없음"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} 복사본",
"emptyAgent": "도우미가 없습니다",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "단일 대화 생성 비용을 최대 90%까지 줄이고, 응답 속도를 4배 향상시킵니다 (<1>자세히 알아보기1>). 활성화하면 자동으로 이전 메시지 수 제한이 비활성화됩니다.",
+ "title": "문맥 캐시 활성화"
+ },
+ "enableReasoning": {
+ "desc": "Claude Thinking 메커니즘에 기반한 제한 (<1>자세히 알아보기1>), 활성화하면 자동으로 이전 메시지 수 제한이 비활성화됩니다.",
+ "title": "심층 사고 활성화"
+ },
+ "reasoningBudgetToken": {
+ "title": "사고 소모 토큰"
+ },
+ "title": "모델 확장 기능"
+ },
+ "history": {
+ "title": "도우미는 마지막 {{count}}개의 메시지만 기억합니다."
+ },
"historyRange": "대화 기록 범위",
+ "historySummary": "역사 메시지 요약",
"inbox": {
"desc": "뇌 클러스터를 활성화하여 창의적인 아이디어를 끌어내는 인공지능 비서입니다. 여기서 모든 것에 대해 대화합니다.",
"title": "무작위 대화"
@@ -45,6 +64,9 @@
"stop": "중지",
"warp": "줄바꿈"
},
+ "intentUnderstanding": {
+ "title": "귀하의 의도를 이해하고 분석하는 중입니다..."
+ },
"knowledgeBase": {
"all": "모든 내용",
"allFiles": "모든 파일",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "삭제하고 다시 생성",
+ "deleteDisabledByThreads": "하위 주제가 존재하여 삭제할 수 없습니다.",
"regenerate": "다시 생성"
},
+ "messages": {
+ "modelCard": {
+ "credit": "포인트",
+ "creditPricing": "가격",
+ "creditTooltip": "계산을 용이하게 하기 위해, 1$를 1M 포인트로 환산합니다. 예를 들어, $3/M 토큰은 3포인트/토큰으로 환산됩니다.",
+ "pricing": {
+ "inputCachedTokens": "캐시된 입력 {{amount}}/포인트 · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M 문자",
+ "inputMinutes": "${{amount}}/분",
+ "inputTokens": "입력 {{amount}}/포인트 · ${{amount}}/M",
+ "outputTokens": "출력 {{amount}}/포인트 · ${{amount}}/M",
+ "writeCacheInputTokens": "캐시 입력 쓰기 {{amount}}/포인트 · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "평균 단가",
+ "input": "입력",
+ "inputAudio": "오디오 입력",
+ "inputCached": "입력 캐시",
+ "inputCitation": "입력 인용",
+ "inputText": "텍스트 입력",
+ "inputTitle": "입력 세부사항",
+ "inputUncached": "입력 비캐시",
+ "inputWriteCached": "입력 캐시 쓰기",
+ "output": "출력",
+ "outputAudio": "오디오 출력",
+ "outputText": "텍스트 출력",
+ "outputTitle": "출력 세부사항",
+ "reasoning": "심층 사고",
+ "title": "생성 세부사항",
+ "total": "총 소모"
+ }
+ },
"newAgent": "새 도우미",
"pin": "고정",
"pinOff": "고정 해제",
@@ -81,6 +137,32 @@
},
"regenerate": "재생성",
"roleAndArchive": "역할 및 아카이브",
+ "search": {
+ "grounding": {
+ "searchQueries": "검색 키워드",
+ "title": "{{count}}개의 결과가 검색되었습니다"
+ },
+ "mode": {
+ "auto": {
+ "desc": "대화 내용을 기반으로 검색 필요성을 스마트하게 판단",
+ "title": "스마트 연결"
+ },
+ "off": {
+ "desc": "모델의 기본 지식만 사용하고 네트워크 검색을 수행하지 않음",
+ "title": "연결 끄기"
+ },
+ "on": {
+ "desc": "지속적으로 네트워크 검색을 수행하여 최신 정보를 얻음",
+ "title": "항상 연결"
+ },
+ "useModelBuiltin": "모델 내장 검색 엔진 사용"
+ },
+ "searchModel": {
+ "desc": "현재 모델은 함수 호출을 지원하지 않으므로 함수 호출을 지원하는 모델과 함께 사용해야 인터넷 검색이 가능합니다.",
+ "title": "검색 보조 모델"
+ },
+ "title": "연결 검색"
+ },
"searchAgentPlaceholder": "검색 도우미...",
"sendPlaceholder": "채팅 내용 입력...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "그룹 이름은 1-20자여야 합니다"
},
"shareModal": {
+ "copy": "복사",
"download": "스크린샷 다운로드",
+ "downloadFile": "파일 다운로드",
+ "exportTitle": "기본 제목",
"imageType": "이미지 형식",
+ "includeTool": "플러그인 메시지 포함",
+ "includeUser": "사용자 메시지 포함",
"screenshot": "스크린샷",
"settings": "내보내기 설정",
- "shareToShareGPT": "ShareGPT 공유 링크 생성",
+ "text": "텍스트",
"withBackground": "배경 이미지 포함",
"withFooter": "푸터 포함",
"withPluginInfo": "플러그인 정보 포함",
+ "withRole": "메시지 역할 포함",
"withSystemRole": "도우미 역할 포함"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "인식 중...",
"prettifying": "정제 중..."
},
- "temp": "임시",
+ "thread": {
+ "divider": "하위 주제",
+ "threadMessageCount": "{{messageCount}}개의 메시지",
+ "title": "하위 주제"
+ },
"tokenDetails": {
"chats": "채팅 메시지",
+ "historySummary": "역사 요약",
"rest": "남은 사용량",
"systemRole": "시스템 역할",
"title": "컨텍스트 세부 정보",
@@ -131,29 +224,10 @@
"used": "사용됨"
},
"topic": {
- "actions": {
- "autoRename": "자동으로 이름 바꾸기",
- "duplicate": "복사본 만들기",
- "export": "주제 내보내기"
- },
"checkOpenNewTopic": "새 주제를 열까요?",
"checkSaveCurrentMessages": "현재 대화를 주제로 저장하시겠습니까?",
- "confirmRemoveAll": "모든 주제를 삭제하시면 되돌릴 수 없습니다. 신중하게 작업하시겠습니까?",
- "confirmRemoveTopic": "이 주제를 삭제하시면 되돌릴 수 없습니다. 신중하게 작업하시겠습니까?",
- "confirmRemoveUnstarred": "별표가 없는 주제를 삭제하시면 되돌릴 수 없습니다. 신중하게 작업하시겠습니까?",
- "defaultTitle": "기본 주제",
- "duplicateLoading": "주제 복사 중...",
- "duplicateSuccess": "주제 복사 성공",
- "guide": {
- "desc": "현재 대화를 히스토리 토픽으로 저장하고 새 대화를 시작하려면 왼쪽 버튼을 클릭하세요.",
- "title": "토픽 목록"
- },
"openNewTopic": "새 주제 열기",
- "removeAll": "모든 주제 삭제",
- "removeUnstarred": "별표가 없는 주제 삭제",
- "saveCurrentMessages": "현재 대화를 주제로 저장",
- "searchPlaceholder": "주제 검색...",
- "title": "주제 목록"
+ "saveCurrentMessages": "현재 대화를 주제로 저장"
},
"translate": {
"action": "번역",
@@ -184,5 +258,6 @@
"processing": "파일 처리 중..."
}
}
- }
+ },
+ "zenMode": "집중 모드"
}
diff --git a/DigitalHumanWeb/locales/ko-KR/common.json b/DigitalHumanWeb/locales/ko-KR/common.json
index bb45541..217386a 100644
--- a/DigitalHumanWeb/locales/ko-KR/common.json
+++ b/DigitalHumanWeb/locales/ko-KR/common.json
@@ -9,15 +9,79 @@
"title": "환영합니다 {{name}}"
}
},
- "appInitializing": "앱 초기화 중...",
+ "appLoading": {
+ "appIdle": "시작 준비 중",
+ "appInitializing": "앱을 초기화하는 중...",
+ "failed": "죄송합니다. 애플리케이션 초기화에 실패했습니다. 상세 정보를 확인하여 문제를 해결해 주세요.",
+ "finished": "데이터베이스 초기화 완료",
+ "goToChat": "대화 페이지 로딩 중...",
+ "initAuth": "인증 서비스 초기화 중...",
+ "initUser": "사용자 상태 초기화 중...",
+ "initializing": "PGlite 데이터베이스 초기화 중...",
+ "loadingDependencies": "의존성 초기화 중...",
+ "loadingWasm": "WASM 모듈 로드 중...",
+ "migrating": "데이터베이스 테이블 마이그레이션 중...",
+ "ready": "데이터베이스 준비 완료",
+ "showDetail": "자세히 보기"
+ },
"autoGenerate": "자동 생성",
"autoGenerateTooltip": "힌트 단어를 기반으로 에이전트 설명을 자동으로 완성합니다",
"autoGenerateTooltipDisabled": "자동 완성 기능을 사용하려면 툴팁을 입력하십시오",
"back": "뒤로",
"batchDelete": "일괄 삭제",
"blog": "제품 블로그",
+ "branching": "하위 주제 만들기",
+ "branchingDisable": "「하위 주제」 기능은 서버 버전에서만 사용할 수 있습니다. 이 기능이 필요하시면 서버 배포 모드로 전환하거나 LobeChat Cloud를 사용하세요.",
"cancel": "취소",
"changelog": "변경 로그",
+ "clientDB": {
+ "autoInit": {
+ "title": "PGlite 데이터베이스 초기화"
+ },
+ "error": {
+ "desc": "죄송합니다. Pglite 데이터베이스 초기화 과정에서 예외가 발생했습니다. 버튼을 클릭하여 다시 시도해 주십시오. 여러 번 시도한 후에도 여전히 문제가 발생하면 <1>문제를 제출1>해 주십시오. 저희가 즉시 문제를 해결해 드리겠습니다.",
+ "detail": "오류 원인: [[[{{type}}]]] {{message}},상세 내용은 다음과 같습니다:",
+ "retry": "재시도",
+ "title": "데이터베이스 초기화 실패"
+ },
+ "initing": {
+ "error": "오류가 발생했습니다. 재시도해 주세요.",
+ "idle": "초기화 대기 중...",
+ "initializing": "초기화 중...",
+ "loadingDependencies": "의존성 로드 중...",
+ "loadingWasmModule": "WASM 모듈 로드 중...",
+ "migrating": "데이터베이스 마이그레이션 실행 중...",
+ "ready": "데이터베이스 준비 완료"
+ },
+ "modal": {
+ "desc": "PGlite 클라이언트 데이터베이스를 활성화하여 브라우저에서 채팅 데이터를 영구 저장하고 지식베이스 등 고급 기능을 사용하세요.",
+ "enable": "즉시 활성화",
+ "features": {
+ "knowledgeBase": {
+ "desc": "개인 지식 기반을 구축하고, 당신의 도우미와 쉽게 지식 기반 대화를 시작하세요(곧 출시 예정)",
+ "title": "지식 기반 대화 지원, 두 번째 뇌를 열다"
+ },
+ "localFirst": {
+ "desc": "채팅 데이터는 완전히 브라우저에 저장되며, 당신의 데이터는 항상 당신의 손에 있습니다.",
+ "title": "로컬 우선, 프라이버시 최우선"
+ },
+ "pglite": {
+ "desc": "PGlite를 기반으로 구축되어, AI 네이티브 고급 기능(벡터 검색)을 원활하게 지원합니다.",
+ "title": "차세대 클라이언트 저장 아키텍처"
+ }
+ },
+ "init": {
+ "desc": "데이터베이스를 초기화 중입니다. 네트워크 차이에 따라 5~30초가 소요될 수 있습니다.",
+ "title": "PGlite 데이터베이스 초기화 중"
+ },
+ "title": "클라이언트 데이터베이스 활성화"
+ },
+ "ready": {
+ "button": "즉시 사용",
+ "desc": "즉시 사용하고 싶습니다.",
+ "title": "PGlite 데이터베이스 준비 완료"
+ }
+ },
"close": "닫기",
"contact": "연락처",
"copy": "복사",
@@ -112,6 +176,7 @@
"en": "영어",
"en-US": "영어",
"es-ES": "스페인어",
+ "fa-IR": "페르시아어",
"fi-FI": "핀란드어",
"fr-FR": "프랑스어",
"hi-IN": "힌디어",
@@ -153,6 +218,7 @@
"pinOff": "고정 해제",
"privacy": "개인정보 보호 정책",
"regenerate": "재생성",
+ "releaseNotes": "버전 세부정보",
"rename": "이름 바꾸기",
"reset": "재설정",
"retry": "재시도",
@@ -209,6 +275,7 @@
},
"temp": "임시",
"terms": "이용 약관",
+ "update": "업데이트",
"updateAgent": "에이전트 정보 업데이트",
"upgradeVersion": {
"action": "업그레이드",
@@ -219,6 +286,7 @@
"anonymousNickName": "익명 사용자",
"billing": "결제 관리",
"cloud": "체험 {{name}}",
+ "community": "커뮤니티 버전",
"data": "데이터 저장",
"defaultNickname": "커뮤니티 사용자",
"discord": "커뮤니티 지원",
@@ -228,7 +296,6 @@
"help": "도움말 센터",
"moveGuide": "설정 버튼을 여기로 이동했습니다",
"plans": "요금제",
- "preview": "미리보기",
"profile": "계정 관리",
"setting": "앱 설정",
"usages": "사용량 통계"
diff --git a/DigitalHumanWeb/locales/ko-KR/components.json b/DigitalHumanWeb/locales/ko-KR/components.json
index bbbc458..441f0ed 100644
--- a/DigitalHumanWeb/locales/ko-KR/components.json
+++ b/DigitalHumanWeb/locales/ko-KR/components.json
@@ -12,6 +12,7 @@
"batchChunking": "배치 청크 분할",
"chunking": "청크 분할",
"chunkingTooltip": "파일을 여러 텍스트 블록으로 분할하고 벡터화한 후, 의미 검색 및 파일 대화에 사용할 수 있습니다.",
+ "chunkingUnsupported": "이 파일은 청크 처리를 지원하지 않습니다.",
"confirmDelete": "해당 파일을 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니, 작업을 확인해 주세요.",
"confirmDeleteMultiFiles": "선택한 {{count}} 개 파일을 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니, 작업을 확인해 주세요.",
"confirmRemoveFromKnowledgeBase": "선택한 {{count}} 개 파일을 지식 베이스에서 제거하려고 합니다. 제거 후에도 파일은 모든 파일에서 볼 수 있으니, 작업을 확인해 주세요.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "뒤로 가기"
},
+ "MaxTokenSlider": {
+ "unlimited": "무제한"
+ },
"ModelSelect": {
"featureTag": {
"custom": "사용자 정의 모델, 기본적으로 함수 호출 및 시각 인식을 모두 지원하며, 실제 기능을 확인하세요",
"file": "이 모델은 파일 업로드 및 인식을 지원합니다",
"functionCall": "이 모델은 함수 호출을 지원합니다",
+ "reasoning": "이 모델은 깊이 있는 사고를 지원합니다.",
+ "search": "이 모델은 온라인 검색을 지원합니다.",
"tokens": "이 모델은 단일 세션당 최대 {{tokens}} 토큰을 지원합니다",
"vision": "이 모델은 시각 인식을 지원합니다"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "활성화된 모델이 없습니다. 설정으로 이동하여 활성화하세요",
+ "emptyProvider": "활성화된 서비스 제공자가 없습니다. 설정으로 가서 활성화하세요.",
+ "goToSettings": "설정으로 가기",
"provider": "제공자"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "브라우저 보안 제한으로 인해 Ollama를 사용하기 위해서는 교차 출처 구성이 필요합니다.",
+ "linux": {
+ "env": "[Service] 섹션에 `Environment`를 추가하고 OLLAMA_ORIGINS 환경 변수를 추가하세요:",
+ "reboot": "systemd를 재로드하고 Ollama를 재시작하세요",
+ "systemd": "systemd를 호출하여 ollama 서비스를 편집하세요:"
+ },
+ "macos": "터미널 애플리케이션을 열고 아래 명령어를 붙여넣은 후 Enter 키를 눌러 실행하세요",
+ "reboot": "작업이 완료된 후 Ollama 서비스를 재시작하세요",
+ "title": "Ollama의 교차 출처 접근 허용 구성",
+ "windows": "Windows에서 '제어판'을 클릭하고 시스템 환경 변수를 편집하세요. 사용자 계정에 'OLLAMA_ORIGINS'라는 이름의 환경 변수를 새로 만들고 값으로 *를 입력한 후 '확인/적용'을 클릭하여 저장하세요."
+ },
+ "install": {
+ "description": "Ollama가 이미 실행 중인지 확인하세요. Ollama를 다운로드하지 않았다면 공식 웹사이트<1>에서 다운로드1>하세요.",
+ "docker": "Docker를 사용하는 것을 선호하는 경우, Ollama는 공식 Docker 이미지를 제공합니다. 아래 명령어로 가져올 수 있습니다:",
+ "linux": {
+ "command": "아래 명령어로 설치하세요:",
+ "manual": "또는 <1>Linux 수동 설치 가이드1>를 참조하여 직접 설치할 수 있습니다."
+ },
+ "title": "로컬에 Ollama 애플리케이션 설치 및 실행",
+ "windowsTab": "Windows (미리보기 버전)"
+ }
+ },
+ "Thinking": {
+ "thinking": "심층적으로 생각 중...",
+ "thought": "심층적으로 생각했습니다 (소요 시간 {{duration}} 초)",
+ "thoughtWithDuration": "심층적으로 생각했습니다"
}
}
diff --git a/DigitalHumanWeb/locales/ko-KR/discover.json b/DigitalHumanWeb/locales/ko-KR/discover.json
index ba698e0..91c64a8 100644
--- a/DigitalHumanWeb/locales/ko-KR/discover.json
+++ b/DigitalHumanWeb/locales/ko-KR/discover.json
@@ -126,6 +126,10 @@
"title": "주제 신선도"
},
"range": "범위",
+ "reasoning_effort": {
+ "desc": "이 설정은 모델이 응답을 생성하기 전에 추론 강도를 제어하는 데 사용됩니다. 낮은 강도는 응답 속도를 우선시하고 토큰을 절약하며, 높은 강도는 더 완전한 추론을 제공하지만 더 많은 토큰을 소모하고 응답 속도를 저하시킵니다. 기본값은 중간으로, 추론 정확성과 응답 속도의 균형을 맞춥니다.",
+ "title": "추론 강도"
+ },
"temperature": {
"desc": "이 설정은 모델 응답의 다양성에 영향을 미칩니다. 낮은 값은 더 예측 가능하고 전형적인 응답을 유도하며, 높은 값은 더 다양하고 드문 응답을 장려합니다. 값이 0으로 설정되면 모델은 주어진 입력에 대해 항상 동일한 응답을 제공합니다.",
"title": "무작위성"
diff --git a/DigitalHumanWeb/locales/ko-KR/error.json b/DigitalHumanWeb/locales/ko-KR/error.json
index dfb815f..8cb3e9a 100644
--- a/DigitalHumanWeb/locales/ko-KR/error.json
+++ b/DigitalHumanWeb/locales/ko-KR/error.json
@@ -12,8 +12,14 @@
"retry": "다시 시도",
"title": "페이지에서 문제가 발생했습니다."
},
- "fetchError": "요청 실패",
- "fetchErrorDetail": "오류 상세",
+ "fetchError": {
+ "detail": "오류 세부정보",
+ "title": "요청 실패"
+ },
+ "loginRequired": {
+ "desc": "곧 로그인 페이지로 자동 이동합니다",
+ "title": "이 기능을 사용하려면 로그인해 주세요"
+ },
"notFound": {
"backHome": "홈페이지로 돌아가기",
"check": "URL이 올바른지 확인해 주세요.",
@@ -51,22 +57,34 @@
"431": "죄송합니다. 요청 헤더 필드가 너무 크기 때문에 서버가 처리할 수 없습니다",
"451": "죄송합니다. 법적 이유로 인해 서버가 이 리소스를 제공하는 것을 거부합니다",
"500": "죄송합니다. 서버에 문제가 발생하여 요청을 완료할 수 없습니다. 잠시 후에 다시 시도해주세요.",
+ "501": "죄송합니다. 서버가 이 요청을 처리하는 방법을 알지 못합니다. 작업이 올바른지 확인해 주세요.",
"502": "죄송합니다. 서버가 잠시 서비스를 제공할 수 없는 상태입니다. 잠시 후에 다시 시도해주세요.",
"503": "죄송합니다. 서버가 현재 요청을 처리할 수 없습니다. 과부하 또는 유지 보수 중일 수 있습니다. 잠시 후에 다시 시도해주세요.",
"504": "죄송합니다. 서버가 상위 서버의 응답을 기다리지 못했습니다. 잠시 후에 다시 시도해주세요.",
+ "505": "죄송합니다. 서버가 사용 중인 HTTP 버전을 지원하지 않습니다. 업데이트 후 다시 시도해 주세요.",
+ "506": "죄송합니다. 서버 구성에 문제가 발생했습니다. 관리자에게 문의하여 해결해 주세요.",
+ "507": "죄송합니다. 서버의 저장 공간이 부족하여 요청을 처리할 수 없습니다. 잠시 후 다시 시도해 주세요.",
+ "509": "죄송합니다. 서버의 대역폭이 소진되었습니다. 잠시 후 다시 시도해 주세요.",
+ "510": "죄송합니다. 서버가 요청된 확장 기능을 지원하지 않습니다. 관리자에게 문의해 주세요.",
+ "524": "죄송합니다. 서버가 응답을 기다리는 동안 시간 초과가 발생했습니다. 응답이 너무 느릴 수 있습니다. 잠시 후 다시 시도해 주세요.",
"AgentRuntimeError": "Lobe 언어 모델 실행 중 오류가 발생했습니다. 아래 정보를 확인하고 다시 시도하십시오.",
+ "ConnectionCheckFailed": "요청이 빈 응답으로 돌아왔습니다. API 프록시 주소의 끝에 `/v1`이 포함되어 있는지 확인하세요.",
+ "ExceededContextWindow": "현재 요청 내용이 모델이 처리할 수 있는 길이를 초과했습니다. 내용량을 줄인 후 다시 시도해 주십시오.",
"FreePlanLimit": "현재 무료 사용자이므로이 기능을 사용할 수 없습니다. 유료 요금제로 업그레이드 한 후 계속 사용하십시오.",
+ "InsufficientQuota": "죄송합니다. 해당 키의 할당량이 초과되었습니다. 계좌 잔액이 충분한지 확인하거나 키 할당량을 늘린 후 다시 시도해 주십시오.",
"InvalidAccessCode": "액세스 코드가 잘못되었거나 비어 있습니다. 올바른 액세스 코드를 입력하거나 사용자 지정 API 키를 추가하십시오.",
"InvalidBedrockCredentials": "Bedrock 인증에 실패했습니다. AccessKeyId/SecretAccessKey를 확인한 후 다시 시도하십시오.",
"InvalidClerkUser": "죄송합니다. 현재 로그인되어 있지 않습니다. 계속하려면 먼저 로그인하거나 계정을 등록해주세요.",
"InvalidGithubToken": "Github 개인 액세스 토큰이 올바르지 않거나 비어 있습니다. Github 개인 액세스 토큰을 확인한 후 다시 시도해 주십시오.",
"InvalidOllamaArgs": "Ollama 구성이 잘못되었습니다. Ollama 구성을 확인한 후 다시 시도하십시오.",
"InvalidProviderAPIKey": "{{provider}} API 키가 잘못되었거나 비어 있습니다. {{provider}} API 키를 확인하고 다시 시도하십시오.",
+ "InvalidVertexCredentials": "Vertex 인증에 실패했습니다. 인증 정보를 확인한 후 다시 시도해 주세요.",
"LocationNotSupportError": "죄송합니다. 귀하의 현재 위치는 해당 모델 서비스를 지원하지 않습니다. 지역 제한 또는 서비스 미개통으로 인한 것일 수 있습니다. 현재 위치가 해당 서비스를 지원하는지 확인하거나 다른 위치 정보를 사용해 보십시오.",
+ "ModelNotFound": "죄송합니다. 요청한 모델을 찾을 수 없습니다. 모델이 존재하지 않거나 접근 권한이 없을 수 있습니다. API 키를 변경하거나 접근 권한을 조정한 후 다시 시도해 주십시오.",
"NoOpenAIAPIKey": "OpenAI API 키가 비어 있습니다. 사용자 정의 OpenAI API 키를 추가해주세요.",
"OllamaBizError": "Ollama 서비스 요청 중 오류가 발생했습니다. 아래 정보를 확인하고 다시 시도하십시오.",
"OllamaServiceUnavailable": "Ollama 서비스를 사용할 수 없습니다. Ollama가 올바르게 작동하는지 또는 Ollama의 교차 도메인 구성이 올바르게 설정되었는지 확인하십시오.",
- "OpenAIBizError": "OpenAI 서비스 요청 중 오류가 발생했습니다. 아래 정보를 확인하고 다시 시도해주세요.",
+ "PermissionDenied": "죄송합니다. 이 서비스에 접근할 권한이 없습니다. 키에 접근 권한이 있는지 확인해 주세요.",
"PluginApiNotFound": "죄송합니다. 플러그인 설명서에 해당 API가 없습니다. 요청 메서드와 플러그인 설명서 API가 일치하는지 확인해주세요.",
"PluginApiParamsError": "죄송합니다. 플러그인 요청의 입력 매개변수 유효성 검사에 실패했습니다. 입력 매개변수와 API 설명 정보가 일치하는지 확인해주세요.",
"PluginFailToTransformArguments": "죄송합니다. 플러그인 호출 인수 변환에 실패했습니다. 도우미 메시지를 다시 생성하거나 더 강력한 AI 모델로 Tools Calling 능력을 변경한 후 다시 시도해주세요.",
@@ -81,8 +99,11 @@
"PluginServerError": "플러그인 서버 요청이 오류로 반환되었습니다. 플러그인 설명 파일, 플러그인 구성 또는 서버 구현을 확인해주세요.",
"PluginSettingsInvalid": "플러그인을 사용하려면 올바른 구성이 필요합니다. 구성이 올바른지 확인해주세요.",
"ProviderBizError": "요청한 {{provider}} 서비스에서 오류가 발생했습니다. 아래 정보를 확인하고 다시 시도해주세요.",
+ "QuotaLimitReached": "죄송합니다. 현재 토큰 사용량 또는 요청 횟수가 해당 키의 할당량 한도에 도달했습니다. 해당 키의 할당량을 늘리거나 나중에 다시 시도해 주십시오.",
"StreamChunkError": "스트리밍 요청의 메시지 블록 구문 분석 오류입니다. 현재 API 인터페이스가 표준 규격에 부합하는지 확인하거나 API 공급자에게 문의하십시오.",
- "SubscriptionPlanLimit": "구독 한도를 모두 사용했으므로이 기능을 사용할 수 없습니다. 더 높은 요금제로 업그레이드하거나 리소스 패키지를 구매하여 계속 사용하십시오.",
+ "SubscriptionKeyMismatch": "죄송합니다. 시스템의 일시적인 오류로 인해 현재 구독 사용량이 일시적으로 비활성화되었습니다. 아래 버튼을 클릭하여 구독을 복구하시거나, 이메일로 저희에게 지원을 요청해 주시기 바랍니다.",
+ "SubscriptionPlanLimit": "귀하의 구독 포인트가 소진되어 이 기능을 사용할 수 없습니다. 더 높은 요금제로 업그레이드하거나 사용자 정의 모델 API를 구성한 후 계속 사용하십시오.",
+ "SystemTimeNotMatchError": "죄송합니다. 귀하의 시스템 시간이 서버와 일치하지 않습니다. 시스템 시간을 확인한 후 다시 시도해 주십시오.",
"UnknownChatFetchError": "죄송합니다. 알 수 없는 요청 오류가 발생했습니다. 아래 정보를 참고하여 문제를 해결하거나 다시 시도해 주세요."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/ko-KR/metadata.json b/DigitalHumanWeb/locales/ko-KR/metadata.json
index 6cd12c3..eb8174e 100644
--- a/DigitalHumanWeb/locales/ko-KR/metadata.json
+++ b/DigitalHumanWeb/locales/ko-KR/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "{{appName}}의 새로운 기능과 개선 사항을 지속적으로 추적합니다.",
+ "title": "변경 로그"
+ },
"chat": {
"description": "{{appName}}가 제공하는 최고의 ChatGPT, Claude, Gemini, OLLaMA WebUI 사용 경험",
"title": "{{appName}}: 개인 AI 효율 도구, 더 똑똑한 두뇌를 위한 선택"
diff --git a/DigitalHumanWeb/locales/ko-KR/modelProvider.json b/DigitalHumanWeb/locales/ko-KR/modelProvider.json
index 39ffd89..420b070 100644
--- a/DigitalHumanWeb/locales/ko-KR/modelProvider.json
+++ b/DigitalHumanWeb/locales/ko-KR/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API 키"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Azure API 버전, YYYY-MM-DD 형식을 따릅니다. [최신 버전](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)을 참조하세요.",
+ "fetch": "목록 가져오기",
+ "title": "Azure API 버전"
+ },
+ "endpoint": {
+ "desc": "Azure AI 프로젝트 개요에서 Azure AI 모델 추론 엔드포인트를 찾습니다.",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AI 엔드포인트"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Azure AI 프로젝트 개요에서 API 키를 찾습니다.",
+ "placeholder": "Azure 키",
+ "title": "키"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "AWS 액세스 키 ID를 입력하세요.",
@@ -51,6 +69,58 @@
"title": "사용자 정의 Bedrock 인증 정보 사용"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Cloudflare API Key 를 작성해 주세요.",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "클라우드 플레어 계정 ID 또는 사용자 지정 API 주소 입력",
+ "placeholder": "클라우드 플레어 계정 ID / 사용자 지정 API 주소",
+ "title": "클라우드 플레어 계정 ID / API 주소"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "API 키를 입력하세요",
+ "title": "API 키"
+ },
+ "basicTitle": "기본 정보",
+ "configTitle": "설정 정보",
+ "confirm": "새로 만들기",
+ "createSuccess": "생성이 성공적으로 완료되었습니다",
+ "description": {
+ "placeholder": "서비스 제공자 소개 (선택 사항)",
+ "title": "서비스 제공자 소개"
+ },
+ "id": {
+ "desc": "서비스 제공자의 고유 식별자로, 생성 후에는 수정할 수 없습니다.",
+ "format": "숫자, 소문자, 하이픈(-), 및 언더스코어(_)만 포함할 수 있습니다.",
+ "placeholder": "소문자로 입력하세요, 예: openai, 생성 후 수정할 수 없습니다",
+ "required": "서비스 제공자 ID를 입력하세요",
+ "title": "서비스 제공자 ID"
+ },
+ "logo": {
+ "required": "올바른 서비스 제공자 로고를 업로드하세요",
+ "title": "서비스 제공자 로고"
+ },
+ "name": {
+ "placeholder": "서비스 제공자의 표시 이름을 입력하세요",
+ "required": "서비스 제공자 이름을 입력하세요",
+ "title": "서비스 제공자 이름"
+ },
+ "proxyUrl": {
+ "required": "프록시 주소를 입력하세요",
+ "title": "프록시 주소"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "SDK 유형을 선택하세요",
+ "title": "요청 형식"
+ },
+ "title": "사용자 정의 AI 서비스 제공자 생성"
+ },
"github": {
"personalAccessToken": {
"desc": "당신의 Github PAT를 입력하세요. [여기](https://github.com/settings/tokens)를 클릭하여 생성하세요.",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "당신의 HuggingFace 토큰을 입력하세요. [여기](https://huggingface.co/settings/tokens)를 클릭하여 생성하세요.",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace 토큰"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "서비스 제공자가 비활성화되었습니다",
+ "enabled": "서비스 제공자가 활성화되었습니다"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "사용자 정의 서비스 제공자 추가",
+ "all": "모두",
+ "list": {
+ "disabled": "비활성화됨",
+ "enabled": "활성화됨"
+ },
+ "notFound": "검색 결과를 찾을 수 없습니다",
+ "searchProviders": "서비스 제공자 검색...",
+ "sort": "사용자 정의 정렬"
+ },
"ollama": {
"checker": {
"desc": "프록시 주소가 올바르게 입력되었는지 테스트합니다",
@@ -69,47 +163,173 @@
"title": "사용자 정의 모델 이름"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. It will resume from where it left off if you restart the download.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama가 모델을 다운로드하고 있습니다. 이 페이지를 닫지 마세요. 다시 다운로드할 경우 중단된 지점에서 계속됩니다.",
+ "remainingTime": "남은 시간",
+ "speed": "다운로드 속도",
+ "title": "모델 {{model}} 다운로드 중"
},
"endpoint": {
- "desc": "Ollama 인터페이스 프록시 주소를 입력하세요. 로컬에서 별도로 지정하지 않은 경우 비워둘 수 있습니다",
+ "desc": "http(s)://를 포함해야 하며, 로컬에서 추가로 지정하지 않은 경우 비워둘 수 있습니다.",
"title": "인터페이스 프록시 주소"
},
- "setup": {
- "cors": {
- "description": "브라우저 보안 제한으로 인해 Ollama를 사용하려면 CORS 구성이 필요합니다.",
- "linux": {
- "env": "[Service] 섹션에 `Environment`를 추가하고 OLLAMA_ORIGINS 환경 변수를 추가하십시오:",
- "reboot": "systemd를 다시로드하고 Ollama를 다시 시작하십시오.",
- "systemd": "systemd를 호출하여 ollama 서비스를 편집하십시오: "
- },
- "macos": "「터미널」앱을 열고 다음 명령을 붙여넣고 Enter를 눌러 실행하십시오.",
- "reboot": "작업을 완료한 후 Ollama 서비스를 다시 시작하십시오.",
- "title": "CORS 액세스를 허용하도록 Ollama 구성",
- "windows": "Windows에서는 '제어판'을 클릭하여 시스템 환경 변수를 편집하십시오. 사용자 계정에 'OLLAMA_ORIGINS'이라는 환경 변수를 만들고 값으로 *을 입력한 후 '확인/적용'을 클릭하여 저장하십시오."
- },
- "install": {
- "description": "Ollama가 활성화되어 있는지 확인하고, Ollama를 다운로드하지 않았다면 공식 웹사이트<1>에서 다운로드1>하십시오.",
- "docker": "Docker를 사용하는 것을 선호하는 경우 Ollama는 공식 Docker 이미지도 제공하며 다음 명령을 사용하여 가져올 수 있습니다:",
- "linux": {
- "command": "다음 명령을 사용하여 설치하십시오:",
- "manual": "또는 <1>Linux 수동 설치 안내1>를 참조하여 직접 설치할 수도 있습니다."
- },
- "title": "로컬에서 Ollama 애플리케이션을 설치하고 시작하십시오",
- "windowsTab": "Windows (미리보기판)"
- }
- },
"title": "Ollama",
"unlock": {
- "cancel": "Cancel Download",
- "confirm": "Download",
- "description": "Enter your Ollama model tag to continue the session",
+ "cancel": "다운로드 취소",
+ "confirm": "다운로드",
+ "description": "Ollama 모델 태그를 입력하여 세션을 계속 진행하세요.",
"downloaded": "{{completed}} / {{total}}",
- "starting": "Starting download...",
- "title": "Download specified Ollama model"
+ "starting": "다운로드 시작 중...",
+ "title": "지정된 Ollama 모델 다운로드"
+ }
+ },
+ "providerModels": {
+ "config": {
+ "aesGcm": "귀하의 비밀 키와 프록시 주소 등은 <1>AES-GCM1> 암호화 알고리즘을 사용하여 암호화됩니다",
+ "apiKey": {
+ "desc": "{{name}} API 키를 입력하세요",
+ "placeholder": "{{name}} API 키",
+ "title": "API 키"
+ },
+ "baseURL": {
+ "desc": "http(s)://를 포함해야 합니다",
+ "invalid": "유효한 URL을 입력하세요",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API 프록시 주소"
+ },
+ "checker": {
+ "button": "검사",
+ "desc": "API 키와 프록시 주소가 올바르게 입력되었는지 테스트합니다",
+ "pass": "검사 통과",
+ "title": "연결성 검사"
+ },
+ "fetchOnClient": {
+ "desc": "클라이언트 요청 모드는 브라우저에서 직접 세션 요청을 시작하여 응답 속도를 높일 수 있습니다",
+ "title": "클라이언트 요청 모드 사용"
+ },
+ "helpDoc": "설정 가이드",
+ "waitingForMore": "더 많은 모델이 <1>계획 중1>입니다. 기대해 주세요"
+ },
+ "createNew": {
+ "title": "사용자 정의 AI 모델 생성"
+ },
+ "item": {
+ "config": "모델 구성",
+ "customModelCards": {
+ "addNew": "{{id}} 모델 생성 및 추가",
+ "confirmDelete": "해당 사용자 정의 모델을 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니 신중하게 진행하세요."
+ },
+ "delete": {
+ "confirm": "모델 {{displayName}}를 삭제하시겠습니까?",
+ "success": "삭제 성공",
+ "title": "모델 삭제"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Azure OpenAI에서 실제 요청되는 필드",
+ "placeholder": "Azure에서 모델 배포 이름을 입력하세요",
+ "title": "모델 배포 이름"
+ },
+ "deployName": {
+ "extra": "요청을 보낼 때 이 필드가 모델 ID로 사용됩니다.",
+ "placeholder": "모델 실제 배포 이름 또는 ID를 입력하세요.",
+ "title": "모델 배포 이름"
+ },
+ "displayName": {
+ "placeholder": "모델의 표시 이름을 입력하세요, 예: ChatGPT, GPT-4 등",
+ "title": "모델 표시 이름"
+ },
+ "files": {
+ "extra": "현재 파일 업로드 구현은 단지 하나의 해킹 방법일 뿐이며, 스스로 시도하는 것만 가능합니다. 완전한 파일 업로드 기능은 후속 구현을 기다려 주세요.",
+ "title": "파일 업로드 지원"
+ },
+ "functionCall": {
+ "extra": "이 설정은 모델이 도구를 사용할 수 있는 기능을 활성화하며, 이를 통해 모델에 도구형 플러그인을 추가할 수 있습니다. 그러나 실제 도구 사용 지원 여부는 모델 자체에 따라 다르므로 사용 가능성을 직접 테스트해 보시기 바랍니다.",
+ "title": "도구 사용 지원"
+ },
+ "id": {
+ "extra": "생성 후 수정할 수 없으며, AI 호출 시 모델 ID로 사용됩니다.",
+ "placeholder": "모델 ID를 입력하세요, 예: gpt-4o 또는 claude-3.5-sonnet",
+ "title": "모델 ID"
+ },
+ "modalTitle": "사용자 정의 모델 구성",
+ "reasoning": {
+ "extra": "이 설정은 모델의 심층 사고 능력만을 활성화합니다. 구체적인 효과는 모델 자체에 따라 다르므로, 해당 모델이 사용 가능한 심층 사고 능력을 갖추고 있는지 직접 테스트해 보시기 바랍니다.",
+ "title": "심층 사고 지원"
+ },
+ "tokens": {
+ "extra": "모델이 지원하는 최대 토큰 수 설정",
+ "title": "최대 컨텍스트 창",
+ "unlimited": "제한 없음"
+ },
+ "vision": {
+ "extra": "이 설정은 애플리케이션 내에서 이미지 업로드 기능만 활성화합니다. 인식 지원 여부는 모델 자체에 따라 다르므로, 해당 모델의 시각 인식 가능성을 스스로 테스트하세요.",
+ "title": "시각 인식 지원"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/이미지",
+ "inputCharts": "${{amount}}/M 문자",
+ "inputMinutes": "${{amount}}/분",
+ "inputTokens": "입력 ${{amount}}/M",
+ "outputTokens": "출력 ${{amount}}/M"
+ },
+ "releasedAt": "발행일 {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "모델 추가",
+ "disabled": "비활성화",
+ "disabledActions": {
+ "showMore": "모두 보기"
+ },
+ "empty": {
+ "desc": "사용할 수 있는 모델이 없습니다. 사용자 정의 모델을 생성하거나 모델을 가져온 후 시작하세요.",
+ "title": "사용 가능한 모델이 없습니다."
+ },
+ "enabled": "활성화",
+ "enabledActions": {
+ "disableAll": "모두 비활성화",
+ "enableAll": "모두 활성화",
+ "sort": "사용자 정의 모델 정렬"
+ },
+ "enabledEmpty": "활성화된 모델이 없습니다. 아래 목록에서 원하는 모델을 활성화하세요~",
+ "fetcher": {
+ "clear": "가져온 모델 지우기",
+ "fetch": "모델 목록 가져오기",
+ "fetching": "모델 목록을 가져오는 중...",
+ "latestTime": "마지막 업데이트 시간: {{time}}",
+ "noLatestTime": "아직 목록을 가져오지 않았습니다."
+ },
+ "resetAll": {
+ "conform": "현재 모델의 모든 수정을 초기화하시겠습니까? 초기화 후 현재 모델 목록은 기본 상태로 돌아갑니다.",
+ "success": "초기화 성공",
+ "title": "모든 수정 초기화"
+ },
+ "search": "모델 검색...",
+ "searchResult": "{{count}} 개의 모델이 검색되었습니다",
+ "title": "모델 목록",
+ "total": "사용 가능한 모델 총 {{count}} 개"
+ },
+ "searchNotFound": "검색 결과를 찾을 수 없습니다"
+ },
+ "sortModal": {
+ "success": "정렬 업데이트 성공",
+ "title": "사용자 정의 정렬",
+ "update": "업데이트"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "해당 AI 서비스 제공자를 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니 확인하시겠습니까?",
+ "deleteSuccess": "삭제 성공",
+ "tooltip": "서비스 제공자 기본 설정 업데이트",
+ "updateSuccess": "업데이트 성공"
+ },
+ "updateCustomAiProvider": {
+ "title": "사용자 정의 AI 서비스 제공자 구성 업데이트"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "당신의 Vertex AI 키를 입력하세요",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI 키"
}
},
"zeroone": {
diff --git a/DigitalHumanWeb/locales/ko-KR/models.json b/DigitalHumanWeb/locales/ko-KR/models.json
index cf0fd1a..3bcd1bf 100644
--- a/DigitalHumanWeb/locales/ko-KR/models.json
+++ b/DigitalHumanWeb/locales/ko-KR/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B는 풍부한 훈련 샘플을 통해 산업 응용에서 우수한 성능을 제공합니다."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat은 Yi-1.5 시리즈의 변형으로, 오픈 소스 채팅 모델에 속합니다. Yi-1.5는 Yi의 업그레이드 버전으로, 500B 개의 고품질 코퍼스에서 지속적으로 사전 훈련되었으며, 3M의 다양한 미세 조정 샘플에서 미세 조정되었습니다. Yi에 비해 Yi-1.5는 코딩, 수학, 추론 및 지침 준수 능력에서 더 강력한 성능을 보이며, 뛰어난 언어 이해, 상식 추론 및 독해 능력을 유지합니다. 이 모델은 4K, 16K 및 32K의 컨텍스트 길이 버전을 제공하며, 총 3.6T 개의 토큰으로 사전 훈련되었습니다."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B는 16K 토큰을 지원하며, 효율적이고 매끄러운 언어 생성 능력을 제공합니다."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "제로일 만물, 최신 오픈 소스 미세 조정 모델로, 340억 개의 매개변수를 가지고 있으며, 다양한 대화 시나리오를 지원하는 미세 조정, 고품질 훈련 데이터, 인간의 선호에 맞춘 조정을 제공합니다."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "제로일 만물, 최신 오픈 소스 미세 조정 모델로, 90억 개의 매개변수를 가지고 있으며, 다양한 대화 시나리오를 지원하는 미세 조정, 고품질 훈련 데이터, 인간의 선호에 맞춘 조정을 제공합니다."
+ },
"360gpt-pro": {
"description": "360GPT Pro는 360 AI 모델 시리즈의 중요한 구성원으로, 다양한 자연어 응용 시나리오에 맞춘 효율적인 텍스트 처리 능력을 갖추고 있으며, 긴 텍스트 이해 및 다중 회화 기능을 지원합니다."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K는 의미 안전성과 책임 지향성을 강조하며, 콘텐츠 안전에 대한 높은 요구가 있는 응용 시나리오를 위해 설계되어 사용자 경험의 정확성과 안정성을 보장합니다."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1은 트리 탐색을 사용하여 사고 체인을 구축하고 반성 메커니즘을 도입하였으며, 강화 학습을 통해 훈련되어 자기 반성과 오류 수정 능력을 갖추고 있습니다."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro는 360 회사에서 출시한 고급 자연어 처리 모델로, 뛰어난 텍스트 생성 및 이해 능력을 갖추고 있으며, 특히 생성 및 창작 분야에서 뛰어난 성능을 발휘하여 복잡한 언어 변환 및 역할 연기 작업을 처리할 수 있습니다."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1은 트리 탐색을 사용하여 사고 체인을 구축하고 반성 메커니즘을 도입하여 강화 학습으로 훈련되며, 모델은 자기 반성과 오류 수정 능력을 갖추고 있습니다."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra는 스타크 대형 모델 시리즈 중 가장 강력한 버전으로, 업그레이드된 네트워크 검색 링크와 함께 텍스트 내용의 이해 및 요약 능력을 향상시킵니다. 사무 생산성을 높이고 정확한 요구에 응답하기 위한 종합 솔루션으로, 업계를 선도하는 스마트 제품입니다."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "모델 능력 국내 1위로, 지식 백과, 긴 텍스트, 생성 창작 등 중국어 작업에서 해외 주류 모델을 초월합니다. 또한 업계 선도적인 다중 모달 능력을 갖추고 있으며, 여러 권위 있는 평가 기준에서 우수한 성과를 보입니다."
},
+ "Baichuan4-Air": {
+ "description": "모델 능력이 국내 1위이며, 지식 백과, 긴 텍스트, 생성 창작 등 중국어 작업에서 해외 주류 모델을 초월합니다. 또한 업계 선도적인 다중 모달 능력을 갖추고 있으며, 여러 권위 있는 평가 기준에서 우수한 성과를 보입니다."
+ },
+ "Baichuan4-Turbo": {
+ "description": "모델 능력이 국내 1위이며, 지식 백과, 긴 텍스트, 생성 창작 등 중국어 작업에서 해외 주류 모델을 초월합니다. 또한 업계 선도적인 다중 모달 능력을 갖추고 있으며, 여러 권위 있는 평가 기준에서 우수한 성과를 보입니다."
+ },
+ "DeepSeek-R1": {
+ "description": "최첨단 효율적인 LLM으로, 추론, 수학 및 프로그래밍에 능숙합니다."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1——DeepSeek 패키지에서 더 크고 더 스마트한 모델——이 Llama 70B 아키텍처로 증류되었습니다. 기준 테스트와 인공지능 평가에 따르면, 이 모델은 원래 Llama 70B보다 더 스마트하며, 특히 수학 및 사실 정확성이 필요한 작업에서 뛰어난 성능을 보입니다."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Qwen2.5-Math-1.5B를 기반으로 한 DeepSeek-R1 증류 모델로, 강화 학습과 콜드 스타트 데이터를 통해 추론 성능을 최적화하며, 오픈 소스 모델로 다중 작업 기준을 갱신합니다."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Qwen2.5-14B를 기반으로 한 DeepSeek-R1 증류 모델로, 강화 학습과 콜드 스타트 데이터를 통해 추론 성능을 최적화하며, 오픈 소스 모델로 다중 작업 기준을 갱신합니다."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1 시리즈는 강화 학습과 콜드 스타트 데이터를 통해 추론 성능을 최적화하며, 오픈 소스 모델로 다중 작업 기준을 갱신하고 OpenAI-o1-mini 수준을 초월합니다."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Qwen2.5-Math-7B를 기반으로 한 DeepSeek-R1 증류 모델로, 강화 학습과 콜드 스타트 데이터를 통해 추론 성능을 최적화하며, 오픈 소스 모델로 다중 작업 기준을 갱신합니다."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro는 새롭게 업그레이드된 다중 모달 대형 모델로, 임의의 해상도와 극단적인 가로 세로 비율의 이미지 인식을 지원하며, 시각적 추론, 문서 인식, 세부 정보 이해 및 지시 준수 능력을 강화했습니다."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite는 극한의 응답 속도와 더 나은 가격 대비 성능을 자랑하며, 고객의 다양한 상황에 유연한 선택을 제공합니다. 128k 컨텍스트 윈도우의 추론 및 세부 조정을 지원합니다."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite는 극한의 응답 속도와 더 나은 가격 대비 성능을 자랑하며, 고객의 다양한 상황에 유연한 선택을 제공합니다. 32k 컨텍스트 윈도우의 추론 및 세부 조정을 지원합니다."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite는 극한의 응답 속도와 더 나은 가격 대비 성능을 자랑하며, 고객의 다양한 상황에 유연한 선택을 제공합니다. 4k 컨텍스트 윈도우의 추론 및 세부 조정을 지원합니다."
+ },
+ "Doubao-pro-128k": {
+ "description": "가장 효과적인 주력 모델로, 복잡한 작업 처리에 적합하며, 참고 질문, 요약, 창작, 텍스트 분류, 역할 수행 등 많은 장면에서 뛰어난 성과를 보입니다. 128k 컨텍스트 윈도우의 추론 및 세부 조정을 지원합니다."
+ },
+ "Doubao-pro-256k": {
+ "description": "가장 효과적인 주력 모델로, 복잡한 작업 처리에 적합하며, 참고 질문 응답, 요약, 창작, 텍스트 분류, 역할 수행 등 다양한 상황에서 좋은 성과를 보입니다. 256k의 컨텍스트 윈도우 추론 및 미세 조정을 지원합니다."
+ },
+ "Doubao-pro-32k": {
+ "description": "가장 효과적인 주력 모델로, 복잡한 작업 처리에 적합하며, 참고 질문, 요약, 창작, 텍스트 분류, 역할 수행 등 많은 장면에서 뛰어난 성과를 보입니다. 32k 컨텍스트 윈도우의 추론 및 세부 조정을 지원합니다."
+ },
+ "Doubao-pro-4k": {
+ "description": "가장 효과적인 주력 모델로, 복잡한 작업 처리에 적합하며, 참고 질문, 요약, 창작, 텍스트 분류, 역할 수행 등 많은 장면에서 뛰어난 성과를 보입니다. 4k 컨텍스트 윈도우의 추론 및 세부 조정을 지원합니다."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Doubao-vision 모델은 Doubao에서 출시한 다중 모달 대형 모델로, 강력한 이미지 이해 및 추론 능력과 정확한 지시 이해 능력을 갖추고 있습니다. 이 모델은 이미지 텍스트 정보 추출 및 이미지 기반 추론 작업에서 강력한 성능을 보여주며, 더 복잡하고 넓은 시각적 질문 응답 작업에 적용될 수 있습니다."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Doubao-vision 모델은 Doubao에서 출시한 다중 모달 대형 모델로, 강력한 이미지 이해 및 추론 능력과 정확한 지시 이해 능력을 갖추고 있습니다. 이 모델은 이미지 텍스트 정보 추출 및 이미지 기반 추론 작업에서 강력한 성능을 보여주며, 더 복잡하고 넓은 시각적 질문 응답 작업에 적용될 수 있습니다."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "바이두가 자체 개발한 플래그십 대규모 언어 모델로, 방대한 중문 및 영문 코퍼스를 포함하고 있으며, 강력한 일반 능력을 갖추고 있어 대부분의 대화형 질문 응답, 창작 생성, 플러그인 응용 시나리오 요구를 충족할 수 있습니다. 또한 바이두 검색 플러그인과의 자동 연동을 지원하여 질문 응답 정보의 시의성을 보장합니다."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "바이두가 자체 개발한 플래그십 대규모 언어 모델로, 방대한 중문 및 영문 코퍼스를 포함하고 있으며, 강력한 일반 능력을 갖추고 있어 대부분의 대화형 질문 응답, 창작 생성, 플러그인 응용 시나리오 요구를 충족할 수 있습니다. 또한 바이두 검색 플러그인과의 자동 연동을 지원하여 질문 응답 정보의 시의성을 보장합니다."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "바이두가 자체 개발한 플래그십 대규모 언어 모델로, 방대한 중문 및 영문 코퍼스를 포함하고 있으며, 강력한 일반 능력을 갖추고 있어 대부분의 대화형 질문 응답, 창작 생성, 플러그인 응용 시나리오 요구를 충족할 수 있습니다. 또한 바이두 검색 플러그인과의 자동 연동을 지원하여 질문 응답 정보의 시의성을 보장합니다."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, ERNIE 3.5에 비해 모델 능력이 전면적으로 업그레이드되었으며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 자동으로 바이두 검색 플러그인과 연결되어 질문 응답 정보의 시의성을 보장합니다."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, ERNIE 3.5에 비해 모델 능력이 전면적으로 업그레이드되었으며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 자동으로 바이두 검색 플러그인과 연결되어 질문 응답 정보의 시의성을 보장합니다."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "바이두가 개발한 플래그십 대규모 언어 모델로, 다양한 분야의 복잡한 작업 환경에서 뛰어난 종합 효과를 보여줍니다. 바이두 검색 플러그인 자동 연결을 지원하여 질문과 답변 정보의 시의성을 보장합니다. ERNIE 4.0에 비해 성능이 더욱 우수합니다."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, 종합적인 성능이 뛰어나며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 자동으로 바이두 검색 플러그인과 연결되어 질문 응답 정보의 시의성을 보장합니다. ERNIE 4.0에 비해 성능이 더욱 우수합니다."
+ },
+ "ERNIE-Character-8K": {
+ "description": "바이두가 자체 개발한 수직 장면 대언어 모델로, 게임 NPC, 고객 서비스 대화, 대화 역할 수행 등 다양한 응용 시나리오에 적합하며, 캐릭터 스타일이 더욱 뚜렷하고 일관되며, 지시 준수 능력이 더 강하고, 추론 성능이 우수합니다."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "바이두가 자체 개발한 경량 대언어 모델로, 우수한 모델 효과와 추론 성능을 겸비하고 있으며, ERNIE Lite보다 더 나은 성능을 보여 저전력 AI 가속 카드에서의 추론 사용에 적합합니다."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "바이두가 2024년에 최신 발표한 자체 개발 고성능 대언어 모델로, 일반 능력이 뛰어나며, 특정 시나리오 문제를 더 잘 처리하기 위해 기본 모델로 조정하는 데 적합하며, 뛰어난 추론 성능을 갖추고 있습니다."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "바이두가 2024년에 최신 발표한 자체 개발 고성능 대언어 모델로, 일반 능력이 뛰어나며, ERNIE Speed보다 더 나은 성능을 보여 특정 시나리오 문제를 더 잘 처리하기 위해 기본 모델로 조정하는 데 적합하며, 뛰어난 추론 성능을 갖추고 있습니다."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B)는 혁신적인 모델로, 다양한 분야의 응용과 복잡한 작업에 적합합니다."
},
- "Max-32k": {
- "description": "Spark Max 32K는 대규모 컨텍스트 처리 능력을 갖추고 있으며, 더 강력한 컨텍스트 이해 및 논리 추론 능력을 제공합니다. 32K 토큰의 텍스트 입력을 지원하며, 긴 문서 읽기, 개인 지식 질문 응답 등 다양한 상황에 적합합니다."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B는 강력한 비주얼 언어 모델로, 이미지와 텍스트의 다중 모달 처리를 지원하며, 이미지 내용을 정확하게 인식하고 관련 설명이나 답변을 생성할 수 있습니다."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B는 강력한 비주얼 언어 모델로, 이미지와 텍스트의 다중 모달 처리를 지원하며, 이미지 내용을 정확하게 인식하고 관련 설명이나 답변을 생성할 수 있습니다."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "고해상도 이미지에서 뛰어난 이미지 추론 능력을 보여주며, 시각적 이해 응용 프로그램에 적합합니다."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "시각적 이해 에이전트 응용 프로그램에 적합한 고급 이미지 추론 능력입니다."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct는 Alibaba Cloud에서 발표한 최신 대규모 언어 모델 시리즈 중 하나입니다. 이 72B 모델은 코딩 및 수학 분야에서 상당한 개선된 능력을 가지고 있습니다. 이 모델은 또한 29개 이상의 언어를 포함한 다국어 지원을 제공합니다. 모델은 지침 준수, 구조화된 데이터 이해 및 구조화된 출력 생성(특히 JSON)에서 상당한 향상을 보입니다."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct는 Alibaba Cloud에서 발표한 최신 대규모 언어 모델 시리즈 중 하나입니다. 이 7B 모델은 코딩 및 수학 분야에서 상당한 개선된 능력을 가지고 있습니다. 이 모델은 또한 29개 이상의 언어를 포함한 다국어 지원을 제공합니다. 모델은 지침 준수, 구조화된 데이터 이해 및 구조화된 출력 생성(특히 JSON)에서 상당한 향상을 보입니다."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Llama 3.1 지시 조정 텍스트 모델로, 다국어 대화 사용 사례에 최적화되어 있으며, 많은 오픈 소스 및 폐쇄형 채팅 모델 중에서 일반 산업 기준에서 우수한 성능을 보입니다."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO는 뛰어난 창의적 경험을 제공하기 위해 설계된 고도로 유연한 다중 모델 통합입니다."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Llama 3.1 지시 조정 텍스트 모델로, 다국어 대화 사용 사례에 최적화되어 있으며, 많은 오픈 소스 및 폐쇄형 채팅 모델 중에서 일반 산업 기준에서 우수한 성능을 보입니다."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Llama 3.1 지시 조정 텍스트 모델로, 다국어 대화 사용 사례에 최적화되어 있으며, 많은 오픈 소스 및 폐쇄형 채팅 모델 중에서 일반 산업 기준에서 우수한 성능을 보입니다."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "언어 이해, 뛰어난 추론 능력 및 텍스트 생성 능력을 갖춘 최첨단 소형 언어 모델입니다."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "언어 이해, 뛰어난 추론 능력 및 텍스트 생성 능력을 갖춘 최첨단 소형 언어 모델입니다."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3은 Llama 시리즈에서 가장 진보된 다국어 오픈 소스 대형 언어 모델로, 매우 낮은 비용으로 405B 모델의 성능을 경험할 수 있습니다. Transformer 구조를 기반으로 하며, 감독 미세 조정(SFT)과 인간 피드백 강화 학습(RLHF)을 통해 유용성과 안전성을 향상시켰습니다. 그 지시 조정 버전은 다국어 대화를 위해 최적화되어 있으며, 여러 산업 기준에서 많은 오픈 소스 및 폐쇄형 채팅 모델보다 우수한 성능을 보입니다. 지식 마감일은 2023년 12월입니다."
+ },
+ "MiniMax-Text-01": {
+ "description": "MiniMax-01 시리즈 모델에서는 대담한 혁신을 이루었습니다: 대규모로 선형 주의 메커니즘을 처음으로 구현하였으며, 전통적인 Transformer 아키텍처가 더 이상 유일한 선택이 아닙니다. 이 모델의 파라미터 수는 4560억에 달하며, 단일 활성화는 45.9억입니다. 모델의 종합 성능은 해외 최고의 모델과 견줄 수 있으며, 전 세계에서 가장 긴 400만 토큰의 문맥을 효율적으로 처리할 수 있습니다. 이는 GPT-4o의 32배, Claude-3.5-Sonnet의 20배에 해당합니다."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B)는 고정밀 지시 모델로, 복잡한 계산에 적합합니다."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B)는 최적화된 언어 출력과 다양한 응용 가능성을 제공합니다."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Phi-3-mini 모델의 새로 고침 버전입니다."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2는 문서 및 차트 이해, 장면 텍스트 이해, OCR, 과학 및 수학 문제 해결을 포함한 다양한 시각 언어 작업에서 뛰어난 성능을 보여줍니다."
},
"Phi-3-medium-128k-instruct": {
"description": "같은 Phi-3-medium 모델이지만 RAG 또는 몇 가지 샷 프롬프트를 위한 더 큰 컨텍스트 크기를 가지고 있습니다."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "7B 매개변수 모델로, Phi-3-mini보다 더 나은 품질을 제공하며, 고품질의 추론 밀집 데이터에 중점을 두고 있습니다."
},
- "Pro-128k": {
- "description": "Spark Pro-128K는 초대형 컨텍스트 처리 능력을 갖추고 있으며, 최대 128K의 컨텍스트 정보를 처리할 수 있어, 특히 전체 분석 및 장기 논리 연관 처리가 필요한 긴 문서 콘텐츠에 적합합니다. 복잡한 텍스트 커뮤니케이션에서 매끄럽고 일관된 논리와 다양한 인용 지원을 제공합니다."
+ "Phi-3.5-mini-instruct": {
+ "description": "Phi-3-mini 모델의 업데이트된 버전입니다."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Phi-3-vision 모델의 업데이트된 버전입니다."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2는 문서 및 차트 이해, 장면 텍스트 이해, OCR, 과학 및 수학 문제 해결을 포함한 다양한 시각 언어 작업에서 뛰어난 성능을 보여줍니다."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct는 Qwen2 시리즈의 지침 미세 조정 대규모 언어 모델로, 파라미터 규모는 1.5B입니다. 이 모델은 Transformer 아키텍처를 기반으로 하며, SwiGLU 활성화 함수, 주의 QKV 편향 및 그룹 쿼리 주의와 같은 기술을 사용합니다. 이 모델은 언어 이해, 생성, 다국어 능력, 코딩, 수학 및 추론 등 여러 벤치마크 테스트에서 뛰어난 성능을 보이며, 대부분의 오픈 소스 모델을 초월합니다. Qwen1.5-1.8B-Chat과 비교할 때, Qwen2-1.5B-Instruct는 MMLU, HumanEval, GSM8K, C-Eval 및 IFEval 등의 테스트에서 상당한 성능 향상을 보였습니다."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct는 Qwen2 시리즈의 지침 미세 조정 대규모 언어 모델로, 파라미터 규모는 7B입니다. 이 모델은 Transformer 아키텍처를 기반으로 하며, SwiGLU 활성화 함수, 주의 QKV 편향 및 그룹 쿼리 주의와 같은 기술을 사용합니다. 이 모델은 대규모 입력을 처리할 수 있습니다. 이 모델은 언어 이해, 생성, 다국어 능력, 코딩, 수학 및 추론 등 여러 벤치마크 테스트에서 뛰어난 성능을 보이며, 대부분의 오픈 소스 모델을 초월하고 특정 작업에서 독점 모델과 동등한 경쟁력을 보여줍니다. Qwen2-7B-Instruct는 여러 평가에서 Qwen1.5-7B-Chat보다 우수하여 상당한 성능 향상을 보였습니다."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL은 Qwen-VL 모델의 최신 반복 버전으로, 시각 이해 기준 테스트에서 최첨단 성능을 달성했습니다."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct는 Alibaba Cloud에서 발표한 최신 대규모 언어 모델 시리즈 중 하나입니다. 이 7B 모델은 코딩 및 수학 분야에서 상당한 개선된 능력을 가지고 있습니다. 이 모델은 또한 29개 이상의 언어를 포함한 다국어 지원을 제공합니다. 모델은 지침 준수, 구조화된 데이터 이해 및 구조화된 출력 생성(특히 JSON)에서 상당한 향상을 보입니다."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct는 Alibaba Cloud에서 발표한 코드 특화 대규모 언어 모델 시리즈의 최신 버전입니다. 이 모델은 Qwen2.5를 기반으로 하여 55조 개의 토큰으로 훈련되어 코드 생성, 추론 및 수정 능력을 크게 향상시켰습니다. 이 모델은 코딩 능력을 강화할 뿐만 아니라 수학 및 일반 능력의 장점도 유지합니다. 모델은 코드 에이전트와 같은 실제 응용 프로그램에 더 포괄적인 기반을 제공합니다."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat은 Zhizhu AI가 출시한 GLM-4 시리즈의 사전 훈련 모델 중 오픈 소스 버전입니다. 이 모델은 의미, 수학, 추론, 코드 및 지식 등 여러 측면에서 뛰어난 성능을 보입니다. GLM-4-9B-Chat은 다중 회전 대화를 지원할 뿐만 아니라 웹 브라우징, 코드 실행, 사용자 정의 도구 호출(Function Call) 및 긴 텍스트 추론과 같은 고급 기능도 갖추고 있습니다. 이 모델은 중국어, 영어, 일본어, 한국어 및 독일어를 포함한 26개 언어를 지원합니다. 여러 벤치마크 테스트에서 GLM-4-9B-Chat은 AlignBench-v2, MT-Bench, MMLU 및 C-Eval 등에서 뛰어난 성능을 보였습니다. 이 모델은 최대 128K의 컨텍스트 길이를 지원하며, 학술 연구 및 상업적 응용에 적합합니다."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1은 강화 학습(RL) 기반의 추론 모델로, 모델 내의 반복성과 가독성 문제를 해결합니다. RL 이전에 DeepSeek-R1은 콜드 스타트 데이터를 도입하여 추론 성능을 더욱 최적화했습니다. 수학, 코드 및 추론 작업에서 OpenAI-o1과 유사한 성능을 보이며, 정교하게 설계된 훈련 방법을 통해 전체적인 효과를 향상시켰습니다."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3는 6710억 개의 매개변수를 가진 혼합 전문가(MoE) 언어 모델로, 다중 헤드 잠재 주의(MLA) 및 DeepSeekMoE 아키텍처를 사용하여 보조 손실 없는 부하 균형 전략을 결합하여 추론 및 훈련 효율성을 최적화합니다. 14.8조 개의 고품질 토큰에서 사전 훈련을 수행하고 감독 미세 조정 및 강화 학습을 통해 DeepSeek-V3는 성능 면에서 다른 오픈 소스 모델을 초월하며, 선도적인 폐쇄형 모델에 근접합니다."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma는 Google이 개발한 경량화된 최첨단 오픈 모델 시리즈 중 하나입니다. 이는 단일 디코더 대규모 언어 모델로, 영어를 지원하며 오픈 가중치, 사전 훈련 변형 및 지침 미세 조정 변형을 제공합니다. Gemma 모델은 질문 응답, 요약 및 추론을 포함한 다양한 텍스트 생성 작업에 적합합니다. 이 9B 모델은 80조 개의 토큰으로 훈련되었습니다. 상대적으로 작은 규모로 인해 노트북, 데스크탑 또는 개인 클라우드 인프라와 같은 자원이 제한된 환경에서 배포할 수 있어 더 많은 사람들이 최첨단 AI 모델에 접근하고 혁신을 촉진할 수 있습니다."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1은 Meta가 개발한 다국어 대규모 언어 모델 가족으로, 8B, 70B 및 405B의 세 가지 파라미터 규모의 사전 훈련 및 지침 미세 조정 변형을 포함합니다. 이 8B 지침 미세 조정 모델은 다국어 대화 시나리오에 최적화되어 있으며, 여러 산업 벤치마크 테스트에서 우수한 성능을 보입니다. 모델 훈련에는 15조 개 이상의 공개 데이터 토큰이 사용되었으며, 감독 미세 조정 및 인간 피드백 강화 학습과 같은 기술을 통해 모델의 유용성과 안전성을 향상시켰습니다. Llama 3.1은 텍스트 생성 및 코드 생성을 지원하며, 지식 마감일은 2023년 12월입니다."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview는 복잡한 대화 생성 및 맥락 이해 작업을 효율적으로 처리할 수 있는 혁신적인 자연어 처리 모델입니다."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview는 Qwen 팀이 개발한 시각적 추론 능력에 중점을 둔 연구 모델로, 복잡한 장면 이해 및 시각 관련 수학 문제 해결에서 독특한 장점을 가지고 있습니다."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Qwen2의 테스트 버전인 Qwen1.5는 대규모 데이터를 사용하여 더 정밀한 대화 기능을 구현하였습니다."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ는 Qwen 시리즈의 추론 모델입니다. 전통적인 지시 조정 모델과 비교할 때, QwQ는 사고 및 추론 능력을 갖추고 있어 하위 작업에서 특히 어려운 문제를 해결하는 데 있어 성능이 크게 향상됩니다. QwQ-32B는 중형 추론 모델로, 최신 추론 모델(예: DeepSeek-R1, o1-mini)과 비교할 때 경쟁력 있는 성능을 발휘합니다. 이 모델은 RoPE, SwiGLU, RMSNorm 및 Attention QKV bias와 같은 기술을 사용하며, 64층 네트워크 구조와 40개의 Q 주의 헤드(GQA 구조에서 KV는 8개)를 가지고 있습니다."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B)는 빠른 응답과 자연스러운 대화 능력을 제공하며, 다국어 환경에 적합합니다."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview는 Qwen의 최신 실험적 연구 모델로, AI 추론 능력을 향상시키는 데 중점을 두고 있습니다. 언어 혼합, 재귀 추론 등 복잡한 메커니즘을 탐구하며, 주요 장점으로는 강력한 추론 분석 능력, 수학 및 프로그래밍 능력이 포함됩니다. 동시에 언어 전환 문제, 추론 루프, 안전성 고려 및 기타 능력 차이와 같은 문제도 존재합니다."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct는 Qwen2 시리즈의 지침 미세 조정 대규모 언어 모델로, 파라미터 규모는 1.5B입니다. 이 모델은 Transformer 아키텍처를 기반으로 하며, SwiGLU 활성화 함수, 주의 QKV 편향 및 그룹 쿼리 주의와 같은 기술을 사용합니다. 이 모델은 언어 이해, 생성, 다국어 능력, 코딩, 수학 및 추론 등 여러 벤치마크 테스트에서 뛰어난 성능을 보이며, 대부분의 오픈 소스 모델을 초월합니다. Qwen1.5-1.8B-Chat과 비교할 때, Qwen2-1.5B-Instruct는 MMLU, HumanEval, GSM8K, C-Eval 및 IFEval 등의 테스트에서 상당한 성능 향상을 보였습니다."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2는 다양한 지시 유형을 지원하는 고급 범용 언어 모델입니다."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct는 Qwen2 시리즈의 지침 미세 조정 대규모 언어 모델로, 파라미터 규모는 72B입니다. 이 모델은 Transformer 아키텍처를 기반으로 하며, SwiGLU 활성화 함수, 주의 QKV 편향 및 그룹 쿼리 주의와 같은 기술을 사용합니다. 이 모델은 대규모 입력을 처리할 수 있습니다. 이 모델은 언어 이해, 생성, 다국어 능력, 코딩, 수학 및 추론 등 여러 벤치마크 테스트에서 뛰어난 성능을 보이며, 대부분의 오픈 소스 모델을 초월하고 특정 작업에서 독점 모델과 동등한 경쟁력을 보여줍니다."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL은 Qwen-VL 모델의 최신 반복 버전으로, 시각 이해 기준 테스트에서 최첨단 성능을 달성했습니다."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5는 지시형 작업 처리를 최적화하기 위해 설계된 새로운 대형 언어 모델 시리즈입니다."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5는 지시형 작업 처리를 최적화하기 위해 설계된 새로운 대형 언어 모델 시리즈입니다."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5는 더 강력한 이해 및 생성 능력을 가진 새로운 대형 언어 모델 시리즈입니다."
+ "description": "알리바바 클라우드 통의 천문 팀이 개발한 대형 언어 모델"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5는 더 강력한 이해 및 생성 능력을 갖춘 새로운 대형 언어 모델 시리즈입니다."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5는 명령형 작업 처리를 최적화하기 위해 설계된 새로운 대형 언어 모델 시리즈입니다."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5는 지시형 작업 처리를 최적화하기 위해 설계된 새로운 대형 언어 모델 시리즈입니다."
},
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5는 명령형 작업 처리를 최적화하기 위해 설계된 새로운 대형 언어 모델 시리즈입니다."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder는 코드 작성에 중점을 둡니다."
+ },
"Qwen/Qwen2.5-Coder-7B-Instruct": {
- "description": "Qwen2.5-Coder는 코드 작성을 전문으로 합니다."
+ "description": "Qwen2.5-Coder-7B-Instruct는 Alibaba Cloud에서 발표한 코드 특화 대규모 언어 모델 시리즈의 최신 버전입니다. 이 모델은 Qwen2.5를 기반으로 하여 55조 개의 토큰으로 훈련되어 코드 생성, 추론 및 수정 능력을 크게 향상시켰습니다. 이 모델은 코딩 능력을 강화할 뿐만 아니라 수학 및 일반 능력의 장점도 유지합니다. 모델은 코드 에이전트와 같은 실제 응용 프로그램에 더 포괄적인 기반을 제공합니다."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2는 Qwen 모델의 최신 시리즈로, 128k 컨텍스트를 지원합니다. 현재 최상의 오픈 소스 모델과 비교할 때, Qwen2-72B는 자연어 이해, 지식, 코드, 수학 및 다국어 등 여러 능력에서 현재 선도하는 모델을 현저히 초월합니다."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2는 Qwen 모델의 최신 시리즈로, 동등한 규모의 최적 오픈 소스 모델은 물론 더 큰 규모의 모델을 초월할 수 있습니다. Qwen2 7B는 여러 평가에서 현저한 우위를 차지하였으며, 특히 코드 및 중국어 이해에서 두드러진 성과를 보였습니다."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B는 강력한 시각 언어 모델로, 이미지와 텍스트의 다중 모드 처리를 지원하며, 이미지 내용을 정확하게 인식하고 관련 설명이나 답변을 생성할 수 있습니다."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct는 140억 매개변수를 가진 대형 언어 모델로, 성능이 우수하며 중국어 및 다국어 시나리오를 최적화하여 스마트 Q&A, 콘텐츠 생성 등의 응용을 지원합니다."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct는 320억 매개변수를 가진 대형 언어 모델로, 성능이 균형 잡혀 있으며 중국어 및 다국어 시나리오를 최적화하여 스마트 Q&A, 콘텐츠 생성 등의 응용을 지원합니다."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct는 16k 컨텍스트를 지원하며, 8K를 초과하는 긴 텍스트를 생성할 수 있습니다. 함수 호출 및 외부 시스템과의 원활한 상호작용을 지원하여 유연성과 확장성을 크게 향상시킵니다. 모델의 지식이 현저히 증가하였고, 인코딩 및 수학 능력이 크게 향상되었으며, 29개 이상의 언어를 지원합니다."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct는 70억 매개변수를 가진 대형 언어 모델로, 함수 호출 및 외부 시스템과의 원활한 상호작용을 지원하여 유연성과 확장성을 크게 향상시킵니다. 중국어 및 다국어 시나리오를 최적화하여 스마트 Q&A, 콘텐츠 생성 등의 응용을 지원합니다."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct는 대규모 사전 훈련된 프로그래밍 지침 모델로, 강력한 코드 이해 및 생성 능력을 갖추고 있으며, 다양한 프로그래밍 작업을 효율적으로 처리할 수 있습니다. 특히 스마트 코드 작성, 자동화 스크립트 생성 및 프로그래밍 문제 해결에 적합합니다."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct는 코드 생성, 코드 이해 및 효율적인 개발 시나리오를 위해 설계된 대형 언어 모델로, 업계 최고의 32B 매개변수 규모를 채택하여 다양한 프로그래밍 요구를 충족합니다."
+ },
+ "SenseChat": {
+ "description": "기본 버전 모델(V4), 4K 컨텍스트 길이, 일반적인 능력이 강력합니다."
+ },
+ "SenseChat-128K": {
+ "description": "기본 버전 모델(V4), 128K 컨텍스트 길이, 긴 텍스트 이해 및 생성 작업에서 뛰어난 성능을 발휘합니다."
+ },
+ "SenseChat-32K": {
+ "description": "기본 버전 모델(V4), 32K 컨텍스트 길이, 다양한 시나리오에 유연하게 적용됩니다."
+ },
+ "SenseChat-5": {
+ "description": "최신 버전 모델(V5.5), 128K 컨텍스트 길이, 수학적 추론, 영어 대화, 지시 따르기 및 긴 텍스트 이해 등 분야에서 능력이 크게 향상되어 GPT-4o와 견줄 수 있습니다."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math는 수학 분야의 문제 해결에 중점을 두고 있으며, 고난이도 문제에 대한 전문적인 해답을 제공합니다."
+ "SenseChat-5-1202": {
+ "description": "V5.5를 기반으로 한 최신 버전으로, 이전 버전보다 중영 기본 능력, 채팅, 이과 지식, 인문 지식, 작문, 수리 논리, 글자 수 조절 등 여러 측면에서 성능이 크게 향상되었습니다."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "32K 컨텍스트 길이, 광둥어 대화 이해에서 GPT-4를 초월하며, 지식, 추론, 수학 및 코드 작성 등 여러 분야에서 GPT-4 Turbo와 견줄 수 있습니다."
+ },
+ "SenseChat-Character": {
+ "description": "표준 버전 모델, 8K 컨텍스트 길이, 높은 응답 속도를 자랑합니다."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "고급 버전 모델, 32K 컨텍스트 길이, 능력이 전반적으로 향상되었으며, 중/영어 대화를 지원합니다."
+ },
+ "SenseChat-Turbo": {
+ "description": "빠른 질문 응답 및 모델 미세 조정 시나리오에 적합합니다."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "최신 경량 버전 모델로, 전체 모델의 90% 이상의 능력을 달성하며, 추론 비용을 크게 줄였습니다."
+ },
+ "SenseChat-Vision": {
+ "description": "최신 버전 모델(V5.5)로, 다중 이미지 입력을 지원하며, 모델의 기본 능력 최적화를 전면적으로 구현하여 객체 속성 인식, 공간 관계, 동작 사건 인식, 장면 이해, 감정 인식, 논리 상식 추론 및 텍스트 이해 생성에서 큰 향상을 이루었습니다."
+ },
+ "Skylark2-lite-8k": {
+ "description": "구름제비(Skylark) 2세대 모델로, Skylark2-lite 모델은 높은 응답 속도를 자랑하며, 실시간 요구가 높은, 비용에 민감하고, 모델 정확도에 대한 요구가 낮은 장면에 적합하며, 컨텍스트 윈도우 길이는 8k입니다."
+ },
+ "Skylark2-pro-32k": {
+ "description": "구름제비(Skylark) 2세대 모델로, Skylark2-pro 버전은 높은 모델 정확도를 자랑하며, 전문 분야 문서 생성, 소설 창작, 고품질 번역 등 복잡한 텍스트 생성 장면에 적합하며, 컨텍스트 윈도우 길이는 32k입니다."
+ },
+ "Skylark2-pro-4k": {
+ "description": "구름제비(Skylark) 2세대 모델로, Skylark2-pro 모델은 높은 모델 정확도를 자랑하며, 전문 분야 문서 생성, 소설 창작, 고품질 번역 등 복잡한 텍스트 생성 장면에 적합하며, 컨텍스트 윈도우 길이는 4k입니다."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "구름제비(Skylark) 2세대 모델로, Skylark2-pro-character 모델은 우수한 역할 수행 및 채팅 능력을 갖추고 있으며, 사용자 프롬프트 요구에 따라 다양한 역할을 수행하고 자연스러운 대화를 이어갈 수 있습니다. 채팅봇, 가상 비서 및 온라인 고객 서비스 등을 구축하는 데 적합하며 높은 응답 속도를 자랑합니다."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "구름제비(Skylark) 2세대 모델로, Skylark2-pro-turbo-8k는 더 빠른 추론과 낮은 비용을 자랑하며, 컨텍스트 윈도우 길이는 8k입니다."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B는 Zhizhu AI가 개발한 ChatGLM 시리즈의 오픈 소스 모델입니다. 이 모델은 이전 모델의 우수한 특성을 유지하면서 대화의 유창함과 배포 장벽을 낮추는 새로운 기능을 도입했습니다. 더 다양한 훈련 데이터, 충분한 훈련 단계 및 합리적인 훈련 전략을 채택하여 10B 이하의 사전 훈련 모델 중에서 뛰어난 성능을 보입니다. ChatGLM3-6B는 다중 회전 대화, 도구 호출, 코드 실행 및 에이전트 작업과 같은 복잡한 시나리오를 지원합니다. 대화 모델 외에도 기본 모델 ChatGLM-6B-Base 및 긴 텍스트 대화 모델 ChatGLM3-6B-32K도 오픈 소스되었습니다. 이 모델은 학술 연구에 완전히 개방되어 있으며, 등록 후 무료 상업적 사용도 허용됩니다."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B 오픈 소스 버전으로, 대화 응용을 위한 최적화된 대화 경험을 제공합니다."
},
+ "TeleAI/TeleChat2": {
+ "description": "TeleChat2 대모델은 중국 전신이 0에서 1까지 독자적으로 개발한 생성적 의미 대모델로, 백과사전 질문 응답, 코드 생성, 긴 문서 생성 등의 기능을 지원하여 사용자에게 대화 상담 서비스를 제공합니다. 사용자가 질문에 답하고 창작을 도와주며, 효율적이고 편리하게 정보, 지식 및 영감을 얻을 수 있도록 돕습니다. 이 모델은 환각 문제, 긴 문서 생성, 논리 이해 등에서 뛰어난 성능을 보입니다."
+ },
+ "TeleAI/TeleMM": {
+ "description": "TeleMM 다중 모달 대모델은 중국 전신이 독자적으로 개발한 다중 모달 이해 대모델로, 텍스트, 이미지 등 다양한 모달 입력을 처리할 수 있으며, 이미지 이해, 차트 분석 등의 기능을 지원하여 사용자에게 교차 모달 이해 서비스를 제공합니다. 이 모델은 사용자와 다중 모달 상호작용을 통해 입력 내용을 정확하게 이해하고 질문에 답하며 창작을 도와주고, 효율적으로 다중 모달 정보와 영감을 제공합니다. 세밀한 인식, 논리 추론 등 다중 모달 작업에서 뛰어난 성능을 보입니다."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct는 Alibaba Cloud에서 발표한 최신 대규모 언어 모델 시리즈 중 하나입니다. 이 72B 모델은 코딩 및 수학 분야에서 상당한 개선된 능력을 가지고 있습니다. 이 모델은 또한 29개 이상의 언어를 포함한 다국어 지원을 제공합니다. 모델은 지침 준수, 구조화된 데이터 이해 및 구조화된 출력 생성(특히 JSON)에서 상당한 향상을 보입니다."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B는 원래 시리즈 모델의 뛰어난 일반 언어 능력을 유지하면서, 5000억 개의 고품질 토큰을 통해 점진적으로 훈련하여 수학적 논리 및 코드 능력을 크게 향상시켰습니다."
+ },
"abab5.5-chat": {
"description": "생산성 시나리오를 위해 설계되었으며, 복잡한 작업 처리 및 효율적인 텍스트 생성을 지원하여 전문 분야 응용에 적합합니다."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "중국어 캐릭터 대화 시나리오에 최적화되어 있으며, 유창하고 중국어 표현 습관에 맞는 대화 생성 능력을 제공합니다."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworks 오픈 소스 함수 호출 모델로, 뛰어난 지시 실행 능력과 개방형 커스터마이징 기능을 제공합니다."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Fireworks 회사의 최신 Firefunction-v2는 Llama-3를 기반으로 개발된 뛰어난 함수 호출 모델로, 많은 최적화를 통해 함수 호출, 대화 및 지시 따르기 등의 시나리오에 특히 적합합니다."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b는 이미지와 텍스트 입력을 동시에 수용할 수 있는 비주얼 언어 모델로, 고품질 데이터로 훈련되어 다중 모달 작업에 적합합니다."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1은 최첨단 대형 언어 모델로, 강화 학습과 콜드 스타트 데이터를 최적화하여 뛰어난 추론, 수학 및 프로그래밍 성능을 제공합니다."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B 지시 모델은 이전 Google 기술을 기반으로 하여 질문 응답, 요약 및 추론 등 다양한 텍스트 생성 작업에 적합합니다."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Deepseek에서 제공하는 강력한 Mixture-of-Experts (MoE) 언어 모델로, 총 매개변수 수는 671B이며, 각 토큰은 37B 매개변수를 활성화합니다."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Llama 3 70B 지시 모델은 다국어 대화 및 자연어 이해를 위해 최적화되어 있으며, 대부분의 경쟁 모델보다 성능이 우수합니다."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B 지시 모델(HF 버전)은 공식 구현 결과와 일치하며, 고품질의 지시 따르기 작업에 적합합니다."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Llama 3 8B 지시 모델은 대화 및 다국어 작업을 위해 최적화되어 있으며, 뛰어난 성능과 효율성을 제공합니다."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Llama 3.1 8B 지시 모델은 다국어 대화를 위해 최적화되어 있으며, 일반 산업 기준에서 대부분의 오픈 소스 및 폐쇄 소스 모델을 초월합니다."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Meta의 11B 파라미터 지시 조정 이미지 추론 모델입니다. 이 모델은 시각 인식, 이미지 추론, 이미지 설명 및 이미지에 대한 일반적인 질문에 답변하기 위해 최적화되었습니다. 이 모델은 차트 및 그래프와 같은 시각 데이터를 이해할 수 있으며, 이미지 세부 사항을 설명하는 텍스트를 생성하여 시각과 언어 간의 격차를 메웁니다."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Llama 3.2 3B 지시 모델은 Meta가 출시한 경량 다국어 모델입니다. 이 모델은 효율성을 높이기 위해 설계되었으며, 더 큰 모델에 비해 지연 시간과 비용에서 상당한 개선을 제공합니다. 이 모델의 예시 사용 사례에는 쿼리 및 프롬프트 재작성, 작문 지원이 포함됩니다."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Meta의 90B 파라미터 지시 조정 이미지 추론 모델입니다. 이 모델은 시각 인식, 이미지 추론, 이미지 설명 및 이미지에 대한 일반적인 질문에 답변하기 위해 최적화되었습니다. 이 모델은 차트 및 그래프와 같은 시각 데이터를 이해할 수 있으며, 이미지 세부 사항을 설명하는 텍스트를 생성하여 시각과 언어 간의 격차를 메웁니다."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct는 Llama 3.1 70B의 12월 업데이트 버전입니다. 이 모델은 Llama 3.1 70B(2024년 7월 출시)를 기반으로 개선되어 도구 호출, 다국어 텍스트 지원, 수학 및 프로그래밍 능력을 강화했습니다. 이 모델은 추론, 수학 및 지시 준수에서 업계 최고 수준에 도달했으며, 3.1 405B와 유사한 성능을 제공하면서 속도와 비용에서 상당한 이점을 가지고 있습니다."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "24B 매개변수 모델로, 더 큰 모델과 동등한 최첨단 능력을 갖추고 있습니다."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B 지시 모델은 대규모 매개변수와 다수의 전문가 아키텍처를 통해 복잡한 작업의 효율적인 처리를 전방위적으로 지원합니다."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B 지시 모델은 다수의 전문가 아키텍처를 통해 효율적인 지시 따르기 및 실행을 제공합니다."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B 지시 모델(HF 버전)은 성능이 공식 구현과 일치하며, 다양한 효율적인 작업 시나리오에 적합합니다."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "MythoMax L2 13B 모델은 혁신적인 통합 기술을 결합하여 서사 및 역할 수행에 강점을 보입니다."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision 지시 모델은 경량 다중 모달 모델로, 복잡한 시각 및 텍스트 정보를 처리할 수 있으며, 강력한 추론 능력을 갖추고 있습니다."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5B 모델은 고급 프로그래밍 작업을 지원하며, 다국어 능력이 강화되어 복잡한 코드 생성 및 이해에 적합합니다."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "QwQ 모델은 Qwen 팀이 개발한 실험적 연구 모델로, AI 추론 능력을 향상시키는 데 중점을 두고 있습니다."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7B 모델은 80개 이상의 프로그래밍 언어를 대상으로 훈련되어 뛰어난 프로그래밍 완성 능력과 문맥 이해를 제공합니다."
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Qwen-VL 모델의 72B 버전은 알리바바의 최신 반복 결과로, 거의 1년간의 혁신을 대표합니다."
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5는 Alibaba Cloud Qwen 팀이 개발한 일련의 디코더 전용 언어 모델입니다. 이러한 모델은 0.5B, 1.5B, 3B, 7B, 14B, 32B 및 72B와 같은 다양한 크기를 제공하며, 기본 버전과 지시 버전 두 가지 변형이 있습니다."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct는 Alibaba Cloud에서 발표한 코드 특화 대규모 언어 모델 시리즈의 최신 버전입니다. 이 모델은 Qwen2.5를 기반으로 하여 55조 개의 토큰으로 훈련되어 코드 생성, 추론 및 수정 능력을 크게 향상시켰습니다. 이 모델은 코딩 능력을 강화할 뿐만 아니라 수학 및 일반 능력의 장점도 유지합니다. 모델은 코드 에이전트와 같은 실제 응용 프로그램에 더 포괄적인 기반을 제공합니다."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Yi-Large 모델은 뛰어난 다국어 처리 능력을 갖추고 있으며, 다양한 언어 생성 및 이해 작업에 사용될 수 있습니다."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "52B 매개변수(12B 활성)의 다국어 모델로, 256K 긴 컨텍스트 창, 함수 호출, 구조화된 출력 및 기반 생성 기능을 제공합니다."
},
- "ai21-jamba-instruct": {
- "description": "최고 수준의 성능, 품질 및 비용 효율성을 달성하기 위해 제작된 Mamba 기반 LLM 모델입니다."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet는 업계 표준을 향상시켜 경쟁 모델 및 Claude 3 Opus를 초월하며, 광범위한 평가에서 뛰어난 성능을 보이고, 중간 수준 모델의 속도와 비용을 갖추고 있습니다."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet는 업계 표준을 향상시켰으며, 경쟁 모델과 Claude 3 Opus를 초월하는 성능을 보여주고, 광범위한 평가에서 뛰어난 성과를 보였습니다. 또한 중간 수준 모델의 속도와 비용을 갖추고 있습니다."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku는 Anthropic의 가장 빠르고 간결한 모델로, 거의 즉각적인 응답 속도를 제공합니다. 간단한 질문과 요청에 신속하게 답변할 수 있습니다. 고객은 인간 상호작용을 모방하는 원활한 AI 경험을 구축할 수 있습니다. Claude 3 Haiku는 이미지를 처리하고 텍스트 출력을 반환할 수 있으며, 200K의 컨텍스트 창을 갖추고 있습니다."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus는 Anthropic이 복잡한 작업을 처리하기 위해 개발한 가장 강력한 모델입니다. 성능, 지능, 유창성 및 이해력에서 뛰어난 성과를 보입니다."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku는 Anthropic의 가장 빠른 차세대 모델입니다. Claude 3 Haiku와 비교하여 Claude 3.5 Haiku는 모든 기술에서 향상되었으며, 많은 지능 벤치마크 테스트에서 이전 세대의 가장 큰 모델인 Claude 3 Opus를 초월했습니다."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet은 Opus를 초월하는 능력과 Sonnet보다 더 빠른 속도를 제공하며, Sonnet과 동일한 가격을 유지합니다. Sonnet은 프로그래밍, 데이터 과학, 비주얼 처리 및 에이전트 작업에 특히 강합니다."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet은 Anthropic이 지금까지 개발한 가장 지능적인 모델로, 시장에서 최초의 혼합 추론 모델입니다. Claude 3.7 Sonnet은 거의 즉각적인 응답이나 연장된 단계적 사고를 생성할 수 있으며, 사용자는 이러한 과정을 명확하게 볼 수 있습니다. Sonnet은 프로그래밍, 데이터 과학, 시각 처리, 대리 작업에 특히 뛰어납니다."
+ },
"aya": {
"description": "Aya 23은 Cohere에서 출시한 다국어 모델로, 23개 언어를 지원하여 다양한 언어 응용에 편리함을 제공합니다."
},
"aya:35b": {
"description": "Aya 23은 Cohere에서 출시한 다국어 모델로, 23개 언어를 지원하여 다양한 언어 응용에 편리함을 제공합니다."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B는 백천 인공지능이 개발한 130억 개의 매개변수를 가진 오픈 소스 상용 대형 언어 모델로, 권위 있는 중국어 및 영어 벤치마크에서 동일한 크기에서 최고의 성과를 달성했습니다."
+ },
"charglm-3": {
"description": "CharGLM-3는 역할 수행 및 감정 동반을 위해 설계된 모델로, 초장 다회 기억 및 개인화된 대화를 지원하여 광범위하게 사용됩니다."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2는 기업에 중요한 능력의 발전을 제공하며, 업계 최고의 200K 토큰 컨텍스트, 모델 환각 발생률 대폭 감소, 시스템 프롬프트 및 새로운 테스트 기능인 도구 호출을 포함합니다."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku는 Anthropic의 가장 빠른 차세대 모델입니다. Claude 3 Haiku와 비교할 때, Claude 3.5 Haiku는 모든 기술에서 향상되었으며, 많은 지능 기준 테스트에서 이전 세대의 가장 큰 모델인 Claude 3 Opus를 초월했습니다."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet은 Opus를 초월하는 능력과 Sonnet보다 더 빠른 속도를 제공하며, Sonnet과 동일한 가격을 유지합니다. Sonnet은 프로그래밍, 데이터 과학, 시각 처리 및 대리 작업에 특히 강합니다."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet은 Opus를 초월하는 능력과 Sonnet보다 빠른 속도를 제공하면서도 Sonnet과 동일한 가격을 유지합니다. Sonnet은 프로그래밍, 데이터 과학, 비주얼 처리 및 대리 작업에 특히 뛰어납니다."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet은 Opus를 초월하는 능력과 Sonnet보다 더 빠른 속도를 제공하며, Sonnet과 동일한 가격을 유지합니다. Sonnet은 프로그래밍, 데이터 과학, 비주얼 처리 및 에이전트 작업에 특히 강합니다."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku는 Anthropic의 가장 빠르고 컴팩트한 모델로, 거의 즉각적인 응답을 목표로 합니다. 빠르고 정확한 방향성 성능을 갖추고 있습니다."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet은 기업 작업 부하에 이상적인 균형을 제공하며, 더 낮은 가격으로 최대 효용을 제공합니다. 신뢰성이 높고 대규모 배포에 적합합니다."
},
- "claude-instant-1.2": {
- "description": "Anthropic의 모델은 낮은 지연 시간과 높은 처리량의 텍스트 생성을 위해 설계되었으며, 수백 페이지의 텍스트 생성을 지원합니다."
- },
"codegeex-4": {
"description": "CodeGeeX-4는 강력한 AI 프로그래밍 도우미로, 다양한 프로그래밍 언어에 대한 스마트 Q&A 및 코드 완성을 지원하여 개발 효율성을 높입니다."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B는 다국어 코드 생성 모델로, 코드 완성 및 생성, 코드 해석기, 웹 검색, 함수 호출, 저장소 수준의 코드 질문 응답 등 다양한 기능을 지원하여 소프트웨어 개발의 여러 시나리오를 포괄합니다. 10B 미만의 매개변수를 가진 최고의 코드 생성 모델입니다."
+ },
"codegemma": {
"description": "CodeGemma는 다양한 프로그래밍 작업을 위한 경량 언어 모델로, 빠른 반복 및 통합을 지원합니다."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama는 코드 생성 및 논의에 중점을 둔 LLM으로, 광범위한 프로그래밍 언어 지원을 결합하여 개발자 환경에 적합합니다."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama는 코드 생성 및 논의에 중점을 둔 LLM으로, 광범위한 프로그래밍 언어 지원을 결합하여 개발자 환경에 적합합니다."
+ },
"codellama:13b": {
"description": "Code Llama는 코드 생성 및 논의에 중점을 둔 LLM으로, 광범위한 프로그래밍 언어 지원을 결합하여 개발자 환경에 적합합니다."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+는 실제 기업 환경 및 복잡한 응용을 위해 설계된 고성능 대형 언어 모델입니다."
},
+ "dall-e-2": {
+ "description": "2세대 DALL·E 모델로, 더 사실적이고 정확한 이미지 생성을 지원하며, 해상도는 1세대의 4배입니다."
+ },
+ "dall-e-3": {
+ "description": "최신 DALL·E 모델로, 2023년 11월에 출시되었습니다. 더 사실적이고 정확한 이미지 생성을 지원하며, 세부 표현력이 강화되었습니다."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct는 높은 신뢰성을 가진 지시 처리 능력을 제공하며, 다양한 산업 응용을 지원합니다."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1은 강화 학습(RL) 기반의 추론 모델로, 모델 내의 반복성과 가독성 문제를 해결합니다. RL 이전에 DeepSeek-R1은 콜드 스타트 데이터를 도입하여 추론 성능을 더욱 최적화했습니다. 수학, 코드 및 추론 작업에서 OpenAI-o1과 유사한 성능을 보이며, 정교하게 설계된 훈련 방법을 통해 전체적인 효과를 향상시켰습니다."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek-R1 증류 모델로, 강화 학습과 콜드 스타트 데이터를 통해 추론 성능을 최적화하며, 오픈 소스 모델로 다중 작업 기준을 갱신합니다."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B는 Llama-3.1-8B를 기반으로 개발된 증류 모델입니다. 이 모델은 DeepSeek-R1이 생성한 샘플을 사용하여 미세 조정되었으며, 뛰어난 추론 능력을 보여줍니다. 여러 기준 테스트에서 좋은 성적을 거두었으며, MATH-500에서 89.1%의 정확도를 달성하고, AIME 2024에서 50.4%의 통과율을 기록했으며, CodeForces에서 1205의 점수를 얻어 8B 규모의 모델로서 강력한 수학 및 프로그래밍 능력을 보여줍니다."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 증류 모델로, 강화 학습과 콜드 스타트 데이터를 통해 추론 성능을 최적화하며, 오픈 소스 모델로 다중 작업 기준을 갱신합니다."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 증류 모델로, 강화 학습과 콜드 스타트 데이터를 통해 추론 성능을 최적화하며, 오픈 소스 모델로 다중 작업 기준을 갱신합니다."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B는 Qwen2.5-32B를 기반으로 지식 증류를 통해 얻은 모델입니다. 이 모델은 DeepSeek-R1이 생성한 80만 개의 선별된 샘플을 사용하여 미세 조정되었으며, 수학, 프로그래밍 및 추론 등 여러 분야에서 뛰어난 성능을 보여줍니다. AIME 2024, MATH-500, GPQA Diamond 등 여러 기준 테스트에서 우수한 성적을 거두었으며, MATH-500에서 94.3%의 정확도를 달성하여 강력한 수학 추론 능력을 보여줍니다."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B는 Qwen2.5-Math-7B를 기반으로 지식 증류를 통해 얻은 모델입니다. 이 모델은 DeepSeek-R1이 생성한 80만 개의 선별된 샘플을 사용하여 미세 조정되었으며, 뛰어난 추론 능력을 보여줍니다. 여러 기준 테스트에서 우수한 성적을 거두었으며, MATH-500에서 92.8%의 정확도를 달성하고, AIME 2024에서 55.5%의 통과율을 기록했으며, CodeForces에서 1189의 점수를 얻어 7B 규모의 모델로서 강력한 수학 및 프로그래밍 능력을 보여줍니다."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5는 이전 버전의 우수한 기능을 집약하여 일반 및 인코딩 능력을 강화했습니다."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3는 6710억 개의 매개변수를 가진 혼합 전문가(MoE) 언어 모델로, 다중 헤드 잠재 주의(MLA) 및 DeepSeekMoE 아키텍처를 채택하여 보조 손실 없는 부하 균형 전략을 결합하여 추론 및 훈련 효율성을 최적화합니다. 14.8조 개의 고품질 토큰에서 사전 훈련을 수행하고 감독 미세 조정 및 강화 학습을 통해 DeepSeek-V3는 성능 면에서 다른 오픈 소스 모델을 초월하며, 선도적인 폐쇄형 모델에 근접합니다."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B는 고복잡성 대화를 위해 훈련된 고급 모델입니다."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "추론, 수학 및 프로그래밍에 능숙한 최첨단 효율 LLM입니다."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2는 DeepSeekMoE-27B를 기반으로 개발된 혼합 전문가(MoE) 비주얼 언어 모델로, 희소 활성화 MoE 아키텍처를 사용하여 4.5B 매개변수만 활성화된 상태에서 뛰어난 성능을 발휘합니다. 이 모델은 비주얼 질문 응답, 광학 문자 인식, 문서/표/차트 이해 및 비주얼 위치 지정 등 여러 작업에서 우수한 성과를 보입니다."
+ },
"deepseek-chat": {
"description": "일반 및 코드 능력을 융합한 새로운 오픈 소스 모델로, 기존 Chat 모델의 일반 대화 능력과 Coder 모델의 강력한 코드 처리 능력을 유지하면서 인간의 선호에 더 잘 맞춰졌습니다. 또한, DeepSeek-V2.5는 작문 작업, 지시 따르기 등 여러 측면에서 큰 향상을 이루었습니다."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B는 코드 언어 모델로, 20조 개의 데이터로 훈련되었으며, 그 중 87%는 코드, 13%는 중문 및 영문입니다. 모델은 16K 창 크기와 빈칸 채우기 작업을 도입하여 프로젝트 수준의 코드 완성과 코드 조각 채우기 기능을 제공합니다."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2는 오픈 소스 혼합 전문가 코드 모델로, 코드 작업에서 뛰어난 성능을 발휘하며, GPT4-Turbo와 경쟁할 수 있습니다."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2는 오픈 소스 혼합 전문가 코드 모델로, 코드 작업에서 뛰어난 성능을 발휘하며, GPT4-Turbo와 경쟁할 수 있습니다."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1은 강화 학습(RL) 기반의 추론 모델로, 모델 내의 반복성과 가독성 문제를 해결합니다. RL 이전에 DeepSeek-R1은 콜드 스타트 데이터를 도입하여 추론 성능을 더욱 최적화했습니다. 수학, 코드 및 추론 작업에서 OpenAI-o1과 유사한 성능을 보이며, 정교하게 설계된 훈련 방법을 통해 전체적인 효과를 향상시켰습니다."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - DeepSeek 패키지에서 더 크고 더 스마트한 모델이 Llama 70B 아키텍처로 증류되었습니다. 기준 테스트와 인공지능 평가에 따르면, 이 모델은 원래 Llama 70B보다 더 스마트하며, 특히 수학 및 사실 정확성이 필요한 작업에서 뛰어난 성능을 보입니다."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek-R1-Distill 시리즈 모델은 지식 증류 기술을 통해 DeepSeek-R1이 생성한 샘플을 Qwen, Llama 등 오픈 소스 모델에 미세 조정하여 얻은 것입니다."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "DeepSeek-R1-Distill 시리즈 모델은 지식 증류 기술을 통해 DeepSeek-R1이 생성한 샘플을 Qwen, Llama 등 오픈 소스 모델에 미세 조정하여 얻은 것입니다."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek-R1-Distill 시리즈 모델은 지식 증류 기술을 통해 DeepSeek-R1이 생성한 샘플을 Qwen, Llama 등 오픈 소스 모델에 미세 조정하여 얻은 것입니다."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek-R1-Distill 시리즈 모델은 지식 증류 기술을 통해 DeepSeek-R1이 생성한 샘플을 Qwen, Llama 등 오픈 소스 모델에 미세 조정하여 얻은 것입니다."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "DeepSeek-R1-Distill 시리즈 모델은 지식 증류 기술을 통해 DeepSeek-R1이 생성한 샘플을 Qwen, Llama 등 오픈 소스 모델에 미세 조정하여 얻은 것입니다."
+ },
+ "deepseek-reasoner": {
+ "description": "DeepSeek에서 제공하는 추론 모델입니다. 최종 답변을 출력하기 전에 모델은 먼저 사고 과정을 출력하여 최종 답변의 정확성을 높입니다."
+ },
"deepseek-v2": {
"description": "DeepSeek V2는 경제적이고 효율적인 처리 요구에 적합한 Mixture-of-Experts 언어 모델입니다."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B는 DeepSeek의 설계 코드 모델로, 강력한 코드 생성 능력을 제공합니다."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3는 항저우 심도 탐색 인공지능 기초 기술 연구 회사에서 자체 개발한 MoE 모델로, 여러 평가에서 뛰어난 성적을 거두며, 주류 순위에서 오픈 소스 모델 1위를 차지하고 있습니다. V3는 V2.5 모델에 비해 생성 속도가 3배 향상되어 사용자에게 더 빠르고 원활한 사용 경험을 제공합니다."
+ },
"deepseek/deepseek-chat": {
"description": "일반 및 코드 능력을 통합한 새로운 오픈 소스 모델로, 기존 Chat 모델의 일반 대화 능력과 Coder 모델의 강력한 코드 처리 능력을 유지하면서 인간의 선호에 더 잘 맞춰졌습니다. 또한, DeepSeek-V2.5는 작문 작업, 지시 따르기 등 여러 분야에서 큰 향상을 이루었습니다."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1은 극히 적은 주석 데이터로 모델의 추론 능력을 크게 향상시킵니다. 최종 답변을 출력하기 전에 모델은 먼저 사고의 연쇄 내용을 출력하여 최종 답변의 정확성을 높입니다."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B는 Llama3.3 70B를 기반으로 한 대형 언어 모델로, DeepSeek R1의 출력을 활용하여 대형 최첨단 모델과 동등한 경쟁 성능을 달성했습니다."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B는 Llama-3.1-8B-Instruct를 기반으로 한 증류 대형 언어 모델로, DeepSeek R1의 출력을 사용하여 훈련되었습니다."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B는 Qwen 2.5 14B를 기반으로 한 증류 대형 언어 모델로, DeepSeek R1의 출력을 사용하여 훈련되었습니다. 이 모델은 여러 벤치마크 테스트에서 OpenAI의 o1-mini를 초월하며, 밀집 모델(dense models)에서 최신 기술 선도 성과(state-of-the-art)를 달성했습니다. 다음은 몇 가지 벤치마크 테스트 결과입니다:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\n이 모델은 DeepSeek R1의 출력을 미세 조정하여 더 큰 규모의 최첨단 모델과 동등한 경쟁 성능을 보여주었습니다."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B는 Qwen 2.5 32B를 기반으로 한 증류 대형 언어 모델로, DeepSeek R1의 출력을 사용하여 훈련되었습니다. 이 모델은 여러 벤치마크 테스트에서 OpenAI의 o1-mini를 초월하며, 밀집 모델(dense models)에서 최신 기술 선도 성과(state-of-the-art)를 달성했습니다. 다음은 몇 가지 벤치마크 테스트 결과입니다:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\n이 모델은 DeepSeek R1의 출력을 미세 조정하여 더 큰 규모의 최첨단 모델과 동등한 경쟁 성능을 보여주었습니다."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1은 DeepSeek 팀이 발표한 최신 오픈 소스 모델로, 특히 수학, 프로그래밍 및 추론 작업에서 OpenAI의 o1 모델과 동등한 수준의 강력한 추론 성능을 갖추고 있습니다."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1은 극히 적은 주석 데이터로 모델의 추론 능력을 크게 향상시킵니다. 최종 답변을 출력하기 전에 모델은 먼저 사고의 연쇄 내용을 출력하여 최종 답변의 정확성을 높입니다."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3는 추론 속도에서 이전 모델에 비해 중대한 돌파구를 이루었습니다. 오픈 소스 모델 중 1위를 차지하며, 세계에서 가장 진보된 폐쇄형 모델과 견줄 수 있습니다. DeepSeek-V3는 다중 헤드 잠재 주의(Multi-Head Latent Attention, MLA)와 DeepSeekMoE 아키텍처를 채택하였으며, 이 아키텍처는 DeepSeek-V2에서 철저히 검증되었습니다. 또한, DeepSeek-V3는 부하 균형을 위한 보조 무손실 전략을 개척하고, 더 강력한 성능을 위해 다중 레이블 예측 훈련 목표를 설정했습니다."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3는 추론 속도에서 이전 모델에 비해 중대한 돌파구를 이루었습니다. 오픈 소스 모델 중 1위를 차지하며, 세계에서 가장 진보된 폐쇄형 모델과 견줄 수 있습니다. DeepSeek-V3는 다중 헤드 잠재 주의(Multi-Head Latent Attention, MLA)와 DeepSeekMoE 아키텍처를 채택하였으며, 이 아키텍처는 DeepSeek-V2에서 철저히 검증되었습니다. 또한, DeepSeek-V3는 부하 균형을 위한 보조 무손실 전략을 개척하고, 더 강력한 성능을 위해 다중 레이블 예측 훈련 목표를 설정했습니다."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite는 전혀 새로운 세대의 경량 모델로, 극한의 응답 속도를 자랑하며, 효과와 지연 모두 세계 최고 수준에 도달했습니다."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k는 Doubao-1.5-Pro의 전면 업그레이드 버전으로, 전체적인 효과가 10% 향상되었습니다. 256k의 컨텍스트 윈도우를 지원하며, 출력 길이는 최대 12k 토큰을 지원합니다. 더 높은 성능, 더 큰 윈도우, 뛰어난 가성비로 더 넓은 응용 분야에 적합합니다."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro는 전혀 새로운 세대의 주력 모델로, 성능이 전면적으로 업그레이드되어 지식, 코드, 추론 등 여러 분야에서 뛰어난 성능을 발휘합니다."
+ },
"emohaa": {
"description": "Emohaa는 심리 모델로, 전문 상담 능력을 갖추고 있어 사용자가 감정 문제를 이해하는 데 도움을 줍니다."
},
+ "ernie-3.5-128k": {
+ "description": "바이두가 자체 개발한 플래그십 대규모 언어 모델로, 방대한 중영문 자료를 포함하고 있으며, 강력한 일반 능력을 가지고 있어 대부분의 대화 질문 답변, 창작 생성, 플러그인 응용 시나리오 요구를 충족할 수 있습니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다."
+ },
+ "ernie-3.5-8k": {
+ "description": "바이두가 자체 개발한 플래그십 대규모 언어 모델로, 방대한 중영문 자료를 포함하고 있으며, 강력한 일반 능력을 가지고 있어 대부분의 대화 질문 답변, 창작 생성, 플러그인 응용 시나리오 요구를 충족할 수 있습니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "바이두가 자체 개발한 플래그십 대규모 언어 모델로, 방대한 중영문 자료를 포함하고 있으며, 강력한 일반 능력을 가지고 있어 대부분의 대화 질문 답변, 창작 생성, 플러그인 응용 시나리오 요구를 충족할 수 있습니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, ERNIE 3.5에 비해 모델 능력이 전면 업그레이드되었으며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, ERNIE 3.5에 비해 모델 능력이 전면 업그레이드되었으며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, 종합적인 성능이 뛰어나며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다. ERNIE 4.0에 비해 성능이 더 우수합니다."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, 종합적인 성능이 뛰어나며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다. ERNIE 4.0에 비해 성능이 더 우수합니다."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "바이두가 자체 개발한 플래그십 초대규모 언어 모델로, 종합적인 성능이 뛰어나며, 다양한 분야의 복잡한 작업 시나리오에 널리 적용됩니다. 바이두 검색 플러그인과 자동으로 연결되어 질문 답변 정보의 시의성을 보장합니다. ERNIE 4.0에 비해 성능이 더 우수합니다."
+ },
+ "ernie-char-8k": {
+ "description": "바이두가 자체 개발한 수직 장면 대형 언어 모델로, 게임 NPC, 고객 서비스 대화, 대화 역할극 등 응용 시나리오에 적합하며, 캐릭터 스타일이 더 뚜렷하고 일관되며, 지시 따르기 능력이 더 강하고 추론 성능이 우수합니다."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "바이두가 자체 개발한 수직 장면 대형 언어 모델로, 게임 NPC, 고객 서비스 대화, 대화 역할극 등 응용 시나리오에 적합하며, 캐릭터 스타일이 더 뚜렷하고 일관되며, 지시 따르기 능력이 더 강하고 추론 성능이 우수합니다."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite는 바이두가 자체 개발한 경량 대형 언어 모델로, 우수한 모델 효과와 추론 성능을 겸비하여 저전력 AI 가속 카드 추론에 적합합니다."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "바이두가 자체 개발한 경량 대형 언어 모델로, 우수한 모델 효과와 추론 성능을 겸비하여 ERNIE Lite보다 더 우수하며, 저전력 AI 가속 카드 추론에 적합합니다."
+ },
+ "ernie-novel-8k": {
+ "description": "바이두가 자체 개발한 일반 대형 언어 모델로, 소설 연속 작성 능력에서 뚜렷한 장점을 가지고 있으며, 단편극, 영화 등 시나리오에서도 사용할 수 있습니다."
+ },
+ "ernie-speed-128k": {
+ "description": "바이두가 2024년에 최신 출시한 고성능 대형 언어 모델로, 일반 능력이 우수하여 특정 시나리오 문제를 더 잘 처리하기 위해 기초 모델로 미세 조정하는 데 적합하며, 뛰어난 추론 성능을 가지고 있습니다."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "바이두가 2024년에 최신 출시한 고성능 대형 언어 모델로, 일반 능력이 우수하여 ERNIE Speed보다 더 우수하며, 특정 시나리오 문제를 더 잘 처리하기 위해 기초 모델로 미세 조정하는 데 적합하며, 뛰어난 추론 성능을 가지고 있습니다."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny는 바이두가 자체 개발한 초고성능 대형 언어 모델로, 문신 시리즈 모델 중 배포 및 미세 조정 비용이 가장 낮습니다."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning)은 안정적이고 조정 가능한 성능을 제공하며, 복잡한 작업 솔루션의 이상적인 선택입니다."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro는 Google의 고성능 AI 모델로, 광범위한 작업 확장을 위해 설계되었습니다."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash는 Google의 최신 다중 모달 AI 모델로, 빠른 처리 능력을 갖추고 있으며 텍스트, 이미지 및 비디오 입력을 지원하여 다양한 작업에 효율적으로 확장할 수 있습니다."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001은 효율적인 다중 모달 모델로, 광범위한 응용 프로그램 확장을 지원합니다."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002는 효율적인 다중 모달 모델로, 광범위한 응용 프로그램의 확장을 지원합니다."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827은 대규모 작업 시나리오 처리를 위해 설계되었으며, 비할 데 없는 처리 속도를 제공합니다."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B는 효율적인 다중 모달 모델로, 광범위한 응용 프로그램의 확장을 지원합니다."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924는 최신 실험 모델로, 텍스트 및 다중 모달 사용 사례에서 상당한 성능 향상을 보여줍니다."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827은 최적화된 다중 모달 처리 능력을 제공하며, 다양한 복잡한 작업 시나리오에 적합합니다."
+ "description": "Gemini 1.5 Flash 0827은 다양한 복잡한 작업에 적합한 최적화된 다중 모달 처리 능력을 제공합니다."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash는 Google의 최신 다중 모달 AI 모델로, 빠른 처리 능력을 갖추고 있으며 텍스트, 이미지 및 비디오 입력을 지원하여 다양한 작업에 효율적으로 확장할 수 있습니다."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002는 최신 생산 준비 모델로, 특히 수학, 긴 문맥 및 시각적 작업에서 더 높은 품질의 출력을 제공합니다."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801은 뛰어난 다중 모달 처리 능력을 제공하여 응용 프로그램 개발에 더 큰 유연성을 제공합니다."
+ "description": "Gemini 1.5 Pro 0801은 뛰어난 다중 모달 처리 능력을 제공하여 애플리케이션 개발에 더 큰 유연성을 제공합니다."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827은 최신 최적화 기술을 결합하여 더 효율적인 다중 모달 데이터 처리 능력을 제공합니다."
+ "description": "Gemini 1.5 Pro 0827은 최신 최적화 기술을 결합하여 보다 효율적인 다중 모달 데이터 처리 능력을 제공합니다."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro는 최대 200만 개의 토큰을 지원하며, 중형 다중 모달 모델의 이상적인 선택으로 복잡한 작업에 대한 다각적인 지원을 제공합니다."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash는 뛰어난 속도, 원주율 도구 사용, 다중 모달 생성 및 1M 토큰 문맥 창을 포함한 차세대 기능과 개선 사항을 제공합니다."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash는 뛰어난 속도, 원주율 도구 사용, 다중 모달 생성 및 1M 토큰 문맥 창을 포함한 차세대 기능과 개선 사항을 제공합니다."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 플래시 모델 변형으로, 비용 효율성과 낮은 지연 시간 등의 목표를 위해 최적화되었습니다."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 플래시 모델 변형으로, 비용 효율성과 낮은 지연 시간 등의 목표를 위해 최적화되었습니다."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "비용 효율성과 낮은 지연 시간 등을 목표로 최적화된 Gemini 2.0 Flash 모델입니다."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp는 Google의 최신 실험적 다중 모드 AI 모델로, 차세대 기능, 뛰어난 속도, 네이티브 도구 호출 및 다중 모드 생성을 제공합니다."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp는 Google의 최신 실험적 다중 모드 AI 모델로, 차세대 기능, 뛰어난 속도, 네이티브 도구 호출 및 다중 모드 생성을 제공합니다."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental은 Google의 최신 실험적 다중 모달 AI 모델로, 이전 버전과 비교하여 품질이 향상되었습니다. 특히 세계 지식, 코드 및 긴 문맥에 대해 개선되었습니다."
+ },
"gemma-7b-it": {
"description": "Gemma 7B는 중소 규모 작업 처리에 적합하며, 비용 효과성을 갖추고 있습니다."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2는 Google에서 출시한 효율적인 모델로, 소형 응용 프로그램부터 복잡한 데이터 처리까지 다양한 응용 시나리오를 포함합니다."
},
- "general": {
- "description": "Spark Lite는 경량 대형 언어 모델로, 매우 낮은 지연 시간과 효율적인 처리 능력을 갖추고 있으며, 완전 무료로 개방되어 실시간 온라인 검색 기능을 지원합니다. 빠른 응답 특성 덕분에 저전력 장치에서의 추론 응용 및 모델 미세 조정에서 뛰어난 성능을 발휘하여 사용자에게 뛰어난 비용 효율성과 지능적인 경험을 제공합니다. 특히 지식 질문 응답, 콘텐츠 생성 및 검색 시나리오에서 두각을 나타냅니다."
- },
"generalv3": {
"description": "Spark Pro는 전문 분야에 최적화된 고성능 대형 언어 모델로, 수학, 프로그래밍, 의료, 교육 등 여러 분야에 중점을 두고 있으며, 네트워크 검색 및 내장된 날씨, 날짜 등의 플러그인을 지원합니다. 최적화된 모델은 복잡한 지식 질문 응답, 언어 이해 및 고급 텍스트 창작에서 뛰어난 성능과 효율성을 보여주며, 전문 응용 시나리오에 적합한 이상적인 선택입니다."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520은 최신 모델 버전으로, 매우 복잡하고 다양한 작업을 위해 설계되어 뛰어난 성능을 발휘합니다."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat은 의미, 수학, 추론, 코드 및 지식 등 여러 분야에서 높은 성능을 보입니다. 웹 브라우징, 코드 실행, 사용자 정의 도구 호출 및 긴 텍스트 추론 기능도 갖추고 있습니다. 일본어, 한국어, 독일어를 포함한 26개 언어를 지원합니다."
+ },
"glm-4-air": {
"description": "GLM-4-Air는 가성비가 높은 버전으로, GLM-4에 가까운 성능을 제공하며 빠른 속도와 저렴한 가격을 자랑합니다."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash는 간단한 작업을 처리하는 데 이상적인 선택으로, 가장 빠른 속도와 가장 저렴한 가격을 자랑합니다."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX는 Flash의 향상된 버전으로, 초고속 추론 속도를 자랑합니다."
+ },
"glm-4-long": {
"description": "GLM-4-Long는 초장 텍스트 입력을 지원하여 기억형 작업 및 대규모 문서 처리에 적합합니다."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V는 강력한 이미지 이해 및 추론 능력을 제공하며, 다양한 시각적 작업을 지원합니다."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash는 효율적인 단일 이미지 이해에 중점을 두며, 실시간 이미지 분석이나 대량 이미지 처리와 같은 빠른 이미지 분석 환경에 적합합니다."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus는 비디오 콘텐츠 및 다수의 이미지에 대한 이해 능력을 갖추고 있어 다중 모드 작업에 적합합니다."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827은 최적화된 다중 모달 처리 능력을 제공하며, 다양한 복잡한 작업 시나리오에 적합합니다."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview는 강력한 복잡한 추론 능력을 갖추고 있으며, 논리 추론, 수학, 프로그래밍 등 분야에서 우수한 성능을 발휘합니다."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash는 뛰어난 속도, 원주율 도구 사용, 다중 모달 생성 및 1M 토큰 문맥 창을 포함한 차세대 기능과 개선 사항을 제공합니다."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827은 최신 최적화 기술을 결합하여 더 효율적인 다중 모달 데이터 처리 능력을 제공합니다."
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental은 Google의 최신 실험적 다중 모달 AI 모델로, 이전 버전과 비교하여 품질이 향상되었습니다. 특히 세계 지식, 코드 및 긴 문맥에 대해 개선되었습니다."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash는 최적화된 다중 모달 처리 능력을 제공하며, 다양한 복잡한 작업 시나리오에 적합합니다."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro는 최신 최적화 기술을 결합하여 더 효율적인 다중 모달 데이터 처리 능력을 제공합니다."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2는 Google에서 출시한 효율적인 모델로, 소형 애플리케이션부터 복잡한 데이터 처리까지 다양한 응용 시나리오를 포함합니다."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2는 경량화와 효율적인 설계를 이어갑니다."
},
+ "google/gemma-2-2b-it": {
+ "description": "Google의 경량 지시 조정 모델"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2는 Google에서 출시한 효율적인 모델로, 소형 애플리케이션부터 복잡한 데이터 처리까지 다양한 응용 시나리오를 포함합니다."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2는 Google의 경량화된 오픈 소스 텍스트 모델 시리즈입니다."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo는 다양한 텍스트 생성 및 이해 작업에 적합하며, 현재 gpt-3.5-turbo-0125를 가리킵니다."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo는 OpenAI에서 제공하는 효율적인 모델로, 채팅 및 텍스트 생성 작업에 적합하며, 병렬 함수 호출을 지원합니다."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k는 복잡한 작업에 적합한 고용량 텍스트 생성 모델입니다."
+ },
"gpt-4": {
"description": "GPT-4는 더 큰 컨텍스트 창을 제공하여 더 긴 텍스트 입력을 처리할 수 있으며, 광범위한 정보 통합 및 데이터 분석이 필요한 상황에 적합합니다."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "최신 GPT-4 Turbo 모델은 시각적 기능을 갖추고 있습니다. 이제 시각적 요청은 JSON 형식과 함수 호출을 사용하여 처리할 수 있습니다. GPT-4 Turbo는 다중 모드 작업을 위한 비용 효율적인 지원을 제공하는 향상된 버전입니다. 정확성과 효율성 간의 균형을 찾아 실시간 상호작용이 필요한 응용 프로그램에 적합합니다."
},
- "gpt-4-1106-vision-preview": {
- "description": "최신 GPT-4 Turbo 모델은 시각적 기능을 갖추고 있습니다. 이제 시각적 요청은 JSON 형식과 함수 호출을 사용하여 처리할 수 있습니다. GPT-4 Turbo는 다중 모드 작업을 위한 비용 효율적인 지원을 제공하는 향상된 버전입니다. 정확성과 효율성 간의 균형을 찾아 실시간 상호작용이 필요한 응용 프로그램에 적합합니다."
- },
"gpt-4-32k": {
"description": "GPT-4는 더 큰 컨텍스트 창을 제공하여 더 긴 텍스트 입력을 처리할 수 있으며, 광범위한 정보 통합 및 데이터 분석이 필요한 상황에 적합합니다."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "최신 GPT-4 Turbo 모델은 시각적 기능을 갖추고 있습니다. 이제 시각적 요청은 JSON 형식과 함수 호출을 사용하여 처리할 수 있습니다. GPT-4 Turbo는 다중 모드 작업을 위한 비용 효율적인 지원을 제공하는 향상된 버전입니다. 정확성과 효율성 간의 균형을 찾아 실시간 상호작용이 필요한 응용 프로그램에 적합합니다."
},
+ "gpt-4.5-preview": {
+ "description": "GPT-4.5 연구 미리보기 버전으로, 지금까지 우리가 만든 가장 크고 강력한 GPT 모델입니다. 광범위한 세계 지식을 보유하고 있으며 사용자 의도를 더 잘 이해하여 창의적인 작업과 자율 계획에서 뛰어난 성능을 발휘합니다. GPT-4.5는 텍스트와 이미지 입력을 수용하고 텍스트 출력을 생성합니다(구조화된 출력 포함). 함수 호출, 배치 API 및 스트리밍 출력을 포함한 주요 개발자 기능을 지원합니다. 창의적이고 개방적인 사고 및 대화가 필요한 작업(예: 글쓰기, 학습 또는 새로운 아이디어 탐색)에서 특히 뛰어난 성능을 보입니다. 지식 기준일은 2023년 10월입니다."
+ },
"gpt-4o": {
"description": "ChatGPT-4o는 동적 모델로, 최신 버전을 유지하기 위해 실시간으로 업데이트됩니다. 강력한 언어 이해 및 생성 능력을 결합하여 고객 서비스, 교육 및 기술 지원을 포함한 대규모 응용 프로그램에 적합합니다."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o는 동적 모델로, 최신 버전을 유지하기 위해 실시간으로 업데이트됩니다. 강력한 언어 이해 및 생성 능력을 결합하여 고객 서비스, 교육 및 기술 지원을 포함한 대규모 응용 프로그램에 적합합니다."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o는 동적 모델로, 최신 버전을 유지하기 위해 실시간으로 업데이트됩니다. 강력한 언어 이해 및 생성 능력을 결합하여 고객 서비스, 교육 및 기술 지원을 포함한 대규모 애플리케이션에 적합합니다."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o 오디오 모델로, 오디오 입력 및 출력을 지원합니다."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini는 OpenAI가 GPT-4 Omni 이후에 출시한 최신 모델로, 텍스트와 이미지를 입력받아 텍스트를 출력합니다. 이 모델은 최신의 소형 모델로, 최근의 다른 최첨단 모델보다 훨씬 저렴하며, GPT-3.5 Turbo보다 60% 이상 저렴합니다. 최첨단의 지능을 유지하면서도 뛰어난 가성비를 자랑합니다. GPT-4o mini는 MMLU 테스트에서 82%의 점수를 기록했으며, 현재 채팅 선호도에서 GPT-4보다 높은 순위를 차지하고 있습니다."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "GPT-4o-mini 실시간 버전으로, 오디오 및 텍스트의 실시간 입력 및 출력을 지원합니다."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "GPT-4o 실시간 버전으로, 오디오 및 텍스트의 실시간 입력 및 출력을 지원합니다."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "GPT-4o 실시간 버전으로, 오디오 및 텍스트의 실시간 입력 및 출력을 지원합니다."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "GPT-4o 실시간 버전으로, 오디오 및 텍스트의 실시간 입력 및 출력을 지원합니다."
+ },
+ "grok-2-1212": {
+ "description": "이 모델은 정확성, 지시 준수 및 다국어 능력에서 개선되었습니다."
+ },
+ "grok-2-vision-1212": {
+ "description": "이 모델은 정확성, 지시 준수 및 다국어 능력에서 개선되었습니다."
+ },
+ "grok-beta": {
+ "description": "Grok 2와 유사한 성능을 가지지만, 더 높은 효율성, 속도 및 기능을 제공합니다."
+ },
+ "grok-vision-beta": {
+ "description": "최신 이미지 이해 모델로, 문서, 차트, 스크린샷 및 사진 등 다양한 시각 정보를 처리할 수 있습니다."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B는 여러 최상위 모델을 통합한 창의성과 지능이 결합된 언어 모델입니다."
},
+ "hunyuan-code": {
+ "description": "혼원 최신 코드 생성 모델로, 200B 고품질 코드 데이터로 증훈된 기초 모델을 기반으로 하며, 6개월간 고품질 SFT 데이터 훈련을 거쳤습니다. 컨텍스트 길이는 8K로 증가하였으며, 다섯 가지 언어의 코드 생성 자동 평가 지표에서 상위에 위치하고 있습니다. 다섯 가지 언어의 10개 항목에서 종합 코드 작업의 인공지능 고품질 평가에서 성능이 1위입니다."
+ },
+ "hunyuan-functioncall": {
+ "description": "혼원 최신 MOE 구조의 FunctionCall 모델로, 고품질 FunctionCall 데이터 훈련을 거쳤으며, 컨텍스트 윈도우는 32K에 도달하고 여러 차원의 평가 지표에서 선두에 있습니다."
+ },
+ "hunyuan-large": {
+ "description": "Hunyuan-large 모델의 총 매개변수 수는 약 389B, 활성화 매개변수 수는 약 52B로, 현재 업계에서 매개변수 규모가 가장 크고 성능이 가장 우수한 Transformer 구조의 오픈 소스 MoE 모델입니다."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "문서 요약 및 문서 질문 응답과 같은 긴 문서 작업을 잘 처리하며, 일반 텍스트 생성 작업도 수행할 수 있는 능력을 갖추고 있습니다. 긴 텍스트의 분석 및 생성에서 뛰어난 성능을 보이며, 복잡하고 상세한 긴 문서 내용 처리 요구에 효과적으로 대응할 수 있습니다."
+ },
+ "hunyuan-lite": {
+ "description": "MOE 구조로 업그레이드되었으며, 컨텍스트 윈도우는 256k로 설정되어 NLP, 코드, 수학, 산업 등 여러 평가 집합에서 많은 오픈 소스 모델을 선도하고 있습니다."
+ },
+ "hunyuan-lite-vision": {
+ "description": "혼원 최신 7B 다중 모달 모델, 컨텍스트 윈도우 32K, 중문 및 영문 환경에서의 다중 모달 대화, 이미지 객체 인식, 문서 표 이해, 다중 모달 수학 등을 지원하며, 여러 차원에서 평가 지표가 7B 경쟁 모델보다 우수합니다."
+ },
+ "hunyuan-pro": {
+ "description": "조 단위 매개변수 규모의 MOE-32K 긴 문서 모델입니다. 다양한 벤치마크에서 절대적인 선두 수준에 도달하며, 복잡한 지시 및 추론, 복잡한 수학 능력을 갖추고 있으며, functioncall을 지원하고 다국어 번역, 금융, 법률, 의료 등 분야에서 최적화된 응용을 제공합니다."
+ },
+ "hunyuan-role": {
+ "description": "혼원 최신 버전의 역할 수행 모델로, 혼원 공식적으로 세밀하게 조정된 훈련을 통해 출시된 역할 수행 모델입니다. 혼원 모델과 역할 수행 시나리오 데이터 세트를 결합하여 증훈하였으며, 역할 수행 시나리오에서 더 나은 기본 성능을 제공합니다."
+ },
+ "hunyuan-standard": {
+ "description": "더 나은 라우팅 전략을 채택하여 부하 균형 및 전문가 수렴 문제를 완화했습니다. 긴 문서의 경우, 대해잡기 지표가 99.9%에 도달했습니다. MOE-32K는 상대적으로 더 높은 가성비를 제공하며, 효과와 가격의 균형을 맞추면서 긴 텍스트 입력 처리를 가능하게 합니다."
+ },
+ "hunyuan-standard-256K": {
+ "description": "더 나은 라우팅 전략을 채택하여 부하 균형 및 전문가 수렴 문제를 완화했습니다. 긴 문서의 경우, 대해잡기 지표가 99.9%에 도달했습니다. MOE-256K는 길이와 효과에서 더욱 발전하여 입력 길이를 크게 확장했습니다."
+ },
+ "hunyuan-standard-vision": {
+ "description": "혼원 최신 다중 모달 모델, 다국어 응답 지원, 중문 및 영문 능력이 균형 잡혀 있습니다."
+ },
+ "hunyuan-translation": {
+ "description": "중국어, 영어, 일본어, 프랑스어, 포르투갈어, 스페인어, 터키어, 러시아어, 아랍어, 한국어, 이탈리아어, 독일어, 베트남어, 말레이어, 인도네시아어 등 15개 언어 간의 상호 번역을 지원하며, 다중 시나리오 번역 평가 집합을 기반으로 한 자동화 평가 COMET 점수를 통해, 10여 개의 일반 언어에서의 상호 번역 능력이 시장의 동급 모델보다 전반적으로 우수합니다."
+ },
+ "hunyuan-translation-lite": {
+ "description": "혼원 번역 모델은 자연어 대화식 번역을 지원하며, 중국어, 영어, 일본어, 프랑스어, 포르투갈어, 스페인어, 터키어, 러시아어, 아랍어, 한국어, 이탈리아어, 독일어, 베트남어, 말레이어, 인도네시아어 등 15개 언어 간의 상호 번역을 지원합니다."
+ },
+ "hunyuan-turbo": {
+ "description": "혼원 최신 세대 대형 언어 모델의 미리보기 버전으로, 새로운 혼합 전문가 모델(MoE) 구조를 채택하여 hunyuan-pro보다 추론 효율이 더 빠르고 성능이 더 뛰어납니다."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "hunyuan-turbo 2024년 11월 20일 고정 버전, hunyuan-turbo와 hunyuan-turbo-latest 사이의 버전."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "이번 버전 최적화: 데이터 지시 스케일링, 모델의 일반화 능력 대폭 향상; 수학, 코드, 논리 추론 능력 대폭 향상; 텍스트 이해 및 단어 이해 관련 능력 최적화; 텍스트 창작 내용 생성 질 최적화."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "일반적인 경험 최적화, NLP 이해, 텍스트 창작, 대화, 지식 질문 응답, 번역, 분야 등; 인간화 향상, 모델의 감정 지능 최적화; 의도가 모호할 때 모델의 능동적인 명확화 능력 향상; 단어 및 구문 분석 관련 문제 처리 능력 향상; 창작의 질과 상호작용성 향상; 다중 회차 경험 향상."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "혼원 차세대 비주얼 언어 플래그십 대형 모델, 새로운 혼합 전문가 모델(MoE) 구조를 채택하여, 이미지 및 텍스트 이해 관련 기본 인식, 콘텐츠 창작, 지식 질문 응답, 분석 추론 등의 능력이 이전 세대 모델에 비해 전반적으로 향상되었습니다."
+ },
+ "hunyuan-vision": {
+ "description": "혼원 최신 다중 모달 모델로, 이미지와 텍스트 입력을 지원하여 텍스트 콘텐츠를 생성합니다."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "혁신적인 오픈 소스 모델 InternLM2.5는 대규모 파라미터를 통해 대화의 지능을 향상시킵니다."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5는 다양한 시나리오에서 스마트 대화 솔루션을 제공합니다."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct 모델은 70B 매개변수를 갖추고 있으며, 대규모 텍스트 생성 및 지시 작업에서 뛰어난 성능을 제공합니다."
+ "internlm2-pro-chat": {
+ "description": "우리가 여전히 유지 관리하는 구버전 모델로, 7B 및 20B와 같은 다양한 모델 매개변수 옵션이 있습니다."
+ },
+ "internlm2.5-latest": {
+ "description": "우리가 최신으로 선보이는 모델 시리즈로, 뛰어난 추론 성능을 자랑하며 1M의 컨텍스트 길이와 더 강력한 지시 따르기 및 도구 호출 기능을 지원합니다."
+ },
+ "internlm3-latest": {
+ "description": "우리의 최신 모델 시리즈는 뛰어난 추론 성능을 가지고 있으며, 동급 오픈 소스 모델 중에서 선두를 달리고 있습니다. 기본적으로 최신 출시된 InternLM3 시리즈 모델을 가리킵니다."
+ },
+ "jina-deepsearch-v1": {
+ "description": "딥 서치는 웹 검색, 독서 및 추론을 결합하여 포괄적인 조사를 수행합니다. 연구 작업을 수용하는 에이전트로 생각할 수 있으며, 광범위한 검색을 수행하고 여러 번 반복한 후에야 답변을 제공합니다. 이 과정은 지속적인 연구, 추론 및 다양한 각도에서 문제를 해결하는 것을 포함합니다. 이는 사전 훈련된 데이터에서 직접 답변을 생성하는 표준 대형 모델 및 일회성 표면 검색에 의존하는 전통적인 RAG 시스템과 근본적으로 다릅니다."
+ },
+ "kimi-latest": {
+ "description": "Kimi 스마트 어시스턴트 제품은 최신 Kimi 대형 모델을 사용하며, 아직 안정되지 않은 기능이 포함될 수 있습니다. 이미지 이해를 지원하며, 요청의 맥락 길이에 따라 8k/32k/128k 모델을 청구 모델로 자동 선택합니다."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM은 학습 과학 원칙에 맞춰 훈련된 실험적이고 특정 작업에 특화된 언어 모델로, 교육 및 학습 환경에서 시스템 지침을 따르며 전문가 멘토 역할을 수행합니다."
+ },
+ "lite": {
+ "description": "Spark Lite는 경량 대형 언어 모델로, 매우 낮은 지연 시간과 효율적인 처리 능력을 갖추고 있으며, 완전히 무료로 제공되고 실시간 온라인 검색 기능을 지원합니다. 빠른 응답 특성 덕분에 저전력 장치에서의 추론 응용 및 모델 미세 조정에서 뛰어난 성능을 발휘하며, 사용자에게 뛰어난 비용 효율성과 스마트한 경험을 제공합니다. 특히 지식 질문 응답, 콘텐츠 생성 및 검색 시나리오에서 두각을 나타냅니다."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B는 더 강력한 AI 추론 능력을 제공하며, 복잡한 응용 프로그램에 적합하고, 많은 계산 처리를 지원하며 효율성과 정확성을 보장합니다."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B는 효율적인 모델로, 빠른 텍스트 생성 능력을 제공하며, 대규모 효율성과 비용 효과성이 필요한 응용 프로그램에 매우 적합합니다."
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct 모델은 8B 매개변수를 갖추고 있으며, 화면 지시 작업의 효율적인 실행을 지원하고 우수한 텍스트 생성 능력을 제공합니다."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "고해상도 이미지에서 탁월한 이미지 추론 능력을 발휘하며, 시각 이해 응용 프로그램에 적합합니다."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Online 모델은 405B 매개변수를 갖추고 있으며, 약 127,000개의 토큰의 컨텍스트 길이를 지원하여 복잡한 온라인 채팅 애플리케이션을 위해 설계되었습니다."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하기 위해 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 보이며, 언어 생성과 시각적 추론 간의 간극을 넘습니다."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chat 모델은 70B 매개변수를 갖추고 있으며, 약 127,000개의 토큰의 컨텍스트 길이를 지원하여 복잡한 오프라인 채팅 작업에 적합합니다."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "시각 이해 에이전트 응용 프로그램에 적합한 고급 이미지 추론 능력입니다."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Online 모델은 70B 매개변수를 갖추고 있으며, 약 127,000개의 토큰의 컨텍스트 길이를 지원하여 대용량 및 다양한 채팅 작업에 적합합니다."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하기 위해 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 보이며, 언어 생성과 시각적 추론 간의 간극을 넘습니다."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chat 모델은 8B 매개변수를 갖추고 있으며, 오프라인 채팅을 위해 설계되어 약 127,000개의 토큰의 컨텍스트 길이를 지원합니다."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3은 Llama 시리즈에서 가장 진보된 다국어 오픈 소스 대형 언어 모델로, 매우 낮은 비용으로 405B 모델의 성능을 경험할 수 있습니다. Transformer 구조를 기반으로 하며, 감독 미세 조정(SFT)과 인간 피드백 강화 학습(RLHF)을 통해 유용성과 안전성을 향상시켰습니다. 이 지시 조정 버전은 다국어 대화를 위해 최적화되어 있으며, 여러 산업 벤치마크에서 많은 오픈 소스 및 폐쇄형 채팅 모델보다 우수한 성능을 보입니다. 지식 마감일은 2023년 12월입니다."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Online 모델은 8B 매개변수를 갖추고 있으며, 약 127,000개의 토큰의 컨텍스트 길이를 지원하여 온라인 채팅을 위해 설계되었습니다."
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 다국어 대형 언어 모델(LLM)은 70B(텍스트 입력/텍스트 출력)에서 사전 학습 및 지침 조정 생성 모델입니다. Llama 3.3의 지침 조정 순수 텍스트 모델은 다국어 대화 사용 사례에 최적화되어 있으며, 많은 오픈 소스 및 폐쇄형 채팅 모델보다 일반 산업 기준에서 우수한 성능을 보입니다."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B는 비할 데 없는 복잡성 처리 능력을 제공하며, 높은 요구 사항을 가진 프로젝트에 맞춤형으로 설계되었습니다."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral은 과학 연구 및 수학 추론을 위해 설계되었으며, 효과적인 계산 능력과 결과 해석을 제공합니다."
},
+ "max-32k": {
+ "description": "Spark Max 32K는 큰 컨텍스트 처리 능력을 갖추고 있으며, 더 강력한 컨텍스트 이해 및 논리 추론 능력을 지원합니다. 32K 토큰의 텍스트 입력을 지원하며, 긴 문서 읽기, 개인 지식 질문 응답 등 다양한 시나리오에 적합합니다."
+ },
"meta-llama-3-70b-instruct": {
"description": "추론, 코딩 및 광범위한 언어 응용 프로그램에서 뛰어난 성능을 발휘하는 강력한 70억 매개변수 모델입니다."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B)는 뛰어난 언어 처리 능력과 우수한 상호작용 경험을 제공합니다."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2는 뛰어난 언어 처리 능력과 뛰어난 상호작용 경험을 제공합니다."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B)는 강력한 채팅 모델로, 복잡한 대화 요구를 지원합니다."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B)는 다국어 지원을 제공하며, 풍부한 분야 지식을 포함합니다."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하도록 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 발휘하며, 언어 생성과 시각 추론 간의 간극을 메웁니다."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하도록 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 발휘하며, 언어 생성과 시각 추론 간의 간극을 메웁니다."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하도록 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 발휘하며, 언어 생성과 시각 추론 간의 간극을 메웁니다."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3은 Llama 시리즈에서 가장 진보된 다국어 오픈 소스 대형 언어 모델로, 매우 낮은 비용으로 405B 모델의 성능을 경험할 수 있습니다. Transformer 구조를 기반으로 하며, 감독 미세 조정(SFT) 및 인간 피드백 강화 학습(RLHF)을 통해 유용성과 안전성을 향상시켰습니다. 그 지시 조정 버전은 다국어 대화를 최적화하여 여러 산업 벤치마크에서 많은 오픈 소스 및 폐쇄형 채팅 모델보다 우수한 성능을 보입니다. 지식 마감일은 2023년 12월입니다."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 다국어 대형 언어 모델(LLM)은 70B(텍스트 입력/텍스트 출력)에서 사전 훈련 및 지시 조정 생성 모델입니다. Llama 3.3 지시 조정의 순수 텍스트 모델은 다국어 대화 사용 사례에 최적화되어 있으며, 일반 산업 기준에서 많은 사용 가능한 오픈 소스 및 폐쇄형 채팅 모델보다 우수한 성능을 보입니다."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하도록 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 발휘하며, 언어 생성과 시각 추론 간의 간극을 메웁니다."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite는 효율성과 낮은 지연 시간이 필요한 환경에 적합합니다."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "405B Llama 3.1 Turbo 모델은 대규모 데이터 처리를 위한 초대용량의 컨텍스트 지원을 제공하며, 초대규모 인공지능 애플리케이션에서 뛰어난 성능을 발휘합니다."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1은 Meta에서 출시한 선도적인 모델로, 최대 405B 매개변수를 지원하며 복잡한 대화, 다국어 번역 및 데이터 분석 분야에 적용됩니다."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B는 다국어의 효율적인 대화 지원을 제공합니다."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct는 고품질 대화 시나리오에 최적화되어 있으며, 많은 폐쇄형 모델보다 우수한 성능을 보입니다."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct는 Meta에서 새롭게 출시한 버전으로, 고품질 대화 생성을 위해 최적화되어 있으며, 많은 선도적인 폐쇄형 모델을 초월합니다."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct는 고품질 대화를 위해 설계되었으며, 인간 평가에서 뛰어난 성능을 보여주고, 특히 높은 상호작용 시나리오에 적합합니다."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1은 다국어 지원을 제공하며, 업계 최고의 생성 모델 중 하나입니다."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하기 위해 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 보이며, 언어 생성과 시각적 추론 간의 간극을 넘습니다."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2는 시각 및 텍스트 데이터를 결합한 작업을 처리하기 위해 설계되었습니다. 이미지 설명 및 시각적 질문 응답과 같은 작업에서 뛰어난 성능을 보이며, 언어 생성과 시각적 추론 간의 간극을 넘습니다."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3은 Llama 시리즈에서 가장 진보된 다국어 오픈 소스 대형 언어 모델로, 매우 낮은 비용으로 405B 모델의 성능을 경험할 수 있습니다. Transformer 구조를 기반으로 하며, 감독 미세 조정(SFT)과 인간 피드백 강화 학습(RLHF)을 통해 유용성과 안전성을 향상시켰습니다. 이 지시 조정 버전은 다국어 대화를 위해 최적화되어 있으며, 여러 산업 벤치마크에서 많은 오픈 소스 및 폐쇄형 채팅 모델보다 우수한 성능을 보입니다. 지식 마감일은 2023년 12월입니다."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3은 Llama 시리즈에서 가장 진보된 다국어 오픈 소스 대형 언어 모델로, 매우 낮은 비용으로 405B 모델의 성능을 경험할 수 있습니다. Transformer 구조를 기반으로 하며, 감독 미세 조정(SFT)과 인간 피드백 강화 학습(RLHF)을 통해 유용성과 안전성을 향상시켰습니다. 이 지시 조정 버전은 다국어 대화를 위해 최적화되어 있으며, 여러 산업 벤치마크에서 많은 오픈 소스 및 폐쇄형 채팅 모델보다 우수한 성능을 보입니다. 지식 마감일은 2023년 12월입니다."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct는 Llama 3.1 Instruct 모델 중 가장 크고 강력한 모델로, 고도로 발전된 대화 추론 및 합성 데이터 생성 모델입니다. 특정 분야에서 전문적인 지속적 사전 훈련 또는 미세 조정의 기초로도 사용될 수 있습니다. Llama 3.1이 제공하는 다국어 대형 언어 모델(LLMs)은 8B, 70B 및 405B 크기의 사전 훈련된 지시 조정 생성 모델로 구성되어 있습니다(텍스트 입력/출력). Llama 3.1 지시 조정 텍스트 모델(8B, 70B, 405B)은 다국어 대화 사용 사례에 최적화되어 있으며, 일반 산업 벤치마크 테스트에서 많은 오픈 소스 채팅 모델을 초과했습니다. Llama 3.1은 다양한 언어의 상업적 및 연구 용도로 설계되었습니다. 지시 조정 텍스트 모델은 비서와 유사한 채팅에 적합하며, 사전 훈련 모델은 다양한 자연어 생성 작업에 적응할 수 있습니다. Llama 3.1 모델은 또한 모델의 출력을 활용하여 다른 모델을 개선하는 것을 지원하며, 합성 데이터 생성 및 정제에 사용될 수 있습니다. Llama 3.1은 최적화된 변압기 아키텍처를 사용한 자기 회귀 언어 모델입니다. 조정된 버전은 감독 미세 조정(SFT) 및 인간 피드백이 포함된 강화 학습(RLHF)을 사용하여 인간의 도움 및 안전성 선호에 부합하도록 설계되었습니다."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3은 개발자, 연구자 및 기업을 위한 오픈 대형 언어 모델(LLM)로, 생성 AI 아이디어를 구축하고 실험하며 책임감 있게 확장하는 데 도움을 주기 위해 설계되었습니다. 전 세계 커뮤니티 혁신의 기초 시스템의 일환으로, 계산 능력과 자원이 제한된 환경, 엣지 장치 및 더 빠른 훈련 시간에 매우 적합합니다."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B는 Microsoft AI의 최신 경량 모델로, 기존 오픈 소스 선도 모델의 성능에 근접합니다."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "합성 데이터 생성, 지식 증류 및 추론을 지원하는 고급 LLM으로, 챗봇, 프로그래밍 및 특정 분야 작업에 적합합니다."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "복잡한 대화를 가능하게 하며, 뛰어난 맥락 이해, 추론 능력 및 텍스트 생성 능력을 갖추고 있습니다."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "언어 이해, 뛰어난 추론 능력 및 텍스트 생성 능력을 갖춘 고급 최첨단 모델입니다."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "이미지에서 고품질 추론을 수행하는 최첨단 비주얼-언어 모델입니다."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "언어 이해, 뛰어난 추론 능력 및 텍스트 생성 능력을 갖춘 최첨단 소형 언어 모델입니다."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "언어 이해, 뛰어난 추론 능력 및 텍스트 생성 능력을 갖춘 최첨단 소형 언어 모델입니다."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "이미지에서 고품질 추론을 수행하는 최첨단 비주얼-언어 모델입니다."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "추론, 수학, 상식 및 함수 호출에 능숙한 고급 LLM입니다."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2는 Microsoft AI가 제공하는 언어 모델로, 복잡한 대화, 다국어, 추론 및 스마트 어시스턴트 분야에서 특히 뛰어난 성능을 보입니다."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B는 마이크로소프트 AI의 최첨단 Wizard 모델로, 매우 경쟁력 있는 성능을 보여줍니다."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V는 OpenBMB에서 출시한 차세대 다중 모달 대형 모델로, 뛰어난 OCR 인식 및 다중 모달 이해 능력을 갖추고 있으며, 다양한 응용 프로그램을 지원합니다."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B는 Mistral의 세계적 수준의 엣지 모델입니다."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B는 Mistral의 뛰어난 가성비를 자랑하는 엣지 모델입니다."
+ },
"mistral": {
"description": "Mistral은 Mistral AI에서 출시한 7B 모델로, 변화하는 언어 처리 요구에 적합합니다."
},
"mistral-large": {
"description": "Mixtral Large는 Mistral의 플래그십 모델로, 코드 생성, 수학 및 추론 능력을 결합하여 128k 컨텍스트 창을 지원합니다."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407)는 최첨단 추론, 지식 및 코딩 능력을 갖춘 고급 대형 언어 모델(LLM)입니다."
- },
"mistral-large-latest": {
"description": "Mistral Large는 플래그십 대형 모델로, 다국어 작업, 복잡한 추론 및 코드 생성에 능숙하여 고급 응용 프로그램에 이상적인 선택입니다."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3는 효율적인 계산 능력과 자연어 이해를 제공하며, 광범위한 응용에 적합합니다."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B는 컴팩트하지만 높은 성능의 모델로, 분류 및 텍스트 생성과 같은 간단한 작업을 잘 처리하며, 좋은 추론 능력을 갖추고 있습니다."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B)는 슈퍼 대형 언어 모델로, 극도의 처리 요구를 지원합니다."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B는 일반 텍스트 작업을 위한 사전 훈련된 희소 혼합 전문가 모델입니다."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B는 여러 파라미터를 활용하여 추론 속도를 높이는 희소 전문가 모델입니다. 다국어 및 코드 생성 작업 처리에 적합합니다."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct는 속도 최적화와 긴 컨텍스트 지원을 갖춘 고성능 산업 표준 모델입니다."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K는 초장기 컨텍스트 처리 능력을 갖춘 모델로, 초장문 생성을 위해 설계되었으며, 복잡한 생성 작업 요구를 충족하고 최대 128,000개의 토큰을 처리할 수 있어, 연구, 학술 및 대형 문서 생성 등 응용 시나리오에 매우 적합합니다."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Kimi 시각 모델(예: moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 등)은 이미지 내용을 이해할 수 있으며, 이미지 텍스트, 이미지 색상 및 물체 형태 등을 포함합니다."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K는 중간 길이의 컨텍스트 처리 능력을 제공하며, 32,768개의 토큰을 처리할 수 있어, 다양한 장문 및 복잡한 대화 생성을 위해 특히 적합하며, 콘텐츠 생성, 보고서 작성 및 대화 시스템 등 분야에 활용됩니다."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Kimi 시각 모델(예: moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 등)은 이미지 내용을 이해할 수 있으며, 이미지 텍스트, 이미지 색상 및 물체 형태 등을 포함합니다."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K는 짧은 텍스트 작업 생성을 위해 설계되었으며, 효율적인 처리 성능을 갖추고 있어 8,192개의 토큰을 처리할 수 있으며, 짧은 대화, 속기 및 빠른 콘텐츠 생성에 매우 적합합니다."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Kimi 시각 모델(예: moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 등)은 이미지 내용을 이해할 수 있으며, 이미지 텍스트, 이미지 색상 및 물체 형태 등을 포함합니다."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto는 현재 맥락에서 사용되는 토큰 수에 따라 적합한 모델을 선택할 수 있습니다."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B는 Nous Hermes 2의 업그레이드 버전으로, 최신 내부 개발 데이터 세트를 포함하고 있습니다."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B는 NVIDIA가 맞춤 제작한 대규모 언어 모델로, LLM이 생성한 응답이 사용자 쿼리에 얼마나 도움이 되는지를 향상시키기 위해 설계되었습니다. 이 모델은 Arena Hard, AlpacaEval 2 LC 및 GPT-4-Turbo MT-Bench와 같은 벤치마크 테스트에서 뛰어난 성능을 보였으며, 2024년 10월 1일 기준으로 모든 자동 정렬 벤치마크 테스트에서 1위를 차지했습니다. 이 모델은 RLHF(특히 REINFORCE), Llama-3.1-Nemotron-70B-Reward 및 HelpSteer2-Preference 프롬프트를 사용하여 Llama-3.1-70B-Instruct 모델을 기반으로 훈련되었습니다."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "비교할 수 없는 정확성과 효율성을 제공하는 독특한 언어 모델입니다."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct는 NVIDIA가 맞춤 제작한 대형 언어 모델로, LLM이 생성한 응답의 유용성을 향상시키기 위해 설계되었습니다."
+ },
+ "o1": {
+ "description": "고급 추론 및 복잡한 문제 해결에 중점을 두며, 수학 및 과학 작업을 포함합니다. 깊이 있는 컨텍스트 이해와 에이전트 작업 흐름이 필요한 애플리케이션에 매우 적합합니다."
+ },
"o1-mini": {
"description": "o1-mini는 프로그래밍, 수학 및 과학 응용 프로그램을 위해 설계된 빠르고 경제적인 추론 모델입니다. 이 모델은 128K의 컨텍스트와 2023년 10월의 지식 기준일을 가지고 있습니다."
},
"o1-preview": {
"description": "o1은 OpenAI의 새로운 추론 모델로, 광범위한 일반 지식이 필요한 복잡한 작업에 적합합니다. 이 모델은 128K의 컨텍스트와 2023년 10월의 지식 기준일을 가지고 있습니다."
},
+ "o3-mini": {
+ "description": "o3-mini는 최신 소형 추론 모델로, o1-mini와 동일한 비용과 지연 목표에서 높은 지능을 제공합니다."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba는 코드 생성을 전문으로 하는 Mamba 2 언어 모델로, 고급 코드 및 추론 작업에 강력한 지원을 제공합니다."
},
@@ -745,7 +1466,7 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B는 희소 전문가 모델로, 여러 매개변수를 활용하여 추론 속도를 높이며, 다국어 및 코드 생성 작업 처리에 적합합니다."
},
- "openai/gpt-4o-2024-08-06": {
+ "openai/gpt-4o": {
"description": "ChatGPT-4o는 동적 모델로, 최신 버전을 유지하기 위해 실시간으로 업데이트됩니다. 강력한 언어 이해 및 생성 능력을 결합하여 고객 서비스, 교육 및 기술 지원을 포함한 대규모 응용 프로그램에 적합합니다."
},
"openai/gpt-4o-mini": {
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Pixtral 모델은 차트 및 이미지 이해, 문서 질문 응답, 다중 모드 추론 및 지시 준수와 같은 작업에서 강력한 능력을 발휘하며, 자연 해상도와 가로 세로 비율로 이미지를 입력할 수 있고, 최대 128K 토큰의 긴 컨텍스트 창에서 임의의 수의 이미지를 처리할 수 있습니다."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large는 1240억 개의 매개변수를 가진 오픈 소스 다중 모달 모델로, Mistral Large 2를 기반으로 구축되었습니다. 이는 우리의 다중 모달 가족 중 두 번째 모델로, 최첨단 수준의 이미지 이해 능력을 보여줍니다."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K는 매우 큰 컨텍스트 처리 능력을 갖추고 있으며, 최대 128K의 컨텍스트 정보를 처리할 수 있습니다. 특히 전체 분석 및 장기 논리 연관 처리가 필요한 긴 문서 콘텐츠에 적합하며, 복잡한 텍스트 커뮤니케이션에서 매끄럽고 일관된 논리와 다양한 인용 지원을 제공합니다."
+ },
+ "qvq-72b-preview": {
+ "description": "QVQ 모델은 Qwen 팀이 개발한 실험적 연구 모델로, 시각적 추론 능력 향상에 중점을 두고 있으며, 특히 수학적 추론 분야에서 두드러진 성과를 보입니다."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "통의 천문 코드 모델입니다."
+ },
"qwen-coder-turbo-latest": {
"description": "통의 천문 코드 모델입니다."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "통의 천문 수학 모델은 수학 문제 해결을 위해 특별히 설계된 언어 모델입니다."
},
+ "qwen-max": {
+ "description": "통의천문 천억 수준 초대형 언어 모델로, 중국어, 영어 등 다양한 언어 입력을 지원하며, 현재 통의천문 2.5 제품 버전 뒤의 API 모델입니다."
+ },
"qwen-max-latest": {
"description": "통의 천문 1000억급 초대규모 언어 모델로, 중국어, 영어 등 다양한 언어 입력을 지원하며, 현재 통의 천문 2.5 제품 버전의 API 모델입니다."
},
+ "qwen-omni-turbo-latest": {
+ "description": "Qwen-Omni 시리즈 모델은 비디오, 오디오, 이미지, 텍스트 등 다양한 모드의 데이터를 입력으로 지원하며, 오디오와 텍스트를 출력합니다."
+ },
+ "qwen-plus": {
+ "description": "통의천문 초대형 언어 모델의 강화 버전으로, 중국어, 영어 등 다양한 언어 입력을 지원합니다."
+ },
"qwen-plus-latest": {
"description": "통의 천문 초대규모 언어 모델의 강화판으로, 중국어, 영어 등 다양한 언어 입력을 지원합니다."
},
+ "qwen-turbo": {
+ "description": "통의천문 초대형 언어 모델로, 중국어, 영어 등 다양한 언어 입력을 지원합니다."
+ },
"qwen-turbo-latest": {
"description": "통의 천문 초대규모 언어 모델로, 중국어, 영어 등 다양한 언어 입력을 지원합니다."
},
"qwen-vl-chat-v1": {
"description": "통의천문 VL은 다중 이미지, 다중 회차 질문 응답, 창작 등 유연한 상호작용 방식을 지원하는 모델입니다."
},
- "qwen-vl-max": {
- "description": "통의천문 초대규모 시각 언어 모델로, 강화 버전보다 시각적 추론 능력과 지시 준수 능력을 다시 향상시켜 더 높은 시각적 인식 및 인지 수준을 제공합니다."
+ "qwen-vl-max-latest": {
+ "description": "통의천문 초대규모 비주얼 언어 모델. 강화판에 비해 시각적 추론 능력과 지시 준수 능력을 다시 한 번 향상시켜, 더 높은 시각적 인식과 인지 수준을 제공합니다."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "통의천문OCR은 문서, 표, 시험지, 손글씨 등 다양한 유형의 이미지에서 텍스트 추출 능력에 중점을 둔 전용 모델입니다. 여러 언어를 인식할 수 있으며, 현재 지원되는 언어는 중국어, 영어, 프랑스어, 일본어, 한국어, 독일어, 러시아어, 이탈리아어, 베트남어, 아랍어입니다."
},
- "qwen-vl-plus": {
- "description": "통의천문 대규모 시각 언어 모델의 강화 버전으로, 세부 사항 인식 능력과 문자 인식 능력을 크게 향상시켰으며, 백만 화소 이상의 해상도와 임의의 가로 세로 비율의 이미지를 지원합니다."
+ "qwen-vl-plus-latest": {
+ "description": "통의천문 대규모 비주얼 언어 모델 강화판. 세부 사항 인식 능력과 문자 인식 능력을 크게 향상시켰으며, 백만 화소 이상의 해상도와 임의의 가로 세로 비율의 이미지를 지원합니다."
},
"qwen-vl-v1": {
"description": "Qwen-7B 언어 모델로 초기화된 모델로, 이미지 모델을 추가하여 이미지 입력 해상도가 448인 사전 훈련 모델입니다."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2는 새로운 Qwen 대형 언어 모델 시리즈입니다. Qwen2 7B는 트랜스포머 기반 모델로, 언어 이해, 다국어 능력, 프로그래밍, 수학 및 추론에서 뛰어난 성능을 보여줍니다."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2는 더 강력한 이해 및 생성 능력을 갖춘 새로운 대형 언어 모델 시리즈입니다."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL은 Qwen-VL 모델의 최신 반복 버전으로, MathVista, DocVQA, RealWorldQA 및 MTVQA와 같은 시각적 이해 벤치마크 테스트에서 최첨단 성능을 달성했습니다. Qwen2-VL은 20분 이상의 비디오를 이해할 수 있으며, 고품질의 비디오 기반 질문 응답, 대화 및 콘텐츠 생성에 사용됩니다. 또한 복잡한 추론 및 의사 결정 능력을 갖추고 있어, 모바일 장치, 로봇 등과 통합되어 시각적 환경 및 텍스트 지침에 따라 자동으로 작업을 수행할 수 있습니다. 영어와 중국어 외에도 Qwen2-VL은 이제 대부분의 유럽 언어, 일본어, 한국어, 아랍어 및 베트남어 등 다양한 언어의 텍스트를 이해할 수 있습니다."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct는 알리바바 클라우드에서 발표한 최신 대형 언어 모델 시리즈 중 하나입니다. 이 72B 모델은 코딩 및 수학 등 분야에서 현저한 개선된 능력을 가지고 있습니다. 이 모델은 또한 29개 이상의 언어를 포함한 다국어 지원을 제공하며, 지침 준수, 구조화된 데이터 이해 및 구조화된 출력 생성(특히 JSON)에서 현저한 향상을 보였습니다."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct는 알리바바 클라우드에서 발표한 최신 대형 언어 모델 시리즈 중 하나입니다. 이 32B 모델은 코딩 및 수학 등 분야에서 현저한 개선된 능력을 가지고 있습니다. 이 모델은 29개 이상의 언어를 포함한 다국어 지원을 제공하며, 지침 준수, 구조화된 데이터 이해 및 구조화된 출력 생성(특히 JSON)에서 현저한 향상을 보였습니다."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "중국어와 영어를 위한 LLM으로, 언어, 프로그래밍, 수학, 추론 등 다양한 분야를 다룹니다."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "코드 생성, 추론 및 수정 지원을 위한 고급 LLM으로, 주요 프로그래밍 언어를 포함합니다."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "32K 컨텍스트 길이를 지원하는 강력한 중형 코드 모델로, 다국어 프로그래밍에 능숙합니다."
+ },
"qwen2": {
"description": "Qwen2는 Alibaba의 차세대 대규모 언어 모델로, 뛰어난 성능으로 다양한 응용 요구를 지원합니다."
},
+ "qwen2.5": {
+ "description": "Qwen2.5는 Alibaba의 차세대 대규모 언어 모델로, 뛰어난 성능으로 다양한 응용 요구를 지원합니다."
+ },
"qwen2.5-14b-instruct": {
"description": "통의 천문 2.5 외부 오픈 소스 14B 규모 모델입니다."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "통의천문2.5의 외부 오픈 소스 72B 규모 모델입니다."
+ },
"qwen2.5-32b-instruct": {
"description": "통의 천문 2.5 외부 오픈 소스 32B 규모 모델입니다."
},
@@ -824,13 +1599,16 @@
"description": "통의 천문 2.5 외부 오픈 소스 7B 규모 모델입니다."
},
"qwen2.5-coder-1.5b-instruct": {
+ "description": "통의천문 코드 모델 오픈 소스 버전입니다."
+ },
+ "qwen2.5-coder-32b-instruct": {
"description": "통의 천문 코드 모델 오픈 소스 버전입니다."
},
"qwen2.5-coder-7b-instruct": {
"description": "통의 천문 코드 모델 오픈 소스 버전입니다."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Qwen-Math 모델은 강력한 수학 문제 해결 능력을 가지고 있습니다."
+ "description": "Qwen-Math 모델은 강력한 수학 문제 해결 능력을 갖추고 있습니다."
},
"qwen2.5-math-72b-instruct": {
"description": "Qwen-Math 모델은 강력한 수학 문제 해결 능력을 가지고 있습니다."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Qwen-Math 모델은 강력한 수학 문제 해결 능력을 가지고 있습니다."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "지시 따르기, 수학, 문제 해결, 코드 전반적인 향상, 모든 사물 인식 능력 향상, 다양한 형식의 시각적 요소를 직접 정확하게 위치 지정할 수 있으며, 최대 10분 길이의 긴 비디오 파일을 이해하고 초 단위의 사건 시점을 위치 지정할 수 있습니다. 시간의 선후와 속도를 이해할 수 있으며, 분석 및 위치 지정 능력을 기반으로 OS 또는 모바일 에이전트를 조작할 수 있습니다. 주요 정보 추출 능력과 Json 형식 출력 능력이 뛰어나며, 이 버전은 72B 버전으로, 이 시리즈에서 가장 강력한 버전입니다."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "지시 따르기, 수학, 문제 해결, 코드 전반적인 향상, 모든 사물 인식 능력 향상, 다양한 형식의 시각적 요소를 직접 정확하게 위치 지정할 수 있으며, 최대 10분 길이의 긴 비디오 파일을 이해하고 초 단위의 사건 시점을 위치 지정할 수 있습니다. 시간의 선후와 속도를 이해할 수 있으며, 분석 및 위치 지정 능력을 기반으로 OS 또는 모바일 에이전트를 조작할 수 있습니다. 주요 정보 추출 능력과 Json 형식 출력 능력이 뛰어나며, 이 버전은 72B 버전으로, 이 시리즈에서 가장 강력한 버전입니다."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5는 Alibaba의 차세대 대규모 언어 모델로, 뛰어난 성능으로 다양한 응용 요구를 지원합니다."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5는 Alibaba의 차세대 대규모 언어 모델로, 뛰어난 성능으로 다양한 응용 요구를 지원합니다."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5는 Alibaba의 차세대 대규모 언어 모델로, 뛰어난 성능으로 다양한 응용 요구를 지원합니다."
+ },
"qwen2:0.5b": {
"description": "Qwen2는 Alibaba의 차세대 대규모 언어 모델로, 뛰어난 성능으로 다양한 응용 요구를 지원합니다."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2는 Alibaba의 차세대 대규모 언어 모델로, 뛰어난 성능으로 다양한 응용 요구를 지원합니다."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini는 컴팩트한 LLM으로, GPT-3.5보다 성능이 우수하며, 강력한 다국어 능력을 갖추고 있어 영어와 한국어를 지원하며, 효율적이고 소형 솔루션을 제공합니다."
+ "qwq": {
+ "description": "QwQ는 AI 추론 능력을 향상시키는 데 중점을 둔 실험 연구 모델입니다."
+ },
+ "qwq-32b": {
+ "description": "Qwen2.5-32B 모델을 기반으로 훈련된 QwQ 추론 모델로, 강화 학습을 통해 모델의 추론 능력을 크게 향상시켰습니다. 모델의 수학 코드 등 핵심 지표(AIME 24/25, LiveCodeBench) 및 일부 일반 지표(IFEval, LiveBench 등)는 DeepSeek-R1 풀 버전 수준에 도달했으며, 모든 지표는 동일하게 Qwen2.5-32B를 기반으로 한 DeepSeek-R1-Distill-Qwen-32B를 크게 초과합니다."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja)는 Solar Mini의 능력을 확장하여 일본어에 중점을 두고 있으며, 영어와 한국어 사용에서도 효율적이고 뛰어난 성능을 유지합니다."
+ "qwq-32b-preview": {
+ "description": "QwQ 모델은 Qwen 팀이 개발한 실험적 연구 모델로, AI 추론 능력을 향상시키는 데 중점을 두고 있습니다."
+ },
+ "qwq-plus-latest": {
+ "description": "Qwen2.5 모델을 기반으로 훈련된 QwQ 추론 모델로, 강화 학습을 통해 모델의 추론 능력을 크게 향상시켰습니다. 모델의 수학 코드 등 핵심 지표(AIME 24/25, LiveCodeBench) 및 일부 일반 지표(IFEval, LiveBench 등)는 DeepSeek-R1 풀 버전 수준에 도달했습니다."
+ },
+ "r1-1776": {
+ "description": "R1-1776은 DeepSeek R1 모델의 한 버전으로, 후속 훈련을 거쳐 검토되지 않은 편향 없는 사실 정보를 제공합니다."
+ },
+ "solar-mini": {
+ "description": "Solar Mini는 컴팩트한 LLM으로, GPT-3.5보다 성능이 우수하며, 강력한 다국어 능력을 갖추고 있어 영어와 한국어를 지원하며, 효율적이고 소형의 솔루션을 제공합니다."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja)는 Solar Mini의 능력을 확장하여 일본어에 집중하며, 영어와 한국어 사용에서도 효율적이고 뛰어난 성능을 유지합니다."
},
"solar-pro": {
"description": "Solar Pro는 Upstage에서 출시한 고지능 LLM으로, 단일 GPU의 지시 추적 능력에 중점을 두고 있으며, IFEval 점수가 80 이상입니다. 현재 영어를 지원하며, 정식 버전은 2024년 11월에 출시될 예정이며, 언어 지원 및 컨텍스트 길이를 확장할 계획입니다."
},
+ "sonar": {
+ "description": "검색 맥락 기반의 경량 검색 제품으로, Sonar Pro보다 더 빠르고 저렴합니다."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research는 포괄적인 전문가 수준의 연구를 수행하고 이를 접근 가능하고 실행 가능한 보고서로 통합합니다."
+ },
+ "sonar-pro": {
+ "description": "고급 쿼리 및 후속 작업을 지원하는 검색 맥락 기반의 고급 검색 제품입니다."
+ },
+ "sonar-reasoning": {
+ "description": "DeepSeek 추론 모델이 지원하는 새로운 API 제품입니다."
+ },
+ "sonar-reasoning-pro": {
+ "description": "DeepSeek 추론 모델이 지원하는 새로운 API 제품입니다."
+ },
"step-1-128k": {
"description": "성능과 비용의 균형을 맞추어 일반적인 시나리오에 적합합니다."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "고속 모델로, 실시간 대화에 적합합니다."
},
+ "step-1.5v-mini": {
+ "description": "이 모델은 강력한 비디오 이해 능력을 가지고 있습니다."
+ },
+ "step-1o-turbo-vision": {
+ "description": "이 모델은 강력한 이미지 이해 능력을 가지고 있으며, 수리 및 코드 분야에서 1o보다 우수합니다. 모델은 1o보다 더 작고, 출력 속도가 더 빠릅니다."
+ },
+ "step-1o-vision-32k": {
+ "description": "이 모델은 강력한 이미지 이해 능력을 가지고 있습니다. step-1v 시리즈 모델에 비해 더 강력한 시각 성능을 자랑합니다."
+ },
"step-1v-32k": {
"description": "시각 입력을 지원하여 다중 모달 상호작용 경험을 강화합니다."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "대규모 컨텍스트 상호작용을 지원하며, 복잡한 대화 시나리오에 적합합니다."
},
+ "step-2-mini": {
+ "description": "신세대 자체 개발 Attention 아키텍처인 MFA를 기반으로 한 초고속 대형 모델로, 매우 낮은 비용으로 step1과 유사한 효과를 달성하면서도 더 높은 처리량과 더 빠른 응답 지연을 유지합니다. 일반적인 작업을 처리할 수 있으며, 코드 능력에 있어 특장점을 가지고 있습니다."
+ },
"taichu_llm": {
"description": "자이동 태초 언어 대모델은 뛰어난 언어 이해 능력과 텍스트 창작, 지식 질문 응답, 코드 프로그래밍, 수학 계산, 논리 추론, 감정 분석, 텍스트 요약 등의 능력을 갖추고 있습니다. 혁신적으로 대규모 데이터 사전 훈련과 다원적 풍부한 지식을 결합하여 알고리즘 기술을 지속적으로 다듬고, 방대한 텍스트 데이터에서 어휘, 구조, 문법, 의미 등의 새로운 지식을 지속적으로 흡수하여 모델 성능을 지속적으로 진화시킵니다. 사용자에게 보다 편리한 정보와 서비스, 그리고 더 지능적인 경험을 제공합니다."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V는 이미지 이해, 지식 이전, 논리적 귀속 등의 능력을 통합하여, 텍스트와 이미지 질문 응답 분야에서 뛰어난 성능을 발휘합니다."
+ "taichu_vl": {
+ "description": "이미지 이해, 지식 이전, 논리 귀속 등의 능력을 통합하여, 이미지-텍스트 질문 응답 분야에서 뛰어난 성능을 보입니다."
+ },
+ "text-embedding-3-large": {
+ "description": "가장 강력한 벡터화 모델로, 영어 및 비영어 작업에 적합합니다."
+ },
+ "text-embedding-3-small": {
+ "description": "효율적이고 경제적인 차세대 임베딩 모델로, 지식 검색, RAG 애플리케이션 등 다양한 상황에 적합합니다."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "지프 AI가 발표한 GLM-4 시리즈 최신 세대의 사전 훈련 모델의 오픈 소스 버전입니다."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B)는 효율적인 전략과 모델 아키텍처를 통해 향상된 계산 능력을 제공합니다."
},
+ "tts-1": {
+ "description": "최신 텍스트 음성 변환 모델로, 실시간 상황에 최적화된 속도를 제공합니다."
+ },
+ "tts-1-hd": {
+ "description": "최신 텍스트 음성 변환 모델로, 품질을 최적화했습니다."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B)는 세밀한 지시 작업에 적합하며, 뛰어난 언어 처리 능력을 제공합니다."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet는 업계 표준을 향상시켰으며, 경쟁 모델과 Claude 3 Opus를 초월하는 성능을 보여주고, 광범위한 평가에서 뛰어난 성과를 보이며, 중간 수준 모델의 속도와 비용을 갖추고 있습니다."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 소네트는 Anthropic의 가장 빠른 차세대 모델입니다. Claude 3 하이쿠와 비교할 때, Claude 3.7 소네트는 모든 기술에서 향상되었으며, 많은 지능 기준 테스트에서 이전 세대의 가장 큰 모델인 Claude 3 오푸스를 초월했습니다."
+ },
+ "whisper-1": {
+ "description": "범용 음성 인식 모델로, 다국어 음성 인식, 음성 번역 및 언어 인식을 지원합니다."
+ },
"wizardlm2": {
"description": "WizardLM 2는 Microsoft AI에서 제공하는 언어 모델로, 복잡한 대화, 다국어, 추론 및 스마트 어시스턴트 분야에서 특히 뛰어난 성능을 발휘합니다."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "초고성능, 뛰어난 성능. 성능과 추론 속도, 비용을 기준으로 균형 잡힌 고정밀 조정을 수행합니다."
},
+ "yi-lightning": {
+ "description": "최신 고성능 모델로, 고품질 출력을 보장하며, 추론 속도를 크게 향상시킵니다."
+ },
+ "yi-lightning-lite": {
+ "description": "경량 버전으로, yi-lightning 사용을 권장합니다."
+ },
"yi-medium": {
"description": "중형 모델 업그레이드 및 미세 조정으로, 능력이 균형 잡히고 가성비가 높습니다. 지시 따르기 능력을 깊이 최적화하였습니다."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "복잡한 시각 작업 모델로, 고성능 이미지 이해 및 분석 능력을 제공합니다."
+ },
+ "yi-vision-v2": {
+ "description": "복잡한 시각적 작업 모델로, 여러 이미지를 기반으로 한 고성능 이해 및 분석 능력을 제공합니다."
}
}
diff --git a/DigitalHumanWeb/locales/ko-KR/plugin.json b/DigitalHumanWeb/locales/ko-KR/plugin.json
index 9862528..4b0d4c1 100644
--- a/DigitalHumanWeb/locales/ko-KR/plugin.json
+++ b/DigitalHumanWeb/locales/ko-KR/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "플러그인 {{name}} 다시 설치 중 오류가 발생했습니다.",
"urlError": "이 링크는 JSON 형식의 내용을 반환하지 않습니다. 유효한 링크인지 확인하세요."
},
+ "inspector": {
+ "args": "매개변수 목록 보기",
+ "pluginRender": "플러그인 인터페이스 보기"
+ },
"list": {
"item": {
"deprecated.title": "삭제됨",
@@ -130,6 +134,34 @@
"plugin": "플러그인 실행 중..."
},
"pluginList": "플러그인 목록",
+ "search": {
+ "config": {
+ "addKey": "키 추가",
+ "close": "삭제",
+ "confirm": "구성이 완료되었습니다. 다시 시도하십시오."
+ },
+ "crawPages": {
+ "crawling": "링크 인식 중",
+ "detail": {
+ "preview": "미리보기",
+ "raw": "원본 텍스트",
+ "tooLong": "텍스트 내용이 너무 깁니다. 대화 맥락은 앞의 {{characters}}자만 유지되며, 초과 부분은 대화 맥락에 포함되지 않습니다."
+ },
+ "meta": {
+ "crawler": "크롤링 모드",
+ "words": "문자 수"
+ }
+ },
+ "searchxng": {
+ "baseURL": "입력하십시오",
+ "description": "SearchXNG의 URL을 입력하면 인터넷 검색을 시작할 수 있습니다.",
+ "keyPlaceholder": "키를 입력하십시오",
+ "title": "SearchXNG 검색 엔진 구성",
+ "unconfiguredDesc": "관리자에게 연락하여 SearchXNG 검색 엔진 구성을 완료하십시오. 인터넷 검색을 시작할 수 있습니다.",
+ "unconfiguredTitle": "SearchXNG 검색 엔진이 아직 구성되지 않았습니다."
+ },
+ "title": "인터넷 검색"
+ },
"setting": "플러그인 설정",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/ko-KR/portal.json b/DigitalHumanWeb/locales/ko-KR/portal.json
index bb9c1a7..4e95480 100644
--- a/DigitalHumanWeb/locales/ko-KR/portal.json
+++ b/DigitalHumanWeb/locales/ko-KR/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "플러그인",
- "actions": {
- "genAiMessage": "AI 메시지 생성",
- "summary": "요약",
- "summaryTooltip": "현재 콘텐츠를 요약합니다"
- },
"artifacts": {
"display": {
"code": "코드",
diff --git a/DigitalHumanWeb/locales/ko-KR/providers.json b/DigitalHumanWeb/locales/ko-KR/providers.json
index 54f6bdc..2ea69de 100644
--- a/DigitalHumanWeb/locales/ko-KR/providers.json
+++ b/DigitalHumanWeb/locales/ko-KR/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs는 기업을 위해 기본 모델과 인공지능 시스템을 구축하여 생성적 인공지능의 생산적 활용을 가속화합니다."
+ },
"ai360": {
"description": "360 AI는 360 회사가 출시한 AI 모델 및 서비스 플랫폼으로, 360GPT2 Pro, 360GPT Pro, 360GPT Turbo 및 360GPT Turbo Responsibility 8K를 포함한 다양한 고급 자연어 처리 모델을 제공합니다. 이러한 모델은 대규모 매개변수와 다중 모드 능력을 결합하여 텍스트 생성, 의미 이해, 대화 시스템 및 코드 생성 등 다양한 분야에 널리 사용됩니다. 유연한 가격 전략을 통해 360 AI는 다양한 사용자 요구를 충족하고 개발자가 통합할 수 있도록 지원하여 스마트화 응용 프로그램의 혁신과 발전을 촉진합니다."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure는 GPT-3.5 및 최신 GPT-4 시리즈를 포함한 다양한 고급 AI 모델을 제공하며, 다양한 데이터 유형과 복잡한 작업을 지원하고 안전하고 신뢰할 수 있으며 지속 가능한 AI 솔루션을 목표로 하고 있습니다."
},
+ "azureai": {
+ "description": "Azure는 GPT-3.5 및 최신 GPT-4 시리즈를 포함한 다양한 고급 AI 모델을 제공하며, 다양한 데이터 유형과 복잡한 작업을 지원하고 안전하고 신뢰할 수 있으며 지속 가능한 AI 솔루션을 위해 노력합니다."
+ },
"baichuan": {
"description": "百川智能은 인공지능 대형 모델 연구 개발에 집중하는 회사로, 그 모델은 국내 지식 백과, 긴 텍스트 처리 및 생성 창작 등 중국어 작업에서 뛰어난 성능을 보이며, 해외 주류 모델을 초월합니다. 百川智能은 업계 선도적인 다중 모드 능력을 갖추고 있으며, 여러 권위 있는 평가에서 우수한 성능을 보였습니다. 그 모델에는 Baichuan 4, Baichuan 3 Turbo 및 Baichuan 3 Turbo 128k 등이 포함되어 있으며, 각각 다른 응용 시나리오에 최적화되어 비용 효율적인 솔루션을 제공합니다."
},
"bedrock": {
"description": "Bedrock은 아마존 AWS가 제공하는 서비스로, 기업에 고급 AI 언어 모델과 비주얼 모델을 제공합니다. 그 모델 가족에는 Anthropic의 Claude 시리즈, Meta의 Llama 3.1 시리즈 등이 포함되어 있으며, 경량형부터 고성능까지 다양한 선택지를 제공하고 텍스트 생성, 대화, 이미지 처리 등 여러 작업을 지원하여 다양한 규모와 요구의 기업 응용 프로그램에 적합합니다."
},
+ "cloudflare": {
+ "description": "Cloudflare의 글로벌 네트워크에서 서버리스 GPU로 구동되는 머신러닝 모델을 실행합니다."
+ },
"deepseek": {
"description": "DeepSeek는 인공지능 기술 연구 및 응용에 집중하는 회사로, 최신 모델인 DeepSeek-V2.5는 일반 대화 및 코드 처리 능력을 통합하고 인간의 선호 정렬, 작문 작업 및 지시 따르기 등에서 상당한 향상을 이루었습니다."
},
+ "doubao": {
+ "description": "바이트댄스가 개발한 자체 대형 모델입니다. 바이트댄스 내부의 50개 이상의 비즈니스 시나리오에서 검증되었으며, 매일 수조 개의 토큰 사용량을 지속적으로 다듬어 다양한 모드 기능을 제공하여 우수한 모델 효과로 기업에 풍부한 비즈니스 경험을 제공합니다."
+ },
"fireworksai": {
"description": "Fireworks AI는 기능 호출 및 다중 모드 처리를 전문으로 하는 선도적인 고급 언어 모델 서비스 제공업체입니다. 최신 모델인 Firefunction V2는 Llama-3를 기반으로 하며, 함수 호출, 대화 및 지시 따르기에 최적화되어 있습니다. 비주얼 언어 모델인 FireLLaVA-13B는 이미지와 텍스트 혼합 입력을 지원합니다. 기타 주목할 만한 모델로는 Llama 시리즈와 Mixtral 시리즈가 있으며, 효율적인 다국어 지시 따르기 및 생성 지원을 제공합니다."
},
+ "giteeai": {
+ "description": "Gitee AI의 Serverless API는 AI 개발자에게 즉시 사용할 수 있는 대형 모델 추론 API 서비스를 제공한다."
+ },
"github": {
"description": "GitHub 모델을 통해 개발자는 AI 엔지니어가 되어 업계 최고의 AI 모델로 구축할 수 있습니다."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Groq의 LPU 추론 엔진은 최신 독립 대형 언어 모델(LLM) 벤치마크 테스트에서 뛰어난 성능을 보이며, 놀라운 속도와 효율성으로 AI 솔루션의 기준을 재정의하고 있습니다. Groq는 즉각적인 추론 속도의 대표주자로, 클라우드 기반 배포에서 우수한 성능을 보여줍니다."
},
+ "higress": {
+ "description": "Higress는 클라우드 네이티브 API 게이트웨이로, 알리 내부에서 Tengine reload가 장기 연결 비즈니스에 미치는 영향을 해결하고 gRPC/Dubbo의 로드 밸런싱 능력이 부족한 문제를 해결하기 위해 탄생했습니다."
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API는 수천 개의 모델을 탐색할 수 있는 빠르고 무료의 방법을 제공합니다. 새로운 애플리케이션을 프로토타입 하거나 머신러닝의 기능을 시도하는 경우, 이 API는 여러 분야의 고성능 모델에 즉시 접근할 수 있게 해줍니다."
+ },
+ "hunyuan": {
+ "description": "텐센트가 개발한 대형 언어 모델로, 강력한 한국어 창작 능력과 복잡한 맥락에서의 논리적 추론 능력, 그리고 신뢰할 수 있는 작업 수행 능력을 갖추고 있습니다."
+ },
+ "internlm": {
+ "description": "대규모 모델 연구 및 개발 도구 체인에 전념하는 오픈 소스 조직입니다. 모든 AI 개발자에게 효율적이고 사용하기 쉬운 오픈 소스 플랫폼을 제공하여 최첨단 대규모 모델 및 알고리즘 기술을 손쉽게 이용할 수 있도록 합니다."
+ },
+ "jina": {
+ "description": "Jina AI는 2020년에 설립된 선도적인 검색 AI 회사입니다. 우리의 검색 기반 플랫폼은 기업이 신뢰할 수 있고 고품질의 생성적 AI 및 다중 모드 검색 애플리케이션을 구축할 수 있도록 돕는 벡터 모델, 재배치기 및 소형 언어 모델을 포함하고 있습니다."
+ },
+ "lmstudio": {
+ "description": "LM Studio는 귀하의 컴퓨터에서 LLM을 개발하고 실험하기 위한 데스크탑 애플리케이션입니다."
+ },
"minimax": {
"description": "MiniMax는 2021년에 설립된 일반 인공지능 기술 회사로, 사용자와 함께 지능을 공동 창출하는 데 전념하고 있습니다. MiniMax는 다양한 모드의 일반 대형 모델을 독자적으로 개발하였으며, 여기에는 조 단위의 MoE 텍스트 대형 모델, 음성 대형 모델 및 이미지 대형 모델이 포함됩니다. 또한 해마 AI와 같은 응용 프로그램을 출시하였습니다."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI는 다양한 대형 언어 모델과 AI 이미지 생성을 제공하는 API 서비스 플랫폼으로, 유연하고 신뢰할 수 있으며 비용 효율적입니다. Llama3, Mistral 등 최신 오픈 소스 모델을 지원하며, 생성적 AI 응용 프로그램 개발을 위한 포괄적이고 사용자 친화적이며 자동 확장 가능한 API 솔루션을 제공하여 AI 스타트업의 빠른 발전에 적합합니다."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™은 클라우드, 데이터 센터, RTX™ AI 개인용 컴퓨터 및 워크스테이션에서 사전 훈련된 AI 모델과 사용자 정의 AI 모델을 배포할 수 있도록 지원하는 컨테이너를 제공합니다."
+ },
"ollama": {
"description": "Ollama가 제공하는 모델은 코드 생성, 수학 연산, 다국어 처리 및 대화 상호작용 등 다양한 분야를 포괄하며, 기업급 및 로컬 배포의 다양한 요구를 지원합니다."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity는 선도적인 대화 생성 모델 제공업체로, 다양한 고급 Llama 3.1 모델을 제공하며, 온라인 및 오프라인 응용 프로그램을 지원하고 복잡한 자연어 처리 작업에 특히 적합합니다."
},
+ "ppio": {
+ "description": "PPIO 파이오 클라우드는 안정적이고 비용 효율적인 오픈 소스 모델 API 서비스를 제공하며, DeepSeek 전 시리즈, Llama, Qwen 등 업계 선도 대모델을 지원합니다."
+ },
"qwen": {
"description": "통의천문은 알리바바 클라우드가 자주 개발한 초대형 언어 모델로, 강력한 자연어 이해 및 생성 능력을 갖추고 있습니다. 다양한 질문에 답변하고, 텍스트 콘텐츠를 창작하며, 의견을 표현하고, 코드를 작성하는 등 여러 분야에서 활용됩니다."
},
+ "sambanova": {
+ "description": "SambaNova Cloud는 개발자가 최고의 오픈 소스 모델을 쉽게 사용하고 가장 빠른 추론 속도를 즐길 수 있도록 합니다."
+ },
+ "sensenova": {
+ "description": "상탕의 일일 혁신은 상탕의 강력한 기반 지원을 바탕으로 효율적이고 사용하기 쉬운 전체 스택 대모델 서비스를 제공합니다."
+ },
"siliconcloud": {
"description": "SiliconFlow는 AGI를 가속화하여 인류에 혜택을 주기 위해 사용하기 쉽고 비용이 저렴한 GenAI 스택을 통해 대규모 AI 효율성을 향상시키는 데 전념하고 있습니다."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "중국과학원 자동화 연구소와 우한 인공지능 연구원이 출시한 차세대 다중 모드 대형 모델은 다중 회차 질문 응답, 텍스트 창작, 이미지 생성, 3D 이해, 신호 분석 등 포괄적인 질문 응답 작업을 지원하며, 더 강력한 인지, 이해 및 창작 능력을 갖추고 있어 새로운 상호작용 경험을 제공합니다."
},
+ "tencentcloud": {
+ "description": "지식 엔진 원자 능력(LLM Knowledge Engine Atomic Power)은 지식 엔진을 기반으로 개발된 지식 질문 응답의 전체 링크 능력으로, 기업 및 개발자를 대상으로 하여 유연한 모델 응용 프로그램 구성 및 개발 능력을 제공합니다. 여러 원자 능력을 통해 귀하만의 모델 서비스를 구성하고, 문서 분석, 분할, 임베딩, 다중 회차 수정 등의 서비스를 호출하여 조합하여 기업 전용 AI 비즈니스를 맞춤화할 수 있습니다."
+ },
"togetherai": {
"description": "Together AI는 혁신적인 AI 모델을 통해 선도적인 성능을 달성하는 데 전념하며, 빠른 확장 지원 및 직관적인 배포 프로세스를 포함한 광범위한 사용자 정의 기능을 제공하여 기업의 다양한 요구를 충족합니다."
},
"upstage": {
"description": "Upstage는 Solar LLM 및 문서 AI를 포함하여 다양한 비즈니스 요구를 위한 AI 모델 개발에 집중하고 있으며, 인공지능 일반 지능(AGI)을 실현하는 것을 목표로 하고 있습니다. Chat API를 통해 간단한 대화 에이전트를 생성하고 기능 호출, 번역, 임베딩 및 특정 분야 응용 프로그램을 지원합니다."
},
+ "vertexai": {
+ "description": "구글의 제미니 시리즈는 구글 딥마인드가 개발한 최첨단 범용 AI 모델로, 다중 모드에 맞춰 설계되어 텍스트, 코드, 이미지, 오디오 및 비디오의 원활한 이해와 처리를 지원합니다. 데이터 센터에서 모바일 장치에 이르기까지 다양한 환경에 적합하며, AI 모델의 효율성과 응용 범위를 크게 향상시킵니다."
+ },
+ "vllm": {
+ "description": "vLLM은 LLM 추론 및 서비스를 위한 빠르고 사용하기 쉬운 라이브러리입니다."
+ },
+ "volcengine": {
+ "description": "바이트댄스가 출시한 대형 모델 서비스 개발 플랫폼으로, 기능이 풍부하고 안전하며 가격 경쟁력이 있는 모델 호출 서비스를 제공합니다. 또한 모델 데이터, 세밀 조정, 추론, 평가 등 엔드 투 엔드 기능을 제공하여 귀하의 AI 애플리케이션 개발을 전방위적으로 지원합니다."
+ },
+ "wenxin": {
+ "description": "기업용 원스톱 대형 모델 및 AI 네이티브 애플리케이션 개발 및 서비스 플랫폼으로, 가장 포괄적이고 사용하기 쉬운 생성적 인공지능 모델 개발 및 애플리케이션 개발 전체 프로세스 도구 체인을 제공합니다."
+ },
+ "xai": {
+ "description": "xAI는 인류의 과학적 발견을 가속화하기 위해 인공지능을 구축하는 데 전념하는 회사입니다. 우리의 사명은 우주에 대한 공동의 이해를 증진하는 것입니다."
+ },
"zeroone": {
"description": "01.AI는 AI 2.0 시대의 인공지능 기술에 집중하며, '인간 + 인공지능'의 혁신과 응용을 적극적으로 추진하고, 초강력 모델과 고급 AI 기술을 활용하여 인간의 생산성을 향상시키고 기술의 힘을 실현합니다."
},
diff --git a/DigitalHumanWeb/locales/ko-KR/setting.json b/DigitalHumanWeb/locales/ko-KR/setting.json
index 9815830..6456716 100644
--- a/DigitalHumanWeb/locales/ko-KR/setting.json
+++ b/DigitalHumanWeb/locales/ko-KR/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "사용자 정의 모델 구성",
"tokens": {
- "title": "최대 토큰 수",
- "unlimited": "제한 없는"
+ "title": "최대 토큰 수"
},
"vision": {
"extra": "이 설정은 애플리케이션 내에서 이미지 업로드 기능만 활성화합니다. 인식 지원 여부는 모델 자체에 따라 다르므로, 해당 모델의 시각 인식 가능성을 직접 테스트해 보시기 바랍니다.",
@@ -98,6 +97,7 @@
"title": "클라이언트 요청 모드 사용"
},
"fetcher": {
+ "clear": "가져온 모델 지우기",
"fetch": "모델 목록 가져오기",
"fetching": "모델 목록을 가져오는 중...",
"latestTime": "마지막 업데이트 시간: {{time}}",
@@ -175,8 +175,8 @@
"desc": "대화 중에 자동으로 주제를 만들지 여부를 설정합니다. 일시적인 주제에서만 작동합니다",
"title": "자동 주제 생성 활성화"
},
- "enableCompressThreshold": {
- "title": "이전 메시지 길이 압축 임계값 활성화"
+ "enableCompressHistory": {
+ "title": "역사 메시지 자동 요약 활성화"
},
"enableHistoryCount": {
"alias": "제한 없음",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "단일 응답 제한 활성화"
},
+ "enableReasoningEffort": {
+ "title": "추론 강도 조정 활성화"
+ },
"frequencyPenalty": {
- "desc": "값이 클수록 반복 단어가 줄어듭니다",
- "title": "빈도 패널티"
+ "desc": "값이 클수록 단어 선택이 더 다양하고 풍부해지며, 값이 작을수록 단어 선택이 더 간단하고 소박해집니다.",
+ "title": "어휘 다양성"
},
"maxTokens": {
"desc": "단일 상호 작용에 사용되는 최대 토큰 수",
@@ -212,19 +215,31 @@
"desc": "{{provider}} 모델",
"title": "모델"
},
+ "params": {
+ "title": "고급 매개변수"
+ },
"presencePenalty": {
- "desc": "값이 클수록 새로운 주제로 확장될 가능성이 높아집니다",
- "title": "주제 신선도"
+ "desc": "값이 클수록 다양한 표현 방식으로 기울어져 개념의 반복을 피하고, 값이 작을수록 반복적인 개념이나 서술을 사용하는 경향이 있어 표현이 더 일관됩니다.",
+ "title": "표현의 다양성"
+ },
+ "reasoningEffort": {
+ "desc": "값이 클수록 추론 능력이 강해지지만, 응답 시간과 토큰 소모가 증가할 수 있습니다.",
+ "options": {
+ "high": "높음",
+ "low": "낮음",
+ "medium": "중간"
+ },
+ "title": "추론 강도"
},
"temperature": {
- "desc": "값이 클수록 응답이 더 무작위해집니다",
- "title": "랜덤성",
- "titleWithValue": "랜덤성 {{value}}"
+ "desc": "값이 클수록 답변이 더 창의적이고 상상력이 풍부해지며, 값이 작을수록 답변이 더 엄격해집니다.",
+ "title": "창의성 활성화",
+ "warning": "창의성 활성화 값이 너무 크면 출력이 깨질 수 있습니다."
},
"title": "모델 설정",
"topP": {
- "desc": "랜덤성과 유사하지만 함께 변경하지 마세요",
- "title": "상위 P 샘플링"
+ "desc": "얼마나 많은 가능성을 고려할지, 값이 클수록 더 많은 가능성 있는 답변을 수용하고, 값이 작을수록 가장 가능성이 높은 답변을 선택하는 경향이 있습니다. 창의성 활성화와 함께 변경하는 것은 권장하지 않습니다.",
+ "title": "사고 개방성"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "어시스턴트 이름, 설명, 프로필 이미지, 레이블을 생성하는 데 사용되는 모델을 지정합니다.",
"title": "어시스턴트 정보 자동 생성"
},
+ "customPrompt": {
+ "addPrompt": "사용자 정의 프롬프트 추가",
+ "desc": "작성 후, 시스템 어시스턴트는 콘텐츠 생성 시 사용자 정의 프롬프트를 사용합니다.",
+ "placeholder": "사용자 정의 프롬프트 입력",
+ "title": "사용자 정의 프롬프트"
+ },
+ "historyCompress": {
+ "label": "대화 기록 모델",
+ "modelDesc": "대화 기록 압축에 사용되는 모델을 지정합니다",
+ "title": "대화 기록 자동 요약"
+ },
"queryRewrite": {
"label": "질문 재작성 모델",
"modelDesc": "사용자의 질문을 최적화하는 데 사용되는 모델 지정",
- "title": "지식 베이스"
+ "title": "지식 베이스 질문 재작성"
+ },
+ "thread": {
+ "label": "하위 주제 명명 모델",
+ "modelDesc": "하위 주제 자동 이름 변경에 사용되는 모델 지정",
+ "title": "하위 주제 자동 명명"
},
"title": "시스템 도우미",
"topic": {
@@ -395,6 +426,7 @@
"common": "일반 설정",
"experiment": "실험",
"llm": "언어 모델",
+ "provider": "AI 서비스 제공자",
"sync": "클라우드 동기화",
"system-agent": "시스템 도우미",
"tts": "음성 서비스"
diff --git a/DigitalHumanWeb/locales/ko-KR/thread.json b/DigitalHumanWeb/locales/ko-KR/thread.json
new file mode 100644
index 0000000..9d168c8
--- /dev/null
+++ b/DigitalHumanWeb/locales/ko-KR/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "이 하위 주제를 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니 신중하게 진행해 주시기 바랍니다."
+ },
+ "newPortalThread": {
+ "includeContext": "주제 맥락 포함",
+ "title": "새로운 하위 주제 시작하기"
+ },
+ "notSupportMultiModals": "하위 주제는 현재 파일/이미지 업로드를 지원하지 않습니다. 필요하신 경우 댓글로 남겨주세요: <1>💬 토론 구역1>"
+}
diff --git a/DigitalHumanWeb/locales/ko-KR/tool.json b/DigitalHumanWeb/locales/ko-KR/tool.json
index eebaab6..510c3ef 100644
--- a/DigitalHumanWeb/locales/ko-KR/tool.json
+++ b/DigitalHumanWeb/locales/ko-KR/tool.json
@@ -6,5 +6,23 @@
"generating": "생성 중...",
"images": "이미지:",
"prompt": "알림 단어"
+ },
+ "search": {
+ "createNewSearch": "새 검색 기록 만들기",
+ "emptyResult": "결과를 찾을 수 없습니다. 키워드를 수정한 후 다시 시도해 주세요.",
+ "genAiMessage": "도움말 메시지 생성",
+ "includedTooltip": "현재 검색 결과는 대화의 맥락에 포함됩니다.",
+ "keywords": "키워드:",
+ "scoreTooltip": "관련성 점수, 이 점수가 높을수록 쿼리 키워드와 더 관련이 있습니다.",
+ "searchBar": {
+ "button": "검색",
+ "placeholder": "키워드",
+ "tooltip": "검색 결과를 다시 가져오고 새로운 요약 메시지를 생성합니다."
+ },
+ "searchEngine": "검색 엔진:",
+ "searchResult": "검색 수:",
+ "summary": "요약",
+ "summaryTooltip": "현재 내용 요약",
+ "viewMoreResults": "{{results}}개의 결과 더 보기"
}
}
diff --git a/DigitalHumanWeb/locales/ko-KR/topic.json b/DigitalHumanWeb/locales/ko-KR/topic.json
new file mode 100644
index 0000000..caeebd1
--- /dev/null
+++ b/DigitalHumanWeb/locales/ko-KR/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "자동 이름 변경",
+ "confirmRemoveAll": "모든 주제를 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니 신중하게 진행해 주세요.",
+ "confirmRemoveTopic": "이 주제를 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니 신중하게 진행해 주세요.",
+ "confirmRemoveUnstarred": "즐겨찾기하지 않은 주제를 삭제하려고 합니다. 삭제 후에는 복구할 수 없으니 신중하게 진행해 주세요.",
+ "duplicate": "복사본 만들기",
+ "export": "주제 내보내기",
+ "removeAll": "모든 주제 삭제",
+ "removeUnstarred": "즐겨찾기하지 않은 주제 삭제"
+ },
+ "defaultTitle": "기본 주제",
+ "duplicateLoading": "주제 복사 중...",
+ "duplicateSuccess": "주제 복사 성공",
+ "favorite": "즐겨찾기",
+ "groupMode": {
+ "ascMessages": "메시지 총 수 오름차순",
+ "byTime": "시간별 그룹화",
+ "descMessages": "메시지 총 수 내림차순",
+ "flat": "그룹화하지 않음"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "이번 달",
+ "today": "오늘",
+ "week": "이번 주",
+ "yesterday": "어제"
+ }
+ },
+ "guide": {
+ "desc": "왼쪽 버튼을 클릭하여 현재 대화를 역사 주제로 저장하고 새로운 대화를 시작하세요.",
+ "title": "주제 목록"
+ },
+ "searchPlaceholder": "주제 검색...",
+ "searchResultEmpty": "검색 결과가 없습니다.",
+ "temp": "임시",
+ "title": "주제"
+}
diff --git a/DigitalHumanWeb/locales/ko-KR/welcome.json b/DigitalHumanWeb/locales/ko-KR/welcome.json
index dee1de3..6882c9c 100644
--- a/DigitalHumanWeb/locales/ko-KR/welcome.json
+++ b/DigitalHumanWeb/locales/ko-KR/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "구성 가져오기",
- "market": "시장 구경하기",
- "start": "지금 시작"
- },
"guide": {
"agents": {
"replaceBtn": "다른 것으로 바꾸기",
diff --git a/DigitalHumanWeb/locales/nl-NL/auth.json b/DigitalHumanWeb/locales/nl-NL/auth.json
index 94c5ab9..db6212b 100644
--- a/DigitalHumanWeb/locales/nl-NL/auth.json
+++ b/DigitalHumanWeb/locales/nl-NL/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Vorige maand",
+ "recent30Days": "Laatste 30 dagen"
+ },
+ "header": {
+ "desc": "Beheer uw accountinformatie.",
+ "title": "Account"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Inactief",
+ "more": "Actief"
+ },
+ "months": {
+ "apr": "Apr",
+ "aug": "Aug",
+ "dec": "Dec",
+ "feb": "Feb",
+ "jan": "Jan",
+ "jul": "Jul",
+ "jun": "Jun",
+ "mar": "Mar",
+ "may": "Mei",
+ "nov": "Nov",
+ "oct": "Okt",
+ "sep": "Sep"
+ },
+ "tooltip": "{{date}} heeft {{count}} berichten op die dag verzonden",
+ "totalCount": "In totaal zijn er {{count}} berichten verzonden in het afgelopen jaar"
+ },
"login": "Inloggen",
- "loginOrSignup": "Inloggen / Registreren",
- "profile": "Profiel",
- "security": "Veiligheid",
+ "loginOrSignup": "Inloggen / Aanmelden",
+ "profile": {
+ "avatar": "Avatar",
+ "email": "E-mailadres",
+ "sso": {
+ "loading": "Bezig met laden van gekoppelde externe accounts",
+ "providers": "Verbindingse accounts",
+ "unlink": {
+ "description": "Als u ontkoppelt, kunt u niet meer inloggen met het {{provider}} account “{{providerAccountId}}”. Als u het {{provider}} account opnieuw aan deze account wilt koppelen, zorg er dan voor dat het e-mailadres van het {{provider}} account {{email}} is, dan zullen we het automatisch koppelen aan de huidige ingelogde account.",
+ "forbidden": "U moet minstens één extern account gekoppeld houden.",
+ "title": "Wilt u dit externe account {{provider}} ontkoppelen?"
+ }
+ },
+ "username": "Gebruikersnaam"
+ },
"signout": "Uitloggen",
- "signup": "Registreren"
+ "signup": "Aanmelden",
+ "stats": {
+ "aiheatmaps": "Activiteitsindex",
+ "assistants": "Assistenten",
+ "assistantsRank": {
+ "left": "Assistent",
+ "right": "Onderwerpen",
+ "title": "Ranglijst Assistentgebruik"
+ },
+ "createdAt": "Geregistreerd op",
+ "days": "dagen",
+ "empty": {
+ "desc": "Verzamel meer chatgegevens om te bekijken",
+ "title": "Geen gegevens"
+ },
+ "lastYearActivity": "activiteit in het afgelopen jaar",
+ "loginGuide": {
+ "f1": "Krijg gratis gebruik",
+ "f2": "Synchroniseer berichten op meerdere apparaten",
+ "f3": "Geniet van een rijke assistent",
+ "f4": "Ontdek krachtige plugins",
+ "title": "Na inloggen kun je:"
+ },
+ "messages": "Berichten",
+ "modelsRank": {
+ "left": "Model",
+ "right": "Berichten",
+ "title": "Ranglijst Modelgebruik"
+ },
+ "share": {
+ "title": "Mijn AI Activiteitsindex"
+ },
+ "topics": "Onderwerpen",
+ "topicsRank": {
+ "left": "Onderwerp",
+ "right": "Berichten",
+ "title": "Ranglijst Onderwerpinhoud"
+ },
+ "updatedAt": "Bijgewerkt op",
+ "welcome": "{{username}}, dit is uw {{days}} dag met {{appName}}",
+ "words": "Woorden"
+ },
+ "tab": {
+ "profile": "Profiel",
+ "security": "Beveiliging",
+ "stats": "Statistieken"
+ }
}
diff --git a/DigitalHumanWeb/locales/nl-NL/changelog.json b/DigitalHumanWeb/locales/nl-NL/changelog.json
new file mode 100644
index 0000000..24027e6
--- /dev/null
+++ b/DigitalHumanWeb/locales/nl-NL/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Volg ons op X",
+ "subscribeToUpdates": "Abonneer op updates",
+ "versions": "Versie details"
+ },
+ "addedWhileAway": "We hebben nieuwe functies toegevoegd terwijl je weg was.",
+ "allChangelog": "Bekijk alle changelogs",
+ "description": "Blijf op de hoogte van nieuwe functies en verbeteringen van {{appName}}",
+ "pagination": {
+ "next": "Volgende pagina",
+ "older": "Bekijk eerdere wijzigingen"
+ },
+ "readDetails": "Lees meer",
+ "title": "Changelog",
+ "versionDetails": "Versie details",
+ "welcomeBack": "Welkom terug!"
+}
diff --git a/DigitalHumanWeb/locales/nl-NL/chat.json b/DigitalHumanWeb/locales/nl-NL/chat.json
index 478299f..b6c35d7 100644
--- a/DigitalHumanWeb/locales/nl-NL/chat.json
+++ b/DigitalHumanWeb/locales/nl-NL/chat.json
@@ -8,6 +8,7 @@
"agents": "Assistent",
"artifact": {
"generating": "Genereren",
+ "inThread": "Je kunt het niet bekijken in het subonderwerp, schakel over naar het hoofdgesprek om het te openen.",
"thinking": "Denken",
"thought": "Denken proces",
"unknownTitle": "Onbenoemd werk"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Kopie",
"emptyAgent": "Geen assistent beschikbaar",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "De kosten voor het genereren van een enkele conversatie kunnen met maximaal 90% worden verlaagd, en de responssnelheid kan tot 4 keer worden verhoogd (<1>Lees meer1>). Wanneer ingeschakeld, wordt automatisch de limiet voor het aantal historische berichten uitgeschakeld.",
+ "title": "Contextcaching inschakelen"
+ },
+ "enableReasoning": {
+ "desc": "Beperkingen op basis van het Claude Thinking-mechanisme (<1>Lees meer1>), wanneer ingeschakeld, wordt automatisch de limiet voor het aantal historische berichten uitgeschakeld.",
+ "title": "Diepe denkwijze inschakelen"
+ },
+ "reasoningBudgetToken": {
+ "title": "Denken verbruik Token"
+ },
+ "title": "Modeluitbreidingsfunctie"
+ },
+ "history": {
+ "title": "De assistent onthoudt alleen de laatste {{count}} berichten"
+ },
"historyRange": "Geschiedenisbereik",
+ "historySummary": "Geschiedenis samenvatting",
"inbox": {
"desc": "Activeer de hersencluster en laat de vonken van gedachten overslaan. Je slimme assistent, hier om met je over alles te praten.",
"title": "Praat maar raak"
@@ -45,6 +64,9 @@
"stop": "Stoppen",
"warp": "Nieuwe regel"
},
+ "intentUnderstanding": {
+ "title": "Bezig met het begrijpen en analyseren van uw intentie..."
+ },
"knowledgeBase": {
"all": "Alle inhoud",
"allFiles": "Alle bestanden",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Verwijderen en opnieuw genereren",
+ "deleteDisabledByThreads": "Er zijn subonderwerpen, verwijderen is niet mogelijk.",
"regenerate": "Opnieuw genereren"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Credits",
+ "creditPricing": "Prijsstelling",
+ "creditTooltip": "Voor de eenvoud van de berekening beschouwen we $1 als 1M credits, bijvoorbeeld $3/M tokens wordt omgezet naar 3 credits/token",
+ "pricing": {
+ "inputCachedTokens": "Gecacheerde invoer {{amount}}/credits · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M tekens",
+ "inputMinutes": "${{amount}}/minuut",
+ "inputTokens": "Invoer {{amount}}/credits · ${{amount}}/M",
+ "outputTokens": "Uitvoer {{amount}}/credits · ${{amount}}/M",
+ "writeCacheInputTokens": "Cache-invoer schrijven {{amount}}/punten · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Gemiddelde prijs",
+ "input": "Invoer",
+ "inputAudio": "Audio-invoer",
+ "inputCached": "Gecacheerde invoer",
+ "inputCitation": "Invoer citeren",
+ "inputText": "Tekstinvoer",
+ "inputTitle": "Invoerdetails",
+ "inputUncached": "Ongecacheerde invoer",
+ "inputWriteCached": "Invoer cache schrijven",
+ "output": "Uitvoer",
+ "outputAudio": "Audio-uitvoer",
+ "outputText": "Tekstuitvoer",
+ "outputTitle": "Uitvoerdetails",
+ "reasoning": "Diep nadenken",
+ "title": "Genereren van details",
+ "total": "Totaal verbruik"
+ }
+ },
"newAgent": "Nieuwe assistent",
"pin": "Vastzetten",
"pinOff": "Vastzetten uitschakelen",
@@ -81,6 +137,32 @@
},
"regenerate": "Opnieuw genereren",
"roleAndArchive": "Rol en archief",
+ "search": {
+ "grounding": {
+ "searchQueries": "Zoekwoorden",
+ "title": "Er zijn {{count}} resultaten gevonden"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Intelligente beoordeling of er gezocht moet worden op basis van de gesprekinhoud",
+ "title": "Slimme verbinding"
+ },
+ "off": {
+ "desc": "Gebruik alleen de basiskennis van het model, zonder online zoekopdrachten",
+ "title": "Verbinding uitschakelen"
+ },
+ "on": {
+ "desc": "Voortdurend online zoeken voor de nieuwste informatie",
+ "title": "Altijd verbonden"
+ },
+ "useModelBuiltin": "Gebruik de ingebouwde zoekmachine van het model"
+ },
+ "searchModel": {
+ "desc": "Het huidige model ondersteunt geen functieaanroepen, dus het moet worden gecombineerd met een model dat functieaanroepen ondersteunt om online te zoeken",
+ "title": "Zoekhulpmiddel model"
+ },
+ "title": "Online zoeken"
+ },
"searchAgentPlaceholder": "Zoekassistent...",
"sendPlaceholder": "Voer chatbericht in...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "De groepsnaam moet tussen 1 en 20 tekens lang zijn"
},
"shareModal": {
+ "copy": "Kopiëren",
"download": "Screenshot downloaden",
+ "downloadFile": "Bestand downloaden",
+ "exportTitle": "Standaardtitel",
"imageType": "Afbeeldingstype",
+ "includeTool": "Inclusief pluginbericht",
+ "includeUser": "Inclusief gebruikersbericht",
"screenshot": "Screenshot",
"settings": "Exportinstellingen",
- "shareToShareGPT": "Genereer ShareGPT-deellink",
+ "text": "Tekst",
"withBackground": "Met achtergrondafbeelding",
"withFooter": "Met voettekst",
"withPluginInfo": "Met plug-in informatie",
+ "withRole": "Inclusief berichtrol",
"withSystemRole": "Met assistentrolinstelling"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Bezig met herkennen...",
"prettifying": "Aan het verfraaien..."
},
- "temp": "Tijdelijk",
+ "thread": {
+ "divider": "Subonderwerp",
+ "threadMessageCount": "{{messageCount}} berichten",
+ "title": "Subonderwerp"
+ },
"tokenDetails": {
"chats": "Chats",
+ "historySummary": "Geschiedenis samenvatting",
"rest": "Rust",
"systemRole": "Systeemrol",
"title": "Contextuele details",
@@ -131,29 +224,10 @@
"used": "Gebruikt"
},
"topic": {
- "actions": {
- "autoRename": "Automatisch hernoemen",
- "duplicate": "Dupliceren",
- "export": "Exporteren"
- },
"checkOpenNewTopic": "Is het openen van een nieuw onderwerp ingeschakeld?",
"checkSaveCurrentMessages": "Wil je het huidige gesprek opslaan als onderwerp?",
- "confirmRemoveAll": "Alle onderwerpen worden verwijderd en kunnen niet worden hersteld. Wees voorzichtig.",
- "confirmRemoveTopic": "Dit onderwerp wordt verwijderd en kan niet worden hersteld. Wees voorzichtig.",
- "confirmRemoveUnstarred": "Niet-gefavoriseerde onderwerpen worden verwijderd en kunnen niet worden hersteld. Wees voorzichtig.",
- "defaultTitle": "Standaard onderwerp",
- "duplicateLoading": "Onderwerp dupliceren...",
- "duplicateSuccess": "Onderwerp succesvol gedupliceerd",
- "guide": {
- "desc": "Klik op de knop aan de linkerkant om het huidige gesprek op te slaan als een historisch onderwerp en een nieuw gesprek te starten",
- "title": "Onderwerplijst"
- },
"openNewTopic": "Nieuw onderwerp openen",
- "removeAll": "Alle onderwerpen verwijderen",
- "removeUnstarred": "Niet-gefavoriseerde onderwerpen verwijderen",
- "saveCurrentMessages": "Huidig gesprek opslaan als onderwerp",
- "searchPlaceholder": "Zoek onderwerpen...",
- "title": "Onderwerpenlijst"
+ "saveCurrentMessages": "Huidig gesprek opslaan als onderwerp"
},
"translate": {
"action": "Vertalen",
@@ -184,5 +258,6 @@
"processing": "Bestand wordt verwerkt..."
}
}
- }
+ },
+ "zenMode": "Focusmodus"
}
diff --git a/DigitalHumanWeb/locales/nl-NL/common.json b/DigitalHumanWeb/locales/nl-NL/common.json
index 1603c76..b06a3a3 100644
--- a/DigitalHumanWeb/locales/nl-NL/common.json
+++ b/DigitalHumanWeb/locales/nl-NL/common.json
@@ -9,15 +9,79 @@
"title": "Welkom bij {{name}}"
}
},
- "appInitializing": "Applicatie wordt gestart...",
+ "appLoading": {
+ "appIdle": "Klaar om te starten",
+ "appInitializing": "Applicatie wordt gestart...",
+ "failed": "Het spijt ons, de applicatie-initialisatie is mislukt. Bekijk de details voor hulp bij het oplossen.",
+ "finished": "Database-initialisatie voltooid",
+ "goToChat": "De chatpagina wordt geladen...",
+ "initAuth": "Authenticatiedienst wordt geïnitialiseerd...",
+ "initUser": "Gebruikersstatus wordt geïnitialiseerd...",
+ "initializing": "PGlite-database wordt geïnitialiseerd...",
+ "loadingDependencies": "Afhankelijkheden worden geïnitialiseerd...",
+ "loadingWasm": "WASM-modules worden geladen...",
+ "migrating": "Gegevens migreren...",
+ "ready": "Database is gereed",
+ "showDetail": "Bekijk details"
+ },
"autoGenerate": "Automatisch genereren",
"autoGenerateTooltip": "Automatisch assistentbeschrijving genereren op basis van suggesties",
"autoGenerateTooltipDisabled": "Schakel de automatische aanvulling in nadat u een suggestiewoord heeft ingevoerd",
"back": "Terug",
"batchDelete": "Batch verwijderen",
"blog": "Product Blog",
+ "branching": "Subonderwerp aanmaken",
+ "branchingDisable": "De functie 'Subonderwerp' is alleen beschikbaar in de serverversie. Als je deze functie wilt gebruiken, schakel dan over naar de serverimplementatiemodus of gebruik LobeChat Cloud.",
"cancel": "Annuleren",
"changelog": "Wijzigingslogboek",
+ "clientDB": {
+ "autoInit": {
+ "title": "Initialiseer de PGlite-database"
+ },
+ "error": {
+ "desc": "Onze excuses, er is een fout opgetreden tijdens het initialisatieproces van de Pglite-database. Klik op de knop om het opnieuw te proberen. Als het probleem zich blijft voordoen na meerdere pogingen, gelieve <1>een probleem te melden1> en we zullen u zo snel mogelijk helpen.",
+ "detail": "Fout reden: [[{{type}}] {{message}}. Details zijn als volgt:",
+ "retry": "Opnieuw proberen",
+ "title": "Fout bij database-initialisatie"
+ },
+ "initing": {
+ "error": "Er is een fout opgetreden, probeer het opnieuw",
+ "idle": "Wachten op initialisatie...",
+ "initializing": "Bezig met initialiseren...",
+ "loadingDependencies": "Afhankelijkheden laden...",
+ "loadingWasmModule": "WASM-module laden...",
+ "migrating": "Gegevens migreren...",
+ "ready": "Database is gereed"
+ },
+ "modal": {
+ "desc": "Schakel de PGlite-clientdatabase in om chatgegevens permanent op te slaan in je browser en gebruik geavanceerde functies zoals de kennisbank.",
+ "enable": "Nu inschakelen",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Bouw je persoonlijke kennisbasis op en start eenvoudig een gesprek met je assistent (binnenkort beschikbaar)",
+ "title": "Ondersteuning voor kennisbasisgesprekken, activeer je tweede brein"
+ },
+ "localFirst": {
+ "desc": "Chatgegevens worden volledig in de browser opgeslagen, jouw gegevens zijn altijd in jouw beheer.",
+ "title": "Lokaal eerst, privacy voorop"
+ },
+ "pglite": {
+ "desc": "Gebaseerd op PGlite, native ondersteuning voor AI Native geavanceerde functies (vectorzoekopdrachten)",
+ "title": "Nieuwe generatie clientopslagarchitectuur"
+ }
+ },
+ "init": {
+ "desc": "Bezig met het initialiseren van de database, afhankelijk van de netwerksnelheid kan dit 5 tot 30 seconden duren.",
+ "title": "Bezig met het initialiseren van de PGlite-database"
+ },
+ "title": "Schakel de clientdatabase in"
+ },
+ "ready": {
+ "button": "Nu gebruiken",
+ "desc": "Direct gebruiken",
+ "title": "PGlite-database is gereed"
+ }
+ },
"close": "Sluiten",
"contact": "Contacteer ons",
"copy": "Kopiëren",
@@ -112,6 +176,7 @@
"en": "Engels",
"en-US": "Engels",
"es-ES": "Spaans",
+ "fa-IR": "Perzisch",
"fi-FI": "Fins",
"fr-FR": "Frans",
"hi-IN": "Hindi",
@@ -153,6 +218,7 @@
"pinOff": "Vastzetten uitschakelen",
"privacy": "Privacybeleid",
"regenerate": "Opnieuw genereren",
+ "releaseNotes": "Versie details",
"rename": "Naam wijzigen",
"reset": "Resetten",
"retry": "Opnieuw proberen",
@@ -209,6 +275,7 @@
},
"temp": "tijdelijk",
"terms": "algemene voorwaarden",
+ "update": "Bijwerken",
"updateAgent": "update assistent",
"upgradeVersion": {
"action": "upgraden",
@@ -219,6 +286,7 @@
"anonymousNickName": "anonieme gebruiker",
"billing": "facturatie",
"cloud": "Ervaar {{name}}",
+ "community": "Gemeenschapsversie",
"data": "gegevensopslag",
"defaultNickname": "communitygebruiker",
"discord": "communityondersteuning",
@@ -228,7 +296,6 @@
"help": "helpcentrum",
"moveGuide": "instellingen verplaatst naar hier",
"plans": "abonnementen",
- "preview": "voorbeeldversie",
"profile": "accountbeheer",
"setting": "app-instellingen",
"usages": "gebruiksstatistieken"
diff --git a/DigitalHumanWeb/locales/nl-NL/components.json b/DigitalHumanWeb/locales/nl-NL/components.json
index 83734c7..575ab42 100644
--- a/DigitalHumanWeb/locales/nl-NL/components.json
+++ b/DigitalHumanWeb/locales/nl-NL/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Batchverdeling",
"chunking": "Verdeling",
"chunkingTooltip": "Splits het bestand in meerdere tekstblokken en vectoriseer deze voor semantische zoekopdrachten en bestandsdialoog",
+ "chunkingUnsupported": "Dit bestand ondersteunt geen chunking",
"confirmDelete": "Je staat op het punt dit bestand te verwijderen. Na verwijdering kan het niet meer worden hersteld. Bevestig je actie.",
"confirmDeleteMultiFiles": "Je staat op het punt de geselecteerde {{count}} bestanden te verwijderen. Na verwijdering kunnen ze niet meer worden hersteld. Bevestig je actie.",
"confirmRemoveFromKnowledgeBase": "Je staat op het punt de geselecteerde {{count}} bestanden uit de kennisbank te verwijderen. Na verwijdering zijn de bestanden nog steeds zichtbaar in alle bestanden. Bevestig je actie.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Terug"
},
+ "MaxTokenSlider": {
+ "unlimited": "Onbeperkt"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Custom model, by default, supports both function call and visual recognition. Please verify the availability of the above capabilities based on actual needs.",
"file": "This model supports file upload for reading and recognition.",
"functionCall": "This model supports function call.",
+ "reasoning": "Dit model ondersteunt diepgaand denken",
+ "search": "Dit model ondersteunt online zoeken",
"tokens": "This model supports up to {{tokens}} tokens in a single session.",
"vision": "This model supports visual recognition."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "No enabled model, please go to settings to enable.",
+ "emptyProvider": "Geen ingeschakelde provider, ga naar instellingen om deze in te schakelen",
+ "goToSettings": "Ga naar instellingen",
"provider": "Provider"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Vanwege beveiligingsbeperkingen in de browser moet je cross-origin configuratie voor Ollama instellen om het correct te kunnen gebruiken.",
+ "linux": {
+ "env": "Voeg `Environment` toe onder de [Service] sectie en voeg de OLLAMA_ORIGINS omgevingsvariabele toe:",
+ "reboot": "Herlaad systemd en herstart Ollama",
+ "systemd": "Roep systemd aan om de ollama service te bewerken:"
+ },
+ "macos": "Open de 'Terminal' applicatie, plak de volgende opdracht en druk op enter om uit te voeren",
+ "reboot": "Herstart de Ollama service na het voltooien van de uitvoering",
+ "title": "Configureer Ollama voor cross-origin toegang",
+ "windows": "Op Windows, klik op 'Configuratiescherm', ga naar systeemomgevingsvariabelen bewerken. Maak een nieuwe omgevingsvariabele aan met de naam 'OLLAMA_ORIGINS' voor je gebruikersaccount, met de waarde * en klik op 'OK/Toepassen' om op te slaan"
+ },
+ "install": {
+ "description": "Zorg ervoor dat je Ollama hebt ingeschakeld. Als je Ollama nog niet hebt gedownload, ga dan naar de officiële website <1>om te downloaden1>",
+ "docker": "Als je de voorkeur geeft aan het gebruik van Docker, biedt Ollama ook een officiële Docker-image aan die je kunt ophalen met de volgende opdracht:",
+ "linux": {
+ "command": "Installeer met de volgende opdracht:",
+ "manual": "Of je kunt de <1>Linux handmatige installatiehandleiding1> raadplegen voor een handmatige installatie"
+ },
+ "title": "Installeer en start de Ollama applicatie lokaal",
+ "windowsTab": "Windows (previewversie)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Diep in gedachten...",
+ "thought": "Diep nagedacht (tijd gebruikt {{duration}} seconden)",
+ "thoughtWithDuration": "Diep nagedacht"
}
}
diff --git a/DigitalHumanWeb/locales/nl-NL/discover.json b/DigitalHumanWeb/locales/nl-NL/discover.json
index 5ff3bd3..c7f34b7 100644
--- a/DigitalHumanWeb/locales/nl-NL/discover.json
+++ b/DigitalHumanWeb/locales/nl-NL/discover.json
@@ -126,6 +126,10 @@
"title": "Onderwerp versheid"
},
"range": "Bereik",
+ "reasoning_effort": {
+ "desc": "Deze instelling wordt gebruikt om de redeneerkracht van het model te regelen voordat het een antwoord genereert. Lage kracht geeft prioriteit aan de responssnelheid en bespaart tokens, terwijl hoge kracht een completere redenering biedt, maar meer tokens verbruikt en de responssnelheid verlaagt. De standaardwaarde is gemiddeld, wat een balans biedt tussen redeneringsnauwkeurigheid en responssnelheid.",
+ "title": "Redeneerkracht"
+ },
"temperature": {
"desc": "Deze instelling beïnvloedt de diversiteit van de reacties van het model. Lagere waarden leiden tot meer voorspelbare en typische reacties, terwijl hogere waarden meer diverse en ongebruikelijke reacties aanmoedigen. Wanneer de waarde op 0 is ingesteld, geeft het model altijd dezelfde reactie op een gegeven invoer.",
"title": "Willekeurigheid"
diff --git a/DigitalHumanWeb/locales/nl-NL/error.json b/DigitalHumanWeb/locales/nl-NL/error.json
index bdbc950..58d6fcc 100644
--- a/DigitalHumanWeb/locales/nl-NL/error.json
+++ b/DigitalHumanWeb/locales/nl-NL/error.json
@@ -12,8 +12,14 @@
"retry": "Opnieuw proberen",
"title": "Er is een probleem opgetreden op de pagina.."
},
- "fetchError": "Verzoek mislukt",
- "fetchErrorDetail": "Foutdetails",
+ "fetchError": {
+ "detail": "Foutdetails",
+ "title": "Verzoek mislukt"
+ },
+ "loginRequired": {
+ "desc": "U wordt binnenkort automatisch doorgestuurd naar de inlogpagina",
+ "title": "Log in om deze functie te gebruiken"
+ },
"notFound": {
"backHome": "Terug naar startpagina",
"check": "Controleer of je URL correct is",
@@ -51,22 +57,34 @@
"431": "Sorry, de kop van uw verzoek is te groot en kan niet worden verwerkt door de server",
"451": "Sorry, vanwege juridische redenen weigert de server deze bron te leveren",
"500": "Sorry, de server lijkt problemen te ondervinden en kan uw verzoek tijdelijk niet voltooien. Probeer het later opnieuw",
+ "501": "Het spijt ons, de server weet nog niet hoe deze aanvraag te verwerken, controleer alstublieft of uw handeling correct is",
"502": "Sorry, de server lijkt de weg kwijt te zijn en kan tijdelijk geen service verlenen. Probeer het later opnieuw",
"503": "Sorry, de server kan uw verzoek momenteel niet verwerken vanwege overbelasting of onderhoud. Probeer het later opnieuw",
"504": "Sorry, de server heeft geen reactie ontvangen van de upstream server. Probeer het later opnieuw",
+ "505": "Het spijt ons, de server ondersteunt de door u gebruikte HTTP-versie niet, probeer het alstublieft opnieuw na een update",
+ "506": "Het spijt ons, er is een probleem met de serverconfiguratie, neem contact op met de beheerder voor hulp",
+ "507": "Het spijt ons, de server heeft onvoldoende opslagruimte om uw aanvraag te verwerken, probeer het alstublieft later opnieuw",
+ "509": "Het spijt ons, de bandbreedte van de server is op, probeer het alstublieft later opnieuw",
+ "510": "Het spijt ons, de server ondersteunt de gevraagde uitbreidingsfunctie niet, neem contact op met de beheerder",
+ "524": "Het spijt ons, de server heeft een time-out terwijl hij op een antwoord wacht, mogelijk omdat de reactie te traag is, probeer het alstublieft later opnieuw",
"AgentRuntimeError": "Lobe language model runtime execution error, please troubleshoot or retry based on the following information",
+ "ConnectionCheckFailed": "Het verzoek heeft geen antwoord geleverd. Controleer of het API-proxyadres niet eindigt met `/v1`.",
+ "ExceededContextWindow": "De inhoud van de huidige aanvraag overschrijdt de lengte die het model kan verwerken. Verminder de hoeveelheid inhoud en probeer het opnieuw.",
"FreePlanLimit": "U bent momenteel een gratis gebruiker en kunt deze functie niet gebruiken. Upgrade naar een betaald plan om door te gaan met gebruiken.",
+ "InsufficientQuota": "Het spijt ons, de quotum van deze sleutel is bereikt. Controleer of uw account voldoende saldo heeft of vergroot het sleutelquotum en probeer het opnieuw.",
"InvalidAccessCode": "Ongeldige toegangscode: het wachtwoord is onjuist of leeg. Voer de juiste toegangscode in of voeg een aangepaste API-sleutel toe.",
"InvalidBedrockCredentials": "Bedrock authentication failed, please check AccessKeyId/SecretAccessKey and retry",
"InvalidClerkUser": "Sorry, you are not currently logged in. Please log in or register an account to continue.",
"InvalidGithubToken": "Github Persoonlijke Toegangstoken is ongeldig of leeg, controleer de Github Persoonlijke Toegangstoken en probeer het opnieuw.",
"InvalidOllamaArgs": "Ollama-configuratie is onjuist, controleer de Ollama-configuratie en probeer het opnieuw",
"InvalidProviderAPIKey": "{{provider}} API-sleutel is onjuist of leeg. Controleer de {{provider}} API-sleutel en probeer het opnieuw.",
+ "InvalidVertexCredentials": "Vertex-authenticatie is mislukt, controleer de authenticatiegegevens en probeer het opnieuw",
"LocationNotSupportError": "Sorry, your current location does not support this model service, possibly due to regional restrictions or service not being available. Please confirm if the current location supports using this service, or try using other location information.",
+ "ModelNotFound": "Het spijt ons, het is niet mogelijk om het bijbehorende model op te vragen. Dit kan komen doordat het model niet bestaat of dat er geen toegang is. Probeer het opnieuw na het wijzigen van de API-sleutel of het aanpassen van de toegangsrechten.",
"NoOpenAIAPIKey": "OpenAI API-sleutel ontbreekt. Voeg een aangepaste OpenAI API-sleutel toe",
"OllamaBizError": "Fout bij het aanroepen van de Ollama-service, controleer de onderstaande informatie en probeer opnieuw",
"OllamaServiceUnavailable": "Ollama-service niet beschikbaar. Controleer of Ollama correct werkt en of de cross-origin configuratie van Ollama juist is ingesteld.",
- "OpenAIBizError": "Er is een fout opgetreden bij het aanvragen van de OpenAI-service. Controleer de volgende informatie of probeer het opnieuw.",
+ "PermissionDenied": "Het spijt ons, je hebt geen toestemming om deze service te gebruiken. Controleer of je sleutel de juiste toegangsrechten heeft.",
"PluginApiNotFound": "Sorry, de API van de plug-inbeschrijvingslijst bestaat niet. Controleer of uw verzoeksmethode overeenkomt met de plug-inbeschrijvingslijst API",
"PluginApiParamsError": "Sorry, de validatie van de invoerparameters van de plug-in is mislukt. Controleer of de invoerparameters overeenkomen met de API-beschrijving",
"PluginFailToTransformArguments": "Sorry, the plugin failed to parse the arguments. Please try regenerating the assistant message or retry with a more powerful AI model with Tools Calling capability.",
@@ -81,8 +99,11 @@
"PluginServerError": "Fout bij serverrespons voor plug-in. Controleer de foutinformatie hieronder voor uw plug-inbeschrijvingsbestand, plug-inconfiguratie of serverimplementatie",
"PluginSettingsInvalid": "Deze plug-in moet correct geconfigureerd zijn voordat deze kan worden gebruikt. Controleer of uw configuratie juist is",
"ProviderBizError": "Er is een fout opgetreden bij het aanvragen van de {{provider}}-service. Controleer de volgende informatie of probeer het opnieuw.",
+ "QuotaLimitReached": "Het spijt ons, het huidige tokenverbruik of het aantal verzoeken heeft de quota-limiet van deze sleutel bereikt. Verhoog de quota van deze sleutel of probeer het later opnieuw.",
"StreamChunkError": "Fout bij het parseren van het berichtblok van de streamingaanroep. Controleer of de huidige API-interface voldoet aan de standaardnormen, of neem contact op met uw API-leverancier voor advies.",
- "SubscriptionPlanLimit": "Uw abonnementslimiet is bereikt en u kunt deze functie niet gebruiken. Upgrade naar een hoger plan of koop een resourcepakket om door te gaan met gebruiken.",
+ "SubscriptionKeyMismatch": "Het spijt ons, maar door een tijdelijke systeemfout is het huidige abonnement tijdelijk ongeldig. Klik op de onderstaande knop om het abonnement te herstellen, of neem contact met ons op via e-mail voor ondersteuning.",
+ "SubscriptionPlanLimit": "Uw abonnementscredits zijn op, u kunt deze functie niet gebruiken. Upgrade naar een hoger plan of configureer de aangepaste model-API om door te gaan.",
+ "SystemTimeNotMatchError": "Het spijt ons, uw systeemtijd komt niet overeen met de server. Controleer uw systeemtijd en probeer het opnieuw.",
"UnknownChatFetchError": "Het spijt me, er is een onbekende verzoekfout opgetreden. Controleer de onderstaande informatie of probeer het opnieuw."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/nl-NL/metadata.json b/DigitalHumanWeb/locales/nl-NL/metadata.json
index 2bf20a5..1571cfb 100644
--- a/DigitalHumanWeb/locales/nl-NL/metadata.json
+++ b/DigitalHumanWeb/locales/nl-NL/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Blijf op de hoogte van nieuwe functies en verbeteringen van {{appName}}",
+ "title": "Wijzigingslog"
+ },
"chat": {
"description": "{{appName}} biedt je de beste ervaring met ChatGPT, Claude, Gemini, en OLLaMA WebUI",
"title": "{{appName}}: Persoonlijke AI-efficiëntietool, geef jezelf een slimmer brein"
diff --git a/DigitalHumanWeb/locales/nl-NL/modelProvider.json b/DigitalHumanWeb/locales/nl-NL/modelProvider.json
index 92f21fc..19e0244 100644
--- a/DigitalHumanWeb/locales/nl-NL/modelProvider.json
+++ b/DigitalHumanWeb/locales/nl-NL/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "De API-versie van Azure, volgens het formaat YYYY-MM-DD. Raadpleeg de [laatste versie](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Lijst ophalen",
+ "title": "Azure API-versie"
+ },
+ "endpoint": {
+ "desc": "Vind het Azure AI-model inferentie-eindpunt in het overzicht van het Azure AI-project",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AI-eindpunt"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Vind de API-sleutel in het overzicht van het Azure AI-project",
+ "placeholder": "Azure-sleutel",
+ "title": "Sleutel"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Voer AWS Access Key Id in",
@@ -51,6 +69,58 @@
"title": "Gebruik aangepaste Bedrock-verificatiegegevens"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Voer Cloudflare API Key in",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Voer uw Cloudflare-account ID of een custom API-URL in",
+ "placeholder": "Cloudflare-account ID / custom API-URL",
+ "title": "Cloudflare-account ID / API-URL"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Vul je API-sleutel in",
+ "title": "API-sleutel"
+ },
+ "basicTitle": "Basisinformatie",
+ "configTitle": "Configuratie-informatie",
+ "confirm": "Nieuw aanmaken",
+ "createSuccess": "Succesvol aangemaakt",
+ "description": {
+ "placeholder": "Beschrijving van de provider (optioneel)",
+ "title": "Beschrijving van de provider"
+ },
+ "id": {
+ "desc": "Een unieke identificatie voor de dienstverlener, kan na creatie niet meer worden gewijzigd",
+ "format": "Mag alleen cijfers, kleine letters, koppeltekens (-) en onderstrepingstekens (_) bevatten",
+ "placeholder": "Gebruik alleen kleine letters, bijvoorbeeld openai, kan niet worden gewijzigd na aanmaak",
+ "required": "Vul de provider ID in",
+ "title": "Provider ID"
+ },
+ "logo": {
+ "required": "Upload een correcte provider-logo",
+ "title": "Provider-logo"
+ },
+ "name": {
+ "placeholder": "Voer de weergavenaam van de provider in",
+ "required": "Vul de naam van de provider in",
+ "title": "Naam van de provider"
+ },
+ "proxyUrl": {
+ "required": "Vul het proxyadres in",
+ "title": "Proxy-adres"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Selecteer het SDK-type",
+ "title": "Aanvraagformaat"
+ },
+ "title": "Maak een aangepaste AI-provider"
+ },
"github": {
"personalAccessToken": {
"desc": "Vul je Github PAT in, klik [hier](https://github.com/settings/tokens) om er een te maken",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Vul je HuggingFace Token in, klik [hier](https://huggingface.co/settings/tokens) om er een te maken",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace Token"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Dienstverlener niet ingeschakeld",
+ "enabled": "Dienstverlener ingeschakeld"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Voeg aangepaste provider toe",
+ "all": "Alles",
+ "list": {
+ "disabled": "Niet ingeschakeld",
+ "enabled": "Ingeschakeld"
+ },
+ "notFound": "Geen zoekresultaten gevonden",
+ "searchProviders": "Zoek providers...",
+ "sort": "Aangepaste sortering"
+ },
"ollama": {
"checker": {
"desc": "Test of het proxyadres correct is ingevuld",
@@ -69,47 +163,173 @@
"title": "Aangepaste Modelnamen"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. It will resume from where it left off if you restart the download.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama is het model aan het downloaden, sluit deze pagina alstublieft niet af. Bij een herstart zal het downloaden op de onderbroken plaats verdergaan.",
+ "remainingTime": "Overgebleven tijd",
+ "speed": "Downloadsnelheid",
+ "title": "Model {{model}} wordt gedownload"
},
"endpoint": {
- "desc": "Voer het Ollama interface proxyadres in, laat leeg indien niet specifiek aangegeven",
+ "desc": "Moet http(s):// bevatten, kan leeg gelaten worden als lokaal niet specifiek opgegeven",
"title": "Interface Proxyadres"
},
- "setup": {
- "cors": {
- "description": "Due to browser security restrictions, you need to configure cross-origin settings for Ollama to function properly.",
- "linux": {
- "env": "Add `Environment` under [Service] section, and set the OLLAMA_ORIGINS environment variable:",
- "reboot": "Reload systemd and restart Ollama.",
- "systemd": "Invoke systemd to edit the ollama service:"
- },
- "macos": "Open the 'Terminal' application, paste the following command, and press Enter to run it.",
- "reboot": "Please restart the Ollama service after the execution is complete.",
- "title": "Configure Ollama for Cross-Origin Access",
- "windows": "On Windows, go to 'Control Panel' and edit system environment variables. Create a new environment variable named 'OLLAMA_ORIGINS' for your user account, set the value to '*', and click 'OK/Apply' to save."
- },
- "install": {
- "description": "Zorg ervoor dat Ollama is ingeschakeld. Als je Ollama nog niet hebt gedownload, ga dan naar de officiële website om <1>te downloaden1>.",
- "docker": "If you prefer using Docker, Ollama also provides official Docker images. You can pull them using the following command:",
- "linux": {
- "command": "Install using the following command:",
- "manual": "Alternatively, you can refer to the <1>Linux Manual Installation Guide1> for manual installation."
- },
- "title": "Install and Start Ollama Locally",
- "windowsTab": "Windows (Preview)"
- }
- },
"title": "Ollama",
"unlock": {
- "cancel": "Cancel Download",
- "confirm": "Download",
- "description": "Enter your Ollama model tag to continue the session",
+ "cancel": "Annuleer download",
+ "confirm": "Downloaden",
+ "description": "Voer je Ollama model label in om door te gaan met de sessie",
"downloaded": "{{completed}} / {{total}}",
- "starting": "Starting download...",
- "title": "Download specified Ollama model"
+ "starting": "Downloaden starten...",
+ "title": "Download het opgegeven Ollama model"
+ }
+ },
+ "providerModels": {
+ "config": {
+ "aesGcm": "Je sleutel en proxy-adres worden versleuteld met <1>AES-GCM1> encryptie-algoritme",
+ "apiKey": {
+ "desc": "Vul je {{name}} API-sleutel in",
+ "placeholder": "{{name}} API-sleutel",
+ "title": "API-sleutel"
+ },
+ "baseURL": {
+ "desc": "Moet http(s):// bevatten",
+ "invalid": "Voer een geldige URL in",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API-proxy-adres"
+ },
+ "checker": {
+ "button": "Controleer",
+ "desc": "Test of de API-sleutel en proxy-adres correct zijn ingevuld",
+ "pass": "Controle geslaagd",
+ "title": "Connectiviteitstest"
+ },
+ "fetchOnClient": {
+ "desc": "Clientaanvraagmodus zal sessieaanvragen rechtstreeks vanuit de browser initiëren, wat de responssnelheid kan verbeteren",
+ "title": "Gebruik clientaanvraagmodus"
+ },
+ "helpDoc": "Configuratiehandleiding",
+ "waitingForMore": "Meer modellen zijn in <1>planning voor integratie1>, blijf op de hoogte"
+ },
+ "createNew": {
+ "title": "Maak een aangepast AI-model"
+ },
+ "item": {
+ "config": "Configureer model",
+ "customModelCards": {
+ "addNew": "Maak en voeg {{id}} model toe",
+ "confirmDelete": "Je staat op het punt dit aangepaste model te verwijderen, na verwijdering kan het niet worden hersteld, wees voorzichtig."
+ },
+ "delete": {
+ "confirm": "Bevestig verwijdering van model {{displayName}}?",
+ "success": "Verwijdering geslaagd",
+ "title": "Verwijder model"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Het veld dat daadwerkelijk wordt aangevraagd in Azure OpenAI",
+ "placeholder": "Voer de modelimplementatienaam in Azure in",
+ "title": "Modelimplementatienaam"
+ },
+ "deployName": {
+ "extra": "Dit veld wordt als model-ID verzonden bij het indienen van een verzoek",
+ "placeholder": "Voer de naam of ID van het daadwerkelijk gedeployde model in",
+ "title": "Modeldeploynaam"
+ },
+ "displayName": {
+ "placeholder": "Voer de weergavenaam van het model in, bijvoorbeeld ChatGPT, GPT-4, enz.",
+ "title": "Weergavenaam van het model"
+ },
+ "files": {
+ "extra": "De huidige bestandsuploadimplementatie is slechts een hackoplossing, alleen voor eigen gebruik. Volledige bestandsuploadcapaciteit komt later beschikbaar.",
+ "title": "Ondersteuning voor bestandsupload"
+ },
+ "functionCall": {
+ "extra": "Deze configuratie schakelt alleen de mogelijkheid in voor het model om tools te gebruiken, waardoor het mogelijk is om plug-ins voor tools aan het model toe te voegen. Of het model daadwerkelijk tools kan gebruiken, hangt echter volledig af van het model zelf; test de bruikbaarheid zelf.",
+ "title": "Ondersteuning voor het gebruik van tools"
+ },
+ "id": {
+ "extra": "Kan niet worden gewijzigd na creatie, wordt gebruikt als model-id bij het aanroepen van AI",
+ "placeholder": "Voer model-id in, bijvoorbeeld gpt-4o of claude-3.5-sonnet",
+ "title": "Model ID"
+ },
+ "modalTitle": "Configuratie van aangepast model",
+ "reasoning": {
+ "extra": "Deze configuratie schakelt alleen de mogelijkheid voor diepgaand denken van het model in. Het specifieke effect hangt volledig af van het model zelf, test zelf of dit model in staat is tot bruikbaar diepgaand denken.",
+ "title": "Ondersteuning voor diepgaand denken"
+ },
+ "tokens": {
+ "extra": "Stel het maximale aantal tokens in dat door het model wordt ondersteund",
+ "title": "Maximale contextvenster",
+ "unlimited": "Onbeperkt"
+ },
+ "vision": {
+ "extra": "Deze configuratie zal alleen de afbeeldinguploadcapaciteit in de applicatie inschakelen, of herkenning wordt ondersteund hangt volledig af van het model zelf, test de beschikbaarheid van de visuele herkenningscapaciteit van dit model zelf.",
+ "title": "Ondersteuning voor visuele herkenning"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/Afbeelding",
+ "inputCharts": "${{amount}}/M Tekens",
+ "inputMinutes": "${{amount}}/Minuten",
+ "inputTokens": "Invoer ${{amount}}/M",
+ "outputTokens": "Uitvoer ${{amount}}/M"
+ },
+ "releasedAt": "Uitgebracht op {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Model toevoegen",
+ "disabled": "Niet ingeschakeld",
+ "disabledActions": {
+ "showMore": "Toon alles"
+ },
+ "empty": {
+ "desc": "Maak een aangepast model of haal een model op om te beginnen met gebruiken.",
+ "title": "Geen beschikbare modellen"
+ },
+ "enabled": "Ingeschakeld",
+ "enabledActions": {
+ "disableAll": "Alle uitschakelen",
+ "enableAll": "Alle inschakelen",
+ "sort": "Aangepaste model sortering"
+ },
+ "enabledEmpty": "Geen ingeschakelde modellen, schakel de modellen hieronder in die je leuk vindt~",
+ "fetcher": {
+ "clear": "Verwijder de opgehaalde modellen",
+ "fetch": "Haal modellenlijst op",
+ "fetching": "Bezig met het ophalen van de modellenlijst...",
+ "latestTime": "Laatste update tijd: {{time}}",
+ "noLatestTime": "Lijst nog niet opgehaald"
+ },
+ "resetAll": {
+ "conform": "Weet je zeker dat je alle wijzigingen van het huidige model wilt resetten? Na de reset zal de huidige modellenlijst terugkeren naar de standaardstatus",
+ "success": "Resetten geslaagd",
+ "title": "Reset alle wijzigingen"
+ },
+ "search": "Zoek modellen...",
+ "searchResult": "Gevonden {{count}} modellen",
+ "title": "Modellenlijst",
+ "total": "In totaal {{count}} modellen beschikbaar"
+ },
+ "searchNotFound": "Geen zoekresultaten gevonden"
+ },
+ "sortModal": {
+ "success": "Sortering succesvol bijgewerkt",
+ "title": "Aangepaste sortering",
+ "update": "Bijwerken"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Je staat op het punt deze AI-provider te verwijderen, na verwijdering kan deze niet worden hersteld, bevestig je verwijdering?",
+ "deleteSuccess": "Verwijdering geslaagd",
+ "tooltip": "Werk basisconfiguratie van provider bij",
+ "updateSuccess": "Bijwerking geslaagd"
+ },
+ "updateCustomAiProvider": {
+ "title": "Bijwerken van de configuratie van de aangepaste AI-provider"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Vul je Vertex AI-sleutels in",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI-sleutels"
}
},
"zeroone": {
diff --git a/DigitalHumanWeb/locales/nl-NL/models.json b/DigitalHumanWeb/locales/nl-NL/models.json
index fdfccbc..1c47a96 100644
--- a/DigitalHumanWeb/locales/nl-NL/models.json
+++ b/DigitalHumanWeb/locales/nl-NL/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B biedt superieure prestaties in de industrie met rijke trainingsvoorbeelden."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat is een variant van de Yi-1.5-serie, die behoort tot de open-source chatmodellen. Yi-1.5 is een upgrade van Yi, die is voorgetraind op 500B hoogwaardige corpus en is fijn afgesteld op meer dan 3M diverse voorbeelden. In vergelijking met Yi presteert Yi-1.5 beter in coderings-, wiskundige, redenerings- en instructievolgcapaciteiten, terwijl het uitstekende taalbegrip, algemene redenering en leesbegrip behoudt. Dit model heeft versies met contextlengtes van 4K, 16K en 32K, met een totale voortraining van 3.6T tokens."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B ondersteunt 16K tokens en biedt efficiënte, vloeiende taalgeneratiecapaciteiten."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Everything, het nieuwste open-source fine-tuning model, met 34 miljard parameters, dat fine-tuning ondersteunt voor verschillende dialoogscenario's, met hoogwaardige trainingsdata die zijn afgestemd op menselijke voorkeuren."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Everything, het nieuwste open-source fine-tuning model, met 9 miljard parameters, dat fine-tuning ondersteunt voor verschillende dialoogscenario's, met hoogwaardige trainingsdata die zijn afgestemd op menselijke voorkeuren."
+ },
"360gpt-pro": {
"description": "360GPT Pro, als een belangrijk lid van de 360 AI-modelreeks, voldoet aan de diverse natuurlijke taaltoepassingsscenario's met efficiënte tekstverwerkingscapaciteiten en ondersteunt lange tekstbegrip en meerdaagse gesprekken."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K legt de nadruk op semantische veiligheid en verantwoordelijkheid, speciaal ontworpen voor toepassingen met hoge eisen aan inhoudsveiligheid, en zorgt voor nauwkeurigheid en robuustheid in de gebruikerservaring."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 bouwt denkketens op met behulp van boomzoekmethoden en introduceert een reflectiemechanisme, getraind met versterkend leren, waardoor het model in staat is tot zelfreflectie en foutcorrectie."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro is een geavanceerd natuurlijk taalverwerkingsmodel dat is ontwikkeld door 360, met uitstekende tekstgeneratie- en begripcapaciteiten, vooral in de generatieve en creatieve domeinen, en kan complexe taaltransformaties en rolinterpretatietaken aan."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 bouwt een denkketen op met behulp van boomzoekmethoden en introduceert een reflectiemechanisme, waarbij het gebruik maakt van versterkend leren om het model in staat te stellen tot zelfreflectie en foutcorrectie."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra is de krachtigste versie in de Spark-grootmodelserie, die de netwerkintegratie heeft geüpgraded en de tekstbegrip- en samenvattingscapaciteiten heeft verbeterd. Het is een allesomvattende oplossing voor het verbeteren van de kantoorproductiviteit en het nauwkeurig reageren op behoeften, en is een toonaangevend intelligent product in de industrie."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Het model heeft de beste prestaties in het binnenland en overtreft buitenlandse mainstream modellen in kennisencyclopedieën, lange teksten en creatieve generaties. Het heeft ook toonaangevende multimodale capaciteiten en presteert uitstekend in verschillende autoritatieve evaluatiebenchmarks."
},
+ "Baichuan4-Air": {
+ "description": "Modelcapaciteiten zijn nationaal de beste, overtreft buitenlandse mainstream modellen in kennisencyclopedie, lange teksten en creatieve generatie in Chinese taken. Beschikt ook over toonaangevende multimodale capaciteiten en presteert uitstekend op verschillende autoritatieve evaluatiebenchmarks."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Modelcapaciteiten zijn nationaal de beste, overtreft buitenlandse mainstream modellen in kennisencyclopedie, lange teksten en creatieve generatie in Chinese taken. Beschikt ook over toonaangevende multimodale capaciteiten en presteert uitstekend op verschillende autoritatieve evaluatiebenchmarks."
+ },
+ "DeepSeek-R1": {
+ "description": "Een geavanceerd en efficiënt LLM, gespecialiseerd in redeneren, wiskunde en programmeren."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 - een groter en slimmer model binnen de DeepSeek-suite - is gedistilleerd naar de Llama 70B-architectuur. Op basis van benchmarktests en menselijke evaluaties is dit model slimmer dan het oorspronkelijke Llama 70B, vooral in taken die wiskunde en feitelijke nauwkeurigheid vereisen."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 distillatiemodel gebaseerd op Qwen2.5-Math-1.5B, geoptimaliseerd voor inferentieprestaties door versterkend leren en koude startdata, open-source model dat de multi-taak benchmark vernieuwt."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 distillatiemodel gebaseerd op Qwen2.5-14B, geoptimaliseerd voor inferentieprestaties door versterkend leren en koude startdata, open-source model dat de multi-taak benchmark vernieuwt."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "De DeepSeek-R1 serie optimaliseert inferentieprestaties door versterkend leren en koude startdata, open-source model dat de multi-taak benchmark vernieuwt en de OpenAI-o1-mini niveaus overtreft."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1 distillatiemodel gebaseerd op Qwen2.5-Math-7B, geoptimaliseerd voor inferentieprestaties door versterkend leren en koude startdata, open-source model dat de multi-taak benchmark vernieuwt."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro is een nieuw geüpgraded multimodaal groot model, dat ondersteuning biedt voor beeldherkenning met willekeurige resoluties en extreme beeldverhoudingen, en de visuele redenering, documentherkenning, begrip van gedetailleerde informatie en het volgen van instructies verbetert."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite beschikt over een uitstekende responssnelheid en een goede prijs-kwaliteitverhouding, en biedt klanten flexibele keuzes voor verschillende scenario's. Ondersteunt inferentie en fine-tuning met een contextvenster van 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite beschikt over een uitstekende responssnelheid en een goede prijs-kwaliteitverhouding, en biedt klanten flexibele keuzes voor verschillende scenario's. Ondersteunt inferentie en fine-tuning met een contextvenster van 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite beschikt over een uitstekende responssnelheid en een goede prijs-kwaliteitverhouding, en biedt klanten flexibele keuzes voor verschillende scenario's. Ondersteunt inferentie en fine-tuning met een contextvenster van 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "Het meest effectieve hoofmodel, geschikt voor het verwerken van complexe taken, met goede resultaten in referentievraag, samenvattingen, creatie, tekstclassificatie, rollenspellen en meer. Ondersteunt inferentie en fine-tuning met een contextvenster van 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "Het beste hoofdmachine model, geschikt voor het verwerken van complexe taken, met goede prestaties in referentievraag- en antwoordsituaties, samenvattingen, creatie, tekstclassificatie, rollenspellen, enz. Ondersteunt redenering en fine-tuning met een contextvenster van 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "Het meest effectieve hoofmodel, geschikt voor het verwerken van complexe taken, met goede resultaten in referentievraag, samenvattingen, creatie, tekstclassificatie, rollenspellen en meer. Ondersteunt inferentie en fine-tuning met een contextvenster van 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "Het meest effectieve hoofmodel, geschikt voor het verwerken van complexe taken, met goede resultaten in referentievraag, samenvattingen, creatie, tekstclassificatie, rollenspellen en meer. Ondersteunt inferentie en fine-tuning met een contextvenster van 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Het Doubao-vision model is een multimodaal groot model dat door Doubao is geïntroduceerd, met krachtige mogelijkheden voor beeldbegrip en redenering, evenals nauwkeurige instructiebegrip. Het model heeft sterke prestaties getoond in het extraheren van tekstinformatie uit afbeeldingen en op afbeeldingen gebaseerde redeneringstaken, en kan worden toegepast op complexere en bredere visuele vraag- en antwoordsituaties."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Het Doubao-vision model is een multimodaal groot model dat door Doubao is geïntroduceerd, met krachtige mogelijkheden voor beeldbegrip en redenering, evenals nauwkeurige instructiebegrip. Het model heeft sterke prestaties getoond in het extraheren van tekstinformatie uit afbeeldingen en op afbeeldingen gebaseerde redeneringstaken, en kan worden toegepast op complexere en bredere visuele vraag- en antwoordsituaties."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "De door Baidu ontwikkelde vlaggenschip grote taalmodel, dat een enorme hoeveelheid Chinese en Engelse gegevens dekt, met krachtige algemene capaciteiten die voldoen aan de meeste eisen voor dialoogvragen, creatieve generatie en plug-in toepassingsscenario's; ondersteunt automatische integratie met de Baidu zoekplug-in, wat de actualiteit van vraag- en antwoordinformatie waarborgt."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "De door Baidu ontwikkelde vlaggenschip grote taalmodel, dat een enorme hoeveelheid Chinese en Engelse gegevens dekt, met krachtige algemene capaciteiten die voldoen aan de meeste eisen voor dialoogvragen, creatieve generatie en plug-in toepassingsscenario's; ondersteunt automatische integratie met de Baidu zoekplug-in, wat de actualiteit van vraag- en antwoordinformatie waarborgt."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "De door Baidu ontwikkelde vlaggenschip grote taalmodel, dat een enorme hoeveelheid Chinese en Engelse gegevens dekt, met krachtige algemene capaciteiten die voldoen aan de meeste eisen voor dialoogvragen, creatieve generatie en plug-in toepassingsscenario's; ondersteunt automatische integratie met de Baidu zoekplug-in, wat de actualiteit van vraag- en antwoordinformatie waarborgt."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Het door Baidu ontwikkelde vlaggenschip van een ultra-groot taalmodel, dat in vergelijking met ERNIE 3.5 een algehele upgrade van de modelcapaciteiten heeft gerealiseerd, en breed toepasbaar is in complexe taken in verschillende domeinen; ondersteunt automatische integratie met de Baidu-zoekplug-in om de actualiteit van vraag- en antwoordinformatie te waarborgen."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Het door Baidu ontwikkelde vlaggenschip van een ultra-groot taalmodel, dat in vergelijking met ERNIE 3.5 een algehele upgrade van de modelcapaciteiten heeft gerealiseerd, en breed toepasbaar is in complexe taken in verschillende domeinen; ondersteunt automatische integratie met de Baidu-zoekplug-in om de actualiteit van vraag- en antwoordinformatie te waarborgen."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "De zelfontwikkelde vlaggenschip super-grote taalmodel van Baidu, dat uitmuntend presteert in diverse complexe taakscenario's in verschillende domeinen; ondersteunt automatische integratie met de Baidu-zoekplug-in, waarborgt de actualiteit van vraag-antwoordinformatie. Overtreft in performance ten opzichte van ERNIE 4.0."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Het door Baidu ontwikkelde vlaggenschip van een ultra-groot taalmodel, dat uitstekende algehele prestaties levert en breed toepasbaar is in complexe taken in verschillende domeinen; ondersteunt automatische integratie met de Baidu-zoekplug-in om de actualiteit van vraag- en antwoordinformatie te waarborgen. In vergelijking met ERNIE 4.0 presteert het beter."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Het door Baidu ontwikkelde verticale taalmodel, geschikt voor toepassingen zoals game NPC's, klantenservice gesprekken en rollenspellen, met een duidelijker en consistenter karakterontwerp, sterkere instructievolgcapaciteiten en betere inferentieprestaties."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Het door Baidu ontwikkelde lichte taalmodel, dat zowel uitstekende modelprestaties als inferentieprestaties biedt, met betere resultaten dan ERNIE Lite, en geschikt is voor inferentie op AI-versnelling kaarten met lage rekencapaciteit."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Het door Baidu in 2024 gepresenteerde nieuwe hoge-prestatie taalmodel, met uitstekende algemene capaciteiten, geschikt als basis model voor fine-tuning, om beter specifieke probleemstellingen aan te pakken, met uitstekende inferentieprestaties."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Het door Baidu in 2024 gepresenteerde nieuwe hoge-prestatie taalmodel, met uitstekende algemene capaciteiten, betere resultaten dan ERNIE Speed, en geschikt als basis model voor fine-tuning, om beter specifieke probleemstellingen aan te pakken, met uitstekende inferentieprestaties."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) is een innovatief model, geschikt voor toepassingen in meerdere domeinen en complexe taken."
},
- "Max-32k": {
- "description": "Spark Max 32K is uitgerust met een grote contextverwerkingscapaciteit, verbeterd begrip van context en logische redeneervaardigheden, ondersteunt tekstinvoer van 32K tokens, geschikt voor het lezen van lange documenten, privé kennisvragen en andere scenario's."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B is een krachtig visueel taalmodel dat multimodale verwerking van afbeeldingen en tekst ondersteunt, in staat om afbeeldingsinhoud nauwkeurig te identificeren en relevante beschrijvingen of antwoorden te genereren."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B is een krachtig visueel taalmodel dat multimodale verwerking van afbeeldingen en tekst ondersteunt, in staat om afbeeldingsinhoud nauwkeurig te identificeren en relevante beschrijvingen of antwoorden te genereren."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Uitstekende beeldredeneringscapaciteiten op hoge resolutie afbeeldingen, geschikt voor visuele begripstoepassingen."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Geavanceerde beeldredeneringscapaciteiten voor visuele begripstoepassingen."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct is een van de nieuwste grote taalmodellen die door Alibaba Cloud is uitgebracht. Dit 72B-model heeft aanzienlijke verbeteringen in coderings- en wiskundige vaardigheden. Het model biedt ook meertalige ondersteuning, met meer dan 29 ondersteunde talen, waaronder Chinees en Engels. Het model heeft aanzienlijke verbeteringen in het volgen van instructies, het begrijpen van gestructureerde gegevens en het genereren van gestructureerde uitvoer (vooral JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct is een van de nieuwste grote taalmodellen die door Alibaba Cloud is uitgebracht. Dit 7B-model heeft aanzienlijke verbeteringen in coderings- en wiskundige vaardigheden. Het model biedt ook meertalige ondersteuning, met meer dan 29 ondersteunde talen, waaronder Chinees en Engels. Het model heeft aanzienlijke verbeteringen in het volgen van instructies, het begrijpen van gestructureerde gegevens en het genereren van gestructureerde uitvoer (vooral JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Llama 3.1 instructie-geoptimaliseerd tekstmodel, geoptimaliseerd voor meertalige gesprekstoepassingen, presteert uitstekend op veel beschikbare open-source en gesloten chatmodellen op veelvoorkomende industriële benchmarks."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO is een zeer flexibele multi-model combinatie, ontworpen om een uitstekende creatieve ervaring te bieden."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Llama 3.1 instructie-geoptimaliseerd tekstmodel, geoptimaliseerd voor meertalige gesprekstoepassingen, presteert uitstekend op veel beschikbare open-source en gesloten chatmodellen op veelvoorkomende industriële benchmarks."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Llama 3.1 instructie-geoptimaliseerd tekstmodel, geoptimaliseerd voor meertalige gesprekstoepassingen, presteert uitstekend op veel beschikbare open-source en gesloten chatmodellen op veelvoorkomende industriële benchmarks."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Een geavanceerd, state-of-the-art klein taalmiddel met taalbegrip, uitstekende redeneervaardigheden en tekstgeneratiecapaciteiten."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Een geavanceerd, state-of-the-art klein taalmiddel met taalbegrip, uitstekende redeneervaardigheden en tekstgeneratiecapaciteiten."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 is het meest geavanceerde meertalige open-source grote taalmiddel in de Llama-serie, dat prestaties biedt die vergelijkbaar zijn met die van een 405B-model tegen zeer lage kosten. Gebaseerd op de Transformer-structuur en verbeterd door middel van supervisie-fijnstelling (SFT) en versterkend leren met menselijke feedback (RLHF) voor nuttigheid en veiligheid. De instructie-geoptimaliseerde versie is speciaal geoptimaliseerd voor meertalige gesprekken en presteert beter dan veel open-source en gesloten chatmodellen op verschillende industriële benchmarks. Kennisafkapdatum is december 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "In de MiniMax-01-serie modellen hebben we gedurfde innovaties doorgevoerd: voor het eerst op grote schaal een lineaire aandachtmechanisme geïmplementeerd, waardoor de traditionele Transformer-architectuur niet langer de enige keuze is. Dit model heeft een parameterhoeveelheid van maar liefst 456 miljard, met een enkele activatie van 45,9 miljard. De algehele prestaties van het model zijn vergelijkbaar met die van de beste modellen in het buitenland, terwijl het efficiënt de wereldwijd langste context van 4 miljoen tokens kan verwerken, wat 32 keer de capaciteit van GPT-4o en 20 keer die van Claude-3.5-Sonnet is."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) is een hoogprecisie instructiemodel, geschikt voor complexe berekeningen."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) biedt geoptimaliseerde taaloutput en diverse toepassingsmogelijkheden."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Vernieuwing van het Phi-3-mini model."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 toont uitstekende prestaties bij diverse visuele taaltaken, waaronder document- en grafiekbegrip, scène-tekstbegrip, OCR, en het oplossen van wetenschappelijke en wiskundige problemen."
},
"Phi-3-medium-128k-instruct": {
"description": "Hetzelfde Phi-3-medium model, maar met een grotere contextgrootte voor RAG of few shot prompting."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Een model met 7 miljard parameters, biedt betere kwaliteit dan Phi-3-mini, met een focus op hoogwaardige, redeneringsdichte gegevens."
},
- "Pro-128k": {
- "description": "Spark Pro-128K is uitgerust met een enorme contextverwerkingscapaciteit, in staat om tot 128K contextinformatie te verwerken, bijzonder geschikt voor lange teksten die volledige analyse en langdurige logische verbanden vereisen, en biedt vloeiende en consistente logica met diverse referenties in complexe tekstcommunicatie."
+ "Phi-3.5-mini-instruct": {
+ "description": "Een geüpdatete versie van het Phi-3-mini model."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Een geüpdatete versie van het Phi-3-vision model."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 toont uitstekende prestaties bij diverse visuele taaltaken, waaronder document- en grafiekbegrip, scène-tekstbegrip, OCR, en het oplossen van wetenschappelijke en wiskundige problemen."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct is een instructie-fijn afgesteld groot taalmodel in de Qwen2-serie, met een parameter grootte van 1.5B. Dit model is gebaseerd op de Transformer-architectuur en maakt gebruik van technieken zoals de SwiGLU-activeringsfunctie, aandacht QKV-bias en groepsquery-aandacht. Het presteert uitstekend in taalbegrip, generatie, meertalige capaciteiten, codering, wiskunde en redenering in verschillende benchmarktests, en overtreft de meeste open-source modellen. In vergelijking met Qwen1.5-1.8B-Chat toont Qwen2-1.5B-Instruct aanzienlijke prestatieverbeteringen in tests zoals MMLU, HumanEval, GSM8K, C-Eval en IFEval, ondanks een iets lager aantal parameters."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct is een instructie-fijn afgesteld groot taalmodel in de Qwen2-serie, met een parameter grootte van 7B. Dit model is gebaseerd op de Transformer-architectuur en maakt gebruik van technieken zoals de SwiGLU-activeringsfunctie, aandacht QKV-bias en groepsquery-aandacht. Het kan grote invoer verwerken. Dit model presteert uitstekend in taalbegrip, generatie, meertalige capaciteiten, codering, wiskunde en redenering in verschillende benchmarktests, en overtreft de meeste open-source modellen, en toont in sommige taken een concurrentievermogen vergelijkbaar met dat van propriëtaire modellen. Qwen2-7B-Instruct presteert beter dan Qwen1.5-7B-Chat in verschillende evaluaties, wat aanzienlijke prestatieverbeteringen aantoont."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL is de nieuwste iteratie van het Qwen-VL-model, dat de toonaangevende prestaties behaalde in benchmarktests voor visueel begrip."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct is een van de nieuwste grote taalmodellen die door Alibaba Cloud is uitgebracht. Dit 7B-model heeft aanzienlijke verbeteringen in coderings- en wiskundige vaardigheden. Het model biedt ook meertalige ondersteuning, met meer dan 29 ondersteunde talen, waaronder Chinees en Engels. Het model heeft aanzienlijke verbeteringen in het volgen van instructies, het begrijpen van gestructureerde gegevens en het genereren van gestructureerde uitvoer (vooral JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct is de nieuwste versie van de code-specifieke grote taalmodelreeks die door Alibaba Cloud is uitgebracht. Dit model is aanzienlijk verbeterd in codegeneratie, redenering en herstelcapaciteiten door training met 55 biljoen tokens, gebaseerd op Qwen2.5. Het versterkt niet alleen de coderingscapaciteiten, maar behoudt ook de voordelen van wiskundige en algemene vaardigheden. Het model biedt een meer uitgebreide basis voor praktische toepassingen zoals code-agenten."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat is de open-source versie van het GLM-4-serie voorgetrainde model, gelanceerd door Zhipu AI. Dit model presteert uitstekend in semantiek, wiskunde, redenering, code en kennis. Naast ondersteuning voor meerdaagse gesprekken, beschikt GLM-4-9B-Chat ook over geavanceerde functies zoals webbrowser, code-uitvoering, aangepaste tool-aanroepen (Function Call) en lange tekstredenering. Het model ondersteunt 26 talen, waaronder Chinees, Engels, Japans, Koreaans en Duits. In verschillende benchmarktests toont GLM-4-9B-Chat uitstekende prestaties, zoals AlignBench-v2, MT-Bench, MMLU en C-Eval. Dit model ondersteunt een maximale contextlengte van 128K, geschikt voor academisch onderzoek en commerciële toepassingen."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 is een inferentiemodel aangedreven door versterkend leren (RL), dat de problemen van herhaling en leesbaarheid in modellen aanpakt. Voor RL introduceert DeepSeek-R1 koude startdata, wat de inferentieprestaties verder optimaliseert. Het presteert vergelijkbaar met OpenAI-o1 in wiskunde, code en inferentietaken, en verbetert de algehele effectiviteit door zorgvuldig ontworpen trainingsmethoden."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 is een hybride expert (MoE) taalmodel met 6710 miljard parameters, dat gebruikmaakt van multi-head latent attention (MLA) en de DeepSeekMoE-architectuur, gecombineerd met een load balancing-strategie zonder extra verlies, om de inferentie- en trainingsefficiëntie te optimaliseren. Door voorgetraind te worden op 14,8 biljoen hoogwaardige tokens en vervolgens te worden fijngesteld met supervisie en versterkend leren, overtreft DeepSeek-V3 andere open-source modellen in prestaties en komt het dicht in de buurt van toonaangevende gesloten modellen."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma is een van de lichtgewicht, state-of-the-art open modelseries ontwikkeld door Google. Het is een groot taalmodel met alleen decodering, dat Engels ondersteunt en open gewichten, voorgetrainde varianten en instructie-fijn afgestelde varianten biedt. Het Gemma-model is geschikt voor verschillende tekstgeneratietaken, waaronder vraag-en-antwoord, samenvattingen en redenering. Dit 9B-model is getraind met 8 biljoen tokens. De relatief kleine omvang maakt het mogelijk om in omgevingen met beperkte middelen te worden geïmplementeerd, zoals laptops, desktops of uw eigen cloudinfrastructuur, waardoor meer mensen toegang hebben tot geavanceerde AI-modellen en innovatie wordt bevorderd."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 is een familie van meertalige grote taalmodellen ontwikkeld door Meta, inclusief voorgetrainde en instructie-fijn afgestelde varianten met parameter groottes van 8B, 70B en 405B. Dit 8B instructie-fijn afgestelde model is geoptimaliseerd voor meertalige gespreksscenario's en presteert uitstekend in verschillende industriële benchmarktests. Het model is getraind met meer dan 150 biljoen tokens van openbare gegevens en maakt gebruik van technieken zoals supervisie-fijn afstemming en versterkend leren met menselijke feedback om de bruikbaarheid en veiligheid van het model te verbeteren. Llama 3.1 ondersteunt tekstgeneratie en codegeneratie, met een kennisafkapdatum van december 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview is een innovatief natuurlijk taalverwerkingsmodel dat efficiënt complexe dialooggeneratie en contextbegripstaken kan verwerken."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview is een onderzoeksmodel ontwikkeld door het Qwen-team, dat zich richt op visuele redeneervaardigheden en unieke voordelen heeft in het begrijpen van complexe scènes en het oplossen van visueel gerelateerde wiskundige problemen."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Als testversie van Qwen2 biedt Qwen1.5 nauwkeurigere gespreksfunctionaliteit door gebruik te maken van grootschalige gegevens."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ is het inferentiemodel van de Qwen-serie. In vergelijking met traditionele instructie-geoptimaliseerde modellen beschikt QwQ over denk- en redeneervaardigheden, waardoor het in staat is om aanzienlijk verbeterde prestaties te leveren in downstream-taken, vooral bij het oplossen van moeilijke problemen. QwQ-32B is een middelgroot inferentiemodel dat concurrerende prestaties kan behalen in vergelijking met de meest geavanceerde inferentiemodellen (zoals DeepSeek-R1, o1-mini). Dit model maakt gebruik van technologieën zoals RoPE, SwiGLU, RMSNorm en Attention QKV bias, en heeft een netwerkstructuur van 64 lagen en 40 Q-aandachtshoofden (met KV van 8 in de GQA-architectuur)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) biedt snelle reacties en natuurlijke gesprekscapaciteiten, geschikt voor meertalige omgevingen."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview is het nieuwste experimentele onderzoeksmodel van Qwen, gericht op het verbeteren van AI-redeneringscapaciteiten. Door het verkennen van complexe mechanismen zoals taalmixing en recursieve redenering, zijn de belangrijkste voordelen onder andere krachtige redeneringsanalyses, wiskundige en programmeervaardigheden. Tegelijkertijd zijn er ook problemen met taalwisseling, redeneringscycli, veiligheidskwesties en verschillen in andere capaciteiten."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct is een instructie-fijn afgesteld groot taalmodel in de Qwen2-serie, met een parameter grootte van 1.5B. Dit model is gebaseerd op de Transformer-architectuur en maakt gebruik van technieken zoals de SwiGLU-activeringsfunctie, aandacht QKV-bias en groepsquery-aandacht. Het presteert uitstekend in taalbegrip, generatie, meertalige capaciteiten, codering, wiskunde en redenering in verschillende benchmarktests, en overtreft de meeste open-source modellen. In vergelijking met Qwen1.5-1.8B-Chat toont Qwen2-1.5B-Instruct aanzienlijke prestatieverbeteringen in tests zoals MMLU, HumanEval, GSM8K, C-Eval en IFEval, ondanks een iets lager aantal parameters."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 is een geavanceerd algemeen taalmodel dat verschillende soorten instructies ondersteunt."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct is een instructie-fijn afgesteld groot taalmodel in de Qwen2-serie, met een parameter grootte van 72B. Dit model is gebaseerd op de Transformer-architectuur en maakt gebruik van technieken zoals de SwiGLU-activeringsfunctie, aandacht QKV-bias en groepsquery-aandacht. Het kan grote invoer verwerken. Dit model presteert uitstekend in taalbegrip, generatie, meertalige capaciteiten, codering, wiskunde en redenering in verschillende benchmarktests, en overtreft de meeste open-source modellen, en toont in sommige taken een concurrentievermogen vergelijkbaar met dat van propriëtaire modellen."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL is de nieuwste iteratie van het Qwen-VL-model, dat de toonaangevende prestaties behaalde in benchmarktests voor visueel begrip."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 is een geheel nieuwe serie van grote taalmodellen, ontworpen om de verwerking van instructietaken te optimaliseren."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 is een geheel nieuwe serie van grote taalmodellen, ontworpen om de verwerking van instructietaken te optimaliseren."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 is een geheel nieuwe serie van grote taalmodellen, met sterkere begrip- en generatiecapaciteiten."
+ "description": "Een groot taalmodel ontwikkeld door het Alibaba Cloud Tongyi Qianwen-team"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 is een geheel nieuwe serie grote taalmodellen, met sterkere begrip- en generatiecapaciteiten."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 is een geheel nieuwe serie grote taalmodellen, ontworpen om de verwerking van instructietaken te optimaliseren."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 is een geheel nieuwe serie van grote taalmodellen, ontworpen om de verwerking van instructietaken te optimaliseren."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 is een geheel nieuwe serie grote taalmodellen, ontworpen om de verwerking van instructietaken te optimaliseren."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder richt zich op het schrijven van code."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math richt zich op het oplossen van wiskundige vraagstukken en biedt professionele antwoorden op moeilijke vragen."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct is de nieuwste versie van de code-specifieke grote taalmodelreeks die door Alibaba Cloud is uitgebracht. Dit model is aanzienlijk verbeterd in codegeneratie, redenering en herstelcapaciteiten door training met 55 biljoen tokens, gebaseerd op Qwen2.5. Het versterkt niet alleen de coderingscapaciteiten, maar behoudt ook de voordelen van wiskundige en algemene vaardigheden. Het model biedt een meer uitgebreide basis voor praktische toepassingen zoals code-agenten."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 is de nieuwste serie van het Qwen-model, dat 128k context ondersteunt. In vergelijking met de huidige beste open-source modellen, overtreft Qwen2-72B op het gebied van natuurlijke taalbegrip, kennis, code, wiskunde en meertaligheid aanzienlijk de huidige toonaangevende modellen."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 is de nieuwste serie van het Qwen-model, dat in staat is om de beste open-source modellen van gelijke grootte of zelfs grotere modellen te overtreffen. Qwen2 7B heeft aanzienlijke voordelen behaald in verschillende evaluaties, vooral op het gebied van code en begrip van het Chinees."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B is een krachtig visueel taalmodel dat multimodale verwerking van afbeeldingen en tekst ondersteunt, in staat om afbeeldingsinhoud nauwkeurig te herkennen en relevante beschrijvingen of antwoorden te genereren."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct is een groot taalmodel met 14 miljard parameters, met uitstekende prestaties, geoptimaliseerd voor Chinese en meertalige scenario's, en ondersteunt toepassingen zoals intelligente vraag-en-antwoord en contentgeneratie."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct is een groot taalmodel met 32 miljard parameters, met een evenwichtige prestatie, geoptimaliseerd voor Chinese en meertalige scenario's, en ondersteunt toepassingen zoals intelligente vraag-en-antwoord en contentgeneratie."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct ondersteunt 16k context en genereert lange teksten van meer dan 8K. Het ondersteunt functieaanroepen en naadloze interactie met externe systemen, wat de flexibiliteit en schaalbaarheid aanzienlijk vergroot. De kennis van het model is duidelijk toegenomen en de coderings- en wiskundige vaardigheden zijn sterk verbeterd, met ondersteuning voor meer dan 29 talen."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct is een groot taalmodel met 7 miljard parameters, dat function calls ondersteunt en naadloos kan interageren met externe systemen, wat de flexibiliteit en schaalbaarheid aanzienlijk vergroot. Geoptimaliseerd voor Chinese en meertalige scenario's, ondersteunt het toepassingen zoals intelligente vraag-en-antwoord en contentgeneratie."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct is een op grote schaal voorgetraind programmeerinstructiemodel met krachtige codebegrip- en generatiecapaciteiten, dat efficiënt verschillende programmeertaken kan verwerken, vooral geschikt voor slimme codegeneratie, automatiseringsscripts en het beantwoorden van programmeervragen."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct is een groot taalmodel dat speciaal is ontworpen voor codegeneratie, codebegrip en efficiënte ontwikkelingsscenario's, met een toonaangevende parameteromvang van 32B, dat kan voldoen aan diverse programmeerbehoeften."
+ },
+ "SenseChat": {
+ "description": "Basisversie van het model (V4), met een contextlengte van 4K, heeft sterke algemene capaciteiten."
+ },
+ "SenseChat-128K": {
+ "description": "Basisversie van het model (V4), met een contextlengte van 128K, presteert uitstekend in taken van begrip en generatie van lange teksten."
+ },
+ "SenseChat-32K": {
+ "description": "Basisversie van het model (V4), met een contextlengte van 32K, flexibel toepasbaar in verschillende scenario's."
+ },
+ "SenseChat-5": {
+ "description": "De nieuwste versie van het model (V5.5), met een contextlengte van 128K, heeft aanzienlijke verbeteringen in wiskundig redeneren, Engelse conversatie, instructievolging en begrip van lange teksten, en kan zich meten met GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "Dit is de nieuwste versie gebaseerd op V5.5, met significante verbeteringen in basisvaardigheden in het Chinees en Engels, chatten, exacte wetenschappen, geesteswetenschappen, schrijven, wiskundige logica en woordtelling in vergelijking met de vorige versie."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Met een contextlengte van 32K overtreft het de conversatiebegrip in het Kantonees van GPT-4 en kan het zich in verschillende domeinen zoals kennis, redeneren, wiskunde en coderen meten met GPT-4 Turbo."
+ },
+ "SenseChat-Character": {
+ "description": "Standaardversie van het model, met een contextlengte van 8K, hoge responsnelheid."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Geavanceerde versie van het model, met een contextlengte van 32K, met uitgebreide verbeteringen in capaciteiten, ondersteunt zowel Chinese als Engelse conversaties."
+ },
+ "SenseChat-Turbo": {
+ "description": "Geschikt voor snelle vraag-en-antwoord en modelafstemming."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "Dit is de nieuwste lichte versie van het model, die meer dan 90% van de capaciteiten van het volledige model bereikt en de kosten voor inferentie aanzienlijk verlaagt."
+ },
+ "SenseChat-Vision": {
+ "description": "De nieuwste versie van het model (V5.5) ondersteunt meerdere afbeeldingen als invoer en heeft aanzienlijke optimalisaties doorgevoerd in de basiscapaciteiten van het model, met verbeteringen in objecteigenschappenherkenning, ruimtelijke relaties, actie-evenementherkenning, scènebegrip, emotieherkenning, logische kennisredenering en tekstbegrip en -generatie."
+ },
+ "Skylark2-lite-8k": {
+ "description": "De tweede generatie Skylark (Skylark2) model, Skylark2-lite model heeft een hoge responssnelheid, geschikt voor scenario's met hoge realtimevereisten, kostenbewustzijn en lagere modelnauwkeurigheidsvereisten, met een contextvenster lengte van 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "De tweede generatie Skylark (Skylark2) model, Skylark2-pro versie heeft een hoge modelnauwkeurigheid, geschikt voor complexere tekstgeneratiescenario's zoals professionele copywriting, romanproductie, en hoogwaardig vertalen, met een contextvenster lengte van 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "De tweede generatie Skylark (Skylark2) model, Skylark2-pro model heeft een hoge modelnauwkeurigheid, geschikt voor complexere tekstgeneratiescenario's zoals professionele copywriting, romanproductie, en hoogwaardig vertalen, met een contextvenster lengte van 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "De tweede generatie Skylark (Skylark2) model, Skylark2-pro-character model heeft uitstekende rolspelin en chatmogelijkheden, en is goed in het aannemen van verschillende rollen op basis van gebruikersprompt, met een natuurlijk vloeiende conversatie. Ideaal voor het bouwen van chatbots, virtuele assistenten en online klantenservice met hoge responssnelheden."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "De tweede generatie Skylark (Skylark2) model, Skylark2-pro-turbo-8k biedt snellere inferentie en lagere kosten, met een contextvenster lengte van 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B is het open-source model van de ChatGLM-serie, ontwikkeld door Zhipu AI. Dit model behoudt de uitstekende kenmerken van de vorige generatie, zoals vloeiende gesprekken en lage implementatiedrempels, terwijl het nieuwe functies introduceert. Het maakt gebruik van meer diverse trainingsdata, een groter aantal trainingsstappen en een meer redelijke trainingsstrategie, en presteert uitstekend onder de voorgetrainde modellen van minder dan 10B. ChatGLM3-6B ondersteunt complexe scenario's zoals meerdaagse gesprekken, tool-aanroepen, code-uitvoering en agenttaken. Naast het gespreksmodel zijn ook het basismodel ChatGLM-6B-Base en het lange tekstgespreksmodel ChatGLM3-6B-32K open-source gemaakt. Dit model is volledig open voor academisch onderzoek en staat ook gratis commercieel gebruik toe na registratie."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B is de open-source versie die een geoptimaliseerde gesprekservaring biedt voor gespreksapplicaties."
},
+ "TeleAI/TeleChat2": {
+ "description": "Het TeleChat2-model is een generatief semantisch groot model dat van de grond af aan is ontwikkeld door China Telecom, en ondersteunt functies zoals encyclopedische vraag-en-antwoord, codegeneratie en lange tekstgeneratie, en biedt gebruikers gespreksadviesdiensten. Het kan met gebruikers communiceren, vragen beantwoorden, helpen bij creatie en efficiënt en gemakkelijk informatie, kennis en inspiratie bieden. Het model presteert goed in het omgaan met hallucinatieproblemen, lange tekstgeneratie en logische begrip."
+ },
+ "TeleAI/TeleMM": {
+ "description": "Het TeleMM multimodale grote model is een door China Telecom ontwikkeld model voor multimodale begrip, dat verschillende modaliteiten zoals tekst en afbeeldingen kan verwerken, en ondersteunt functies zoals beeldbegrip en grafiekanalyse, en biedt gebruikers cross-modale begripdiensten. Het model kan met gebruikers communiceren in meerdere modaliteiten, de invoer nauwkeurig begrijpen, vragen beantwoorden, helpen bij creatie en efficiënt multimodale informatie en inspiratie bieden. Het presteert uitstekend in multimodale taken zoals fijne perceptie en logische redenering."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct is een van de nieuwste grote taalmodellen die door Alibaba Cloud is uitgebracht. Dit 72B-model heeft aanzienlijke verbeteringen in coderings- en wiskundige vaardigheden. Het model biedt ook meertalige ondersteuning, met meer dan 29 ondersteunde talen, waaronder Chinees en Engels. Het model heeft aanzienlijke verbeteringen in het volgen van instructies, het begrijpen van gestructureerde gegevens en het genereren van gestructureerde uitvoer (vooral JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B heeft de uitstekende algemene taalvaardigheden van de oorspronkelijke modelserie behouden en heeft door incrementele training van 500 miljard hoogwaardige tokens de wiskundige logica en codevaardigheden aanzienlijk verbeterd."
+ },
"abab5.5-chat": {
"description": "Gericht op productiviteitsscenario's, ondersteunt complexe taakverwerking en efficiënte tekstgeneratie, geschikt voor professionele toepassingen."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Geoptimaliseerd voor Chinese personagegesprekken, biedt vloeiende en cultureel passende gespreksgeneratiecapaciteiten."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworks open-source functie-aanroepmodel biedt uitstekende instructie-uitvoeringscapaciteiten en aanpasbare functies."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2, ontwikkeld door Fireworks, is een hoogpresterend functie-aanroepmodel, gebaseerd op Llama-3 en geoptimaliseerd voor functie-aanroepen, gesprekken en instructies."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b is een visueel taalmodel dat zowel afbeeldingen als tekstinvoer kan verwerken, getraind op hoogwaardige gegevens, geschikt voor multimodale taken."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 is een geavanceerd groot taalmodel, geoptimaliseerd met versterkend leren en koude startdata, met uitstekende prestaties in redeneren, wiskunde en programmeren."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B instructiemodel, gebaseerd op eerdere Google-technologie, geschikt voor vraagbeantwoording, samenvattingen en redenering."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Een krachtige Mixture-of-Experts (MoE) taalmodel van Deepseek, met een totaal aantal parameters van 671B, waarbij 37B parameters per token worden geactiveerd."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Llama 3 70B instructiemodel, speciaal geoptimaliseerd voor meertalige gesprekken en natuurlijke taalbegrip, presteert beter dan de meeste concurrerende modellen."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B instructiemodel (HF-versie), consistent met de officiële implementatieresultaten, geschikt voor hoogwaardige instructietaken."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Llama 3 8B instructiemodel, geoptimaliseerd voor gesprekken en meertalige taken, presteert uitstekend en efficiënt."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Llama 3.1 8B instructiemodel, geoptimaliseerd voor meertalige gesprekken, kan de meeste open-source en gesloten-source modellen overtreffen op gangbare industriestandaarden."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Meta's 11B-parameter instructie-geoptimaliseerde beeldredeneringsmodel. Dit model is geoptimaliseerd voor visuele herkenning, beeldredenering, afbeeldingsbeschrijving en het beantwoorden van algemene vragen over afbeeldingen. Dit model kan visuele gegevens begrijpen, zoals diagrammen en grafieken, en overbrugt de kloof tussen visuele informatie en tekst door het genereren van tekstbeschrijvingen van afbeeldingsdetails."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Llama 3.2 3B instructiemodel is een lichtgewicht meertalig model geïntroduceerd door Meta. Dit model is ontworpen om de efficiëntie te verhogen, met aanzienlijke verbeteringen in latentie en kosten in vergelijking met grotere modellen. Voorbeelden van gebruikssituaties van dit model zijn het herformuleren van vragen en prompts, evenals schrijfondersteuning."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Meta's 90B-parameter instructie-geoptimaliseerde beeldredeneringsmodel. Dit model is geoptimaliseerd voor visuele herkenning, beeldredenering, afbeeldingsbeschrijving en het beantwoorden van algemene vragen over afbeeldingen. Dit model kan visuele gegevens begrijpen, zoals diagrammen en grafieken, en overbrugt de kloof tussen visuele informatie en tekst door het genereren van tekstbeschrijvingen van afbeeldingsdetails."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct is de update van december voor Llama 3.1 70B. Dit model is verbeterd op basis van Llama 3.1 70B (uitgebracht in juli 2024) en biedt verbeterde toolaanroepen, ondersteuning voor meertalige teksten, wiskunde en programmeervaardigheden. Het model heeft een toonaangevende prestatie bereikt op het gebied van redeneren, wiskunde en het volgen van instructies, en kan prestaties bieden die vergelijkbaar zijn met die van 3.1 405B, met aanzienlijke voordelen op het gebied van snelheid en kosten."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Een model met 24B parameters, dat geavanceerde mogelijkheden biedt die vergelijkbaar zijn met grotere modellen."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B instructiemodel, met een groot aantal parameters en een multi-expertarchitectuur, biedt uitgebreide ondersteuning voor de efficiënte verwerking van complexe taken."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B instructiemodel, met een multi-expertarchitectuur die efficiënte instructievolging en uitvoering biedt."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B instructiemodel (HF-versie), met prestaties die overeenkomen met de officiële implementatie, geschikt voor verschillende efficiënte taakscenario's."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "MythoMax L2 13B model, dat gebruik maakt van innovatieve samenvoegtechnologie, is goed in verhalen vertellen en rollenspellen."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision instructiemodel, een lichtgewicht multimodaal model dat complexe visuele en tekstuele informatie kan verwerken, met sterke redeneercapaciteiten."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5B model, ondersteunt geavanceerde programmeertaken, met verbeterde meertalige capaciteiten, geschikt voor complexe codegeneratie en -begrip."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Het QwQ-model is een experimenteel onderzoeksmodel ontwikkeld door het Qwen-team, gericht op het verbeteren van de AI-redeneringscapaciteiten."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "De 72B versie van het Qwen-VL model is het nieuwste resultaat van Alibaba's iteraties, dat bijna een jaar aan innovaties vertegenwoordigt."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7B model, getraind op meer dan 80 programmeertalen, met uitstekende programmeervulcapaciteiten en contextbegrip."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 is een serie decoder-only taalmodellen ontwikkeld door het Alibaba Qwen-team. Deze modellen zijn beschikbaar in verschillende groottes, waaronder 0.5B, 1.5B, 3B, 7B, 14B, 32B en 72B, met zowel een basisversie als een instructieversie."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct is de nieuwste versie van de code-specifieke grote taalmodelreeks die door Alibaba Cloud is uitgebracht. Dit model is aanzienlijk verbeterd in codegeneratie, redenering en herstelcapaciteiten door training met 55 biljoen tokens, gebaseerd op Qwen2.5. Het versterkt niet alleen de coderingscapaciteiten, maar behoudt ook de voordelen van wiskundige en algemene vaardigheden. Het model biedt een meer uitgebreide basis voor praktische toepassingen zoals code-agenten."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Yi-Large model, met uitstekende meertalige verwerkingscapaciteiten, geschikt voor verschillende taalgeneratie- en begripstaken."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Een meertalig model met 52 miljard parameters (12 miljard actief), biedt een contextvenster van 256K, functieaanroep, gestructureerde output en gegronde generatie."
},
- "ai21-jamba-instruct": {
- "description": "Een productieklare Mamba-gebaseerde LLM-model om de beste prestaties, kwaliteit en kostenefficiëntie te bereiken."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet heeft de industrienormen verbeterd, met prestaties die de concurrentiemodellen en Claude 3 Opus overtreffen, en presteert uitstekend in brede evaluaties, met de snelheid en kosten van ons gemiddelde model."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet heeft de industrienormen verhoogd, met prestaties die de concurrentiemodellen en Claude 3 Opus overtreffen. Het presteert uitstekend in uitgebreide evaluaties, terwijl het de snelheid en kosten van onze middelgrote modellen behoudt."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku is het snelste en meest compacte model van Anthropic, met bijna onmiddellijke reactietijden. Het kan snel eenvoudige vragen en verzoeken beantwoorden. Klanten kunnen een naadloze AI-ervaring creëren die menselijke interactie nabootst. Claude 3 Haiku kan afbeeldingen verwerken en tekstoutput retourneren, met een contextvenster van 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus is het krachtigste model van Anthropic voor het verwerken van zeer complexe taken. Het excelleert in prestaties, intelligentie, vloeiendheid en begrip."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku is het snelste volgende generatie model van Anthropic. In vergelijking met Claude 3 Haiku heeft Claude 3.5 Haiku verbeteringen in verschillende vaardigheden en overtreft het de grootste modellen van de vorige generatie, Claude 3 Opus, in veel intellectuele benchmarktests."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet biedt mogelijkheden die verder gaan dan Opus en een snellere snelheid dan Sonnet, terwijl het dezelfde prijs als Sonnet behoudt. Sonnet is bijzonder goed in programmeren, datawetenschap, visuele verwerking en agenttaken."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet is het meest geavanceerde model van Anthropic tot nu toe en het eerste hybride redeneermodel op de markt. Claude 3.7 Sonnet kan bijna onmiddellijke reacties of uitgebreide stapsgewijze overpeinzingen genereren, waarbij gebruikers deze processen duidelijk kunnen volgen. Sonnet is bijzonder goed in programmeren, datawetenschap, visuele verwerking en agenttaken."
+ },
"aya": {
"description": "Aya 23 is een meertalig model van Cohere, ondersteunt 23 talen en biedt gemak voor diverse taaltoepassingen."
},
"aya:35b": {
"description": "Aya 23 is een meertalig model van Cohere, ondersteunt 23 talen en biedt gemak voor diverse taaltoepassingen."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B is een open-source, commercieel bruikbaar groot taalmodel ontwikkeld door Baichuan Intelligent, met 13 miljard parameters, dat de beste prestaties in zijn klasse heeft behaald op gezaghebbende Chinese en Engelse benchmarks."
+ },
"charglm-3": {
"description": "CharGLM-3 is ontworpen voor rollenspellen en emotionele begeleiding, ondersteunt zeer lange meerdaagse herinneringen en gepersonaliseerde gesprekken, met brede toepassingen."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 biedt belangrijke vooruitgangen in capaciteiten voor bedrijven, waaronder de toonaangevende 200K token context, een aanzienlijke vermindering van de frequentie van modelhallucinaties, systeemprompten en een nieuwe testfunctie: functie-aanroepen."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku is het snelste volgende generatie model van Anthropic. In vergelijking met Claude 3 Haiku heeft Claude 3.5 Haiku verbeteringen in alle vaardigheden en overtreft het de grootste modellen van de vorige generatie, Claude 3 Opus, in veel intellectuele benchmarktests."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet biedt mogelijkheden die verder gaan dan Opus en is sneller dan Sonnet, terwijl het dezelfde prijs behoudt. Sonnet is bijzonder goed in programmeren, datawetenschap, visuele verwerking en agenttaken."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet biedt mogelijkheden die verder gaan dan Opus en is sneller dan Sonnet, terwijl het dezelfde prijs als Sonnet behoudt. Sonnet is bijzonder goed in programmeren, datawetenschap, visuele verwerking en agendataken."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet is een van de nieuwste modellen van Anthropic, met verbeterde prestaties en een groter contextvenster, waardoor het model beter in staat is om complexe taken uit te voeren."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku is het snelste en meest compacte model van Anthropic, ontworpen voor bijna onmiddellijke reacties. Het heeft snelle en nauwkeurige gerichte prestaties."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet biedt een ideale balans tussen intelligentie en snelheid voor bedrijfswerkbelastingen. Het biedt maximale bruikbaarheid tegen een lagere prijs, betrouwbaar en geschikt voor grootschalige implementatie."
},
- "claude-instant-1.2": {
- "description": "Het model van Anthropic is ontworpen voor lage latentie en hoge doorvoer in tekstgeneratie, en ondersteunt het genereren van honderden pagina's tekst."
- },
"codegeex-4": {
"description": "CodeGeeX-4 is een krachtige AI-programmeerassistent die slimme vraag- en antwoordmogelijkheden en code-aanvulling ondersteunt voor verschillende programmeertalen, waardoor de ontwikkelingssnelheid wordt verhoogd."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B is een meertalig codegeneratiemodel dat uitgebreide functionaliteit biedt, waaronder code-aanvulling en -generatie, code-interpreter, webzoekfunctie, functieaanroepen en repository-niveau codevragen, en dekt verschillende scenario's in softwareontwikkeling. Het is een top codegeneratiemodel met minder dan 10B parameters."
+ },
"codegemma": {
"description": "CodeGemma is een lichtgewicht taalmodel dat speciaal is ontworpen voor verschillende programmeertaken, ondersteunt snelle iteratie en integratie."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama is een LLM dat zich richt op codegeneratie en -discussie, met brede ondersteuning voor programmeertalen, geschikt voor ontwikkelaarsomgevingen."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama is een LLM die zich richt op codegeneratie en -discussie, met uitgebreide ondersteuning voor programmeertalen, geschikt voor ontwikkelaarsomgevingen."
+ },
"codellama:13b": {
"description": "Code Llama is een LLM dat zich richt op codegeneratie en -discussie, met brede ondersteuning voor programmeertalen, geschikt voor ontwikkelaarsomgevingen."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ is een hoogpresterend groot taalmodel, speciaal ontworpen voor echte zakelijke scenario's en complexe toepassingen."
},
+ "dall-e-2": {
+ "description": "De tweede generatie DALL·E model, ondersteunt realistischere en nauwkeurigere beeldgeneratie, met een resolutie die vier keer zo hoog is als die van de eerste generatie."
+ },
+ "dall-e-3": {
+ "description": "Het nieuwste DALL·E model, uitgebracht in november 2023. Ondersteunt realistischere en nauwkeurigere beeldgeneratie met een sterkere detailweergave."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct biedt betrouwbare instructieverwerkingscapaciteiten en ondersteunt toepassingen in verschillende sectoren."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 is een op versterkend leren (RL) aangedreven inferentiemodel dat de problemen van herhaling en leesbaarheid in het model oplost. Voor RL introduceerde DeepSeek-R1 koude startdata om de inferentieprestaties verder te optimaliseren. Het presteert vergelijkbaar met OpenAI-o1 in wiskunde, code en inferentietaken, en verbetert de algehele effectiviteit door zorgvuldig ontworpen trainingsmethoden."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek-R1 distillatiemodel, geoptimaliseerd voor inferentieprestaties door versterkend leren en koude startdata, open-source model dat de multi-taak benchmark vernieuwt."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B is een distillatiemodel ontwikkeld op basis van Llama-3.1-8B. Dit model is fijn afgestemd met voorbeelden gegenereerd door DeepSeek-R1 en toont uitstekende inferentiecapaciteiten. Het heeft goed gepresteerd in verschillende benchmarktests, met een nauwkeurigheid van 89,1% op MATH-500, een slaagpercentage van 50,4% op AIME 2024, en een score van 1205 op CodeForces, wat sterke wiskundige en programmeercapaciteiten aantoont voor een model van 8B schaal."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 distillatiemodel, geoptimaliseerd voor inferentieprestaties door versterkend leren en koude startdata, open-source model dat de multi-taak benchmark vernieuwt."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 distillatiemodel, geoptimaliseerd voor inferentieprestaties door versterkend leren en koude startdata, open-source model dat de multi-taak benchmark vernieuwt."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B is een model dat is verkregen door kennisdistillatie van Qwen2.5-32B. Dit model is fijn afgestemd met 800.000 zorgvuldig geselecteerde voorbeelden gegenereerd door DeepSeek-R1 en toont uitstekende prestaties in verschillende domeinen zoals wiskunde, programmeren en redeneren. Het heeft uitstekende resultaten behaald in meerdere benchmarktests, waaronder een nauwkeurigheid van 94,3% op MATH-500, wat sterke wiskundige redeneringscapaciteiten aantoont."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B is een model dat is verkregen door kennisdistillatie van Qwen2.5-Math-7B. Dit model is fijn afgestemd met 800.000 zorgvuldig geselecteerde voorbeelden gegenereerd door DeepSeek-R1 en toont uitstekende inferentiecapaciteiten. Het heeft uitstekende resultaten behaald in verschillende benchmarktests, met een nauwkeurigheid van 92,8% op MATH-500, een slaagpercentage van 55,5% op AIME 2024, en een score van 1189 op CodeForces, wat sterke wiskundige en programmeercapaciteiten aantoont voor een model van 7B schaal."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 combineert de uitstekende kenmerken van eerdere versies en versterkt de algemene en coderingscapaciteiten."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 is een hybride expert (MoE) taalmodel met 6710 miljard parameters, dat gebruikmaakt van multi-head latent attention (MLA) en de DeepSeekMoE-architectuur, gecombineerd met een load balancing-strategie zonder extra verlies, om de inferentie- en trainingsefficiëntie te optimaliseren. Door voorgetraind te worden op 14,8 biljoen hoogwaardige tokens en vervolgens te worden fijngetuned met supervisie en versterkend leren, overtreft DeepSeek-V3 andere open-source modellen in prestaties en komt het dicht in de buurt van toonaangevende gesloten modellen."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B is een geavanceerd model dat is getraind voor complexe gesprekken."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "Geavanceerd efficiënt LLM, gespecialiseerd in redeneren, wiskunde en programmeren."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 is een hybride expert (MoE) visueel taalmodel dat is ontwikkeld op basis van DeepSeekMoE-27B, met een MoE-architectuur met spaarzame activatie, die uitstekende prestaties levert met slechts 4,5 miljard geactiveerde parameters. Dit model presteert uitstekend in verschillende taken, waaronder visuele vraag-antwoord, optische tekenherkenning, document/tabel/grafiekbegrip en visuele positionering."
+ },
"deepseek-chat": {
"description": "Een nieuw open-source model dat algemene en code-capaciteiten combineert, behoudt niet alleen de algemene conversatiecapaciteiten van het oorspronkelijke Chat-model en de krachtige codeverwerkingscapaciteiten van het Coder-model, maar is ook beter afgestemd op menselijke voorkeuren. Bovendien heeft DeepSeek-V2.5 aanzienlijke verbeteringen gerealiseerd in schrijfopdrachten, instructievolging en andere gebieden."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B is een code-taalmodel, getraind op 20 biljoen gegevens, waarvan 87% code en 13% in het Chinees en Engels. Het model introduceert een venstergrootte van 16K en invultaken, en biedt projectniveau code-aanvulling en fragmentinvulfunctionaliteit."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 is een open-source hybride expertcode-model, presteert uitstekend in code-taken en is vergelijkbaar met GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 is een open-source hybride expertcode-model, presteert uitstekend in code-taken en is vergelijkbaar met GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 is een op versterkend leren (RL) aangedreven inferentiemodel dat de problemen van herhaling en leesbaarheid in het model oplost. Voor RL introduceerde DeepSeek-R1 koude startdata om de inferentieprestaties verder te optimaliseren. Het presteert vergelijkbaar met OpenAI-o1 in wiskunde, code en inferentietaken, en verbetert de algehele effectiviteit door zorgvuldig ontworpen trainingsmethoden."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - een groter en slimmer model binnen de DeepSeek suite - is gedistilleerd naar de Llama 70B architectuur. Op basis van benchmarktests en menselijke evaluaties is dit model slimmer dan de originele Llama 70B, vooral in taken die wiskundige en feitelijke nauwkeurigheid vereisen."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Het DeepSeek-R1-Distill model is verkregen door middel van kennisdistillatie-technologie, waarbij samples gegenereerd door DeepSeek-R1 zijn afgestemd op open-source modellen zoals Qwen en Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Het DeepSeek-R1-Distill model is verkregen door middel van kennisdistillatie-technologie, waarbij samples gegenereerd door DeepSeek-R1 zijn afgestemd op open-source modellen zoals Qwen en Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Het DeepSeek-R1-Distill model is verkregen door middel van kennisdistillatie-technologie, waarbij samples gegenereerd door DeepSeek-R1 zijn afgestemd op open-source modellen zoals Qwen en Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Het DeepSeek-R1-Distill model is verkregen door middel van kennisdistillatie-technologie, waarbij samples gegenereerd door DeepSeek-R1 zijn afgestemd op open-source modellen zoals Qwen en Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Het DeepSeek-R1-Distill model is verkregen door middel van kennisdistillatie-technologie, waarbij samples gegenereerd door DeepSeek-R1 zijn afgestemd op open-source modellen zoals Qwen en Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "Het redeneer model van DeepSeek. Voordat het model het uiteindelijke antwoord geeft, genereert het eerst een stuk denkproces om de nauwkeurigheid van het uiteindelijke antwoord te verbeteren."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 is een efficiënt Mixture-of-Experts taalmodel, geschikt voor kosteneffectieve verwerkingsbehoeften."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B is het ontwerpcode-model van DeepSeek, biedt krachtige codegeneratiecapaciteiten."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 is een MoE-model dat is ontwikkeld door Hangzhou DeepSeek Artificial Intelligence Technology Research Co., Ltd. Het heeft uitstekende scores in verschillende evaluaties en staat bovenaan de open-source modellen in de mainstream ranglijsten. V3 heeft de generatiesnelheid met 3 keer verbeterd in vergelijking met het V2.5 model, wat zorgt voor een snellere en soepelere gebruikerservaring."
+ },
"deepseek/deepseek-chat": {
"description": "Een nieuw open-source model dat algemene en codeercapaciteiten combineert, niet alleen de algemene gespreksvaardigheden van het oorspronkelijke Chat-model en de krachtige codeverwerkingscapaciteiten van het Coder-model behoudt, maar ook beter is afgestemd op menselijke voorkeuren. Bovendien heeft DeepSeek-V2.5 aanzienlijke verbeteringen gerealiseerd in schrijfopdrachten, instructievolging en meer."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 heeft de redeneringscapaciteiten van het model aanzienlijk verbeterd, zelfs met zeer weinig gelabelde gegevens. Voordat het model het uiteindelijke antwoord geeft, genereert het eerst een denkproces om de nauwkeurigheid van het uiteindelijke antwoord te verbeteren."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B is een groot taalmodel gebaseerd op Llama3.3 70B, dat gebruikmaakt van de fine-tuning van DeepSeek R1-output en vergelijkbare concurrentieprestaties bereikt als grote vooraanstaande modellen."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B is een gedistilleerd groot taalmodel gebaseerd op Llama-3.1-8B-Instruct, dat is getraind met behulp van de output van DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B is een gedistilleerd groot taalmodel gebaseerd op Qwen 2.5 14B, dat is getraind met behulp van de output van DeepSeek R1. Dit model heeft in verschillende benchmarktests OpenAI's o1-mini overtroffen en heeft de nieuwste technologische vooruitgang behaald voor dichte modellen (state-of-the-art). Hier zijn enkele resultaten van benchmarktests:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nDit model toont concurrentieprestaties die vergelijkbaar zijn met grotere vooraanstaande modellen door fine-tuning op de output van DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B is een gedistilleerd groot taalmodel gebaseerd op Qwen 2.5 32B, dat is getraind met behulp van de output van DeepSeek R1. Dit model heeft in verschillende benchmarktests OpenAI's o1-mini overtroffen en heeft de nieuwste technologische vooruitgang behaald voor dichte modellen (state-of-the-art). Hier zijn enkele resultaten van benchmarktests:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nDit model toont concurrentieprestaties die vergelijkbaar zijn met grotere vooraanstaande modellen door fine-tuning op de output van DeepSeek R1."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 is het nieuwste open-source model dat door het DeepSeek-team is uitgebracht, met zeer krachtige inferentieprestaties, vooral op het gebied van wiskunde, programmeren en redeneringstaken, en bereikt een niveau dat vergelijkbaar is met het o1-model van OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 heeft de redeneringscapaciteiten van het model aanzienlijk verbeterd, zelfs met zeer weinig gelabelde gegevens. Voordat het model het uiteindelijke antwoord geeft, genereert het eerst een denkproces om de nauwkeurigheid van het uiteindelijke antwoord te verbeteren."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 heeft een belangrijke doorbraak bereikt in inferentiesnelheid ten opzichte van eerdere modellen. Het staat op de eerste plaats onder open-source modellen en kan zich meten met de meest geavanceerde gesloten modellen ter wereld. DeepSeek-V3 maakt gebruik van Multi-Head Latent Attention (MLA) en de DeepSeekMoE-architectuur, die grondig zijn gevalideerd in DeepSeek-V2. Bovendien introduceert DeepSeek-V3 een aanvullende verliesloze strategie voor load balancing en stelt het multi-label voorspellingsdoelen in om sterkere prestaties te behalen."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 heeft een belangrijke doorbraak bereikt in inferentiesnelheid ten opzichte van eerdere modellen. Het staat op de eerste plaats onder open-source modellen en kan zich meten met de meest geavanceerde gesloten modellen ter wereld. DeepSeek-V3 maakt gebruik van Multi-Head Latent Attention (MLA) en de DeepSeekMoE-architectuur, die grondig zijn gevalideerd in DeepSeek-V2. Bovendien introduceert DeepSeek-V3 een aanvullende verliesloze strategie voor load balancing en stelt het multi-label voorspellingsdoelen in om sterkere prestaties te behalen."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite is de nieuwste generatie lichtgewicht model, met extreme responssnelheid en prestaties die wereldwijd tot de top behoren."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k is een uitgebreide upgrade van Doubao-1.5-Pro, met een algehele prestatieverbetering van 10%. Ondersteunt redenering met een contextvenster van 256k en een maximale uitvoerlengte van 12k tokens. Hogere prestaties, groter venster, uitstekende prijs-kwaliteitverhouding, geschikt voor een breder scala aan toepassingsscenario's."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro is de nieuwste generatie hoofdmachine, met algehele prestatie-upgrades en uitstekende prestaties op het gebied van kennis, code, redenering, enz."
+ },
"emohaa": {
"description": "Emohaa is een psychologisch model met professionele adviescapaciteiten, dat gebruikers helpt emotionele problemen te begrijpen."
},
+ "ernie-3.5-128k": {
+ "description": "Het vlaggenschip grote taalmodel van Baidu, zelf ontwikkeld, dekt een enorme hoeveelheid Chinese en Engelse corpora, met sterke algemene capaciteiten die voldoen aan de meeste eisen voor dialoogvragen, creatieve generatie en plug-in toepassingsscenario's; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen."
+ },
+ "ernie-3.5-8k": {
+ "description": "Het vlaggenschip grote taalmodel van Baidu, zelf ontwikkeld, dekt een enorme hoeveelheid Chinese en Engelse corpora, met sterke algemene capaciteiten die voldoen aan de meeste eisen voor dialoogvragen, creatieve generatie en plug-in toepassingsscenario's; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Het vlaggenschip grote taalmodel van Baidu, zelf ontwikkeld, dekt een enorme hoeveelheid Chinese en Engelse corpora, met sterke algemene capaciteiten die voldoen aan de meeste eisen voor dialoogvragen, creatieve generatie en plug-in toepassingsscenario's; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Het vlaggenschip ultra-grote taalmodel van Baidu, zelf ontwikkeld, heeft een algehele upgrade van modelcapaciteiten in vergelijking met ERNIE 3.5, en is breed toepasbaar in complexe taakscenario's in verschillende domeinen; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Het vlaggenschip ultra-grote taalmodel van Baidu, zelf ontwikkeld, heeft een algehele upgrade van modelcapaciteiten in vergelijking met ERNIE 3.5, en is breed toepasbaar in complexe taakscenario's in verschillende domeinen; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Het vlaggenschip ultra-grote taalmodel van Baidu, zelf ontwikkeld, presteert uitstekend in algehele effectiviteit en is breed toepasbaar in complexe taakscenario's in verschillende domeinen; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen. Het presteert beter dan ERNIE 4.0."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Het vlaggenschip ultra-grote taalmodel van Baidu, zelf ontwikkeld, presteert uitstekend in algehele effectiviteit en is breed toepasbaar in complexe taakscenario's in verschillende domeinen; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen. Het presteert beter dan ERNIE 4.0."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Het vlaggenschip ultra-grote taalmodel van Baidu, zelf ontwikkeld, presteert uitstekend in algehele effectiviteit en is breed toepasbaar in complexe taakscenario's in verschillende domeinen; ondersteunt automatische integratie met Baidu zoekplug-ins om de actualiteit van vraag- en antwoordinformatie te waarborgen. Het presteert beter dan ERNIE 4.0."
+ },
+ "ernie-char-8k": {
+ "description": "Een door Baidu ontwikkeld groot taalmodel voor verticale scenario's, geschikt voor toepassingen zoals game NPC's, klantenservice dialoog, en rollenspellen, met een duidelijkere en consistentere karakterstijl, sterkere instructievolgcapaciteiten en betere inferentieprestaties."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Een door Baidu ontwikkeld groot taalmodel voor verticale scenario's, geschikt voor toepassingen zoals game NPC's, klantenservice dialoog, en rollenspellen, met een duidelijkere en consistentere karakterstijl, sterkere instructievolgcapaciteiten en betere inferentieprestaties."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite is een lichtgewicht groot taalmodel dat door Baidu is ontwikkeld, dat uitstekende modelprestaties en inferentiecapaciteiten combineert, geschikt voor gebruik met AI-versnelling kaarten met lage rekencapaciteit."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Een lichtgewicht groot taalmodel dat door Baidu is ontwikkeld, dat uitstekende modelprestaties en inferentiecapaciteiten combineert, met betere prestaties dan ERNIE Lite, geschikt voor gebruik met AI-versnelling kaarten met lage rekencapaciteit."
+ },
+ "ernie-novel-8k": {
+ "description": "Een algemeen groot taalmodel dat door Baidu is ontwikkeld, met duidelijke voordelen in het vervolgschrijven van romans, en ook toepasbaar in korte toneelstukken, films en andere scenario's."
+ },
+ "ernie-speed-128k": {
+ "description": "Het nieuwste zelfontwikkelde hoge-prestatie grote taalmodel van Baidu, dat uitstekende algemene capaciteiten heeft en geschikt is als basis model voor afstemming, om beter specifieke scenario's aan te pakken, met uitstekende inferentieprestaties."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Het nieuwste zelfontwikkelde hoge-prestatie grote taalmodel van Baidu, dat uitstekende algemene capaciteiten heeft en betere prestaties levert dan ERNIE Speed, geschikt als basis model voor afstemming, om beter specifieke scenario's aan te pakken, met uitstekende inferentieprestaties."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny is een ultra-presterend groot taalmodel dat de laagste implementatie- en afstemmingskosten heeft binnen de Wenxin modelreeks."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) biedt stabiele en afstelbare prestaties, ideaal voor oplossingen voor complexe taken."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro is Google's high-performance AI-model, ontworpen voor brede taakuitbreiding."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash is het nieuwste multimodale AI-model van Google, met snelle verwerkingscapaciteiten, ondersteuning voor tekst-, beeld- en video-invoer, en efficiënt schaalbaar voor verschillende taken."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 is een efficiënt multimodaal model dat ondersteuning biedt voor brede toepassingsuitbreiding."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 is een efficiënt multimodaal model dat ondersteuning biedt voor een breed scala aan toepassingen."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 is ontworpen voor het verwerken van grootschalige taakscenario's en biedt ongeëvenaarde verwerkingssnelheid."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B is een efficiënte multimodale model dat een breed scala aan toepassingen ondersteunt."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 is het nieuwste experimentele model, met aanzienlijke prestatieverbeteringen in tekst- en multimodale toepassingen."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 biedt geoptimaliseerde multimodale verwerkingscapaciteiten, geschikt voor verschillende complexe taakscenario's."
+ "description": "Gemini 1.5 Flash 0827 biedt geoptimaliseerde multimodale verwerkingscapaciteiten, geschikt voor verschillende complexe taak scenario's."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash is Google's nieuwste multimodale AI-model, met snelle verwerkingscapaciteiten, ondersteunt tekst-, beeld- en video-invoer, en is geschikt voor efficiënte opschaling van verschillende taken."
@@ -354,7 +819,7 @@
"description": "Gemini 1.5 Pro 002 is het nieuwste productieklare model, dat hogere kwaliteit output biedt, met name op het gebied van wiskunde, lange contexten en visuele taken."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 biedt uitstekende multimodale verwerkingscapaciteiten en biedt meer flexibiliteit voor applicatieontwikkeling."
+ "description": "Gemini 1.5 Pro 0801 biedt uitstekende multimodale verwerkingscapaciteiten, wat grotere flexibiliteit in applicatieontwikkeling mogelijk maakt."
},
"gemini-1.5-pro-exp-0827": {
"description": "Gemini 1.5 Pro 0827 combineert de nieuwste optimalisatietechnologieën en biedt efficiëntere multimodale gegevensverwerkingscapaciteiten."
@@ -362,6 +827,30 @@
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro ondersteunt tot 2 miljoen tokens en is de ideale keuze voor middelgrote multimodale modellen, geschikt voor veelzijdige ondersteuning van complexe taken."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash biedt next-gen functies en verbeteringen, waaronder uitstekende snelheid, native toolgebruik, multimodale generatie en een contextvenster van 1M tokens."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash biedt next-gen functies en verbeteringen, waaronder uitstekende snelheid, native toolgebruik, multimodale generatie en een contextvenster van 1M tokens."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash is een modelvariant die is geoptimaliseerd voor kosteneffectiviteit en lage latentie."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash is een modelvariant die is geoptimaliseerd voor kosteneffectiviteit en lage latentie."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Een Gemini 2.0 Flash-model dat is geoptimaliseerd voor kosteneffectiviteit en lage latentie."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp is Google's nieuwste experimentele multimodale AI-model, met next-gen functies, uitstekende snelheid, native tool-aanroepen en multimodale generatie."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp is Google's nieuwste experimentele multimodale AI-model, met next-gen functies, uitstekende snelheid, native tool-aanroepen en multimodale generatie."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental is Google's nieuwste experimentele multimodale AI-model, met aanzienlijke kwaliteitsverbeteringen ten opzichte van eerdere versies, vooral op het gebied van wereldkennis, code en lange context."
+ },
"gemma-7b-it": {
"description": "Gemma 7B is geschikt voor het verwerken van middelgrote taken, met een goede kosteneffectiviteit."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 is een efficiënt model van Google, dat een breed scala aan toepassingsscenario's dekt, van kleine toepassingen tot complexe gegevensverwerking."
},
- "general": {
- "description": "Spark Lite is een lichtgewicht groot taalmodel met extreem lage latentie en efficiënte verwerkingscapaciteiten, volledig gratis en open, met ondersteuning voor realtime online zoekfunctionaliteit. De snelle respons maakt het uitermate geschikt voor inferentie-toepassingen en modelfijnstelling op apparaten met lage rekenkracht, en biedt gebruikers uitstekende kosteneffectiviteit en een intelligente ervaring, vooral in kennisvragen, inhoudsgeneratie en zoekscenario's."
- },
"generalv3": {
"description": "Spark Pro is een hoogwaardig groot taalmodel dat is geoptimaliseerd voor professionele domeinen, met een focus op wiskunde, programmeren, geneeskunde, onderwijs en meer, en ondersteunt online zoeken en ingebouwde plugins voor weer, datum, enz. Het geoptimaliseerde model toont uitstekende prestaties en efficiëntie in complexe kennisvragen, taalbegrip en hoogwaardig tekstcreatie, en is de ideale keuze voor professionele toepassingsscenario's."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 is de nieuwste modelversie, speciaal ontworpen voor zeer complexe en diverse taken, met uitstekende prestaties."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat presteert goed op het gebied van semantiek, wiskunde, redeneren, code en kennis. Het beschikt ook over webbrowserfunctionaliteit, code-uitvoering, aangepaste toolaanroepen en lange tekstredenering. Ondersteunt 26 talen, waaronder Japans, Koreaans en Duits."
+ },
"glm-4-air": {
"description": "GLM-4-Air is een kosteneffectieve versie met prestaties die dicht bij GLM-4 liggen, met snelle snelheid en een betaalbare prijs."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash is de ideale keuze voor het verwerken van eenvoudige taken, met de snelste snelheid en de laagste prijs."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX is een verbeterde versie van Flash met een super snelle inferentiesnelheid."
+ },
"glm-4-long": {
"description": "GLM-4-Long ondersteunt zeer lange tekstinvoer, geschikt voor geheugenintensieve taken en grootschalige documentverwerking."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V biedt krachtige beeldbegrip- en redeneercapaciteiten, ondersteunt verschillende visuele taken."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash richt zich op efficiënte enkele afbeelding begrip, en is geschikt voor scenario's met snelle afbeeldingsanalyse, zoals real-time beeldanalyse of batchafbeeldingsverwerking."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus heeft de capaciteit om video-inhoud en meerdere afbeeldingen te begrijpen, geschikt voor multimodale taken."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 biedt geoptimaliseerde multimodale verwerkingscapaciteiten, geschikt voor verschillende complexe taakscenario's."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview heeft krachtige complexe redeneercapaciteiten en presteert uitstekend in logische redenering, wiskunde en programmeren."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash biedt next-gen functies en verbeteringen, waaronder uitstekende snelheid, native toolgebruik, multimodale generatie en een contextvenster van 1M tokens."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 combineert de nieuwste optimalisatietechnologieën voor efficiëntere multimodale gegevensverwerking."
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental is Google's nieuwste experimentele multimodale AI-model, met aanzienlijke kwaliteitsverbeteringen ten opzichte van eerdere versies, vooral op het gebied van wereldkennis, code en lange context."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash biedt geoptimaliseerde multimodale verwerkingscapaciteiten, geschikt voor verschillende complexe taakscenario's."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro combineert de nieuwste optimalisatietechnologieën en biedt efficiëntere multimodale gegevensverwerkingscapaciteiten."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 is een efficiënt model van Google, dat een breed scala aan toepassingen dekt, van kleine toepassingen tot complexe gegevensverwerking."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 behoudt het ontwerpprincipe van lichtgewicht en efficiëntie."
},
+ "google/gemma-2-2b-it": {
+ "description": "Google's lichtgewicht instructieafstemmingsmodel"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 is een efficiënt model van Google, dat een breed scala aan toepassingen dekt, van kleine toepassingen tot complexe gegevensverwerking."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 is een lichtgewicht open-source tekstmodelserie van Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, geschikt voor verschillende tekstgeneratie- en begrijptaken, wijst momenteel naar gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo, een efficiënt model aangeboden door OpenAI, geschikt voor chat- en tekstgeneratietaken, met ondersteuning voor parallelle functieaanroepen."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k, een tekstgeneratiemodel met hoge capaciteit, geschikt voor complexe taken."
+ },
"gpt-4": {
"description": "GPT-4 biedt een groter contextvenster en kan langere tekstinvoer verwerken, geschikt voor scenario's die uitgebreide informatie-integratie en data-analyse vereisen."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "Het nieuwste GPT-4 Turbo-model heeft visuele functies. Nu kunnen visuele verzoeken worden gedaan met behulp van JSON-indeling en functieaanroepen. GPT-4 Turbo is een verbeterde versie die kosteneffectieve ondersteuning biedt voor multimodale taken. Het vindt een balans tussen nauwkeurigheid en efficiëntie, geschikt voor toepassingen die realtime interactie vereisen."
},
- "gpt-4-1106-vision-preview": {
- "description": "Het nieuwste GPT-4 Turbo-model heeft visuele functies. Nu kunnen visuele verzoeken worden gedaan met behulp van JSON-indeling en functieaanroepen. GPT-4 Turbo is een verbeterde versie die kosteneffectieve ondersteuning biedt voor multimodale taken. Het vindt een balans tussen nauwkeurigheid en efficiëntie, geschikt voor toepassingen die realtime interactie vereisen."
- },
"gpt-4-32k": {
"description": "GPT-4 biedt een groter contextvenster en kan langere tekstinvoer verwerken, geschikt voor scenario's die uitgebreide informatie-integratie en data-analyse vereisen."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "Het nieuwste GPT-4 Turbo-model heeft visuele functies. Nu kunnen visuele verzoeken worden gedaan met behulp van JSON-indeling en functieaanroepen. GPT-4 Turbo is een verbeterde versie die kosteneffectieve ondersteuning biedt voor multimodale taken. Het vindt een balans tussen nauwkeurigheid en efficiëntie, geschikt voor toepassingen die realtime interactie vereisen."
},
+ "gpt-4.5-preview": {
+ "description": "De onderzoekspreview van GPT-4.5, ons grootste en krachtigste GPT-model tot nu toe. Het heeft een uitgebreide wereldkennis en kan de intenties van gebruikers beter begrijpen, waardoor het uitblinkt in creatieve taken en autonome planning. GPT-4.5 accepteert tekst- en afbeeldingsinvoer en genereert tekstuitvoer (inclusief gestructureerde uitvoer). Het ondersteunt belangrijke ontwikkelaarsfuncties zoals functieaanroepen, batch-API's en streaminguitvoer. In taken die creativiteit, open denken en dialoog vereisen (zoals schrijven, leren of het verkennen van nieuwe ideeën), presteert GPT-4.5 bijzonder goed. De kennis is bijgewerkt tot oktober 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o is een dynamisch model dat in realtime wordt bijgewerkt om de meest actuele versie te behouden. Het combineert krachtige taalbegrip- en generatiecapaciteiten, geschikt voor grootschalige toepassingsscenario's, waaronder klantenservice, onderwijs en technische ondersteuning."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o is een dynamisch model dat in realtime wordt bijgewerkt om de meest actuele versie te behouden. Het combineert krachtige taalbegrip- en generatiecapaciteiten, geschikt voor grootschalige toepassingsscenario's, waaronder klantenservice, onderwijs en technische ondersteuning."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o is een dynamisch model dat in real-time wordt bijgewerkt om de meest actuele versie te behouden. Het combineert krachtige taalbegrip en generatiemogelijkheden, geschikt voor grootschalige toepassingen zoals klantenservice, onderwijs en technische ondersteuning."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o Audio model, ondersteunt audio-invoer en -uitvoer."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini is het nieuwste model van OpenAI, gelanceerd na GPT-4 Omni, en ondersteunt zowel tekst- als beeldinvoer met tekstuitvoer. Als hun meest geavanceerde kleine model is het veel goedkoper dan andere recente toonaangevende modellen en meer dan 60% goedkoper dan GPT-3.5 Turbo. Het behoudt de meest geavanceerde intelligentie met een aanzienlijke prijs-kwaliteitverhouding. GPT-4o mini behaalde 82% op de MMLU-test en staat momenteel hoger in chatvoorkeuren dan GPT-4."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "GPT-4o-mini realtime versie, ondersteunt audio en tekst realtime invoer en uitvoer."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "GPT-4o realtime versie, ondersteunt audio en tekst realtime invoer en uitvoer."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "GPT-4o realtime versie, ondersteunt audio en tekst realtime invoer en uitvoer."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "GPT-4o realtime versie, ondersteunt audio en tekst realtime invoer en uitvoer."
+ },
+ "grok-2-1212": {
+ "description": "Dit model heeft verbeteringen aangebracht in nauwkeurigheid, instructievolging en meertalige capaciteiten."
+ },
+ "grok-2-vision-1212": {
+ "description": "Dit model heeft verbeteringen aangebracht in nauwkeurigheid, instructievolging en meertalige capaciteiten."
+ },
+ "grok-beta": {
+ "description": "Biedt prestaties vergelijkbaar met Grok 2, maar met hogere efficiëntie, snelheid en functionaliteit."
+ },
+ "grok-vision-beta": {
+ "description": "Het nieuwste model voor beeldbegrip, dat een breed scala aan visuele informatie kan verwerken, waaronder documenten, grafieken, screenshots en foto's."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B is een taalmodel dat creativiteit en intelligentie combineert door meerdere topmodellen te integreren."
},
+ "hunyuan-code": {
+ "description": "Het nieuwste codegeneratiemodel van Hunyuan, getraind op 200B hoogwaardige codegegevens, met een half jaar training op hoogwaardige SFT-gegevens, met een vergroot contextvenster van 8K, en staat bovenaan de automatische evaluatie-indicatoren voor codegeneratie in vijf grote programmeertalen; presteert in de eerste divisie op basis van handmatige kwaliteitsbeoordelingen van 10 aspecten van code-taken in vijf grote talen."
+ },
+ "hunyuan-functioncall": {
+ "description": "Het nieuwste MOE-architectuur FunctionCall-model van Hunyuan, getraind op hoogwaardige FunctionCall-gegevens, met een contextvenster van 32K, en staat voorop in meerdere dimensies van evaluatie-indicatoren."
+ },
+ "hunyuan-large": {
+ "description": "Het Hunyuan-large model heeft een totaal aantal parameters van ongeveer 389B, met ongeveer 52B actieve parameters, en is het grootste en beste open-source MoE-model met Transformer-architectuur in de industrie."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Uitstekend in het verwerken van lange teksttaken zoals document samenvattingen en documentvragen, en heeft ook de capaciteit om algemene tekstgeneratietaken uit te voeren. Het presteert uitstekend in de analyse en generatie van lange teksten en kan effectief omgaan met complexe en gedetailleerde lange inhoudsverwerkingsbehoeften."
+ },
+ "hunyuan-lite": {
+ "description": "Geüpgraded naar een MOE-structuur, met een contextvenster van 256k, en leidt in verschillende evaluatiesets op het gebied van NLP, code, wiskunde en industrie ten opzichte van vele open-source modellen."
+ },
+ "hunyuan-lite-vision": {
+ "description": "De nieuwste 7B multimodale Hunyuan-model, met een contextvenster van 32K, ondersteunt multimodale gesprekken in het Chinees en het Engels, objectherkenning in afbeeldingen, document- en tabelbegrip, multimodale wiskunde, enz., en scoort op meerdere dimensies beter dan 7B concurrentiemodellen."
+ },
+ "hunyuan-pro": {
+ "description": "Een MOE-32K lange tekstmodel met triljoenen parameters. Bereikt een absoluut leidend niveau op verschillende benchmarks, met complexe instructies en redenering, beschikt over complexe wiskundige capaciteiten, ondersteunt function calls, en is geoptimaliseerd voor toepassingen in meertalige vertaling, financiële, juridische en medische gebieden."
+ },
+ "hunyuan-role": {
+ "description": "Het nieuwste rolspelmodel van Hunyuan, een rolspelmodel dat is ontwikkeld door de officiële fine-tuning training van Hunyuan, dat is getraind op basis van rolspel-scenario datasets, en betere basisprestaties biedt in rolspel-scenario's."
+ },
+ "hunyuan-standard": {
+ "description": "Maakt gebruik van een betere routeringsstrategie en verlicht tegelijkertijd de problemen van load balancing en expert convergentie. Voor lange teksten bereikt de naald in een hooiberg-index 99,9%. MOE-32K biedt een relatief betere prijs-kwaliteitverhouding, en kan lange tekstinvoer verwerken terwijl het effect en prijs in balans houdt."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Maakt gebruik van een betere routeringsstrategie en verlicht tegelijkertijd de problemen van load balancing en expert convergentie. Voor lange teksten bereikt de naald in een hooiberg-index 99,9%. MOE-256K doorbreekt verder in lengte en effectiviteit, waardoor de invoerlengte aanzienlijk wordt vergroot."
+ },
+ "hunyuan-standard-vision": {
+ "description": "De nieuwste multimodale Hunyuan-model, ondersteunt meertalige antwoorden, met evenwichtige capaciteiten in het Chinees en het Engels."
+ },
+ "hunyuan-translation": {
+ "description": "Ondersteunt vertalingen tussen het Chinees en 15 andere talen, waaronder Engels, Japans, Frans, Portugees, Spaans, Turks, Russisch, Arabisch, Koreaans, Italiaans, Duits, Vietnamees, Maleis en Indonesisch. Gebaseerd op een geautomatiseerde evaluatie van de COMET-score met een meervoudige scenario-vertalingstestset, overtreft het in het algemeen de vertaalcapaciteiten van vergelijkbare modellen op de markt."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Het Hunyuan vertaalmodel ondersteunt natuurlijke taal conversatievertalingen; het ondersteunt vertalingen tussen het Chinees en 15 andere talen, waaronder Engels, Japans, Frans, Portugees, Spaans, Turks, Russisch, Arabisch, Koreaans, Italiaans, Duits, Vietnamees, Maleis en Indonesisch."
+ },
+ "hunyuan-turbo": {
+ "description": "Een previewversie van het nieuwe generatie grote taalmodel van Hunyuan, met een nieuwe hybride expertmodel (MoE) structuur, die sneller inferentie-efficiëntie biedt en betere prestaties levert dan hunyan-pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Hunyuan-turbo versie van 20 november 2024, een vaste versie die zich tussen hunyuan-turbo en hunyuan-turbo-latest bevindt."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Deze versie optimaliseert: gegevensinstructiescaling, wat de algemene generalisatiecapaciteit van het model aanzienlijk verbetert; aanzienlijke verbetering van wiskunde-, code- en logische redeneervaardigheden; optimalisatie van tekstbegrip en woordbegrip gerelateerde capaciteiten; optimalisatie van de kwaliteit van tekstcreatie en inhoudsgeneratie."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Algemene ervaring optimalisatie, inclusief NLP-begrip, tekstcreatie, casual gesprekken, kennisvragen, vertalingen, en domeinspecifieke toepassingen; verbetering van de menselijkheid, optimalisatie van de emotionele intelligentie van het model; verbetering van het vermogen van het model om actief te verduidelijken bij vage intenties; verbetering van de verwerking van vragen over woord- en zinsanalyse; verbetering van de kwaliteit en interactie van creaties; verbetering van de ervaring in meerdere rondes."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "De nieuwe generatie visuele taal vlaggenschipmodel van Hunyuan, met een geheel nieuwe hybride expertmodel (MoE) structuur, biedt aanzienlijke verbeteringen in basisherkenning, inhoudcreatie, kennisvragen, en analytische redeneervaardigheden in vergelijking met de vorige generatie modellen."
+ },
+ "hunyuan-vision": {
+ "description": "Het nieuwste multimodale model van Hunyuan, ondersteunt het genereren van tekstinhoud op basis van afbeelding + tekstinvoer."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Het innovatieve open-source model InternLM2.5 verhoogt de gespreksintelligentie door een groot aantal parameters."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 biedt intelligente gespreksoplossingen voor meerdere scenario's."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct model, met 70B parameters, biedt uitstekende prestaties in grote tekstgeneratie- en instructietaken."
+ "internlm2-pro-chat": {
+ "description": "Onze oudere modelversie die we nog steeds onderhouden, met opties voor 7B en 20B parameters."
+ },
+ "internlm2.5-latest": {
+ "description": "Onze nieuwste modelreeks met uitstekende redeneervaardigheden, ondersteunt een contextlengte van 1M en heeft verbeterde instructievolging en toolaanroepmogelijkheden."
+ },
+ "internlm3-latest": {
+ "description": "Onze nieuwste modelreeks heeft uitstekende inferentieprestaties en leidt de open-source modellen in dezelfde klasse. Standaard gericht op ons recentste InternLM3 model."
+ },
+ "jina-deepsearch-v1": {
+ "description": "Diepe zoekopdrachten combineren webzoekopdrachten, lezen en redeneren voor een uitgebreide verkenning. Je kunt het beschouwen als een agent die jouw onderzoeksopdracht aanneemt - het zal een uitgebreide zoektocht uitvoeren en meerdere iteraties doorlopen voordat het een antwoord geeft. Dit proces omvat voortdurende onderzoek, redeneren en het oplossen van problemen vanuit verschillende invalshoeken. Dit is fundamenteel anders dan het rechtstreeks genereren van antwoorden uit voorgetrainde gegevens door standaard grote modellen en het vertrouwen op eenmalige oppervlakkige zoekopdrachten van traditionele RAG-systemen."
+ },
+ "kimi-latest": {
+ "description": "Kimi slimme assistent product maakt gebruik van het nieuwste Kimi grote model, dat mogelijk nog niet stabiele functies bevat. Ondersteunt beeldbegrip en kiest automatisch het 8k/32k/128k model als factureringsmodel op basis van de lengte van de context van het verzoek."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM is een experimenteel, taak-specifiek taalmodel dat is getraind volgens de principes van de leerwetenschap, en kan systeeminstructies volgen in onderwijs- en leeromgevingen, en fungeert als een expertmentor."
+ },
+ "lite": {
+ "description": "Spark Lite is een lichtgewicht groot taalmodel met extreem lage latentie en efficiënte verwerkingscapaciteit. Het is volledig gratis en open, en ondersteunt realtime online zoekfunctionaliteit. De snelle respons maakt het uitermate geschikt voor inferentie op apparaten met lage rekenkracht en modelafstemming, wat gebruikers uitstekende kosteneffectiviteit en een slimme ervaring biedt, vooral in kennisvragen, contentgeneratie en zoekscenario's."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B biedt krachtigere AI-inferentiecapaciteiten, geschikt voor complexe toepassingen, ondersteunt een enorme rekenverwerking en garandeert efficiëntie en nauwkeurigheid."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B is een hoogpresterend model dat snelle tekstgeneratiecapaciteiten biedt, zeer geschikt voor toepassingen die grootschalige efficiëntie en kosteneffectiviteit vereisen."
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct model, met 8B parameters, ondersteunt de efficiënte uitvoering van visuele instructietaken en biedt hoogwaardige tekstgeneratiecapaciteiten."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Uitstekende beeldredeneringscapaciteiten op hoge resolutie-afbeeldingen, geschikt voor visuele begrijptoepassingen."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Online model, met 405B parameters, ondersteunt een contextlengte van ongeveer 127.000 tokens, ontworpen voor complexe online chattoepassingen."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 is ontworpen om taken te verwerken die visuele en tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraag-en-antwoord, en overbrugt de kloof tussen taalgeneratie en visuele redeneervaardigheden."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chat model, met 70B parameters, ondersteunt een contextlengte van ongeveer 127.000 tokens, geschikt voor complexe offline chattaken."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Geavanceerde beeldredeneringscapaciteiten voor visuele begrijppoort toepassingen."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Online model, met 70B parameters, ondersteunt een contextlengte van ongeveer 127.000 tokens, geschikt voor hoge capaciteit en diverse chattaken."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 is ontworpen om taken te verwerken die visuele en tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraag-en-antwoord, en overbrugt de kloof tussen taalgeneratie en visuele redeneervaardigheden."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chat model, met 8B parameters, speciaal ontworpen voor offline chat, ondersteunt een contextlengte van ongeveer 127.000 tokens."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 is het meest geavanceerde meertalige open-source grote taalmodel in de Llama-serie, dat prestaties biedt die vergelijkbaar zijn met die van het 405B-model tegen zeer lage kosten. Gebaseerd op de Transformer-structuur en verbeterd door middel van supervisie-fijnstelling (SFT) en versterkend leren met menselijke feedback (RLHF) voor gebruiksvriendelijkheid en veiligheid. De instructie-geoptimaliseerde versie is speciaal ontworpen voor meertalige dialogen en presteert beter dan veel open-source en gesloten chatmodellen op verschillende industriële benchmarks. Kennisafkapdatum is december 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Online model, met 8B parameters, ondersteunt een contextlengte van ongeveer 127.000 tokens, speciaal ontworpen voor online chat en kan efficiënt verschillende tekstinteracties verwerken."
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 is een meertalige grote taalmodel (LLM) met 70B (tekstinvoer/tekstuitvoer) dat is voorgetraind en aangepast voor instructies. Het pure tekstmodel van Llama 3.3 is geoptimaliseerd voor meertalige gespreksgebruik en scoort beter dan veel beschikbare open-source en gesloten chatmodellen op gangbare industrie benchmarks."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B biedt ongeëvenaarde complexiteitsverwerkingscapaciteiten, op maat gemaakt voor veeleisende projecten."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral is ontworpen voor wetenschappelijk onderzoek en wiskundige inferentie, biedt effectieve rekencapaciteiten en resultaatinterpretatie."
},
+ "max-32k": {
+ "description": "Spark Max 32K is uitgerust met een grote contextverwerkingscapaciteit, met verbeterd begrip van context en logische redeneervaardigheden. Het ondersteunt tekstinvoer van 32K tokens en is geschikt voor het lezen van lange documenten, privé kennisvragen en andere scenario's."
+ },
"meta-llama-3-70b-instruct": {
"description": "Een krachtig model met 70 miljard parameters dat uitblinkt in redeneren, coderen en brede taaltoepassingen."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) biedt uitstekende taalverwerkingscapaciteiten en een geweldige interactie-ervaring."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 biedt uitstekende taalverwerkingscapaciteiten en een geweldige interactieve ervaring."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) is een krachtig chatmodel dat complexe gespreksbehoeften ondersteunt."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) biedt meertalige ondersteuning en dekt een breed scala aan domeinkennis."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 is ontworpen voor taken die zowel visuele als tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraagstukken, en overbrugt de kloof tussen taalgeneratie en visuele redenering."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 is ontworpen voor taken die zowel visuele als tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraagstukken, en overbrugt de kloof tussen taalgeneratie en visuele redenering."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 is ontworpen voor taken die zowel visuele als tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraagstukken, en overbrugt de kloof tussen taalgeneratie en visuele redenering."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 is het meest geavanceerde meertalige open-source grote taalmodel uit de Llama-serie, dat een vergelijkbare prestatie biedt als het 405B model tegen zeer lage kosten. Gebaseerd op de Transformer-structuur en verbeterd in bruikbaarheid en veiligheid door middel van supervisie-fijnstelling (SFT) en versterkend leren met menselijke feedback (RLHF). De instructie-geoptimaliseerde versie is speciaal ontworpen voor meertalige gesprekken en presteert beter dan veel open-source en gesloten chatmodellen op verschillende industriële benchmarks. Kennisafkapdatum is december 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 meertalige grote taalmodel (LLM) is een voorgetraind en instructie-aangepast generatief model van 70B (tekstinvoer/tekstuitvoer). Het Llama 3.3 instructie-aangepaste pure tekstmodel is geoptimaliseerd voor meertalige dialoogtoepassingen en presteert beter dan veel beschikbare open-source en gesloten chatmodellen op gangbare industriële benchmarks."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 is ontworpen voor taken die zowel visuele als tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraagstukken, en overbrugt de kloof tussen taalgeneratie en visuele redenering."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite is geschikt voor omgevingen die hoge prestaties en lage latentie vereisen."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "405B Llama 3.1 Turbo model biedt enorme contextondersteuning voor big data verwerking en presteert uitstekend in grootschalige AI-toepassingen."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 is een toonaangevend model van Meta, ondersteunt tot 405B parameters en kan worden toegepast in complexe gesprekken, meertalige vertalingen en data-analyse."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B biedt efficiënte gespreksondersteuning in meerdere talen."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct is geoptimaliseerd voor hoogwaardige gespreksscenario's en presteert beter dan veel gesloten modellen."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct is de nieuwste versie van Meta, geoptimaliseerd voor het genereren van hoogwaardige gesprekken en overtreft veel toonaangevende gesloten modellen."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct is ontworpen voor hoogwaardige gesprekken en presteert uitstekend in menselijke evaluaties, vooral in interactieve scenario's."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 biedt ondersteuning voor meerdere talen en is een van de toonaangevende generatiemodellen in de industrie."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 is ontworpen voor taken die visuele en tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraag-en-antwoord, en overbrugt de kloof tussen taalgeneratie en visuele redenering."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 is ontworpen voor taken die visuele en tekstuele gegevens combineren. Het presteert uitstekend in taken zoals afbeeldingsbeschrijving en visuele vraag-en-antwoord, en overbrugt de kloof tussen taalgeneratie en visuele redenering."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 is het meest geavanceerde meertalige open-source grote taalmodel in de Llama-serie, dat prestaties biedt die vergelijkbaar zijn met die van het 405B-model tegen zeer lage kosten. Gebaseerd op de Transformer-structuur en verbeterd door middel van supervisie-fijnstelling (SFT) en versterkend leren met menselijke feedback (RLHF) voor gebruiksvriendelijkheid en veiligheid. De instructie-geoptimaliseerde versie is speciaal ontworpen voor meertalige dialogen en presteert beter dan veel open-source en gesloten chatmodellen op verschillende industriële benchmarks. Kennisafkapdatum is december 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 is het meest geavanceerde meertalige open-source grote taalmodel in de Llama-serie, dat prestaties biedt die vergelijkbaar zijn met die van het 405B-model tegen zeer lage kosten. Gebaseerd op de Transformer-structuur en verbeterd door middel van supervisie-fijnstelling (SFT) en versterkend leren met menselijke feedback (RLHF) voor gebruiksvriendelijkheid en veiligheid. De instructie-geoptimaliseerde versie is speciaal ontworpen voor meertalige dialogen en presteert beter dan veel open-source en gesloten chatmodellen op verschillende industriële benchmarks. Kennisafkapdatum is december 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct is het grootste en krachtigste model binnen het Llama 3.1 Instruct-model, een geavanceerd model voor conversatie-inferentie en synthetische datageneratie, dat ook kan worden gebruikt als basis voor gespecialiseerde continue pre-training of fine-tuning in specifieke domeinen. De meertalige grote taalmodellen (LLMs) die Llama 3.1 biedt, zijn een set van voorgetrainde, instructie-geoptimaliseerde generatieve modellen, waaronder 8B, 70B en 405B in grootte (tekstinvoer/uitvoer). De tekstmodellen van Llama 3.1, die zijn geoptimaliseerd voor meertalige conversatiegebruik, overtreffen veel beschikbare open-source chatmodellen in gangbare industriële benchmarktests. Llama 3.1 is ontworpen voor commercieel en onderzoeksgebruik in meerdere talen. De instructie-geoptimaliseerde tekstmodellen zijn geschikt voor assistentachtige chats, terwijl de voorgetrainde modellen zich kunnen aanpassen aan verschillende taken voor natuurlijke taalgeneratie. Het Llama 3.1-model ondersteunt ook het verbeteren van andere modellen door gebruik te maken van de output van zijn modellen, inclusief synthetische datageneratie en verfijning. Llama 3.1 is een autoregressief taalmodel dat gebruikmaakt van een geoptimaliseerde transformer-architectuur. De afgestelde versies gebruiken supervisie-finetuning (SFT) en versterkend leren met menselijke feedback (RLHF) om te voldoen aan menselijke voorkeuren voor behulpzaamheid en veiligheid."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 is een open groot taalmodel (LLM) gericht op ontwikkelaars, onderzoekers en bedrijven, ontworpen om hen te helpen bij het bouwen, experimenteren en verantwoordelijk opschalen van hun generatieve AI-ideeën. Als onderdeel van het basis systeem voor wereldwijde gemeenschapsinnovatie is het zeer geschikt voor apparaten met beperkte rekenkracht en middelen, edge-apparaten en snellere trainingstijden."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B is het nieuwste snelle en lichte model van Microsoft AI, met prestaties die bijna 10 keer beter zijn dan de huidige toonaangevende open-source modellen."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "Geavanceerd LLM, ondersteunt synthetische gegevensgeneratie, kennisdistillatie en redeneren, geschikt voor chatbots, programmeren en specifieke domeintaken."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "In staat om complexe gesprekken te ondersteunen, met uitstekende contextbegrip, redeneringsvaardigheden en tekstgeneratiecapaciteiten."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Geavanceerd, state-of-the-art model met taalbegrip, uitstekende redeneringsvaardigheden en tekstgeneratiecapaciteiten."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "State-of-the-art visueel-taalmodel, gespecialiseerd in hoogwaardige redeneringen vanuit afbeeldingen."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Geavanceerd, state-of-the-art klein taalmodel met taalbegrip, uitstekende redeneringsvaardigheden en tekstgeneratiecapaciteiten."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Geavanceerd, state-of-the-art klein taalmodel met taalbegrip, uitstekende redeneringsvaardigheden en tekstgeneratiecapaciteiten."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "State-of-the-art visueel-taalmodel, gespecialiseerd in hoogwaardige redeneringen vanuit afbeeldingen."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Geavanceerd LLM, gespecialiseerd in redeneren, wiskunde, algemene kennis en functieaanroepen."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 is een taalmodel van Microsoft AI dat uitblinkt in complexe gesprekken, meertaligheid, redenering en intelligente assistenttoepassingen."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B is het meest geavanceerde Wizard-model van Microsoft AI, met een uiterst competitieve prestatie."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V is de nieuwe generatie multimodale grote modellen van OpenBMB, met uitstekende OCR-herkenning en multimodaal begrip, geschikt voor een breed scala aan toepassingsscenario's."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B is het toonaangevende edge-model van Mistral."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B is een zeer kosteneffectief edge-model van Mistral."
+ },
"mistral": {
"description": "Mistral is het 7B-model van Mistral AI, geschikt voor variabele taalverwerkingsbehoeften."
},
"mistral-large": {
"description": "Mixtral Large is het vlaggenschipmodel van Mistral, dat de capaciteiten van codegeneratie, wiskunde en inferentie combineert, ondersteunt een contextvenster van 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) is een geavanceerd Large Language Model (LLM) met state-of-the-art redenerings-, kennis- en coderingscapaciteiten."
- },
"mistral-large-latest": {
"description": "Mistral Large is het vlaggenschipmodel, dat uitblinkt in meertalige taken, complexe inferentie en codegeneratie, ideaal voor high-end toepassingen."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 biedt efficiënte rekenkracht en natuurlijke taalbegrip, geschikt voor een breed scala aan toepassingen."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B is een compact maar hoogwaardig model, dat goed presteert in batchverwerking en eenvoudige taken zoals classificatie en tekstgeneratie, met goede redeneringscapaciteiten."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) is een supergroot taalmodel dat extreem hoge verwerkingsbehoeften ondersteunt."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B is een voorgetraind spaarzaam mengexpertmodel, gebruikt voor algemene teksttaken."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B is een spaarzaam expert-model dat meerdere parameters gebruikt om de redeneringssnelheid te verhogen, ideaal voor meertalige en codegeneratietaken."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct is een hoogwaardig industrieel standaardmodel met snelheidoptimalisatie en ondersteuning voor lange contexten."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K is een model met een superlange contextverwerkingscapaciteit, geschikt voor het genereren van zeer lange teksten, voldoet aan de behoeften van complexe generatietaken en kan tot 128.000 tokens verwerken, zeer geschikt voor onderzoek, academische en grote documentgeneratie."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Het Kimi visuele model (inclusief moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, enz.) kan de inhoud van afbeeldingen begrijpen, inclusief afbeeldingstekst, kleuren en vormen van objecten."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K biedt een gemiddelde contextverwerkingscapaciteit, kan 32.768 tokens verwerken, bijzonder geschikt voor het genereren van verschillende lange documenten en complexe gesprekken, toegepast in contentcreatie, rapportgeneratie en conversatiesystemen."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Het Kimi visuele model (inclusief moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, enz.) kan de inhoud van afbeeldingen begrijpen, inclusief afbeeldingstekst, kleuren en vormen van objecten."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K is speciaal ontworpen voor het genereren van korte teksttaken, met efficiënte verwerkingsprestaties, kan 8.192 tokens verwerken, zeer geschikt voor korte gesprekken, notities en snelle contentgeneratie."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Het Kimi visuele model (inclusief moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, enz.) kan de inhoud van afbeeldingen begrijpen, inclusief afbeeldingstekst, kleuren en vormen van objecten."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto kan het geschikte model kiezen op basis van het aantal Tokens dat momenteel door de context wordt gebruikt."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B is een upgrade van Nous Hermes 2, met de nieuwste intern ontwikkelde datasets."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B is een op maat gemaakt groot taalmodel van NVIDIA, ontworpen om de hulp van LLM-gegenereerde reacties op gebruikersvragen te verbeteren. Dit model presteert uitstekend in benchmarktests zoals Arena Hard, AlpacaEval 2 LC en GPT-4-Turbo MT-Bench, en staat per 1 oktober 2024 op de eerste plaats in alle drie de automatische afstemmingsbenchmarktests. Het model is getraind met RLHF (met name REINFORCE), Llama-3.1-Nemotron-70B-Reward en HelpSteer2-Preference prompts op basis van het Llama-3.1-70B-Instruct model."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Uniek taalmodel dat ongeëvenaarde nauwkeurigheid en efficiëntie biedt."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct is een op maat gemaakt groot taalmodel van NVIDIA, ontworpen om de nuttigheid van de door LLM gegenereerde reacties te verbeteren."
+ },
+ "o1": {
+ "description": "Gefocust op geavanceerd redeneren en het oplossen van complexe problemen, inclusief wiskunde en wetenschappelijke taken. Zeer geschikt voor toepassingen die diepgaand begrip van context en agentwerkstromen vereisen."
+ },
"o1-mini": {
"description": "o1-mini is een snel en kosteneffectief redeneermodel dat is ontworpen voor programmeer-, wiskunde- en wetenschappelijke toepassingen. Dit model heeft een context van 128K en een kennisafkapdatum van oktober 2023."
},
"o1-preview": {
"description": "o1 is het nieuwe redeneermodel van OpenAI, geschikt voor complexe taken die uitgebreide algemene kennis vereisen. Dit model heeft een context van 128K en een kennisafkapdatum van oktober 2023."
},
+ "o3-mini": {
+ "description": "o3-mini is ons nieuwste kleine inferentiemodel dat hoge intelligentie biedt met dezelfde kosten- en vertragingdoelen als o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba is een Mamba 2-taalmodel dat zich richt op codegeneratie en krachtige ondersteuning biedt voor geavanceerde code- en inferentietaken."
},
@@ -745,7 +1466,7 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B is een spaarzaam expertmodel dat meerdere parameters benut om de inferentiesnelheid te verhogen, geschikt voor het verwerken van meertalige en codegeneratietaken."
},
- "openai/gpt-4o-2024-08-06": {
+ "openai/gpt-4o": {
"description": "ChatGPT-4o is een dynamisch model dat in realtime wordt bijgewerkt om de meest actuele versie te behouden. Het combineert krachtige taalbegrip- en generatiecapaciteiten, geschikt voor grootschalige toepassingsscenario's, waaronder klantenservice, onderwijs en technische ondersteuning."
},
"openai/gpt-4o-mini": {
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Het Pixtral model toont sterke capaciteiten in taken zoals grafiek- en beeldbegrip, documentvraag-en-antwoord, multimodale redenering en instructievolging, en kan afbeeldingen met natuurlijke resolutie en beeldverhouding verwerken, evenals een onbeperkt aantal afbeeldingen in een lange contextvenster van maximaal 128K tokens."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large is een open-source multimodaal model met 124 miljard parameters, gebaseerd op Mistral Large 2. Dit is ons tweede model in de multimodale familie en toont geavanceerde beeldbegripcapaciteiten."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K is uitgerust met een zeer grote contextverwerkingscapaciteit, in staat om tot 128K contextinformatie te verwerken. Het is bijzonder geschikt voor lange teksten die een volledige analyse en langdurige logische verbanden vereisen, en biedt een vloeiende en consistente logica met diverse ondersteuningen voor citaten in complexe tekstcommunicatie."
+ },
+ "qvq-72b-preview": {
+ "description": "Het QVQ-model is een experimenteel onderzoeksmodel ontwikkeld door het Qwen-team, gericht op het verbeteren van visuele redeneervaardigheden, vooral in het domein van wiskundige redenering."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Tongyi Qianwen code model."
+ },
"qwen-coder-turbo-latest": {
"description": "Het Tongyi Qianwen codeermodel."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Het Tongyi Qianwen wiskundemodel is speciaal ontworpen voor het oplossen van wiskundige problemen."
},
+ "qwen-max": {
+ "description": "Qwen is een enorme versie van het grootschalige taalmodel, dat ondersteuning biedt voor verschillende taalinputs zoals Chinees en Engels en momenteel de API-modellen achter de Qwen 2.5-productversie vertegenwoordigt."
+ },
"qwen-max-latest": {
"description": "Het Tongyi Qianwen model met een schaal van honderden miljarden, ondersteunt invoer in verschillende talen, waaronder Chinees en Engels, en is de API-model achter de huidige Tongyi Qianwen 2.5 productversie."
},
+ "qwen-omni-turbo-latest": {
+ "description": "De Qwen-Omni serie modellen ondersteunt het invoeren van gegevens in verschillende modaliteiten, waaronder video, audio, afbeeldingen en tekst, en kan audio en tekst als output genereren."
+ },
+ "qwen-plus": {
+ "description": "Qwen is een verbeterde versie van het grootschalige taalmodel dat ondersteuning biedt voor verschillende taalinputs zoals Chinees en Engels."
+ },
"qwen-plus-latest": {
"description": "De verbeterde versie van het Tongyi Qianwen supergrote taalmodel ondersteunt invoer in verschillende talen, waaronder Chinees en Engels."
},
+ "qwen-turbo": {
+ "description": "Qwen is een grootschalig taalmodel dat ondersteuning biedt voor verschillende taalinputs zoals Chinees en Engels."
+ },
"qwen-turbo-latest": {
"description": "De Tongyi Qianwen supergrote taalmodel ondersteunt invoer in verschillende talen, waaronder Chinees en Engels."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL ondersteunt flexibele interactiemethoden, inclusief meerdere afbeeldingen, meerdere rondes van vraag en antwoord, en creatiecapaciteiten."
},
- "qwen-vl-max": {
- "description": "Qwen is een grootschalig visueel taalmodel. In vergelijking met de verbeterde versie biedt het een verdere verbetering van de visuele redeneercapaciteit en de naleving van instructies, met een hoger niveau van visuele waarneming en cognitie."
+ "qwen-vl-max-latest": {
+ "description": "Het Tongyi Qianwen ultra-grootschalige visuele taalmodel. In vergelijking met de verbeterde versie, verhoogt het opnieuw de visuele redeneervaardigheden en de naleving van instructies, en biedt het een hoger niveau van visuele waarneming en cognitie."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Qwen OCR is een speciaal model voor tekstextractie, gericht op het extraheren van tekst uit documenten, tabellen, examenvragen, handgeschreven teksten en andere soorten afbeeldingen. Het kan verschillende talen herkennen, waaronder: Chinees, Engels, Frans, Japans, Koreaans, Duits, Russisch, Italiaans, Vietnamees en Arabisch."
},
- "qwen-vl-plus": {
- "description": "Qwen is een verbeterde versie van het grootschalige visuele taalmodel. Het verbetert aanzienlijk de detailherkenning en tekstherkenning, en ondersteunt afbeeldingen met een resolutie van meer dan een miljoen pixels en een willekeurige beeldverhouding."
+ "qwen-vl-plus-latest": {
+ "description": "De verbeterde versie van het Tongyi Qianwen grootschalige visuele taalmodel. Het verbetert aanzienlijk de detailherkenning en tekstherkenning, ondersteunt resoluties van meer dan een miljoen pixels en afbeeldingen met elke verhouding."
},
"qwen-vl-v1": {
"description": "Geïnitieerd met het Qwen-7B taalmodel, voegt het een afbeeldingsmodel toe, met een invoerresolutie van 448 voor het voorgetrainde model."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 is de gloednieuwe serie van grote taalmodellen van Qwen. Qwen2 7B is een transformer-gebaseerd model dat uitblinkt in taalbegrip, meertalige capaciteiten, programmeren, wiskunde en redenering."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 is een gloednieuwe serie grote taalmodellen met sterkere begrip- en generatiecapaciteiten."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL is de nieuwste iteratie van het Qwen-VL-model en heeft geavanceerde prestaties behaald in visuele begrip benchmarktests, waaronder MathVista, DocVQA, RealWorldQA en MTVQA. Qwen2-VL kan video's van meer dan 20 minuten begrijpen voor hoogwaardige video-gebaseerde vraag-en-antwoord, dialoog en contentcreatie. Het heeft ook complexe redenerings- en besluitvormingscapaciteiten en kan worden geïntegreerd met mobiele apparaten, robots, enzovoort, voor automatische operaties op basis van visuele omgevingen en tekstinstructies. Naast Engels en Chinees ondersteunt Qwen2-VL nu ook het begrijpen van tekst in verschillende talen in afbeeldingen, waaronder de meeste Europese talen, Japans, Koreaans, Arabisch en Vietnamees."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct is een van de nieuwste grote taalmodellen die door Alibaba Cloud is uitgebracht. Dit 72B-model heeft aanzienlijke verbeteringen in codering en wiskunde. Het model biedt ook ondersteuning voor meerdere talen, met meer dan 29 talen, waaronder Chinees en Engels. Het model heeft aanzienlijke verbeteringen in het volgen van instructies, het begrijpen van gestructureerde gegevens en het genereren van gestructureerde output (vooral JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct is een van de nieuwste grote taalmodellen die door Alibaba Cloud is uitgebracht. Dit 32B-model heeft aanzienlijke verbeteringen in codering en wiskunde. Het model biedt ook ondersteuning voor meerdere talen, met meer dan 29 talen, waaronder Chinees en Engels. Het model heeft aanzienlijke verbeteringen in het volgen van instructies, het begrijpen van gestructureerde gegevens en het genereren van gestructureerde output (vooral JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM gericht op zowel Chinees als Engels, gericht op taal, programmeren, wiskunde, redeneren en meer."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "Geavanceerd LLM, ondersteunt codegeneratie, redeneren en reparatie, dekt gangbare programmeertalen."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Krachtig middelgroot codeermodel, ondersteunt 32K contextlengte, gespecialiseerd in meertalige programmering."
+ },
"qwen2": {
"description": "Qwen2 is Alibaba's nieuwe generatie grootschalig taalmodel, ondersteunt diverse toepassingsbehoeften met uitstekende prestaties."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 is de nieuwe generatie grootschalig taalmodel van Alibaba, dat uitstekende prestaties levert ter ondersteuning van diverse toepassingsbehoeften."
+ },
"qwen2.5-14b-instruct": {
"description": "Het 14B model van Tongyi Qianwen 2.5 is open source beschikbaar."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Qwen2.5 is een open-source model van 72B schaal."
+ },
"qwen2.5-32b-instruct": {
"description": "Het 32B model van Tongyi Qianwen 2.5 is open source beschikbaar."
},
@@ -824,13 +1599,16 @@
"description": "Het 7B model van Tongyi Qianwen 2.5 is open source beschikbaar."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "De open source versie van het Tongyi Qianwen codeermodel."
+ "description": "Qwen-code model open source versie."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Open source versie van het Tongyi Qianwen code model."
},
"qwen2.5-coder-7b-instruct": {
"description": "De open source versie van het Tongyi Qianwen codeermodel."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Het Qwen-Math model heeft krachtige capaciteiten voor het oplossen van wiskundige problemen."
+ "description": "Qwen-Math model beschikt over krachtige wiskundige probleemoplossende mogelijkheden."
},
"qwen2.5-math-72b-instruct": {
"description": "Het Qwen-Math model heeft krachtige capaciteiten voor het oplossen van wiskundige problemen."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Het Qwen-Math model heeft krachtige capaciteiten voor het oplossen van wiskundige problemen."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Verbeterde instructievolging, wiskunde, probleemoplossing en code, met verbeterde herkenningscapaciteiten voor verschillende formaten, directe en nauwkeurige lokalisatie van visuele elementen, ondersteuning voor lange videobestanden (maximaal 10 minuten) en seconde-niveau gebeurtenislocatie, kan tijdsvolgorde en snelheid begrijpen, en ondersteunt het bedienen van OS of mobiele agenten op basis van analyse- en lokalisatiecapaciteiten, sterke capaciteiten voor het extraheren van belangrijke informatie en JSON-formaat uitvoer, deze versie is de 72B versie, de krachtigste versie in deze serie."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Verbeterde instructievolging, wiskunde, probleemoplossing en code, met verbeterde herkenningscapaciteiten voor verschillende formaten, directe en nauwkeurige lokalisatie van visuele elementen, ondersteuning voor lange videobestanden (maximaal 10 minuten) en seconde-niveau gebeurtenislocatie, kan tijdsvolgorde en snelheid begrijpen, en ondersteunt het bedienen van OS of mobiele agenten op basis van analyse- en lokalisatiecapaciteiten, sterke capaciteiten voor het extraheren van belangrijke informatie en JSON-formaat uitvoer, deze versie is de 72B versie, de krachtigste versie in deze serie."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 is de nieuwe generatie grootschalig taalmodel van Alibaba, dat uitstekende prestaties levert ter ondersteuning van diverse toepassingsbehoeften."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 is de nieuwe generatie grootschalig taalmodel van Alibaba, dat uitstekende prestaties levert ter ondersteuning van diverse toepassingsbehoeften."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 is de nieuwe generatie grootschalig taalmodel van Alibaba, dat uitstekende prestaties levert ter ondersteuning van diverse toepassingsbehoeften."
+ },
"qwen2:0.5b": {
"description": "Qwen2 is Alibaba's nieuwe generatie grootschalig taalmodel, ondersteunt diverse toepassingsbehoeften met uitstekende prestaties."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 is Alibaba's nieuwe generatie grootschalig taalmodel, ondersteunt diverse toepassingsbehoeften met uitstekende prestaties."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini is een compact LLM dat beter presteert dan GPT-3.5, met sterke meertalige capaciteiten, ondersteunt Engels en Koreaans, en biedt een efficiënte en compacte oplossing."
+ "qwq": {
+ "description": "QwQ is een experimenteel onderzoeksmodel dat zich richt op het verbeteren van de AI-redeneringscapaciteiten."
+ },
+ "qwq-32b": {
+ "description": "De QwQ-inferentiemodel, getraind op het Qwen2.5-32B-model, heeft zijn inferentievermogen aanzienlijk verbeterd door middel van versterkend leren. De kernindicatoren van het model, zoals wiskundige code (AIME 24/25, LiveCodeBench) en enkele algemene indicatoren (IFEval, LiveBench, enz.), bereiken het niveau van de DeepSeek-R1 volwaardige versie, waarbij alle indicatoren aanzienlijk beter presteren dan de DeepSeek-R1-Distill-Qwen-32B, die ook op Qwen2.5-32B is gebaseerd."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) breidt de mogelijkheden van Solar Mini uit, met een focus op de Japanse taal, terwijl het ook efficiënt en uitstekend presteert in het gebruik van Engels en Koreaans."
+ "qwq-32b-preview": {
+ "description": "Het QwQ-model is een experimenteel onderzoeksmodel ontwikkeld door het Qwen-team, gericht op het verbeteren van de AI-redeneringscapaciteiten."
+ },
+ "qwq-plus-latest": {
+ "description": "De QwQ-inferentiemodel, getraind op het Qwen2.5-model, heeft zijn inferentievermogen aanzienlijk verbeterd door middel van versterkend leren. De kernindicatoren van het model, zoals wiskundige code (AIME 24/25, LiveCodeBench) en enkele algemene indicatoren (IFEval, LiveBench, enz.), bereiken het niveau van de DeepSeek-R1 volwaardige versie."
+ },
+ "r1-1776": {
+ "description": "R1-1776 is een versie van het DeepSeek R1-model, dat is bijgetraind om ongecensureerde, onpartijdige feitelijke informatie te bieden."
+ },
+ "solar-mini": {
+ "description": "Solar Mini is een compacte LLM die beter presteert dan GPT-3.5, met sterke meertalige capaciteiten, ondersteunt Engels en Koreaans, en biedt een efficiënte en compacte oplossing."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) breidt de capaciteiten van Solar Mini uit, met een focus op het Japans, terwijl het efficiënt en uitstekend presteert in het gebruik van Engels en Koreaans."
},
"solar-pro": {
"description": "Solar Pro is een zeer intelligent LLM dat is uitgebracht door Upstage, gericht op instructievolging met één GPU, met een IFEval-score van boven de 80. Momenteel ondersteunt het Engels, met een officiële versie die gepland staat voor november 2024, die de taalondersteuning en contextlengte zal uitbreiden."
},
+ "sonar": {
+ "description": "Een lichtgewicht zoekproduct op basis van contextuele zoekopdrachten, sneller en goedkoper dan Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research voert uitgebreide expertstudies uit en bundelt deze in toegankelijke, bruikbare rapporten."
+ },
+ "sonar-pro": {
+ "description": "Een geavanceerd zoekproduct dat contextuele zoekopdrachten ondersteunt, met geavanceerde query's en vervolgacties."
+ },
+ "sonar-reasoning": {
+ "description": "Een nieuw API-product ondersteund door het DeepSeek redeneringsmodel."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Een nieuw API-product ondersteund door het DeepSeek redeneringsmodel."
+ },
"step-1-128k": {
"description": "Biedt een balans tussen prestaties en kosten, geschikt voor algemene scenario's."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Hogesnelheidsmodel, geschikt voor realtime gesprekken."
},
+ "step-1.5v-mini": {
+ "description": "Dit model heeft krachtige video begrip capaciteiten."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Dit model heeft krachtige beeldbegripcapaciteiten en presteert beter dan 1o in wiskunde en codering. Het model is kleiner dan 1o en heeft een snellere uitvoersnelheid."
+ },
+ "step-1o-vision-32k": {
+ "description": "Dit model heeft krachtige beeldbegripcapaciteiten. In vergelijking met de step-1v serie modellen heeft het een sterkere visuele prestatie."
+ },
"step-1v-32k": {
"description": "Ondersteunt visuele invoer, verbetert de multimodale interactie-ervaring."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Ondersteunt grootschalige contextinteracties, geschikt voor complexe gespreksscenario's."
},
+ "step-2-mini": {
+ "description": "Een razendsnel groot model gebaseerd op de nieuwe generatie zelfontwikkelde Attention-architectuur MFA, dat met zeer lage kosten vergelijkbare resultaten als step1 behaalt, terwijl het een hogere doorvoer en snellere responstijd behoudt. Het kan algemene taken verwerken en heeft speciale vaardigheden op het gebied van codering."
+ },
"taichu_llm": {
"description": "Het Zido Tai Chu-taalmodel heeft een sterke taalbegripcapaciteit en kan tekstcreatie, kennisvragen, codeprogrammering, wiskundige berekeningen, logische redenering, sentimentanalyse, tekstsamenvattingen en meer aan. Het combineert innovatief grote data voortraining met rijke kennis uit meerdere bronnen, door algoritmische technologie continu te verfijnen en voortdurend nieuwe kennis op te nemen uit enorme tekstdata op het gebied van vocabulaire, structuur, grammatica en semantiek, waardoor de modelprestaties voortdurend evolueren. Het biedt gebruikers gemakkelijkere informatie en diensten en een meer intelligente ervaring."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V combineert capaciteiten zoals beeldbegrip, kennisoverdracht en logische toerekening, en presteert uitstekend in het domein van beeld-tekst vraag en antwoord."
+ "taichu_vl": {
+ "description": "Integreert beeldbegrip, kennisoverdracht en logische toerekening, en presteert uitstekend in het domein van vraag-en-antwoord met tekst en afbeeldingen."
+ },
+ "text-embedding-3-large": {
+ "description": "Het krachtigste vectorisatie model, geschikt voor Engelse en niet-Engelse taken."
+ },
+ "text-embedding-3-small": {
+ "description": "Een efficiënte en kosteneffectieve nieuwe generatie Embedding model, geschikt voor kennisretrieval, RAG-toepassingen en andere scenario's."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "De open-source versie van de nieuwste generatie voorgetrainde modellen van de GLM-4-serie, uitgebracht door Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) biedt verbeterde rekenkracht door middel van efficiënte strategieën en modelarchitectuur."
},
+ "tts-1": {
+ "description": "Het nieuwste tekst-naar-spraak model, geoptimaliseerd voor snelheid in realtime scenario's."
+ },
+ "tts-1-hd": {
+ "description": "Het nieuwste tekst-naar-spraak model, geoptimaliseerd voor kwaliteit."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) is geschikt voor verfijnde instructietaken en biedt uitstekende taalverwerkingscapaciteiten."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet heeft de industrienormen verbeterd, met prestaties die de concurrentiemodellen en Claude 3 Opus overtreffen, en excelleert in uitgebreide evaluaties, terwijl het de snelheid en kosten van onze middelgrote modellen behoudt."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet is het snelste volgende generatie model van Anthropic. In vergelijking met Claude 3 Haiku heeft Claude 3.7 Sonnet verbeteringen in verschillende vaardigheden en overtreft het de grootste modellen van de vorige generatie, Claude 3 Opus, in veel intellectuele benchmarktests."
+ },
+ "whisper-1": {
+ "description": "Algemeen spraakherkenningsmodel, ondersteunt meertalige spraakherkenning, spraakvertaling en taalherkenning."
+ },
"wizardlm2": {
"description": "WizardLM 2 is een taalmodel van Microsoft AI dat uitblinkt in complexe gesprekken, meertaligheid, inferentie en intelligente assistentie."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Biedt een uitstekende prijs-kwaliteitverhouding en prestaties. Voert een nauwkeurige afstemming uit op basis van prestaties, redeneersnelheid en kosten."
},
+ "yi-lightning": {
+ "description": "Het nieuwste high-performance model, dat zorgt voor hoogwaardige output met aanzienlijke versnelling van de redeneringssnelheid."
+ },
+ "yi-lightning-lite": {
+ "description": "Lichte versie, aanbevolen voor gebruik met yi-lightning."
+ },
"yi-medium": {
"description": "Gemiddeld formaat model met geoptimaliseerde afstemming, biedt een evenwichtige prijs-kwaliteitverhouding. Diep geoptimaliseerde instructievolgcapaciteiten."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Model voor complexe visuele taken, biedt hoge prestaties in beeldbegrip en analyse."
+ },
+ "yi-vision-v2": {
+ "description": "Complex visietakenmodel dat hoge prestaties biedt in begrip en analyse op basis van meerdere afbeeldingen."
}
}
diff --git a/DigitalHumanWeb/locales/nl-NL/plugin.json b/DigitalHumanWeb/locales/nl-NL/plugin.json
index 3ada908..1c465f3 100644
--- a/DigitalHumanWeb/locales/nl-NL/plugin.json
+++ b/DigitalHumanWeb/locales/nl-NL/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Vernieuwen van de plugin {{name}} is mislukt.",
"urlError": "De link retourneert geen JSON-indeling. Zorg ervoor dat het een geldige link is."
},
+ "inspector": {
+ "args": "Bekijk parameterlijst",
+ "pluginRender": "Bekijk plugininterface"
+ },
"list": {
"item": {
"deprecated.title": "Verouderd",
@@ -130,6 +134,34 @@
"plugin": "Plugin wordt uitgevoerd..."
},
"pluginList": "Lijst met plugins",
+ "search": {
+ "config": {
+ "addKey": "Voeg sleutel toe",
+ "close": "Verwijderen",
+ "confirm": "Configuratie voltooid en opnieuw proberen"
+ },
+ "crawPages": {
+ "crawling": "Linkherkenning",
+ "detail": {
+ "preview": "Voorbeeld",
+ "raw": "Oorspronkelijke tekst",
+ "tooLong": "De tekstinhoud is te lang, de gesprekscontext houdt alleen de eerste {{characters}} tekens vast, het overschot wordt niet meegerekend in de gesprekscontext"
+ },
+ "meta": {
+ "crawler": "Crawler-modus",
+ "words": "Aantal tekens"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Voer in",
+ "description": "Voer de URL van SearchXNG in om te beginnen met online zoeken",
+ "keyPlaceholder": "Voer sleutel in",
+ "title": "Configureer SearchXNG zoekmachine",
+ "unconfiguredDesc": "Neem contact op met de beheerder om de configuratie van de SearchXNG zoekmachine te voltooien en te beginnen met online zoeken",
+ "unconfiguredTitle": "SearchXNG zoekmachine is nog niet geconfigureerd"
+ },
+ "title": "Online zoeken"
+ },
"setting": "Plugin-instellingen",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/nl-NL/portal.json b/DigitalHumanWeb/locales/nl-NL/portal.json
index 3ffe58c..8541743 100644
--- a/DigitalHumanWeb/locales/nl-NL/portal.json
+++ b/DigitalHumanWeb/locales/nl-NL/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Plugins",
- "actions": {
- "genAiMessage": "Creëer assistentbericht",
- "summary": "Samenvatting",
- "summaryTooltip": "Samenvatting van de huidige inhoud"
- },
"artifacts": {
"display": {
"code": "Code",
diff --git a/DigitalHumanWeb/locales/nl-NL/providers.json b/DigitalHumanWeb/locales/nl-NL/providers.json
index 79b4561..9245de0 100644
--- a/DigitalHumanWeb/locales/nl-NL/providers.json
+++ b/DigitalHumanWeb/locales/nl-NL/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs bouwt basismodellen en AI-systemen voor bedrijven, en versnelt de toepassing van generatieve AI in de productie."
+ },
"ai360": {
"description": "360 AI is een AI-model- en serviceplatform gelanceerd door het bedrijf 360, dat verschillende geavanceerde modellen voor natuurlijke taalverwerking biedt, waaronder 360GPT2 Pro, 360GPT Pro, 360GPT Turbo en 360GPT Turbo Responsibility 8K. Deze modellen combineren grootschalige parameters en multimodale capaciteiten, en worden breed toegepast in tekstgeneratie, semantisch begrip, dialoogsystemen en codegeneratie. Met flexibele prijsstrategieën voldoet 360 AI aan diverse gebruikersbehoeften, ondersteunt het ontwikkelaars bij integratie en bevordert het de innovatie en ontwikkeling van intelligente toepassingen."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure biedt een scala aan geavanceerde AI-modellen, waaronder GPT-3.5 en de nieuwste GPT-4-serie, die verschillende datatypes en complexe taken ondersteunen, met een focus op veilige, betrouwbare en duurzame AI-oplossingen."
},
+ "azureai": {
+ "description": "Azure biedt een verscheidenheid aan geavanceerde AI-modellen, waaronder GPT-3.5 en de nieuwste GPT-4-serie, die verschillende datatypes en complexe taken ondersteunt, met een focus op veilige, betrouwbare en duurzame AI-oplossingen."
+ },
"baichuan": {
"description": "Baichuan Intelligent is een bedrijf dat zich richt op de ontwikkeling van grote modellen voor kunstmatige intelligentie, wiens modellen uitblinken in Chinese taken zoals kennisencyclopedieën, lange tekstverwerking en generatieve creatie, en de mainstream modellen uit het buitenland overtreffen. Baichuan Intelligent heeft ook toonaangevende multimodale capaciteiten en presteert uitstekend in verschillende autoritatieve evaluaties. Hun modellen omvatten Baichuan 4, Baichuan 3 Turbo en Baichuan 3 Turbo 128k, die zijn geoptimaliseerd voor verschillende toepassingsscenario's en kosteneffectieve oplossingen bieden."
},
"bedrock": {
"description": "Bedrock is een dienst van Amazon AWS die zich richt op het bieden van geavanceerde AI-taalmodellen en visuele modellen voor bedrijven. De modellenfamilie omvat de Claude-serie van Anthropic, de Llama 3.1-serie van Meta, en meer, met opties variërend van lichtgewicht tot hoge prestaties, en ondersteunt tekstgeneratie, dialogen, beeldverwerking en meer, geschikt voor bedrijfsapplicaties van verschillende schalen en behoeften."
},
+ "cloudflare": {
+ "description": "Voer machine learning-modellen aan, aangedreven door serverloze GPU's, uit op het wereldwijde netwerk van Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek is een bedrijf dat zich richt op onderzoek en toepassing van kunstmatige intelligentietechnologie, en hun nieuwste model DeepSeek-V2.5 combineert algemene dialoog- en codeverwerkingscapaciteiten, met significante verbeteringen in het afstemmen op menselijke voorkeuren, schrijfopdrachten en het volgen van instructies."
},
+ "doubao": {
+ "description": "Een door ByteDance ontwikkelde grote model. Bewezen in meer dan 50 interne zakelijke scenario's, met een dagelijks gebruik van triljoenen tokens, biedt het verschillende modaliteiten en creëert een rijke zakelijke ervaring voor bedrijven met hoogwaardige modelprestaties."
+ },
"fireworksai": {
"description": "Fireworks AI is een toonaangevende aanbieder van geavanceerde taalmodellen, met een focus op functionele aanroepen en multimodale verwerking. Hun nieuwste model Firefunction V2 is gebaseerd op Llama-3 en geoptimaliseerd voor functieaanroepen, dialogen en het volgen van instructies. Het visuele taalmodel FireLLaVA-13B ondersteunt gemengde invoer van afbeeldingen en tekst. Andere opmerkelijke modellen zijn de Llama-serie en de Mixtral-serie, die efficiënte ondersteuning bieden voor meertalig volgen van instructies en genereren."
},
+ "giteeai": {
+ "description": "Gitee AI's Serverless API biedt AI ontwikkelaars een out of the box grote model inference API service."
+ },
"github": {
"description": "Met GitHub-modellen kunnen ontwikkelaars AI-ingenieurs worden en bouwen met de toonaangevende AI-modellen in de industrie."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "De LPU-inferentie-engine van Groq presteert uitstekend in de nieuwste onafhankelijke benchmarktests voor grote taalmodellen (LLM), en herdefinieert de normen voor AI-oplossingen met zijn verbazingwekkende snelheid en efficiëntie. Groq is een vertegenwoordiger van onmiddellijke inferentiesnelheid en toont goede prestaties in cloudgebaseerde implementaties."
},
+ "higress": {
+ "description": "Higress is een cloud-native API-gateway, ontwikkeld binnen Alibaba om de nadelige effecten van Tengine reload op langdurige verbindingen en de onvoldoende load balancing capaciteiten van gRPC/Dubbo aan te pakken."
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API biedt een snelle en gratis manier om duizenden modellen te verkennen voor verschillende taken. Of u nu prototypes voor nieuwe applicaties ontwerpt of de mogelijkheden van machine learning uitprobeert, deze API geeft u directe toegang tot hoogpresterende modellen in meerdere domeinen."
+ },
+ "hunyuan": {
+ "description": "Een door Tencent ontwikkeld groot taalmodel, dat beschikt over krachtige Chinese creatiecapaciteiten, logische redeneervaardigheden in complexe contexten, en betrouwbare taakuitvoeringscapaciteiten."
+ },
+ "internlm": {
+ "description": "Een open-source organisatie die zich richt op onderzoek en ontwikkeling van tools voor grote modellen. Biedt een efficiënt en gebruiksvriendelijk open-source platform voor alle AI-ontwikkelaars, zodat de meest geavanceerde modellen en algoritmische technologieën binnen handbereik zijn."
+ },
+ "jina": {
+ "description": "Jina AI, opgericht in 2020, is een toonaangevend zoek-AI-bedrijf. Ons zoekplatform bevat vectormodellen, herschikkers en kleine taalmodellen, die bedrijven helpen betrouwbare en hoogwaardige generatieve AI- en multimodale zoektoepassingen te bouwen."
+ },
+ "lmstudio": {
+ "description": "LM Studio is een desktopapplicatie voor het ontwikkelen en experimenteren met LLM's op uw computer."
+ },
"minimax": {
"description": "MiniMax is een algemeen kunstmatige intelligentietechnologiebedrijf dat in 2021 is opgericht, en zich richt op co-creatie van intelligentie met gebruikers. MiniMax heeft verschillende multimodale algemene grote modellen ontwikkeld, waaronder een MoE-tekstgrootmodel met triljoenen parameters, een spraakgrootmodel en een afbeeldingsgrootmodel. Ze hebben ook toepassingen zoals Conch AI gelanceerd."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI is een platform dat API-diensten biedt voor verschillende grote taalmodellen en AI-beeldgeneratie, flexibel, betrouwbaar en kosteneffectief. Het ondersteunt de nieuwste open-source modellen zoals Llama3 en Mistral, en biedt een uitgebreide, gebruiksvriendelijke en automatisch schaalbare API-oplossing voor de ontwikkeling van generatieve AI-toepassingen, geschikt voor de snelle groei van AI-startups."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ biedt containers voor zelf-gehoste GPU-versnelde inferentie-microservices, die de implementatie van voorgetrainde en aangepaste AI-modellen in de cloud, datacenters, RTX™ AI-pc's en werkstations ondersteunen."
+ },
"ollama": {
"description": "De modellen van Ollama bestrijken een breed scala aan gebieden, waaronder codegeneratie, wiskundige berekeningen, meertalige verwerking en interactieve dialogen, en voldoen aan de diverse behoeften van bedrijfs- en lokale implementaties."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity is een toonaangevende aanbieder van dialooggeneratiemodellen, die verschillende geavanceerde Llama 3.1-modellen aanbiedt, die zowel online als offline toepassingen ondersteunen, en bijzonder geschikt zijn voor complexe natuurlijke taalverwerkingstaken."
},
+ "ppio": {
+ "description": "PPIO biedt stabiele en kosteneffectieve open source model API-diensten, die ondersteuning bieden voor de volledige DeepSeek-serie, Llama, Qwen en andere toonaangevende grote modellen in de industrie."
+ },
"qwen": {
"description": "Tongyi Qianwen is een door Alibaba Cloud zelf ontwikkeld grootschalig taalmodel met krachtige mogelijkheden voor natuurlijke taalbegrip en -generatie. Het kan verschillende vragen beantwoorden, tekstinhoud creëren, meningen uiten, code schrijven, en speelt een rol in verschillende domeinen."
},
+ "sambanova": {
+ "description": "SambaNova Cloud stelt ontwikkelaars in staat om eenvoudig gebruik te maken van de beste open-source modellen en te profiteren van de snelste inferentiesnelheden."
+ },
+ "sensenova": {
+ "description": "SenseNova, ondersteund door de krachtige infrastructuur van SenseTime, biedt efficiënte en gebruiksvriendelijke full-stack modelservices."
+ },
"siliconcloud": {
"description": "SiliconFlow streeft ernaar AGI te versnellen ten behoeve van de mensheid, door de efficiëntie van grootschalige AI te verbeteren met een gebruiksvriendelijke en kosteneffectieve GenAI-stack."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "Het Instituut voor Automatisering van de Chinese Academie van Wetenschappen en het Wuhan Instituut voor Kunstmatige Intelligentie hebben een nieuwe generatie multimodale grote modellen gelanceerd, die ondersteuning bieden voor meerdaagse vraag-en-antwoord, tekstcreatie, beeldgeneratie, 3D-begrip, signaalanalyse en andere uitgebreide vraag-en-antwoordtaken, met sterkere cognitieve, begrip en creatiecapaciteiten, wat zorgt voor een geheel nieuwe interactie-ervaring."
},
+ "tencentcloud": {
+ "description": "De atomische capaciteiten van de kennisengine (LLM Knowledge Engine Atomic Power) zijn gebaseerd op de ontwikkeling van de kennisengine en bieden een volledige keten van kennisvraag- en antwoordmogelijkheden, gericht op bedrijven en ontwikkelaars. U kunt verschillende atomische capaciteiten gebruiken om uw eigen modelservice samen te stellen, door gebruik te maken van diensten zoals documentanalyse, splitsing, embedding en meervoudige herschrijving, om een op maat gemaakte AI-oplossing voor uw bedrijf te creëren."
+ },
"togetherai": {
"description": "Together AI streeft ernaar toonaangevende prestaties te bereiken door middel van innovatieve AI-modellen, en biedt uitgebreide aanpassingsmogelijkheden, waaronder ondersteuning voor snelle schaling en intuïtieve implementatieprocessen, om aan de verschillende behoeften van bedrijven te voldoen."
},
"upstage": {
"description": "Upstage richt zich op het ontwikkelen van AI-modellen voor verschillende zakelijke behoeften, waaronder Solar LLM en document AI, met als doel het realiseren van kunstmatige algemene intelligentie (AGI). Het creëert eenvoudige dialoogagenten via de Chat API en ondersteunt functionele aanroepen, vertalingen, insluitingen en specifieke domeintoepassingen."
},
+ "vertexai": {
+ "description": "De Gemini-serie van Google is zijn meest geavanceerde, algemene AI-modellen, ontwikkeld door Google DeepMind. Deze modellen zijn ontworpen voor multimodale toepassingen en ondersteunen naadloze begrip en verwerking van tekst, code, afbeeldingen, audio en video. Ze zijn geschikt voor verschillende omgevingen, van datacenters tot mobiele apparaten, en verbeteren aanzienlijk de efficiëntie en toepasbaarheid van AI-modellen."
+ },
+ "vllm": {
+ "description": "vLLM is een snelle en gebruiksvriendelijke bibliotheek voor LLM-inferentie en -diensten."
+ },
+ "volcengine": {
+ "description": "Het ontwikkelingsplatform voor de grote modellenservice van ByteDance, dat een breed scala aan functies biedt, veilig is en concurrerende prijzen heeft voor modelaanroepdiensten. Het biedt ook end-to-end functionaliteiten zoals modelgegevens, fine-tuning, inferentie en evaluatie, om de ontwikkeling van uw AI-toepassingen volledig te ondersteunen."
+ },
+ "wenxin": {
+ "description": "Een enterprise-grade, alles-in-één platform voor de ontwikkeling en service van grote modellen en AI-native applicaties, dat de meest uitgebreide en gebruiksvriendelijke toolchain biedt voor de ontwikkeling van generatieve kunstmatige intelligentiemodellen en applicaties."
+ },
+ "xai": {
+ "description": "xAI is ein bedrijf dat zich richt op het bouwen van kunstmatige intelligentie om menselijke wetenschappelijke ontdekkingen te versnellen. Onze missie is om onze gezamenlijke begrip van het universum te bevorderen."
+ },
"zeroone": {
"description": "01.AI richt zich op kunstmatige intelligentietechnologie in het tijdperk van AI 2.0, en bevordert sterk de innovatie en toepassing van 'mens + kunstmatige intelligentie', met behulp van krachtige modellen en geavanceerde AI-technologie om de productiviteit van de mens te verbeteren en technologische capaciteiten te realiseren."
},
diff --git a/DigitalHumanWeb/locales/nl-NL/setting.json b/DigitalHumanWeb/locales/nl-NL/setting.json
index ce4491a..8087fb6 100644
--- a/DigitalHumanWeb/locales/nl-NL/setting.json
+++ b/DigitalHumanWeb/locales/nl-NL/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Aangepaste modelconfiguratie",
"tokens": {
- "title": "Maximaal tokenaantal",
- "unlimited": "onbeperkt"
+ "title": "Maximaal tokenaantal"
},
"vision": {
"extra": "Deze configuratie zal alleen de mogelijkheid voor het uploaden van afbeeldingen in de applicatie inschakelen. Of herkenning wordt ondersteund, hangt volledig af van het model zelf. Test de beschikbaarheid van visuele herkenning van dit model zelf.",
@@ -98,6 +97,7 @@
"title": "Gebruik de ophaalmodus aan de clientzijde"
},
"fetcher": {
+ "clear": "Verwijder opgehaalde model",
"fetch": "Haal model lijst op",
"fetching": "Model lijst wordt opgehaald...",
"latestTime": "Laatst bijgewerkt: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Automatisch een onderwerp maken tijdens het gesprek, alleen van toepassing op tijdelijke onderwerpen",
"title": "Automatisch onderwerp maken"
},
- "enableCompressThreshold": {
- "title": "Compressiedrempel voor berichtlengte inschakelen"
+ "enableCompressHistory": {
+ "title": "Automatisch samenvatten van historische berichten inschakelen"
},
"enableHistoryCount": {
"alias": "Onbeperkt",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Limiet voor enkele reacties inschakelen"
},
+ "enableReasoningEffort": {
+ "title": "Inschakelen van redeneringsinspanningsaanpassing"
+ },
"frequencyPenalty": {
- "desc": "Hoe hoger de waarde, hoe waarschijnlijker het is dat herhaalde woorden worden verminderd",
- "title": "Frequentieboete"
+ "desc": "Hoe hoger de waarde, hoe rijker en gevarieerder de woordkeuze; hoe lager de waarde, hoe eenvoudiger en directer de woordkeuze",
+ "title": "Woordenschat diversiteit"
},
"maxTokens": {
"desc": "Het maximale aantal tokens dat wordt gebruikt voor een enkele interactie",
@@ -212,19 +215,31 @@
"desc": "{{provider}} model",
"title": "Model"
},
+ "params": {
+ "title": "Geavanceerde parameters"
+ },
"presencePenalty": {
- "desc": "Hoe hoger de waarde, hoe waarschijnlijker het is dat het gesprek naar nieuwe onderwerpen wordt uitgebreid",
- "title": "Onderwerpnieuwheid"
+ "desc": "Hoe hoger de waarde, hoe meer de neiging om verschillende uitdrukkingen te gebruiken en herhaling van concepten te vermijden; hoe lager de waarde, hoe meer de neiging om herhalende concepten of verhalen te gebruiken, wat zorgt voor meer consistentie in de uitdrukking",
+ "title": "Uitdrukkingsdiversiteit"
+ },
+ "reasoningEffort": {
+ "desc": "Hoe hoger de waarde, hoe sterker de redeneringscapaciteit, maar dit kan de responstijd en het tokenverbruik verhogen",
+ "options": {
+ "high": "Hoog",
+ "low": "Laag",
+ "medium": "Gemiddeld"
+ },
+ "title": "Redeneringsinspanningsniveau"
},
"temperature": {
- "desc": "Hoe hoger de waarde, hoe willekeuriger de reactie",
- "title": "Willekeurigheid",
- "titleWithValue": "Willekeurigheid {{value}}"
+ "desc": "Hoe hoger de waarde, hoe creatiever en fantasierijker het antwoord; hoe lager de waarde, hoe strikter het antwoord.",
+ "title": "Creativiteit Activiteit",
+ "warning": "Een te hoge waarde voor creativiteit activiteit kan leiden tot onleesbare output."
},
"title": "Modelinstellingen",
"topP": {
- "desc": "Vergelijkbaar met willekeurigheid, maar verander dit niet samen met willekeurigheid",
- "title": "Top-P-monstername"
+ "desc": "Hoeveel mogelijkheden er in overweging worden genomen; hoe hoger de waarde, hoe meer mogelijke antwoorden worden geaccepteerd; hoe lager de waarde, hoe meer de voorkeur uitgaat naar het meest waarschijnlijke antwoord. Het wordt niet aanbevolen om dit samen met creativiteit activiteit te wijzigen.",
+ "title": "Openheid van Denken"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Model voor het genereren van assistentnaam, beschrijving, profielfoto en labels",
"title": "Automatisch assistentinformatie genereren"
},
+ "customPrompt": {
+ "addPrompt": "Voeg aangepaste prompt toe",
+ "desc": "Vul dit in, zodat de systeemassistent de aangepaste prompt gebruikt bij het genereren van inhoud",
+ "placeholder": "Voer aangepaste prompt in",
+ "title": "Aangepaste prompt"
+ },
+ "historyCompress": {
+ "label": "Gespreksgeschiedenismodel",
+ "modelDesc": "Specificeer het model dat wordt gebruikt voor het comprimeren van gespreksgeschiedenis",
+ "title": "Automatisch samenvatten van gespreksgeschiedenis"
+ },
"queryRewrite": {
"label": "Vraag herschrijvingsmodel",
"modelDesc": "Model dat is opgegeven voor het optimaliseren van gebruikersvragen",
- "title": "Kennisbank"
+ "title": "Herformuleren van vragen in de kennisbank"
+ },
+ "thread": {
+ "label": "Subtopic Naamgevingsmodel",
+ "modelDesc": "Model dat wordt gebruikt voor het automatisch hernoemen van subonderwerpen",
+ "title": "Automatische naamgeving van subonderwerpen"
},
"title": "Systeemassistent",
"topic": {
@@ -395,6 +426,7 @@
"common": "Algemene instellingen",
"experiment": "Experiment",
"llm": "Taalmodel",
+ "provider": "AI-dienstverlener",
"sync": "Cloudsynchronisatie",
"system-agent": "Systeemassistent",
"tts": "Spraakdienst"
diff --git a/DigitalHumanWeb/locales/nl-NL/thread.json b/DigitalHumanWeb/locales/nl-NL/thread.json
new file mode 100644
index 0000000..7793fb7
--- /dev/null
+++ b/DigitalHumanWeb/locales/nl-NL/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "U staat op het punt dit subonderwerp te verwijderen. Na verwijdering kan het niet worden hersteld, dus wees voorzichtig."
+ },
+ "newPortalThread": {
+ "includeContext": "Inclusief onderwerpcontext",
+ "title": "Een nieuw subonderwerp starten"
+ },
+ "notSupportMultiModals": "Subonderwerpen ondersteunen momenteel geen bestand/afbeelding uploads. Als u behoefte heeft, laat dan gerust een bericht achter: <1>💬 Discussieforum1>"
+}
diff --git a/DigitalHumanWeb/locales/nl-NL/tool.json b/DigitalHumanWeb/locales/nl-NL/tool.json
index 52448ec..996bef4 100644
--- a/DigitalHumanWeb/locales/nl-NL/tool.json
+++ b/DigitalHumanWeb/locales/nl-NL/tool.json
@@ -6,5 +6,23 @@
"generating": "Bezig met genereren...",
"images": "Afbeeldingen:",
"prompt": "prompt"
+ },
+ "search": {
+ "createNewSearch": "Maak een nieuwe zoekopdracht",
+ "emptyResult": "Geen resultaten gevonden, pas alstublieft uw zoekwoorden aan en probeer het opnieuw",
+ "genAiMessage": "Maak assistentbericht",
+ "includedTooltip": "De huidige zoekresultaten worden opgenomen in de context van de sessie",
+ "keywords": "Zoekwoorden:",
+ "scoreTooltip": "Relevantie score, hoe hoger de score, hoe relevanter het is voor de zoekwoorden",
+ "searchBar": {
+ "button": "Zoeken",
+ "placeholder": "Zoekwoorden",
+ "tooltip": "De zoekresultaten worden opnieuw opgehaald en er wordt een nieuwe samenvattingsbericht aangemaakt"
+ },
+ "searchEngine": "Zoekmachine:",
+ "searchResult": "Aantal zoekresultaten:",
+ "summary": "Samenvatting",
+ "summaryTooltip": "Samenvatting van de huidige inhoud",
+ "viewMoreResults": "Bekijk meer {{results}} resultaten"
}
}
diff --git a/DigitalHumanWeb/locales/nl-NL/topic.json b/DigitalHumanWeb/locales/nl-NL/topic.json
new file mode 100644
index 0000000..c8366a0
--- /dev/null
+++ b/DigitalHumanWeb/locales/nl-NL/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Slim hernoemen",
+ "confirmRemoveAll": "U staat op het punt om alle onderwerpen te verwijderen. Na verwijdering kunnen ze niet worden hersteld, wees voorzichtig.",
+ "confirmRemoveTopic": "U staat op het punt om dit onderwerp te verwijderen. Na verwijdering kan het niet worden hersteld, wees voorzichtig.",
+ "confirmRemoveUnstarred": "U staat op het punt om niet-gemarkeerde onderwerpen te verwijderen. Na verwijdering kunnen ze niet worden hersteld, wees voorzichtig.",
+ "duplicate": "Maak een kopie",
+ "export": "Exporteer onderwerp",
+ "removeAll": "Verwijder alle onderwerpen",
+ "removeUnstarred": "Verwijder niet-gemarkeerde onderwerpen"
+ },
+ "defaultTitle": "Standaard onderwerp",
+ "duplicateLoading": "Onderwerp wordt gekopieerd...",
+ "duplicateSuccess": "Onderwerp succesvol gekopieerd",
+ "favorite": "Favoriet",
+ "groupMode": {
+ "ascMessages": "Op volgorde van totaal aantal berichten",
+ "byTime": "Groeperen op tijd",
+ "descMessages": "Op volgorde van totaal aantal berichten (aflopend)",
+ "flat": "Niet groeperen"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Deze maand",
+ "today": "Vandaag",
+ "week": "Deze week",
+ "yesterday": "Gisteren"
+ }
+ },
+ "guide": {
+ "desc": "Klik op de knop aan de linkerkant om de huidige conversatie op te slaan als een historisch onderwerp en een nieuwe conversatie te starten.",
+ "title": "Onderwerpenlijst"
+ },
+ "searchPlaceholder": "Zoek onderwerpen...",
+ "searchResultEmpty": "Geen zoekresultaten gevonden",
+ "temp": "Tijdelijk",
+ "title": "Onderwerp"
+}
diff --git a/DigitalHumanWeb/locales/nl-NL/welcome.json b/DigitalHumanWeb/locales/nl-NL/welcome.json
index 86e50a5..67ce3bb 100644
--- a/DigitalHumanWeb/locales/nl-NL/welcome.json
+++ b/DigitalHumanWeb/locales/nl-NL/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Importeer configuratie",
- "market": "Verken de markt",
- "start": "Nu beginnen"
- },
"guide": {
"agents": {
"replaceBtn": "Vervang een groep",
diff --git a/DigitalHumanWeb/locales/pl-PL/auth.json b/DigitalHumanWeb/locales/pl-PL/auth.json
index 64f2b15..6679e70 100644
--- a/DigitalHumanWeb/locales/pl-PL/auth.json
+++ b/DigitalHumanWeb/locales/pl-PL/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Poprzedni miesiąc",
+ "recent30Days": "Ostatnie 30 dni"
+ },
+ "header": {
+ "desc": "Zarządzaj informacjami o swoim koncie.",
+ "title": "Konto"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Nieaktywny",
+ "more": "Aktywny"
+ },
+ "months": {
+ "apr": "Kwi",
+ "aug": "Sie",
+ "dec": "Gru",
+ "feb": "Lut",
+ "jan": "Sty",
+ "jul": "Lip",
+ "jun": "Cze",
+ "mar": "Mar",
+ "may": "Maj",
+ "nov": "Lis",
+ "oct": "Paź",
+ "sep": "Wrz"
+ },
+ "tooltip": "{{date}} wysłał {{count}} wiadomości tego dnia",
+ "totalCount": "Łącznie {{count}} wiadomości wysłanych w ciągu ostatniego roku"
+ },
"login": "Zaloguj się",
"loginOrSignup": "Zaloguj się / Zarejestruj się",
- "profile": "Profil użytkownika",
- "security": "Bezpieczeństwo",
- "signout": "Wyloguj",
- "signup": "Zarejestruj się"
+ "profile": {
+ "avatar": "Awatar",
+ "email": "Adres e-mail",
+ "sso": {
+ "loading": "Ładowanie powiązanych kont zewnętrznych",
+ "providers": "Podłączone konta",
+ "unlink": {
+ "description": "Po odłączeniu nie będziesz mógł korzystać z konta {{provider}} „{{providerAccountId}}” do logowania. Jeśli potrzebujesz ponownie powiązać konto {{provider}} z bieżącym kontem, upewnij się, że adres e-mail konta {{provider}} to {{email}}, a my automatycznie je powiążemy podczas logowania.",
+ "forbidden": "Musisz zachować co najmniej jedno powiązane konto zewnętrzne.",
+ "title": "Czy odłączyć to konto zewnętrzne {{provider}}?"
+ }
+ },
+ "username": "Nazwa użytkownika"
+ },
+ "signout": "Wyloguj się",
+ "signup": "Zarejestruj się",
+ "stats": {
+ "aiheatmaps": "Indeks Aktywności",
+ "assistants": "Asystenci",
+ "assistantsRank": {
+ "left": "Asystent",
+ "right": "Tematy",
+ "title": "Ranking Użycia Asystentów"
+ },
+ "createdAt": "Zarejestrowano",
+ "days": "dni",
+ "empty": {
+ "desc": "Proszę zgromadzić więcej danych czatu, aby wyświetlić",
+ "title": "Brak danych"
+ },
+ "lastYearActivity": "aktywność w ciągu ostatniego roku",
+ "loginGuide": {
+ "f1": "Uzyskaj darmowy limit",
+ "f2": "Synchronizuj wiadomości na wielu urządzeniach",
+ "f3": "Skorzystaj z bogatego asystenta",
+ "f4": "Odkryj potężne wtyczki",
+ "title": "Po zalogowaniu możesz:"
+ },
+ "messages": "Wiadomości",
+ "modelsRank": {
+ "left": "Model",
+ "right": "Wiadomości",
+ "title": "Ranking Użycia Modeli"
+ },
+ "share": {
+ "title": "Mój Indeks Aktywności AI"
+ },
+ "topics": "Tematy",
+ "topicsRank": {
+ "left": "Temat",
+ "right": "Wiadomości",
+ "title": "Ranking Treści Tematów"
+ },
+ "updatedAt": "Zaktualizowano",
+ "welcome": "{{username}}, to twój {{days}} dzień z {{appName}}",
+ "words": "Słowa"
+ },
+ "tab": {
+ "profile": "Profil",
+ "security": "Bezpieczeństwo",
+ "stats": "Statystyki"
+ }
}
diff --git a/DigitalHumanWeb/locales/pl-PL/changelog.json b/DigitalHumanWeb/locales/pl-PL/changelog.json
new file mode 100644
index 0000000..65b0aec
--- /dev/null
+++ b/DigitalHumanWeb/locales/pl-PL/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Obserwuj nas na X",
+ "subscribeToUpdates": "Subskrybuj aktualizacje",
+ "versions": "Szczegóły wersji"
+ },
+ "addedWhileAway": "W czasie Twojej nieobecności wprowadziliśmy nowe funkcje.",
+ "allChangelog": "Zobacz wszystkie dzienniki zmian",
+ "description": "Na bieżąco śledź nowe funkcje i ulepszenia {{appName}}",
+ "pagination": {
+ "next": "Następna strona",
+ "older": "Zobacz wcześniejsze zmiany"
+ },
+ "readDetails": "Przeczytaj szczegóły",
+ "title": "Dziennik zmian",
+ "versionDetails": "Szczegóły wersji",
+ "welcomeBack": "Witaj z powrotem!"
+}
diff --git a/DigitalHumanWeb/locales/pl-PL/chat.json b/DigitalHumanWeb/locales/pl-PL/chat.json
index fc5d47c..43fc54b 100644
--- a/DigitalHumanWeb/locales/pl-PL/chat.json
+++ b/DigitalHumanWeb/locales/pl-PL/chat.json
@@ -8,6 +8,7 @@
"agents": "Asystent",
"artifact": {
"generating": "Generowanie",
+ "inThread": "Nie można przeglądać w wątku, przełącz się na główny obszar rozmowy, aby otworzyć",
"thinking": "Myślenie",
"thought": "Proces myślenia",
"unknownTitle": "Nienazwane dzieło"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} kopia",
"emptyAgent": "Brak asystenta",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Koszt generowania pojedynczej rozmowy może zostać obniżony o 90%, a prędkość odpowiedzi wzrośnie czterokrotnie (<1>Dowiedz się więcej1>). Po włączeniu automatycznie wyłączone zostanie ograniczenie liczby wiadomości historycznych",
+ "title": "Włącz pamięć kontekstową"
+ },
+ "enableReasoning": {
+ "desc": "Ograniczenia oparte na mechanizmie Claude Thinking (<1>Dowiedz się więcej1>), po włączeniu automatycznie wyłączone zostanie ograniczenie liczby wiadomości historycznych",
+ "title": "Włącz głębokie myślenie"
+ },
+ "reasoningBudgetToken": {
+ "title": "Token zużycia myślenia"
+ },
+ "title": "Funkcje rozszerzenia modelu"
+ },
+ "history": {
+ "title": "Asystent zapamięta tylko ostatnie {{count}} wiadomości"
+ },
"historyRange": "Zakres historii",
+ "historySummary": "Podsumowanie wiadomości historycznych",
"inbox": {
"desc": "Włącz klastry mózgów, rozpal iskrę myślenia. Twój inteligentny asystent, gotowy do rozmowy o wszystkim.",
"title": "Pogadajmy sobie"
@@ -45,6 +64,9 @@
"stop": "Zatrzymaj",
"warp": "Złamanie wiersza"
},
+ "intentUnderstanding": {
+ "title": "Rozumiemy i analizujemy Twoje intencje..."
+ },
"knowledgeBase": {
"all": "Wszystkie treści",
"allFiles": "Wszystkie pliki",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Usuń i wygeneruj ponownie",
+ "deleteDisabledByThreads": "Istnieją podwątki, nie można usunąć",
"regenerate": "Wygeneruj ponownie"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Punkty",
+ "creditPricing": "Cennik",
+ "creditTooltip": "Aby ułatwić obliczenia, przeliczamy 1$ na 1M punktów, na przykład $3/M tokenów to 3 punkty/token",
+ "pricing": {
+ "inputCachedTokens": "Zbuforowane wejście {{amount}}/punktów · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M znaków",
+ "inputMinutes": "${{amount}}/minutę",
+ "inputTokens": "Wejście {{amount}}/punktów · ${{amount}}/M",
+ "outputTokens": "Wyjście {{amount}}/punktów · ${{amount}}/M",
+ "writeCacheInputTokens": "Zapisz wejście w pamięci podręcznej {{amount}}/punktów · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Średnia cena",
+ "input": "Wejście",
+ "inputAudio": "Wejście audio",
+ "inputCached": "Zbuforowane wejście",
+ "inputCitation": "Cytowanie wejścia",
+ "inputText": "Wejście tekstowe",
+ "inputTitle": "Szczegóły wejścia",
+ "inputUncached": "Wejście niezbuforowane",
+ "inputWriteCached": "Zapisz wejście w pamięci podręcznej",
+ "output": "Wyjście",
+ "outputAudio": "Wyjście audio",
+ "outputText": "Wyjście tekstowe",
+ "outputTitle": "Szczegóły wyjścia",
+ "reasoning": "Głębokie myślenie",
+ "title": "Szczegóły generacji",
+ "total": "Całkowite zużycie"
+ }
+ },
"newAgent": "Nowy asystent",
"pin": "Przypnij",
"pinOff": "Odepnij",
@@ -81,6 +137,32 @@
},
"regenerate": "Wygeneruj ponownie",
"roleAndArchive": "Rola i archiwum",
+ "search": {
+ "grounding": {
+ "searchQueries": "Szukaj słów kluczowych",
+ "title": "Znaleziono {{count}} wyników"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Inteligentne określenie, czy potrzebne jest wyszukiwanie na podstawie treści rozmowy",
+ "title": "Inteligentne połączenie"
+ },
+ "off": {
+ "desc": "Używaj tylko podstawowej wiedzy modelu, bez wyszukiwania w sieci",
+ "title": "Wyłącz połączenie"
+ },
+ "on": {
+ "desc": "Ciągłe wyszukiwanie w sieci, aby uzyskać najnowsze informacje",
+ "title": "Zawsze połączony"
+ },
+ "useModelBuiltin": "Użyj wbudowanej wyszukiwarki modelu"
+ },
+ "searchModel": {
+ "desc": "Aktualny model nie obsługuje wywołań funkcji, dlatego wymaga współpracy z modelem obsługującym wywołania funkcji, aby móc przeszukiwać sieć",
+ "title": "Model wspomagający wyszukiwanie"
+ },
+ "title": "Wyszukiwanie w sieci"
+ },
"searchAgentPlaceholder": "Wyszukaj pomocnika...",
"sendPlaceholder": "Wpisz treść rozmowy...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Nazwa grupy musi mieć od 1 do 20 znaków"
},
"shareModal": {
+ "copy": "Kopiuj",
"download": "Pobierz zrzut ekranu",
+ "downloadFile": "Pobierz plik",
+ "exportTitle": "Domyślny tytuł",
"imageType": "Typ obrazu",
+ "includeTool": "Uwzględnij wiadomości z narzędzi",
+ "includeUser": "Uwzględnij wiadomości od użytkowników",
"screenshot": "Zrzut ekranu",
"settings": "Ustawienia eksportu",
- "shareToShareGPT": "Generuj link udostępniania ShareGPT",
+ "text": "Tekst",
"withBackground": "Z tłem",
"withFooter": "Z stopką",
"withPluginInfo": "Z informacjami o wtyczce",
+ "withRole": "Uwzględnij rolę wiadomości",
"withSystemRole": "Z rolą asystenta"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Rozpoznawanie...",
"prettifying": "Upiększanie..."
},
- "temp": "Tymczasowy",
+ "thread": {
+ "divider": "Podwątek",
+ "threadMessageCount": "{{messageCount}} wiadomości",
+ "title": "Podwątek"
+ },
"tokenDetails": {
"chats": "Rozmowy",
+ "historySummary": "Podsumowanie historii",
"rest": "Pozostałe",
"systemRole": "Rola systemowa",
"title": "Szczegóły tokena",
@@ -131,29 +224,10 @@
"used": "Użyte"
},
"topic": {
- "actions": {
- "autoRename": "Automatyczna zmiana nazwy",
- "duplicate": "Utwórz kopię",
- "export": "Eksportuj temat"
- },
"checkOpenNewTopic": "Czy otworzyć nowy temat?",
"checkSaveCurrentMessages": "Czy zapisać bieżącą rozmowę jako temat?",
- "confirmRemoveAll": "Czy na pewno chcesz usunąć wszystkie tematy? Tej operacji nie można cofnąć. Proszę potwierdź swoją decyzję.",
- "confirmRemoveTopic": "Czy na pewno chcesz usunąć ten temat? Tej operacji nie można cofnąć. Proszę potwierdź swoją decyzję.",
- "confirmRemoveUnstarred": "Czy na pewno chcesz usunąć nieoznaczone tematy? Tej operacji nie można cofnąć. Proszę potwierdź swoją decyzję.",
- "defaultTitle": "Domyślne tematy",
- "duplicateLoading": "Kopiowanie tematu...",
- "duplicateSuccess": "Temat został skopiowany pomyślnie",
- "guide": {
- "desc": "Kliknij przycisk po lewej stronie, aby zapisać bieżącą rozmowę jako historię tematu i rozpocząć nową rundę rozmowy",
- "title": "Lista tematów"
- },
"openNewTopic": "Otwórz nowy temat",
- "removeAll": "Usuń wszystkie tematy",
- "removeUnstarred": "Usuń nieoznaczone tematy",
- "saveCurrentMessages": "Zapisz bieżącą rozmowę jako temat",
- "searchPlaceholder": "Szukaj tematów...",
- "title": "Lista tematów"
+ "saveCurrentMessages": "Zapisz bieżącą rozmowę jako temat"
},
"translate": {
"action": "Tłumaczenie",
@@ -184,5 +258,6 @@
"processing": "Przetwarzanie pliku..."
}
}
- }
+ },
+ "zenMode": "Tryb skupienia"
}
diff --git a/DigitalHumanWeb/locales/pl-PL/common.json b/DigitalHumanWeb/locales/pl-PL/common.json
index 352189c..4c0af23 100644
--- a/DigitalHumanWeb/locales/pl-PL/common.json
+++ b/DigitalHumanWeb/locales/pl-PL/common.json
@@ -9,15 +9,79 @@
"title": "Witaj w {{name}}"
}
},
- "appInitializing": "Aplikacja uruchamia się...",
+ "appLoading": {
+ "appIdle": "Zarządzanie uruchomieniem",
+ "appInitializing": "Aplikacja się uruchamia...",
+ "failed": "Przykro nam, inicjalizacja aplikacji nie powiodła się, proszę sprawdzić szczegóły, aby znaleźć przyczynę.",
+ "finished": "Inicjalizacja bazy danych zakończona",
+ "goToChat": "Ładowanie strony czatu...",
+ "initAuth": "Inicjalizacja usługi autoryzacji...",
+ "initUser": "Inicjalizacja stanu użytkownika...",
+ "initializing": "Inicjalizacja bazy danych PGlite...",
+ "loadingDependencies": "Inicjalizacja zależności...",
+ "loadingWasm": "Ładowanie modułu WASM...",
+ "migrating": "Wykonywanie migracji tabeli danych...",
+ "ready": "Baza danych jest gotowa",
+ "showDetail": "Zobacz szczegóły"
+ },
"autoGenerate": "Automatyczne generowanie",
"autoGenerateTooltip": "Automatyczne uzupełnianie opisu asystenta na podstawie sugestii",
"autoGenerateTooltipDisabled": "Proszę wprowadzić słowo kluczowe przed użyciem funkcji automatycznego uzupełniania",
"back": "Powrót",
"batchDelete": "Usuń wiele",
"blog": "Blog produktowy",
+ "branching": "Utwórz podtemat",
+ "branchingDisable": "Funkcja „podtemat” jest dostępna tylko w wersji serwerowej. Aby skorzystać z tej funkcji, przełącz się na tryb wdrożenia serwera lub użyj LobeChat Cloud.",
"cancel": "Anuluj",
"changelog": "Dziennik zmian",
+ "clientDB": {
+ "autoInit": {
+ "title": "Inicjalizacja bazy danych PGlite"
+ },
+ "error": {
+ "desc": "Przykro nam, wystąpił błąd podczas inicjalizacji bazy danych Pglite. Proszę kliknąć przycisk, aby spróbować ponownie. Jeśli błąd powtarza się po wielokrotnych próbach, proszę <1>zgłosić problem1>, a my jak najszybciej pomożemy w rozwiązaniu.",
+ "detail": "Powód błędu: [{{type}}] {{message}}. Szczegóły poniżej:",
+ "retry": "Spróbuj ponownie",
+ "title": "Błąd inicjalizacji bazy danych"
+ },
+ "initing": {
+ "error": "Wystąpił błąd, proszę spróbować ponownie",
+ "idle": "Oczekiwanie na inicjalizację...",
+ "initializing": "Inicjalizowanie...",
+ "loadingDependencies": "Ładowanie zależności...",
+ "loadingWasmModule": "Ładowanie modułu WASM...",
+ "migrating": "Wykonywanie migracji tabeli danych...",
+ "ready": "Baza danych gotowa"
+ },
+ "modal": {
+ "desc": "Włącz klienta bazy danych PGlite, aby trwale przechowywać dane czatu w przeglądarce i korzystać z zaawansowanych funkcji, takich jak baza wiedzy",
+ "enable": "Włącz teraz",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Zgromadź swoją osobistą bazę wiedzy i łatwo rozpocznij rozmowę z asystentem (wkrótce dostępne)",
+ "title": "Wsparcie dla rozmów w bazie wiedzy, uruchomienie drugiego mózgu"
+ },
+ "localFirst": {
+ "desc": "Dane czatu są całkowicie przechowywane w przeglądarce, twoje dane są zawsze pod twoją kontrolą.",
+ "title": "Lokalnie najpierw, prywatność przede wszystkim"
+ },
+ "pglite": {
+ "desc": "Zbudowane na PGlite, natywne wsparcie dla zaawansowanych funkcji AI Native (wyszukiwanie wektorowe)",
+ "title": "Nowa generacja architektury przechowywania klienta"
+ }
+ },
+ "init": {
+ "desc": "Inicjalizacja bazy danych trwa, w zależności od jakości sieci może zająć od 5 do 30 sekund",
+ "title": "Inicjalizacja bazy danych PGlite"
+ },
+ "title": "Włącz bazę danych klienta"
+ },
+ "ready": {
+ "button": "Użyj teraz",
+ "desc": "Chcę użyć teraz",
+ "title": "Baza danych PGlite jest gotowa"
+ }
+ },
"close": "Zamknij",
"contact": "Skontaktuj się z nami",
"copy": "Kopiuj",
@@ -112,6 +176,7 @@
"en": "Angielski",
"en-US": "Angielski (USA)",
"es-ES": "Hiszpański",
+ "fa-IR": "perski",
"fi-FI": "Fiński",
"fr-FR": "Francuski",
"hi-IN": "Hindi",
@@ -153,6 +218,7 @@
"pinOff": "Odepnij",
"privacy": "Polityka prywatności",
"regenerate": "Regeneruj",
+ "releaseNotes": "Szczegóły wersji",
"rename": "Zmień nazwę",
"reset": "Resetuj",
"retry": "Ponów",
@@ -209,6 +275,7 @@
},
"temp": "Tymczasowy",
"terms": "Warunki korzystania",
+ "update": "Aktualizuj",
"updateAgent": "Zaktualizuj informacje o agencie",
"upgradeVersion": {
"action": "Aktualizuj",
@@ -219,6 +286,7 @@
"anonymousNickName": "Użytkownik Anonimowy",
"billing": "Zarządzanie rachunkami",
"cloud": "Wypróbuj {{name}}",
+ "community": "Wersja społeczności",
"data": "Przechowywanie danych",
"defaultNickname": "Użytkownik Wersji Społecznościowej",
"discord": "Wsparcie społeczności",
@@ -228,7 +296,6 @@
"help": "Centrum pomocy",
"moveGuide": "Przenieś przycisk ustawień tutaj",
"plans": "Plan abonamentu",
- "preview": "Podgląd",
"profile": "Zarządzanie kontem",
"setting": "Ustawienia aplikacji",
"usages": "Statystyki użycia"
diff --git a/DigitalHumanWeb/locales/pl-PL/components.json b/DigitalHumanWeb/locales/pl-PL/components.json
index a91bed0..861c79a 100644
--- a/DigitalHumanWeb/locales/pl-PL/components.json
+++ b/DigitalHumanWeb/locales/pl-PL/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Partycjonowanie wsadowe",
"chunking": "Partycjonowanie",
"chunkingTooltip": "Podziel plik na wiele bloków tekstowych i wektoryzuj, aby umożliwić wyszukiwanie semantyczne i rozmowy o plikach",
+ "chunkingUnsupported": "Ten plik nie obsługuje podziału na części.",
"confirmDelete": "Zaraz usuniesz ten plik. Po usunięciu nie będzie można go odzyskać, proszę potwierdź swoje działanie",
"confirmDeleteMultiFiles": "Zaraz usuniesz wybrane {{count}} plików. Po usunięciu nie będzie można ich odzyskać, proszę potwierdź swoje działanie",
"confirmRemoveFromKnowledgeBase": "Zaraz usuniesz wybrane {{count}} plików z bazy wiedzy. Po usunięciu pliki będą nadal widoczne wśród wszystkich plików, proszę potwierdź swoje działanie",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Wróć"
},
+ "MaxTokenSlider": {
+ "unlimited": "Bez ograniczeń"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Niestandardowy model, domyślnie obsługujący zarówno wywołania funkcji, jak i rozpoznawanie wizualne. Proszę zweryfikować możliwość użycia tych funkcji w praktyce.",
"file": "Ten model obsługuje wczytywanie plików i rozpoznawanie",
"functionCall": "Ten model obsługuje wywołania funkcji (Function Call).",
+ "reasoning": "Ten model wspiera głębokie myślenie",
+ "search": "Ten model wspiera wyszukiwanie w sieci",
"tokens": "Ten model obsługuje maksymalnie {{tokens}} tokenów w pojedynczej sesji.",
"vision": "Ten model obsługuje rozpoznawanie wizualne."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Brak włączonych modeli, przejdź do ustawień i włącz je",
+ "emptyProvider": "Nie ma aktywnego dostawcy usług, przejdź do ustawień, aby go włączyć",
+ "goToSettings": "Przejdź do ustawień",
"provider": "Dostawca"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Z powodu ograniczeń bezpieczeństwa przeglądarki, musisz skonfigurować CORS dla Ollama, aby móc go używać.",
+ "linux": {
+ "env": "Dodaj `Environment` w sekcji [Service], dodając zmienną środowiskową OLLAMA_ORIGINS:",
+ "reboot": "Przeładuj systemd i uruchom ponownie Ollama",
+ "systemd": "Wywołaj systemd, aby edytować usługę ollama:"
+ },
+ "macos": "Otwórz aplikację „Terminal” i wklej poniższe polecenie, a następnie naciśnij Enter, aby je uruchomić",
+ "reboot": "Po zakończeniu wykonania, uruchom ponownie usługę Ollama",
+ "title": "Skonfiguruj Ollama, aby zezwolić na dostęp międzydomenowy",
+ "windows": "Na Windowsie, kliknij „Panel sterowania”, aby edytować zmienne środowiskowe systemu. Utwórz nową zmienną środowiskową o nazwie „OLLAMA_ORIGINS” dla swojego konta użytkownika, ustawiając wartość na * i kliknij „OK/Zastosuj”, aby zapisać"
+ },
+ "install": {
+ "description": "Upewnij się, że uruchomiłeś Ollama. Jeśli nie masz Ollama, przejdź na oficjalną stronę <1>pobierz1>",
+ "docker": "Jeśli wolisz używać Dockera, Ollama również oferuje oficjalny obraz Dockera, który możesz pobrać za pomocą poniższego polecenia:",
+ "linux": {
+ "command": "Zainstaluj za pomocą poniższego polecenia:",
+ "manual": "Alternatywnie, możesz również zapoznać się z <1>podręcznikiem instalacji ręcznej dla Linuxa1>, aby zainstalować samodzielnie"
+ },
+ "title": "Zainstaluj i uruchom aplikację Ollama lokalnie",
+ "windowsTab": "Windows (wersja podglądowa)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Głęboko myślę...",
+ "thought": "Głęboko przemyślane (czas: {{duration}} sekund)",
+ "thoughtWithDuration": "Głęboko przemyślane"
}
}
diff --git a/DigitalHumanWeb/locales/pl-PL/discover.json b/DigitalHumanWeb/locales/pl-PL/discover.json
index fb78a54..a9071ae 100644
--- a/DigitalHumanWeb/locales/pl-PL/discover.json
+++ b/DigitalHumanWeb/locales/pl-PL/discover.json
@@ -126,6 +126,10 @@
"title": "Świeżość tematu"
},
"range": "Zakres",
+ "reasoning_effort": {
+ "desc": "To ustawienie kontroluje intensywność rozumowania modelu przed wygenerowaniem odpowiedzi. Niska intensywność priorytetowo traktuje szybkość odpowiedzi i oszczędza tokeny, podczas gdy wysoka intensywność zapewnia pełniejsze rozumowanie, ale zużywa więcej tokenów i obniża szybkość odpowiedzi. Wartość domyślna to średnia, co równoważy dokładność rozumowania z szybkością odpowiedzi.",
+ "title": "Intensywność rozumowania"
+ },
"temperature": {
"desc": "To ustawienie wpływa na różnorodność odpowiedzi modelu. Niższe wartości prowadzą do bardziej przewidywalnych i typowych odpowiedzi, podczas gdy wyższe wartości zachęcają do bardziej zróżnicowanych i rzadziej spotykanych odpowiedzi. Gdy wartość wynosi 0, model zawsze daje tę samą odpowiedź na dane wejście.",
"title": "Losowość"
diff --git a/DigitalHumanWeb/locales/pl-PL/error.json b/DigitalHumanWeb/locales/pl-PL/error.json
index a2be5ff..a4a9585 100644
--- a/DigitalHumanWeb/locales/pl-PL/error.json
+++ b/DigitalHumanWeb/locales/pl-PL/error.json
@@ -12,8 +12,14 @@
"retry": "Ponów próbę",
"title": "Napotkano problem na stronie.."
},
- "fetchError": "Błąd żądania",
- "fetchErrorDetail": "Szczegóły błędu",
+ "fetchError": {
+ "detail": "Szczegóły błędu",
+ "title": "Żądanie nie powiodło się"
+ },
+ "loginRequired": {
+ "desc": "Zaraz nastąpi automatyczne przekierowanie do strony logowania",
+ "title": "Proszę zalogować się, aby korzystać z tej funkcji"
+ },
"notFound": {
"backHome": "Powrót do strony głównej",
"check": "Proszę sprawdzić, czy Twój adres URL jest poprawny",
@@ -51,22 +57,34 @@
"431": "Przepraszamy, nagłówek żądania jest zbyt duży, serwer nie może go przetworzyć",
"451": "Przepraszamy, z powodów prawnych serwer odmawia dostarczenia tego zasobu",
"500": "Przepraszamy, serwer napotkał pewne trudności i tymczasowo nie może zrealizować Twojego żądania. Proszę spróbuj ponownie później",
+ "501": "Przykro nam, serwer nie wie, jak obsłużyć to żądanie, proszę upewnić się, że Twoje działanie jest poprawne",
"502": "Przepraszamy, serwer wydaje się zgubić kierunek i tymczasowo nie może świadczyć usług. Proszę spróbuj ponownie później",
"503": "Przepraszamy, serwer tymczasowo nie może przetworzyć Twojego żądania, prawdopodobnie z powodu przeciążenia lub konserwacji. Proszę spróbuj ponownie później",
"504": "Przepraszamy, serwer nie otrzymał odpowiedzi od serwera nadrzędnego. Proszę spróbuj ponownie później",
+ "505": "Przykro nam, serwer nie obsługuje używanej wersji HTTP, proszę zaktualizować i spróbować ponownie",
+ "506": "Przykro nam, wystąpił problem z konfiguracją serwera, proszę skontaktować się z administratorem w celu rozwiązania",
+ "507": "Przykro nam, serwer ma niewystarczającą przestrzeń dyskową, aby obsłużyć Twoje żądanie, proszę spróbować ponownie później",
+ "509": "Przykro nam, pasmo serwera zostało wyczerpane, proszę spróbować ponownie później",
+ "510": "Przykro nam, serwer nie obsługuje żądanej funkcji rozszerzenia, proszę skontaktować się z administratorem",
+ "524": "Przykro nam, serwer przekroczył czas oczekiwania na odpowiedź, może to być spowodowane zbyt wolną odpowiedzią, proszę spróbować ponownie później",
"AgentRuntimeError": "Wystąpił błąd wykonania modelu językowego Lobe, prosimy o sprawdzenie poniższych informacji lub ponowne próbowanie.",
+ "ConnectionCheckFailed": "Odpowiedź jest pusta. Sprawdź, czy na końcu adresu proxy API nie brakuje `/v1`",
+ "ExceededContextWindow": "Aktualna zawartość żądania przekracza długość, którą model może przetworzyć. Proszę zmniejszyć ilość treści i spróbować ponownie.",
"FreePlanLimit": "Jesteś obecnie użytkownikiem darmowej wersji, nie możesz korzystać z tej funkcji. Proszę uaktualnić do planu płatnego, aby kontynuować korzystanie.",
+ "InsufficientQuota": "Przykro nam, limit dla tego klucza został osiągnięty. Proszę sprawdzić saldo konta lub zwiększyć limit klucza i spróbować ponownie.",
"InvalidAccessCode": "Nieprawidłowy kod dostępu: Hasło jest nieprawidłowe lub puste. Proszę wprowadzić poprawne hasło dostępu lub dodać niestandardowy klucz API.",
"InvalidBedrockCredentials": "Uwierzytelnienie Bedrock nie powiodło się, prosimy sprawdzić AccessKeyId/SecretAccessKey i spróbować ponownie.",
"InvalidClerkUser": "Przepraszamy, nie jesteś obecnie zalogowany. Proszę najpierw zalogować się lub zarejestrować, aby kontynuować.",
"InvalidGithubToken": "Token dostępu osobistego do GitHub jest niewłaściwy lub pusty. Proszę sprawdzić Token dostępu osobistego do GitHub i spróbować ponownie.",
"InvalidOllamaArgs": "Nieprawidłowa konfiguracja Ollama, sprawdź konfigurację Ollama i spróbuj ponownie",
"InvalidProviderAPIKey": "{{provider}} Klucz API jest nieprawidłowy lub pusty. Sprawdź Klucz API {{provider}} i spróbuj ponownie.",
+ "InvalidVertexCredentials": "Weryfikacja poświadczeń Vertex nie powiodła się, proszę sprawdzić poświadczenia i spróbować ponownie",
"LocationNotSupportError": "Przepraszamy, Twoja lokalizacja nie obsługuje tego usługi modelu, być może ze względu na ograniczenia regionalne lub brak dostępności usługi. Proszę sprawdź, czy bieżąca lokalizacja obsługuje tę usługę, lub spróbuj użyć innych informacji o lokalizacji.",
+ "ModelNotFound": "Przykro nam, nie można zażądać odpowiedniego modelu, może on nie istnieć lub brakować dostępu. Proszę zmienić klucz API lub dostosować uprawnienia dostępu, a następnie spróbować ponownie.",
"NoOpenAIAPIKey": "Klucz API OpenAI jest pusty. Proszę dodać niestandardowy klucz API OpenAI",
"OllamaBizError": "Błąd usługi Ollama, sprawdź poniższe informacje lub spróbuj ponownie",
"OllamaServiceUnavailable": "Usługa Ollama jest niedostępna. Sprawdź, czy Ollama działa poprawnie, lub czy poprawnie skonfigurowano ustawienia przekraczania domeny Ollama",
- "OpenAIBizError": "Wystąpił błąd usługi OpenAI, proszę sprawdzić poniższe informacje lub spróbować ponownie",
+ "PermissionDenied": "Przykro nam, nie masz uprawnień do dostępu do tej usługi. Proszę sprawdzić, czy Twój klucz ma odpowiednie uprawnienia dostępu.",
"PluginApiNotFound": "Przepraszamy, w manifestach wtyczki nie istnieje to API. Proszę sprawdź, czy metoda żądania jest zgodna z API w manifestach wtyczki",
"PluginApiParamsError": "Przepraszamy, walidacja parametrów wejściowych żądanej wtyczki nie powiodła się. Proszę sprawdź, czy parametry wejściowe są zgodne z informacjami opisującymi API",
"PluginFailToTransformArguments": "Przepraszamy, nie udało się przekształcić argumentów wywołania wtyczki. Spróbuj ponownie wygenerować wiadomość pomocnika lub zmień model AI o większej zdolności do wywoływania narzędzi i spróbuj ponownie",
@@ -81,8 +99,11 @@
"PluginServerError": "Błąd zwrócony przez serwer wtyczki. Proszę sprawdź plik opisowy wtyczki, konfigurację wtyczki lub implementację serwera zgodnie z poniższymi informacjami o błędzie",
"PluginSettingsInvalid": "Ta wtyczka wymaga poprawnej konfiguracji przed użyciem. Proszę sprawdź, czy Twoja konfiguracja jest poprawna",
"ProviderBizError": "Wystąpił błąd usługi {{provider}}, proszę sprawdzić poniższe informacje lub spróbować ponownie",
+ "QuotaLimitReached": "Przykro nam, bieżące zużycie tokenów lub liczba żądań osiągnęła limit kwoty dla tego klucza. Proszę zwiększyć limit kwoty dla tego klucza lub spróbować ponownie później.",
"StreamChunkError": "Błąd analizy bloku wiadomości w żądaniu strumieniowym. Proszę sprawdzić, czy aktualny interfejs API jest zgodny z normami, lub skontaktować się z dostawcą API w celu uzyskania informacji.",
- "SubscriptionPlanLimit": "Wykorzystałeś limit swojego abonamentu i nie możesz korzystać z tej funkcji. Proszę uaktualnić do wyższego planu lub zakupić dodatkowy pakiet zasobów, aby kontynuować korzystanie.",
+ "SubscriptionKeyMismatch": "Przepraszamy, z powodu sporadycznych awarii systemu, bieżące zużycie subskrypcji jest tymczasowo nieaktywne. Proszę kliknąć przycisk poniżej, aby przywrócić subskrypcję lub skontaktować się z nami drogą mailową w celu uzyskania wsparcia.",
+ "SubscriptionPlanLimit": "Twoje punkty subskrypcyjne zostały wyczerpane, nie możesz korzystać z tej funkcji. Proszę zaktualizować do wyższego planu lub skonfigurować API modelu niestandardowego, aby kontynuować korzystanie.",
+ "SystemTimeNotMatchError": "Przykro nam, czas systemowy nie zgadza się z czasem serwera. Proszę sprawdzić czas systemowy i spróbować ponownie.",
"UnknownChatFetchError": "Przykro nam, wystąpił nieznany błąd żądania. Proszę sprawdzić poniższe informacje lub spróbować ponownie."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/pl-PL/metadata.json b/DigitalHumanWeb/locales/pl-PL/metadata.json
index abfb8db..c5533eb 100644
--- a/DigitalHumanWeb/locales/pl-PL/metadata.json
+++ b/DigitalHumanWeb/locales/pl-PL/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Bieżące śledzenie nowych funkcji i ulepszeń {{appName}}",
+ "title": "Dziennik zmian"
+ },
"chat": {
"description": "{{appName}} oferuje najlepsze doświadczenia z ChatGPT, Claude, Gemini, OLLaMA WebUI",
"title": "{{appName}}: osobiste narzędzie AI, które daje ci mądrzejszy umysł"
diff --git a/DigitalHumanWeb/locales/pl-PL/modelProvider.json b/DigitalHumanWeb/locales/pl-PL/modelProvider.json
index 75f611b..c4512be 100644
--- a/DigitalHumanWeb/locales/pl-PL/modelProvider.json
+++ b/DigitalHumanWeb/locales/pl-PL/modelProvider.json
@@ -19,6 +19,24 @@
"title": "Klucz API"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Wersja API Azure, w formacie YYYY-MM-DD, sprawdź [najnowszą wersję](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Pobierz listę",
+ "title": "Wersja API Azure"
+ },
+ "endpoint": {
+ "desc": "Znajdź punkt końcowy wnioskowania modelu Azure AI w przeglądzie projektu Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Punkt końcowy Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Znajdź klucz API w przeglądzie projektu Azure AI",
+ "placeholder": "Klucz Azure",
+ "title": "Klucz"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Wprowadź AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "Użyj niestandardowych informacji uwierzytelniających Bedrock"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Wprowadź klucz Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Wprowadź ID konta Cloudflare lub adres API niestandardowy",
+ "placeholder": "ID konta Cloudflare / adres API niestandardowy",
+ "title": "ID konta Cloudflare / adres API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Proszę wpisać swój klucz API",
+ "title": "Klucz API"
+ },
+ "basicTitle": "Podstawowe informacje",
+ "configTitle": "Informacje konfiguracyjne",
+ "confirm": "Utwórz",
+ "createSuccess": "Utworzenie zakończone sukcesem",
+ "description": {
+ "placeholder": "Opis dostawcy usług (opcjonalnie)",
+ "title": "Opis dostawcy usług"
+ },
+ "id": {
+ "desc": "Unikalny identyfikator dostawcy usług, po utworzeniu nie można go zmienić",
+ "format": "Może zawierać tylko cyfry, małe litery, myślniki (-) i podkreślenia (_) ",
+ "placeholder": "Zaleca się użycie małych liter, np. openai, po utworzeniu nie można edytować",
+ "required": "Proszę wpisać identyfikator dostawcy",
+ "title": "Identyfikator dostawcy"
+ },
+ "logo": {
+ "required": "Proszę przesłać poprawne logo dostawcy",
+ "title": "Logo dostawcy"
+ },
+ "name": {
+ "placeholder": "Proszę wpisać nazwę wyświetlaną dostawcy",
+ "required": "Proszę wpisać nazwę dostawcy",
+ "title": "Nazwa dostawcy"
+ },
+ "proxyUrl": {
+ "required": "Proszę wpisać adres proxy",
+ "title": "Adres proxy"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Proszę wybrać typ SDK",
+ "title": "Format żądania"
+ },
+ "title": "Utwórz niestandardowego dostawcę AI"
+ },
"github": {
"personalAccessToken": {
"desc": "Wprowadź swój osobisty token dostępu GitHub (PAT), kliknij [tutaj](https://github.com/settings/tokens), aby go utworzyć",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Wprowadź swój token HuggingFace, kliknij [tutaj](https://huggingface.co/settings/tokens), aby go utworzyć",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "Token HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Usługa nieaktywna",
+ "enabled": "Usługa aktywna"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Dodaj niestandardowego dostawcę",
+ "all": "Wszystko",
+ "list": {
+ "disabled": "Nieaktywny",
+ "enabled": "Aktywny"
+ },
+ "notFound": "Nie znaleziono wyników wyszukiwania",
+ "searchProviders": "Szukaj dostawców...",
+ "sort": "Niestandardowe sortowanie"
+ },
"ollama": {
"checker": {
"desc": "Test czy adres proxy jest poprawnie wypełniony",
@@ -69,47 +163,173 @@
"title": "Nazwa własnego modelu"
},
"download": {
- "desc": "Ollama is currently downloading the model. Please try not to close this page. The download will resume from where it left off if interrupted.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama pobiera ten model, proszę nie zamykać tej strony. Wznowienie pobierania nastąpi od miejsca przerwania",
+ "remainingTime": "Pozostały czas",
+ "speed": "Prędkość pobierania",
+ "title": "Pobieranie modelu {{model}}"
},
"endpoint": {
- "desc": "Wprowadź adres rest API Ollama, jeśli lokalnie nie określono, pozostaw puste",
+ "desc": "Musi zawierać http(s)://, lokalnie, jeśli nie określono inaczej, można pozostawić puste",
"title": "Adres proxy API"
},
- "setup": {
- "cors": {
- "description": "Due to browser security restrictions, you need to configure cross-origin settings for Ollama to function properly.",
- "linux": {
- "env": "Add `Environment` under [Service] section, and set the OLLAMA_ORIGINS environment variable:",
- "reboot": "Reload systemd and restart Ollama.",
- "systemd": "Invoke systemd to edit the ollama service:"
- },
- "macos": "Open the Terminal application, paste the following command, and press Enter to run it.",
- "reboot": "Restart the Ollama service after the execution is complete.",
- "title": "Configure Ollama for Cross-Origin Access",
- "windows": "On Windows, go to 'Control Panel' and edit system environment variables. Create a new environment variable named 'OLLAMA_ORIGINS' for your user account, set the value to '*', and click 'OK/Apply' to save."
- },
- "install": {
- "description": "Upewnij się, że masz zainstalowanego Ollamę. Jeśli nie, pobierz ją ze strony internetowej <1> tutaj1>",
- "docker": "If you prefer using Docker, Ollama also provides an official Docker image. You can pull it using the following command:",
- "linux": {
- "command": "Install using the following command:",
- "manual": "Alternatively, you can refer to the <1>Linux Manual Installation Guide1> for manual installation."
- },
- "title": "Install and Start Ollama Locally",
- "windowsTab": "Windows (Preview)"
- }
- },
"title": "Ollama",
"unlock": {
- "cancel": "Cancel Download",
- "confirm": "Download",
- "description": "Enter your Ollama model tag to continue the session",
+ "cancel": "Anuluj pobieranie",
+ "confirm": "Pobierz",
+ "description": "Wprowadź etykietę swojego modelu Ollama, aby zakończyć i kontynuować rozmowę",
"downloaded": "{{completed}} / {{total}}",
- "starting": "Starting download...",
- "title": "Download specified Ollama model"
+ "starting": "Rozpoczynam pobieranie...",
+ "title": "Pobierz określony model Ollama"
+ }
+ },
+ "providerModels": {
+ "config": {
+ "aesGcm": "Twój klucz oraz adres proxy będą szyfrowane za pomocą <1>AES-GCM1>",
+ "apiKey": {
+ "desc": "Proszę wpisać swój {{name}} klucz API",
+ "placeholder": "{{name}} klucz API",
+ "title": "Klucz API"
+ },
+ "baseURL": {
+ "desc": "Musi zawierać http(s)://",
+ "invalid": "Proszę wprowadzić prawidłowy URL",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "Adres proxy API"
+ },
+ "checker": {
+ "button": "Sprawdź",
+ "desc": "Testuj, czy klucz API i adres proxy są poprawnie wpisane",
+ "pass": "Sprawdzenie zakończone sukcesem",
+ "title": "Sprawdzenie łączności"
+ },
+ "fetchOnClient": {
+ "desc": "Tryb żądania klienta rozpocznie sesję bezpośrednio z przeglądarki, co może przyspieszyć czas odpowiedzi",
+ "title": "Użyj trybu żądania klienta"
+ },
+ "helpDoc": "Dokumentacja konfiguracyjna",
+ "waitingForMore": "Więcej modeli jest w <1>planach integracji1>, proszę czekać"
+ },
+ "createNew": {
+ "title": "Utwórz niestandardowy model AI"
+ },
+ "item": {
+ "config": "Konfiguracja modelu",
+ "customModelCards": {
+ "addNew": "Utwórz i dodaj model {{id}}",
+ "confirmDelete": "Zaraz usuniesz ten niestandardowy model, po usunięciu nie będzie można go przywrócić, proszę działać ostrożnie."
+ },
+ "delete": {
+ "confirm": "Czy na pewno chcesz usunąć model {{displayName}}?",
+ "success": "Usunięcie zakończone sukcesem",
+ "title": "Usuń model"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Pole, które jest rzeczywiście używane w Azure OpenAI",
+ "placeholder": "Proszę wpisać nazwę wdrożenia modelu w Azure",
+ "title": "Nazwa wdrożenia modelu"
+ },
+ "deployName": {
+ "extra": "To pole będzie używane jako identyfikator modelu podczas wysyłania żądania",
+ "placeholder": "Wprowadź rzeczywistą nazwę lub identyfikator wdrożenia modelu",
+ "title": "Nazwa wdrożenia modelu"
+ },
+ "displayName": {
+ "placeholder": "Proszę wpisać nazwę wyświetlaną modelu, np. ChatGPT, GPT-4 itp.",
+ "title": "Nazwa wyświetlana modelu"
+ },
+ "files": {
+ "extra": "Obecna implementacja przesyłania plików jest jedynie rozwiązaniem hackowym, przeznaczonym do samodzielnego testowania. Pełna funkcjonalność przesyłania plików będzie dostępna w przyszłości.",
+ "title": "Wsparcie dla przesyłania plików"
+ },
+ "functionCall": {
+ "extra": "Ta konfiguracja włączy jedynie możliwość korzystania z narzędzi przez model, co pozwoli na dodanie wtyczek narzędziowych. Jednakże, czy model rzeczywiście obsługuje korzystanie z narzędzi, zależy całkowicie od samego modelu, proszę samodzielnie przetestować jego użyteczność",
+ "title": "Wsparcie dla korzystania z narzędzi"
+ },
+ "id": {
+ "extra": "Nie można zmieniać po utworzeniu, będzie używane jako identyfikator modelu podczas wywoływania AI",
+ "placeholder": "Wprowadź identyfikator modelu, na przykład gpt-4o lub claude-3.5-sonnet",
+ "title": "ID modelu"
+ },
+ "modalTitle": "Konfiguracja niestandardowego modelu",
+ "reasoning": {
+ "extra": "Ta konfiguracja włączy jedynie zdolność modelu do głębokiego myślenia, a konkretne efekty w pełni zależą od samego modelu. Proszę samodzielnie przetestować, czy model ma zdolność do głębokiego myślenia.",
+ "title": "Wsparcie dla głębokiego myślenia"
+ },
+ "tokens": {
+ "extra": "Ustaw maksymalną liczbę tokenów wspieranych przez model",
+ "title": "Maksymalne okno kontekstu",
+ "unlimited": "Bez ograniczeń"
+ },
+ "vision": {
+ "extra": "Ta konfiguracja włączy tylko możliwość przesyłania obrazów w aplikacji, czy model obsługuje rozpoznawanie zależy od samego modelu, proszę samodzielnie przetestować dostępność rozpoznawania wizualnego tego modelu.",
+ "title": "Wsparcie dla rozpoznawania wizualnego"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/obraz",
+ "inputCharts": "${{amount}}/M znaków",
+ "inputMinutes": "${{amount}}/minut",
+ "inputTokens": "Wprowadzenie ${{amount}}/M",
+ "outputTokens": "Wyjście ${{amount}}/M"
+ },
+ "releasedAt": "Wydano {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Dodaj model",
+ "disabled": "Nieaktywne",
+ "disabledActions": {
+ "showMore": "Pokaż więcej"
+ },
+ "empty": {
+ "desc": "Proszę utworzyć model niestandardowy lub pobrać model, aby rozpocząć korzystanie.",
+ "title": "Brak dostępnych modeli"
+ },
+ "enabled": "Aktywne",
+ "enabledActions": {
+ "disableAll": "Dezaktywuj wszystkie",
+ "enableAll": "Aktywuj wszystkie",
+ "sort": "Sortowanie modeli niestandardowych"
+ },
+ "enabledEmpty": "Brak aktywnych modeli, aktywuj ulubione modele z poniższej listy~",
+ "fetcher": {
+ "clear": "Wyczyść pobrane modele",
+ "fetch": "Pobierz listę modeli",
+ "fetching": "Pobieranie listy modeli...",
+ "latestTime": "Ostatnia aktualizacja: {{time}}",
+ "noLatestTime": "Lista nie została jeszcze pobrana"
+ },
+ "resetAll": {
+ "conform": "Czy na pewno chcesz zresetować wszystkie zmiany w bieżącym modelu? Po zresetowaniu lista modeli wróci do stanu domyślnego",
+ "success": "Resetowanie zakończone sukcesem",
+ "title": "Zresetuj wszystkie zmiany"
+ },
+ "search": "Szukaj modeli...",
+ "searchResult": "Znaleziono {{count}} modeli",
+ "title": "Lista modeli",
+ "total": "Łącznie dostępnych modeli: {{count}}"
+ },
+ "searchNotFound": "Nie znaleziono wyników wyszukiwania"
+ },
+ "sortModal": {
+ "success": "Aktualizacja sortowania zakończona sukcesem",
+ "title": "Niestandardowe sortowanie",
+ "update": "Aktualizuj"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Zaraz usuniesz tego dostawcę AI, po usunięciu nie będzie można go przywrócić, czy na pewno chcesz usunąć?",
+ "deleteSuccess": "Usunięcie zakończone sukcesem",
+ "tooltip": "Aktualizuj podstawowe ustawienia dostawcy",
+ "updateSuccess": "Aktualizacja zakończona sukcesem"
+ },
+ "updateCustomAiProvider": {
+ "title": "Aktualizuj konfigurację dostawcy AI"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Wprowadź swoje klucze Vertex AI",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Klucze Vertex AI"
}
},
"zeroone": {
diff --git a/DigitalHumanWeb/locales/pl-PL/models.json b/DigitalHumanWeb/locales/pl-PL/models.json
index e0b3870..038f3bf 100644
--- a/DigitalHumanWeb/locales/pl-PL/models.json
+++ b/DigitalHumanWeb/locales/pl-PL/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, dzięki bogatym próbom treningowym, oferuje doskonałe wyniki w zastosowaniach branżowych."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat to wariant serii Yi-1.5, należący do otwartych modeli czatu. Yi-1.5 to ulepszona wersja Yi, która była nieprzerwanie trenowana na 500B wysokiej jakości korpusie i dostosowywana na 3M zróżnicowanych próbkach. W porównaniu do Yi, Yi-1.5 wykazuje lepsze zdolności w zakresie kodowania, matematyki, wnioskowania i przestrzegania instrukcji, jednocześnie zachowując doskonałe umiejętności rozumienia języka, wnioskowania ogólnego i rozumienia tekstu. Model ten oferuje wersje o długości kontekstu 4K, 16K i 32K, a całkowita liczba tokenów w pretreningu wynosi 3.6T."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B obsługuje 16K tokenów, oferując wydajne i płynne zdolności generowania języka."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One, najnowszy model open source z dostrojeniem, zawierający 34 miliardy parametrów, dostosowany do różnych scenariuszy dialogowych, z wysokiej jakości danymi treningowymi, dostosowany do preferencji ludzkich."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One, najnowszy model open source z dostrojeniem, zawierający 9 miliardów parametrów, dostosowany do różnych scenariuszy dialogowych, z wysokiej jakości danymi treningowymi, dostosowany do preferencji ludzkich."
+ },
"360gpt-pro": {
"description": "360GPT Pro, jako ważny członek serii modeli AI 360, zaspokaja różnorodne potrzeby aplikacji przetwarzania języka naturalnego dzięki wydajnym zdolnościom przetwarzania tekstu, obsługując zrozumienie długich tekstów i wielokrotne dialogi."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K kładzie nacisk na bezpieczeństwo semantyczne i odpowiedzialność, zaprojektowany specjalnie dla aplikacji o wysokich wymaganiach dotyczących bezpieczeństwa treści, zapewniając dokładność i stabilność doświadczeń użytkowników."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 wykorzystuje wyszukiwanie drzew do budowy łańcucha myślenia i wprowadza mechanizm refleksji, wykorzystując uczenie przez wzmocnienie, model posiada zdolność do samorefleksji i korekty błędów."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro to zaawansowany model przetwarzania języka naturalnego wydany przez firmę 360, charakteryzujący się doskonałymi zdolnościami generowania i rozumienia tekstu, szczególnie w obszarze generowania i tworzenia treści, zdolny do obsługi skomplikowanych zadań związanych z konwersją językową i odgrywaniem ról."
},
+ "360zhinao2-o1": {
+ "description": "Model 360zhinao2-o1 wykorzystuje wyszukiwanie drzewne do budowy łańcucha myślowego i wprowadza mechanizm refleksji, wykorzystując uczenie przez wzmocnienie do treningu, co pozwala modelowi na samorefleksję i korekcję błędów."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra to najsilniejsza wersja w serii modeli Spark, która, oprócz ulepszonego łącza wyszukiwania w sieci, zwiększa zdolność rozumienia i podsumowywania treści tekstowych. Jest to kompleksowe rozwiązanie mające na celu zwiększenie wydajności biurowej i dokładne odpowiadanie na potrzeby, stanowiące inteligentny produkt wiodący w branży."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Model o najwyższej wydajności w kraju, przewyższający zagraniczne modele w zadaniach związanych z encyklopedią, długimi tekstami i generowaniem treści w języku chińskim. Posiada również wiodące w branży zdolności multimodalne, osiągając doskonałe wyniki w wielu autorytatywnych testach."
},
+ "Baichuan4-Air": {
+ "description": "Model o najlepszych możliwościach w kraju, przewyższający zagraniczne modele w zadaniach związanych z wiedzą encyklopedyczną, długimi tekstami i twórczością w języku chińskim. Posiada również wiodące w branży możliwości multimodalne, osiągając doskonałe wyniki w wielu autorytatywnych testach."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Model o najlepszych możliwościach w kraju, przewyższający zagraniczne modele w zadaniach związanych z wiedzą encyklopedyczną, długimi tekstami i twórczością w języku chińskim. Posiada również wiodące w branży możliwości multimodalne, osiągając doskonałe wyniki w wielu autorytatywnych testach."
+ },
+ "DeepSeek-R1": {
+ "description": "Najnowocześniejszy, wydajny LLM, specjalizujący się w wnioskowaniu, matematyce i programowaniu."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 — większy i inteligentniejszy model w zestawie DeepSeek — został skondensowany do architektury Llama 70B. Na podstawie testów porównawczych i ocen ludzkich, model ten jest bardziej inteligentny niż oryginalny Llama 70B, zwłaszcza w zadaniach wymagających precyzji matematycznej i faktograficznej."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Model destylacyjny DeepSeek-R1 oparty na Qwen2.5-Math-1.5B, optymalizujący wydajność wnioskowania dzięki uczeniu przez wzmocnienie i danym z zimnego startu, otwarty model ustanawiający nowe standardy w wielu zadaniach."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Model destylacyjny DeepSeek-R1 oparty na Qwen2.5-14B, optymalizujący wydajność wnioskowania dzięki uczeniu przez wzmocnienie i danym z zimnego startu, otwarty model ustanawiający nowe standardy w wielu zadaniach."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "Seria DeepSeek-R1 optymalizuje wydajność wnioskowania dzięki uczeniu przez wzmocnienie i danym z zimnego startu, otwarty model ustanawiający nowe standardy w wielu zadaniach, przewyższający poziom OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Model destylacyjny DeepSeek-R1 oparty na Qwen2.5-Math-7B, optymalizujący wydajność wnioskowania dzięki uczeniu przez wzmocnienie i danym z zimnego startu, otwarty model ustanawiający nowe standardy w wielu zadaniach."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro to nowa wersja ulepszonego modelu multimodalnego, który obsługuje rozpoznawanie obrazów o dowolnej rozdzielczości i ekstremalnych proporcjach, wzmacniając zdolności wnioskowania wizualnego, rozpoznawania dokumentów, rozumienia szczegółowych informacji oraz przestrzegania instrukcji."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite cechuje się ekstremalną szybkością reakcji i lepszym stosunkiem jakości do ceny, oferując klientom elastyczność w różnych scenariuszach. Obsługuje wnioskowanie i dostosowywanie z kontekstem 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite cechuje się ekstremalną szybkością reakcji i lepszym stosunkiem jakości do ceny, oferując klientom elastyczność w różnych scenariuszach. Obsługuje wnioskowanie i dostosowywanie z kontekstem 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite cechuje się ekstremalną szybkością reakcji i lepszym stosunkiem jakości do ceny, oferując klientom elastyczność w różnych scenariuszach. Obsługuje wnioskowanie i dostosowywanie z kontekstem 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "Model o najlepszych wynikach, odpowiedni do złożonych zadań, z doskonałymi wynikami w scenariuszach takich jak odpowiedzi referencyjne, podsumowania, twórczość, klasyfikacja tekstu i odgrywanie ról. Obsługuje wnioskowanie i dostosowywanie z kontekstem 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "Najlepszy model główny, odpowiedni do obsługi złożonych zadań, osiągający dobre wyniki w scenariuszach takich jak pytania i odpowiedzi, podsumowania, twórczość, klasyfikacja tekstu, odgrywanie ról itp. Obsługuje wnioskowanie i dostrajanie w kontekście 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "Model o najlepszych wynikach, odpowiedni do złożonych zadań, z doskonałymi wynikami w scenariuszach takich jak odpowiedzi referencyjne, podsumowania, twórczość, klasyfikacja tekstu i odgrywanie ról. Obsługuje wnioskowanie i dostosowywanie z kontekstem 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "Model o najlepszych wynikach, odpowiedni do złożonych zadań, z doskonałymi wynikami w scenariuszach takich jak odpowiedzi referencyjne, podsumowania, twórczość, klasyfikacja tekstu i odgrywanie ról. Obsługuje wnioskowanie i dostosowywanie z kontekstem 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Model Doubao-vision to multimodalny model stworzony przez Doubao, który dysponuje potężnymi zdolnościami rozumienia i wnioskowania obrazów oraz precyzyjnym rozumieniem instrukcji. Model wykazuje silną wydajność w zakresie ekstrakcji informacji tekstowych z obrazów oraz zadań wnioskowania opartych na obrazach, co pozwala na zastosowanie w bardziej złożonych i szerszych zadaniach wizualnych."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Model Doubao-vision to multimodalny model stworzony przez Doubao, który dysponuje potężnymi zdolnościami rozumienia i wnioskowania obrazów oraz precyzyjnym rozumieniem instrukcji. Model wykazuje silną wydajność w zakresie ekstrakcji informacji tekstowych z obrazów oraz zadań wnioskowania opartych na obrazach, co pozwala na zastosowanie w bardziej złożonych i szerszych zadaniach wizualnych."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Flagowy model dużego języka opracowany przez Baidu, obejmujący ogromne zbiory danych w języku chińskim i angielskim, charakteryzujący się silnymi zdolnościami ogólnymi, zdolny do spełnienia wymagań w większości scenariuszy związanych z pytaniami i odpowiedziami, generowaniem treści oraz aplikacjami wtyczek; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji w odpowiedziach."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Flagowy model dużego języka opracowany przez Baidu, obejmujący ogromne zbiory danych w języku chińskim i angielskim, charakteryzujący się silnymi zdolnościami ogólnymi, zdolny do spełnienia wymagań w większości scenariuszy związanych z pytaniami i odpowiedziami, generowaniem treści oraz aplikacjami wtyczek; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji w odpowiedziach."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Flagowy model dużego języka opracowany przez Baidu, obejmujący ogromne zbiory danych w języku chińskim i angielskim, charakteryzujący się silnymi zdolnościami ogólnymi, zdolny do spełnienia wymagań w większości scenariuszy związanych z pytaniami i odpowiedziami, generowaniem treści oraz aplikacjami wtyczek; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji w odpowiedziach."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Flagowy model ultra dużego języka opracowany przez Baidu, w porównaniu do ERNIE 3.5, oferujący kompleksową aktualizację możliwości modelu, szeroko stosowany w złożonych scenariuszach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Flagowy model ultra dużego języka opracowany przez Baidu, w porównaniu do ERNIE 3.5, oferujący kompleksową aktualizację możliwości modelu, szeroko stosowany w złożonych scenariuszach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Opracowany przez Baidu flagowy, ultra-duży model językowy, który wykazuje doskonałe ogólne rezultaty i jest szeroko stosowany w złożonych zadaniach w różnych dziedzinach; obsługuje automatyczne łączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji odpowiadających na pytania. W porównaniu do ERNIE 4.0 wykazuje lepszą wydajność."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Flagowy model ultra dużego języka opracowany przez Baidu, charakteryzujący się doskonałymi wynikami ogólnymi, szeroko stosowany w złożonych scenariuszach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji. W porównaniu do ERNIE 4.0, oferuje lepsze wyniki wydajności."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Model dużego języka opracowany przez Baidu, skoncentrowany na specyficznych scenariuszach, odpowiedni do zastosowań takich jak NPC w grach, rozmowy z obsługą klienta, odgrywanie ról w dialogach, charakteryzujący się wyraźnym i spójnym stylem postaci, silniejszą zdolnością do przestrzegania poleceń oraz lepszą wydajnością wnioskowania."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Lekki model dużego języka opracowany przez Baidu, łączący doskonałe wyniki modelu z wydajnością wnioskowania, oferujący lepsze wyniki niż ERNIE Lite, odpowiedni do użycia w niskomocowych kartach przyspieszających AI."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Najnowocześniejszy model dużego języka opracowany przez Baidu w 2024 roku, charakteryzujący się doskonałymi zdolnościami ogólnymi, odpowiedni jako model bazowy do dalszego dostosowywania, lepiej radzący sobie z problemami w specyficznych scenariuszach, a także zapewniający doskonałą wydajność wnioskowania."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Najnowocześniejszy model dużego języka opracowany przez Baidu w 2024 roku, charakteryzujący się doskonałymi zdolnościami ogólnymi, oferujący lepsze wyniki niż ERNIE Speed, odpowiedni jako model bazowy do dalszego dostosowywania, lepiej radzący sobie z problemami w specyficznych scenariuszach, a także zapewniający doskonałą wydajność wnioskowania."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) to innowacyjny model, idealny do zastosowań w wielu dziedzinach i złożonych zadań."
},
- "Max-32k": {
- "description": "Spark Max 32K ma dużą zdolność przetwarzania kontekstu, lepsze zrozumienie kontekstu i zdolności logicznego rozumowania, obsługując teksty o długości 32K tokenów, odpowiednie do czytania długich dokumentów, prywatnych pytań o wiedzę i innych scenariuszy."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B to potężny model językowy wizualny, wspierający przetwarzanie multimodalne obrazów i tekstu, zdolny do precyzyjnego rozpoznawania treści obrazów i generowania odpowiednich opisów lub odpowiedzi."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B to potężny model językowy wizualny, wspierający przetwarzanie multimodalne obrazów i tekstu, zdolny do precyzyjnego rozpoznawania treści obrazów i generowania odpowiednich opisów lub odpowiedzi."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Wyróżniające się zdolnościami wnioskowania obrazów na wysokiej rozdzielczości, odpowiednie do zastosowań w rozumieniu wizualnym."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Zaawansowane zdolności wnioskowania obrazów, odpowiednie do zastosowań w agentach rozumienia wizualnego."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct to jeden z najnowszych modeli dużych języków wydanych przez Alibaba Cloud. Model 72B ma znacząco poprawione zdolności w zakresie kodowania i matematyki. Oferuje również wsparcie dla wielu języków, obejmując ponad 29 języków, w tym chiński i angielski. Model ten wykazuje znaczną poprawę w zakresie przestrzegania instrukcji, rozumienia danych strukturalnych oraz generowania strukturalnych wyników (szczególnie JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct to jeden z najnowszych modeli dużych języków wydanych przez Alibaba Cloud. Model 7B ma znacząco poprawione zdolności w zakresie kodowania i matematyki. Oferuje również wsparcie dla wielu języków, obejmując ponad 29 języków, w tym chiński i angielski. Model ten wykazuje znaczną poprawę w zakresie przestrzegania instrukcji, rozumienia danych strukturalnych oraz generowania strukturalnych wyników (szczególnie JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Model tekstowy Llama 3.1 dostosowany do instrukcji, zoptymalizowany do wielojęzycznych przypadków użycia dialogów, osiągający doskonałe wyniki w wielu dostępnych modelach czatu, zarówno otwartych, jak i zamkniętych, w powszechnych benchmarkach branżowych."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO to wysoce elastyczna fuzja wielu modeli, mająca na celu zapewnienie doskonałego doświadczenia twórczego."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Model tekstowy Llama 3.1 dostosowany do instrukcji, zoptymalizowany do wielojęzycznych przypadków użycia dialogów, osiągający doskonałe wyniki w wielu dostępnych modelach czatu, zarówno otwartych, jak i zamkniętych, w powszechnych benchmarkach branżowych."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Model tekstowy Llama 3.1 dostosowany do instrukcji, zoptymalizowany do wielojęzycznych przypadków użycia dialogów, osiągający doskonałe wyniki w wielu dostępnych modelach czatu, zarówno otwartych, jak i zamkniętych, w powszechnych benchmarkach branżowych."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Zaawansowany, nowoczesny mały model językowy, posiadający zdolności rozumienia języka, doskonałe umiejętności wnioskowania oraz generowania tekstu."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Zaawansowany, nowoczesny mały model językowy, posiadający zdolności rozumienia języka, doskonałe umiejętności wnioskowania oraz generowania tekstu."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 to najnowocześniejszy wielojęzyczny otwarty model językowy z serii Llama, oferujący wydajność porównywalną z modelem 405B przy bardzo niskich kosztach. Oparty na strukturze Transformer, poprawiony dzięki nadzorowanemu dostrajaniu (SFT) oraz uczeniu ze wzmocnieniem opartym na ludzkiej opinii (RLHF), co zwiększa jego użyteczność i bezpieczeństwo. Jego wersja dostosowana do instrukcji została zoptymalizowana do wielojęzycznych dialogów, osiągając lepsze wyniki niż wiele dostępnych modeli czatu, zarówno otwartych, jak i zamkniętych, w wielu branżowych benchmarkach. Data graniczna wiedzy to grudzień 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "W serii modeli MiniMax-01 wprowadziliśmy odważne innowacje: po raz pierwszy na dużą skalę zrealizowano mechanizm liniowej uwagi, tradycyjna architektura Transformera nie jest już jedynym wyborem. Liczba parametrów tego modelu wynosi aż 456 miliardów, z aktywacją wynoszącą 45,9 miliarda. Ogólna wydajność modelu dorównuje najlepszym modelom zagranicznym, jednocześnie efektywnie przetwarzając kontekst o długości do 4 milionów tokenów, co stanowi 32 razy więcej niż GPT-4o i 20 razy więcej niż Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) to model poleceń o wysokiej precyzji, idealny do złożonych obliczeń."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) oferuje zoptymalizowane wyjście językowe i różnorodne możliwości zastosowania."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Odświeżona wersja modelu Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 pokazuje wyjątkowe wyniki w różnych zadaniach językowych i wizualnych, w tym zrozumieniu dokumentów i wykresów, zrozumieniu tekstu w scenach, OCR, rozwiązywaniu problemów naukowych i matematycznych."
},
"Phi-3-medium-128k-instruct": {
"description": "Ten sam model Phi-3-medium, ale z większym rozmiarem kontekstu do RAG lub kilku strzałowego wywoływania."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Model z 7 miliardami parametrów, oferujący lepszą jakość niż Phi-3-mini, z naciskiem na dane o wysokiej jakości i gęstości rozumowania."
},
- "Pro-128k": {
- "description": "Spark Pro-128K ma wyjątkową zdolność przetwarzania kontekstu, mogąc obsługiwać do 128K informacji kontekstowych, szczególnie odpowiedni do analizy całościowej i długoterminowego przetwarzania logicznego w długich tekstach, zapewniając płynne i spójne logicznie komunikowanie się oraz różnorodne wsparcie cytatów."
+ "Phi-3.5-mini-instruct": {
+ "description": "Zaktualizowana wersja modelu Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Zaktualizowana wersja modelu Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 pokazuje wyjątkowe wyniki w różnych zadaniach językowych i wizualnych, w tym zrozumieniu dokumentów i wykresów, zrozumieniu tekstu w scenach, OCR, rozwiązywaniu problemów naukowych i matematycznych."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct to model dużego języka z serii Qwen2, dostosowany do instrukcji, o rozmiarze parametrów wynoszącym 1.5B. Model ten oparty jest na architekturze Transformer, wykorzystując funkcję aktywacji SwiGLU, przesunięcia QKV w uwadze oraz grupowe zapytania uwagi. Wykazuje doskonałe wyniki w wielu testach benchmarkowych dotyczących rozumienia języka, generowania, zdolności wielojęzycznych, kodowania, matematyki i wnioskowania, przewyższając większość modeli open-source. W porównaniu do Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct wykazuje znaczną poprawę wydajności w testach MMLU, HumanEval, GSM8K, C-Eval i IFEval, mimo że ma nieco mniejszą liczbę parametrów."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct to model dużego języka z serii Qwen2, dostosowany do instrukcji, o rozmiarze parametrów wynoszącym 7B. Model ten oparty jest na architekturze Transformer, wykorzystując funkcję aktywacji SwiGLU, przesunięcia QKV w uwadze oraz grupowe zapytania uwagi. Może obsługiwać duże wejścia. Model ten wykazuje doskonałe wyniki w wielu testach benchmarkowych dotyczących rozumienia języka, generowania, zdolności wielojęzycznych, kodowania, matematyki i wnioskowania, przewyższając większość modeli open-source i wykazując konkurencyjność z modelami własnościowymi w niektórych zadaniach. Qwen2-7B-Instruct wykazuje znaczną poprawę wydajności w wielu ocenach w porównaniu do Qwen1.5-7B-Chat."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL to najnowsza iteracja modelu Qwen-VL, osiągająca najnowocześniejsze wyniki w benchmarkach zrozumienia wizualnego."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct to jeden z najnowszych modeli dużych języków wydanych przez Alibaba Cloud. Model 7B ma znacząco poprawione zdolności w zakresie kodowania i matematyki. Oferuje również wsparcie dla wielu języków, obejmując ponad 29 języków, w tym chiński i angielski. Model ten wykazuje znaczną poprawę w zakresie przestrzegania instrukcji, rozumienia danych strukturalnych oraz generowania strukturalnych wyników (szczególnie JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct to najnowsza wersja serii dużych modeli językowych specyficznych dla kodu wydana przez Alibaba Cloud. Model ten, oparty na Qwen2.5, został przeszkolony na 55 bilionach tokenów, znacznie poprawiając zdolności generowania kodu, wnioskowania i naprawy. Wzmacnia on nie tylko zdolności kodowania, ale także utrzymuje przewagę w zakresie matematyki i ogólnych umiejętności. Model ten stanowi bardziej kompleksową podstawę dla rzeczywistych zastosowań, takich jak inteligentne agenty kodowe."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat to otwarta wersja modelu pretrenowanego z serii GLM-4, wydana przez Zhipu AI. Model ten wykazuje doskonałe wyniki w zakresie semantyki, matematyki, wnioskowania, kodu i wiedzy. Oprócz wsparcia dla wieloetapowych rozmów, GLM-4-9B-Chat oferuje również zaawansowane funkcje, takie jak przeglądanie stron internetowych, wykonywanie kodu, wywoływanie niestandardowych narzędzi (Function Call) oraz wnioskowanie z długich tekstów. Model obsługuje 26 języków, w tym chiński, angielski, japoński, koreański i niemiecki. W wielu testach benchmarkowych, takich jak AlignBench-v2, MT-Bench, MMLU i C-Eval, GLM-4-9B-Chat wykazuje doskonałą wydajność. Model obsługuje maksymalną długość kontekstu 128K, co czyni go odpowiednim do badań akademickich i zastosowań komercyjnych."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 to model wnioskowania napędzany uczeniem ze wzmocnieniem (RL), który rozwiązuje problemy z powtarzalnością i czytelnością modeli. Przed RL, DeepSeek-R1 wprowadził dane do zimnego startu, co dodatkowo zoptymalizowało wydajność wnioskowania. W zadaniach matematycznych, kodowych i wnioskowania, osiąga wyniki porównywalne z OpenAI-o1, a dzięki starannie zaprojektowanym metodom treningowym poprawia ogólne wyniki."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 to model językowy z 6710 miliardami parametrów, oparty na architekturze mieszanych ekspertów (MoE), wykorzystujący wielogłowicową potencjalną uwagę (MLA) oraz strategię równoważenia obciążenia bez dodatkowych strat, co optymalizuje wydajność wnioskowania i treningu. Dzięki wstępnemu treningowi na 14,8 bilionach wysokiej jakości tokenów oraz nadzorowanemu dostrajaniu i uczeniu ze wzmocnieniem, DeepSeek-V3 przewyższa inne modele open source, zbliżając się do wiodących modeli zamkniętych."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma to jedna z lekkich, nowoczesnych otwartych serii modeli opracowanych przez Google. Jest to duży model językowy z jedynie dekoderem, wspierający język angielski, oferujący otwarte wagi, pretrenowane warianty oraz warianty dostosowane do instrukcji. Model Gemma nadaje się do różnych zadań generowania tekstu, w tym pytania-odpowiedzi, streszczenia i wnioskowania. Model 9B został przeszkolony na 8 bilionach tokenów. Jego stosunkowo mała skala umożliwia wdrożenie w środowiskach o ograniczonych zasobach, takich jak laptopy, komputery stacjonarne lub własna infrastruktura chmurowa, co umożliwia większej liczbie osób dostęp do nowoczesnych modeli AI i wspiera innowacje."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 to rodzina dużych modeli językowych opracowanych przez Meta, obejmująca pretrenowane i dostosowane do instrukcji warianty o rozmiarach parametrów 8B, 70B i 405B. Model 8B dostosowany do instrukcji został zoptymalizowany do scenariuszy rozmów wielojęzycznych, osiągając doskonałe wyniki w wielu branżowych testach benchmarkowych. Trening modelu wykorzystał ponad 150 bilionów tokenów danych publicznych oraz zastosował techniki takie jak nadzorowane dostrajanie i uczenie przez wzmacnianie z ludzkim feedbackiem, aby zwiększyć użyteczność i bezpieczeństwo modelu. Llama 3.1 wspiera generowanie tekstu i kodu, a data graniczna wiedzy to grudzień 2023 roku."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview to innowacyjny model przetwarzania języka naturalnego, który efektywnie radzi sobie z złożonymi zadaniami generowania dialogów i rozumienia kontekstu."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview to model badawczy opracowany przez zespół Qwen, skoncentrowany na zdolnościach wnioskowania wizualnego, który ma unikalne zalety w zrozumieniu złożonych scenariuszy i rozwiązywaniu wizualnie związanych problemów matematycznych."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Jako wersja testowa Qwen2, Qwen1.5 wykorzystuje dużą ilość danych do osiągnięcia bardziej precyzyjnych funkcji dialogowych."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ jest modelem inferencyjnym z serii Qwen. W porównaniu do tradycyjnych modeli dostosowanych do instrukcji, QwQ posiada zdolności myślenia i wnioskowania, co pozwala na znaczące zwiększenie wydajności w zadaniach końcowych, szczególnie w rozwiązywaniu trudnych problemów. QwQ-32B to średniej wielkości model inferencyjny, który osiąga konkurencyjną wydajność w porównaniu z najnowocześniejszymi modelami inferencyjnymi, takimi jak DeepSeek-R1 i o1-mini. Model ten wykorzystuje technologie takie jak RoPE, SwiGLU, RMSNorm oraz Attention QKV bias, posiada 64-warstwową strukturę sieci i 40 głowic uwagi Q (w architekturze GQA KV wynosi 8)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) oferuje szybkie odpowiedzi i naturalne umiejętności dialogowe, idealne do środowisk wielojęzycznych."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview to najnowszy eksperymentalny model badawczy Qwen, skoncentrowany na zwiększeniu zdolności wnioskowania AI. Poprzez eksplorację złożonych mechanizmów, takich jak mieszanie języków i wnioskowanie rekurencyjne, główne zalety obejmują silne zdolności analizy wnioskowania, matematyki i programowania. Jednocześnie występują problemy z przełączaniem języków, cyklami wnioskowania, kwestiami bezpieczeństwa oraz różnicami w innych zdolnościach."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct to model dużego języka z serii Qwen2, dostosowany do instrukcji, o rozmiarze parametrów wynoszącym 1.5B. Model ten oparty jest na architekturze Transformer, wykorzystując funkcję aktywacji SwiGLU, przesunięcia QKV w uwadze oraz grupowe zapytania uwagi. Wykazuje doskonałe wyniki w wielu testach benchmarkowych dotyczących rozumienia języka, generowania, zdolności wielojęzycznych, kodowania, matematyki i wnioskowania, przewyższając większość modeli open-source. W porównaniu do Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct wykazuje znaczną poprawę wydajności w testach MMLU, HumanEval, GSM8K, C-Eval i IFEval, mimo że ma nieco mniejszą liczbę parametrów."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 to zaawansowany uniwersalny model językowy, wspierający różne typy poleceń."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct to model dużego języka z serii Qwen2, dostosowany do instrukcji, o rozmiarze parametrów wynoszącym 72B. Model ten oparty jest na architekturze Transformer, wykorzystując funkcję aktywacji SwiGLU, przesunięcia QKV w uwadze oraz grupowe zapytania uwagi. Może obsługiwać duże wejścia. Model ten wykazuje doskonałe wyniki w wielu testach benchmarkowych dotyczących rozumienia języka, generowania, zdolności wielojęzycznych, kodowania, matematyki i wnioskowania, przewyższając większość modeli open-source i wykazując konkurencyjność z modelami własnościowymi w niektórych zadaniach."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL to najnowsza iteracja modelu Qwen-VL, osiągająca najnowocześniejsze wyniki w benchmarkach zrozumienia wizualnego."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 to nowa seria dużych modeli językowych, zaprojektowana w celu optymalizacji przetwarzania zadań instrukcyjnych."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 to nowa seria dużych modeli językowych, zaprojektowana w celu optymalizacji przetwarzania zadań instrukcyjnych."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 to nowa seria dużych modeli językowych, z silniejszymi zdolnościami rozumienia i generacji."
+ "description": "Duży model językowy opracowany przez zespół Alibaba Cloud Tongyi Qianwen"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 to nowa seria dużych modeli językowych, charakteryzująca się mocniejszymi zdolnościami rozumienia i generowania."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 to nowa seria dużych modeli językowych, mająca na celu optymalizację przetwarzania zadań instruktażowych."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 to nowa seria dużych modeli językowych, zaprojektowana w celu optymalizacji przetwarzania zadań instrukcyjnych."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 to nowa seria dużych modeli językowych, mająca na celu optymalizację przetwarzania zadań instruktażowych."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder koncentruje się na pisaniu kodu."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math koncentruje się na rozwiązywaniu problemów w dziedzinie matematyki, oferując profesjonalne odpowiedzi na trudne pytania."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct to najnowsza wersja serii dużych modeli językowych specyficznych dla kodu wydana przez Alibaba Cloud. Model ten, oparty na Qwen2.5, został przeszkolony na 55 bilionach tokenów, znacznie poprawiając zdolności generowania kodu, wnioskowania i naprawy. Wzmacnia on nie tylko zdolności kodowania, ale także utrzymuje przewagę w zakresie matematyki i ogólnych umiejętności. Model ten stanowi bardziej kompleksową podstawę dla rzeczywistych zastosowań, takich jak inteligentne agenty kodowe."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 to najnowsza seria modeli Qwen, obsługująca kontekst 128k. W porównaniu do obecnie najlepszych modeli open source, Qwen2-72B znacznie przewyższa w zakresie rozumienia języka naturalnego, wiedzy, kodowania, matematyki i wielu języków."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 to najnowsza seria modeli Qwen, która przewyższa najlepsze modele open source o podobnej skali, a nawet większe. Qwen2 7B osiągnęła znaczną przewagę w wielu testach, szczególnie w zakresie kodowania i rozumienia języka chińskiego."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B to potężny model językowo-wizualny, wspierający przetwarzanie multimodalne obrazów i tekstu, zdolny do precyzyjnego rozpoznawania treści obrazów i generowania odpowiednich opisów lub odpowiedzi."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct to model językowy z 14 miliardami parametrów, o doskonałej wydajności, optymalizujący scenariusze w języku chińskim i wielojęzyczne, wspierający inteligentne odpowiedzi, generowanie treści i inne zastosowania."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct to model językowy z 32 miliardami parametrów, o zrównoważonej wydajności, optymalizujący scenariusze w języku chińskim i wielojęzyczne, wspierający inteligentne odpowiedzi, generowanie treści i inne zastosowania."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct obsługuje kontekst 16k, generując długie teksty przekraczające 8K. Wspiera wywołania funkcji i bezproblemową interakcję z systemami zewnętrznymi, znacznie zwiększając elastyczność i skalowalność. Wiedza modelu znacznie wzrosła, a jego zdolności w zakresie kodowania i matematyki uległy znacznemu poprawieniu, z obsługą ponad 29 języków."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct to model językowy z 7 miliardami parametrów, wspierający wywołania funkcji i bezproblemową interakcję z systemami zewnętrznymi, znacznie zwiększając elastyczność i skalowalność. Optymalizuje scenariusze w języku chińskim i wielojęzyczne, wspierając inteligentne odpowiedzi, generowanie treści i inne zastosowania."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct to model instrukcji programowania oparty na dużych wstępnych treningach, posiadający silne zdolności rozumienia i generowania kodu, zdolny do efektywnego przetwarzania różnych zadań programistycznych, szczególnie odpowiedni do inteligentnego pisania kodu, generowania skryptów automatycznych i rozwiązywania problemów programistycznych."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct to duży model językowy zaprojektowany specjalnie do generowania kodu, rozumienia kodu i efektywnych scenariuszy rozwoju, wykorzystujący wiodącą w branży skalę 32B parametrów, zdolny do zaspokojenia różnorodnych potrzeb programistycznych."
+ },
+ "SenseChat": {
+ "description": "Podstawowa wersja modelu (V4), długość kontekstu 4K, silne zdolności ogólne."
+ },
+ "SenseChat-128K": {
+ "description": "Podstawowa wersja modelu (V4), długość kontekstu 128K, doskonałe wyniki w zadaniach związanych z rozumieniem i generowaniem długich tekstów."
+ },
+ "SenseChat-32K": {
+ "description": "Podstawowa wersja modelu (V4), długość kontekstu 32K, elastycznie stosowana w różnych scenariuszach."
+ },
+ "SenseChat-5": {
+ "description": "Najnowsza wersja modelu (V5.5), długość kontekstu 128K, znacznie poprawione zdolności w zakresie rozumowania matematycznego, rozmów w języku angielskim, podążania za instrukcjami oraz rozumienia długich tekstów, dorównująca GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "Jest to najnowsza wersja oparta na V5.5, która w porównaniu do poprzedniej wersji wykazuje znaczną poprawę w podstawowych umiejętnościach językowych w chińskim i angielskim, czatach, wiedzy ścisłej, wiedzy humanistycznej, pisaniu, logice matematycznej oraz kontroli liczby słów."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Długość kontekstu 32K, w rozumieniu rozmów w języku kantońskim przewyższa GPT-4, w wielu dziedzinach, takich jak wiedza, rozumowanie, matematyka i programowanie, dorównuje GPT-4 Turbo."
+ },
+ "SenseChat-Character": {
+ "description": "Standardowa wersja modelu, długość kontekstu 8K, wysoka szybkość reakcji."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Zaawansowana wersja modelu, długość kontekstu 32K, znacznie poprawione zdolności, obsługuje rozmowy w języku chińskim i angielskim."
+ },
+ "SenseChat-Turbo": {
+ "description": "Idealny do szybkich odpowiedzi i scenariuszy dostosowywania modelu."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "Jest to najnowsza wersja modelu o niskiej wadze, osiągająca ponad 90% możliwości pełnego modelu, znacznie obniżając koszty wnioskowania."
+ },
+ "SenseChat-Vision": {
+ "description": "Najnowsza wersja modelu (V5.5), obsługująca wiele obrazów jako wejście, w pełni optymalizuje podstawowe możliwości modelu, osiągając znaczną poprawę w rozpoznawaniu atrybutów obiektów, relacji przestrzennych, rozpoznawaniu zdarzeń, zrozumieniu scen, rozpoznawaniu emocji, wnioskowaniu logicznym oraz generowaniu i rozumieniu tekstu."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Model drugiej generacji Skylark (Skylark2) o wysokiej szybkości reakcji, odpowiedni do scenariuszy wymagających wysokiej reaktywności, wrażliwych na koszty, z mniejszymi wymaganiami co do precyzji modelu, z długością okna kontekstowego 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Model drugiej generacji Skylark (Skylark2) o wysokiej precyzji, odpowiedni do bardziej złożonych scenariuszy generowania tekstu, takich jak generowanie treści w profesjonalnych dziedzinach, tworzenie powieści oraz tłumaczenia wysokiej jakości, z długością okna kontekstowego 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Model drugiej generacji Skylark (Skylark2) o wysokiej precyzji, odpowiedni do bardziej złożonych scenariuszy generowania tekstu, takich jak generowanie treści w profesjonalnych dziedzinach, tworzenie powieści oraz tłumaczenia wysokiej jakości, z długością okna kontekstowego 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Model drugiej generacji Skylark (Skylark2) z doskonałymi umiejętnościami w odgrywaniu ról i czatowaniu. Doskonale reaguje na prompty użytkowników, odgrywając różne role w naturalny sposób, idealny do budowy chatbotów, wirtualnych asystentów i obsługi klienta online, cechujący się wysoką szybkością reakcji."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Model drugiej generacji Skylark (Skylark2) z szybszym wnioskowaniem i niższymi kosztami, z długością okna kontekstowego 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B to otwarty model z serii ChatGLM, opracowany przez Zhipu AI. Model ten zachowuje doskonałe cechy poprzednich modeli, takie jak płynność rozmowy i niski próg wdrożenia, jednocześnie wprowadzając nowe funkcje. Wykorzystuje bardziej zróżnicowane dane treningowe, większą liczbę kroków treningowych i bardziej rozsądne strategie treningowe, osiągając doskonałe wyniki w modelach pretrenowanych poniżej 10B. ChatGLM3-6B obsługuje złożone scenariusze, takie jak wieloetapowe rozmowy, wywoływanie narzędzi, wykonywanie kodu i zadania agenta. Oprócz modelu konwersacyjnego, udostępniono również podstawowy model ChatGLM-6B-Base oraz model do rozmów długotematycznych ChatGLM3-6B-32K. Model jest całkowicie otwarty dla badań akademickich i pozwala na bezpłatne wykorzystanie komercyjne po rejestracji."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B to otwarta wersja, oferująca zoptymalizowane doświadczenie dialogowe dla aplikacji konwersacyjnych."
},
+ "TeleAI/TeleChat2": {
+ "description": "Model TeleChat2 to generatywny model semantyczny opracowany przez China Telecom, który wspiera funkcje takie jak pytania i odpowiedzi encyklopedyczne, generowanie kodu oraz generowanie długich tekstów, oferując użytkownikom usługi konsultacyjne. Model ten potrafi prowadzić interakcje z użytkownikami, odpowiadać na pytania, wspierać twórczość oraz efektywnie pomagać w pozyskiwaniu informacji, wiedzy i inspiracji. Model wykazuje dobre wyniki w zakresie problemów z halucynacjami, generowaniem długich tekstów oraz rozumieniem logicznym."
+ },
+ "TeleAI/TeleMM": {
+ "description": "Model TeleMM to model wielomodalny opracowany przez China Telecom, który potrafi przetwarzać różne rodzaje wejść, takie jak tekst i obrazy, wspierając funkcje rozumienia obrazów oraz analizy wykresów, oferując użytkownikom usługi rozumienia międzymodalnego. Model ten potrafi prowadzić interakcje wielomodalne z użytkownikami, dokładnie rozumiejąc wprowadzone treści, odpowiadając na pytania, wspierając twórczość oraz efektywnie dostarczając informacji i inspiracji w różnych modalnościach. Wykazuje doskonałe wyniki w zadaniach wielomodalnych, takich jak precyzyjne postrzeganie i rozumowanie logiczne."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct to jeden z najnowszych modeli dużych języków wydanych przez Alibaba Cloud. Model 72B ma znacząco poprawione zdolności w zakresie kodowania i matematyki. Oferuje również wsparcie dla wielu języków, obejmując ponad 29 języków, w tym chiński i angielski. Model ten wykazuje znaczną poprawę w zakresie przestrzegania instrukcji, rozumienia danych strukturalnych oraz generowania strukturalnych wyników (szczególnie JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, zachowując doskonałe ogólne zdolności językowe oryginalnej serii modeli, znacznie poprawił zdolności logiczne i kodowania dzięki dodatkowym treningom na 500 miliardach wysokiej jakości tokenów."
+ },
"abab5.5-chat": {
"description": "Skierowany do scenariuszy produkcyjnych, wspierający przetwarzanie złożonych zadań i efektywne generowanie tekstu, odpowiedni do zastosowań w profesjonalnych dziedzinach."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Optymalizowany do scenariuszy dialogowych w języku chińskim, oferujący płynne i zgodne z chińskimi zwyczajami generowanie dialogów."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Open source model wywołań funkcji od Fireworks, oferujący doskonałe możliwości wykonania poleceń i otwarte, konfigurowalne cechy."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2, najnowszy model firmy Fireworks, to wydajny model wywołań funkcji, opracowany na bazie Llama-3, zoptymalizowany do wywołań funkcji, dialogów i śledzenia poleceń."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b to model językowy wizualny, który może jednocześnie przyjmować obrazy i tekst, przeszkolony na wysokiej jakości danych, idealny do zadań multimodalnych."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 to zaawansowany model językowy, który został zoptymalizowany dzięki uczeniu przez wzmocnienie i danym z zimnego startu, oferując doskonałe możliwości wnioskowania, matematyki i programowania."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Model Gemma 2 9B Instruct, oparty na wcześniejszej technologii Google, idealny do zadań generowania tekstu, takich jak odpowiadanie na pytania, podsumowywanie i wnioskowanie."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Potężny model językowy Mixture-of-Experts (MoE) oferowany przez Deepseek, z całkowitą liczbą parametrów wynoszącą 671 miliardów, aktywującym 37 miliardów parametrów na każdy token."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Model Llama 3 70B Instruct, zaprojektowany do wielojęzycznych dialogów i rozumienia języka naturalnego, przewyższa większość konkurencyjnych modeli."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Model Llama 3 70B Instruct (wersja HF), zgodny z wynikami oficjalnej implementacji, idealny do wysokiej jakości zadań śledzenia poleceń."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Model Llama 3 8B Instruct, zoptymalizowany do dialogów i zadań wielojęzycznych, oferuje doskonałe i efektywne osiągi."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Model Llama 3.1 8B Instruct, zoptymalizowany do wielojęzycznych dialogów, potrafi przewyższyć większość modeli open source i closed source w powszechnych standardach branżowych."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Model wnioskowania wizualnego z 11B parametrów od Meta. Model zoptymalizowany do rozpoznawania wizualnego, wnioskowania obrazów, opisywania obrazów oraz odpowiadania na ogólne pytania dotyczące obrazów. Model potrafi rozumieć dane wizualne, takie jak wykresy i grafiki, a dzięki generowaniu tekstowych opisów szczegółów obrazów, łączy wizję z językiem."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Model instruktażowy Llama 3.2 3B to lekki model wielojęzyczny zaprezentowany przez Meta. Zaprojektowany, aby poprawić wydajność, oferując znaczące usprawnienia w opóźnieniu i kosztach w porównaniu do większych modeli. Przykładowe przypadki użycia tego modelu obejmują zapytania i przepisanie sugestii oraz pomoc w pisaniu."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Model wnioskowania wizualnego z 90B parametrów od Meta. Model zoptymalizowany do rozpoznawania wizualnego, wnioskowania obrazów, opisywania obrazów oraz odpowiadania na ogólne pytania dotyczące obrazów. Model potrafi rozumieć dane wizualne, takie jak wykresy i grafiki, a dzięki generowaniu tekstowych opisów szczegółów obrazów, łączy wizję z językiem."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct to zaktualizowana wersja Llama 3.1 70B z grudnia. Model ten został ulepszony w oparciu o Llama 3.1 70B (wydany w lipcu 2024), wzmacniając możliwości wywoływania narzędzi, wsparcie dla tekstów w wielu językach, a także umiejętności matematyczne i programistyczne. Model osiągnął wiodący w branży poziom w zakresie wnioskowania, matematyki i przestrzegania instrukcji, oferując wydajność porównywalną z 3.1 405B, jednocześnie zapewniając znaczące korzyści w zakresie szybkości i kosztów."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Model z 24 miliardami parametrów, oferujący zaawansowane możliwości porównywalne z większymi modelami."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Model Mixtral MoE 8x22B Instruct, z dużą liczbą parametrów i architekturą wielu ekspertów, kompleksowo wspierający efektywne przetwarzanie złożonych zadań."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Model Mixtral MoE 8x7B Instruct, architektura wielu ekspertów, oferująca efektywne śledzenie i wykonanie poleceń."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Model Mixtral MoE 8x7B Instruct (wersja HF), wydajność zgodna z oficjalną implementacją, idealny do różnych scenariuszy efektywnych zadań."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "Model MythoMax L2 13B, łączący nowatorskie techniki łączenia, doskonały w narracji i odgrywaniu ról."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Model Phi 3 Vision Instruct, lekki model multimodalny, zdolny do przetwarzania złożonych informacji wizualnych i tekstowych, z silnymi zdolnościami wnioskowania."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "Model StarCoder 15.5B, wspierający zaawansowane zadania programistyczne, z wzmocnionymi możliwościami wielojęzycznymi, idealny do złożonego generowania i rozumienia kodu."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Model QwQ to eksperymentalny model badawczy opracowany przez zespół Qwen, skoncentrowany na zwiększeniu zdolności wnioskowania AI."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Wersja 72B modelu Qwen-VL to najnowszy owoc iteracji Alibaba, reprezentujący innowacje z ostatniego roku."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "Model StarCoder 7B, przeszkolony w ponad 80 językach programowania, oferujący doskonałe możliwości uzupełniania kodu i rozumienia kontekstu."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 to seria modeli językowych opracowana przez zespół Qwen na chmurze Alibaba, która zawiera jedynie dekodery. Modele te występują w różnych rozmiarach, w tym 0.5B, 1.5B, 3B, 7B, 14B, 32B i 72B, i oferują dwie wersje: bazową (base) i instruktażową (instruct)."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct to najnowsza wersja serii dużych modeli językowych specyficznych dla kodu wydana przez Alibaba Cloud. Model ten, oparty na Qwen2.5, został przeszkolony na 55 bilionach tokenów, znacznie poprawiając zdolności generowania kodu, wnioskowania i naprawy. Wzmacnia on nie tylko zdolności kodowania, ale także utrzymuje przewagę w zakresie matematyki i ogólnych umiejętności. Model ten stanowi bardziej kompleksową podstawę dla rzeczywistych zastosowań, takich jak inteligentne agenty kodowe."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Model Yi-Large, oferujący doskonałe możliwości przetwarzania wielojęzycznego, nadający się do różnych zadań generowania i rozumienia języka."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Model wielojęzyczny z 52 miliardami parametrów (12 miliardów aktywnych), oferujący okno kontekstowe o długości 256K, wywoływanie funkcji, strukturalne wyjście i generację opartą na kontekście."
},
- "ai21-jamba-instruct": {
- "description": "Model LLM oparty na Mamba, zaprojektowany do osiągania najlepszej wydajności, jakości i efektywności kosztowej."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet podnosi standardy branżowe, przewyższając modele konkurencji oraz Claude 3 Opus, osiągając doskonałe wyniki w szerokim zakresie ocen, jednocześnie oferując szybkość i koszty na poziomie naszych modeli średniej klasy."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet podnosi standardy branżowe, przewyższając modele konkurencji oraz Claude 3 Opus, wykazując doskonałe wyniki w szerokich ocenach, jednocześnie oferując prędkość i koszty naszych modeli średniego poziomu."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku to najszybszy i najbardziej kompaktowy model od Anthropic, oferujący niemal natychmiastową szybkość odpowiedzi. Może szybko odpowiadać na proste zapytania i prośby. Klienci będą mogli budować płynne doświadczenia AI, które naśladują interakcje międzyludzkie. Claude 3 Haiku może przetwarzać obrazy i zwracać wyjścia tekstowe, z oknem kontekstowym wynoszącym 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus to najpotężniejszy model Anthropic do obsługi wysoce złożonych zadań. Wyróżnia się doskonałymi osiągami, inteligencją, płynnością i zdolnością rozumienia."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku to najszybszy model nowej generacji od Anthropic. W porównaniu do Claude 3 Haiku, Claude 3.5 Haiku wykazuje poprawę w różnych umiejętnościach i przewyższa największy model poprzedniej generacji, Claude 3 Opus, w wielu testach inteligencji."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet oferuje możliwości przewyższające Opus oraz szybsze tempo niż Sonnet, zachowując tę samą cenę. Sonnet szczególnie dobrze radzi sobie z programowaniem, nauką o danych, przetwarzaniem wizualnym i zadaniami agenta."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet to najinteligentniejszy model stworzony przez Anthropic, a także pierwszy na rynku model mieszanej dedukcji. Claude 3.7 Sonnet potrafi generować niemal natychmiastowe odpowiedzi lub wydłużone, krok po kroku myślenie, które użytkownicy mogą wyraźnie obserwować. Sonnet szczególnie dobrze radzi sobie z programowaniem, nauką o danych, przetwarzaniem wizualnym oraz zadaniami agenta."
+ },
"aya": {
"description": "Aya 23 to model wielojęzyczny wydany przez Cohere, wspierający 23 języki, ułatwiający różnorodne zastosowania językowe."
},
"aya:35b": {
"description": "Aya 23 to model wielojęzyczny wydany przez Cohere, wspierający 23 języki, ułatwiający różnorodne zastosowania językowe."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B to otwarty model językowy stworzony przez Baichuan Intelligence, zawierający 13 miliardów parametrów, który osiągnął najlepsze wyniki w swojej klasie w autorytatywnych benchmarkach w języku chińskim i angielskim."
+ },
"charglm-3": {
"description": "CharGLM-3 zaprojektowany z myślą o odgrywaniu ról i emocjonalnym towarzyszeniu, obsługujący ultra-długą pamięć wielokrotną i spersonalizowane dialogi, z szerokim zakresem zastosowań."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 oferuje postępy w kluczowych możliwościach dla przedsiębiorstw, w tym wiodącą w branży kontekst 200K tokenów, znacznie zmniejszającą częstość występowania halucynacji modelu, systemowe podpowiedzi oraz nową funkcję testową: wywołania narzędzi."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku to najszybszy model następnej generacji od Anthropic. W porównaniu do Claude 3 Haiku, Claude 3.5 Haiku wykazuje poprawę w różnych umiejętnościach i przewyższa największy model poprzedniej generacji, Claude 3 Opus, w wielu testach inteligencji."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet oferuje możliwości przewyższające Opus oraz szybsze tempo niż Sonnet, przy zachowaniu tej samej ceny. Sonnet szczególnie dobrze radzi sobie z programowaniem, nauką danych, przetwarzaniem wizualnym i zadaniami agenta."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet oferuje możliwości wykraczające poza Opus oraz szybsze działanie niż Sonnet, zachowując jednocześnie tę samą cenę. Sonnet jest szczególnie uzdolniony w programowaniu, naukach danych, przetwarzaniu wizualnym oraz zadaniach związanych z pośrednictwem."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet to najnowszy model od Anthropic, który oferuje doskonałe wyniki w szerokim zakresie zadań, w tym generowanie treści, rozumienie języka naturalnego i przestrzeganie instrukcji. Claude 3.7 Sonnet jest szybki, niezawodny i ekonomiczny, co sprawia, że jest idealny do zastosowań produkcyjnych."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku to najszybszy i najbardziej kompaktowy model Anthropic, zaprojektowany do osiągania niemal natychmiastowych odpowiedzi. Oferuje szybkie i dokładne wyniki w ukierunkowanych zadaniach."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet zapewnia idealną równowagę między inteligencją a szybkością dla obciążeń roboczych w przedsiębiorstwach. Oferuje maksymalną użyteczność przy niższej cenie, jest niezawodny i odpowiedni do dużych wdrożeń."
},
- "claude-instant-1.2": {
- "description": "Model Anthropic przeznaczony do generowania tekstu o niskim opóźnieniu i wysokiej przepustowości, wspierający generowanie setek stron tekstu."
- },
"codegeex-4": {
"description": "CodeGeeX-4 to potężny asystent programowania AI, obsługujący inteligentne pytania i odpowiedzi oraz uzupełnianie kodu w różnych językach programowania, zwiększając wydajność programistów."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B to model generowania kodu w wielu językach, który obsługuje kompleksowe funkcje, w tym uzupełnianie i generowanie kodu, interpreter kodu, wyszukiwanie w sieci, wywołania funkcji oraz pytania i odpowiedzi na poziomie repozytoriów, obejmując różne scenariusze rozwoju oprogramowania. Jest to wiodący model generowania kodu z mniej niż 10B parametrów."
+ },
"codegemma": {
"description": "CodeGemma to lekki model językowy, specjalizujący się w różnych zadaniach programistycznych, wspierający szybkie iteracje i integrację."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama to model LLM skoncentrowany na generowaniu i dyskusji kodu, łączący wsparcie dla szerokiego zakresu języków programowania, odpowiedni do środowisk deweloperskich."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama to LLM skoncentrowany na generowaniu i omawianiu kodu, z szerokim wsparciem dla różnych języków programowania, odpowiedni dla środowisk deweloperskich."
+ },
"codellama:13b": {
"description": "Code Llama to model LLM skoncentrowany na generowaniu i dyskusji kodu, łączący wsparcie dla szerokiego zakresu języków programowania, odpowiedni do środowisk deweloperskich."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ to model językowy o wysokiej wydajności, zaprojektowany z myślą o rzeczywistych scenariuszach biznesowych i złożonych zastosowaniach."
},
+ "dall-e-2": {
+ "description": "Druga generacja modelu DALL·E, obsługująca bardziej realistyczne i dokładne generowanie obrazów, o rozdzielczości czterokrotnie większej niż pierwsza generacja."
+ },
+ "dall-e-3": {
+ "description": "Najnowocześniejszy model DALL·E, wydany w listopadzie 2023 roku. Obsługuje bardziej realistyczne i dokładne generowanie obrazów, z lepszą zdolnością do oddawania szczegółów."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct oferuje wysoką niezawodność w przetwarzaniu poleceń, wspierając różne branże."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 to model wnioskowania napędzany uczeniem przez wzmacnianie (RL), który rozwiązuje problemy z powtarzalnością i czytelnością modelu. Przed RL, DeepSeek-R1 wprowadził dane z zimnego startu, co dodatkowo zoptymalizowało wydajność wnioskowania. W zadaniach matematycznych, kodowania i wnioskowania osiąga wyniki porównywalne z OpenAI-o1, a dzięki starannie zaprojektowanym metodom treningowym poprawia ogólne efekty."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "Model destylacyjny DeepSeek-R1, optymalizujący wydajność wnioskowania dzięki uczeniu przez wzmocnienie i danym z zimnego startu, otwarty model ustanawiający nowe standardy w wielu zadaniach."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B to model destylacyjny oparty na Llama-3.1-8B. Model ten został dostosowany przy użyciu próbek wygenerowanych przez DeepSeek-R1, wykazując doskonałe zdolności wnioskowania. Osiągnął dobre wyniki w wielu testach referencyjnych, w tym 89,1% dokładności w MATH-500, 50,4% wskaźnika zdawalności w AIME 2024 oraz 1205 punktów w CodeForces, demonstrując silne zdolności matematyczne i programistyczne jako model o skali 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Model destylacyjny DeepSeek-R1, optymalizujący wydajność wnioskowania dzięki uczeniu przez wzmocnienie i danym z zimnego startu, otwarty model ustanawiający nowe standardy w wielu zadaniach."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Model destylacyjny DeepSeek-R1, optymalizujący wydajność wnioskowania dzięki uczeniu przez wzmocnienie i danym z zimnego startu, otwarty model ustanawiający nowe standardy w wielu zadaniach."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B to model uzyskany przez destylację Qwen2.5-32B. Model ten został dostosowany przy użyciu 800 000 starannie wybranych próbek wygenerowanych przez DeepSeek-R1, wykazując doskonałe osiągi w wielu dziedzinach, takich jak matematyka, programowanie i wnioskowanie. Osiągnął znakomite wyniki w wielu testach referencyjnych, w tym 94,3% dokładności w MATH-500, co pokazuje jego silne zdolności wnioskowania matematycznego."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B to model uzyskany przez destylację Qwen2.5-Math-7B. Model ten został dostosowany przy użyciu 800 000 starannie wybranych próbek wygenerowanych przez DeepSeek-R1, wykazując doskonałe zdolności wnioskowania. Osiągnął znakomite wyniki w wielu testach referencyjnych, w tym 92,8% dokładności w MATH-500, 55,5% wskaźnika zdawalności w AIME 2024 oraz 1189 punktów w CodeForces, demonstrując silne zdolności matematyczne i programistyczne jako model o skali 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 łączy doskonałe cechy wcześniejszych wersji, wzmacniając zdolności ogólne i kodowania."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 to model językowy z 6710 miliardami parametrów, oparty na mieszanych ekspertach (MoE), wykorzystujący wielogłowicową potencjalną uwagę (MLA) oraz architekturę DeepSeekMoE, łączącą strategię równoważenia obciążenia bez dodatkowych strat, co optymalizuje wydajność wnioskowania i treningu. Dzięki wstępnemu treningowi na 14,8 bilionach wysokiej jakości tokenów oraz nadzorowanemu dostrajaniu i uczeniu przez wzmacnianie, DeepSeek-V3 przewyższa inne modele open source, zbliżając się do wiodących modeli zamkniętych."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B to zaawansowany model przeszkolony do złożonych dialogów."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "Najnowocześniejszy, wydajny LLM, specjalizujący się w wnioskowaniu, matematyce i programowaniu."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 to model wizualno-językowy oparty na DeepSeekMoE-27B, wykorzystujący architekturę MoE z rzadką aktywacją, osiągający doskonałe wyniki przy aktywacji jedynie 4,5 miliarda parametrów. Model ten wyróżnia się w wielu zadaniach, takich jak wizualne pytania i odpowiedzi, optyczne rozpoznawanie znaków, zrozumienie dokumentów/tabel/wykresów oraz lokalizacja wizualna."
+ },
"deepseek-chat": {
"description": "Nowy otwarty model łączący zdolności ogólne i kodowe, który nie tylko zachowuje ogólne zdolności dialogowe oryginalnego modelu czatu i potężne zdolności przetwarzania kodu modelu Coder, ale także lepiej dostosowuje się do ludzkich preferencji. Ponadto, DeepSeek-V2.5 osiągnął znaczne poprawy w zadaniach pisarskich, przestrzeganiu instrukcji i innych obszarach."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B to model języka kodu, wytrenowany na 20 bilionach danych, z czego 87% to kod, a 13% to języki chiński i angielski. Model wprowadza okno o rozmiarze 16K oraz zadania uzupełniania, oferując funkcje uzupełniania kodu na poziomie projektu i wypełniania fragmentów."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 to otwarty model kodowy Mixture-of-Experts, który doskonale radzi sobie z zadaniami kodowymi, porównywalny z GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 to otwarty model kodowy Mixture-of-Experts, który doskonale radzi sobie z zadaniami kodowymi, porównywalny z GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 to model wnioskowania napędzany uczeniem przez wzmacnianie (RL), który rozwiązuje problemy z powtarzalnością i czytelnością modelu. Przed RL, DeepSeek-R1 wprowadził dane z zimnego startu, co dodatkowo zoptymalizowało wydajność wnioskowania. W zadaniach matematycznych, kodowania i wnioskowania osiąga wyniki porównywalne z OpenAI-o1, a dzięki starannie zaprojektowanym metodom treningowym poprawia ogólne efekty."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 — większy i inteligentniejszy model w zestawie DeepSeek — został destylowany do architektury Llama 70B. Na podstawie testów referencyjnych i ocen ręcznych, model ten jest bardziej inteligentny niż oryginalna Llama 70B, szczególnie w zadaniach wymagających precyzji matematycznej i faktograficznej."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Modele z serii DeepSeek-R1-Distill są dostosowywane do modeli open source, takich jak Qwen i Llama, poprzez technologię destylacji wiedzy, na podstawie próbek generowanych przez DeepSeek-R1."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Modele z serii DeepSeek-R1-Distill są dostosowywane do modeli open source, takich jak Qwen i Llama, poprzez technologię destylacji wiedzy, na podstawie próbek generowanych przez DeepSeek-R1."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Modele z serii DeepSeek-R1-Distill są dostosowywane do modeli open source, takich jak Qwen i Llama, poprzez technologię destylacji wiedzy, na podstawie próbek generowanych przez DeepSeek-R1."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Modele z serii DeepSeek-R1-Distill są dostosowywane do modeli open source, takich jak Qwen i Llama, poprzez technologię destylacji wiedzy, na podstawie próbek generowanych przez DeepSeek-R1."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Modele z serii DeepSeek-R1-Distill są dostosowywane do modeli open source, takich jak Qwen i Llama, poprzez technologię destylacji wiedzy, na podstawie próbek generowanych przez DeepSeek-R1."
+ },
+ "deepseek-reasoner": {
+ "description": "Model inferency wprowadzony przez DeepSeek. Przed wygenerowaniem ostatecznej odpowiedzi, model najpierw przedstawia fragment łańcucha myślowego, aby zwiększyć dokładność końcowej odpowiedzi."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 to wydajny model językowy Mixture-of-Experts, odpowiedni do ekonomicznych potrzeb przetwarzania."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B to model kodowy zaprojektowany przez DeepSeek, oferujący potężne możliwości generowania kodu."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 to model MoE opracowany przez Hangzhou DeepSeek AI Technology Research Co., Ltd., który osiągnął znakomite wyniki w wielu testach, zajmując pierwsze miejsce wśród modeli open-source na głównych listach. W porównaniu do modelu V2.5, prędkość generowania wzrosła trzykrotnie, co zapewnia użytkownikom szybsze i płynniejsze doświadczenia."
+ },
"deepseek/deepseek-chat": {
"description": "Nowy, otwarty model łączący zdolności ogólne i kodowe, który nie tylko zachowuje ogólne zdolności dialogowe oryginalnego modelu Chat, ale także potężne zdolności przetwarzania kodu modelu Coder, lepiej dostosowując się do ludzkich preferencji. Ponadto, DeepSeek-V2.5 osiągnął znaczne poprawy w zadaniach pisarskich, przestrzeganiu instrukcji i wielu innych obszarach."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 znacznie poprawił zdolności wnioskowania modelu przy minimalnej ilości oznaczonych danych. Przed wygenerowaniem ostatecznej odpowiedzi, model najpierw wygeneruje fragment myślenia, aby zwiększyć dokładność końcowej odpowiedzi."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B to duży model językowy oparty na Llama3.3 70B, który wykorzystuje dostrojenie na podstawie wyjścia DeepSeek R1, osiągając konkurencyjną wydajność porównywalną z dużymi modelami na czołowej pozycji."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B to destylowany duży model językowy oparty na Llama-3.1-8B-Instruct, wytrenowany przy użyciu wyjścia DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B to destylowany duży model językowy oparty na Qwen 2.5 14B, wytrenowany przy użyciu wyjścia DeepSeek R1. Model ten przewyższył OpenAI o1-mini w wielu testach benchmarkowych, osiągając najnowsze osiągnięcia technologiczne w dziedzinie modeli gęstych (dense models). Oto niektóre wyniki testów benchmarkowych:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nModel ten, dostrojony na podstawie wyjścia DeepSeek R1, wykazuje konkurencyjną wydajność porównywalną z większymi modelami na czołowej pozycji."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B to destylowany duży model językowy oparty na Qwen 2.5 32B, wytrenowany przy użyciu wyjścia DeepSeek R1. Model ten przewyższył OpenAI o1-mini w wielu testach benchmarkowych, osiągając najnowsze osiągnięcia technologiczne w dziedzinie modeli gęstych (dense models). Oto niektóre wyniki testów benchmarkowych:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nModel ten, dostrojony na podstawie wyjścia DeepSeek R1, wykazuje konkurencyjną wydajność porównywalną z większymi modelami na czołowej pozycji."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 to najnowszy model open source wydany przez zespół DeepSeek, który charakteryzuje się bardzo silnymi możliwościami wnioskowania, szczególnie w zadaniach matematycznych, programistycznych i logicznych, osiągając poziom porównywalny z modelem o1 OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 znacznie poprawił zdolności wnioskowania modelu przy minimalnej ilości oznaczonych danych. Przed wygenerowaniem ostatecznej odpowiedzi, model najpierw wygeneruje fragment myślenia, aby zwiększyć dokładność końcowej odpowiedzi."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 osiągnął znaczący przełom w szybkości wnioskowania w porównaniu do wcześniejszych modeli. Zajmuje pierwsze miejsce wśród modeli open source i może konkurować z najnowocześniejszymi modelami zamkniętymi na świecie. DeepSeek-V3 wykorzystuje architekturę wielogłowicowej uwagi (MLA) oraz DeepSeekMoE, które zostały w pełni zweryfikowane w DeepSeek-V2. Ponadto, DeepSeek-V3 wprowadza pomocniczą strategię bezstratną do równoważenia obciążenia oraz ustala cele treningowe dla wieloetykietowego przewidywania, aby uzyskać lepszą wydajność."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 osiągnął znaczący przełom w szybkości wnioskowania w porównaniu do wcześniejszych modeli. Zajmuje pierwsze miejsce wśród modeli open source i może konkurować z najnowocześniejszymi modelami zamkniętymi na świecie. DeepSeek-V3 wykorzystuje architekturę wielogłowicowej uwagi (MLA) oraz DeepSeekMoE, które zostały w pełni zweryfikowane w DeepSeek-V2. Ponadto, DeepSeek-V3 wprowadza pomocniczą strategię bezstratną do równoważenia obciążenia oraz ustala cele treningowe dla wieloetykietowego przewidywania, aby uzyskać lepszą wydajność."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite to nowa generacja modelu o lekkiej konstrukcji, charakteryzująca się ekstremalną szybkością reakcji, osiągając światowy poziom zarówno w zakresie wydajności, jak i opóźnienia."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k to kompleksowa wersja ulepszona na bazie Doubao-1.5-Pro, która oferuje znaczny wzrost wydajności o 10%. Obsługuje wnioskowanie w kontekście 256k, a maksymalna długość wyjścia wynosi 12k tokenów. Wyższa wydajność, większe okno, doskonały stosunek jakości do ceny, odpowiedni do szerszego zakresu zastosowań."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro to nowa generacja głównego modelu, który oferuje kompleksowe ulepszenia wydajności, wykazując doskonałe wyniki w zakresie wiedzy, kodowania, wnioskowania i innych obszarów."
+ },
"emohaa": {
"description": "Emohaa to model psychologiczny, posiadający profesjonalne umiejętności doradcze, pomagający użytkownikom zrozumieć problemy emocjonalne."
},
+ "ernie-3.5-128k": {
+ "description": "Flagowy model językowy opracowany przez Baidu, obejmujący ogromne zbiory danych w języku chińskim i angielskim, charakteryzujący się silnymi zdolnościami ogólnymi, spełniającym wymagania większości zastosowań w dialogach, generowaniu treści i aplikacjach wtyczek; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji."
+ },
+ "ernie-3.5-8k": {
+ "description": "Flagowy model językowy opracowany przez Baidu, obejmujący ogromne zbiory danych w języku chińskim i angielskim, charakteryzujący się silnymi zdolnościami ogólnymi, spełniającym wymagania większości zastosowań w dialogach, generowaniu treści i aplikacjach wtyczek; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Flagowy model językowy opracowany przez Baidu, obejmujący ogromne zbiory danych w języku chińskim i angielskim, charakteryzujący się silnymi zdolnościami ogólnymi, spełniającym wymagania większości zastosowań w dialogach, generowaniu treści i aplikacjach wtyczek; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Flagowy model językowy Baidu o ultra dużej skali, w porównaniu do ERNIE 3.5, oferujący kompleksową aktualizację zdolności modelu, szeroko stosowany w złożonych zadaniach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Flagowy model językowy Baidu o ultra dużej skali, w porównaniu do ERNIE 3.5, oferujący kompleksową aktualizację zdolności modelu, szeroko stosowany w złożonych zadaniach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Flagowy model językowy Baidu o ultra dużej skali, charakteryzujący się doskonałymi wynikami ogólnymi, szeroko stosowany w złożonych zadaniach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji. W porównaniu do ERNIE 4.0, oferuje lepsze wyniki wydajności."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Flagowy model językowy Baidu o ultra dużej skali, charakteryzujący się doskonałymi wynikami ogólnymi, szeroko stosowany w złożonych zadaniach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji. W porównaniu do ERNIE 4.0, oferuje lepsze wyniki wydajności."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Flagowy model językowy Baidu o ultra dużej skali, charakteryzujący się doskonałymi wynikami ogólnymi, szeroko stosowany w złożonych zadaniach w różnych dziedzinach; wspiera automatyczne połączenie z wtyczką wyszukiwania Baidu, zapewniając aktualność informacji. W porównaniu do ERNIE 4.0, oferuje lepsze wyniki wydajności."
+ },
+ "ernie-char-8k": {
+ "description": "Model językowy opracowany przez Baidu, skoncentrowany na specyficznych scenariuszach, odpowiedni do zastosowań w grach NPC, dialogach obsługi klienta, odgrywaniu ról w dialogach, charakteryzujący się wyraźnym i spójnym stylem postaci, silniejszą zdolnością do podążania za instrukcjami oraz lepszą wydajnością wnioskowania."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Model językowy opracowany przez Baidu, skoncentrowany na specyficznych scenariuszach, odpowiedni do zastosowań w grach NPC, dialogach obsługi klienta, odgrywaniu ról w dialogach, charakteryzujący się wyraźnym i spójnym stylem postaci, silniejszą zdolnością do podążania za instrukcjami oraz lepszą wydajnością wnioskowania."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite to lekki model językowy opracowany przez Baidu, łączący doskonałe wyniki modelu z wydajnością wnioskowania, odpowiedni do użycia na kartach przyspieszających AI o niskiej mocy obliczeniowej."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Lekki model językowy opracowany przez Baidu, łączący doskonałe wyniki modelu z wydajnością wnioskowania, oferujący lepsze wyniki niż ERNIE Lite, odpowiedni do użycia na kartach przyspieszających AI o niskiej mocy obliczeniowej."
+ },
+ "ernie-novel-8k": {
+ "description": "Ogólny model językowy opracowany przez Baidu, który wykazuje wyraźne przewagi w zakresie kontynuacji powieści, może być również stosowany w scenariuszach krótkich dramatów i filmów."
+ },
+ "ernie-speed-128k": {
+ "description": "Najnowszy model językowy o wysokiej wydajności opracowany przez Baidu w 2024 roku, charakteryzujący się doskonałymi zdolnościami ogólnymi, odpowiedni jako model bazowy do dalszego dostosowania, lepiej radzący sobie z problemami w specyficznych scenariuszach, a także oferujący doskonałą wydajność wnioskowania."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Najnowszy model językowy o wysokiej wydajności opracowany przez Baidu w 2024 roku, charakteryzujący się doskonałymi zdolnościami ogólnymi, oferujący lepsze wyniki niż ERNIE Speed, odpowiedni jako model bazowy do dalszego dostosowania, lepiej radzący sobie z problemami w specyficznych scenariuszach, a także oferujący doskonałą wydajność wnioskowania."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny to model językowy o ultra wysokiej wydajności opracowany przez Baidu, charakteryzujący się najniższymi kosztami wdrożenia i dostosowania w serii modeli Wenxin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) oferuje stabilną i dostosowywalną wydajność, co czyni go idealnym wyborem dla rozwiązań złożonych zadań."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro to model AI o wysokiej wydajności od Google, zaprojektowany do szerokiego rozszerzania zadań."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash to najnowszy model AI wielomodalnego od Google, charakteryzujący się szybkim przetwarzaniem, obsługujący wejścia tekstowe, obrazowe i wideo, idealny do efektywnego rozszerzania w różnych zadaniach."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 to wydajny model multimodalny, wspierający szerokie zastosowania."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 to wydajny model multimodalny, który wspiera szeroką gamę zastosowań."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 został zaprojektowany do obsługi dużych zadań, oferując niezrównaną prędkość przetwarzania."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B to wydajny model multimodalny, który wspiera szeroki zakres zastosowań."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 to najnowszy eksperymentalny model, który wykazuje znaczące poprawy wydajności w zastosowaniach tekstowych i multimodalnych."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 oferuje zoptymalizowane możliwości przetwarzania multimodalnego, odpowiednie do różnych złożonych scenariuszy zadań."
+ "description": "Gemini 1.5 Flash 0827 oferuje zoptymalizowane możliwości przetwarzania multimodalnego, odpowiednie dla wielu złożonych scenariuszy."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash to najnowszy model AI Google o wielu modalnościach, który charakteryzuje się szybkim przetwarzaniem i obsługuje wejścia tekstowe, obrazowe i wideo, co czyni go odpowiednim do efektywnego rozszerzania w różnych zadaniach."
@@ -362,6 +827,30 @@
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro obsługuje do 2 milionów tokenów, co czyni go idealnym wyborem dla średniej wielkości modeli multimodalnych, odpowiednim do wszechstronnej obsługi złożonych zadań."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash oferuje funkcje i ulepszenia nowej generacji, w tym doskonałą prędkość, natywne korzystanie z narzędzi, generowanie multimodalne oraz okno kontekstowe o długości 1M tokenów."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash oferuje funkcje i ulepszenia nowej generacji, w tym doskonałą prędkość, natywne korzystanie z narzędzi, generowanie multimodalne oraz okno kontekstowe o długości 1M tokenów."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash to wariant modelu, zoptymalizowany pod kątem efektywności kosztowej i niskiego opóźnienia."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash to wariant modelu, zoptymalizowany pod kątem efektywności kosztowej i niskiego opóźnienia."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Model Gemini 2.0 Flash, zoptymalizowany pod kątem efektywności kosztowej i niskiej latencji."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp to najnowszy eksperymentalny model AI multimodalnego Google, posiadający cechy nowej generacji, doskonałą prędkość, natywne wywołania narzędzi oraz generację multimodalną."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp to najnowszy eksperymentalny model AI multimodalnego Google, posiadający cechy nowej generacji, doskonałą prędkość, natywne wywołania narzędzi oraz generację multimodalną."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental to najnowszy eksperymentalny model AI o wielu modalnościach od Google, który w porównaniu do wcześniejszych wersji oferuje pewne poprawy jakości, szczególnie w zakresie wiedzy o świecie, kodu i długiego kontekstu."
+ },
"gemma-7b-it": {
"description": "Gemma 7B nadaje się do przetwarzania zadań średniej i małej skali, łącząc efektywność kosztową."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 to wydajny model wydany przez Google, obejmujący różnorodne zastosowania, od małych aplikacji po złożone przetwarzanie danych."
},
- "general": {
- "description": "Spark Lite to lekki model dużego języka, charakteryzujący się bardzo niskim opóźnieniem i wysoką wydajnością przetwarzania, całkowicie darmowy i otwarty, wspierający funkcję wyszukiwania w czasie rzeczywistym. Jego szybka reakcja sprawia, że doskonale sprawdza się w zastosowaniach inferencyjnych i dostrajaniu modeli na urządzeniach o niskiej mocy obliczeniowej, oferując użytkownikom doskonały stosunek kosztów do korzyści oraz inteligentne doświadczenie, szczególnie w zadaniach związanych z pytaniami o wiedzę, generowaniem treści i wyszukiwaniem."
- },
"generalv3": {
"description": "Spark Pro to model dużego języka o wysokiej wydajności, zoptymalizowany do profesjonalnych dziedzin, takich jak matematyka, programowanie, medycyna i edukacja, wspierający wyszukiwanie w sieci oraz wbudowane wtyczki, takie jak pogoda i daty. Jego zoptymalizowany model wykazuje doskonałe wyniki i wysoką wydajność w skomplikowanych pytaniach o wiedzę, rozumieniu języka oraz tworzeniu zaawansowanych tekstów, co czyni go idealnym wyborem do profesjonalnych zastosowań."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 to najnowsza wersja modelu, zaprojektowana do wysoko złożonych i zróżnicowanych zadań, z doskonałymi wynikami."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat wykazuje wysoką wydajność w wielu aspektach, takich jak semantyka, matematyka, wnioskowanie, kodowanie i wiedza. Posiada również funkcje przeglądania stron internetowych, wykonywania kodu, wywoływania niestandardowych narzędzi oraz wnioskowania z długich tekstów. Obsługuje 26 języków, w tym japoński, koreański i niemiecki."
+ },
"glm-4-air": {
"description": "GLM-4-Air to opłacalna wersja, której wydajność jest zbliżona do GLM-4, oferująca szybkie działanie i przystępną cenę."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash to idealny wybór do przetwarzania prostych zadań, najszybszy i najtańszy."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX to ulepszona wersja Flash, charakteryzująca się niezwykle szybkim czasem wnioskowania."
+ },
"glm-4-long": {
"description": "GLM-4-Long obsługuje ultra-długie wejścia tekstowe, odpowiednie do zadań pamięciowych i przetwarzania dużych dokumentów."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V oferuje potężne zdolności rozumienia i wnioskowania obrazów, obsługując różne zadania wizualne."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash koncentruje się na efektywnym zrozumieniu pojedynczego obrazu, idealny do scenariuszy szybkiej analizy obrazu, takich jak analiza obrazów w czasie rzeczywistym lub przetwarzanie partii obrazów."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus ma zdolność rozumienia treści wideo oraz wielu obrazów, odpowiedni do zadań multimodalnych."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 oferuje zoptymalizowane możliwości przetwarzania multimodalnego, odpowiednie do różnych złożonych zadań."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview posiada silne zdolności do złożonego wnioskowania, wyróżniając się w dziedzinach takich jak wnioskowanie logiczne, matematyka i programowanie."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash oferuje funkcje i ulepszenia nowej generacji, w tym doskonałą prędkość, natywne korzystanie z narzędzi, generowanie multimodalne oraz okno kontekstowe o długości 1M tokenów."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 łączy najnowsze technologie optymalizacji, oferując bardziej efektywne przetwarzanie danych multimodalnych."
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental to najnowszy eksperymentalny model AI o wielu modalnościach od Google, który w porównaniu do wcześniejszych wersji oferuje pewne poprawy jakości, szczególnie w zakresie wiedzy o świecie, kodu i długiego kontekstu."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash oferuje zoptymalizowane możliwości przetwarzania multimodalnego, odpowiednie do różnych złożonych scenariuszy zadań."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro łączy najnowsze technologie optymalizacji, oferując bardziej efektywne przetwarzanie danych multimodalnych."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 to wydajny model wydany przez Google, obejmujący różnorodne scenariusze zastosowań, od małych aplikacji po złożone przetwarzanie danych."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 kontynuuje ideę lekkiego i wydajnego projektowania."
},
+ "google/gemma-2-2b-it": {
+ "description": "Lekki model dostosowywania instrukcji od Google."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 to wydajny model wydany przez Google, obejmujący różnorodne scenariusze zastosowań, od małych aplikacji po złożone przetwarzanie danych."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 to lekka seria modeli tekstowych open source od Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, odpowiedni do różnych zadań generowania i rozumienia tekstu, obecnie wskazuje na gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo to wydajny model dostarczany przez OpenAI, idealny do obsługi zadań związanych z czatowaniem i generowaniem tekstu, wspierający równoległe wywołania funkcji."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k, model do generowania tekstu o dużej pojemności, odpowiedni do bardziej złożonych zadań."
+ },
"gpt-4": {
"description": "GPT-4 oferuje większe okno kontekstowe, zdolne do przetwarzania dłuższych wejść tekstowych, co czyni go odpowiednim do scenariuszy wymagających szerokiej integracji informacji i analizy danych."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "Najnowszy model GPT-4 Turbo posiada funkcje wizualne. Teraz zapytania wizualne mogą być obsługiwane za pomocą formatu JSON i wywołań funkcji. GPT-4 Turbo to ulepszona wersja, która oferuje opłacalne wsparcie dla zadań multimodalnych. Znajduje równowagę między dokładnością a wydajnością, co czyni go odpowiednim do aplikacji wymagających interakcji w czasie rzeczywistym."
},
- "gpt-4-1106-vision-preview": {
- "description": "Najnowszy model GPT-4 Turbo posiada funkcje wizualne. Teraz zapytania wizualne mogą być obsługiwane za pomocą formatu JSON i wywołań funkcji. GPT-4 Turbo to ulepszona wersja, która oferuje opłacalne wsparcie dla zadań multimodalnych. Znajduje równowagę między dokładnością a wydajnością, co czyni go odpowiednim do aplikacji wymagających interakcji w czasie rzeczywistym."
- },
"gpt-4-32k": {
"description": "GPT-4 oferuje większe okno kontekstowe, zdolne do przetwarzania dłuższych wejść tekstowych, co czyni go odpowiednim do scenariuszy wymagających szerokiej integracji informacji i analizy danych."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "Najnowszy model GPT-4 Turbo posiada funkcje wizualne. Teraz zapytania wizualne mogą być obsługiwane za pomocą formatu JSON i wywołań funkcji. GPT-4 Turbo to ulepszona wersja, która oferuje opłacalne wsparcie dla zadań multimodalnych. Znajduje równowagę między dokładnością a wydajnością, co czyni go odpowiednim do aplikacji wymagających interakcji w czasie rzeczywistym."
},
+ "gpt-4.5-preview": {
+ "description": "Wersja badawcza GPT-4.5, która jest naszym największym i najpotężniejszym modelem GPT do tej pory. Posiada szeroką wiedzę o świecie i lepiej rozumie intencje użytkowników, co sprawia, że doskonale radzi sobie w zadaniach kreatywnych i autonomicznym planowaniu. GPT-4.5 akceptuje tekstowe i graficzne wejścia oraz generuje wyjścia tekstowe (w tym wyjścia strukturalne). Wspiera kluczowe funkcje dla deweloperów, takie jak wywołania funkcji, API wsadowe i strumieniowe wyjścia. W zadaniach wymagających kreatywności, otwartego myślenia i dialogu (takich jak pisanie, nauka czy odkrywanie nowych pomysłów), GPT-4.5 sprawdza się szczególnie dobrze. Data graniczna wiedzy to październik 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o to dynamiczny model, który jest na bieżąco aktualizowany, aby utrzymać najnowszą wersję. Łączy potężne zdolności rozumienia i generowania języka, co czyni go odpowiednim do zastosowań na dużą skalę, w tym obsługi klienta, edukacji i wsparcia technicznego."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o to dynamiczny model, który jest na bieżąco aktualizowany, aby utrzymać najnowszą wersję. Łączy potężne zdolności rozumienia i generowania języka, co czyni go odpowiednim do zastosowań na dużą skalę, w tym obsługi klienta, edukacji i wsparcia technicznego."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o to dynamiczny model, aktualizowany w czasie rzeczywistym, aby być zawsze na bieżąco z najnowszą wersją. Łączy potężne zdolności rozumienia i generowania języka, idealny do zastosowań w dużej skali, w tym obsłudze klienta, edukacji i wsparciu technicznym."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Model audio GPT-4o, obsługujący wejście i wyjście audio."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini to najnowszy model OpenAI, wprowadzony po GPT-4 Omni, obsługujący wejścia tekstowe i wizualne oraz generujący tekst. Jako ich najnowocześniejszy model w małej skali, jest znacznie tańszy niż inne niedawno wprowadzone modele, a jego cena jest o ponad 60% niższa niż GPT-3.5 Turbo. Utrzymuje najnowocześniejszą inteligencję, jednocześnie oferując znaczną wartość za pieniądze. GPT-4o mini uzyskał wynik 82% w teście MMLU i obecnie zajmuje wyższą pozycję w preferencjach czatu niż GPT-4."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Wersja na żywo GPT-4o-mini, obsługująca wejście i wyjście audio oraz tekstowe w czasie rzeczywistym."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Wersja na żywo GPT-4o, obsługująca wejście i wyjście audio oraz tekstowe w czasie rzeczywistym."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Wersja na żywo GPT-4o, obsługująca wejście i wyjście audio oraz tekstowe w czasie rzeczywistym."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Wersja na żywo GPT-4o, obsługująca wejście i wyjście audio oraz tekstowe w czasie rzeczywistym."
+ },
+ "grok-2-1212": {
+ "description": "Model ten poprawił dokładność, przestrzeganie instrukcji oraz zdolności wielojęzyczne."
+ },
+ "grok-2-vision-1212": {
+ "description": "Model ten poprawił dokładność, przestrzeganie instrukcji oraz zdolności wielojęzyczne."
+ },
+ "grok-beta": {
+ "description": "Oferuje wydajność porównywalną z Grok 2, ale z wyższą efektywnością, prędkością i funkcjonalnością."
+ },
+ "grok-vision-beta": {
+ "description": "Najnowszy model rozumienia obrazów, który potrafi przetwarzać różnorodne informacje wizualne, w tym dokumenty, wykresy, zrzuty ekranu i zdjęcia."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B to model językowy łączący kreatywność i inteligencję, zintegrowany z wieloma wiodącymi modelami."
},
+ "hunyuan-code": {
+ "description": "Najnowocześniejszy model generowania kodu Hunyuan, przeszkolony na bazie 200B wysokiej jakości danych kodu, z półrocznym treningiem na wysokiej jakości danych SFT, z wydłużonym oknem kontekstowym do 8K, zajmującym czołowe miejsca w automatycznych wskaźnikach oceny generowania kodu w pięciu językach; w ocenie jakościowej zadań kodowych w pięciu językach, osiąga wyniki w pierwszej lidze."
+ },
+ "hunyuan-functioncall": {
+ "description": "Najnowocześniejszy model FunctionCall w architekturze MOE Hunyuan, przeszkolony na wysokiej jakości danych FunctionCall, z oknem kontekstowym o długości 32K, osiągający wiodące wyniki w wielu wymiarach oceny."
+ },
+ "hunyuan-large": {
+ "description": "Model Hunyuan-large ma całkowitą liczbę parametrów wynoszącą około 389B, z aktywowanymi parametrami wynoszącymi około 52B, co czyni go obecnie największym i najlepiej działającym modelem MoE w architekturze Transformer w branży."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Specjalizuje się w zadaniach związanych z długimi tekstami, takich jak streszczenia dokumentów i pytania i odpowiedzi dotyczące dokumentów, a także ma zdolność do obsługi ogólnych zadań generowania tekstu. Wykazuje doskonałe wyniki w analizie i generowaniu długich tekstów, skutecznie radząc sobie z złożonymi i szczegółowymi wymaganiami dotyczącymi przetwarzania długich treści."
+ },
+ "hunyuan-lite": {
+ "description": "Zaktualizowana do struktury MOE, z oknem kontekstowym o długości 256k, prowadzi w wielu zestawach testowych w NLP, kodowaniu, matematyce i innych dziedzinach w porównaniu do wielu modeli open source."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Najnowocześniejszy model multimodalny 7B Hunyuan, z oknem kontekstowym 32K, wspierający multimodalne dialogi w języku chińskim i angielskim, rozpoznawanie obiektów w obrazach, zrozumienie dokumentów i tabel, multimodalną matematykę itp., z wynikami w wielu wymiarach lepszymi niż modele konkurencyjne 7B."
+ },
+ "hunyuan-pro": {
+ "description": "Model długiego tekstu MOE-32K o skali bilionów parametrów. Osiąga absolutnie wiodący poziom w różnych benchmarkach, obsługując złożone instrukcje i wnioskowanie, posiadając zaawansowane umiejętności matematyczne, wspierając wywołania funkcji, z optymalizacjami w obszarach takich jak tłumaczenia wielojęzyczne, prawo finansowe i medyczne."
+ },
+ "hunyuan-role": {
+ "description": "Najnowocześniejszy model odgrywania ról Hunyuan, stworzony przez oficjalne dostosowanie i trening Hunyuan, oparty na modelu Hunyuan i zestawie danych scenariuszy odgrywania ról, oferujący lepsze podstawowe wyniki w scenariuszach odgrywania ról."
+ },
+ "hunyuan-standard": {
+ "description": "Zastosowano lepszą strategię routingu, jednocześnie łagodząc problemy z równoważeniem obciążenia i zbieżnością ekspertów. W przypadku długich tekstów wskaźnik 'znalezienia igły w stogu siana' osiąga 99,9%. MOE-32K oferuje lepszy stosunek jakości do ceny, równoważąc efektywność i cenę, umożliwiając przetwarzanie długich tekstów."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Zastosowano lepszą strategię routingu, jednocześnie łagodząc problemy z równoważeniem obciążenia i zbieżnością ekspertów. W przypadku długich tekstów wskaźnik 'znalezienia igły w stogu siana' osiąga 99,9%. MOE-256K dokonuje dalszych przełomów w długości i efektywności, znacznie rozszerzając możliwą długość wejścia."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Najnowocześniejszy model multimodalny Hunyuan, wspierający odpowiedzi w wielu językach, z równoważnymi zdolnościami w języku chińskim i angielskim."
+ },
+ "hunyuan-translation": {
+ "description": "Obsługuje tłumaczenie między 15 językami, w tym chińskim, angielskim, japońskim, francuskim, portugalskim, hiszpańskim, tureckim, rosyjskim, arabskim, koreańskim, włoskim, niemieckim, wietnamskim, malajskim i indonezyjskim, opartym na automatycznej ocenie COMET w oparciu o zestaw testowy do tłumaczenia w różnych scenariuszach, wykazując ogólnie lepsze zdolności tłumaczeniowe w porównaniu do modeli o podobnej skali na rynku."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Model tłumaczenia Hunyuan wspiera naturalne tłumaczenie w formie dialogu; obsługuje tłumaczenie między chińskim, angielskim, japońskim, francuskim, portugalskim, hiszpańskim, tureckim, rosyjskim, arabskim, koreańskim, włoskim, niemieckim, wietnamskim, malajskim i indonezyjskim."
+ },
+ "hunyuan-turbo": {
+ "description": "Hunyuan to nowa generacja dużego modelu językowego w wersji próbnej, wykorzystująca nową strukturę modelu mieszanych ekspertów (MoE), która w porównaniu do hunyuan-pro charakteryzuje się szybszą efektywnością wnioskowania i lepszymi wynikami."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Stała wersja hunyuan-turbo z dnia 20 listopada 2024 roku, będąca pomiędzy hunyuan-turbo a hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Optymalizacja tej wersji: skalowanie danych instrukcji, znaczne zwiększenie ogólnej zdolności generalizacji modelu; znaczne zwiększenie zdolności w zakresie matematyki, kodowania i rozumowania logicznego; optymalizacja zdolności związanych z rozumieniem tekstu i słów; optymalizacja jakości generowania treści w tworzeniu tekstów."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Ogólna optymalizacja doświadczeń, w tym zrozumienie NLP, tworzenie tekstów, rozmowy, pytania i odpowiedzi, tłumaczenia, obszary tematyczne itp.; zwiększenie humanizacji, optymalizacja inteligencji emocjonalnej modelu; poprawa zdolności modelu do aktywnego wyjaśniania w przypadku niejasnych intencji; poprawa zdolności do rozwiązywania problemów związanych z analizą słów; poprawa jakości i interaktywności twórczości; poprawa doświadczeń w wielokrotnych interakcjach."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Nowa generacja flagowego modelu językowo-wizualnego Hunyuan, wykorzystująca nową strukturę modelu mieszanych ekspertów (MoE), z pełnym zwiększeniem zdolności w zakresie podstawowego rozpoznawania, tworzenia treści, pytań i odpowiedzi oraz analizy i rozumowania w porównaniu do poprzedniej generacji modeli."
+ },
+ "hunyuan-vision": {
+ "description": "Najnowocześniejszy model multimodalny Hunyuan, wspierający generowanie treści tekstowych na podstawie obrazów i tekstu."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Innowacyjny model open source InternLM2.5, dzięki dużej liczbie parametrów, zwiększa inteligencję dialogową."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 oferuje inteligentne rozwiązania dialogowe w różnych scenariuszach."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Model Llama 3.1 70B Instruct, z 70B parametrami, oferujący doskonałe osiągi w dużych zadaniach generowania tekstu i poleceń."
+ "internlm2-pro-chat": {
+ "description": "Starsza wersja modelu, którą nadal utrzymujemy, dostępna w różnych wariantach parametrów: 7B i 20B."
+ },
+ "internlm2.5-latest": {
+ "description": "Nasza najnowsza seria modeli, charakteryzująca się doskonałymi osiągami wnioskowania, obsługująca długość kontekstu do 1M oraz lepsze możliwości śledzenia instrukcji i wywoływania narzędzi."
+ },
+ "internlm3-latest": {
+ "description": "Nasza najnowsza seria modeli, charakteryzująca się doskonałą wydajnością wnioskowania, prowadzi wśród modeli open-source o podobnej skali. Domyślnie wskazuje na naszą najnowszą wersję modelu InternLM3."
+ },
+ "jina-deepsearch-v1": {
+ "description": "Głębokie wyszukiwanie łączy wyszukiwanie w sieci, czytanie i wnioskowanie, umożliwiając kompleksowe badania. Możesz to traktować jako agenta, który przyjmuje Twoje zadania badawcze - przeprowadza szerokie poszukiwania i wielokrotne iteracje, zanim poda odpowiedź. Proces ten obejmuje ciągłe badania, wnioskowanie i rozwiązywanie problemów z różnych perspektyw. To zasadniczo różni się od standardowych dużych modeli, które generują odpowiedzi bezpośrednio z wstępnie wytrenowanych danych oraz od tradycyjnych systemów RAG, które polegają na jednorazowym powierzchownym wyszukiwaniu."
+ },
+ "kimi-latest": {
+ "description": "Produkt Kimi Smart Assistant korzysta z najnowszego modelu Kimi, który może zawierać cechy jeszcze niestabilne. Obsługuje zrozumienie obrazów i automatycznie wybiera model 8k/32k/128k jako model rozliczeniowy w zależności od długości kontekstu żądania."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM to eksperymentalny model językowy, specyficzny dla zadań, przeszkolony zgodnie z zasadami nauki o uczeniu się, który może przestrzegać systemowych instrukcji w scenariuszach nauczania i uczenia się, pełniąc rolę eksperta mentora."
+ },
+ "lite": {
+ "description": "Spark Lite to lekki model językowy o dużej skali, charakteryzujący się niezwykle niskim opóźnieniem i wysoką wydajnością przetwarzania, całkowicie darmowy i otwarty, wspierający funkcje wyszukiwania w czasie rzeczywistym. Jego cechy szybkiej reakcji sprawiają, że doskonale sprawdza się w zastosowaniach inferencyjnych na urządzeniach o niskiej mocy obliczeniowej oraz w dostosowywaniu modeli, oferując użytkownikom znakomity stosunek kosztów do korzyści oraz inteligentne doświadczenie, szczególnie w kontekście pytań i odpowiedzi, generowania treści oraz wyszukiwania."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B oferuje potężne możliwości wnioskowania AI, odpowiednie do złożonych zastosowań, wspierające ogromne przetwarzanie obliczeniowe przy zachowaniu efektywności i dokładności."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B to model o wysokiej wydajności, oferujący szybkie możliwości generowania tekstu, idealny do zastosowań wymagających dużej efektywności i opłacalności."
},
- "llama-3.1-8b-instruct": {
- "description": "Model Llama 3.1 8B Instruct, z 8B parametrami, wspierający efektywne wykonanie zadań wskazujących, oferujący wysoką jakość generowania tekstu."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Wyjątkowe zdolności wnioskowania wizualnego na obrazach o wysokiej rozdzielczości, idealne do zastosowań związanych ze zrozumieniem wizualnym."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Model Llama 3.1 Sonar Huge Online, z 405B parametrami, obsługujący kontekst o długości około 127,000 tokenów, zaprojektowany do złożonych aplikacji czatu online."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 jest zaprojektowana do obsługi zadań łączących dane wizualne i tekstowe. Wykazuje doskonałe wyniki w zadaniach takich jak opisywanie obrazów i wizualne pytania i odpowiedzi, przekraczając przepaść między generowaniem języka a wnioskowaniem wizualnym."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Model Llama 3.1 Sonar Large Chat, z 70B parametrami, obsługujący kontekst o długości około 127,000 tokenów, idealny do złożonych zadań czatu offline."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Zaawansowane zdolności wnioskowania obrazów dla zastosowań w agentach zrozumienia wizualnego."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Model Llama 3.1 Sonar Large Online, z 70B parametrami, obsługujący kontekst o długości około 127,000 tokenów, idealny do zadań czatu o dużej pojemności i różnorodności."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 jest zaprojektowana do obsługi zadań łączących dane wizualne i tekstowe. Wykazuje doskonałe wyniki w zadaniach takich jak opisywanie obrazów i wizualne pytania i odpowiedzi, przekraczając przepaść między generowaniem języka a wnioskowaniem wizualnym."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Model Llama 3.1 Sonar Small Chat, z 8B parametrami, zaprojektowany do czatów offline, obsługujący kontekst o długości około 127,000 tokenów."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 to najnowocześniejszy wielojęzyczny, otwarty model językowy z serii Llama, który oferuje wydajność porównywalną z modelem 405B przy bardzo niskich kosztach. Opiera się na strukturze Transformer i poprawia użyteczność oraz bezpieczeństwo dzięki nadzorowanemu dostrajaniu (SFT) i uczeniu ze wzmocnieniem na podstawie ludzkich opinii (RLHF). Jego wersja dostosowana do instrukcji jest zoptymalizowana do wielojęzycznych rozmów i w wielu branżowych benchmarkach przewyższa wiele otwartych i zamkniętych modeli czatu. Data graniczna wiedzy to grudzień 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Model Llama 3.1 Sonar Small Online, z 8B parametrami, obsługujący kontekst o długości około 127,000 tokenów, zaprojektowany do czatów online, efektywnie przetwarzający różne interakcje tekstowe."
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 to wielojęzyczny model językowy (LLM) 70B, pretrenowany i dostosowany do poleceń. Model Llama 3.3, dostosowany do poleceń, jest zoptymalizowany do zastosowań w dialogach wielojęzycznych i przewyższa wiele dostępnych modeli czatu, zarówno open source, jak i zamkniętych, w popularnych branżowych benchmarkach."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B oferuje niezrównane możliwości przetwarzania złożoności, dostosowane do projektów o wysokich wymaganiach."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral zaprojektowany do badań naukowych i wnioskowania matematycznego, oferujący efektywne możliwości obliczeniowe i interpretację wyników."
},
+ "max-32k": {
+ "description": "Spark Max 32K jest wyposażony w dużą zdolność przetwarzania kontekstu, oferując silniejsze zrozumienie kontekstu i zdolności logicznego wnioskowania, obsługując teksty o długości do 32K tokenów, co czyni go odpowiednim do czytania długich dokumentów, prywatnych pytań i odpowiedzi oraz innych scenariuszy."
+ },
"meta-llama-3-70b-instruct": {
"description": "Potężny model z 70 miliardami parametrów, doskonały w rozumowaniu, kodowaniu i szerokich zastosowaniach językowych."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) oferuje doskonałe możliwości przetwarzania języka i znakomite doświadczenie interakcji."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 oferuje doskonałe zdolności przetwarzania języka i znakomite doświadczenie interakcyjne."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) to potężny model czatu, wspierający złożone potrzeby dialogowe."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) oferuje wsparcie dla wielu języków, obejmując bogatą wiedzę z różnych dziedzin."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 zaprojektowana do przetwarzania zadań łączących dane wizualne i tekstowe. Doskonała w zadaniach takich jak opisywanie obrazów i wizualne pytania odpowiedzi, przekracza granice między generowaniem języka a wnioskowaniem wizualnym."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 zaprojektowana do przetwarzania zadań łączących dane wizualne i tekstowe. Doskonała w zadaniach takich jak opisywanie obrazów i wizualne pytania odpowiedzi, przekracza granice między generowaniem języka a wnioskowaniem wizualnym."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 zaprojektowana do przetwarzania zadań łączących dane wizualne i tekstowe. Doskonała w zadaniach takich jak opisywanie obrazów i wizualne pytania odpowiedzi, przekracza granice między generowaniem języka a wnioskowaniem wizualnym."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 to najnowocześniejszy wielojęzyczny model językowy open-source z serii Llama, oferujący wydajność porównywalną z modelem 405B przy bardzo niskich kosztach. Oparty na strukturze Transformer, poprawiony dzięki nadzorowanemu dostrajaniu (SFT) oraz uczeniu się z ludzkiego feedbacku (RLHF), co zwiększa użyteczność i bezpieczeństwo. Jego wersja dostosowana do instrukcji jest zoptymalizowana do wielojęzycznych rozmów, osiągając lepsze wyniki w wielu branżowych benchmarkach niż wiele modeli czatu open-source i zamkniętych. Data graniczna wiedzy to grudzień 2023 roku."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 to wielojęzyczny model językowy (LLM) o skali 70B (wejście/wyjście tekstowe), będący modelem generacyjnym wstępnie wytrenowanym i dostosowanym do instrukcji. Model Llama 3.3 dostosowany do instrukcji jest zoptymalizowany pod kątem zastosowań w dialogach wielojęzycznych i przewyższa wiele dostępnych modeli open-source i zamkniętych w popularnych testach branżowych."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 zaprojektowana do przetwarzania zadań łączących dane wizualne i tekstowe. Doskonała w zadaniach takich jak opisywanie obrazów i wizualne pytania odpowiedzi, przekracza granice między generowaniem języka a wnioskowaniem wizualnym."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite jest idealny do środowisk wymagających wysokiej wydajności i niskiego opóźnienia."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "Model Llama 3.1 Turbo 405B oferuje ogromną pojemność kontekstową dla przetwarzania dużych danych, wyróżniając się w zastosowaniach sztucznej inteligencji o dużej skali."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 to wiodący model wydany przez Meta, wspierający do 405B parametrów, mogący być stosowany w złożonych rozmowach, tłumaczeniach wielojęzycznych i analizie danych."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B oferuje efektywne wsparcie dialogowe w wielu językach."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct zoptymalizowano do wysokiej jakości scenariuszy dialogowych, osiągając lepsze wyniki niż wiele modeli zamkniętych."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct to najnowsza wersja wydana przez Meta, zoptymalizowana do generowania wysokiej jakości dialogów, przewyższająca wiele wiodących modeli zamkniętych."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct zaprojektowano z myślą o wysokiej jakości dialogach, osiągając znakomite wyniki w ocenach ludzkich, szczególnie w scenariuszach o wysokiej interakcji."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 oferuje wsparcie dla wielu języków i jest jednym z wiodących modeli generacyjnych w branży."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 jest zaprojektowana do przetwarzania zadań łączących dane wizualne i tekstowe. Wykazuje doskonałe wyniki w zadaniach takich jak opisywanie obrazów i wizualne pytania i odpowiedzi, przekraczając granice między generowaniem języka a wnioskowaniem wizualnym."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 jest zaprojektowana do przetwarzania zadań łączących dane wizualne i tekstowe. Wykazuje doskonałe wyniki w zadaniach takich jak opisywanie obrazów i wizualne pytania i odpowiedzi, przekraczając granice między generowaniem języka a wnioskowaniem wizualnym."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 to najnowocześniejszy wielojęzyczny, otwarty model językowy z serii Llama, który oferuje wydajność porównywalną z modelem 405B przy bardzo niskich kosztach. Opiera się na strukturze Transformer i poprawia użyteczność oraz bezpieczeństwo dzięki nadzorowanemu dostrajaniu (SFT) i uczeniu ze wzmocnieniem na podstawie ludzkich opinii (RLHF). Jego wersja dostosowana do instrukcji jest zoptymalizowana do wielojęzycznych rozmów i w wielu branżowych benchmarkach przewyższa wiele otwartych i zamkniętych modeli czatu. Data graniczna wiedzy to grudzień 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 to najnowocześniejszy wielojęzyczny, otwarty model językowy z serii Llama, który oferuje wydajność porównywalną z modelem 405B przy bardzo niskich kosztach. Opiera się na strukturze Transformer i poprawia użyteczność oraz bezpieczeństwo dzięki nadzorowanemu dostrajaniu (SFT) i uczeniu ze wzmocnieniem na podstawie ludzkich opinii (RLHF). Jego wersja dostosowana do instrukcji jest zoptymalizowana do wielojęzycznych rozmów i w wielu branżowych benchmarkach przewyższa wiele otwartych i zamkniętych modeli czatu. Data graniczna wiedzy to grudzień 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct to największy i najpotężniejszy model w rodzinie modeli Llama 3.1 Instruct. Jest to wysoko zaawansowany model do dialogów, wnioskowania i generowania danych, który może być również używany jako podstawa do specjalistycznego, ciągłego wstępnego szkolenia lub dostosowywania w określonych dziedzinach. Llama 3.1 oferuje wielojęzyczne duże modele językowe (LLM), które są zestawem wstępnie wytrenowanych, dostosowanych do instrukcji modeli generacyjnych, obejmujących rozmiary 8B, 70B i 405B (wejście/wyjście tekstowe). Modele tekstowe Llama 3.1 dostosowane do instrukcji (8B, 70B, 405B) zostały zoptymalizowane do zastosowań w wielojęzycznych dialogach i przewyższają wiele dostępnych modeli czatu open source w powszechnych testach branżowych. Llama 3.1 jest zaprojektowana do użytku komercyjnego i badawczego w wielu językach. Modele tekstowe dostosowane do instrukcji nadają się do czatu w stylu asystenta, podczas gdy modele wstępnie wytrenowane mogą być dostosowane do różnych zadań generowania języka naturalnego. Modele Llama 3.1 wspierają również wykorzystanie ich wyjść do poprawy innych modeli, w tym generowania danych syntetycznych i udoskonalania. Llama 3.1 jest modelem językowym autoregresywnym opartym na zoptymalizowanej architekturze transformatora. Dostosowane wersje wykorzystują nadzorowane dostosowywanie (SFT) oraz uczenie się ze wzmocnieniem z ludzkim feedbackiem (RLHF), aby odpowiadać ludzkim preferencjom dotyczącym pomocności i bezpieczeństwa."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 to otwarty duży model językowy (LLM) skierowany do deweloperów, badaczy i przedsiębiorstw, mający na celu pomoc w budowaniu, eksperymentowaniu i odpowiedzialnym rozwijaniu ich pomysłów na generatywną sztuczną inteligencję. Jako część podstawowego systemu innowacji globalnej społeczności, jest idealny dla urządzeń o ograniczonej mocy obliczeniowej i zasobach, a także dla szybszego czasu szkolenia."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B to najnowszy szybki i lekki model AI od Microsoftu, osiągający wydajność bliską 10-krotności istniejących wiodących modeli open source."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "Zaawansowany LLM, wspierający generowanie danych syntetycznych, destylację wiedzy i wnioskowanie, odpowiedni do chatbotów, programowania i zadań w określonych dziedzinach."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Umożliwia złożone rozmowy, posiadając doskonałe zrozumienie kontekstu, zdolności wnioskowania i generowania tekstu."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Zaawansowany, nowoczesny model, posiadający zrozumienie języka, doskonałe zdolności wnioskowania i generowania tekstu."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Nowoczesny model wizualno-językowy, specjalizujący się w wysokiej jakości wnioskowaniu z obrazów."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Zaawansowany, nowoczesny mały model językowy, posiadający zrozumienie języka, doskonałe zdolności wnioskowania i generowania tekstu."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Zaawansowany, nowoczesny mały model językowy, posiadający zrozumienie języka, doskonałe zdolności wnioskowania i generowania tekstu."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Nowoczesny model wizualno-językowy, specjalizujący się w wysokiej jakości wnioskowaniu z obrazów."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Zaawansowany LLM, specjalizujący się w wnioskowaniu, matematyce, zdrowym rozsądku i wywoływaniu funkcji."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 to model językowy oferowany przez Microsoft AI, który wyróżnia się w złożonych rozmowach, wielojęzyczności, wnioskowaniu i jako inteligentny asystent."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B to najnowocześniejszy model Wizard od Microsoftu, wykazujący niezwykle konkurencyjne osiągi."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V to nowa generacja multimodalnego dużego modelu wydanego przez OpenBMB, który posiada doskonałe zdolności rozpoznawania OCR oraz zrozumienia multimodalnego, wspierając szeroki zakres zastosowań."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B to czołowy model brzegowy Mistrala."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B to opłacalny model brzegowy Mistrala."
+ },
"mistral": {
"description": "Mistral to model 7B wydany przez Mistral AI, odpowiedni do zmiennych potrzeb przetwarzania języka."
},
"mistral-large": {
"description": "Mixtral Large to flagowy model Mistral, łączący zdolności generowania kodu, matematyki i wnioskowania, wspierający kontekst o długości 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) to zaawansowany model językowy (LLM) z najnowocześniejszymi zdolnościami rozumowania, wiedzy i kodowania."
- },
"mistral-large-latest": {
"description": "Mistral Large to flagowy model, doskonały w zadaniach wielojęzycznych, złożonym wnioskowaniu i generowaniu kodu, idealny do zaawansowanych zastosowań."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 oferuje efektywne możliwości obliczeniowe i rozumienia języka naturalnego, idealne do szerokiego zakresu zastosowań."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B to kompaktowy, ale wysokowydajny model, dobrze radzący sobie z przetwarzaniem wsadowym i prostymi zadaniami, takimi jak klasyfikacja i generowanie tekstu, z dobrą zdolnością wnioskowania."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) to super duży model językowy, wspierający ekstremalne wymagania przetwarzania."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B to wstępnie wytrenowany model rzadkiego mieszania ekspertów, przeznaczony do ogólnych zadań tekstowych."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B to model sparsity expert, który korzysta z wielu parametrów, aby zwiększyć prędkość wnioskowania, idealny do przetwarzania zadań wielojęzycznych i generowania kodu."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct to model o wysokiej wydajności, który łączy optymalizację prędkości z obsługą długiego kontekstu."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K to model o zdolności przetwarzania kontekstu o ultra-długiej długości, odpowiedni do generowania bardzo długich tekstów, spełniający wymagania złożonych zadań generacyjnych, zdolny do przetwarzania treści do 128 000 tokenów, idealny do zastosowań w badaniach, akademickich i generowaniu dużych dokumentów."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Model wizualny Kimi (w tym moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview itp.) potrafi rozumieć treść obrazów, w tym teksty na obrazach, kolory obrazów i kształty obiektów."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K oferuje zdolność przetwarzania kontekstu o średniej długości, zdolną do przetwarzania 32 768 tokenów, szczególnie odpowiednią do generowania różnych długich dokumentów i złożonych dialogów, stosowaną w tworzeniu treści, generowaniu raportów i systemach dialogowych."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Model wizualny Kimi (w tym moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview itp.) potrafi rozumieć treść obrazów, w tym teksty na obrazach, kolory obrazów i kształty obiektów."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K zaprojektowany do generowania krótkich tekstów, charakteryzuje się wydajnością przetwarzania, zdolny do przetwarzania 8 192 tokenów, idealny do krótkich dialogów, notatek i szybkiego generowania treści."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Model wizualny Kimi (w tym moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview itp.) potrafi rozumieć treść obrazów, w tym teksty na obrazach, kolory obrazów i kształty obiektów."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto może wybierać odpowiedni model w zależności od liczby tokenów zajmowanych przez bieżący kontekst."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B to ulepszona wersja Nous Hermes 2, zawierająca najnowsze wewnętrznie opracowane zbiory danych."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B to dostosowany przez NVIDIA duży model językowy, mający na celu zwiększenie użyteczności odpowiedzi generowanych przez LLM w odpowiedzi na zapytania użytkowników. Model ten osiągnął doskonałe wyniki w testach benchmarkowych, takich jak Arena Hard, AlpacaEval 2 LC i GPT-4-Turbo MT-Bench, zajmując pierwsze miejsce we wszystkich trzech automatycznych testach do 1 października 2024 roku. Model został przeszkolony przy użyciu RLHF (szczególnie REINFORCE), Llama-3.1-Nemotron-70B-Reward i HelpSteer2-Preference na bazie modelu Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Unikalny model językowy, oferujący niezrównaną dokładność i wydajność."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct to dostosowany przez NVIDIA duży model językowy, zaprojektowany w celu zwiększenia użyteczności odpowiedzi generowanych przez LLM."
+ },
+ "o1": {
+ "description": "Skupia się na zaawansowanym wnioskowaniu i rozwiązywaniu złożonych problemów, w tym zadań matematycznych i naukowych. Doskonale nadaje się do aplikacji wymagających głębokiego zrozumienia kontekstu i zarządzania procesami."
+ },
"o1-mini": {
"description": "o1-mini to szybki i ekonomiczny model wnioskowania zaprojektowany z myślą o programowaniu, matematyce i zastosowaniach naukowych. Model ten ma kontekst 128K i datę graniczną wiedzy z października 2023 roku."
},
"o1-preview": {
"description": "o1 to nowy model wnioskowania OpenAI, odpowiedni do złożonych zadań wymagających szerokiej wiedzy ogólnej. Model ten ma kontekst 128K i datę graniczną wiedzy z października 2023 roku."
},
+ "o3-mini": {
+ "description": "o3-mini to nasz najnowszy mały model wnioskowania, który oferuje wysoką inteligencję przy tych samych kosztach i celach opóźnienia co o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba to model językowy Mamba 2 skoncentrowany na generowaniu kodu, oferujący silne wsparcie dla zaawansowanych zadań kodowania i wnioskowania."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B to model rzadkiego eksperta, który wykorzystuje wiele parametrów do zwiększenia prędkości wnioskowania, odpowiedni do przetwarzania zadań wielojęzycznych i generowania kodu."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o to dynamiczny model, który jest na bieżąco aktualizowany, aby utrzymać najnowszą wersję. Łączy potężne zdolności rozumienia i generowania języka, odpowiedni do zastosowań na dużą skalę, w tym obsługi klienta, edukacji i wsparcia technicznego."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o to dynamiczny model, który jest na bieżąco aktualizowany, aby utrzymać najnowszą wersję. Łączy potężne zdolności rozumienia i generowania języka, idealny do zastosowań na dużą skalę, w tym obsługi klienta, edukacji i wsparcia technicznego."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini to najnowszy model OpenAI, wydany po GPT-4 Omni, obsługujący wejścia tekstowe i wizualne. Jako ich najnowocześniejszy mały model, jest znacznie tańszy od innych niedawnych modeli czołowych i kosztuje o ponad 60% mniej niż GPT-3.5 Turbo. Utrzymuje najnowocześniejszą inteligencję, oferując jednocześnie znaczną wartość za pieniądze. GPT-4o mini uzyskał wynik 82% w teście MMLU i obecnie zajmuje wyższą pozycję w preferencjach czatu niż GPT-4."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Model Pixtral wykazuje silne zdolności w zadaniach związanych z analizą wykresów i zrozumieniem obrazów, pytaniami dokumentowymi, wielomodalnym rozumowaniem i przestrzeganiem instrukcji, zdolny do przyjmowania obrazów w naturalnej rozdzielczości i proporcjach, a także do przetwarzania dowolnej liczby obrazów w długim oknie kontekstowym o długości do 128K tokenów."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large to otwarty model wielomodalny z 124 miliardami parametrów, zbudowany na bazie Mistral Large 2. To nasz drugi model w rodzinie wielomodalnej, który wykazuje zaawansowane zdolności rozumienia obrazów."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K jest wyposażony w wyjątkową zdolność przetwarzania kontekstu, mogąc obsługiwać do 128K informacji kontekstowych, co czyni go idealnym do analizy całościowej i długoterminowego przetwarzania logicznych powiązań w długich treściach, zapewniając płynność i spójność logiczną oraz różnorodne wsparcie cytatów w złożonej komunikacji tekstowej."
+ },
+ "qvq-72b-preview": {
+ "description": "Model QVQ jest eksperymentalnym modelem badawczym opracowanym przez zespół Qwen, skoncentrowanym na zwiększeniu zdolności w zakresie rozumowania wizualnego, szczególnie w dziedzinie rozumowania matematycznego."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Model kodowania Qwen, oparty na ogólnym zrozumieniu."
+ },
"qwen-coder-turbo-latest": {
"description": "Model kodowania Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Model matematyczny Qwen, stworzony specjalnie do rozwiązywania problemów matematycznych."
},
+ "qwen-max": {
+ "description": "Qwen Max to model językowy o skali miliardowej, obsługujący chiński, angielski i inne języki. Aktualna wersja API modelu na bazie Qwen 2.5."
+ },
"qwen-max-latest": {
"description": "Model językowy Qwen Max o skali miliardów parametrów, obsługujący różne języki, w tym chiński i angielski, będący API modelu za produktem Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "Modele z serii Qwen-Omni obsługują różne rodzaje danych wejściowych, w tym wideo, audio, obrazy i tekst, oraz generują wyjścia w postaci audio i tekstu."
+ },
+ "qwen-plus": {
+ "description": "Qwen Plus to ulepszona wersja ogromnego modelu językowego, wspierająca różne języki, w tym chiński i angielski."
+ },
"qwen-plus-latest": {
"description": "Wzmocniona wersja modelu językowego Qwen Plus, obsługująca różne języki, w tym chiński i angielski."
},
+ "qwen-turbo": {
+ "description": "Qwen Turbo to ogromny model językowy, który obsługuje różne języki, w tym chiński i angielski."
+ },
"qwen-turbo-latest": {
"description": "Model językowy Qwen Turbo, obsługujący różne języki, w tym chiński i angielski."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL obsługuje elastyczne interakcje, w tym wiele obrazów, wielokrotne pytania i odpowiedzi oraz zdolności twórcze."
},
- "qwen-vl-max": {
- "description": "Qwen to ultra-duży model językowy wizualny. W porównaniu do wersji ulepszonej, ponownie poprawia zdolności rozumienia wizualnego i przestrzegania instrukcji, oferując wyższy poziom percepcji wizualnej i poznawczej."
+ "qwen-vl-max-latest": {
+ "description": "Model wizualno-językowy Qwen o ultra dużej skali. W porównaniu do wersji rozszerzonej, ponownie zwiększa zdolności wnioskowania wizualnego i przestrzegania instrukcji, oferując wyższy poziom percepcji wizualnej i poznawczej."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Model OCR Tongyi Qianwen to specjalistyczny model do ekstrakcji tekstu, skoncentrowany na zdolności do wydobywania tekstu z obrazów dokumentów, tabel, zadań testowych i pisma ręcznego. Potrafi rozpoznawać wiele języków, w tym: chiński, angielski, francuski, japoński, koreański, niemiecki, rosyjski, włoski, wietnamski i arabski."
},
- "qwen-vl-plus": {
- "description": "Qwen to ulepszona wersja dużego modelu językowego wizualnego. Znacząco poprawia zdolności rozpoznawania szczegółów i tekstu, obsługując obrazy o rozdzielczości powyżej miliona pikseli i dowolnych proporcjach."
+ "qwen-vl-plus-latest": {
+ "description": "Wersja rozszerzona modelu wizualno-językowego Qwen. Znacząco poprawia zdolność rozpoznawania szczegółów i tekstu, obsługuje obrazy o rozdzielczości przekraczającej milion pikseli oraz dowolnych proporcjach."
},
"qwen-vl-v1": {
"description": "Model wstępnie wytrenowany, zainicjowany przez model językowy Qwen-7B, dodający model obrazowy, z rozdzielczością wejściową obrazu wynoszącą 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 to nowa seria dużych modeli językowych Qwen. Qwen2 7B to model oparty na transformatorze, który wykazuje doskonałe wyniki w zakresie rozumienia języka, zdolności wielojęzycznych, programowania, matematyki i wnioskowania."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 to nowa seria dużych modeli językowych, charakteryzująca się silniejszymi zdolnościami rozumienia i generowania."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL to najnowsza iteracja modelu Qwen-VL, która osiągnęła najnowocześniejsze wyniki w testach benchmarkowych dotyczących rozumienia wizualnego, w tym MathVista, DocVQA, RealWorldQA i MTVQA. Qwen2-VL potrafi rozumieć filmy trwające ponad 20 minut, umożliwiając wysokiej jakości pytania i odpowiedzi, dialogi oraz tworzenie treści oparte na wideo. Posiada również zdolności do złożonego wnioskowania i podejmowania decyzji, co pozwala na integrację z urządzeniami mobilnymi, robotami itp., aby automatycznie działać na podstawie środowiska wizualnego i instrukcji tekstowych. Oprócz angielskiego i chińskiego, Qwen2-VL teraz wspiera również rozumienie tekstu w różnych językach w obrazach, w tym większości języków europejskich, japońskiego, koreańskiego, arabskiego i wietnamskiego."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct to jeden z najnowszych modeli dużych języków wydanych przez Alibaba Cloud. Model 72B wykazuje znaczną poprawę w obszarach kodowania i matematyki. Model ten oferuje wsparcie dla wielu języków, obejmując ponad 29 języków, w tym chiński i angielski. Model znacząco poprawił zdolność do podążania za instrukcjami, rozumienia danych strukturalnych oraz generowania strukturalnych wyników (szczególnie JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct to jeden z najnowszych modeli dużych języków wydanych przez Alibaba Cloud. Model 32B wykazuje znaczną poprawę w obszarach kodowania i matematyki. Model ten oferuje wsparcie dla wielu języków, obejmując ponad 29 języków, w tym chiński i angielski. Model znacząco poprawił zdolność do podążania za instrukcjami, rozumienia danych strukturalnych oraz generowania strukturalnych wyników (szczególnie JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM skierowany na język chiński i angielski, skoncentrowany na języku, programowaniu, matematyce, wnioskowaniu i innych dziedzinach."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "Zaawansowany LLM, wspierający generowanie kodu, wnioskowanie i naprawę, obejmujący główne języki programowania."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Potężny średniej wielkości model kodu, wspierający długość kontekstu 32K, specjalizujący się w programowaniu wielojęzycznym."
+ },
"qwen2": {
"description": "Qwen2 to nowa generacja dużego modelu językowego Alibaba, wspierająca różnorodne potrzeby aplikacyjne dzięki doskonałej wydajności."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 to nowa generacja dużego modelu językowego Alibaba, który wspiera różnorodne potrzeby aplikacyjne dzięki doskonałej wydajności."
+ },
"qwen2.5-14b-instruct": {
"description": "Model Qwen 2.5 o skali 14B, udostępniony na zasadzie open source."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Model o skali 72B, udostępniony przez Tongyi Qianwen 2.5."
+ },
"qwen2.5-32b-instruct": {
"description": "Model Qwen 2.5 o skali 32B, udostępniony na zasadzie open source."
},
@@ -826,11 +1601,14 @@
"qwen2.5-coder-1.5b-instruct": {
"description": "Otwarta wersja modelu kodowania Qwen."
},
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Otwarta wersja modelu kodowania Qwen."
+ },
"qwen2.5-coder-7b-instruct": {
"description": "Otwarta wersja modelu kodowania Qwen."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Model Qwen-Math, który ma silne zdolności rozwiązywania problemów matematycznych."
+ "description": "Model Qwen-Math ma silne umiejętności rozwiązywania problemów matematycznych."
},
"qwen2.5-math-72b-instruct": {
"description": "Model Qwen-Math, który ma silne zdolności rozwiązywania problemów matematycznych."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Model Qwen-Math, który ma silne zdolności rozwiązywania problemów matematycznych."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Zwiększona zdolność do podążania za instrukcjami, matematyki, rozwiązywania problemów i kodowania, poprawiona zdolność do rozpoznawania obiektów, wsparcie dla różnych formatów do precyzyjnego lokalizowania elementów wizualnych, zdolność do rozumienia długich plików wideo (do 10 minut) oraz lokalizowania momentów zdarzeń w czasie rzeczywistym, zdolność do rozumienia kolejności czasowej i szybkości, wsparcie dla operacji na systemach OS lub Mobile, silna zdolność do ekstrakcji kluczowych informacji i generowania wyjścia w formacie JSON. Ta wersja to wersja 72B, najsilniejsza w tej serii."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Zwiększona zdolność do podążania za instrukcjami, matematyki, rozwiązywania problemów i kodowania, poprawiona zdolność do rozpoznawania obiektów, wsparcie dla różnych formatów do precyzyjnego lokalizowania elementów wizualnych, zdolność do rozumienia długich plików wideo (do 10 minut) oraz lokalizowania momentów zdarzeń w czasie rzeczywistym, zdolność do rozumienia kolejności czasowej i szybkości, wsparcie dla operacji na systemach OS lub Mobile, silna zdolność do ekstrakcji kluczowych informacji i generowania wyjścia w formacie JSON. Ta wersja to wersja 72B, najsilniejsza w tej serii."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 to nowa generacja dużego modelu językowego Alibaba, który wspiera różnorodne potrzeby aplikacyjne dzięki doskonałej wydajności."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 to nowa generacja dużego modelu językowego Alibaba, który wspiera różnorodne potrzeby aplikacyjne dzięki doskonałej wydajności."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 to nowa generacja dużego modelu językowego Alibaba, który wspiera różnorodne potrzeby aplikacyjne dzięki doskonałej wydajności."
+ },
"qwen2:0.5b": {
"description": "Qwen2 to nowa generacja dużego modelu językowego Alibaba, wspierająca różnorodne potrzeby aplikacyjne dzięki doskonałej wydajności."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 to nowa generacja dużego modelu językowego Alibaba, wspierająca różnorodne potrzeby aplikacyjne dzięki doskonałej wydajności."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini to kompaktowy LLM, przewyższający GPT-3.5, z silnymi zdolnościami wielojęzycznymi, wspierający język angielski i koreański, oferujący wydajne i małe rozwiązanie."
+ "qwq": {
+ "description": "QwQ to eksperymentalny model badawczy, skoncentrowany na zwiększeniu zdolności wnioskowania AI."
+ },
+ "qwq-32b": {
+ "description": "Model inferency QwQ, oparty na modelu Qwen2.5-32B, został znacznie ulepszony dzięki uczeniu przez wzmocnienie, co zwiększa jego zdolności inferencyjne. Kluczowe wskaźniki modelu, takie jak matematyczny kod i inne (AIME 24/25, LiveCodeBench), oraz niektóre ogólne wskaźniki (IFEval, LiveBench itp.) osiągają poziom pełnej wersji DeepSeek-R1, a wszystkie wskaźniki znacznie przewyższają te, które są oparte na Qwen2.5-32B, w tym DeepSeek-R1-Distill-Qwen-32B."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) rozszerza możliwości Solar Mini, koncentrując się na języku japońskim, jednocześnie zachowując wysoką wydajność i doskonałe wyniki w użyciu języka angielskiego i koreańskiego."
+ "qwq-32b-preview": {
+ "description": "Model QwQ to eksperymentalny model badawczy opracowany przez zespół Qwen, skoncentrowany na zwiększeniu zdolności wnioskowania AI."
+ },
+ "qwq-plus-latest": {
+ "description": "Model inferency QwQ, oparty na modelu Qwen2.5, został znacznie ulepszony dzięki uczeniu przez wzmocnienie, co zwiększa jego zdolności inferencyjne. Kluczowe wskaźniki modelu, takie jak matematyczny kod i inne (AIME 24/25, LiveCodeBench), oraz niektóre ogólne wskaźniki (IFEval, LiveBench itp.) osiągają poziom pełnej wersji DeepSeek-R1."
+ },
+ "r1-1776": {
+ "description": "R1-1776 to wersja modelu DeepSeek R1, która została poddana dalszemu treningowi, aby dostarczać nieocenzurowane, bezstronne informacje faktograficzne."
+ },
+ "solar-mini": {
+ "description": "Solar Mini to kompaktowy LLM, który przewyższa GPT-3.5, posiadając potężne zdolności wielojęzyczne, wspierając angielski i koreański, oferując efektywne i zgrabne rozwiązania."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) rozszerza możliwości Solar Mini, koncentrując się na języku japońskim, jednocześnie zachowując wysoką efektywność i doskonałe osiągi w użyciu angielskiego i koreańskiego."
},
"solar-pro": {
"description": "Solar Pro to model LLM o wysokiej inteligencji wydany przez Upstage, koncentrujący się na zdolności do przestrzegania instrukcji na pojedynczym GPU, osiągając wynik IFEval powyżej 80. Obecnie wspiera język angielski, a wersja oficjalna planowana jest na listopad 2024, z rozszerzeniem wsparcia językowego i długości kontekstu."
},
+ "sonar": {
+ "description": "Lekki produkt wyszukiwania oparty na kontekście, szybszy i tańszy niż Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research przeprowadza kompleksowe badania na poziomie eksperckim i łączy je w dostępne, praktyczne raporty."
+ },
+ "sonar-pro": {
+ "description": "Zaawansowany produkt wyszukiwania wspierający kontekst wyszukiwania, oferujący zaawansowane zapytania i śledzenie."
+ },
+ "sonar-reasoning": {
+ "description": "Nowy produkt API wspierany przez model wnioskowania DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Nowy produkt API wspierany przez model wnioskowania DeepSeek."
+ },
"step-1-128k": {
"description": "Równoważy wydajność i koszty, odpowiedni do ogólnych scenariuszy."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Model o wysokiej prędkości, odpowiedni do dialogów w czasie rzeczywistym."
},
+ "step-1.5v-mini": {
+ "description": "Ten model ma potężne zdolności rozumienia wideo."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Model ten ma potężne zdolności rozumienia obrazów, w dziedzinie matematyki i kodowania przewyższa 1o. Model jest mniejszy niż 1o, a prędkość wyjścia jest szybsza."
+ },
+ "step-1o-vision-32k": {
+ "description": "Ten model ma potężne zdolności rozumienia obrazów. W porównaniu do modeli z serii step-1v, oferuje lepsze osiągi wizualne."
+ },
"step-1v-32k": {
"description": "Obsługuje wejścia wizualne, wzmacniając doświadczenie interakcji multimodalnych."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Obsługuje interakcje z dużą ilością kontekstu, idealny do złożonych scenariuszy dialogowych."
},
+ "step-2-mini": {
+ "description": "Model oparty na nowej generacji własnej architektury Attention MFA, osiągający podobne wyniki jak step1 przy bardzo niskich kosztach, jednocześnie zapewniając wyższą przepustowość i szybszy czas reakcji. Potrafi obsługiwać ogólne zadania, a w zakresie umiejętności kodowania ma szczególne zdolności."
+ },
"taichu_llm": {
"description": "Model językowy TaiChu charakteryzuje się wyjątkową zdolnością rozumienia języka oraz umiejętnościami w zakresie tworzenia tekstów, odpowiadania na pytania, programowania, obliczeń matematycznych, wnioskowania logicznego, analizy emocji i streszczenia tekstu. Innowacyjnie łączy wstępne uczenie się na dużych zbiorach danych z bogatą wiedzą z wielu źródeł, stale doskonaląc technologię algorytmiczną i nieustannie przyswajając nową wiedzę z zakresu słownictwa, struktury, gramatyki i semantyki z ogromnych zbiorów danych tekstowych, co prowadzi do ciągłej ewolucji modelu. Umożliwia użytkownikom łatwiejszy dostęp do informacji i usług oraz bardziej inteligentne doświadczenia."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V łączy zdolności rozumienia obrazów, transferu wiedzy i logicznego wnioskowania, osiągając znakomite wyniki w dziedzinie pytań i odpowiedzi na podstawie tekstu i obrazów."
+ "taichu_vl": {
+ "description": "Łączy zdolności rozumienia obrazów, transferu wiedzy i logicznego wnioskowania, wyróżniając się w dziedzinie pytań i odpowiedzi na podstawie tekstu i obrazów."
+ },
+ "text-embedding-3-large": {
+ "description": "Najpotężniejszy model wektoryzacji, odpowiedni do zadań w języku angielskim i innych językach."
+ },
+ "text-embedding-3-small": {
+ "description": "Nowej generacji model Embedding, efektywny i ekonomiczny, odpowiedni do wyszukiwania wiedzy, aplikacji RAG i innych scenariuszy."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Otwarta wersja najnowszej generacji modelu pretrenowanego GLM-4 wydanego przez Zhipu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) oferuje zwiększoną moc obliczeniową dzięki efektywnym strategiom i architekturze modelu."
},
+ "tts-1": {
+ "description": "Najnowocześniejszy model tekstu na mowę, zoptymalizowany pod kątem szybkości w scenariuszach w czasie rzeczywistym."
+ },
+ "tts-1-hd": {
+ "description": "Najnowocześniejszy model tekstu na mowę, zoptymalizowany pod kątem jakości."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) jest przeznaczony do precyzyjnych zadań poleceniowych, oferując doskonałe możliwości przetwarzania języka."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet podnosi standardy branżowe, przewyższając modele konkurencji oraz Claude 3 Opus, osiągając doskonałe wyniki w szerokim zakresie ocen, przy zachowaniu prędkości i kosztów naszych modeli średniego poziomu."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonet to najszybszy model następnej generacji od Anthropic. W porównaniu do Claude 3 Haiku, Claude 3.7 Sonet wykazuje poprawę w różnych umiejętnościach i przewyższa największy model poprzedniej generacji, Claude 3 Opus, w wielu testach inteligencji."
+ },
+ "whisper-1": {
+ "description": "Uniwersalny model rozpoznawania mowy, obsługujący rozpoznawanie mowy w wielu językach, tłumaczenie mowy i rozpoznawanie języków."
+ },
"wizardlm2": {
"description": "WizardLM 2 to model językowy dostarczany przez Microsoft AI, który wyróżnia się w złożonych dialogach, wielojęzyczności, wnioskowaniu i inteligentnych asystentach."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Model o doskonałym stosunku jakości do ceny, z doskonałymi osiągami. Wysokiej precyzji optymalizacja w oparciu o wydajność, szybkość wnioskowania i koszty."
},
+ "yi-lightning": {
+ "description": "Najnowocześniejszy model o wysokiej wydajności, zapewniający wysoką jakość wyjściową przy znacznie zwiększonej prędkości wnioskowania."
+ },
+ "yi-lightning-lite": {
+ "description": "Lekka wersja, zaleca się użycie yi-lightning."
+ },
"yi-medium": {
"description": "Model średniej wielkości, zrównoważony pod względem możliwości i kosztów. Głęboko zoptymalizowana zdolność do przestrzegania poleceń."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Model do złożonych zadań wizualnych, oferujący wysoką wydajność w zakresie rozumienia i analizy obrazów."
+ },
+ "yi-vision-v2": {
+ "description": "Model do złożonych zadań wizualnych, oferujący wysokowydajną zdolność rozumienia i analizy na podstawie wielu obrazów."
}
}
diff --git a/DigitalHumanWeb/locales/pl-PL/plugin.json b/DigitalHumanWeb/locales/pl-PL/plugin.json
index f04bd80..f86516e 100644
--- a/DigitalHumanWeb/locales/pl-PL/plugin.json
+++ b/DigitalHumanWeb/locales/pl-PL/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Nie udało się odświeżyć wtyczki {{name}}",
"urlError": "Link nie zwrócił treści w formacie JSON. Upewnij się, że jest to poprawny link."
},
+ "inspector": {
+ "args": "Zobacz listę parametrów",
+ "pluginRender": "Zobacz interfejs wtyczki"
+ },
"list": {
"item": {
"deprecated.title": "Usunięte",
@@ -130,6 +134,34 @@
"plugin": "Wtyczka jest uruchomiona..."
},
"pluginList": "Lista wtyczek",
+ "search": {
+ "config": {
+ "addKey": "Dodaj klucz",
+ "close": "Usuń",
+ "confirm": "Konfiguracja zakończona, spróbuj ponownie"
+ },
+ "crawPages": {
+ "crawling": "Rozpoznawanie linków",
+ "detail": {
+ "preview": "Podgląd",
+ "raw": "Tekst źródłowy",
+ "tooLong": "Treść tekstu jest zbyt długa, kontekst rozmowy zachowuje tylko pierwsze {{characters}} znaków, a nadmiar nie jest uwzględniany w kontekście rozmowy"
+ },
+ "meta": {
+ "crawler": "Tryb przeszukiwania",
+ "words": "Liczba znaków"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Wprowadź",
+ "description": "Wprowadź adres URL SearchXNG, aby rozpocząć wyszukiwanie w sieci",
+ "keyPlaceholder": "Wprowadź klucz",
+ "title": "Konfiguracja silnika wyszukiwania SearchXNG",
+ "unconfiguredDesc": "Skontaktuj się z administratorem, aby zakończyć konfigurację silnika wyszukiwania SearchXNG i rozpocząć wyszukiwanie w sieci",
+ "unconfiguredTitle": "Silnik wyszukiwania SearchXNG nie jest jeszcze skonfigurowany"
+ },
+ "title": "Wyszukiwanie w sieci"
+ },
"setting": "Ustawienia wtyczki",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/pl-PL/portal.json b/DigitalHumanWeb/locales/pl-PL/portal.json
index 1dbd5fe..8ece822 100644
--- a/DigitalHumanWeb/locales/pl-PL/portal.json
+++ b/DigitalHumanWeb/locales/pl-PL/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Wtyczki",
- "actions": {
- "genAiMessage": "Tworzenie wiadomości AI",
- "summary": "Podsumowanie",
- "summaryTooltip": "Podsumowanie bieżącej zawartości"
- },
"artifacts": {
"display": {
"code": "Kod",
diff --git a/DigitalHumanWeb/locales/pl-PL/providers.json b/DigitalHumanWeb/locales/pl-PL/providers.json
index 6be7bb5..233bce0 100644
--- a/DigitalHumanWeb/locales/pl-PL/providers.json
+++ b/DigitalHumanWeb/locales/pl-PL/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs buduje podstawowe modele i systemy sztucznej inteligencji dla przedsiębiorstw, przyspieszając zastosowanie generatywnej sztucznej inteligencji w produkcji."
+ },
"ai360": {
"description": "360 AI to platforma modeli i usług AI wprowadzona przez firmę 360, oferująca różnorodne zaawansowane modele przetwarzania języka naturalnego, w tym 360GPT2 Pro, 360GPT Pro, 360GPT Turbo i 360GPT Turbo Responsibility 8K. Modele te łączą dużą liczbę parametrów z multimodalnymi zdolnościami, szeroko stosowanymi w generowaniu tekstu, rozumieniu semantycznym, systemach dialogowych i generowaniu kodu. Dzięki elastycznej strategii cenowej, 360 AI zaspokaja zróżnicowane potrzeby użytkowników, wspierając integrację przez deweloperów, co przyczynia się do innowacji i rozwoju aplikacji inteligentnych."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure oferuje różnorodne zaawansowane modele AI, w tym GPT-3.5 i najnowszą serię GPT-4, wspierające różne typy danych i złożone zadania, koncentrując się na bezpiecznych, niezawodnych i zrównoważonych rozwiązaniach AI."
},
+ "azureai": {
+ "description": "Azure oferuje wiele zaawansowanych modeli AI, w tym GPT-3.5 i najnowszą serię GPT-4, wspierając różne typy danych i złożone zadania, dążąc do bezpiecznych, niezawodnych i zrównoważonych rozwiązań AI."
+ },
"baichuan": {
"description": "Baichuan Intelligent to firma skoncentrowana na badaniach nad dużymi modelami sztucznej inteligencji, której modele osiągają doskonałe wyniki w krajowych zadaniach związanych z encyklopedią wiedzy, przetwarzaniem długich tekstów i generowaniem treści w języku chińskim, przewyższając zagraniczne modele mainstreamowe. Baichuan Intelligent dysponuje również wiodącymi w branży zdolnościami multimodalnymi, osiągając doskonałe wyniki w wielu autorytatywnych ocenach. Jej modele obejmują Baichuan 4, Baichuan 3 Turbo i Baichuan 3 Turbo 128k, zoptymalizowane pod kątem różnych scenariuszy zastosowań, oferując opłacalne rozwiązania."
},
"bedrock": {
"description": "Bedrock to usługa oferowana przez Amazon AWS, skoncentrowana na dostarczaniu zaawansowanych modeli językowych i wizualnych dla przedsiębiorstw. Jej rodzina modeli obejmuje serię Claude od Anthropic, serię Llama 3.1 od Meta i inne, oferując różnorodne opcje od lekkich do wysokowydajnych, wspierając generowanie tekstu, dialogi, przetwarzanie obrazów i inne zadania, odpowiednie dla różnych skal i potrzeb aplikacji biznesowych."
},
+ "cloudflare": {
+ "description": "Uruchamiaj modele uczenia maszynowego napędzane przez GPU w globalnej sieci Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek to firma skoncentrowana na badaniach i zastosowaniach technologii sztucznej inteligencji, której najnowszy model DeepSeek-V2.5 łączy zdolności do prowadzenia ogólnych rozmów i przetwarzania kodu, osiągając znaczące postępy w zakresie dostosowywania do preferencji ludzkich, zadań pisarskich i przestrzegania instrukcji."
},
+ "doubao": {
+ "description": "Model dużych rozmiarów opracowany przez ByteDance. Potwierdzony w ponad 50 scenariuszach biznesowych wewnątrz firmy, z codziennym użyciem bilionów tokenów, co pozwala na ciągłe doskonalenie. Oferuje różnorodne możliwości modalne, tworząc bogate doświadczenia biznesowe dla przedsiębiorstw dzięki wysokiej jakości modelom."
+ },
"fireworksai": {
"description": "Fireworks AI to wiodący dostawca zaawansowanych modeli językowych, skoncentrowany na wywołaniach funkcji i przetwarzaniu multimodalnym. Jego najnowszy model Firefunction V2 oparty na Llama-3, zoptymalizowany do wywołań funkcji, dialogów i przestrzegania instrukcji. Model wizualny FireLLaVA-13B wspiera mieszane wejścia obrazów i tekstu. Inne znaczące modele to seria Llama i seria Mixtral, oferujące efektywne wsparcie dla wielojęzycznego przestrzegania instrukcji i generacji."
},
+ "giteeai": {
+ "description": "Serverless API Gitee AI zapewnia deweloperom sztucznej inteligencji gotową usługę interfejsu interfejsu interfejsu dużych modeli."
+ },
"github": {
"description": "Dzięki modelom GitHub, deweloperzy mogą stać się inżynierami AI i budować z wykorzystaniem wiodących modeli AI w branży."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Silnik inferencyjny LPU firmy Groq wyróżnia się w najnowszych niezależnych testach benchmarkowych dużych modeli językowych (LLM), redefiniując standardy rozwiązań AI dzięki niesamowitej szybkości i wydajności. Groq jest reprezentantem natychmiastowej szybkości inferencji, wykazując dobrą wydajność w wdrożeniach opartych na chmurze."
},
+ "higress": {
+ "description": "Higress to chmurowa brama API, która powstała w firmie Alibaba, aby rozwiązać problemy związane z ponownym ładowaniem Tengine, które negatywnie wpływa na długoterminowe połączenia, oraz niewystarczającą zdolnością do równoważenia obciążenia gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API oferuje szybki i bezpłatny sposób na eksplorację tysięcy modeli, które nadają się do różnych zadań. Niezależnie od tego, czy prototypujesz nową aplikację, czy próbujesz funkcji uczenia maszynowego, to API zapewnia natychmiastowy dostęp do wysokowydajnych modeli z wielu dziedzin."
+ },
+ "hunyuan": {
+ "description": "Model językowy opracowany przez Tencent, który posiada potężne zdolności twórcze w języku chińskim, umiejętność logicznego wnioskowania w złożonych kontekstach oraz niezawodne zdolności wykonawcze w zadaniach."
+ },
+ "internlm": {
+ "description": "Organizacja open source poświęcona badaniom i rozwojowi narzędzi dla dużych modeli. Oferuje wszystkim deweloperom AI wydajną i łatwą w użyciu platformę open source, umożliwiającą dostęp do najnowocześniejszych technologii modeli i algorytmów."
+ },
+ "jina": {
+ "description": "Jina AI została założona w 2020 roku i jest wiodącą firmą zajmującą się AI w zakresie wyszukiwania. Nasza platforma bazowa do wyszukiwania zawiera modele wektorowe, przetasowujące i małe modele językowe, które pomagają firmom budować niezawodne i wysokiej jakości aplikacje wyszukiwania generatywnego i multimodalnego."
+ },
+ "lmstudio": {
+ "description": "LM Studio to aplikacja desktopowa do rozwijania i eksperymentowania z LLM-ami na Twoim komputerze."
+ },
"minimax": {
"description": "MiniMax to firma technologiczna zajmująca się ogólną sztuczną inteligencją, założona w 2021 roku, dążąca do współtworzenia inteligencji z użytkownikami. MiniMax opracowało różne modele dużych modeli o różnych modalnościach, w tym model tekstowy MoE z bilionem parametrów, model głosowy oraz model obrazowy. Wprowadziło również aplikacje takie jak Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI to platforma oferująca API do różnych dużych modeli językowych i generacji obrazów AI, elastyczna, niezawodna i opłacalna. Wspiera najnowsze modele open-source, takie jak Llama3, Mistral, i oferuje kompleksowe, przyjazne dla użytkownika oraz automatycznie skalowalne rozwiązania API dla rozwoju aplikacji generatywnej AI, odpowiednie dla szybkiego rozwoju startupów AI."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ oferuje kontenery do samodzielnego hostowania przyspieszonych przez GPU mikroserwisów wnioskowania, wspierając wdrażanie w chmurze, centrach danych, komputerach osobistych RTX™ AI i stacjach roboczych wstępnie wytrenowanych i dostosowanych modeli AI."
+ },
"ollama": {
"description": "Modele oferowane przez Ollama obejmują szeroki zakres zastosowań, w tym generowanie kodu, obliczenia matematyczne, przetwarzanie wielojęzyczne i interakcje konwersacyjne, wspierając różnorodne potrzeby wdrożeń na poziomie przedsiębiorstw i lokalnych."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity to wiodący dostawca modeli generacji dialogów, oferujący różnorodne zaawansowane modele Llama 3.1, wspierające aplikacje online i offline, szczególnie odpowiednie do złożonych zadań przetwarzania języka naturalnego."
},
+ "ppio": {
+ "description": "PPIO Paiou Cloud oferuje stabilne i opłacalne usługi API modeli open source, wspierające pełną gamę DeepSeek, Llama, Qwen i inne wiodące modele w branży."
+ },
"qwen": {
"description": "Tongyi Qianwen to samodzielnie opracowany przez Alibaba Cloud model językowy o dużej skali, charakteryzujący się silnymi zdolnościami rozumienia i generowania języka naturalnego. Może odpowiadać na różnorodne pytania, tworzyć treści pisemne, wyrażać opinie, pisać kod i działać w wielu dziedzinach."
},
+ "sambanova": {
+ "description": "SambaNova Cloud umożliwia deweloperom łatwe korzystanie z najlepszych modeli open source oraz cieszenie się najszybszą prędkością wnioskowania."
+ },
+ "sensenova": {
+ "description": "SenseTime codziennie się rozwija, opierając się na potężnym wsparciu infrastrukturalnym SenseTime, oferując wydajne i łatwe w użyciu usługi dużych modeli w pełnym zakresie."
+ },
"siliconcloud": {
"description": "SiliconFlow dąży do przyspieszenia AGI, aby przynieść korzyści ludzkości, poprawiając wydajność dużych modeli AI dzięki łatwemu w użyciu i niskokosztowemu stosowi GenAI."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "Nowa generacja multimodalnych dużych modeli opracowana przez Instytut Automatyki Chińskiej Akademii Nauk i Wuhan Institute of Artificial Intelligence wspiera wielorundowe pytania i odpowiedzi, tworzenie tekstów, generowanie obrazów, zrozumienie 3D, analizę sygnałów i inne kompleksowe zadania pytaniowe, posiadając silniejsze zdolności poznawcze, rozumienia i tworzenia, oferując nową interaktywną doświadczenie."
},
+ "tencentcloud": {
+ "description": "Atomowe możliwości silnika wiedzy (LLM Knowledge Engine Atomic Power) oparte na silniku wiedzy, oferujące pełne możliwości zadawania pytań i odpowiedzi, skierowane do przedsiębiorstw i deweloperów, zapewniające elastyczność w budowaniu i rozwijaniu aplikacji modelowych. Możesz tworzyć własne usługi modelowe za pomocą różnych atomowych możliwości, korzystając z usług takich jak analiza dokumentów, podział, embedding, wielokrotne przeredagowywanie i inne, aby dostosować AI do specyficznych potrzeb Twojej firmy."
+ },
"togetherai": {
"description": "Together AI dąży do osiągnięcia wiodącej wydajności poprzez innowacyjne modele AI, oferując szerokie możliwości dostosowywania, w tym wsparcie dla szybkiej ekspansji i intuicyjnych procesów wdrożeniowych, aby zaspokoić różnorodne potrzeby przedsiębiorstw."
},
"upstage": {
"description": "Upstage koncentruje się na opracowywaniu modeli AI dla różnych potrzeb biznesowych, w tym Solar LLM i dokumentów AI, mając na celu osiągnięcie sztucznej ogólnej inteligencji (AGI). Umożliwia tworzenie prostych agentów konwersacyjnych za pomocą Chat API oraz wspiera wywołania funkcji, tłumaczenia, osadzenia i zastosowania w określonych dziedzinach."
},
+ "vertexai": {
+ "description": "Seria Gemini od Google to najnowocześniejsze, uniwersalne modele AI stworzone przez Google DeepMind, zaprojektowane z myślą o multimodalności, wspierające bezproblemowe rozumienie i przetwarzanie tekstu, kodu, obrazów, dźwięku i wideo. Odpowiednie do różnych środowisk, od centrów danych po urządzenia mobilne, znacznie zwiększa efektywność i wszechstronność modeli AI."
+ },
+ "vllm": {
+ "description": "vLLM to szybka i łatwa w użyciu biblioteka do wnioskowania i usług LLM."
+ },
+ "volcengine": {
+ "description": "Platforma deweloperska usług dużych modeli wprowadzona przez ByteDance, oferująca bogate w funkcje, bezpieczne i konkurencyjne cenowo usługi wywoływania modeli. Oferuje również dane modelowe, dostosowywanie, wnioskowanie, ocenę i inne funkcje end-to-end, zapewniając kompleksowe wsparcie dla rozwoju aplikacji AI."
+ },
+ "wenxin": {
+ "description": "Platforma do rozwoju i usług aplikacji AI oraz dużych modeli w skali przedsiębiorstwa, oferująca najbardziej kompleksowy i łatwy w użyciu zestaw narzędzi do rozwoju modeli sztucznej inteligencji generatywnej oraz całego procesu tworzenia aplikacji."
+ },
+ "xai": {
+ "description": "xAI to firma, która dąży do budowy sztucznej inteligencji w celu przyspieszenia ludzkich odkryć naukowych. Naszą misją jest wspieranie wspólnego zrozumienia wszechświata."
+ },
"zeroone": {
"description": "01.AI koncentruje się na technologiach sztucznej inteligencji w erze AI 2.0, intensywnie promując innowacje i zastosowania „człowiek + sztuczna inteligencja”, wykorzystując potężne modele i zaawansowane technologie AI w celu zwiększenia wydajności ludzkiej produkcji i realizacji technologicznego wsparcia."
},
diff --git a/DigitalHumanWeb/locales/pl-PL/setting.json b/DigitalHumanWeb/locales/pl-PL/setting.json
index 4f8ec49..ec76e38 100644
--- a/DigitalHumanWeb/locales/pl-PL/setting.json
+++ b/DigitalHumanWeb/locales/pl-PL/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Konfiguracja niestandardowego modelu",
"tokens": {
- "title": "Maksymalna liczba tokenów",
- "unlimited": "Nieograniczony"
+ "title": "Maksymalna liczba tokenów"
},
"vision": {
"extra": "Ta konfiguracja włączy jedynie możliwość przesyłania obrazów w aplikacji, a to, czy rozpoznawanie będzie wspierane, zależy całkowicie od samego modelu. Proszę samodzielnie przetestować dostępność rozpoznawania wizualnego w tym modelu.",
@@ -98,6 +97,7 @@
"title": "使用客户端请求模式"
},
"fetcher": {
+ "clear": "Wyczyść pobrany model",
"fetch": "Pobierz listę modeli",
"fetching": "Trwa pobieranie listy modeli...",
"latestTime": "Ostatnia aktualizacja: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Automatyczne tworzenie tematu podczas rozmowy, działa tylko w przypadku tymczasowych tematów",
"title": "Automatyczne tworzenie tematu"
},
- "enableCompressThreshold": {
- "title": "Włącz próg kompresji historii"
+ "enableCompressHistory": {
+ "title": "Włącz automatyczne podsumowywanie historii wiadomości"
},
"enableHistoryCount": {
"alias": "Bez limitu",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Włącz limit jednorazowej odpowiedzi"
},
+ "enableReasoningEffort": {
+ "title": "Włącz dostosowanie intensywności rozumowania"
+ },
"frequencyPenalty": {
- "desc": "Im większa wartość, tym większe prawdopodobieństwo zmniejszenia powtarzających się słów",
- "title": "Kara za częstość"
+ "desc": "Im większa wartość, tym bardziej zróżnicowane i bogate słownictwo; im mniejsza wartość, tym prostsze i bardziej bezpośrednie słownictwo",
+ "title": "Różnorodność słownictwa"
},
"maxTokens": {
"desc": "Maksymalna liczba tokenów używanych w pojedynczej interakcji",
@@ -212,19 +215,31 @@
"desc": "{{provider}} model",
"title": "Model"
},
+ "params": {
+ "title": "Zaawansowane parametry"
+ },
"presencePenalty": {
- "desc": "Im większa wartość, tym większe prawdopodobieństwo rozszerzenia się na nowe tematy",
- "title": "Świeżość tematu"
+ "desc": "Im większa wartość, tym większa tendencja do różnorodnych wyrażeń, unikanie powtórzeń; im mniejsza wartość, tym większa tendencja do używania powtarzających się koncepcji lub narracji, co prowadzi do większej spójności",
+ "title": "Różnorodność wyrażeń"
+ },
+ "reasoningEffort": {
+ "desc": "Im wyższa wartość, tym silniejsza zdolność rozumowania, ale może to zwiększyć czas odpowiedzi i zużycie tokenów",
+ "options": {
+ "high": "Wysoki",
+ "low": "Niski",
+ "medium": "Średni"
+ },
+ "title": "Intensywność rozumowania"
},
"temperature": {
- "desc": "Im większa wartość, tym odpowiedzi są bardziej losowe",
- "title": "Losowość",
- "titleWithValue": "Losowość {{value}}"
+ "desc": "Im większa wartość, tym bardziej kreatywne i wyobrażeniowe będą odpowiedzi; im mniejsza wartość, tym bardziej rygorystyczne odpowiedzi",
+ "title": "Aktywność kreatywna",
+ "warning": "Zbyt wysoka wartość aktywności kreatywnej może prowadzić do nieczytelnych wyników"
},
"title": "Ustawienia modelu",
"topP": {
- "desc": "Podobne do losowości, ale nie należy zmieniać razem z losowością",
- "title": "Najlepsze P"
+ "desc": "Ile możliwości należy rozważyć, im większa wartość, tym więcej możliwych odpowiedzi; im mniejsza wartość, tym większa tendencja do wyboru najbardziej prawdopodobnej odpowiedzi. Nie zaleca się jednoczesnej zmiany z aktywnością kreatywną",
+ "title": "Otwartość myślenia"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Określa model używany do generowania nazwy, opisu, awatara i etykiety asystenta",
"title": "Automatyczne generowanie informacji o asystencie"
},
+ "customPrompt": {
+ "addPrompt": "Dodaj niestandardowy podpowiedź",
+ "desc": "Po wypełnieniu, asystent systemowy użyje niestandardowej podpowiedzi podczas generowania treści",
+ "placeholder": "Wprowadź niestandardowe słowo podpowiedzi",
+ "title": "Niestandardowe słowo podpowiedzi"
+ },
+ "historyCompress": {
+ "label": "Model historii rozmów",
+ "modelDesc": "Model używany do kompresji historii rozmów",
+ "title": "Automatyczne podsumowanie historii rozmów"
+ },
"queryRewrite": {
"label": "Model przekształcania zapytań",
"modelDesc": "Model używany do optymalizacji zapytań użytkowników",
- "title": "Baza wiedzy"
+ "title": "Przekształcenie zapytań w bazie wiedzy"
+ },
+ "thread": {
+ "label": "Model do nazywania podtematów",
+ "modelDesc": "Model używany do automatycznego zmieniania nazw podtematów",
+ "title": "Automatyczne nazywanie podtematów"
},
"title": "Asystent Systemowy",
"topic": {
@@ -395,6 +426,7 @@
"common": "Ustawienia ogólne",
"experiment": "Eksperyment",
"llm": "Model językowy",
+ "provider": "Dostawca usług AI",
"sync": "Synchronizacja w chmurze",
"system-agent": "System Agent",
"tts": "Usługa głosowa"
diff --git a/DigitalHumanWeb/locales/pl-PL/thread.json b/DigitalHumanWeb/locales/pl-PL/thread.json
new file mode 100644
index 0000000..663e273
--- /dev/null
+++ b/DigitalHumanWeb/locales/pl-PL/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Zaraz usuniesz ten wątek, po usunięciu nie będzie można go przywrócić, proszę postępować ostrożnie."
+ },
+ "newPortalThread": {
+ "includeContext": "Zawiera kontekst tematu",
+ "title": "Rozpocznij nowy podtemat"
+ },
+ "notSupportMultiModals": "Podtematy obecnie nie obsługują przesyłania plików/zdjęć. W przypadku potrzeby, zapraszamy do pozostawienia wiadomości: <1>💬 Dyskusja1>"
+}
diff --git a/DigitalHumanWeb/locales/pl-PL/tool.json b/DigitalHumanWeb/locales/pl-PL/tool.json
index 104d25e..1a55136 100644
--- a/DigitalHumanWeb/locales/pl-PL/tool.json
+++ b/DigitalHumanWeb/locales/pl-PL/tool.json
@@ -6,5 +6,23 @@
"generating": "Generowanie...",
"images": "Obrazy:",
"prompt": "słowo kluczowe"
+ },
+ "search": {
+ "createNewSearch": "Utwórz nową historię wyszukiwania",
+ "emptyResult": "Nie znaleziono wyników, spróbuj zmienić słowa kluczowe",
+ "genAiMessage": "Utwórz wiadomość asystenta",
+ "includedTooltip": "Aktualne wyniki wyszukiwania będą częścią kontekstu rozmowy",
+ "keywords": "Słowa kluczowe:",
+ "scoreTooltip": "Wynik trafności, im wyższy wynik, tym bardziej związany z zapytaniem",
+ "searchBar": {
+ "button": "Szukaj",
+ "placeholder": "Słowa kluczowe",
+ "tooltip": "Ponownie pobierze wyniki wyszukiwania i utworzy nową wiadomość podsumowującą"
+ },
+ "searchEngine": "Silnik wyszukiwania:",
+ "searchResult": "Liczba wyników:",
+ "summary": "Podsumowanie",
+ "summaryTooltip": "Podsumuj bieżącą treść",
+ "viewMoreResults": "Zobacz więcej {{results}} wyników"
}
}
diff --git a/DigitalHumanWeb/locales/pl-PL/topic.json b/DigitalHumanWeb/locales/pl-PL/topic.json
new file mode 100644
index 0000000..cd6e088
--- /dev/null
+++ b/DigitalHumanWeb/locales/pl-PL/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Inteligentne zmienianie nazw",
+ "confirmRemoveAll": "Zaraz usuniesz wszystkie tematy. Po usunięciu nie będzie możliwości ich przywrócenia, proszę działać ostrożnie.",
+ "confirmRemoveTopic": "Zaraz usuniesz ten temat. Po usunięciu nie będzie możliwości jego przywrócenia, proszę działać ostrożnie.",
+ "confirmRemoveUnstarred": "Zaraz usuniesz tematy, które nie są ulubione. Po usunięciu nie będzie możliwości ich przywrócenia, proszę działać ostrożnie.",
+ "duplicate": "Utwórz kopię",
+ "export": "Eksportuj temat",
+ "removeAll": "Usuń wszystkie tematy",
+ "removeUnstarred": "Usuń tematy, które nie są ulubione"
+ },
+ "defaultTitle": "Domyślny temat",
+ "duplicateLoading": "Kopiowanie tematu...",
+ "duplicateSuccess": "Temat skopiowany pomyślnie",
+ "favorite": "Ulubione",
+ "groupMode": {
+ "ascMessages": "Według liczby wiadomości rosnąco",
+ "byTime": "Grupuj według czasu",
+ "descMessages": "Według liczby wiadomości malejąco",
+ "flat": "Bez grupowania"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Ten miesiąc",
+ "today": "Dziś",
+ "week": "Ten tydzień",
+ "yesterday": "Wczoraj"
+ }
+ },
+ "guide": {
+ "desc": "Kliknij przycisk po lewej stronie, aby zapisać bieżącą rozmowę jako temat historyczny i rozpocząć nową rozmowę.",
+ "title": "Lista tematów"
+ },
+ "searchPlaceholder": "Szukaj tematów...",
+ "searchResultEmpty": "Brak wyników wyszukiwania",
+ "temp": "Tymczasowy",
+ "title": "Temat"
+}
diff --git a/DigitalHumanWeb/locales/pl-PL/welcome.json b/DigitalHumanWeb/locales/pl-PL/welcome.json
index 5166d58..73aec50 100644
--- a/DigitalHumanWeb/locales/pl-PL/welcome.json
+++ b/DigitalHumanWeb/locales/pl-PL/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Importuj konfigurację",
- "market": "Przeglądaj rynek",
- "start": "Rozpocznij teraz"
- },
"guide": {
"agents": {
"replaceBtn": "Zmień",
diff --git a/DigitalHumanWeb/locales/pt-BR/auth.json b/DigitalHumanWeb/locales/pt-BR/auth.json
index ef3b9ce..17d3ea8 100644
--- a/DigitalHumanWeb/locales/pt-BR/auth.json
+++ b/DigitalHumanWeb/locales/pt-BR/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Último Mês",
+ "recent30Days": "Últimos 30 Dias"
+ },
+ "header": {
+ "desc": "Gerencie as informações da sua conta.",
+ "title": "Conta"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Inativo",
+ "more": "Ativo"
+ },
+ "months": {
+ "apr": "Abr",
+ "aug": "Ago",
+ "dec": "Dez",
+ "feb": "Fev",
+ "jan": "Jan",
+ "jul": "Jul",
+ "jun": "Jun",
+ "mar": "Mar",
+ "may": "Mai",
+ "nov": "Nov",
+ "oct": "Out",
+ "sep": "Set"
+ },
+ "tooltip": "{{date}} enviou {{count}} mensagens naquele dia",
+ "totalCount": "Um total de {{count}} mensagens enviadas no último ano"
+ },
"login": "Entrar",
- "loginOrSignup": "Entrar / Registrar",
- "profile": "Perfil",
- "security": "Segurança",
+ "loginOrSignup": "Entrar / Cadastrar",
+ "profile": {
+ "avatar": "Avatar",
+ "email": "Endereço de E-mail",
+ "sso": {
+ "loading": "Carregando contas de terceiros vinculadas",
+ "providers": "Contas conectadas",
+ "unlink": {
+ "description": "Após desvincular, você não poderá usar a conta {{provider}} “{{providerAccountId}}” para fazer login. Se precisar re-vincular a conta {{provider}} à conta atual, certifique-se de que o endereço de e-mail da conta {{provider}} seja {{email}}; nós a vincularemos automaticamente à conta de login atual.",
+ "forbidden": "Você deve manter pelo menos uma conta de terceiros vinculada.",
+ "title": "Deseja desvincular a conta de terceiros {{provider}}?"
+ }
+ },
+ "username": "Nome de Usuário"
+ },
"signout": "Sair",
- "signup": "Cadastre-se"
+ "signup": "Cadastrar",
+ "stats": {
+ "aiheatmaps": "Índice de Atividade",
+ "assistants": "Assistentes",
+ "assistantsRank": {
+ "left": "Assistente",
+ "right": "Tópicos",
+ "title": "Ranking de Uso do Assistente"
+ },
+ "createdAt": "Registrado em",
+ "days": "dias",
+ "empty": {
+ "desc": "Por favor, acumule mais dados de chat para visualizar",
+ "title": "Sem Dados"
+ },
+ "lastYearActivity": "atividade no último ano",
+ "loginGuide": {
+ "f1": "Obter uso gratuito",
+ "f2": "Sincronizar mensagens em vários dispositivos",
+ "f3": "Ter assistentes ricos",
+ "f4": "Explorar poderosos plugins",
+ "title": "Após o login, você pode:"
+ },
+ "messages": "Mensagens",
+ "modelsRank": {
+ "left": "Modelo",
+ "right": "Mensagens",
+ "title": "Ranking de Uso do Modelo"
+ },
+ "share": {
+ "title": "Meu Índice de Atividade de IA"
+ },
+ "topics": "Tópicos",
+ "topicsRank": {
+ "left": "Tópico",
+ "right": "Mensagens",
+ "title": "Ranking de Conteúdo do Tópico"
+ },
+ "updatedAt": "Atualizado em",
+ "welcome": "{{username}}, este é seu {{days}} dia com {{appName}}",
+ "words": "Palavras"
+ },
+ "tab": {
+ "profile": "Perfil",
+ "security": "Segurança",
+ "stats": "Estatísticas"
+ }
}
diff --git a/DigitalHumanWeb/locales/pt-BR/changelog.json b/DigitalHumanWeb/locales/pt-BR/changelog.json
new file mode 100644
index 0000000..384c7eb
--- /dev/null
+++ b/DigitalHumanWeb/locales/pt-BR/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Siga-nos no X",
+ "subscribeToUpdates": "Inscreva-se para atualizações",
+ "versions": "Detalhes da versão"
+ },
+ "addedWhileAway": "Trouxemos novos recursos enquanto você estava ausente.",
+ "allChangelog": "Veja todos os registros de alterações",
+ "description": "Acompanhe as novas funcionalidades e melhorias do {{appName}}",
+ "pagination": {
+ "next": "Próxima página",
+ "older": "Ver alterações anteriores"
+ },
+ "readDetails": "Leia os detalhes",
+ "title": "Registro de Atualizações",
+ "versionDetails": "Detalhes da versão",
+ "welcomeBack": "Bem-vindo de volta!"
+}
diff --git a/DigitalHumanWeb/locales/pt-BR/chat.json b/DigitalHumanWeb/locales/pt-BR/chat.json
index 6258b73..72e5dd3 100644
--- a/DigitalHumanWeb/locales/pt-BR/chat.json
+++ b/DigitalHumanWeb/locales/pt-BR/chat.json
@@ -8,6 +8,7 @@
"agents": "Assistente",
"artifact": {
"generating": "Gerando",
+ "inThread": "Não é possível visualizar no subtópico, por favor, mude para a área de conversa principal.",
"thinking": "Pensando",
"thought": "Processo de pensamento",
"unknownTitle": "Obra sem título"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Cópia",
"emptyAgent": "Sem assistente disponível",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "O custo de geração de uma única conversa pode ser reduzido em até 90%, com um aumento de 4 vezes na velocidade de resposta (<1>Saiba mais1>). Ao ativar, o limite de mensagens históricas será desativado automaticamente.",
+ "title": "Ativar cache de contexto"
+ },
+ "enableReasoning": {
+ "desc": "Baseado nas restrições do mecanismo Claude Thinking (<1>Saiba mais1>), ao ativar, o limite de mensagens históricas será desativado automaticamente.",
+ "title": "Ativar Pensamento Profundo"
+ },
+ "reasoningBudgetToken": {
+ "title": "Token de Consumo de Pensamento"
+ },
+ "title": "Funcionalidade de Extensão do Modelo"
+ },
+ "history": {
+ "title": "O assistente lembrará apenas das últimas {{count}} mensagens"
+ },
"historyRange": "Intervalo de Histórico",
+ "historySummary": "Resumo das mensagens históricas",
"inbox": {
"desc": "Ative o cluster cerebral, inspire faíscas de pensamento. Seu assistente inteligente, aqui para conversar sobre tudo.",
"title": "Conversa Aleatória"
@@ -45,6 +64,9 @@
"stop": "Parar",
"warp": "Quebrar linha"
},
+ "intentUnderstanding": {
+ "title": "Entendendo e analisando sua intenção..."
+ },
"knowledgeBase": {
"all": "Todo conteúdo",
"allFiles": "Todos os arquivos",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Excluir e Regenerar",
+ "deleteDisabledByThreads": "Existem subtópicos, não é possível deletar.",
"regenerate": "Regenerar"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Créditos",
+ "creditPricing": "Precificação",
+ "creditTooltip": "Para facilitar a contagem, consideramos 1$ como 1M créditos, por exemplo, $3/M tokens se converte em 3 créditos/token",
+ "pricing": {
+ "inputCachedTokens": "Entrada em cache {{amount}}/créditos · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M caracteres",
+ "inputMinutes": "${{amount}}/minuto",
+ "inputTokens": "Entrada {{amount}}/créditos · ${{amount}}/M",
+ "outputTokens": "Saída {{amount}}/créditos · ${{amount}}/M",
+ "writeCacheInputTokens": "Cache de entrada de escrita {{amount}}/pontos · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Preço médio",
+ "input": "Entrada",
+ "inputAudio": "Entrada de áudio",
+ "inputCached": "Entrada em cache",
+ "inputCitation": "Citação de entrada",
+ "inputText": "Entrada de texto",
+ "inputTitle": "Detalhes da entrada",
+ "inputUncached": "Entrada não cacheada",
+ "inputWriteCached": "Entrada de cache de escrita",
+ "output": "Saída",
+ "outputAudio": "Saída de áudio",
+ "outputText": "Saída de texto",
+ "outputTitle": "Detalhes da saída",
+ "reasoning": "Raciocínio profundo",
+ "title": "Detalhes da geração",
+ "total": "Total consumido"
+ }
+ },
"newAgent": "Novo Assistente",
"pin": "Fixar",
"pinOff": "Desafixar",
@@ -81,6 +137,32 @@
},
"regenerate": "Regenerar",
"roleAndArchive": "Função e Arquivo",
+ "search": {
+ "grounding": {
+ "searchQueries": "Palavras-chave de pesquisa",
+ "title": "Foram encontrados {{count}} resultados"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Determina inteligentemente se é necessário pesquisar com base no conteúdo da conversa",
+ "title": "Conexão Inteligente"
+ },
+ "off": {
+ "desc": "Usa apenas o conhecimento básico do modelo, sem realizar pesquisas na web",
+ "title": "Desativar Conexão"
+ },
+ "on": {
+ "desc": "Realiza pesquisas contínuas na web para obter informações atualizadas",
+ "title": "Sempre Conectado"
+ },
+ "useModelBuiltin": "Usar o mecanismo de busca embutido no modelo"
+ },
+ "searchModel": {
+ "desc": "O modelo atual não suporta chamadas de função, portanto, é necessário combiná-lo com um modelo que suporte chamadas de função para realizar buscas na internet",
+ "title": "Modelo de busca auxiliar"
+ },
+ "title": "Pesquisa Conectada"
+ },
"searchAgentPlaceholder": "Assistente de busca...",
"sendPlaceholder": "Digite a mensagem...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "O nome do grupo deve ter entre 1 e 20 caracteres"
},
"shareModal": {
+ "copy": "Copiar",
"download": "Baixar Captura de Tela",
+ "downloadFile": "Baixar arquivo",
+ "exportTitle": "Título padrão",
"imageType": "Tipo de Imagem",
+ "includeTool": "Incluir mensagens de ferramentas",
+ "includeUser": "Incluir mensagens de usuários",
"screenshot": "Captura de Tela",
"settings": "Configurações de Exportação",
- "shareToShareGPT": "Gerar Link de Compartilhamento ShareGPT",
+ "text": "Texto",
"withBackground": "Com Imagem de Fundo",
"withFooter": "Com Rodapé",
"withPluginInfo": "Com Informações do Plugin",
+ "withRole": "Incluir papel da mensagem",
"withSystemRole": "Com Função do Assistente"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Reconhecendo...",
"prettifying": "Embelezando..."
},
- "temp": "Temporário",
+ "thread": {
+ "divider": "Subtópico",
+ "threadMessageCount": "{{messageCount}} mensagens",
+ "title": "Subtópico"
+ },
"tokenDetails": {
"chats": "Mensagens de bate-papo",
+ "historySummary": "Resumo Histórico",
"rest": "Restante disponível",
"systemRole": "Configuração de papel do sistema",
"title": "Detalhes do Token",
@@ -131,29 +224,10 @@
"used": "Usado"
},
"topic": {
- "actions": {
- "autoRename": "Renomeação Automática",
- "duplicate": "Criar Cópia",
- "export": "Exportar Tópico"
- },
"checkOpenNewTopic": "Deseja abrir um novo tópico?",
"checkSaveCurrentMessages": "Salvar a conversa atual como tópico?",
- "confirmRemoveAll": "Você está prestes a remover todos os tópicos. Depois de remover, não será possível recuperá-los. Por favor, confirme sua ação.",
- "confirmRemoveTopic": "Você está prestes a remover este tópico. Depois de remover, não será possível recuperá-lo. Por favor, confirme sua ação.",
- "confirmRemoveUnstarred": "Você está prestes a remover os tópicos não favoritados. Depois de remover, não será possível recuperá-los. Por favor, confirme sua ação.",
- "defaultTitle": "Tópico Padrão",
- "duplicateLoading": "Tópico sendo duplicado...",
- "duplicateSuccess": "Tópico duplicado com sucesso",
- "guide": {
- "desc": "Clique em enviar no botão esquerdo para salvar a conversa atual como um tópico histórico e iniciar uma nova rodada de conversa",
- "title": "Lista de Tópicos"
- },
"openNewTopic": "Abrir Novo Tópico",
- "removeAll": "Remover Todos os Tópicos",
- "removeUnstarred": "Remover Tópicos Não Favoritados",
- "saveCurrentMessages": "Salvar Mensagens Atuais como Tópico",
- "searchPlaceholder": "Pesquisar tópicos...",
- "title": "Lista de Tópicos"
+ "saveCurrentMessages": "Salvar Mensagens Atuais como Tópico"
},
"translate": {
"action": "Traduzir",
@@ -184,5 +258,6 @@
"processing": "Processando arquivo..."
}
}
- }
+ },
+ "zenMode": "Modo de Foco"
}
diff --git a/DigitalHumanWeb/locales/pt-BR/common.json b/DigitalHumanWeb/locales/pt-BR/common.json
index 0cff597..3328ad3 100644
--- a/DigitalHumanWeb/locales/pt-BR/common.json
+++ b/DigitalHumanWeb/locales/pt-BR/common.json
@@ -9,15 +9,79 @@
"title": "Bem-vindo para experimentar {{name}}"
}
},
- "appInitializing": "Aplicativo iniciando...",
+ "appLoading": {
+ "appIdle": "Preparando para iniciar",
+ "appInitializing": "Iniciando o aplicativo...",
+ "failed": "Desculpe, a inicialização do aplicativo falhou. Por favor, verifique os detalhes para solucionar o problema.",
+ "finished": "Inicialização do banco de dados concluída",
+ "goToChat": "Carregando página de conversa...",
+ "initAuth": "Inicializando serviço de autenticação...",
+ "initUser": "Inicializando estado do usuário...",
+ "initializing": "Inicializando banco de dados PGlite...",
+ "loadingDependencies": "Inicializando dependências...",
+ "loadingWasm": "Carregando módulo WASM...",
+ "migrating": "Executando migração de tabelas de dados...",
+ "ready": "Banco de dados pronto",
+ "showDetail": "Ver detalhes"
+ },
"autoGenerate": "Auto completar",
"autoGenerateTooltip": "Auto completar descrição do assistente com base em sugestões",
"autoGenerateTooltipDisabled": "Por favor, preencha a dica antes de usar a função de preenchimento automático",
"back": "Voltar",
"batchDelete": "Excluir em massa",
"blog": "Blog de Produtos",
+ "branching": "Criar subtópico",
+ "branchingDisable": "A funcionalidade de \"subtópico\" está disponível apenas na versão do servidor. Se precisar dessa funcionalidade, mude para o modo de implantação no servidor ou use o LobeChat Cloud.",
"cancel": "Cancelar",
"changelog": "Registro de alterações",
+ "clientDB": {
+ "autoInit": {
+ "title": "Inicializando o banco de dados PGlite"
+ },
+ "error": {
+ "desc": "Lamentamos, ocorreu uma exceção durante o processo de inicialização do banco de dados Pglite. Por favor, clique no botão para tentar novamente. Se o erro persistir após várias tentativas, por favor <1>envie um problema1> e nós iremos ajudá-lo a resolver o quanto antes",
+ "detail": "Causa do erro: [{{type}}] {{message}}. Detalhes abaixo:",
+ "retry": "Tentar Novamente",
+ "title": "Falha na inicialização do banco de dados"
+ },
+ "initing": {
+ "error": "Ocorreu um erro, por favor tente novamente",
+ "idle": "Aguardando inicialização...",
+ "initializing": "Inicializando...",
+ "loadingDependencies": "Carregando dependências...",
+ "loadingWasmModule": "Carregando módulo WASM...",
+ "migrating": "Executando migração de tabela de dados...",
+ "ready": "Banco de dados pronto"
+ },
+ "modal": {
+ "desc": "Ative o banco de dados cliente PGlite para armazenar dados de chat de forma persistente no seu navegador e usar recursos avançados como a base de conhecimento",
+ "enable": "Ativar agora",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Consolide seu repositório de conhecimento pessoal e inicie conversas sobre ele com seu assistente de forma fácil (em breve)",
+ "title": "Suporte a conversas sobre o repositório de conhecimento, ative seu segundo cérebro"
+ },
+ "localFirst": {
+ "desc": "Os dados do chat são armazenados completamente no navegador, seus dados estão sempre sob seu controle.",
+ "title": "Prioridade local, privacidade em primeiro lugar"
+ },
+ "pglite": {
+ "desc": "Construído com base no PGlite, suporte nativo para recursos avançados de IA (busca vetorial)",
+ "title": "Nova geração de arquitetura de armazenamento de cliente"
+ }
+ },
+ "init": {
+ "desc": "Inicializando o banco de dados, pode levar de 5 a 30 segundos dependendo da rede",
+ "title": "Inicializando o banco de dados PGlite"
+ },
+ "title": "Ativar banco de dados cliente"
+ },
+ "ready": {
+ "button": "Usar agora",
+ "desc": "Pronto para uso",
+ "title": "Banco de dados PGlite pronto"
+ }
+ },
"close": "Fechar",
"contact": "Entre em contato",
"copy": "Copiar",
@@ -112,6 +176,7 @@
"en": "Inglês",
"en-US": "Inglês",
"es-ES": "Espanhol",
+ "fa-IR": "Persa",
"fi-FI": "Finlandês",
"fr-FR": "Francês",
"hi-IN": "Hindi",
@@ -153,6 +218,7 @@
"pinOff": "Desafixar",
"privacy": "Política de Privacidade",
"regenerate": "Regenerar",
+ "releaseNotes": "Notas da versão",
"rename": "Renomear",
"reset": "Redefinir",
"retry": "Tentar novamente",
@@ -209,6 +275,7 @@
},
"temp": "Temporário",
"terms": "Termos de Serviço",
+ "update": "Atualizar",
"updateAgent": "Atualizar informações do assistente",
"upgradeVersion": {
"action": "Atualizar",
@@ -219,6 +286,7 @@
"anonymousNickName": "Usuário Anônimo",
"billing": "Gerenciamento de faturas",
"cloud": "Experimente {{name}}",
+ "community": "Versão Comunitária",
"data": "Armazenamento de dados",
"defaultNickname": "Usuário da Comunidade",
"discord": "Suporte da Comunidade",
@@ -228,7 +296,6 @@
"help": "Central de Ajuda",
"moveGuide": "O botão de configurações foi movido para cá",
"plans": "Planos de Assinatura",
- "preview": "Versão de visualização",
"profile": "Gerenciamento de Conta",
"setting": "Configurações do Aplicativo",
"usages": "Estatísticas de Uso"
diff --git a/DigitalHumanWeb/locales/pt-BR/components.json b/DigitalHumanWeb/locales/pt-BR/components.json
index f2d8cb0..aa3b577 100644
--- a/DigitalHumanWeb/locales/pt-BR/components.json
+++ b/DigitalHumanWeb/locales/pt-BR/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Divisão em lotes",
"chunking": "Divisão",
"chunkingTooltip": "Divida o arquivo em vários blocos de texto e vetorize, podendo ser usado para busca semântica e diálogo sobre o arquivo",
+ "chunkingUnsupported": "Este arquivo não suporta divisão em partes.",
"confirmDelete": "Você está prestes a excluir este arquivo. Após a exclusão, ele não poderá ser recuperado. Por favor, confirme sua ação.",
"confirmDeleteMultiFiles": "Você está prestes a excluir {{count}} arquivos selecionados. Após a exclusão, eles não poderão ser recuperados. Por favor, confirme sua ação.",
"confirmRemoveFromKnowledgeBase": "Você está prestes a remover {{count}} arquivos selecionados do banco de conhecimento. Após a remoção, os arquivos ainda poderão ser visualizados em todos os arquivos. Por favor, confirme sua ação.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Voltar"
},
+ "MaxTokenSlider": {
+ "unlimited": "Ilimitado"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Modelo personalizado, por padrão, suporta chamadas de função e reconhecimento visual. Por favor, verifique a disponibilidade dessas capacidades de acordo com a situação real.",
"file": "Este modelo suporta leitura e reconhecimento de arquivos enviados.",
"functionCall": "Este modelo suporta chamadas de função.",
+ "reasoning": "Este modelo suporta pensamento profundo",
+ "search": "Este modelo suporta pesquisa online",
"tokens": "Este modelo suporta no máximo {{tokens}} tokens por sessão.",
"vision": "Este modelo suporta reconhecimento visual."
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Nenhum modelo habilitado. Por favor, vá para as configurações e habilite um.",
+ "emptyProvider": "Nenhum provedor ativado, por favor vá para as configurações para ativar",
+ "goToSettings": "Ir para as configurações",
"provider": "Fornecedor"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Devido a restrições de segurança do navegador, você precisa configurar o CORS para o Ollama antes de usá-lo normalmente.",
+ "linux": {
+ "env": "Adicione `Environment` na seção [Service] e adicione a variável de ambiente OLLAMA_ORIGINS:",
+ "reboot": "Recarregue o systemd e reinicie o Ollama",
+ "systemd": "Chame o systemd para editar o serviço ollama:"
+ },
+ "macos": "Abra o aplicativo 'Terminal', cole o seguinte comando e pressione Enter para executar",
+ "reboot": "Reinicie o serviço Ollama após a conclusão da execução",
+ "title": "Configurar o Ollama para permitir acesso CORS",
+ "windows": "No Windows, clique em 'Painel de Controle' e entre na edição das variáveis de ambiente do sistema. Crie uma nova variável de ambiente chamada 'OLLAMA_ORIGINS' para sua conta de usuário, com o valor * e clique em 'OK/Aplicar' para salvar."
+ },
+ "install": {
+ "description": "Por favor, confirme que você já ativou o Ollama. Se não tiver baixado o Ollama, visite o site oficial <1>para baixar1>",
+ "docker": "Se você preferir usar o Docker, o Ollama também oferece uma imagem oficial do Docker, que você pode puxar com o seguinte comando:",
+ "linux": {
+ "command": "Instale com o seguinte comando:",
+ "manual": "Ou, você também pode consultar o <1>Guia de Instalação Manual do Linux1> para instalar por conta própria."
+ },
+ "title": "Instalar e iniciar o aplicativo Ollama localmente",
+ "windowsTab": "Windows (versão de pré-visualização)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Pensando profundamente...",
+ "thought": "Já pensei profundamente (tempo gasto {{duration}} segundos)",
+ "thoughtWithDuration": "Já pensei profundamente"
}
}
diff --git a/DigitalHumanWeb/locales/pt-BR/discover.json b/DigitalHumanWeb/locales/pt-BR/discover.json
index 4b88bc8..6f2c6de 100644
--- a/DigitalHumanWeb/locales/pt-BR/discover.json
+++ b/DigitalHumanWeb/locales/pt-BR/discover.json
@@ -126,6 +126,10 @@
"title": "Novidade do Tópico"
},
"range": "Faixa",
+ "reasoning_effort": {
+ "desc": "Esta configuração é usada para controlar a intensidade de raciocínio do modelo antes de gerar uma resposta. Intensidade baixa prioriza a velocidade de resposta e economiza Tokens, enquanto intensidade alta oferece um raciocínio mais completo, mas consome mais Tokens e reduz a velocidade de resposta. O valor padrão é médio, equilibrando a precisão do raciocínio com a velocidade de resposta.",
+ "title": "Intensidade de Raciocínio"
+ },
"temperature": {
"desc": "Esta configuração afeta a diversidade das respostas do modelo. Valores mais baixos resultam em respostas mais previsíveis e típicas, enquanto valores mais altos incentivam respostas mais variadas e incomuns. Quando o valor é 0, o modelo sempre dá a mesma resposta para uma entrada dada.",
"title": "Aleatoriedade"
diff --git a/DigitalHumanWeb/locales/pt-BR/error.json b/DigitalHumanWeb/locales/pt-BR/error.json
index dc9479d..005c821 100644
--- a/DigitalHumanWeb/locales/pt-BR/error.json
+++ b/DigitalHumanWeb/locales/pt-BR/error.json
@@ -12,8 +12,14 @@
"retry": "Tentar novamente",
"title": "Ocorreu um problema na página.."
},
- "fetchError": "Falha na solicitação",
- "fetchErrorDetail": "Detalhes do erro",
+ "fetchError": {
+ "detail": "Detalhes do erro",
+ "title": "Solicitação falhou"
+ },
+ "loginRequired": {
+ "desc": "Você será redirecionado para a página de login em breve",
+ "title": "Por favor, faça login para usar esta função"
+ },
"notFound": {
"backHome": "Voltar para a página inicial",
"check": "Por favor, verifique se a sua URL está correta",
@@ -51,22 +57,34 @@
"431": "Desculpe, o campo de cabeçalho da sua solicitação é muito grande e o servidor não pode processá-lo",
"451": "Desculpe, por razões legais, o servidor se recusa a fornecer este recurso",
"500": "Desculpe, o servidor parece estar enfrentando algumas dificuldades e não pode concluir sua solicitação no momento. Por favor, tente novamente mais tarde",
+ "501": "Desculpe, o servidor ainda não sabe como processar este pedido. Por favor, verifique se sua operação está correta.",
"502": "Desculpe, o servidor parece estar temporariamente indisponível. Por favor, tente novamente mais tarde",
"503": "Desculpe, o servidor não pode processar sua solicitação no momento, possivelmente devido a sobrecarga ou manutenção. Por favor, tente novamente mais tarde",
"504": "Desculpe, o servidor não recebeu resposta do servidor upstream. Por favor, tente novamente mais tarde",
+ "505": "Desculpe, o servidor não suporta a versão HTTP que você está usando. Por favor, atualize e tente novamente.",
+ "506": "Desculpe, houve um problema na configuração do servidor. Por favor, entre em contato com o administrador para resolver.",
+ "507": "Desculpe, o espaço de armazenamento do servidor está insuficiente para processar seu pedido. Por favor, tente novamente mais tarde.",
+ "509": "Desculpe, a largura de banda do servidor foi esgotada. Por favor, tente novamente mais tarde.",
+ "510": "Desculpe, o servidor não suporta a funcionalidade de extensão solicitada. Por favor, entre em contato com o administrador.",
+ "524": "Desculpe, o servidor excedeu o tempo de espera enquanto aguardava uma resposta, possivelmente devido à lentidão da resposta. Por favor, tente novamente mais tarde.",
"AgentRuntimeError": "Erro de execução do modelo de linguagem Lobe, por favor, verifique as informações abaixo ou tente novamente",
+ "ConnectionCheckFailed": "A resposta da solicitação está vazia. Verifique se o endereço do proxy da API não termina com `/v1`",
+ "ExceededContextWindow": "O conteúdo da solicitação atual excede o comprimento que o modelo pode processar. Por favor, reduza a quantidade de conteúdo e tente novamente.",
"FreePlanLimit": "Atualmente, você é um usuário gratuito e não pode usar essa função. Por favor, faça upgrade para um plano pago para continuar usando.",
+ "InsufficientQuota": "Desculpe, a cota dessa chave atingiu o limite. Verifique se o saldo da conta é suficiente ou aumente a cota da chave e tente novamente.",
"InvalidAccessCode": "Senha de acesso inválida ou em branco. Por favor, insira a senha de acesso correta ou adicione uma Chave de API personalizada.",
"InvalidBedrockCredentials": "Credenciais Bedrock inválidas, por favor, verifique AccessKeyId/SecretAccessKey e tente novamente",
"InvalidClerkUser": "Desculpe, você ainda não fez login. Por favor, faça login ou registre uma conta antes de continuar.",
"InvalidGithubToken": "O Token de Acesso Pessoal do Github está incorreto ou vazio. Por favor, verifique o Token de Acesso Pessoal do Github e tente novamente.",
"InvalidOllamaArgs": "Configuração Ollama inválida, verifique a configuração do Ollama e tente novamente",
"InvalidProviderAPIKey": "{{provider}} API Key inválido ou em branco, por favor, verifique o {{provider}} API Key e tente novamente",
+ "InvalidVertexCredentials": "A autenticação do Vertex falhou, por favor verifique suas credenciais e tente novamente",
"LocationNotSupportError": "Desculpe, sua localização atual não suporta este serviço de modelo, pode ser devido a restrições geográficas ou serviço não disponível. Por favor, verifique se a localização atual suporta o uso deste serviço ou tente usar outras informações de localização.",
+ "ModelNotFound": "Desculpe, não foi possível solicitar o modelo correspondente. Isso pode ser devido ao modelo não existir ou a falta de permissões de acesso. Por favor, troque a chave da API ou ajuste as permissões de acesso e tente novamente.",
"NoOpenAIAPIKey": "A chave de API do OpenAI está em branco. Adicione uma chave de API personalizada do OpenAI",
"OllamaBizError": "Erro de negócio ao solicitar o serviço Ollama, verifique as informações a seguir ou tente novamente",
"OllamaServiceUnavailable": "O serviço Ollama não está disponível. Verifique se o Ollama está em execução corretamente ou se a configuração de CORS do Ollama está correta",
- "OpenAIBizError": "Erro no serviço OpenAI solicitado. Por favor, verifique as informações abaixo ou tente novamente.",
+ "PermissionDenied": "Desculpe, você não tem permissão para acessar este serviço. Verifique se sua chave tem as permissões necessárias.",
"PluginApiNotFound": "Desculpe, o API especificado não existe no manifesto do plugin. Verifique se o método de solicitação corresponde ao API do manifesto do plugin",
"PluginApiParamsError": "Desculpe, a validação dos parâmetros de entrada da solicitação do plugin falhou. Verifique se os parâmetros de entrada correspondem às informações de descrição do API",
"PluginFailToTransformArguments": "Desculpe, falha ao transformar os argumentos da chamada do plugin. Por favor, tente regerar a mensagem do assistente ou tente novamente com um modelo de IA de chamada de ferramentas mais robusto.",
@@ -81,8 +99,11 @@
"PluginServerError": "Erro na resposta do servidor do plugin. Verifique o arquivo de descrição do plugin, a configuração do plugin ou a implementação do servidor de acordo com as informações de erro abaixo",
"PluginSettingsInvalid": "Este plugin precisa ser configurado corretamente antes de ser usado. Verifique se sua configuração está correta",
"ProviderBizError": "Erro no serviço {{provider}} solicitado. Por favor, verifique as informações abaixo ou tente novamente.",
+ "QuotaLimitReached": "Desculpe, o uso atual de tokens ou o número de solicitações atingiu o limite de quota da chave. Por favor, aumente a quota dessa chave ou tente novamente mais tarde.",
"StreamChunkError": "Erro de análise do bloco de mensagem da solicitação em fluxo. Verifique se a interface da API atual está em conformidade com os padrões ou entre em contato com seu fornecedor de API para mais informações.",
- "SubscriptionPlanLimit": "Você atingiu o limite de sua assinatura e não pode usar essa função. Por favor, faça upgrade para um plano superior ou compre um pacote de recursos para continuar usando.",
+ "SubscriptionKeyMismatch": "Desculpe, devido a uma falha ocasional no sistema, o uso da assinatura atual está temporariamente inativo. Por favor, clique no botão abaixo para restaurar a assinatura ou entre em contato conosco por e-mail para obter suporte.",
+ "SubscriptionPlanLimit": "Seu limite de pontos de assinatura foi atingido, não é possível usar essa funcionalidade. Por favor, faça um upgrade para um plano superior ou configure a API do modelo personalizado para continuar usando.",
+ "SystemTimeNotMatchError": "Desculpe, o horário do seu sistema não coincide com o do servidor. Por favor, verifique o horário do seu sistema e tente novamente.",
"UnknownChatFetchError": "Desculpe, ocorreu um erro desconhecido na solicitação. Por favor, verifique as informações abaixo ou tente novamente."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/pt-BR/metadata.json b/DigitalHumanWeb/locales/pt-BR/metadata.json
index ff20720..adceb37 100644
--- a/DigitalHumanWeb/locales/pt-BR/metadata.json
+++ b/DigitalHumanWeb/locales/pt-BR/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Acompanhe as novas funcionalidades e melhorias do {{appName}}",
+ "title": "Registro de Atualizações"
+ },
"chat": {
"description": "{{appName}} traz a você a melhor experiência de uso do ChatGPT, Claude, Gemini e OLLaMA WebUI",
"title": "{{appName}}: Ferramenta de eficiência pessoal em IA, dê a si mesmo um cérebro mais inteligente"
diff --git a/DigitalHumanWeb/locales/pt-BR/modelProvider.json b/DigitalHumanWeb/locales/pt-BR/modelProvider.json
index 2fda52a..d5f133c 100644
--- a/DigitalHumanWeb/locales/pt-BR/modelProvider.json
+++ b/DigitalHumanWeb/locales/pt-BR/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Versão da API do Azure, seguindo o formato AAAA-MM-DD. Consulte a [versão mais recente](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Obter lista",
+ "title": "Versão da API do Azure"
+ },
+ "endpoint": {
+ "desc": "Encontre o ponto de extremidade de inferência do modelo do Azure AI na visão geral do projeto Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Ponto de extremidade do Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Encontre a chave da API na visão geral do projeto Azure AI",
+ "placeholder": "Chave do Azure",
+ "title": "Chave"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Insira o AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "Usar informações de autenticação Bedrock personalizadas"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Insira o Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Insira o ID da conta do Cloudflare ou o endereço da API personalizado",
+ "placeholder": "ID da conta do Cloudflare / URL da API personalizada",
+ "title": "ID da conta do Cloudflare / Endereço da API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Por favor, insira sua API Key",
+ "title": "API Key"
+ },
+ "basicTitle": "Informações Básicas",
+ "configTitle": "Informações de Configuração",
+ "confirm": "Criar Novo",
+ "createSuccess": "Criação bem-sucedida",
+ "description": {
+ "placeholder": "Descrição do provedor (opcional)",
+ "title": "Descrição do Provedor"
+ },
+ "id": {
+ "desc": "Identificador único do provedor de serviços, não pode ser modificado após a criação",
+ "format": "Só pode conter números, letras minúsculas, hífens (-) e sublinhados (_) ",
+ "placeholder": "Sugestão: tudo em minúsculas, por exemplo, openai, não poderá ser modificado após a criação",
+ "required": "Por favor, insira o ID do provedor",
+ "title": "ID do Provedor"
+ },
+ "logo": {
+ "required": "Por favor, envie um logo correto do provedor",
+ "title": "Logo do Provedor"
+ },
+ "name": {
+ "placeholder": "Por favor, insira o nome de exibição do provedor",
+ "required": "Por favor, insira o nome do provedor",
+ "title": "Nome do Provedor"
+ },
+ "proxyUrl": {
+ "required": "Por favor, insira o endereço do proxy",
+ "title": "Endereço do Proxy"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Por favor, selecione o tipo de SDK",
+ "title": "Formato da Requisição"
+ },
+ "title": "Criar Provedor de AI Personalizado"
+ },
"github": {
"personalAccessToken": {
"desc": "Insira seu PAT do Github, clique [aqui](https://github.com/settings/tokens) para criar",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Insira seu Token do HuggingFace, clique [aqui](https://huggingface.co/settings/tokens) para criar",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "Token do HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Fornecedor não habilitado",
+ "enabled": "Fornecedor habilitado"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Adicionar Provedor Personalizado",
+ "all": "Todos",
+ "list": {
+ "disabled": "Desativado",
+ "enabled": "Ativado"
+ },
+ "notFound": "Nenhum resultado encontrado",
+ "searchProviders": "Pesquisar Provedores...",
+ "sort": "Ordenação Personalizada"
+ },
"ollama": {
"checker": {
"desc": "Teste se o endereço do proxy está corretamente preenchido",
@@ -69,39 +163,15 @@
"title": "Nomes dos Modelos Personalizados"
},
"download": {
- "desc": "Ollama is downloading the model. Please do not close this page. It will resume from where it left off if you restart the download.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama está baixando este modelo, por favor, evite fechar esta página. O download será retomado do ponto em que parou.",
+ "remainingTime": "Tempo restante",
+ "speed": "Velocidade de download",
+ "title": "Baixando o modelo {{model}} "
},
"endpoint": {
- "desc": "Insira o endereço do proxy de interface da Ollama, se não foi especificado localmente, pode deixar em branco",
+ "desc": "Deve incluir http(s)://, pode deixar em branco se não houver especificação local adicional",
"title": "Endereço do Proxy de Interface"
},
- "setup": {
- "cors": {
- "description": "Devido às restrições de segurança do navegador, você precisa configurar o Ollama para permitir o acesso entre domínios.",
- "linux": {
- "env": "Sob a seção [Service], adicione `Environment` e inclua a variável de ambiente OLLAMA_ORIGINS:",
- "reboot": "Recarregue o systemd e reinicie o Ollama.",
- "systemd": "Chame o systemd para editar o serviço ollama:"
- },
- "macos": "Abra o aplicativo 'Terminal', cole o comando abaixo e pressione Enter para executar:",
- "reboot": "Após a conclusão, reinicie o serviço Ollama.",
- "title": "Configurar o Ollama para permitir acesso entre domínios",
- "windows": "No Windows, acesse o 'Painel de Controle' e edite as variáveis de ambiente do sistema. Crie uma nova variável de ambiente chamada 'OLLAMA_ORIGINS' para sua conta de usuário, com o valor '*', e clique em 'OK/Aplicar' para salvar."
- },
- "install": {
- "description": "Certifique-se de que você ativou o Ollama. Se ainda não o fez, baixe o Ollama no site oficial <1>aqui1>.",
- "docker": "Se preferir usar o Docker, o Ollama também oferece uma imagem oficial. Você pode puxá-la com o comando:",
- "linux": {
- "command": "Instale com o comando a seguir:",
- "manual": "Ou, se preferir, consulte o <1>Guia de Instalação Manual do Linux1> para instalar manualmente."
- },
- "title": "Instale e inicie o aplicativo Ollama localmente",
- "windowsTab": "Windows (Versão de Visualização)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Cancel Download",
@@ -112,6 +182,156 @@
"title": "Download specified Ollama model"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "Sua chave e o endereço do proxy serão criptografados usando o algoritmo de criptografia <1>AES-GCM1>",
+ "apiKey": {
+ "desc": "Por favor, insira sua {{name}} API Key",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "Deve incluir http(s)://",
+ "invalid": "Por favor, insira uma URL válida",
+ "placeholder": "https://seu-endereco-proxy.com/v1",
+ "title": "Endereço do Proxy API"
+ },
+ "checker": {
+ "button": "Verificar",
+ "desc": "Teste se a API Key e o endereço do proxy estão preenchidos corretamente",
+ "pass": "Verificação bem-sucedida",
+ "title": "Verificação de Conectividade"
+ },
+ "fetchOnClient": {
+ "desc": "O modo de requisição do cliente iniciará a requisição de sessão diretamente do navegador, podendo aumentar a velocidade de resposta",
+ "title": "Usar Modo de Requisição do Cliente"
+ },
+ "helpDoc": "Tutorial de Configuração",
+ "waitingForMore": "Mais modelos estão <1>planejados para integração1>, fique atento"
+ },
+ "createNew": {
+ "title": "Criar Modelo de AI Personalizado"
+ },
+ "item": {
+ "config": "Configurar Modelo",
+ "customModelCards": {
+ "addNew": "Criar e adicionar modelo {{id}}",
+ "confirmDelete": "Você está prestes a excluir este modelo personalizado, após a exclusão não poderá ser recuperado, por favor, proceda com cautela."
+ },
+ "delete": {
+ "confirm": "Confirmar exclusão do modelo {{displayName}}?",
+ "success": "Exclusão bem-sucedida",
+ "title": "Excluir Modelo"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Campo solicitado na Azure OpenAI",
+ "placeholder": "Por favor, insira o nome de implantação do modelo na Azure",
+ "title": "Nome de Implantação do Modelo"
+ },
+ "deployName": {
+ "extra": "Este campo será usado como ID do modelo ao enviar a solicitação",
+ "placeholder": "Insira o nome ou ID real do modelo implantado",
+ "title": "Nome da implantação do modelo"
+ },
+ "displayName": {
+ "placeholder": "Por favor, insira o nome de exibição do modelo, por exemplo, ChatGPT, GPT-4, etc.",
+ "title": "Nome de Exibição do Modelo"
+ },
+ "files": {
+ "extra": "A implementação atual de upload de arquivos é apenas uma solução temporária, limitada a tentativas pessoais. A capacidade completa de upload de arquivos será implementada posteriormente.",
+ "title": "Suporte a Upload de Arquivos"
+ },
+ "functionCall": {
+ "extra": "Esta configuração ativará apenas a capacidade do modelo de usar ferramentas, permitindo assim a adição de plugins do tipo ferramenta. No entanto, se o uso real das ferramentas é suportado depende inteiramente do modelo em si, teste a usabilidade por conta própria.",
+ "title": "Suporte ao uso de ferramentas"
+ },
+ "id": {
+ "extra": "Não pode ser modificado após a criação, será usado como ID do modelo ao chamar a IA",
+ "placeholder": "Insira o ID do modelo, por exemplo, gpt-4o ou claude-3.5-sonnet",
+ "title": "ID do Modelo"
+ },
+ "modalTitle": "Configuração do Modelo Personalizado",
+ "reasoning": {
+ "extra": "Esta configuração ativará apenas a capacidade de pensamento profundo do modelo, e o efeito específico depende totalmente do próprio modelo. Por favor, teste se este modelo possui a capacidade de pensamento profundo utilizável.",
+ "title": "Suporte a Pensamento Profundo"
+ },
+ "tokens": {
+ "extra": "Configurar o número máximo de tokens suportados pelo modelo",
+ "title": "Janela de contexto máxima",
+ "unlimited": "Ilimitado"
+ },
+ "vision": {
+ "extra": "Esta configuração apenas habilitará a configuração de upload de imagens no aplicativo, se o reconhecimento for suportado depende do modelo em si, teste a capacidade de reconhecimento visual desse modelo.",
+ "title": "Suporte a Reconhecimento Visual"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/imagem",
+ "inputCharts": "${{amount}}/M caracteres",
+ "inputMinutes": "${{amount}}/minuto",
+ "inputTokens": "Entrada ${{amount}}/M",
+ "outputTokens": "Saída ${{amount}}/M"
+ },
+ "releasedAt": "Lançado em {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Adicionar Modelo",
+ "disabled": "Não habilitado",
+ "disabledActions": {
+ "showMore": "Mostrar tudo"
+ },
+ "empty": {
+ "desc": "Por favor, crie um modelo personalizado ou importe um modelo para começar a usar.",
+ "title": "Nenhum modelo disponível"
+ },
+ "enabled": "Habilitado",
+ "enabledActions": {
+ "disableAll": "Desabilitar todos",
+ "enableAll": "Habilitar todos",
+ "sort": "Ordenar modelos personalizados"
+ },
+ "enabledEmpty": "Nenhum modelo habilitado no momento, por favor habilite os modelos desejados na lista abaixo~",
+ "fetcher": {
+ "clear": "Limpar modelos obtidos",
+ "fetch": "Obter lista de modelos",
+ "fetching": "Obtendo lista de modelos...",
+ "latestTime": "Última atualização: {{time}}",
+ "noLatestTime": "Lista ainda não obtida"
+ },
+ "resetAll": {
+ "conform": "Você tem certeza de que deseja redefinir todas as modificações do modelo atual? Após a redefinição, a lista de modelos atuais voltará ao estado padrão",
+ "success": "Redefinição bem-sucedida",
+ "title": "Redefinir todas as modificações"
+ },
+ "search": "Pesquisar modelos...",
+ "searchResult": "Encontrados {{count}} modelos",
+ "title": "Lista de Modelos",
+ "total": "Um total de {{count}} modelos disponíveis"
+ },
+ "searchNotFound": "Nenhum resultado encontrado"
+ },
+ "sortModal": {
+ "success": "Ordenação atualizada com sucesso",
+ "title": "Ordenação Personalizada",
+ "update": "Atualizar"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Você está prestes a excluir este provedor de AI, após a exclusão não poderá ser recuperado, deseja confirmar a exclusão?",
+ "deleteSuccess": "Exclusão bem-sucedida",
+ "tooltip": "Atualizar configurações básicas do provedor",
+ "updateSuccess": "Atualização bem-sucedida"
+ },
+ "updateCustomAiProvider": {
+ "title": "Atualizar configuração do provedor de IA personalizado"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Insira suas Chaves do Vertex AI",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Chaves do Vertex AI"
+ }
+ },
"zeroone": {
"title": "01.AI Zero e Um"
},
diff --git a/DigitalHumanWeb/locales/pt-BR/models.json b/DigitalHumanWeb/locales/pt-BR/models.json
index a496c8d..7033a05 100644
--- a/DigitalHumanWeb/locales/pt-BR/models.json
+++ b/DigitalHumanWeb/locales/pt-BR/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, com um rico conjunto de amostras de treinamento, oferece desempenho superior em aplicações industriais."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat é uma variante da série Yi-1.5, pertencente aos modelos de chat de código aberto. Yi-1.5 é uma versão aprimorada do Yi, tendo sido continuamente pré-treinada em 500B de corpus de alta qualidade e ajustada em mais de 3M de amostras diversificadas. Em comparação com o Yi, o Yi-1.5 apresenta desempenho superior em codificação, matemática, raciocínio e capacidade de seguir instruções, mantendo uma excelente compreensão de linguagem, raciocínio de senso comum e compreensão de leitura. Este modelo possui versões com comprimento de contexto de 4K, 16K e 32K, com um total de pré-treinamento de 3.6T de tokens."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B suporta 16K Tokens, oferecendo capacidade de geração de linguagem eficiente e fluida."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero Um, o mais recente modelo de ajuste fino de código aberto, com 34 bilhões de parâmetros, suporta múltiplos cenários de diálogo, com dados de treinamento de alta qualidade, alinhados às preferências humanas."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero Um, o mais recente modelo de ajuste fino de código aberto, com 9 bilhões de parâmetros, suporta múltiplos cenários de diálogo, com dados de treinamento de alta qualidade, alinhados às preferências humanas."
+ },
"360gpt-pro": {
"description": "360GPT Pro, como um membro importante da série de modelos de IA da 360, atende a diversas aplicações de linguagem natural com sua capacidade eficiente de processamento de texto, suportando compreensão de longos textos e diálogos em múltiplas rodadas."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K enfatiza segurança semântica e responsabilidade, projetado especificamente para cenários de aplicação com altas exigências de segurança de conteúdo, garantindo precisão e robustez na experiência do usuário."
},
+ "360gpt2-o1": {
+ "description": "O 360gpt2-o1 utiliza busca em árvore para construir cadeias de pensamento e introduz um mecanismo de reflexão, sendo treinado com aprendizado por reforço, o modelo possui a capacidade de auto-reflexão e correção de erros."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro é um modelo avançado de processamento de linguagem natural lançado pela 360, com excelente capacidade de geração e compreensão de texto, destacando-se especialmente na geração e criação de conteúdo, capaz de lidar com tarefas complexas de conversão de linguagem e interpretação de papéis."
},
+ "360zhinao2-o1": {
+ "description": "O 360zhinao2-o1 utiliza busca em árvore para construir cadeias de pensamento e introduz um mecanismo de reflexão, utilizando aprendizado por reforço para treinar, permitindo que o modelo tenha a capacidade de auto-reflexão e correção de erros."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra é a versão mais poderosa da série de grandes modelos Xinghuo, que, ao atualizar a conexão de busca online, melhora a capacidade de compreensão e resumo de conteúdo textual. É uma solução abrangente para aumentar a produtividade no trabalho e responder com precisão às demandas, sendo um produto inteligente líder na indústria."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "O modelo é o melhor do país, superando modelos estrangeiros em tarefas em chinês, como enciclopédias, textos longos e criação de conteúdo. Também possui capacidades multimodais líderes na indústria, com desempenho excepcional em várias avaliações de referência."
},
+ "Baichuan4-Air": {
+ "description": "Modelo com a melhor capacidade do país, superando modelos estrangeiros em tarefas em chinês como enciclopédia, textos longos e criação de conteúdo. Também possui capacidades multimodais líderes da indústria, com excelente desempenho em várias avaliações de referência."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Modelo com a melhor capacidade do país, superando modelos estrangeiros em tarefas em chinês como enciclopédia, textos longos e criação de conteúdo. Também possui capacidades multimodais líderes da indústria, com excelente desempenho em várias avaliações de referência."
+ },
+ "DeepSeek-R1": {
+ "description": "LLM eficiente de ponta, especializado em raciocínio, matemática e programação."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 — o modelo maior e mais inteligente do conjunto DeepSeek — foi destilado para a arquitetura Llama 70B. Com base em testes de benchmark e avaliações humanas, este modelo é mais inteligente do que o Llama 70B original, destacando-se especialmente em tarefas que exigem precisão matemática e factual."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Modelo de destilação DeepSeek-R1 baseado no Qwen2.5-Math-1.5B, otimizado para desempenho de inferência através de aprendizado por reforço e dados de inicialização fria, modelo de código aberto que redefine os padrões de múltiplas tarefas."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Modelo de destilação DeepSeek-R1 baseado no Qwen2.5-14B, otimizado para desempenho de inferência através de aprendizado por reforço e dados de inicialização fria, modelo de código aberto que redefine os padrões de múltiplas tarefas."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "A série DeepSeek-R1 otimiza o desempenho de inferência através de aprendizado por reforço e dados de inicialização fria, modelo de código aberto que redefine os padrões de múltiplas tarefas, superando o nível do OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Modelo de destilação DeepSeek-R1 baseado no Qwen2.5-Math-7B, otimizado para desempenho de inferência através de aprendizado por reforço e dados de inicialização fria, modelo de código aberto que redefine os padrões de múltiplas tarefas."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro é um modelo multimodal de grande porte totalmente atualizado, que suporta reconhecimento de imagens em qualquer resolução e proporções extremas, melhorando a capacidade de raciocínio visual, reconhecimento de documentos, compreensão de informações detalhadas e seguimento de instruções."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite possui uma velocidade de resposta excepcional e uma melhor relação custo-benefício, oferecendo opções mais flexíveis para diferentes cenários dos clientes. Suporta raciocínio e ajuste fino em janelas de contexto de 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite possui uma velocidade de resposta excepcional e uma melhor relação custo-benefício, oferecendo opções mais flexíveis para diferentes cenários dos clientes. Suporta raciocínio e ajuste fino em janelas de contexto de 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite possui uma velocidade de resposta excepcional e uma melhor relação custo-benefício, oferecendo opções mais flexíveis para diferentes cenários dos clientes. Suporta raciocínio e ajuste fino em janelas de contexto de 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "O modelo principal com o melhor desempenho, adequado para tarefas complexas, apresentando excelentes resultados em cenários como perguntas e respostas, resumos, criação, classificação de texto e interpretação de papéis. Suporta raciocínio e ajuste fino em janelas de contexto de 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "O modelo principal com o melhor desempenho, adequado para lidar com tarefas complexas, apresentando bons resultados em cenários como perguntas e respostas de referência, resumos, criação, classificação de texto e interpretação de papéis. Suporta raciocínio e ajuste fino com janelas de contexto de 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "O modelo principal com o melhor desempenho, adequado para tarefas complexas, apresentando excelentes resultados em cenários como perguntas e respostas, resumos, criação, classificação de texto e interpretação de papéis. Suporta raciocínio e ajuste fino em janelas de contexto de 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "O modelo principal com o melhor desempenho, adequado para tarefas complexas, apresentando excelentes resultados em cenários como perguntas e respostas, resumos, criação, classificação de texto e interpretação de papéis. Suporta raciocínio e ajuste fino em janelas de contexto de 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "O modelo Doubao-vision é um modelo multimodal de grande porte lançado pela Doubao, com poderosas capacidades de compreensão e raciocínio de imagens, além de uma compreensão precisa de instruções. O modelo demonstrou um desempenho robusto em extração de informações textuais de imagens e tarefas de raciocínio baseadas em imagens, podendo ser aplicado em tarefas de perguntas e respostas visuais mais complexas e abrangentes."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "O modelo Doubao-vision é um modelo multimodal de grande porte lançado pela Doubao, com poderosas capacidades de compreensão e raciocínio de imagens, além de uma compreensão precisa de instruções. O modelo demonstrou um desempenho robusto em extração de informações textuais de imagens e tarefas de raciocínio baseadas em imagens, podendo ser aplicado em tarefas de perguntas e respostas visuais mais complexas e abrangentes."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Modelo de linguagem de grande escala desenvolvido pela Baidu, cobrindo uma vasta quantidade de dados em chinês e inglês, com poderosas capacidades gerais, capaz de atender à maioria das demandas de perguntas e respostas em diálogos, geração de conteúdo e aplicações de plugins; suporta integração automática com o plugin de busca da Baidu, garantindo a atualidade das informações nas respostas."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Modelo de linguagem de grande escala desenvolvido pela Baidu, cobrindo uma vasta quantidade de dados em chinês e inglês, com poderosas capacidades gerais, capaz de atender à maioria das demandas de perguntas e respostas em diálogos, geração de conteúdo e aplicações de plugins; suporta integração automática com o plugin de busca da Baidu, garantindo a atualidade das informações nas respostas."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Modelo de linguagem de grande escala desenvolvido pela Baidu, cobrindo uma vasta quantidade de dados em chinês e inglês, com poderosas capacidades gerais, capaz de atender à maioria das demandas de perguntas e respostas em diálogos, geração de conteúdo e aplicações de plugins; suporta integração automática com o plugin de busca da Baidu, garantindo a atualidade das informações nas respostas."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Modelo de linguagem ultra grande escala desenvolvido pela Baidu, que em comparação com o ERNIE 3.5, apresenta uma atualização completa nas capacidades do modelo, amplamente aplicável em cenários de tarefas complexas em diversas áreas; suporta integração automática com o plugin de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Modelo de linguagem ultra grande escala desenvolvido pela Baidu, que em comparação com o ERNIE 3.5, apresenta uma atualização completa nas capacidades do modelo, amplamente aplicável em cenários de tarefas complexas em diversas áreas; suporta integração automática com o plugin de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Modelo de linguagem de última geração desenvolvido pela Baidu, com desempenho excepcional em uma ampla gama de cenários de tarefas complexas; suporta integração automática com plugins de busca da Baidu, garantindo a relevância da informação nas respostas. Supera o desempenho do ERNIE 4.0."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Modelo de linguagem ultra grande escala desenvolvido pela Baidu, com desempenho excepcional em resultados gerais, amplamente aplicável em cenários de tarefas complexas em diversas áreas; suporta integração automática com o plugin de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas. Em comparação com o ERNIE 4.0, apresenta desempenho superior."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Modelo de linguagem vertical desenvolvido pela Baidu, adequado para aplicações como NPCs em jogos, diálogos de atendimento ao cliente e interpretação de personagens em diálogos, com estilos de personagem mais distintos e consistentes, maior capacidade de seguir instruções e desempenho de inferência superior."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Modelo de linguagem leve desenvolvido pela Baidu, que combina excelente desempenho do modelo com eficiência de inferência, apresentando resultados superiores ao ERNIE Lite, adequado para uso em inferência com placas de aceleração de IA de baixo poder computacional."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Modelo de linguagem de alto desempenho desenvolvido pela Baidu, lançado em 2024, com capacidades gerais excepcionais, adequado como modelo base para ajuste fino, melhorando o tratamento de problemas em cenários específicos, enquanto mantém excelente desempenho de inferência."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Modelo de linguagem de alto desempenho desenvolvido pela Baidu, lançado em 2024, com capacidades gerais excepcionais, apresentando resultados superiores ao ERNIE Speed, adequado como modelo base para ajuste fino, melhorando o tratamento de problemas em cenários específicos, enquanto mantém excelente desempenho de inferência."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) é um modelo inovador, adequado para aplicações em múltiplas áreas e tarefas complexas."
},
- "Max-32k": {
- "description": "O Spark Max 32K possui uma grande capacidade de processamento de contexto, com uma compreensão e raciocínio lógico mais robustos, suportando entradas de texto de 32K tokens, adequado para leitura de documentos longos, perguntas e respostas sobre conhecimento privado e outros cenários."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B é um poderoso modelo de linguagem visual, que suporta processamento multimodal de imagens e textos, capaz de identificar com precisão o conteúdo da imagem e gerar descrições ou respostas relevantes."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B é um poderoso modelo de linguagem visual, que suporta processamento multimodal de imagens e textos, capaz de identificar com precisão o conteúdo da imagem e gerar descrições ou respostas relevantes."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Capacidade de raciocínio de imagem excepcional em imagens de alta resolução, adequada para aplicações de compreensão visual."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Capacidade avançada de raciocínio de imagem para aplicações de agentes de compreensão visual."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct é um dos mais recentes modelos de linguagem de grande escala lançados pela Alibaba Cloud. Este modelo de 72B apresenta melhorias significativas em áreas como codificação e matemática. O modelo também oferece suporte multilíngue, abrangendo mais de 29 idiomas, incluindo chinês e inglês. O modelo teve melhorias significativas em seguir instruções, entender dados estruturados e gerar saídas estruturadas (especialmente JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct é um dos mais recentes modelos de linguagem de grande escala lançados pela Alibaba Cloud. Este modelo de 7B apresenta melhorias significativas em áreas como codificação e matemática. O modelo também oferece suporte multilíngue, abrangendo mais de 29 idiomas, incluindo chinês e inglês. O modelo teve melhorias significativas em seguir instruções, entender dados estruturados e gerar saídas estruturadas (especialmente JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Modelo de texto ajustado para instruções Llama 3.1, otimizado para casos de uso de diálogos multilíngues, apresentando desempenho superior em muitos modelos de chat de código aberto e fechados em benchmarks da indústria."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO é uma fusão de múltiplos modelos altamente flexível, projetada para oferecer uma experiência criativa excepcional."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Modelo de texto ajustado para instruções Llama 3.1, otimizado para casos de uso de diálogos multilíngues, apresentando desempenho superior em muitos modelos de chat de código aberto e fechados em benchmarks da indústria."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Modelo de texto ajustado para instruções Llama 3.1, otimizado para casos de uso de diálogos multilíngues, apresentando desempenho superior em muitos modelos de chat de código aberto e fechados em benchmarks da indústria."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Modelo de linguagem pequeno de ponta, com compreensão de linguagem, excelente capacidade de raciocínio e geração de texto."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Modelo de linguagem pequeno de ponta, com compreensão de linguagem, excelente capacidade de raciocínio e geração de texto."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 é o modelo de linguagem de código aberto multilíngue mais avançado da série Llama, oferecendo desempenho comparável ao modelo de 405B a um custo extremamente baixo. Baseado na estrutura Transformer, e aprimorado por meio de ajuste fino supervisionado (SFT) e aprendizado por reforço com feedback humano (RLHF) para aumentar a utilidade e a segurança. Sua versão ajustada para instruções é otimizada para diálogos multilíngues, superando muitos modelos de chat de código aberto e fechados em vários benchmarks da indústria. A data limite de conhecimento é dezembro de 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "Na série de modelos MiniMax-01, fizemos inovações ousadas: pela primeira vez, implementamos em larga escala um mecanismo de atenção linear, tornando a arquitetura Transformer tradicional não mais a única opção. Este modelo possui um total de 456 bilhões de parâmetros, com 45,9 bilhões ativados em uma única vez. O desempenho geral do modelo é comparável aos melhores modelos internacionais, enquanto lida eficientemente com contextos de até 4 milhões de tokens, 32 vezes mais que o GPT-4o e 20 vezes mais que o Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) é um modelo de instrução de alta precisão, adequado para cálculos complexos."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) oferece saídas de linguagem otimizadas e diversas possibilidades de aplicação."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Atualização do modelo Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 demonstrou desempenho excepcional em diversas tarefas de linguagem visual, incluindo compreensão de documentos e gráficos, compreensão de texto em cena, OCR, e resolução de problemas científicos e matemáticos."
},
"Phi-3-medium-128k-instruct": {
"description": "Mesmo modelo Phi-3-medium, mas com um tamanho de contexto maior para RAG ou prompting de poucos exemplos."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Um modelo de 7B parâmetros, que apresenta melhor qualidade do que o Phi-3-mini, com foco em dados densos de raciocínio de alta qualidade."
},
- "Pro-128k": {
- "description": "Spark Pro-128K possui capacidade de processamento de contexto extremamente grande, capaz de lidar com até 128K de informações de contexto, especialmente adequado para análise completa e processamento de associações lógicas de longo prazo em conteúdos longos, podendo fornecer lógica fluida e consistente e suporte a diversas citações em comunicações textuais complexas."
+ "Phi-3.5-mini-instruct": {
+ "description": "Versão atualizada do modelo Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Versão atualizada do modelo Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 demonstrou desempenho excepcional em diversas tarefas de linguagem visual, incluindo compreensão de documentos e gráficos, compreensão de texto em cena, OCR, e resolução de problemas científicos e matemáticos."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct é um modelo de linguagem de grande escala com ajuste fino para instruções na série Qwen2, com um tamanho de parâmetro de 1.5B. Este modelo é baseado na arquitetura Transformer, utilizando funções de ativação SwiGLU, viés de atenção QKV e atenção de consulta em grupo. Ele se destaca em compreensão de linguagem, geração, capacidade multilíngue, codificação, matemática e raciocínio em vários benchmarks, superando a maioria dos modelos de código aberto. Em comparação com o Qwen1.5-1.8B-Chat, o Qwen2-1.5B-Instruct mostrou melhorias significativas de desempenho em testes como MMLU, HumanEval, GSM8K, C-Eval e IFEval, apesar de ter um número de parâmetros ligeiramente menor."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct é um modelo de linguagem de grande escala com ajuste fino para instruções na série Qwen2, com um tamanho de parâmetro de 7B. Este modelo é baseado na arquitetura Transformer, utilizando funções de ativação SwiGLU, viés de atenção QKV e atenção de consulta em grupo. Ele é capaz de lidar com entradas em larga escala. O modelo se destaca em compreensão de linguagem, geração, capacidade multilíngue, codificação, matemática e raciocínio em vários benchmarks, superando a maioria dos modelos de código aberto e demonstrando competitividade comparável a modelos proprietários em algumas tarefas. O Qwen2-7B-Instruct superou o Qwen1.5-7B-Chat em várias avaliações, mostrando melhorias significativas de desempenho."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL é a versão mais recente do modelo Qwen-VL, alcançando desempenho de ponta em testes de compreensão visual."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct é um dos mais recentes modelos de linguagem de grande escala lançados pela Alibaba Cloud. Este modelo de 7B apresenta melhorias significativas em áreas como codificação e matemática. O modelo também oferece suporte multilíngue, abrangendo mais de 29 idiomas, incluindo chinês e inglês. O modelo teve melhorias significativas em seguir instruções, entender dados estruturados e gerar saídas estruturadas (especialmente JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct é a versão mais recente da série de modelos de linguagem de grande escala específicos para código lançada pela Alibaba Cloud. Este modelo, baseado no Qwen2.5, foi treinado com 55 trilhões de tokens, melhorando significativamente a capacidade de geração, raciocínio e correção de código. Ele não apenas aprimora a capacidade de codificação, mas também mantém as vantagens em matemática e habilidades gerais. O modelo fornece uma base mais abrangente para aplicações práticas, como agentes de código."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat é a versão de código aberto da série de modelos pré-treinados GLM-4 lançada pela Zhipu AI. Este modelo se destaca em semântica, matemática, raciocínio, código e conhecimento. Além de suportar diálogos de múltiplas rodadas, o GLM-4-9B-Chat também possui recursos avançados como navegação na web, execução de código, chamadas de ferramentas personalizadas (Function Call) e raciocínio de longo texto. O modelo suporta 26 idiomas, incluindo chinês, inglês, japonês, coreano e alemão. Em vários benchmarks, o GLM-4-9B-Chat demonstrou desempenho excepcional, como AlignBench-v2, MT-Bench, MMLU e C-Eval. O modelo suporta um comprimento de contexto máximo de 128K, adequado para pesquisa acadêmica e aplicações comerciais."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 é um modelo de inferência impulsionado por aprendizado por reforço (RL), que resolve problemas de repetitividade e legibilidade no modelo. Antes do RL, o DeepSeek-R1 introduziu dados de inicialização a frio, otimizando ainda mais o desempenho de inferência. Ele se compara ao OpenAI-o1 em tarefas matemáticas, de código e de inferência, e melhora o desempenho geral por meio de métodos de treinamento cuidadosamente projetados."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 é um modelo de linguagem com 671 bilhões de parâmetros, utilizando uma arquitetura de especialistas mistos (MoE) com atenção potencial de múltiplas cabeças (MLA) e uma estratégia de balanceamento de carga sem perda auxiliar, otimizando a eficiência de inferência e treinamento. Pré-treinado em 14,8 trilhões de tokens de alta qualidade, e ajustado por supervisão e aprendizado por reforço, o DeepSeek-V3 supera outros modelos de código aberto, aproximando-se de modelos fechados líderes."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma é uma das séries de modelos abertos mais avançadas e leves desenvolvidas pelo Google. É um modelo de linguagem em larga escala apenas de decodificação, que suporta inglês, oferecendo pesos abertos, variantes pré-treinadas e variantes de ajuste fino para instruções. O modelo Gemma é adequado para várias tarefas de geração de texto, incluindo perguntas e respostas, resumos e raciocínio. Este modelo de 9B foi treinado com 80 trilhões de tokens. Seu tamanho relativamente pequeno permite que seja implantado em ambientes com recursos limitados, como laptops, desktops ou sua própria infraestrutura em nuvem, permitindo que mais pessoas acessem modelos de IA de ponta e promovam inovações."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 é uma família de modelos de linguagem em larga escala multilíngue desenvolvida pela Meta, incluindo variantes pré-treinadas e de ajuste fino para instruções com tamanhos de parâmetros de 8B, 70B e 405B. Este modelo de 8B foi otimizado para cenários de diálogo multilíngue e se destacou em vários benchmarks da indústria. O treinamento do modelo utilizou mais de 150 trilhões de tokens de dados públicos e empregou técnicas como ajuste fino supervisionado e aprendizado por reforço com feedback humano para melhorar a utilidade e segurança do modelo. Llama 3.1 suporta geração de texto e geração de código, com data de corte de conhecimento em dezembro de 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "O QwQ-32B-Preview é um modelo de processamento de linguagem natural inovador, capaz de lidar eficientemente com tarefas complexas de geração de diálogos e compreensão de contexto."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview é um modelo de pesquisa desenvolvido pela equipe Qwen, focado em capacidades de raciocínio visual, apresentando vantagens únicas na compreensão de cenários complexos e na resolução de problemas matemáticos relacionados à visão."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Como uma versão de teste do Qwen2, Qwen1.5 utiliza dados em larga escala para alcançar funcionalidades de diálogo mais precisas."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ é o modelo de inferência da série Qwen. Em comparação com modelos tradicionais de ajuste de instruções, o QwQ possui habilidades de raciocínio e inferência, permitindo um desempenho significativamente melhorado em tarefas de downstream, especialmente na resolução de problemas difíceis. O QwQ-32B é um modelo de inferência de médio porte, capaz de obter um desempenho competitivo em comparação com modelos de inferência de ponta, como DeepSeek-R1 e o1-mini. Este modelo utiliza tecnologias como RoPE, SwiGLU, RMSNorm e viés de atenção QKV, apresentando uma estrutura de rede de 64 camadas e 40 cabeças de atenção Q (sendo KV 8 no GQA)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) oferece respostas rápidas e capacidade de diálogo natural, adequado para ambientes multilíngues."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview é o mais recente modelo de pesquisa experimental da Qwen, focado em melhorar a capacidade de raciocínio da IA. Ao explorar mecanismos complexos como mistura de linguagem e raciocínio recursivo, suas principais vantagens incluem forte capacidade de análise de raciocínio, habilidades matemáticas e de programação. Ao mesmo tempo, existem questões de troca de linguagem, ciclos de raciocínio, considerações de segurança e diferenças em outras capacidades."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct é um modelo de linguagem de grande escala com ajuste fino para instruções na série Qwen2, com um tamanho de parâmetro de 1.5B. Este modelo é baseado na arquitetura Transformer, utilizando funções de ativação SwiGLU, viés de atenção QKV e atenção de consulta em grupo. Ele se destaca em compreensão de linguagem, geração, capacidade multilíngue, codificação, matemática e raciocínio em vários benchmarks, superando a maioria dos modelos de código aberto. Em comparação com o Qwen1.5-1.8B-Chat, o Qwen2-1.5B-Instruct mostrou melhorias significativas de desempenho em testes como MMLU, HumanEval, GSM8K, C-Eval e IFEval, apesar de ter um número de parâmetros ligeiramente menor."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 é um modelo de linguagem universal avançado, suportando diversos tipos de instruções."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct é um modelo de linguagem de grande escala com ajuste fino para instruções na série Qwen2, com um tamanho de parâmetro de 72B. Este modelo é baseado na arquitetura Transformer, utilizando funções de ativação SwiGLU, viés de atenção QKV e atenção de consulta em grupo. Ele é capaz de lidar com entradas em larga escala. O modelo se destaca em compreensão de linguagem, geração, capacidade multilíngue, codificação, matemática e raciocínio em vários benchmarks, superando a maioria dos modelos de código aberto e demonstrando competitividade comparável a modelos proprietários em algumas tarefas."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL é a versão mais recente do modelo Qwen-VL, alcançando desempenho de ponta em testes de compreensão visual."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 é uma nova série de modelos de linguagem em larga escala, projetada para otimizar o processamento de tarefas instrucionais."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 é uma nova série de modelos de linguagem em larga escala, projetada para otimizar o processamento de tarefas instrucionais."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 é uma nova série de modelos de linguagem em larga escala, com maior capacidade de compreensão e geração."
+ "description": "Modelo de linguagem de grande escala desenvolvido pela equipe Qianwen da Alibaba Cloud."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 é uma nova série de grandes modelos de linguagem, com capacidades de compreensão e geração aprimoradas."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 é uma nova série de grandes modelos de linguagem, projetada para otimizar o processamento de tarefas instrucionais."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 é uma nova série de modelos de linguagem em larga escala, projetada para otimizar o processamento de tarefas instrucionais."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 é uma nova série de grandes modelos de linguagem, projetada para otimizar o processamento de tarefas instrucionais."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder foca na escrita de código."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math foca na resolução de problemas na área de matemática, oferecendo respostas especializadas para questões de alta dificuldade."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct é a versão mais recente da série de modelos de linguagem de grande escala específicos para código lançada pela Alibaba Cloud. Este modelo, baseado no Qwen2.5, foi treinado com 55 trilhões de tokens, melhorando significativamente a capacidade de geração, raciocínio e correção de código. Ele não apenas aprimora a capacidade de codificação, mas também mantém as vantagens em matemática e habilidades gerais. O modelo fornece uma base mais abrangente para aplicações práticas, como agentes de código."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 é a mais recente série do modelo Qwen, suportando 128k de contexto. Em comparação com os melhores modelos de código aberto atuais, o Qwen2-72B supera significativamente os modelos líderes em várias capacidades, incluindo compreensão de linguagem natural, conhecimento, código, matemática e multilinguismo."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 é a mais recente série do modelo Qwen, capaz de superar modelos de código aberto de tamanho equivalente e até mesmo modelos de maior escala. O Qwen2 7B obteve vantagens significativas em várias avaliações, especialmente em compreensão de código e chinês."
+ },
+ "Qwen2-VL-72B": {
+ "description": "O Qwen2-VL-72B é um poderoso modelo de linguagem visual, que suporta processamento multimodal de imagens e texto, capaz de reconhecer com precisão o conteúdo das imagens e gerar descrições ou respostas relacionadas."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct é um grande modelo de linguagem com 14 bilhões de parâmetros, com desempenho excelente, otimizado para cenários em chinês e multilíngues, suportando aplicações como perguntas e respostas inteligentes e geração de conteúdo."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct é um grande modelo de linguagem com 32 bilhões de parâmetros, com desempenho equilibrado, otimizado para cenários em chinês e multilíngues, suportando aplicações como perguntas e respostas inteligentes e geração de conteúdo."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct suporta 16k de contexto, gerando textos longos com mais de 8K. Suporta chamadas de função e interação sem costura com sistemas externos, aumentando significativamente a flexibilidade e escalabilidade. O conhecimento do modelo aumentou consideravelmente, e suas habilidades em codificação e matemática melhoraram muito, com suporte a mais de 29 idiomas."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct é um grande modelo de linguagem com 7 bilhões de parâmetros, que suporta chamadas de função e interação sem costura com sistemas externos, aumentando significativamente a flexibilidade e escalabilidade. Otimizado para cenários em chinês e multilíngues, suporta aplicações como perguntas e respostas inteligentes e geração de conteúdo."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "O Qwen2.5-Coder-14B-Instruct é um modelo de instrução de programação baseado em pré-treinamento em larga escala, com forte capacidade de compreensão e geração de código, capaz de lidar eficientemente com diversas tarefas de programação, especialmente adequado para escrita inteligente de código, geração de scripts automatizados e resolução de problemas de programação."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct é um grande modelo de linguagem projetado para geração de código, compreensão de código e cenários de desenvolvimento eficiente, com uma escala de 32 bilhões de parâmetros, atendendo a diversas necessidades de programação."
+ },
+ "SenseChat": {
+ "description": "Modelo da versão básica (V4), com comprimento de contexto de 4K, com capacidades gerais poderosas."
+ },
+ "SenseChat-128K": {
+ "description": "Modelo da versão básica (V4), com comprimento de contexto de 128K, se destaca em tarefas de compreensão e geração de textos longos."
+ },
+ "SenseChat-32K": {
+ "description": "Modelo da versão básica (V4), com comprimento de contexto de 32K, aplicável de forma flexível em diversos cenários."
+ },
+ "SenseChat-5": {
+ "description": "Modelo da versão mais recente (V5.5), com comprimento de contexto de 128K, com capacidades significativamente aprimoradas em raciocínio matemático, diálogos em inglês, seguimento de instruções e compreensão de textos longos, rivalizando com o GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "É a versão mais recente baseada no V5.5, com melhorias significativas em várias dimensões, como habilidades básicas em chinês e inglês, conversação, conhecimento em ciências exatas, conhecimento em ciências humanas, redação, lógica matemática e controle de contagem de palavras em comparação com a versão anterior."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Comprimento de contexto de 32K, superando o GPT-4 na compreensão de diálogos em cantonês, competindo com o GPT-4 Turbo em várias áreas, incluindo conhecimento, raciocínio, matemática e programação."
+ },
+ "SenseChat-Character": {
+ "description": "Modelo padrão, com comprimento de contexto de 8K, alta velocidade de resposta."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Modelo avançado, com comprimento de contexto de 32K, com capacidades amplamente aprimoradas, suportando diálogos em chinês e inglês."
+ },
+ "SenseChat-Turbo": {
+ "description": "Adequado para perguntas rápidas e cenários de ajuste fino do modelo."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "É a versão mais recente do modelo leve, alcançando mais de 90% da capacidade do modelo completo, reduzindo significativamente o custo de inferência."
+ },
+ "SenseChat-Vision": {
+ "description": "Modelo da versão mais recente (V5.5), suporta entrada de múltiplas imagens, otimizando completamente as capacidades básicas do modelo, com grandes melhorias em reconhecimento de atributos de objetos, relações espaciais, reconhecimento de eventos, compreensão de cenários, reconhecimento de emoções, raciocínio lógico e compreensão e geração de texto."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Modelo de segunda geração Skylark, o modelo Skylark2-lite possui alta velocidade de resposta, adequado para cenários que exigem alta capacidade de resposta, sensíveis ao custo e com baixa exigência de precisão do modelo, com uma janela de contexto de 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Modelo de segunda geração Skylark, a versão Skylark2-pro possui alta precisão, adequada para cenários de geração de texto mais complexos, como geração de textos em campos especializados, criação de romances e traduções de alta qualidade, com uma janela de contexto de 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Modelo de segunda geração Skylark, o modelo Skylark2-pro possui alta precisão, adequado para cenários de geração de texto mais complexos, como geração de textos em campos especializados, criação de romances e traduções de alta qualidade, com uma janela de contexto de 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Modelo de segunda geração Skylark, o modelo Skylark2-pro-character possui excelentes habilidades de interpretação de papéis e chat, especializado em interpretar diferentes papéis com base nas solicitações do usuário e engajar em conversas, apresentando um estilo de personagem distinto e um conteúdo de diálogo natural e fluído, adequado para construir chatbots, assistentes virtuais e atendimento ao cliente online, com alta velocidade de resposta."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Modelo de segunda geração Skylark, o Skylark2-pro-turbo-8k proporciona raciocínio mais rápido e menor custo, com uma janela de contexto de 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B é um modelo de código aberto da série ChatGLM, desenvolvido pela Zhipu AI. Este modelo mantém as excelentes características da geração anterior, como fluência no diálogo e baixo custo de implantação, enquanto introduz novos recursos. Ele utiliza dados de treinamento mais variados, um número de passos de treinamento mais robusto e uma estratégia de treinamento mais razoável, destacando-se entre modelos pré-treinados abaixo de 10B. O ChatGLM3-6B suporta diálogos de múltiplas rodadas, chamadas de ferramentas, execução de código e tarefas de agente em cenários complexos. Além do modelo de diálogo, também foram lançados o modelo base ChatGLM-6B-Base e o modelo de diálogo de longo texto ChatGLM3-6B-32K. Este modelo está completamente aberto para pesquisa acadêmica e permite uso comercial gratuito após registro."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B é uma versão de código aberto, oferecendo uma experiência de diálogo otimizada para aplicações de conversa."
},
+ "TeleAI/TeleChat2": {
+ "description": "O modelo TeleChat2 é um modelo semântico gerador desenvolvido de forma independente pela China Telecom, que suporta funções como perguntas e respostas enciclopédicas, geração de código e geração de textos longos, oferecendo serviços de consulta de diálogo aos usuários, permitindo interações de diálogo, respondendo perguntas e auxiliando na criação, ajudando os usuários a obter informações, conhecimento e inspiração de forma eficiente e conveniente. O modelo apresenta um desempenho notável em questões de alucinação, geração de textos longos e compreensão lógica."
+ },
+ "TeleAI/TeleMM": {
+ "description": "O modelo TeleMM é um modelo de compreensão multimodal desenvolvido de forma independente pela China Telecom, capaz de lidar com entradas de múltiplas modalidades, como texto e imagem, suportando funções como compreensão de imagem e análise de gráficos, oferecendo serviços de compreensão multimodal aos usuários. O modelo pode interagir com os usuários de forma multimodal, compreendendo com precisão o conteúdo de entrada, respondendo perguntas, auxiliando na criação e fornecendo informações e suporte de inspiração multimodal de forma eficiente. O modelo se destaca em tarefas multimodais, como percepção de granularidade fina e raciocínio lógico."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct é um dos mais recentes modelos de linguagem de grande escala lançados pela Alibaba Cloud. Este modelo de 72B apresenta melhorias significativas em áreas como codificação e matemática. O modelo também oferece suporte multilíngue, abrangendo mais de 29 idiomas, incluindo chinês e inglês. O modelo teve melhorias significativas em seguir instruções, entender dados estruturados e gerar saídas estruturadas (especialmente JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, mantendo as excelentes habilidades linguísticas do modelo original, aumentou significativamente suas capacidades de lógica matemática e codificação através de treinamento incremental com 500 bilhões de tokens de alta qualidade."
+ },
"abab5.5-chat": {
"description": "Voltado para cenários de produtividade, suportando o processamento de tarefas complexas e geração de texto eficiente, adequado para aplicações em áreas profissionais."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Otimizado para cenários de diálogo de personagens em chinês, oferecendo capacidade de geração de diálogos fluentes e que respeitam os hábitos de expressão em chinês."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Modelo de chamada de função de código aberto da Fireworks, oferecendo excelente capacidade de execução de instruções e características personalizáveis."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "O Firefunction-v2 da Fireworks é um modelo de chamada de função de alto desempenho, desenvolvido com base no Llama-3 e otimizado para cenários como chamadas de função, diálogos e seguimento de instruções."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b é um modelo de linguagem visual que pode receber entradas de imagem e texto simultaneamente, treinado com dados de alta qualidade, adequado para tarefas multimodais."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 é um modelo de linguagem grande de última geração, otimizado com aprendizado por reforço e dados de inicialização a frio, apresentando desempenho excepcional em raciocínio, matemática e programação."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "O modelo Gemma 2 9B Instruct, baseado na tecnologia anterior da Google, é adequado para responder perguntas, resumir e realizar inferências em diversas tarefas de geração de texto."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Modelo de linguagem poderoso da Deepseek, baseado em Mixture-of-Experts (MoE), com um total de 671B de parâmetros, ativando 37B de parâmetros por token."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "O modelo Llama 3 70B Instruct é otimizado para diálogos multilíngues e compreensão de linguagem natural, superando a maioria dos modelos concorrentes."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "O modelo Llama 3 70B Instruct (versão HF) mantém consistência com os resultados da implementação oficial, adequado para tarefas de seguimento de instruções de alta qualidade."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "O modelo Llama 3 8B Instruct é otimizado para diálogos e tarefas multilíngues, apresentando desempenho excepcional e eficiência."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "O modelo Llama 3.1 8B Instruct é otimizado para diálogos multilíngues, superando a maioria dos modelos de código aberto e fechado em benchmarks do setor."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Modelo de raciocínio visual de 11B parâmetros da Meta, otimizado para reconhecimento visual, raciocínio visual, descrição de imagens e resposta a perguntas gerais sobre imagens. Este modelo é capaz de entender dados visuais, como gráficos e diagramas, e preencher a lacuna entre visão e linguagem gerando descrições textuais dos detalhes das imagens."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "O modelo de instrução Llama 3.2 3B é um modelo multilíngue leve lançado pela Meta. Este modelo visa aumentar a eficiência, oferecendo melhorias significativas em latência e custo em comparação com modelos maiores. Exemplos de uso incluem consultas, reescrita de prompts e auxílio na redação."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Modelo de raciocínio visual de 90B parâmetros da Meta, otimizado para reconhecimento visual, raciocínio visual, descrição de imagens e resposta a perguntas gerais sobre imagens. Este modelo é capaz de entender dados visuais, como gráficos e diagramas, e preencher a lacuna entre visão e linguagem gerando descrições textuais dos detalhes das imagens."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct é a versão atualizada de dezembro do Llama 3.1 70B. Este modelo foi aprimorado com base no Llama 3.1 70B (lançado em julho de 2024), melhorando a chamada de ferramentas, suporte a textos multilíngues, habilidades matemáticas e de programação. O modelo alcançou níveis de liderança da indústria em raciocínio, matemática e seguimento de instruções, e é capaz de oferecer desempenho semelhante ao 3.1 405B, ao mesmo tempo em que apresenta vantagens significativas em velocidade e custo."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Modelo com 24B de parâmetros, com capacidades de ponta comparáveis a modelos maiores."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "O modelo Mixtral MoE 8x22B Instruct, com parâmetros em grande escala e arquitetura de múltiplos especialistas, suporta o processamento eficiente de tarefas complexas."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "O modelo Mixtral MoE 8x7B Instruct, com uma arquitetura de múltiplos especialistas, oferece seguimento e execução de instruções de forma eficiente."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "O modelo Mixtral MoE 8x7B Instruct (versão HF) apresenta desempenho consistente com a implementação oficial, adequado para uma variedade de cenários de tarefas eficientes."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "O modelo MythoMax L2 13B combina novas técnicas de fusão, sendo especializado em narrativas e interpretação de personagens."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "O modelo Phi 3 Vision Instruct é um modelo multimodal leve, capaz de processar informações visuais e textuais complexas, com forte capacidade de raciocínio."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "O modelo StarCoder 15.5B suporta tarefas de programação avançadas, com capacidade multilíngue aprimorada, adequado para geração e compreensão de código complexos."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "O modelo QwQ é um modelo de pesquisa experimental desenvolvido pela equipe Qwen, focado em aprimorar a capacidade de raciocínio da IA."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "A versão 72B do modelo Qwen-VL é o resultado da mais recente iteração da Alibaba, representando quase um ano de inovações."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "O modelo StarCoder 7B é treinado para mais de 80 linguagens de programação, apresentando excelente capacidade de preenchimento de código e compreensão de contexto."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 é uma série de modelos de linguagem com apenas decodificadores, desenvolvida pela equipe Qwen da Alibaba Cloud. Estes modelos têm tamanhos variados, incluindo 0.5B, 1.5B, 3B, 7B, 14B, 32B e 72B, com variantes base (base) e de instrução (instruct)."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct é a versão mais recente da série de modelos de linguagem de grande escala específicos para código lançada pela Alibaba Cloud. Este modelo, baseado no Qwen2.5, foi treinado com 55 trilhões de tokens, melhorando significativamente a capacidade de geração, raciocínio e correção de código. Ele não apenas aprimora a capacidade de codificação, mas também mantém as vantagens em matemática e habilidades gerais. O modelo fornece uma base mais abrangente para aplicações práticas, como agentes de código."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "O modelo Yi-Large oferece excelente capacidade de processamento multilíngue, adequado para diversas tarefas de geração e compreensão de linguagem."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Um modelo multilíngue com 52B de parâmetros (12B ativos), oferecendo uma janela de contexto longa de 256K, chamada de função, saída estruturada e geração fundamentada."
},
- "ai21-jamba-instruct": {
- "description": "Um modelo LLM baseado em Mamba de qualidade de produção para alcançar desempenho, qualidade e eficiência de custo de classe mundial."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "O Claude 3.5 Sonnet eleva o padrão da indústria, superando modelos concorrentes e o Claude 3 Opus, apresentando um desempenho excepcional em avaliações amplas, ao mesmo tempo que mantém a velocidade e o custo de nossos modelos de nível médio."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet elevou o padrão da indústria, superando modelos concorrentes e o Claude 3 Opus, apresentando um desempenho excepcional em avaliações amplas, enquanto mantém a velocidade e o custo de nossos modelos de nível médio."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "O Claude 3 Haiku é o modelo mais rápido e compacto da Anthropic, oferecendo uma velocidade de resposta quase instantânea. Ele pode responder rapidamente a consultas e solicitações simples. Os clientes poderão construir uma experiência de IA sem costura que imita a interação humana. O Claude 3 Haiku pode processar imagens e retornar saídas de texto, com uma janela de contexto de 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus é o modelo mais poderoso da Anthropic para lidar com tarefas altamente complexas. Ele se destaca em desempenho, inteligência, fluência e compreensão."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku é o modelo de próxima geração mais rápido da Anthropic. Em comparação com Claude 3 Haiku, Claude 3.5 Haiku apresenta melhorias em várias habilidades e supera o maior modelo da geração anterior, Claude 3 Opus, em muitos testes de inteligência."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet oferece capacidades que vão além do Opus e uma velocidade superior ao Sonnet, mantendo o mesmo preço do Sonnet. O Sonnet é especialmente habilidoso em programação, ciência de dados, processamento visual e tarefas de agente."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet é o modelo mais inteligente da Anthropic até agora e é o primeiro modelo de raciocínio misto do mercado. Claude 3.7 Sonnet pode gerar respostas quase instantâneas ou um pensamento gradual prolongado, permitindo que os usuários vejam claramente esses processos. Sonnet é especialmente habilidoso em programação, ciência de dados, processamento visual e tarefas de agente."
+ },
"aya": {
"description": "Aya 23 é um modelo multilíngue lançado pela Cohere, suportando 23 idiomas, facilitando aplicações linguísticas diversificadas."
},
"aya:35b": {
"description": "Aya 23 é um modelo multilíngue lançado pela Cohere, suportando 23 idiomas, facilitando aplicações linguísticas diversificadas."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B é um modelo de linguagem de código aberto e comercializável desenvolvido pela Baichuan Intelligence, contendo 13 bilhões de parâmetros, alcançando os melhores resultados em benchmarks de chinês e inglês na mesma dimensão."
+ },
"charglm-3": {
"description": "O CharGLM-3 é projetado para interpretação de personagens e companhia emocional, suportando memória de múltiplas rodadas e diálogos personalizados, com ampla aplicação."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 oferece avanços em capacidades críticas para empresas, incluindo um contexto líder do setor de 200K tokens, uma redução significativa na taxa de alucinação do modelo, prompts de sistema e uma nova funcionalidade de teste: chamadas de ferramentas."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku é o modelo de próxima geração mais rápido da Anthropic. Em comparação com o Claude 3 Haiku, o Claude 3.5 Haiku apresenta melhorias em várias habilidades e superou o maior modelo da geração anterior, o Claude 3 Opus, em muitos testes de referência de inteligência."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet oferece capacidades que superam o Opus e uma velocidade mais rápida que o Sonnet, mantendo o mesmo preço. O Sonnet é especialmente bom em programação, ciência de dados, processamento visual e tarefas de agente."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet oferece capacidades que vão além do Opus e uma velocidade mais rápida do que o Sonnet, mantendo o mesmo preço do Sonnet. O Sonnet é especialmente bom em programação, ciência de dados, processamento visual e tarefas de agente."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet é o modelo de IA mais poderoso da Anthropic, com desempenho de ponta em tarefas altamente complexas. Ele pode lidar com prompts abertos e cenários não vistos, apresentando fluência excepcional e compreensão semelhante à humana. O Claude 3.7 Sonnet demonstra as possibilidades de geração de IA na vanguarda."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku é o modelo mais rápido e compacto da Anthropic, projetado para respostas quase instantâneas. Ele possui desempenho direcionado rápido e preciso."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet oferece um equilíbrio ideal entre inteligência e velocidade para cargas de trabalho empresariais. Ele fornece máxima utilidade a um custo mais baixo, sendo confiável e adequado para implantação em larga escala."
},
- "claude-instant-1.2": {
- "description": "O modelo da Anthropic é utilizado para geração de texto de baixa latência e alta taxa de transferência, suportando a geração de centenas de páginas de texto."
- },
"codegeex-4": {
"description": "O CodeGeeX-4 é um poderoso assistente de programação AI, suportando perguntas e respostas inteligentes e autocompletar em várias linguagens de programação, aumentando a eficiência do desenvolvimento."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B é um modelo de geração de código multilíngue, suportando funcionalidades abrangentes, incluindo completude e geração de código, interpretador de código, busca na web, chamadas de função e perguntas e respostas em nível de repositório, cobrindo diversos cenários de desenvolvimento de software. É um modelo de geração de código de ponta com menos de 10B de parâmetros."
+ },
"codegemma": {
"description": "CodeGemma é um modelo de linguagem leve especializado em diferentes tarefas de programação, suportando iterações rápidas e integração."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama é um LLM focado em geração e discussão de código, combinando suporte a uma ampla gama de linguagens de programação, adequado para ambientes de desenvolvedores."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama é um LLM focado em geração e discussão de código, combinando amplo suporte a linguagens de programação, adequado para ambientes de desenvolvedores."
+ },
"codellama:13b": {
"description": "Code Llama é um LLM focado em geração e discussão de código, combinando suporte a uma ampla gama de linguagens de programação, adequado para ambientes de desenvolvedores."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ é um modelo de linguagem de grande porte de alto desempenho, projetado para cenários empresariais reais e aplicações complexas."
},
+ "dall-e-2": {
+ "description": "O segundo modelo DALL·E, suporta geração de imagens mais realistas e precisas, com resolução quatro vezes maior que a da primeira geração."
+ },
+ "dall-e-3": {
+ "description": "O mais recente modelo DALL·E, lançado em novembro de 2023. Suporta geração de imagens mais realistas e precisas, com maior capacidade de detalhamento."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct oferece capacidade de processamento de instruções altamente confiável, suportando aplicações em diversos setores."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 é um modelo de inferência impulsionado por aprendizado por reforço (RL), que resolve problemas de repetitividade e legibilidade no modelo. Antes do RL, o DeepSeek-R1 introduziu dados de inicialização a frio, otimizando ainda mais o desempenho da inferência. Ele apresenta desempenho comparável ao OpenAI-o1 em tarefas matemáticas, de código e de inferência, e melhora o resultado geral por meio de métodos de treinamento cuidadosamente projetados."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "Modelo de destilação DeepSeek-R1, otimizado para desempenho de inferência através de aprendizado por reforço e dados de inicialização fria, modelo de código aberto que redefine os padrões de múltiplas tarefas."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B é um modelo de destilação desenvolvido com base no Llama-3.1-8B. Este modelo foi ajustado com amostras geradas pelo DeepSeek-R1, demonstrando excelente capacidade de inferência. Apresentou bom desempenho em vários testes de referência, alcançando uma precisão de 89,1% no MATH-500, uma taxa de aprovação de 50,4% no AIME 2024 e uma pontuação de 1205 no CodeForces, demonstrando forte capacidade matemática e de programação para um modelo de 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Modelo de destilação DeepSeek-R1, otimizado para desempenho de inferência através de aprendizado por reforço e dados de inicialização fria, modelo de código aberto que redefine os padrões de múltiplas tarefas."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Modelo de destilação DeepSeek-R1, otimizado para desempenho de inferência através de aprendizado por reforço e dados de inicialização fria, modelo de código aberto que redefine os padrões de múltiplas tarefas."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B é um modelo obtido através da destilação do Qwen2.5-32B. Este modelo foi ajustado com 800 mil amostras selecionadas geradas pelo DeepSeek-R1, demonstrando desempenho excepcional em várias áreas, como matemática, programação e raciocínio. Obteve resultados notáveis em vários testes de referência, alcançando uma precisão de 94,3% no MATH-500, demonstrando forte capacidade de raciocínio matemático."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B é um modelo obtido através da destilação do Qwen2.5-Math-7B. Este modelo foi ajustado com 800 mil amostras selecionadas geradas pelo DeepSeek-R1, demonstrando excelente capacidade de inferência. Apresentou desempenho notável em vários testes de referência, alcançando uma precisão de 92,8% no MATH-500, uma taxa de aprovação de 55,5% no AIME 2024 e uma pontuação de 1189 no CodeForces, demonstrando forte capacidade matemática e de programação para um modelo de 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 combina as excelentes características das versões anteriores, aprimorando a capacidade geral e de codificação."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 é um modelo de linguagem de especialistas mistos (MoE) com 671 bilhões de parâmetros, utilizando atenção latente de múltiplas cabeças (MLA) e a arquitetura DeepSeekMoE, combinando uma estratégia de balanceamento de carga sem perda auxiliar para otimizar a eficiência de inferência e treinamento. Após ser pré-treinado em 14,8 trilhões de tokens de alta qualidade e passar por ajuste fino supervisionado e aprendizado por reforço, o DeepSeek-V3 supera outros modelos de código aberto em desempenho, aproximando-se de modelos fechados líderes."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B é um modelo avançado treinado para diálogos de alta complexidade."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "LLM avançado e eficiente, especializado em raciocínio, matemática e programação."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 é um modelo de linguagem visual baseado no DeepSeekMoE-27B, desenvolvido como um especialista misto (MoE), utilizando uma arquitetura de MoE com ativação esparsa, alcançando desempenho excepcional com apenas 4,5 bilhões de parâmetros ativados. Este modelo se destaca em várias tarefas, incluindo perguntas visuais, reconhecimento óptico de caracteres, compreensão de documentos/tabelas/gráficos e localização visual."
+ },
"deepseek-chat": {
"description": "Um novo modelo de código aberto que combina capacidades gerais e de codificação, não apenas preservando a capacidade de diálogo geral do modelo Chat original e a poderosa capacidade de processamento de código do modelo Coder, mas também alinhando-se melhor às preferências humanas. Além disso, o DeepSeek-V2.5 também alcançou melhorias significativas em várias áreas, como tarefas de escrita e seguimento de instruções."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B é um modelo de linguagem de código, treinado com 20 trilhões de dados, dos quais 87% são código e 13% são em chinês e inglês. O modelo introduz uma janela de 16K e tarefas de preenchimento, oferecendo funcionalidades de completude de código e preenchimento de fragmentos em nível de projeto."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 é um modelo de código de especialistas abertos, destacando-se em tarefas de codificação, comparável ao GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 é um modelo de código de especialistas abertos, destacando-se em tarefas de codificação, comparável ao GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 é um modelo de inferência impulsionado por aprendizado por reforço (RL), que resolve problemas de repetitividade e legibilidade no modelo. Antes do RL, o DeepSeek-R1 introduziu dados de inicialização a frio, otimizando ainda mais o desempenho da inferência. Ele apresenta desempenho comparável ao OpenAI-o1 em tarefas matemáticas, de código e de inferência, e melhora o resultado geral por meio de métodos de treinamento cuidadosamente projetados."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 — um modelo maior e mais inteligente dentro do pacote DeepSeek — foi destilado para a arquitetura Llama 70B. Com base em testes de referência e avaliações humanas, este modelo é mais inteligente que o Llama 70B original, destacando-se especialmente em tarefas que exigem precisão matemática e factual."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "O modelo da série DeepSeek-R1-Distill é obtido através da técnica de destilação de conhecimento, ajustando amostras geradas pelo DeepSeek-R1 em modelos de código aberto como Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "O modelo da série DeepSeek-R1-Distill é obtido através da técnica de destilação de conhecimento, ajustando amostras geradas pelo DeepSeek-R1 em modelos de código aberto como Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "O modelo da série DeepSeek-R1-Distill é obtido através da técnica de destilação de conhecimento, ajustando amostras geradas pelo DeepSeek-R1 em modelos de código aberto como Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "O modelo da série DeepSeek-R1-Distill é obtido através da técnica de destilação de conhecimento, ajustando amostras geradas pelo DeepSeek-R1 em modelos de código aberto como Qwen e Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "O modelo da série DeepSeek-R1-Distill é obtido através da técnica de destilação de conhecimento, ajustando amostras geradas pelo DeepSeek-R1 em modelos de código aberto como Qwen e Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "Modelo de raciocínio lançado pela DeepSeek. Antes de fornecer a resposta final, o modelo gera uma cadeia de pensamento para aumentar a precisão da resposta final."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 é um modelo de linguagem eficiente Mixture-of-Experts, adequado para demandas de processamento econômico."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B é o modelo de código projetado do DeepSeek, oferecendo forte capacidade de geração de código."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 é um modelo MoE desenvolvido pela Hangzhou DeepSeek Artificial Intelligence Technology Research Co., Ltd., com desempenho destacado em várias avaliações, ocupando o primeiro lugar entre os modelos de código aberto nas principais listas. Em comparação com o modelo V2.5, a velocidade de geração do V3 foi aumentada em 3 vezes, proporcionando uma experiência de uso mais rápida e fluida."
+ },
"deepseek/deepseek-chat": {
"description": "Um novo modelo de código aberto que integra capacidades gerais e de codificação, não apenas preservando a capacidade de diálogo geral do modelo Chat original e a poderosa capacidade de processamento de código do modelo Coder, mas também alinhando-se melhor às preferências humanas. Além disso, o DeepSeek-V2.5 também alcançou melhorias significativas em várias áreas, como tarefas de escrita e seguimento de instruções."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 melhorou significativamente a capacidade de raciocínio do modelo com muito poucos dados rotulados. Antes de fornecer a resposta final, o modelo gera uma cadeia de pensamento para aumentar a precisão da resposta final."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B é um grande modelo de linguagem baseado no Llama3.3 70B, que utiliza o ajuste fino da saída do DeepSeek R1 para alcançar um desempenho competitivo comparável aos grandes modelos de ponta."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B é um modelo de linguagem grande destilado baseado no Llama-3.1-8B-Instruct, treinado usando a saída do DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B é um modelo de linguagem grande destilado baseado no Qwen 2.5 14B, treinado usando a saída do DeepSeek R1. Este modelo superou o o1-mini da OpenAI em vários benchmarks, alcançando os mais recentes avanços tecnológicos em modelos densos (state-of-the-art). Aqui estão alguns resultados de benchmarks:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nClassificação CodeForces: 1481\nEste modelo, ajustado a partir da saída do DeepSeek R1, demonstrou desempenho competitivo comparável a modelos de ponta de maior escala."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B é um modelo de linguagem grande destilado baseado no Qwen 2.5 32B, treinado usando a saída do DeepSeek R1. Este modelo superou o o1-mini da OpenAI em vários benchmarks, alcançando os mais recentes avanços tecnológicos em modelos densos (state-of-the-art). Aqui estão alguns resultados de benchmarks:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nClassificação CodeForces: 1691\nEste modelo, ajustado a partir da saída do DeepSeek R1, demonstrou desempenho competitivo comparável a modelos de ponta de maior escala."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 é o mais recente modelo de código aberto lançado pela equipe DeepSeek, com desempenho de inferência extremamente robusto, especialmente em tarefas de matemática, programação e raciocínio, alcançando níveis comparáveis ao modelo o1 da OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 melhorou significativamente a capacidade de raciocínio do modelo com muito poucos dados rotulados. Antes de fornecer a resposta final, o modelo gera uma cadeia de pensamento para aumentar a precisão da resposta final."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 alcançou um avanço significativo na velocidade de inferência em comparação com os modelos anteriores. Classificado como o número um entre os modelos de código aberto, pode competir com os modelos fechados mais avançados do mundo. DeepSeek-V3 utiliza a arquitetura de Atenção Multi-Cabeça (MLA) e DeepSeekMoE, que foram amplamente validadas no DeepSeek-V2. Além disso, DeepSeek-V3 introduziu uma estratégia auxiliar sem perdas para balanceamento de carga e definiu objetivos de treinamento de previsão de múltiplos rótulos para obter um desempenho mais forte."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 alcançou um avanço significativo na velocidade de inferência em comparação com os modelos anteriores. Classificado como o número um entre os modelos de código aberto, pode competir com os modelos fechados mais avançados do mundo. DeepSeek-V3 utiliza a arquitetura de Atenção Multi-Cabeça (MLA) e DeepSeekMoE, que foram amplamente validadas no DeepSeek-V2. Além disso, DeepSeek-V3 introduziu uma estratégia auxiliar sem perdas para balanceamento de carga e definiu objetivos de treinamento de previsão de múltiplos rótulos para obter um desempenho mais forte."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite é a nova geração de modelo leve, com velocidade de resposta extrema, alcançando níveis de desempenho e latência de classe mundial."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k é uma versão totalmente aprimorada do Doubao-1.5-Pro, com um aumento significativo de 10% no desempenho geral. Suporta raciocínio com janelas de contexto de 256k e um comprimento de saída de até 12k tokens. Maior desempenho, janelas maiores e excelente custo-benefício, adequado para uma ampla gama de cenários de aplicação."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro é a nova geração de modelo principal, com desempenho totalmente aprimorado, destacando-se em conhecimento, código, raciocínio, entre outros aspectos."
+ },
"emohaa": {
"description": "O Emohaa é um modelo psicológico com capacidade de consultoria profissional, ajudando os usuários a entender questões emocionais."
},
+ "ernie-3.5-128k": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, cobrindo uma vasta quantidade de dados em chinês e inglês, com forte capacidade geral, capaz de atender à maioria das demandas de diálogo, geração criativa e aplicações de plugins; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas."
+ },
+ "ernie-3.5-8k": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, cobrindo uma vasta quantidade de dados em chinês e inglês, com forte capacidade geral, capaz de atender à maioria das demandas de diálogo, geração criativa e aplicações de plugins; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, cobrindo uma vasta quantidade de dados em chinês e inglês, com forte capacidade geral, capaz de atender à maioria das demandas de diálogo, geração criativa e aplicações de plugins; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, com capacidade de modelo amplamente aprimorada em comparação com o ERNIE 3.5, amplamente aplicável a cenários de tarefas complexas em várias áreas; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, com capacidade de modelo amplamente aprimorada em comparação com o ERNIE 3.5, amplamente aplicável a cenários de tarefas complexas em várias áreas; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, com desempenho geral excepcional, amplamente aplicável a cenários de tarefas complexas em várias áreas; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas. Em comparação com o ERNIE 4.0, apresenta desempenho superior."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, com desempenho geral excepcional, amplamente aplicável a cenários de tarefas complexas em várias áreas; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas. Em comparação com o ERNIE 4.0, apresenta desempenho superior."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Modelo de linguagem de grande escala de nível flagship desenvolvido pela Baidu, com desempenho geral excepcional, amplamente aplicável a cenários de tarefas complexas em várias áreas; suporta integração automática com plugins de busca da Baidu, garantindo a atualidade das informações de perguntas e respostas. Em comparação com o ERNIE 4.0, apresenta desempenho superior."
+ },
+ "ernie-char-8k": {
+ "description": "Modelo de linguagem de grande escala vertical desenvolvido pela Baidu, adequado para aplicações como NPCs de jogos, diálogos de atendimento ao cliente e interpretação de personagens, com estilo de personagem mais distinto e consistente, capacidade de seguir instruções mais forte e desempenho de inferência superior."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Modelo de linguagem de grande escala vertical desenvolvido pela Baidu, adequado para aplicações como NPCs de jogos, diálogos de atendimento ao cliente e interpretação de personagens, com estilo de personagem mais distinto e consistente, capacidade de seguir instruções mais forte e desempenho de inferência superior."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite é um modelo de linguagem de grande escala leve desenvolvido pela Baidu, equilibrando excelente desempenho do modelo e eficiência de inferência, adequado para uso em placas de aceleração de IA de baixa potência."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Modelo de linguagem de grande escala leve desenvolvido pela Baidu, equilibrando excelente desempenho do modelo e eficiência de inferência, com desempenho superior ao ERNIE Lite, adequado para uso em placas de aceleração de IA de baixa potência."
+ },
+ "ernie-novel-8k": {
+ "description": "Modelo de linguagem de grande escala geral desenvolvido pela Baidu, com vantagens notáveis na capacidade de continuar histórias, também aplicável em cenários como peças curtas e filmes."
+ },
+ "ernie-speed-128k": {
+ "description": "Modelo de linguagem de alto desempenho desenvolvido pela Baidu, lançado em 2024, com excelente capacidade geral, adequado para ser usado como modelo base para ajuste fino, lidando melhor com problemas de cenários específicos, enquanto apresenta excelente desempenho de inferência."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Modelo de linguagem de alto desempenho desenvolvido pela Baidu, lançado em 2024, com excelente capacidade geral, desempenho superior ao ERNIE Speed, adequado para ser usado como modelo base para ajuste fino, lidando melhor com problemas de cenários específicos, enquanto apresenta excelente desempenho de inferência."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny é um modelo de linguagem de grande escala de alto desempenho desenvolvido pela Baidu, com os menores custos de implantação e ajuste entre os modelos da série Wenxin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Ajuste) oferece desempenho estável e ajustável, sendo a escolha ideal para soluções de tarefas complexas."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro é o modelo de IA de alto desempenho do Google, projetado para expansão em uma ampla gama de tarefas."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash é o mais recente modelo de IA multimodal do Google, com capacidade de processamento rápido, suportando entradas de texto, imagem e vídeo, adequado para a escalabilidade eficiente de diversas tarefas."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 é um modelo multimodal eficiente, suportando a expansão de aplicações amplas."
},
"gemini-1.5-flash-002": {
"description": "O Gemini 1.5 Flash 002 é um modelo multimodal eficiente, que suporta uma ampla gama de aplicações."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 é projetado para lidar com cenários de tarefas em larga escala, oferecendo velocidade de processamento incomparável."
+ "gemini-1.5-flash-8b": {
+ "description": "O Gemini 1.5 Flash 8B é um modelo multimodal eficiente, com suporte para uma ampla gama de aplicações."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "O Gemini 1.5 Flash 8B 0924 é o mais recente modelo experimental, com melhorias significativas de desempenho em casos de uso de texto e multimídia."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 oferece capacidade de processamento multimodal otimizada, adequada para uma variedade de cenários de tarefas complexas."
+ "description": "Gemini 1.5 Flash 0827 oferece capacidade de processamento multimodal otimizada, adequada para diversos cenários de tarefas complexas."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash é o mais recente modelo de IA multimodal do Google, com capacidade de processamento rápido, suportando entradas de texto, imagem e vídeo, adequado para uma variedade de tarefas de expansão eficiente."
@@ -357,11 +822,35 @@
"description": "Gemini 1.5 Pro 0801 oferece excelente capacidade de processamento multimodal, proporcionando maior flexibilidade para o desenvolvimento de aplicações."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 combina as mais recentes tecnologias de otimização, trazendo maior eficiência no processamento de dados multimodais."
+ "description": "Gemini 1.5 Pro 0827 combina as mais recentes técnicas de otimização, proporcionando uma capacidade de processamento de dados multimodal mais eficiente."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro suporta até 2 milhões de tokens, sendo a escolha ideal para modelos multimodais de médio porte, adequados para suporte multifacetado em tarefas complexas."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash oferece funcionalidades e melhorias de próxima geração, incluindo velocidade excepcional, uso nativo de ferramentas, geração multimodal e uma janela de contexto de 1M tokens."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash oferece funcionalidades e melhorias de próxima geração, incluindo velocidade excepcional, uso nativo de ferramentas, geração multimodal e uma janela de contexto de 1M tokens."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Variante do modelo Gemini 2.0 Flash, otimizada para custo-benefício e baixa latência."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Variante do modelo Gemini 2.0 Flash, otimizada para custo-benefício e baixa latência."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Um modelo Gemini 2.0 Flash otimizado para custo-benefício e baixa latência."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "O Gemini 2.0 Flash Exp é o mais recente modelo experimental de IA multimodal do Google, com características de próxima geração, velocidade excepcional, chamadas nativas de ferramentas e geração multimodal."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "O Gemini 2.0 Flash Exp é o mais recente modelo experimental de IA multimodal do Google, com características de próxima geração, velocidade excepcional, chamadas nativas de ferramentas e geração multimodal."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental é o mais recente modelo de IA multimodal experimental do Google, apresentando melhorias de qualidade em comparação com versões anteriores, especialmente em conhecimento mundial, código e contextos longos."
+ },
"gemma-7b-it": {
"description": "Gemma 7B é adequado para o processamento de tarefas de pequeno a médio porte, combinando custo e eficiência."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 é um modelo eficiente lançado pelo Google, abrangendo uma variedade de cenários de aplicação, desde aplicações pequenas até processamento de dados complexos."
},
- "general": {
- "description": "Spark Lite é um modelo de linguagem leve, com latência extremamente baixa e alta capacidade de processamento, totalmente gratuito e aberto, suportando funcionalidade de busca online em tempo real. Sua característica de resposta rápida o torna excelente em aplicações de inferência e ajuste de modelo em dispositivos de baixa potência, proporcionando aos usuários um excelente custo-benefício e experiência inteligente, especialmente em perguntas e respostas, geração de conteúdo e cenários de busca."
- },
"generalv3": {
"description": "Spark Pro é um modelo de linguagem de alto desempenho otimizado para áreas profissionais, focando em matemática, programação, medicina, educação e outros campos, e suportando busca online e plugins integrados como clima e data. Seu modelo otimizado apresenta desempenho excepcional e eficiência em perguntas e respostas complexas, compreensão de linguagem e criação de texto de alto nível, sendo a escolha ideal para cenários de aplicação profissional."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "O GLM-4-0520 é a versão mais recente do modelo, projetada para tarefas altamente complexas e diversificadas, com desempenho excepcional."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat apresenta alto desempenho em semântica, matemática, raciocínio, código e conhecimento. Também possui navegação na web, execução de código, chamadas de ferramentas personalizadas e raciocínio de texto longo. Suporta 26 idiomas, incluindo japonês, coreano e alemão."
+ },
"glm-4-air": {
"description": "O GLM-4-Air é uma versão econômica, com desempenho próximo ao GLM-4, oferecendo alta velocidade a um preço acessível."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "O GLM-4-Flash é a escolha ideal para tarefas simples, com a maior velocidade e o preço mais acessível."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX é uma versão aprimorada do Flash, com velocidade de inferência super rápida."
+ },
"glm-4-long": {
"description": "O GLM-4-Long suporta entradas de texto superlongas, adequado para tarefas de memória e processamento de documentos em larga escala."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "O GLM-4V oferece uma forte capacidade de compreensão e raciocínio de imagens, suportando várias tarefas visuais."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash é focado na compreensão eficiente de uma única imagem, adequado para cenários de análise de imagem rápida, como análise de imagem em tempo real ou processamento em lote de imagens."
+ },
"glm-4v-plus": {
"description": "O GLM-4V-Plus possui a capacidade de entender conteúdo de vídeo e múltiplas imagens, adequado para tarefas multimodais."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 oferece capacidade de processamento multimodal otimizada, adequada para uma variedade de cenários de tarefas complexas."
+ "glm-zero-preview": {
+ "description": "O GLM-Zero-Preview possui uma poderosa capacidade de raciocínio complexo, destacando-se em áreas como raciocínio lógico, matemática e programação."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash oferece funcionalidades e melhorias de próxima geração, incluindo velocidade excepcional, uso nativo de ferramentas, geração multimodal e uma janela de contexto de 1M tokens."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental é o mais recente modelo de IA multimodal experimental do Google, apresentando melhorias de qualidade em comparação com versões anteriores, especialmente em conhecimento mundial, código e contextos longos."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 combina as mais recentes tecnologias de otimização, proporcionando uma capacidade de processamento de dados multimodal mais eficiente."
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash oferece capacidades de processamento multimodal otimizadas, adequadas para uma variedade de cenários de tarefas complexas."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro combina as mais recentes tecnologias de otimização, proporcionando uma capacidade de processamento de dados multimodais mais eficiente."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 é um modelo eficiente lançado pelo Google, abrangendo uma variedade de cenários de aplicação, desde pequenos aplicativos até processamento de dados complexos."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 continua a filosofia de design leve e eficiente."
},
+ "google/gemma-2-2b-it": {
+ "description": "Modelo leve de ajuste de instruções do Google."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 é um modelo eficiente lançado pelo Google, abrangendo uma variedade de cenários de aplicação, desde pequenos aplicativos até processamento de dados complexos."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 é uma série de modelos de texto de código aberto leve da Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "O GPT 3.5 Turbo é adequado para uma variedade de tarefas de geração e compreensão de texto, atualmente apontando para gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo, um modelo eficiente fornecido pela OpenAI, adequado para tarefas de chat e geração de texto, suportando chamadas de função paralelas."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k, um modelo de geração de texto de alta capacidade, adequado para tarefas complexas."
+ },
"gpt-4": {
"description": "O GPT-4 oferece uma janela de contexto maior, capaz de lidar com entradas de texto mais longas, adequado para cenários que exigem integração ampla de informações e análise de dados."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "O mais recente modelo GPT-4 Turbo possui funcionalidades visuais. Agora, solicitações visuais podem ser feitas usando o modo JSON e chamadas de função. O GPT-4 Turbo é uma versão aprimorada, oferecendo suporte econômico para tarefas multimodais. Ele encontra um equilíbrio entre precisão e eficiência, adequado para aplicações que requerem interação em tempo real."
},
- "gpt-4-1106-vision-preview": {
- "description": "O mais recente modelo GPT-4 Turbo possui funcionalidades visuais. Agora, solicitações visuais podem ser feitas usando o modo JSON e chamadas de função. O GPT-4 Turbo é uma versão aprimorada, oferecendo suporte econômico para tarefas multimodais. Ele encontra um equilíbrio entre precisão e eficiência, adequado para aplicações que requerem interação em tempo real."
- },
"gpt-4-32k": {
"description": "O GPT-4 oferece uma janela de contexto maior, capaz de lidar com entradas de texto mais longas, adequado para cenários que exigem integração ampla de informações e análise de dados."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "O mais recente modelo GPT-4 Turbo possui funcionalidades visuais. Agora, solicitações visuais podem ser feitas usando o modo JSON e chamadas de função. O GPT-4 Turbo é uma versão aprimorada, oferecendo suporte econômico para tarefas multimodais. Ele encontra um equilíbrio entre precisão e eficiência, adequado para aplicações que requerem interação em tempo real."
},
+ "gpt-4.5-preview": {
+ "description": "Versão de pesquisa do GPT-4.5, que é o nosso maior e mais poderoso modelo GPT até agora. Ele possui um amplo conhecimento sobre o mundo e consegue entender melhor a intenção do usuário, destacando-se em tarefas criativas e planejamento autônomo. O GPT-4.5 aceita entradas de texto e imagem, gerando saídas de texto (incluindo saídas estruturadas). Suporta recursos essenciais para desenvolvedores, como chamadas de função, API em lote e saída em fluxo. O GPT-4.5 se destaca especialmente em tarefas que requerem criatividade, pensamento aberto e diálogo (como escrita, aprendizado ou exploração de novas ideias). A data limite do conhecimento é outubro de 2023."
+ },
"gpt-4o": {
"description": "O ChatGPT-4o é um modelo dinâmico, atualizado em tempo real para manter a versão mais atual. Ele combina uma poderosa capacidade de compreensão e geração de linguagem, adequado para cenários de aplicação em larga escala, incluindo atendimento ao cliente, educação e suporte técnico."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "O ChatGPT-4o é um modelo dinâmico, atualizado em tempo real para manter a versão mais atual. Ele combina uma poderosa capacidade de compreensão e geração de linguagem, adequado para cenários de aplicação em larga escala, incluindo atendimento ao cliente, educação e suporte técnico."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o é um modelo dinâmico, atualizado em tempo real para manter a versão mais atualizada. Combina uma poderosa compreensão e capacidade de geração de linguagem, adequado para cenários de aplicação em larga escala, incluindo atendimento ao cliente, educação e suporte técnico."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Modelo de áudio GPT-4o, suporta entrada e saída de áudio."
+ },
"gpt-4o-mini": {
"description": "O GPT-4o mini é o mais recente modelo lançado pela OpenAI após o GPT-4 Omni, suportando entrada de texto e imagem e gerando texto como saída. Como seu modelo compacto mais avançado, ele é muito mais acessível do que outros modelos de ponta recentes, custando mais de 60% menos que o GPT-3.5 Turbo. Ele mantém uma inteligência de ponta, ao mesmo tempo que oferece um custo-benefício significativo. O GPT-4o mini obteve uma pontuação de 82% no teste MMLU e atualmente está classificado acima do GPT-4 em preferências de chat."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Versão em tempo real do GPT-4o-mini, suporta entrada e saída de áudio e texto em tempo real."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Versão em tempo real do GPT-4o, suporta entrada e saída de áudio e texto em tempo real."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Versão em tempo real do GPT-4o, suporta entrada e saída de áudio e texto em tempo real."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Versão em tempo real do GPT-4o, suporta entrada e saída de áudio e texto em tempo real."
+ },
+ "grok-2-1212": {
+ "description": "Este modelo apresenta melhorias em precisão, conformidade com instruções e capacidade multilíngue."
+ },
+ "grok-2-vision-1212": {
+ "description": "Este modelo apresenta melhorias em precisão, conformidade com instruções e capacidade multilíngue."
+ },
+ "grok-beta": {
+ "description": "Apresenta desempenho equivalente ao Grok 2, mas com maior eficiência, velocidade e funcionalidades."
+ },
+ "grok-vision-beta": {
+ "description": "O mais recente modelo de compreensão de imagem, capaz de lidar com uma variedade de informações visuais, incluindo documentos, gráficos, capturas de tela e fotos."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B é um modelo de linguagem que combina criatividade e inteligência, integrando vários modelos de ponta."
},
+ "hunyuan-code": {
+ "description": "O mais recente modelo de geração de código Hunyuan, treinado com 200B de dados de código de alta qualidade, com seis meses de treinamento de dados SFT de alta qualidade, aumentando o comprimento da janela de contexto para 8K, destacando-se em métricas automáticas de geração de código em cinco linguagens; em avaliações de qualidade de código em dez aspectos em cinco linguagens, o desempenho está na primeira divisão."
+ },
+ "hunyuan-functioncall": {
+ "description": "O mais recente modelo FunctionCall da arquitetura MOE Hunyuan, treinado com dados de alta qualidade de FunctionCall, com uma janela de contexto de 32K, liderando em várias métricas de avaliação."
+ },
+ "hunyuan-large": {
+ "description": "O modelo Hunyuan-large possui um total de aproximadamente 389B de parâmetros, com cerca de 52B de parâmetros ativados, sendo o modelo MoE de código aberto com a maior escala de parâmetros e melhor desempenho na arquitetura Transformer atualmente disponível no mercado."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Especializado em tarefas de texto longo, como resumo de documentos e perguntas e respostas de documentos, também possui a capacidade de lidar com tarefas gerais de geração de texto. Apresenta desempenho excepcional na análise e geração de textos longos, conseguindo atender efetivamente às demandas complexas e detalhadas de processamento de conteúdo longo."
+ },
+ "hunyuan-lite": {
+ "description": "Atualizado para uma estrutura MOE, com uma janela de contexto de 256k, liderando em várias avaliações em NLP, código, matemática e setores diversos em comparação com muitos modelos de código aberto."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Modelo multimodal mais recente de 7B da Hunyuan, com janela de contexto de 32K, suporta diálogos multimodais em cenários em chinês e português, reconhecimento de objetos em imagens, compreensão de documentos e tabelas, matemática multimodal, entre outros, superando modelos concorrentes de 7B em várias métricas de avaliação."
+ },
+ "hunyuan-pro": {
+ "description": "Modelo de texto longo MOE-32K com trilhões de parâmetros. Alcança níveis de liderança absoluta em vários benchmarks, com capacidades complexas de instrução e raciocínio, habilidades matemáticas complexas, suporte a chamadas de função, otimizado para áreas como tradução multilíngue, finanças, direito e saúde."
+ },
+ "hunyuan-role": {
+ "description": "O mais recente modelo de interpretação de papéis Hunyuan, um modelo de interpretação de papéis ajustado e treinado oficialmente pela Hunyuan, que combina o modelo Hunyuan com um conjunto de dados de cenários de interpretação de papéis, apresentando um desempenho básico melhor em cenários de interpretação de papéis."
+ },
+ "hunyuan-standard": {
+ "description": "Adota uma estratégia de roteamento superior, ao mesmo tempo que mitiga problemas de balanceamento de carga e convergência de especialistas. Em termos de textos longos, o índice de precisão atinge 99,9%. O MOE-32K oferece uma relação custo-benefício relativamente melhor, equilibrando desempenho e preço, permitindo o processamento de entradas de texto longo."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Adota uma estratégia de roteamento superior, ao mesmo tempo que mitiga problemas de balanceamento de carga e convergência de especialistas. Em termos de textos longos, o índice de precisão atinge 99,9%. O MOE-256K rompe ainda mais em comprimento e desempenho, expandindo significativamente o comprimento de entrada permitido."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Modelo multimodal mais recente da Hunyuan, suporta respostas em múltiplas línguas, com habilidades equilibradas em chinês e português."
+ },
+ "hunyuan-translation": {
+ "description": "Suporta tradução entre 15 idiomas, incluindo chinês, inglês, japonês, francês, português, espanhol, turco, russo, árabe, coreano, italiano, alemão, vietnamita, malaio e indonésio, com avaliação automatizada baseada no conjunto de testes de tradução em múltiplos cenários e pontuação COMET, superando modelos de tamanho semelhante no mercado em termos de capacidade de tradução entre idiomas."
+ },
+ "hunyuan-translation-lite": {
+ "description": "O modelo de tradução Hunyuan suporta tradução em estilo de diálogo em linguagem natural; suporta tradução entre 15 idiomas, incluindo chinês, inglês, japonês, francês, português, espanhol, turco, russo, árabe, coreano, italiano, alemão, vietnamita, malaio e indonésio."
+ },
+ "hunyuan-turbo": {
+ "description": "Versão de pré-visualização do novo modelo de linguagem de próxima geração Hunyuan, utilizando uma nova estrutura de modelo de especialistas mistos (MoE), com eficiência de inferência mais rápida e desempenho superior em comparação ao Hunyuan-Pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Versão fixa do hunyuan-turbo de 20 de novembro de 2024, uma versão intermediária entre hunyuan-turbo e hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Esta versão otimiza: escalonamento de instruções de dados, aumentando significativamente a capacidade de generalização do modelo; melhoria substancial nas habilidades matemáticas, de codificação e de raciocínio lógico; otimização das capacidades de compreensão de texto e palavras; melhoria na qualidade da geração de conteúdo de criação de texto."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Otimização da experiência geral, incluindo compreensão de NLP, criação de texto, conversas informais, perguntas e respostas de conhecimento, tradução, entre outros; aumento da humanização, otimização da inteligência emocional do modelo; melhoria na capacidade do modelo de esclarecer ativamente em casos de intenção ambígua; aprimoramento na capacidade de lidar com questões de análise de palavras; melhoria na qualidade e interatividade da criação; aprimoramento da experiência em múltiplas interações."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Novo modelo de linguagem visual de próxima geração da Hunyuan, adotando uma nova estrutura de modelo de especialistas mistos (MoE), com melhorias abrangentes em relação ao modelo anterior nas capacidades de reconhecimento básico, criação de conteúdo, perguntas e respostas de conhecimento, e análise e raciocínio relacionados à compreensão de texto e imagem."
+ },
+ "hunyuan-vision": {
+ "description": "O mais recente modelo multimodal Hunyuan, que suporta a entrada de imagens e texto para gerar conteúdo textual."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "O modelo de código aberto inovador InternLM2.5, com um grande número de parâmetros, melhora a inteligência do diálogo."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 oferece soluções de diálogo inteligente em múltiplos cenários."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "O modelo Llama 3.1 70B Instruct possui 70B de parâmetros, capaz de oferecer desempenho excepcional em tarefas de geração de texto e instrução em larga escala."
+ "internlm2-pro-chat": {
+ "description": "Modelo mais antigo que ainda estamos mantendo, disponível em opções de 7B e 20B de parâmetros."
+ },
+ "internlm2.5-latest": {
+ "description": "Nossa mais recente série de modelos, com desempenho de raciocínio excepcional, suportando um comprimento de contexto de 1M e capacidades aprimoradas de seguimento de instruções e chamadas de ferramentas."
+ },
+ "internlm3-latest": {
+ "description": "Nossa mais recente série de modelos, com desempenho de inferência excepcional, liderando entre modelos de código aberto de mesma escala. Aponta por padrão para nossa mais recente série de modelos InternLM3."
+ },
+ "jina-deepsearch-v1": {
+ "description": "A busca profunda combina pesquisa na web, leitura e raciocínio para realizar investigações abrangentes. Você pode vê-la como um agente que aceita suas tarefas de pesquisa - ela realizará uma busca extensa e passará por várias iterações antes de fornecer uma resposta. Esse processo envolve pesquisa contínua, raciocínio e resolução de problemas sob diferentes ângulos. Isso é fundamentalmente diferente de gerar respostas diretamente a partir de dados pré-treinados de grandes modelos padrão e de sistemas RAG tradicionais que dependem de buscas superficiais únicas."
+ },
+ "kimi-latest": {
+ "description": "O produto assistente inteligente Kimi utiliza o mais recente modelo Kimi, que pode conter recursos ainda não estáveis. Suporta compreensão de imagens e seleciona automaticamente o modelo de cobrança de 8k/32k/128k com base no comprimento do contexto da solicitação."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM é um modelo de linguagem experimental e específico para tarefas, treinado para atender aos princípios da ciência da aprendizagem, podendo seguir instruções sistemáticas em cenários de ensino e aprendizagem, atuando como um mentor especialista, entre outros."
+ },
+ "lite": {
+ "description": "Spark Lite é um modelo de linguagem grande leve, com latência extremamente baixa e alta eficiência de processamento, totalmente gratuito e aberto, suportando funcionalidades de busca online em tempo real. Sua característica de resposta rápida o torna excelente para aplicações de inferência em dispositivos de baixo poder computacional e ajuste fino de modelos, proporcionando aos usuários uma excelente relação custo-benefício e experiência inteligente, especialmente em cenários de perguntas e respostas, geração de conteúdo e busca."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B oferece capacidade de raciocínio AI mais poderosa, adequada para aplicações complexas, suportando um processamento computacional extenso e garantindo eficiência e precisão."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B é um modelo de alto desempenho, oferecendo capacidade de geração de texto rápida, ideal para cenários de aplicação que exigem eficiência em larga escala e custo-benefício."
},
- "llama-3.1-8b-instruct": {
- "description": "O modelo Llama 3.1 8B Instruct possui 8B de parâmetros, suportando a execução eficiente de tarefas de instrução, oferecendo excelente capacidade de geração de texto."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Capacidade excepcional de raciocínio visual em imagens de alta resolução, adequada para aplicações de compreensão visual."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "O modelo Llama 3.1 Sonar Huge Online possui 405B de parâmetros, suportando um comprimento de contexto de aproximadamente 127.000 tokens, projetado para aplicações de chat online complexas."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "O modelo Llama 3.1 Sonar Large Chat possui 70B de parâmetros, suportando um comprimento de contexto de aproximadamente 127.000 tokens, adequado para tarefas de chat offline complexas."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Capacidade avançada de raciocínio visual para aplicações de agentes de compreensão visual."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "O modelo Llama 3.1 Sonar Large Online possui 70B de parâmetros, suportando um comprimento de contexto de aproximadamente 127.000 tokens, adequado para tarefas de chat de alta capacidade e diversidade."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "O modelo Llama 3.1 Sonar Small Chat possui 8B de parâmetros, projetado para chats offline, suportando um comprimento de contexto de aproximadamente 127.000 tokens."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 é o modelo de linguagem de código aberto multilíngue mais avançado da série Llama, oferecendo desempenho comparável ao modelo 405B a um custo extremamente baixo. Baseado na estrutura Transformer, e aprimorado por meio de ajuste fino supervisionado (SFT) e aprendizado por reforço com feedback humano (RLHF) para aumentar a utilidade e a segurança. Sua versão ajustada para instruções é otimizada para diálogos multilíngues, superando muitos modelos de chat de código aberto e fechado em vários benchmarks da indústria. A data limite de conhecimento é dezembro de 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "O modelo Llama 3.1 Sonar Small Online possui 8B de parâmetros, suportando um comprimento de contexto de aproximadamente 127.000 tokens, projetado para chats online, capaz de processar eficientemente diversas interações textuais."
+ "llama-3.3-70b-versatile": {
+ "description": "O modelo de linguagem multilíngue Meta Llama 3.3 (LLM) é um modelo gerador pré-treinado e ajustado para instruções, com 70B (entrada/saída de texto). O modelo de texto puro ajustado para instruções do Llama 3.3 é otimizado para casos de uso de diálogo multilíngue e supera muitos modelos de chat open source e fechados disponíveis em benchmarks comuns da indústria."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B oferece capacidade de processamento incomparável para complexidade, projetado sob medida para projetos de alta demanda."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral é projetado para pesquisa científica e raciocínio matemático, oferecendo capacidade de cálculo eficaz e interpretação de resultados."
},
+ "max-32k": {
+ "description": "Spark Max 32K possui uma capacidade de processamento de contexto grande, com melhor compreensão de contexto e capacidade de raciocínio lógico, suportando entradas de texto de 32K tokens, adequado para leitura de documentos longos, perguntas e respostas de conhecimento privado e outros cenários."
+ },
"meta-llama-3-70b-instruct": {
"description": "Um poderoso modelo com 70 bilhões de parâmetros, destacando-se em raciocínio, codificação e amplas aplicações linguísticas."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) oferece excelente capacidade de processamento de linguagem e uma experiência interativa notável."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 oferece excelente capacidade de processamento de linguagem e uma experiência interativa excepcional."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) é um modelo de chat poderoso, suportando necessidades de diálogo complexas."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) oferece suporte multilíngue, abrangendo um rico conhecimento em diversas áreas."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 é o modelo de linguagem de código aberto multilíngue mais avançado da série Llama, oferecendo uma experiência de desempenho comparável ao modelo de 405B a um custo extremamente baixo. Baseado na estrutura Transformer e aprimorado por meio de ajuste fino supervisionado (SFT) e aprendizado por reforço com feedback humano (RLHF) para aumentar a utilidade e segurança. Sua versão ajustada para instruções é otimizada para diálogos multilíngues, superando muitos modelos de chat de código aberto e fechado em vários benchmarks da indústria. Data limite de conhecimento é dezembro de 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "O Meta Llama 3.3 é um modelo de linguagem de grande escala multilíngue (LLM) com 70B (entrada/saída de texto) que é um modelo gerado por pré-treinamento e ajuste de instruções. O modelo de texto puro ajustado por instruções do Llama 3.3 foi otimizado para casos de uso de diálogo multilíngue e supera muitos modelos de chat de código aberto e fechados disponíveis em benchmarks de indústria comuns."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite é ideal para ambientes que exigem alta eficiência e baixa latência."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "O modelo Llama 3.1 Turbo 405B oferece suporte a um contexto de capacidade extremamente grande para processamento de grandes volumes de dados, destacando-se em aplicações de inteligência artificial em larga escala."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 é o modelo líder lançado pela Meta, suportando até 405B de parâmetros, aplicável em diálogos complexos, tradução multilíngue e análise de dados."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B oferece suporte a diálogos multilíngues de forma eficiente."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct otimiza cenários de diálogo de alta qualidade, com desempenho superior a muitos modelos fechados."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct é a versão mais recente da Meta, otimizada para gerar diálogos de alta qualidade, superando muitos modelos fechados de liderança."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct é projetado para diálogos de alta qualidade, destacando-se em avaliações humanas, especialmente em cenários de alta interação."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 oferece suporte multilíngue e é um dos modelos geradores líderes do setor."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 é projetado para lidar com tarefas que combinam dados visuais e textuais. Ele se destaca em tarefas como descrição de imagens e perguntas visuais, superando a lacuna entre geração de linguagem e raciocínio visual."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 é o modelo de linguagem de código aberto multilíngue mais avançado da série Llama, oferecendo desempenho comparável ao modelo 405B a um custo extremamente baixo. Baseado na estrutura Transformer, e aprimorado por meio de ajuste fino supervisionado (SFT) e aprendizado por reforço com feedback humano (RLHF) para aumentar a utilidade e a segurança. Sua versão ajustada para instruções é otimizada para diálogos multilíngues, superando muitos modelos de chat de código aberto e fechado em vários benchmarks da indústria. A data limite de conhecimento é dezembro de 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 é o modelo de linguagem de código aberto multilíngue mais avançado da série Llama, oferecendo desempenho comparável ao modelo 405B a um custo extremamente baixo. Baseado na estrutura Transformer, e aprimorado por meio de ajuste fino supervisionado (SFT) e aprendizado por reforço com feedback humano (RLHF) para aumentar a utilidade e a segurança. Sua versão ajustada para instruções é otimizada para diálogos multilíngues, superando muitos modelos de chat de código aberto e fechado em vários benchmarks da indústria. A data limite de conhecimento é dezembro de 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct é o maior e mais poderoso modelo da série Llama 3.1 Instruct, sendo um modelo altamente avançado para raciocínio conversacional e geração de dados sintéticos, que também pode ser usado como base para pré-treinamento ou ajuste fino em domínios específicos. Os modelos de linguagem de grande escala (LLMs) multilíngues oferecidos pelo Llama 3.1 são um conjunto de modelos geradores pré-treinados e ajustados por instruções, incluindo tamanhos de 8B, 70B e 405B (entrada/saída de texto). Os modelos de texto ajustados por instruções do Llama 3.1 (8B, 70B, 405B) são otimizados para casos de uso de diálogo multilíngue e superaram muitos modelos de chat de código aberto disponíveis em benchmarks comuns da indústria. O Llama 3.1 é projetado para uso comercial e de pesquisa em várias línguas. Os modelos de texto ajustados por instruções são adequados para chats semelhantes a assistentes, enquanto os modelos pré-treinados podem se adaptar a várias tarefas de geração de linguagem natural. O modelo Llama 3.1 também suporta a utilização de sua saída para melhorar outros modelos, incluindo geração de dados sintéticos e refinamento. O Llama 3.1 é um modelo de linguagem autoregressivo que utiliza uma arquitetura de transformador otimizada. As versões ajustadas utilizam ajuste fino supervisionado (SFT) e aprendizado por reforço com feedback humano (RLHF) para alinhar-se às preferências humanas em relação à utilidade e segurança."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 é um modelo de linguagem de grande escala (LLM) aberto voltado para desenvolvedores, pesquisadores e empresas, projetado para ajudá-los a construir, experimentar e expandir suas ideias de IA geradora de forma responsável. Como parte de um sistema de base para inovação da comunidade global, é ideal para dispositivos de borda com capacidade de computação e recursos limitados, além de tempos de treinamento mais rápidos."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B é o modelo leve e rápido mais recente da Microsoft AI, com desempenho próximo a 10 vezes o de modelos de código aberto existentes."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "LLM avançado, suporta geração de dados sintéticos, destilação de conhecimento e raciocínio, adequado para chatbots, programação e tarefas de domínio específico."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Capacita diálogos complexos, com excelente compreensão de contexto, capacidade de raciocínio e geração de texto."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Modelo de ponta avançado, com compreensão de linguagem, excelente capacidade de raciocínio e geração de texto."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Modelo de visão-linguagem de ponta, especializado em raciocínio de alta qualidade a partir de imagens."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Modelo de linguagem de ponta avançado e compacto, com compreensão de linguagem, excelente capacidade de raciocínio e geração de texto."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Modelo de linguagem de ponta avançado e compacto, com compreensão de linguagem, excelente capacidade de raciocínio e geração de texto."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Modelo de visão-linguagem de ponta, especializado em raciocínio de alta qualidade a partir de imagens."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Modelo LLM avançado, especializado em raciocínio, matemática, conhecimento geral e chamadas de função."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 é um modelo de linguagem fornecido pela Microsoft AI, que se destaca em diálogos complexos, multilíngue, raciocínio e assistentes inteligentes."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B é o modelo Wizard mais avançado da Microsoft, demonstrando um desempenho extremamente competitivo."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V é a nova geração de grandes modelos multimodais lançada pela OpenBMB, com excelente capacidade de reconhecimento de OCR e compreensão multimodal, suportando uma ampla gama de cenários de aplicação."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B é o modelo de ponta da Mistral para aplicações de edge computing."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B é o modelo de edge computing altamente custo-efetivo da Mistral."
+ },
"mistral": {
"description": "Mistral é um modelo de 7B lançado pela Mistral AI, adequado para demandas de processamento de linguagem variáveis."
},
"mistral-large": {
"description": "Mixtral Large é o modelo de destaque da Mistral, combinando capacidades de geração de código, matemática e raciocínio, suportando uma janela de contexto de 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) é um modelo de linguagem avançado (LLM) com capacidades de raciocínio, conhecimento e codificação de última geração."
- },
"mistral-large-latest": {
"description": "Mistral Large é o modelo de destaque, especializado em tarefas multilíngues, raciocínio complexo e geração de código, sendo a escolha ideal para aplicações de alto nível."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 oferece capacidade computacional eficiente e compreensão de linguagem natural, adequada para uma ampla gama de aplicações."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B é um modelo compacto, mas de alto desempenho, especializado em processamento em lote e tarefas simples, como classificação e geração de texto, com boa capacidade de raciocínio."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) é um super modelo de linguagem, suportando demandas de processamento extremamente altas."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B é um modelo de especialistas esparsos pré-treinados, utilizado para tarefas de texto de uso geral."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B é um modelo de especialistas esparsos, que utiliza múltiplos parâmetros para aumentar a velocidade de raciocínio, ideal para tarefas de geração de código e multilíngues."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct é um modelo de padrão industrial de alto desempenho, com otimização de velocidade e suporte a longos contextos."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K é um modelo com capacidade de processamento de contexto ultra longo, adequado para gerar textos muito longos, atendendo a demandas complexas de geração, capaz de lidar com até 128.000 tokens, ideal para pesquisa, acadêmicos e geração de documentos extensos."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "O modelo visual Kimi (incluindo moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) é capaz de entender o conteúdo das imagens, incluindo texto, cores e formas dos objetos."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K oferece capacidade de processamento de contexto de comprimento médio, capaz de lidar com 32.768 tokens, especialmente adequado para gerar vários documentos longos e diálogos complexos, aplicável em criação de conteúdo, geração de relatórios e sistemas de diálogo."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "O modelo visual Kimi (incluindo moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) é capaz de entender o conteúdo das imagens, incluindo texto, cores e formas dos objetos."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K é projetado para tarefas de geração de texto curto, com desempenho de processamento eficiente, capaz de lidar com 8.192 tokens, ideal para diálogos curtos, anotações e geração rápida de conteúdo."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "O modelo visual Kimi (incluindo moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, etc.) é capaz de entender o conteúdo das imagens, incluindo texto, cores e formas dos objetos."
+ },
+ "moonshot-v1-auto": {
+ "description": "O Moonshot V1 Auto pode escolher o modelo adequado com base na quantidade de Tokens ocupados pelo contexto atual."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B é uma versão aprimorada do Nous Hermes 2, contendo os conjuntos de dados mais recentes desenvolvidos internamente."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B é um modelo de linguagem em larga escala personalizado pela NVIDIA, projetado para aumentar a utilidade das respostas geradas pelo LLM em relação às consultas dos usuários. Este modelo se destacou em benchmarks como Arena Hard, AlpacaEval 2 LC e GPT-4-Turbo MT-Bench, ocupando o primeiro lugar em todos os três benchmarks de alinhamento automático até 1º de outubro de 2024. O modelo foi treinado usando RLHF (especialmente REINFORCE), Llama-3.1-Nemotron-70B-Reward e HelpSteer2-Preference prompts, com base no modelo Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Modelo de linguagem único, oferecendo precisão e eficiência incomparáveis."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct é um modelo de linguagem de grande porte personalizado pela NVIDIA, projetado para melhorar a utilidade das respostas geradas pelo LLM."
+ },
+ "o1": {
+ "description": "Focado em raciocínio avançado e resolução de problemas complexos, incluindo tarefas matemáticas e científicas. Muito adequado para aplicativos que exigem compreensão profunda do contexto e gerenciamento de fluxos de trabalho."
+ },
"o1-mini": {
"description": "o1-mini é um modelo de raciocínio rápido e econômico, projetado para cenários de programação, matemática e ciências. Este modelo possui um contexto de 128K e uma data limite de conhecimento em outubro de 2023."
},
"o1-preview": {
"description": "o1 é o novo modelo de raciocínio da OpenAI, adequado para tarefas complexas que exigem amplo conhecimento geral. Este modelo possui um contexto de 128K e uma data limite de conhecimento em outubro de 2023."
},
+ "o3-mini": {
+ "description": "o3-mini é nosso mais recente modelo de inferência em miniatura, oferecendo alta inteligência com os mesmos custos e metas de latência que o o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba é um modelo de linguagem Mamba 2 focado em geração de código, oferecendo forte suporte para tarefas avançadas de codificação e raciocínio."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B é um modelo de especialistas esparsos, utilizando múltiplos parâmetros para aumentar a velocidade de raciocínio, adequado para tarefas de geração de linguagem e código."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o é um modelo dinâmico, atualizado em tempo real para manter a versão mais atual. Ele combina forte compreensão e capacidade de geração de linguagem, adequado para cenários de aplicação em larga escala, incluindo atendimento ao cliente, educação e suporte técnico."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o é um modelo dinâmico, atualizado em tempo real para manter a versão mais recente. Combina uma poderosa capacidade de compreensão e geração de linguagem, adequado para cenários de aplicação em larga escala, incluindo atendimento ao cliente, educação e suporte técnico."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini é o mais recente modelo da OpenAI, lançado após o GPT-4 Omni, que suporta entrada de texto e imagem e saída de texto. Como seu modelo compacto mais avançado, é muito mais barato do que outros modelos de ponta recentes e custa mais de 60% menos que o GPT-3.5 Turbo. Ele mantém inteligência de ponta, ao mesmo tempo que oferece uma relação custo-benefício significativa. O GPT-4o mini obteve uma pontuação de 82% no teste MMLU e atualmente está classificado acima do GPT-4 em preferências de chat."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "O modelo Pixtral demonstra forte capacidade em tarefas de compreensão de gráficos e imagens, perguntas e respostas de documentos, raciocínio multimodal e seguimento de instruções, podendo ingerir imagens em resolução natural e proporções, além de processar um número arbitrário de imagens em uma janela de contexto longa de até 128K tokens."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large é um modelo multimodal de código aberto com 124 bilhões de parâmetros, baseado no Mistral Large 2. Este é o segundo modelo da nossa família multimodal, demonstrando capacidades de compreensão de imagem de nível avançado."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K possui uma capacidade de processamento de contexto extremamente grande, capaz de lidar com até 128K de informações contextuais, especialmente adequado para análise completa e processamento de associações lógicas de longo prazo em conteúdos longos, podendo oferecer lógica fluida e consistente e suporte a diversas citações em comunicações textuais complexas."
+ },
+ "qvq-72b-preview": {
+ "description": "O modelo QVQ é um modelo de pesquisa experimental desenvolvido pela equipe Qwen, focado em melhorar a capacidade de raciocínio visual, especialmente na área de raciocínio matemático."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Modelo de código Qwen."
+ },
"qwen-coder-turbo-latest": {
"description": "Modelo de código Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "O modelo de matemática Qwen é especificamente projetado para resolver problemas matemáticos."
},
+ "qwen-max": {
+ "description": "Modelo de linguagem em larga escala com trilhões de parâmetros do Qwen, suportando entradas em diferentes idiomas, como português e inglês, atualmente a versão API por trás do produto Qwen 2.5."
+ },
"qwen-max-latest": {
"description": "O modelo de linguagem em larga escala Qwen Max, com trilhões de parâmetros, que suporta entradas em diferentes idiomas, incluindo chinês e inglês, e é o modelo de API por trás da versão do produto Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "A série de modelos Qwen-Omni suporta a entrada de dados em várias modalidades, incluindo vídeo, áudio, imagens e texto, e produz saídas em áudio e texto."
+ },
+ "qwen-plus": {
+ "description": "Versão aprimorada do modelo de linguagem em larga escala Qwen, que suporta entradas em diferentes idiomas, como português e inglês."
+ },
"qwen-plus-latest": {
"description": "A versão aprimorada do modelo de linguagem em larga escala Qwen Plus, que suporta entradas em diferentes idiomas, incluindo chinês e inglês."
},
+ "qwen-turbo": {
+ "description": "O modelo de linguagem em larga escala Qwen suporta entradas em diferentes idiomas, como português e inglês."
+ },
"qwen-turbo-latest": {
"description": "O modelo de linguagem em larga escala Qwen Turbo, que suporta entradas em diferentes idiomas, incluindo chinês e inglês."
},
"qwen-vl-chat-v1": {
"description": "O Qwen VL suporta uma maneira de interação flexível, incluindo múltiplas imagens, perguntas e respostas em várias rodadas, e capacidades criativas."
},
- "qwen-vl-max": {
- "description": "O Qwen é um modelo de linguagem visual em larga escala. Em comparação com a versão aprimorada, ele melhora ainda mais a capacidade de raciocínio visual e a adesão a instruções, oferecendo um nível mais alto de percepção e cognição visual."
+ "qwen-vl-max-latest": {
+ "description": "Modelo de linguagem visual em escala ultra grande Qwen. Em comparação com a versão aprimorada, melhora ainda mais a capacidade de raciocínio visual e de seguir instruções, oferecendo um nível mais alto de percepção e cognição visual."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "O OCR Qwen é um modelo especializado em extração de texto, focado na capacidade de extrair texto de imagens de documentos, tabelas, questões de exames, escrita manual, entre outros. Ele pode reconhecer vários idiomas, atualmente suportando: chinês, inglês, francês, japonês, coreano, alemão, russo, italiano, vietnamita e árabe."
},
- "qwen-vl-plus": {
- "description": "O Qwen é uma versão aprimorada do modelo de linguagem visual em larga escala, melhorando significativamente a capacidade de reconhecimento de detalhes e texto, suportando imagens com resolução superior a um milhão de pixels e qualquer proporção de largura e altura."
+ "qwen-vl-plus-latest": {
+ "description": "Versão aprimorada do modelo de linguagem visual em larga escala Qwen. Aumenta significativamente a capacidade de reconhecimento de detalhes e de texto, suportando resolução de mais de um milhão de pixels e imagens de qualquer proporção."
},
"qwen-vl-v1": {
"description": "Inicializado com o modelo de linguagem Qwen-7B, adicionando um modelo de imagem, um modelo pré-treinado com resolução de entrada de imagem de 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 é uma nova série de modelos de linguagem grande Qwen. Qwen2 7B é um modelo baseado em transformer, com excelente desempenho em compreensão de linguagem, capacidade multilíngue, programação, matemática e raciocínio."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 é uma nova série de grandes modelos de linguagem, com capacidades de compreensão e geração mais robustas."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL é a versão mais recente do modelo Qwen-VL, alcançando desempenho de ponta em benchmarks de compreensão visual, incluindo MathVista, DocVQA, RealWorldQA e MTVQA. Qwen2-VL é capaz de entender vídeos de mais de 20 minutos, permitindo perguntas e respostas, diálogos e criação de conteúdo de alta qualidade baseados em vídeo. Ele também possui capacidades complexas de raciocínio e tomada de decisão, podendo ser integrado a dispositivos móveis, robôs, etc., para operações automáticas baseadas em ambientes visuais e instruções textuais. Além do inglês e do chinês, o Qwen2-VL agora também suporta a compreensão de texto em diferentes idiomas em imagens, incluindo a maioria das línguas europeias, japonês, coreano, árabe e vietnamita."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct é uma das mais recentes séries de modelos de linguagem grande lançadas pela Alibaba Cloud. Este modelo de 72B apresenta capacidades significativamente aprimoradas em áreas como codificação e matemática. O modelo também oferece suporte a múltiplas línguas, cobrindo mais de 29 idiomas, incluindo chinês e inglês. O modelo teve melhorias significativas em seguir instruções, entender dados estruturados e gerar saídas estruturadas (especialmente JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct é uma das mais recentes séries de modelos de linguagem grande lançadas pela Alibaba Cloud. Este modelo de 32B apresenta capacidades significativamente aprimoradas em áreas como codificação e matemática. O modelo oferece suporte a múltiplas línguas, cobrindo mais de 29 idiomas, incluindo chinês e inglês. O modelo teve melhorias significativas em seguir instruções, entender dados estruturados e gerar saídas estruturadas (especialmente JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM voltado para chinês e inglês, focado em linguagem, programação, matemática, raciocínio e outras áreas."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "LLM avançado, suporta geração de código, raciocínio e correção, abrangendo linguagens de programação populares."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Modelo de código de médio porte poderoso, suporta comprimento de contexto de 32K, especializado em programação multilíngue."
+ },
"qwen2": {
"description": "Qwen2 é a nova geração de modelo de linguagem em larga escala da Alibaba, oferecendo desempenho excepcional para atender a diversas necessidades de aplicação."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 é a nova geração de modelo de linguagem em larga escala da Alibaba, oferecendo desempenho excepcional para atender a diversas necessidades de aplicação."
+ },
"qwen2.5-14b-instruct": {
"description": "Modelo de 14B parâmetros do Qwen 2.5, disponível como código aberto."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Modelo de 72B de código aberto do Qwen2.5."
+ },
"qwen2.5-32b-instruct": {
"description": "Modelo de 32B parâmetros do Qwen 2.5, disponível como código aberto."
},
@@ -824,13 +1599,16 @@
"description": "Modelo de 7B parâmetros do Qwen 2.5, disponível como código aberto."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "Versão de código aberto do modelo de código Qwen."
+ "description": "Versão open source do modelo de código do Qwen."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Versão open source do modelo de código Qwen."
},
"qwen2.5-coder-7b-instruct": {
"description": "Versão de código aberto do modelo de código Qwen."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "O modelo Qwen-Math possui uma forte capacidade de resolução de problemas matemáticos."
+ "description": "O modelo Qwen-Math possui poderosas capacidades de resolução de problemas matemáticos."
},
"qwen2.5-math-72b-instruct": {
"description": "O modelo Qwen-Math possui uma forte capacidade de resolução de problemas matemáticos."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "O modelo Qwen-Math possui uma forte capacidade de resolução de problemas matemáticos."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Aprimoramento geral em seguimento de instruções, matemática, resolução de problemas e código, com capacidade de reconhecimento de objetos aprimorada, suporte a formatos diversos para localização precisa de elementos visuais, compreensão de arquivos de vídeo longos (até 10 minutos) e localização de eventos em segundos, capaz de entender a sequência e a velocidade do tempo, suportando controle de agentes em OS ou Mobile com forte capacidade de extração de informações e saída em formato Json. Esta versão é a de 72B, a mais poderosa da série."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Aprimoramento geral em seguimento de instruções, matemática, resolução de problemas e código, com capacidade de reconhecimento de objetos aprimorada, suporte a formatos diversos para localização precisa de elementos visuais, compreensão de arquivos de vídeo longos (até 10 minutos) e localização de eventos em segundos, capaz de entender a sequência e a velocidade do tempo, suportando controle de agentes em OS ou Mobile com forte capacidade de extração de informações e saída em formato Json. Esta versão é a de 72B, a mais poderosa da série."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 é a nova geração de modelo de linguagem em larga escala da Alibaba, oferecendo desempenho excepcional para atender a diversas necessidades de aplicação."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 é a nova geração de modelo de linguagem em larga escala da Alibaba, oferecendo desempenho excepcional para atender a diversas necessidades de aplicação."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 é a nova geração de modelo de linguagem em larga escala da Alibaba, oferecendo desempenho excepcional para atender a diversas necessidades de aplicação."
+ },
"qwen2:0.5b": {
"description": "Qwen2 é a nova geração de modelo de linguagem em larga escala da Alibaba, oferecendo desempenho excepcional para atender a diversas necessidades de aplicação."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 é a nova geração de modelo de linguagem em larga escala da Alibaba, oferecendo desempenho excepcional para atender a diversas necessidades de aplicação."
},
- "solar-1-mini-chat": {
+ "qwq": {
+ "description": "QwQ é um modelo de pesquisa experimental, focado em melhorar a capacidade de raciocínio da IA."
+ },
+ "qwq-32b": {
+ "description": "Modelo de inferência QwQ treinado com base no modelo Qwen2.5-32B, que melhorou significativamente a capacidade de inferência do modelo através de aprendizado por reforço. Os indicadores principais do modelo, como código matemático (AIME 24/25, LiveCodeBench) e alguns indicadores gerais (IFEval, LiveBench, etc.), alcançaram o nível do DeepSeek-R1 versão completa, com todos os indicadores superando significativamente o DeepSeek-R1-Distill-Qwen-32B, que também é baseado no Qwen2.5-32B."
+ },
+ "qwq-32b-preview": {
+ "description": "O modelo QwQ é um modelo de pesquisa experimental desenvolvido pela equipe Qwen, focado em aprimorar a capacidade de raciocínio da IA."
+ },
+ "qwq-plus-latest": {
+ "description": "Modelo de inferência QwQ treinado com base no modelo Qwen2.5, que melhorou significativamente a capacidade de inferência do modelo através de aprendizado por reforço. Os indicadores principais do modelo, como código matemático (AIME 24/25, LiveCodeBench) e alguns indicadores gerais (IFEval, LiveBench, etc.), alcançaram o nível do DeepSeek-R1 versão completa."
+ },
+ "r1-1776": {
+ "description": "R1-1776 é uma versão do modelo DeepSeek R1, treinada posteriormente para fornecer informações factuais não filtradas e imparciais."
+ },
+ "solar-mini": {
"description": "Solar Mini é um LLM compacto, com desempenho superior ao GPT-3.5, possuindo forte capacidade multilíngue, suportando inglês e coreano, oferecendo uma solução eficiente e compacta."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) expande as capacidades do Solar Mini, focando no japonês, enquanto mantém eficiência e desempenho excepcional no uso do inglês e coreano."
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) expande as capacidades do Solar Mini, focando no japonês, enquanto mantém eficiência e desempenho excepcional no uso de inglês e coreano."
},
"solar-pro": {
"description": "Solar Pro é um LLM de alta inteligência lançado pela Upstage, focado na capacidade de seguir instruções em um único GPU, com pontuação IFEval acima de 80. Atualmente suporta inglês, com uma versão oficial planejada para lançamento em novembro de 2024, que expandirá o suporte a idiomas e comprimento de contexto."
},
+ "sonar": {
+ "description": "Produto de busca leve baseado em contexto de busca, mais rápido e mais barato que o Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "A Pesquisa Profunda realiza uma pesquisa abrangente de nível especialista e a sintetiza em relatórios acessíveis e acionáveis."
+ },
+ "sonar-pro": {
+ "description": "Produto de busca avançada que suporta contexto de busca, consultas avançadas e acompanhamento."
+ },
+ "sonar-reasoning": {
+ "description": "Novo produto API suportado pelo modelo de raciocínio da DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Um novo produto de API suportado pelo modelo de raciocínio DeepSeek."
+ },
"step-1-128k": {
"description": "Equilibra desempenho e custo, adequado para cenários gerais."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Modelo de alta velocidade, adequado para diálogos em tempo real."
},
+ "step-1.5v-mini": {
+ "description": "Este modelo possui uma poderosa capacidade de compreensão de vídeo."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Este modelo possui uma poderosa capacidade de compreensão de imagens, superando o 1o em áreas de matemática e programação. O modelo é menor que o 1o e oferece uma velocidade de saída mais rápida."
+ },
+ "step-1o-vision-32k": {
+ "description": "Este modelo possui uma poderosa capacidade de compreensão de imagens. Em comparação com a série de modelos step-1v, apresenta um desempenho visual superior."
+ },
"step-1v-32k": {
"description": "Suporta entradas visuais, aprimorando a experiência de interação multimodal."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Suporta interações de contexto em larga escala, adequado para cenários de diálogo complexos."
},
+ "step-2-mini": {
+ "description": "Um modelo de grande escala de alta velocidade baseado na nova arquitetura de atenção auto-desenvolvida MFA, alcançando resultados semelhantes ao step1 com um custo muito baixo, enquanto mantém uma maior taxa de transferência e um tempo de resposta mais rápido. Capaz de lidar com tarefas gerais, possui especialização em habilidades de codificação."
+ },
"taichu_llm": {
"description": "O modelo de linguagem Taichu possui uma forte capacidade de compreensão de linguagem, além de habilidades em criação de texto, perguntas e respostas, programação de código, cálculos matemáticos, raciocínio lógico, análise de sentimentos e resumo de texto. Inova ao combinar pré-treinamento com grandes dados e conhecimento rico de múltiplas fontes, aprimorando continuamente a tecnologia de algoritmos e absorvendo novos conhecimentos de vocabulário, estrutura, gramática e semântica de grandes volumes de dados textuais, proporcionando aos usuários informações e serviços mais convenientes e uma experiência mais inteligente."
},
- "taichu_vqa": {
- "description": "O Taichu 2.0V combina habilidades de compreensão de imagem, transferência de conhecimento e atribuição lógica, destacando-se no campo de perguntas e respostas baseadas em texto e imagem."
+ "taichu_vl": {
+ "description": "Integra capacidades de compreensão de imagens, transferência de conhecimento e atribuição lógica, destacando-se na área de perguntas e respostas baseadas em texto e imagem."
+ },
+ "text-embedding-3-large": {
+ "description": "O modelo de vetorização mais poderoso, adequado para tarefas em inglês e não inglês."
+ },
+ "text-embedding-3-small": {
+ "description": "Modelo de Embedding de nova geração, eficiente e econômico, adequado para recuperação de conhecimento, aplicações RAG e outros cenários."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Versão de código aberto da última geração do modelo pré-treinado GLM-4, lançado pela Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) oferece capacidade de computação aprimorada através de estratégias e arquiteturas de modelo eficientes."
},
+ "tts-1": {
+ "description": "O mais recente modelo de texto para fala, otimizado para velocidade em cenários em tempo real."
+ },
+ "tts-1-hd": {
+ "description": "O mais recente modelo de texto para fala, otimizado para qualidade."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) é adequado para tarefas de instrução refinadas, oferecendo excelente capacidade de processamento de linguagem."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet eleva o padrão da indústria, superando modelos concorrentes e Claude 3 Opus, apresentando um desempenho excepcional em uma ampla gama de avaliações, enquanto mantém a velocidade e o custo de nossos modelos de nível médio."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet é o modelo de próxima geração mais rápido da Anthropic. Em comparação com o Claude 3 Haiku, o Claude 3.7 Sonnet apresenta melhorias em várias habilidades e supera o maior modelo da geração anterior, o Claude 3 Opus, em muitos testes de referência de inteligência."
+ },
+ "whisper-1": {
+ "description": "Modelo de reconhecimento de voz universal, suporta reconhecimento de voz multilíngue, tradução de voz e identificação de idiomas."
+ },
"wizardlm2": {
"description": "WizardLM 2 é um modelo de linguagem fornecido pela Microsoft AI, destacando-se em diálogos complexos, multilíngue, raciocínio e assistentes inteligentes."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Excelente relação custo-benefício e desempenho excepcional. Ajuste de alta precisão baseado em desempenho, velocidade de raciocínio e custo."
},
+ "yi-lightning": {
+ "description": "Modelo de alto desempenho mais recente, garantindo saída de alta qualidade enquanto a velocidade de raciocínio é significativamente aprimorada."
+ },
+ "yi-lightning-lite": {
+ "description": "Versão leve, recomendada para uso com yi-lightning."
+ },
"yi-medium": {
"description": "Modelo de tamanho médio com ajuste fino, equilibrando capacidades e custo. Otimização profunda da capacidade de seguir instruções."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Modelo para tarefas visuais complexas, oferecendo alta performance em compreensão e análise de imagens."
+ },
+ "yi-vision-v2": {
+ "description": "Modelo para tarefas visuais complexas, oferecendo alta performance em compreensão e análise baseadas em múltiplas imagens."
}
}
diff --git a/DigitalHumanWeb/locales/pt-BR/plugin.json b/DigitalHumanWeb/locales/pt-BR/plugin.json
index 0a34b12..7815573 100644
--- a/DigitalHumanWeb/locales/pt-BR/plugin.json
+++ b/DigitalHumanWeb/locales/pt-BR/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Falha ao atualizar o plugin {{name}}",
"urlError": "O link não retornou conteúdo no formato JSON. Certifique-se de que o link é válido."
},
+ "inspector": {
+ "args": "Ver parâmetros",
+ "pluginRender": "Ver interface do plugin"
+ },
"list": {
"item": {
"deprecated.title": "Obsoleto",
@@ -130,6 +134,34 @@
"plugin": "Executando o plugin..."
},
"pluginList": "Lista de Plugins",
+ "search": {
+ "config": {
+ "addKey": "Adicionar chave",
+ "close": "Remover",
+ "confirm": "Configuração concluída, tente novamente"
+ },
+ "crawPages": {
+ "crawling": "Reconhecendo links",
+ "detail": {
+ "preview": "Prévia",
+ "raw": "Texto original",
+ "tooLong": "O conteúdo do texto é muito longo, o contexto da conversa manterá apenas os primeiros {{characters}} caracteres, e a parte excedente não será considerada no contexto da conversa"
+ },
+ "meta": {
+ "crawler": "Modo de Rastreamento",
+ "words": "Número de caracteres"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Digite",
+ "description": "Digite o URL do SearchXNG para começar a pesquisa na internet",
+ "keyPlaceholder": "Digite a chave",
+ "title": "Configurar o mecanismo de busca SearchXNG",
+ "unconfiguredDesc": "Por favor, entre em contato com o administrador para concluir a configuração do mecanismo de busca SearchXNG e começar a pesquisa na internet",
+ "unconfiguredTitle": "Mecanismo de busca SearchXNG ainda não configurado"
+ },
+ "title": "Pesquisa na internet"
+ },
"setting": "Configuração do Plugin",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/pt-BR/portal.json b/DigitalHumanWeb/locales/pt-BR/portal.json
index 6c890f7..d0df76e 100644
--- a/DigitalHumanWeb/locales/pt-BR/portal.json
+++ b/DigitalHumanWeb/locales/pt-BR/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Plugins",
- "actions": {
- "genAiMessage": "Gerar mensagem de IA",
- "summary": "Resumo",
- "summaryTooltip": "Resumir o conteúdo atual"
- },
"artifacts": {
"display": {
"code": "Código",
diff --git a/DigitalHumanWeb/locales/pt-BR/providers.json b/DigitalHumanWeb/locales/pt-BR/providers.json
index 96da851..368526d 100644
--- a/DigitalHumanWeb/locales/pt-BR/providers.json
+++ b/DigitalHumanWeb/locales/pt-BR/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs constrói modelos fundamentais e sistemas de inteligência artificial para empresas, acelerando a aplicação da inteligência artificial generativa na produção."
+ },
"ai360": {
"description": "360 AI é a plataforma de modelos e serviços de IA lançada pela empresa 360, oferecendo uma variedade de modelos avançados de processamento de linguagem natural, incluindo 360GPT2 Pro, 360GPT Pro, 360GPT Turbo e 360GPT Turbo Responsibility 8K. Esses modelos combinam grandes parâmetros e capacidades multimodais, sendo amplamente aplicados em geração de texto, compreensão semântica, sistemas de diálogo e geração de código. Com uma estratégia de preços flexível, a 360 AI atende a diversas necessidades dos usuários, apoiando a integração de desenvolvedores e promovendo a inovação e o desenvolvimento de aplicações inteligentes."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure oferece uma variedade de modelos avançados de IA, incluindo GPT-3.5 e a mais recente série GPT-4, suportando diversos tipos de dados e tarefas complexas, com foco em soluções de IA seguras, confiáveis e sustentáveis."
},
+ "azureai": {
+ "description": "A Azure oferece uma variedade de modelos de IA avançados, incluindo o GPT-3.5 e a mais recente série GPT-4, suportando diversos tipos de dados e tarefas complexas, comprometendo-se com soluções de IA seguras, confiáveis e sustentáveis."
+ },
"baichuan": {
"description": "Baichuan Intelligent é uma empresa focada no desenvolvimento de grandes modelos de inteligência artificial, cujos modelos se destacam em tarefas em chinês, como enciclopédias de conhecimento, processamento de textos longos e criação de conteúdo, superando modelos mainstream estrangeiros. A Baichuan Intelligent também possui capacidades multimodais líderes do setor, destacando-se em várias avaliações de autoridade. Seus modelos incluem Baichuan 4, Baichuan 3 Turbo e Baichuan 3 Turbo 128k, otimizados para diferentes cenários de aplicação, oferecendo soluções com alta relação custo-benefício."
},
"bedrock": {
"description": "Bedrock é um serviço oferecido pela Amazon AWS, focado em fornecer modelos de linguagem e visão de IA avançados para empresas. Sua família de modelos inclui a série Claude da Anthropic, a série Llama 3.1 da Meta, entre outros, abrangendo uma variedade de opções, desde modelos leves até de alto desempenho, suportando geração de texto, diálogos, processamento de imagens e outras tarefas, adequando-se a aplicações empresariais de diferentes escalas e necessidades."
},
+ "cloudflare": {
+ "description": "Execute modelos de aprendizado de máquina impulsionados por GPU sem servidor na rede global da Cloudflare."
+ },
"deepseek": {
"description": "A DeepSeek é uma empresa focada em pesquisa e aplicação de tecnologia de inteligência artificial, cujo modelo mais recente, DeepSeek-V2.5, combina capacidades de diálogo geral e processamento de código, alcançando melhorias significativas em alinhamento com preferências humanas, tarefas de escrita e seguimento de instruções."
},
+ "doubao": {
+ "description": "Um grande modelo desenvolvido internamente pela ByteDance. Validado através da prática em mais de 50 cenários de negócios dentro da ByteDance, com um uso diário de trilhões de tokens, continuamente aprimorado, oferece diversas capacidades multimodais, criando uma rica experiência de negócios para as empresas com resultados de modelo de alta qualidade."
+ },
"fireworksai": {
"description": "Fireworks AI é um fornecedor líder de serviços de modelos de linguagem avançados, focando em chamadas de função e processamento multimodal. Seu modelo mais recente, Firefunction V2, baseado em Llama-3, é otimizado para chamadas de função, diálogos e seguimento de instruções. O modelo de linguagem visual FireLLaVA-13B suporta entradas mistas de imagem e texto. Outros modelos notáveis incluem a série Llama e a série Mixtral, oferecendo suporte eficiente para seguimento e geração de instruções multilíngues."
},
+ "giteeai": {
+ "description": "A API Serverless do Gitee AI fornece aos desenvolvedores de IA um serviço de API de inferência de modelos grandes prontos para uso."
+ },
"github": {
"description": "Com os Modelos do GitHub, os desenvolvedores podem se tornar engenheiros de IA e construir com os principais modelos de IA da indústria."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "O motor de inferência LPU da Groq se destacou em testes de benchmark independentes de modelos de linguagem de grande escala (LLM), redefinindo os padrões de soluções de IA com sua velocidade e eficiência impressionantes. A Groq representa uma velocidade de inferência em tempo real, demonstrando bom desempenho em implantações baseadas em nuvem."
},
+ "higress": {
+ "description": "Higress é um gateway de API nativo da nuvem, criado internamente na Alibaba para resolver problemas de recarga do Tengine que afetam negócios de conexões longas, além de melhorar a capacidade de balanceamento de carga do gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "A API de Inferência do HuggingFace oferece uma maneira rápida e gratuita de explorar milhares de modelos para diversas tarefas. Seja você um protótipo para um novo aplicativo ou tentando as funcionalidades de aprendizado de máquina, esta API permite acesso instantâneo a modelos de alto desempenho em múltiplas áreas."
+ },
+ "hunyuan": {
+ "description": "Um modelo de linguagem desenvolvido pela Tencent, com forte capacidade de criação em chinês, habilidade de raciocínio lógico em contextos complexos e capacidade confiável de execução de tarefas."
+ },
+ "internlm": {
+ "description": "Uma organização de código aberto dedicada à pesquisa e desenvolvimento de ferramentas para grandes modelos. Oferece uma plataforma de código aberto eficiente e fácil de usar para todos os desenvolvedores de IA, tornando as tecnologias e algoritmos de ponta acessíveis."
+ },
+ "jina": {
+ "description": "A Jina AI foi fundada em 2020 e é uma empresa líder em IA de busca. Nossa plataforma de busca base contém modelos vetoriais, reordenadores e pequenos modelos de linguagem, ajudando empresas a construir aplicações de busca generativa e multimodal confiáveis e de alta qualidade."
+ },
+ "lmstudio": {
+ "description": "LM Studio é um aplicativo de desktop para desenvolver e experimentar LLMs em seu computador."
+ },
"minimax": {
"description": "MiniMax é uma empresa de tecnologia de inteligência artificial geral fundada em 2021, dedicada a co-criar inteligência com os usuários. A MiniMax desenvolveu internamente diferentes modelos gerais de grande escala, incluindo um modelo de texto MoE com trilhões de parâmetros, um modelo de voz e um modelo de imagem. Também lançou aplicações como Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI é uma plataforma que oferece uma variedade de modelos de linguagem de grande escala e serviços de geração de imagens de IA, sendo flexível, confiável e econômica. Suporta os mais recentes modelos de código aberto, como Llama3 e Mistral, e fornece soluções de API abrangentes, amigáveis ao usuário e escaláveis para o desenvolvimento de aplicações de IA, adequadas para o rápido crescimento de startups de IA."
},
+ "nvidia": {
+ "description": "O NVIDIA NIM™ fornece contêineres para inferência de microserviços acelerados por GPU autogerenciados, suportando a implantação de modelos de IA pré-treinados e personalizados na nuvem, em data centers, em PCs RTX™ AI e estações de trabalho."
+ },
"ollama": {
"description": "Os modelos oferecidos pela Ollama abrangem amplamente áreas como geração de código, operações matemáticas, processamento multilíngue e interações de diálogo, atendendo a diversas necessidades de implantação em nível empresarial e local."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity é um fornecedor líder de modelos de geração de diálogo, oferecendo uma variedade de modelos avançados Llama 3.1, suportando aplicações online e offline, especialmente adequados para tarefas complexas de processamento de linguagem natural."
},
+ "ppio": {
+ "description": "O PPIO Paiouyun oferece serviços de API de modelos de código aberto estáveis e com alto custo-benefício, suportando toda a linha DeepSeek, Llama, Qwen e outros grandes modelos líderes da indústria."
+ },
"qwen": {
"description": "Qwen é um modelo de linguagem de grande escala desenvolvido pela Alibaba Cloud, com forte capacidade de compreensão e geração de linguagem natural. Ele pode responder a várias perguntas, criar conteúdo escrito, expressar opiniões e escrever código, atuando em vários campos."
},
+ "sambanova": {
+ "description": "O SambaNova Cloud permite que os desenvolvedores utilizem facilmente os melhores modelos de código aberto e desfrutem da maior velocidade de inferência."
+ },
+ "sensenova": {
+ "description": "A SenseTime oferece serviços de grandes modelos de pilha completa, aproveitando o forte suporte da infraestrutura da SenseTime."
+ },
"siliconcloud": {
"description": "SiliconFlow se dedica a acelerar a AGI para beneficiar a humanidade, melhorando a eficiência da IA em larga escala por meio de uma pilha GenAI fácil de usar e de baixo custo."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "O Instituto de Automação da Academia Chinesa de Ciências e o Instituto de Pesquisa em Inteligência Artificial de Wuhan lançaram uma nova geração de grandes modelos multimodais, suportando tarefas abrangentes de perguntas e respostas, criação de texto, geração de imagens, compreensão 3D, análise de sinais, entre outras, com capacidades cognitivas, de compreensão e criação mais fortes, proporcionando uma nova experiência interativa."
},
+ "tencentcloud": {
+ "description": "A capacidade atômica do mecanismo de conhecimento (LLM Knowledge Engine Atomic Power) é uma capacidade completa de perguntas e respostas baseada no desenvolvimento do mecanismo de conhecimento, voltada para empresas e desenvolvedores, oferecendo a capacidade de montar e desenvolver aplicações de modelo de forma flexível. Você pode montar seu serviço de modelo exclusivo usando várias capacidades atômicas, chamando serviços de análise de documentos, divisão, embedding, reescrita em várias rodadas, entre outros, para personalizar negócios de IA exclusivos para sua empresa."
+ },
"togetherai": {
"description": "A Together AI se dedica a alcançar desempenho de ponta por meio de modelos de IA inovadores, oferecendo amplas capacidades de personalização, incluindo suporte para escalabilidade rápida e processos de implantação intuitivos, atendendo a diversas necessidades empresariais."
},
"upstage": {
"description": "Upstage se concentra no desenvolvimento de modelos de IA para diversas necessidades comerciais, incluindo Solar LLM e Document AI, visando alcançar uma inteligência geral artificial (AGI) que funcione. Crie agentes de diálogo simples por meio da API de Chat e suporte chamadas de função, tradução, incorporação e aplicações em domínios específicos."
},
+ "vertexai": {
+ "description": "A série Gemini do Google é seu modelo de IA mais avançado e versátil, desenvolvido pelo Google DeepMind, projetado para ser multimodal, suportando compreensão e processamento sem costura de texto, código, imagens, áudio e vídeo. Adequado para uma variedade de ambientes, desde data centers até dispositivos móveis, aumentando significativamente a eficiência e a aplicabilidade dos modelos de IA."
+ },
+ "vllm": {
+ "description": "vLLM é uma biblioteca rápida e fácil de usar para inferência e serviços de LLM."
+ },
+ "volcengine": {
+ "description": "A plataforma de desenvolvimento de serviços de grandes modelos lançada pela ByteDance, que oferece serviços de chamada de modelos ricos em funcionalidades, seguros e com preços competitivos, além de fornecer dados de modelos, ajuste fino, inferência, avaliação e outras funcionalidades de ponta a ponta, garantindo de forma abrangente a implementação do seu desenvolvimento de aplicações de IA."
+ },
+ "wenxin": {
+ "description": "Plataforma de desenvolvimento e serviços de aplicativos nativos de IA e modelos de grande escala, voltada para empresas, que oferece a mais completa e fácil ferramenta de cadeia de ferramentas para o desenvolvimento de modelos de inteligência artificial generativa e aplicativos."
+ },
+ "xai": {
+ "description": "xAI é uma empresa dedicada a construir inteligência artificial para acelerar as descobertas científicas da humanidade. Nossa missão é promover a nossa compreensão coletiva do universo."
+ },
"zeroone": {
"description": "01.AI se concentra na tecnologia de inteligência artificial da era 2.0, promovendo fortemente a inovação e aplicação de 'humano + inteligência artificial', utilizando modelos poderosos e tecnologia de IA avançada para aumentar a produtividade humana e realizar a capacitação tecnológica."
},
diff --git a/DigitalHumanWeb/locales/pt-BR/setting.json b/DigitalHumanWeb/locales/pt-BR/setting.json
index 0192eb8..d98ad43 100644
--- a/DigitalHumanWeb/locales/pt-BR/setting.json
+++ b/DigitalHumanWeb/locales/pt-BR/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Configuração de Modelo Personalizado",
"tokens": {
- "title": "Número Máximo de Tokens",
- "unlimited": "ilimitado"
+ "title": "Número Máximo de Tokens"
},
"vision": {
"extra": "Esta configuração ativará apenas a configuração de upload de imagens dentro do aplicativo; a capacidade de reconhecimento depende totalmente do modelo em si. Por favor, teste a disponibilidade da capacidade de reconhecimento visual desse modelo.",
@@ -98,6 +97,7 @@
"title": "Usar o modo de solicitação do cliente"
},
"fetcher": {
+ "clear": "Limpar o modelo obtido",
"fetch": "Obter lista de modelos",
"fetching": "Obtendo lista de modelos...",
"latestTime": "Última atualização: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Se deve criar automaticamente um tópico durante a conversa, apenas válido em tópicos temporários",
"title": "Criar tópico automaticamente"
},
- "enableCompressThreshold": {
- "title": "Ativar limite de compactação de mensagens"
+ "enableCompressHistory": {
+ "title": "Ativar resumo automático de mensagens históricas"
},
"enableHistoryCount": {
"alias": "Sem limite",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Ativar limite de resposta única"
},
+ "enableReasoningEffort": {
+ "title": "Ativar ajuste de intensidade de raciocínio"
+ },
"frequencyPenalty": {
- "desc": "Quanto maior o valor, maior a probabilidade de reduzir palavras repetidas",
- "title": "Penalidade de frequência"
+ "desc": "Quanto maior o valor, mais rica e variada será a escolha de palavras; quanto menor o valor, mais simples e direta será a escolha de palavras.",
+ "title": "Riqueza do Vocabulário"
},
"maxTokens": {
"desc": "Número máximo de tokens a serem usados em uma interação única",
@@ -212,19 +215,31 @@
"desc": "{{provider}} modelo",
"title": "Modelo"
},
+ "params": {
+ "title": "Parâmetros Avançados"
+ },
"presencePenalty": {
- "desc": "Quanto maior o valor, maior a probabilidade de expandir para novos tópicos",
- "title": "Penalidade de novidade do tópico"
+ "desc": "Quanto maior o valor, mais inclinado a diferentes formas de expressão, evitando repetições de conceitos; quanto menor o valor, mais inclinado a usar conceitos ou narrativas repetidas, resultando em uma expressão mais consistente.",
+ "title": "Diversidade de Expressão"
+ },
+ "reasoningEffort": {
+ "desc": "Quanto maior o valor, mais forte será a capacidade de raciocínio, mas isso pode aumentar o tempo de resposta e o consumo de tokens",
+ "options": {
+ "high": "Alto",
+ "low": "Baixo",
+ "medium": "Médio"
+ },
+ "title": "Intensidade de raciocínio"
},
"temperature": {
- "desc": "Quanto maior o valor, mais aleatória será a resposta",
- "title": "Aleatoriedade",
- "titleWithValue": "Aleatoriedade {{value}}"
+ "desc": "Quanto maior o valor, mais criativas e imaginativas serão as respostas; quanto menor o valor, mais rigorosas serão as respostas",
+ "title": "Atividade Criativa",
+ "warning": "Valor de atividade criativa muito alto pode resultar em saídas confusas"
},
- "title": "Configurações do modelo",
+ "title": "Configurações do Modelo",
"topP": {
- "desc": "Semelhante à aleatoriedade, mas não deve ser alterado junto com a aleatoriedade",
- "title": "Amostragem principal"
+ "desc": "Quantas possibilidades considerar; quanto maior o valor, mais respostas possíveis serão aceitas; quanto menor o valor, mais se tende a escolher a resposta mais provável. Não é recomendado alterar junto com a atividade criativa",
+ "title": "Abertura Mental"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Especifica o modelo usado para gerar o nome, descrição, avatar e tags do assistente",
"title": "Geração Automática de Informações do Assistente"
},
+ "customPrompt": {
+ "addPrompt": "Adicionar prompt personalizado",
+ "desc": "Após preenchido, o assistente do sistema usará o prompt personalizado ao gerar conteúdo",
+ "placeholder": "Digite a palavra-chave personalizada",
+ "title": "Palavra-chave personalizada"
+ },
+ "historyCompress": {
+ "label": "Modelo de Histórico de Conversa",
+ "modelDesc": "Especifica o modelo usado para comprimir o histórico de conversa",
+ "title": "Resumo Automático do Histórico de Conversa"
+ },
"queryRewrite": {
"label": "Modelo de Reescrita de Perguntas",
"modelDesc": "Modelo designado para otimizar as perguntas dos usuários",
- "title": "Base de Conhecimento"
+ "title": "Reescrita de perguntas do banco de dados"
+ },
+ "thread": {
+ "label": "Modelo de Nomeação de Subtópicos",
+ "modelDesc": "Modelo designado para a renomeação automática de subtópicos",
+ "title": "Nomeação Automática de Subtópicos"
},
"title": "Assistente do Sistema",
"topic": {
@@ -395,6 +426,7 @@
"common": "Configurações Comuns",
"experiment": "Experimento",
"llm": "Modelo de Linguagem",
+ "provider": "Fornecedor de IA",
"sync": "Sincronização na nuvem",
"system-agent": "Assistente do Sistema",
"tts": "Serviço de Voz"
diff --git a/DigitalHumanWeb/locales/pt-BR/thread.json b/DigitalHumanWeb/locales/pt-BR/thread.json
new file mode 100644
index 0000000..a90dde9
--- /dev/null
+++ b/DigitalHumanWeb/locales/pt-BR/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Você está prestes a remover este subtópico. Após a exclusão, não será possível recuperá-lo. Por favor, proceda com cautela."
+ },
+ "newPortalThread": {
+ "includeContext": "Incluir contexto do tópico",
+ "title": "Iniciar um novo subtópico"
+ },
+ "notSupportMultiModals": "Subtópicos atualmente não suportam upload de arquivos/imagens. Se houver necessidade, sinta-se à vontade para deixar uma mensagem: <1>💬 Área de Discussão1>"
+}
diff --git a/DigitalHumanWeb/locales/pt-BR/tool.json b/DigitalHumanWeb/locales/pt-BR/tool.json
index 8c1e193..90d0599 100644
--- a/DigitalHumanWeb/locales/pt-BR/tool.json
+++ b/DigitalHumanWeb/locales/pt-BR/tool.json
@@ -6,5 +6,23 @@
"generating": "Gerando...",
"images": "Imagens:",
"prompt": "Palavra-chave"
+ },
+ "search": {
+ "createNewSearch": "Criar nova pesquisa",
+ "emptyResult": "Nenhum resultado encontrado, por favor, modifique as palavras-chave e tente novamente",
+ "genAiMessage": "Criar mensagem do assistente",
+ "includedTooltip": "Os resultados da pesquisa atual serão incluídos no contexto da conversa",
+ "keywords": "Palavras-chave:",
+ "scoreTooltip": "Pontuação de relevância, quanto maior a pontuação, mais relevante é em relação às palavras-chave da consulta",
+ "searchBar": {
+ "button": "Pesquisar",
+ "placeholder": "Palavras-chave",
+ "tooltip": "Isso irá recuperar os resultados da pesquisa novamente e criar uma nova mensagem de resumo"
+ },
+ "searchEngine": "Motor de busca:",
+ "searchResult": "Número de pesquisas:",
+ "summary": "Resumo",
+ "summaryTooltip": "Resumir o conteúdo atual",
+ "viewMoreResults": "Ver mais {{results}} resultados"
}
}
diff --git a/DigitalHumanWeb/locales/pt-BR/topic.json b/DigitalHumanWeb/locales/pt-BR/topic.json
new file mode 100644
index 0000000..ba11080
--- /dev/null
+++ b/DigitalHumanWeb/locales/pt-BR/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Renomeação automática",
+ "confirmRemoveAll": "Você está prestes a remover todos os tópicos. Após a exclusão, não será possível recuperar. Por favor, proceda com cautela.",
+ "confirmRemoveTopic": "Você está prestes a remover este tópico. Após a exclusão, não será possível recuperar. Por favor, proceda com cautela.",
+ "confirmRemoveUnstarred": "Você está prestes a remover tópicos não favoritos. Após a exclusão, não será possível recuperar. Por favor, proceda com cautela.",
+ "duplicate": "Criar cópia",
+ "export": "Exportar tópicos",
+ "removeAll": "Remover todos os tópicos",
+ "removeUnstarred": "Remover tópicos não favoritos"
+ },
+ "defaultTitle": "Tópico padrão",
+ "duplicateLoading": "Copiando tópico...",
+ "duplicateSuccess": "Tópico copiado com sucesso",
+ "favorite": "Favoritar",
+ "groupMode": {
+ "ascMessages": "Por ordem de total de mensagens",
+ "byTime": "Agrupado por tempo",
+ "descMessages": "Por ordem decrescente de total de mensagens",
+ "flat": "Sem agrupamento"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Este mês",
+ "today": "Hoje",
+ "week": "Esta semana",
+ "yesterday": "Ontem"
+ }
+ },
+ "guide": {
+ "desc": "Clique no botão à esquerda para salvar a conversa atual como um tópico histórico e iniciar uma nova conversa.",
+ "title": "Lista de tópicos"
+ },
+ "searchPlaceholder": "Pesquisar tópicos...",
+ "searchResultEmpty": "Nenhum resultado encontrado",
+ "temp": "Temporário",
+ "title": "Tópico"
+}
diff --git a/DigitalHumanWeb/locales/pt-BR/welcome.json b/DigitalHumanWeb/locales/pt-BR/welcome.json
index 36e8b3a..6a9101b 100644
--- a/DigitalHumanWeb/locales/pt-BR/welcome.json
+++ b/DigitalHumanWeb/locales/pt-BR/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Importar configuração",
- "market": "Explorar o mercado",
- "start": "Começar agora"
- },
"guide": {
"agents": {
"replaceBtn": "Trocar",
diff --git a/DigitalHumanWeb/locales/ru-RU/auth.json b/DigitalHumanWeb/locales/ru-RU/auth.json
index 08be604..fc308f4 100644
--- a/DigitalHumanWeb/locales/ru-RU/auth.json
+++ b/DigitalHumanWeb/locales/ru-RU/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Прошлый месяц",
+ "recent30Days": "Последние 30 дней"
+ },
+ "header": {
+ "desc": "Управляйте информацией о своей учетной записи.",
+ "title": "Учетная запись"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Неактивный",
+ "more": "Активный"
+ },
+ "months": {
+ "apr": "Апр",
+ "aug": "Авг",
+ "dec": "Дек",
+ "feb": "Фев",
+ "jan": "Янв",
+ "jul": "Июл",
+ "jun": "Июн",
+ "mar": "Мар",
+ "may": "Май",
+ "nov": "Ноя",
+ "oct": "Окт",
+ "sep": "Сен"
+ },
+ "tooltip": "{{date}} отправил {{count}} сообщений в этот день",
+ "totalCount": "Всего {{count}} сообщений отправлено за последний год"
+ },
"login": "Войти",
"loginOrSignup": "Войти / Зарегистрироваться",
- "profile": "Профиль",
- "security": "Безопасность",
+ "profile": {
+ "avatar": "Аватар",
+ "email": "Электронная почта",
+ "sso": {
+ "loading": "Загрузка связанных сторонних аккаунтов",
+ "providers": "Подключенные аккаунты",
+ "unlink": {
+ "description": "После отключения вы не сможете использовать аккаунт {{provider}} \"{{providerAccountId}}\" для входа. Если вам нужно повторно связать аккаунт {{provider}} с текущим аккаунтом, убедитесь, что адрес электронной почты вашего аккаунта {{provider}} - {{email}}. Мы автоматически свяжем его с текущим вошедшим в систему аккаунтом при входе.",
+ "forbidden": "Вы должны оставить хотя бы одну привязку стороннего аккаунта.",
+ "title": "Вы уверены, что хотите отменить связь с сторонним аккаунтом {{provider}}?"
+ }
+ },
+ "username": "Имя пользователя"
+ },
"signout": "Выйти",
- "signup": "Зарегистрироваться"
+ "signup": "Зарегистрироваться",
+ "stats": {
+ "aiheatmaps": "Индекс активности",
+ "assistants": "Ассистенты",
+ "assistantsRank": {
+ "left": "Ассистент",
+ "right": "Темы",
+ "title": "Рейтинг использования ассистентов"
+ },
+ "createdAt": "Зарегистрирован",
+ "days": "дней",
+ "empty": {
+ "desc": "Пожалуйста, накопите больше данных чата для просмотра",
+ "title": "Нет данных"
+ },
+ "lastYearActivity": "активность за последний год",
+ "loginGuide": {
+ "f1": "Получите бесплатный объем",
+ "f2": "Синхронизируйте сообщения на разных устройствах",
+ "f3": "Имеете доступ к богатым помощникам",
+ "f4": "Исследуйте мощные плагины",
+ "title": "После входа в систему вы можете:"
+ },
+ "messages": "Сообщения",
+ "modelsRank": {
+ "left": "Модель",
+ "right": "Сообщения",
+ "title": "Рейтинг использования моделей"
+ },
+ "share": {
+ "title": "Мой индекс активности ИИ"
+ },
+ "topics": "Темы",
+ "topicsRank": {
+ "left": "Тема",
+ "right": "Сообщения",
+ "title": "Рейтинг содержания тем"
+ },
+ "updatedAt": "Обновлено",
+ "welcome": "{{username}}, это ваш {{days}} день с {{appName}}",
+ "words": "Слова"
+ },
+ "tab": {
+ "profile": "Профиль",
+ "security": "Безопасность",
+ "stats": "Статистика"
+ }
}
diff --git a/DigitalHumanWeb/locales/ru-RU/changelog.json b/DigitalHumanWeb/locales/ru-RU/changelog.json
new file mode 100644
index 0000000..da64b0a
--- /dev/null
+++ b/DigitalHumanWeb/locales/ru-RU/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Подписывайтесь на нас в X",
+ "subscribeToUpdates": "Подписаться на обновления",
+ "versions": "Детали версий"
+ },
+ "addedWhileAway": "Мы добавили новые функции, пока вы отсутствовали.",
+ "allChangelog": "Просмотреть все журналы изменений",
+ "description": "Постоянно следите за новыми функциями и улучшениями {{appName}}",
+ "pagination": {
+ "next": "Следующая страница",
+ "older": "Посмотреть историю изменений"
+ },
+ "readDetails": "Читать детали",
+ "title": "Журнал изменений",
+ "versionDetails": "Детали версий",
+ "welcomeBack": "С возвращением!"
+}
diff --git a/DigitalHumanWeb/locales/ru-RU/chat.json b/DigitalHumanWeb/locales/ru-RU/chat.json
index b900f9a..da1ded3 100644
--- a/DigitalHumanWeb/locales/ru-RU/chat.json
+++ b/DigitalHumanWeb/locales/ru-RU/chat.json
@@ -8,6 +8,7 @@
"agents": "Ассистент",
"artifact": {
"generating": "Генерация",
+ "inThread": "Невозможно просмотреть в подтеме, переключитесь на основную область диалога",
"thinking": "В процессе размышлений",
"thought": "Процесс мышления",
"unknownTitle": "Безымянное произведение"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Копия",
"emptyAgent": "Нет ассистента",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Стоимость генерации одного диалога может быть снижена до 90%, скорость ответа увеличивается в 4 раза (<1>Узнать больше1>). При включении автоматически отключается ограничение на количество исторических сообщений",
+ "title": "Включить кэширование контекста"
+ },
+ "enableReasoning": {
+ "desc": "Ограничение на основе механизма Claude Thinking (<1>Узнать больше1>), при включении автоматически отключается ограничение на количество исторических сообщений",
+ "title": "Включить глубокое мышление"
+ },
+ "reasoningBudgetToken": {
+ "title": "Токены на размышления"
+ },
+ "title": "Расширенные функции модели"
+ },
+ "history": {
+ "title": "Ассистент будет помнить только последние {{count}} сообщений"
+ },
"historyRange": "История сообщений",
+ "historySummary": "Сводка исторических сообщений",
"inbox": {
"desc": "Зажги искру мысли, открой кластер мозгов. Твой виртуальный ассистент, готовый обсудить все с тобой.",
"title": "Просто поболтаем"
@@ -45,6 +64,9 @@
"stop": "Остановить",
"warp": "Перенос строки"
},
+ "intentUnderstanding": {
+ "title": "Мы понимаем и анализируем ваше намерение..."
+ },
"knowledgeBase": {
"all": "Все содержимое",
"allFiles": "Все файлы",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Удалить и пересоздать",
+ "deleteDisabledByThreads": "Существуют подтемы, удаление невозможно",
"regenerate": "Пересоздать"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Кредиты",
+ "creditPricing": "Ценообразование",
+ "creditTooltip": "Для удобства подсчета мы приравниваем 1$ к 1M кредитов, например, $3/M токенов эквивалентно 3 кредитам/токен",
+ "pricing": {
+ "inputCachedTokens": "Кэшированные входные {{amount}}/кредиты · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M символов",
+ "inputMinutes": "${{amount}}/минуту",
+ "inputTokens": "Входные {{amount}}/кредиты · ${{amount}}/M",
+ "outputTokens": "Выходные {{amount}}/кредиты · ${{amount}}/M",
+ "writeCacheInputTokens": "Кэширование ввода записи {{amount}}/баллов · ${{amount}}/М"
+ }
+ },
+ "tokenDetails": {
+ "average": "Средняя цена",
+ "input": "Вход",
+ "inputAudio": "Аудиовход",
+ "inputCached": "Кэшированный вход",
+ "inputCitation": "Цитирование ввода",
+ "inputText": "Текстовый вход",
+ "inputTitle": "Детали входа",
+ "inputUncached": "Некэшированный вход",
+ "inputWriteCached": "Запись кэшированного ввода",
+ "output": "Выход",
+ "outputAudio": "Аудиовыход",
+ "outputText": "Текстовый выход",
+ "outputTitle": "Детали выхода",
+ "reasoning": "Глубокое мышление",
+ "title": "Детали генерации",
+ "total": "Общее потребление"
+ }
+ },
"newAgent": "Создать помощника",
"pin": "Закрепить",
"pinOff": "Открепить",
@@ -81,6 +137,32 @@
},
"regenerate": "Сгенерировать заново",
"roleAndArchive": "Роль и архив",
+ "search": {
+ "grounding": {
+ "searchQueries": "Поисковые ключевые слова",
+ "title": "Найдено {{count}} результатов"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Интеллектуально определяет необходимость поиска на основе содержания диалога",
+ "title": "Интеллектуальное подключение к сети"
+ },
+ "off": {
+ "desc": "Использует только базовые знания модели, без сетевого поиска",
+ "title": "Отключить подключение к сети"
+ },
+ "on": {
+ "desc": "Постоянно выполняет сетевой поиск для получения актуальной информации",
+ "title": "Всегда подключен к сети"
+ },
+ "useModelBuiltin": "Использовать встроенный поисковый движок модели"
+ },
+ "searchModel": {
+ "desc": "Текущая модель не поддерживает вызов функций, поэтому необходимо использовать модель, поддерживающую вызов функций, для поиска в интернете",
+ "title": "Модель поиска"
+ },
+ "title": "Поиск в сети"
+ },
"searchAgentPlaceholder": "Поиск помощника...",
"sendPlaceholder": "Введите сообщение...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Название группы должно содержать от 1 до 20 символов"
},
"shareModal": {
+ "copy": "Копировать",
"download": "Скачать скриншот",
+ "downloadFile": "Скачать файл",
+ "exportTitle": "Заголовок по умолчанию",
"imageType": "Тип изображения",
+ "includeTool": "Включить сообщения плагина",
+ "includeUser": "Включить сообщения пользователя",
"screenshot": "Скриншот",
"settings": "Настройки экспорта",
- "shareToShareGPT": "Создать ссылку для обмена ShareGPT",
+ "text": "Текст",
"withBackground": "С фоном",
"withFooter": "С нижним колонтитулом",
"withPluginInfo": "С информацией о плагинах",
+ "withRole": "Включить роль сообщения",
"withSystemRole": "С ролью помощника"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Распознавание...",
"prettifying": "Форматирование..."
},
- "temp": "Временный",
+ "thread": {
+ "divider": "Подтема",
+ "threadMessageCount": "{{messageCount}} сообщений",
+ "title": "Подтема"
+ },
"tokenDetails": {
"chats": "Чаты",
+ "historySummary": "Историческое резюме",
"rest": "Остаток",
"systemRole": "Роль системы",
"title": "Детали контекста",
@@ -131,29 +224,10 @@
"used": "Использовано"
},
"topic": {
- "actions": {
- "autoRename": "Умное переименование",
- "duplicate": "Создать копию",
- "export": "Экспорт темы"
- },
"checkOpenNewTopic": "Открыть новую тему?",
"checkSaveCurrentMessages": "Сохранить текущий разговор как тему?",
- "confirmRemoveAll": "Вы уверены, что хотите удалить все темы? После этого их нельзя будет восстановить.",
- "confirmRemoveTopic": "Вы уверены, что хотите удалить эту тему? После этого ее нельзя будет восстановить.",
- "confirmRemoveUnstarred": "Вы уверены, что хотите удалить неотмеченные темы? После этого их нельзя будет восстановить.",
- "defaultTitle": "Стандартная тема",
- "duplicateLoading": "Копирование темы...",
- "duplicateSuccess": "Тема успешно скопирована",
- "guide": {
- "desc": "Нажмите на кнопку слева, чтобы сохранить текущий разговор в качестве исторической темы и начать новый разговор",
- "title": "Список тем"
- },
"openNewTopic": "Создать новую тему",
- "removeAll": "Удалить все темы",
- "removeUnstarred": "Удалить неотмеченные темы",
- "saveCurrentMessages": "Сохранить текущий разговор как тему",
- "searchPlaceholder": "Поиск тем...",
- "title": "Список тем"
+ "saveCurrentMessages": "Сохранить текущий разговор как тему"
},
"translate": {
"action": "Перевести",
@@ -184,5 +258,6 @@
"processing": "Обработка файла..."
}
}
- }
+ },
+ "zenMode": "Режим концентрации"
}
diff --git a/DigitalHumanWeb/locales/ru-RU/common.json b/DigitalHumanWeb/locales/ru-RU/common.json
index dfb77b6..f5499b4 100644
--- a/DigitalHumanWeb/locales/ru-RU/common.json
+++ b/DigitalHumanWeb/locales/ru-RU/common.json
@@ -9,15 +9,79 @@
"title": "Добро пожаловать в {{name}}"
}
},
- "appInitializing": "Приложение запускается...",
+ "appLoading": {
+ "appIdle": "Подготовка к запуску",
+ "appInitializing": "Инициализация приложения...",
+ "failed": "К сожалению, инициализация приложения не удалась, пожалуйста, посмотрите подробности для устранения проблемы",
+ "finished": "Инициализация базы данных завершена",
+ "goToChat": "Загрузка страницы чата...",
+ "initAuth": "Инициализация службы аутентификации...",
+ "initUser": "Инициализация состояния пользователя...",
+ "initializing": "Инициализация базы данных PGlite...",
+ "loadingDependencies": "Инициализация зависимостей...",
+ "loadingWasm": "Загрузка модуля WASM...",
+ "migrating": "Выполнение миграции таблиц данных...",
+ "ready": "База данных готова",
+ "showDetail": "Посмотреть детали"
+ },
"autoGenerate": "Автозаполнение",
"autoGenerateTooltip": "Автоматическое дополнение описания агента на основе подсказок",
"autoGenerateTooltipDisabled": "Пожалуйста, введите подсказку перед использованием функции автозаполнения",
"back": "Назад",
"batchDelete": "Пакетное удаление",
"blog": "Блог о продуктах",
+ "branching": "Создать подтему",
+ "branchingDisable": "Функция «Подтема» доступна только в серверной версии. Если вам нужна эта функция, переключитесь на серверный режим развертывания или используйте LobeChat Cloud.",
"cancel": "Отмена",
"changelog": "История изменений",
+ "clientDB": {
+ "autoInit": {
+ "title": "Инициализация базы данных PGlite"
+ },
+ "error": {
+ "desc": "К сожалению, произошла ошибка при инициализации базы данных Pglite. Пожалуйста, нажмите кнопку, чтобы попробовать снова. Если после нескольких попыток ошибка сохраняется, пожалуйста, <1>отправьте запрос1>, и мы постараемся помочь вам в кратчайшие сроки.",
+ "detail": "Причина ошибки: [{{type}}] {{message}}. Подробности ниже:",
+ "retry": "Повторить",
+ "title": "Не удалось инициализировать базу данных"
+ },
+ "initing": {
+ "error": "Произошла ошибка, пожалуйста, повторите попытку",
+ "idle": "Ожидание инициализации...",
+ "initializing": "Инициализация...",
+ "loadingDependencies": "Загрузка зависимостей...",
+ "loadingWasmModule": "Загрузка модуля WASM...",
+ "migrating": "Выполнение миграции таблицы данных...",
+ "ready": "База данных готова"
+ },
+ "modal": {
+ "desc": "Включите клиентскую базу данных PGlite для постоянного хранения данных чата в вашем браузере и использования таких расширенных функций, как база знаний.",
+ "enable": "Включить сейчас",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Создайте свою личную базу знаний и легко начните диалог с вашим помощником (скоро будет доступно)",
+ "title": "Поддержка диалога с базой знаний, откройте второй мозг"
+ },
+ "localFirst": {
+ "desc": "Данные чата полностью хранятся в браузере, ваши данные всегда под вашим контролем.",
+ "title": "Локальный приоритет, конфиденциальность превыше всего"
+ },
+ "pglite": {
+ "desc": "Построено на основе PGlite, нативная поддержка высокоуровневых функций AI Native (векторный поиск)",
+ "title": "Новая архитектура клиентского хранения"
+ }
+ },
+ "init": {
+ "desc": "Идет инициализация базы данных, в зависимости от сети это может занять от 5 до 30 секунд.",
+ "title": "Инициализация базы данных PGlite"
+ },
+ "title": "Включить клиентскую базу данных"
+ },
+ "ready": {
+ "button": "Использовать сейчас",
+ "desc": "Использовать сейчас",
+ "title": "База данных PGlite готова"
+ }
+ },
"close": "Закрыть",
"contact": "Свяжитесь с нами",
"copy": "Копировать",
@@ -112,6 +176,7 @@
"en": "Английский",
"en-US": "Английский",
"es-ES": "испанский",
+ "fa-IR": "Персидский",
"fi-FI": "Финский",
"fr-FR": "французский",
"hi-IN": "Хинди",
@@ -153,6 +218,7 @@
"pinOff": "Открепить",
"privacy": "Политика конфиденциальности",
"regenerate": "Перегенерировать",
+ "releaseNotes": "Подробности о версии",
"rename": "Переименовать",
"reset": "Сброс",
"retry": "Повторить",
@@ -209,6 +275,7 @@
},
"temp": "Временный",
"terms": "Условия использования",
+ "update": "Обновить",
"updateAgent": "Обновить информацию об агенте",
"upgradeVersion": {
"action": "обновить",
@@ -219,6 +286,7 @@
"anonymousNickName": "Анонимный пользователь",
"billing": "Управление счетами",
"cloud": "Опыт {{name}}",
+ "community": "Сообщество",
"data": "Хранилище данных",
"defaultNickname": "Пользователь сообщества",
"discord": "Поддержка сообщества",
@@ -228,7 +296,6 @@
"help": "Центр помощи",
"moveGuide": "Кнопка настроек перемещена сюда",
"plans": "Планы подписки",
- "preview": "Предпросмотр",
"profile": "Управление аккаунтом",
"setting": "Настройки приложения",
"usages": "Статистика использования"
diff --git a/DigitalHumanWeb/locales/ru-RU/components.json b/DigitalHumanWeb/locales/ru-RU/components.json
index d3d9d0d..4f3dc76 100644
--- a/DigitalHumanWeb/locales/ru-RU/components.json
+++ b/DigitalHumanWeb/locales/ru-RU/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Пакетная разбивка",
"chunking": "Разбивка",
"chunkingTooltip": "Разделите файл на несколько текстовых блоков и векторизуйте их для семантического поиска и диалога с файлом",
+ "chunkingUnsupported": "Этот файл не поддерживает разбиение на части",
"confirmDelete": "Вы собираетесь удалить этот файл. После удаления его нельзя будет восстановить. Пожалуйста, подтвердите ваше действие.",
"confirmDeleteMultiFiles": "Вы собираетесь удалить выбранные {{count}} файлов. После удаления их нельзя будет восстановить. Пожалуйста, подтвердите ваше действие.",
"confirmRemoveFromKnowledgeBase": "Вы собираетесь удалить выбранные {{count}} файлов из базы знаний. После удаления файлы все еще будут доступны во всех файлах. Пожалуйста, подтвердите ваше действие.",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Назад"
},
+ "MaxTokenSlider": {
+ "unlimited": "Без ограничений"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Пользовательская модель по умолчанию поддерживает как вызов функций, так и распознавание изображений. Пожалуйста, проверьте доступность указанных возможностей в вашем случае",
"file": "Эта модель поддерживает загрузку и распознавание файлов",
"functionCall": "Эта модель поддерживает вызов функций",
+ "reasoning": "Эта модель поддерживает глубокое мышление",
+ "search": "Эта модель поддерживает поиск в интернете",
"tokens": "Эта модель поддерживает до {{tokens}} токенов в одной сессии",
"vision": "Эта модель поддерживает распознавание изображений"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Нет активированных моделей. Пожалуйста, перейдите в настройки и включите модель",
+ "emptyProvider": "Нет активных провайдеров, пожалуйста, перейдите в настройки для их включения",
+ "goToSettings": "Перейти в настройки",
"provider": "Поставщик"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Из-за ограничений безопасности браузера вам необходимо настроить кросс-доменные запросы для корректного использования Ollama.",
+ "linux": {
+ "env": "Добавьте `Environment` в раздел [Service] и добавьте переменную окружения OLLAMA_ORIGINS:",
+ "reboot": "Перезагрузите systemd и перезапустите Ollama",
+ "systemd": "Вызовите systemd для редактирования службы ollama:"
+ },
+ "macos": "Откройте приложение «Терминал», вставьте следующую команду и нажмите Enter для выполнения",
+ "reboot": "Пожалуйста, перезапустите службу Ollama после завершения выполнения",
+ "title": "Настройка Ollama для разрешения кросс-доменных запросов",
+ "windows": "На Windows нажмите «Панель управления», перейдите к редактированию системных переменных окружения. Создайте новую переменную окружения с именем «OLLAMA_ORIGINS» для вашей учетной записи пользователя, значение - * , нажмите «OK/Применить» для сохранения"
+ },
+ "install": {
+ "description": "Пожалуйста, убедитесь, что вы запустили Ollama. Если вы еще не скачали Ollama, перейдите на официальный сайт <1>для загрузки1>",
+ "docker": "Если вы предпочитаете использовать Docker, Ollama также предоставляет официальный образ Docker, который вы можете загрузить с помощью следующей команды:",
+ "linux": {
+ "command": "Установите с помощью следующей команды:",
+ "manual": "Или вы можете обратиться к <1>руководству по ручной установке для Linux1> для самостоятельной установки"
+ },
+ "title": "Установите и запустите приложение Ollama локально",
+ "windowsTab": "Windows (предварительная версия)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Глубокое размышление...",
+ "thought": "Глубоко обдумано (время: {{duration}} секунд)",
+ "thoughtWithDuration": "Глубоко обдумано"
}
}
diff --git a/DigitalHumanWeb/locales/ru-RU/discover.json b/DigitalHumanWeb/locales/ru-RU/discover.json
index 1259a91..9553af4 100644
--- a/DigitalHumanWeb/locales/ru-RU/discover.json
+++ b/DigitalHumanWeb/locales/ru-RU/discover.json
@@ -126,6 +126,10 @@
"title": "Свежесть темы"
},
"range": "Диапазон",
+ "reasoning_effort": {
+ "desc": "Эта настройка используется для управления интенсивностью размышлений модели перед генерацией ответа. Низкая интенсивность приоритизирует скорость ответа и экономит токены, высокая интенсивность обеспечивает более полное размышление, но потребляет больше токенов и снижает скорость ответа. Значение по умолчанию - среднее, что обеспечивает баланс между точностью размышлений и скоростью ответа.",
+ "title": "Интенсивность размышлений"
+ },
"temperature": {
"desc": "Эта настройка влияет на разнообразие ответов модели. Более низкие значения приводят к более предсказуемым и типичным ответам, в то время как более высокие значения поощряют более разнообразные и необычные ответы. Когда значение установлено на 0, модель всегда дает один и тот же ответ на данный ввод.",
"title": "Случайность"
diff --git a/DigitalHumanWeb/locales/ru-RU/error.json b/DigitalHumanWeb/locales/ru-RU/error.json
index 0c8cb0b..4bf9c01 100644
--- a/DigitalHumanWeb/locales/ru-RU/error.json
+++ b/DigitalHumanWeb/locales/ru-RU/error.json
@@ -12,8 +12,14 @@
"retry": "Повторить попытку",
"title": "Произошла проблема на странице.."
},
- "fetchError": "Ошибка запроса",
- "fetchErrorDetail": "Подробности ошибки",
+ "fetchError": {
+ "detail": "Детали ошибки",
+ "title": "Запрос не удался"
+ },
+ "loginRequired": {
+ "desc": "Скоро произойдет автоматический переход на страницу входа",
+ "title": "Пожалуйста, войдите в систему, чтобы использовать эту функцию"
+ },
"notFound": {
"backHome": "Вернуться на главную",
"check": "Пожалуйста, проверьте, правильный ли ваш URL",
@@ -51,22 +57,34 @@
"431": "Извините, ваш заголовок запроса слишком велик, сервер не может его обработать",
"451": "Извините, по юридическим причинам сервер отказывается предоставить этот ресурс",
"500": "К сожалению, сервер, похоже, испытывает некоторые трудности и временно не может выполнить ваш запрос. Повторите попытку позже.",
+ "501": "Извините, сервер еще не знает, как обработать этот запрос. Пожалуйста, убедитесь, что ваши действия правильны.",
"502": "К сожалению, сервер, похоже, потерян и временно не может предоставлять услуги. Повторите попытку позже.",
"503": "К сожалению, сервер в настоящее время не может обработать ваш запрос, возможно, из-за перегрузки или технического обслуживания. Повторите попытку позже.",
"504": "К сожалению, сервер не получил ответа от вышестоящего сервера. Повторите попытку позже.",
+ "505": "Извините, сервер не поддерживает используемую вами версию HTTP. Пожалуйста, обновите и попробуйте снова.",
+ "506": "Извините, возникла проблема с конфигурацией сервера. Пожалуйста, свяжитесь с администратором для решения проблемы.",
+ "507": "Извините, на сервере недостаточно места для хранения, чтобы обработать ваш запрос. Пожалуйста, попробуйте позже.",
+ "509": "Извините, пропускная способность сервера исчерпана. Пожалуйста, попробуйте позже.",
+ "510": "Извините, сервер не поддерживает запрашиваемую расширенную функцию. Пожалуйста, свяжитесь с администратором.",
+ "524": "Извините, сервер превысил время ожидания ответа, возможно, из-за слишком медленного ответа. Пожалуйста, попробуйте позже.",
"AgentRuntimeError": "Ошибка выполнения времени выполнения языковой модели Lobe, пожалуйста, проверьте и повторите попытку в соответствии с предоставленной информацией",
+ "ConnectionCheckFailed": "Запрос вернул пустой ответ, пожалуйста, проверьте, что в конце адреса API-прокси не указано `/v1`",
+ "ExceededContextWindow": "Содержимое текущего запроса превышает длину, которую модель может обработать. Пожалуйста, уменьшите объем содержимого и попробуйте снова.",
"FreePlanLimit": "Вы являетесь бесплатным пользователем и не можете использовать эту функцию. Пожалуйста, перейдите на платный план для продолжения использования.",
+ "InsufficientQuota": "Извините, квота для этого ключа достигла предела. Пожалуйста, проверьте, достаточно ли средств на вашем счете, или увеличьте квоту ключа и попробуйте снова.",
"InvalidAccessCode": "Неверный код доступа: введите правильный код доступа или добавьте пользовательский ключ API",
"InvalidBedrockCredentials": "Аутентификация Bedrock не прошла, пожалуйста, проверьте AccessKeyId/SecretAccessKey и повторите попытку",
"InvalidClerkUser": "Извините, вы еще не вошли в систему. Пожалуйста, войдите или зарегистрируйтесь, прежде чем продолжить",
"InvalidGithubToken": "Личный токен доступа Github некорректен или пуст, пожалуйста, проверьте личный токен доступа Github и повторите попытку",
"InvalidOllamaArgs": "Неверная конфигурация Ollama, пожалуйста, проверьте конфигурацию Ollama и повторите попытку",
"InvalidProviderAPIKey": "{{provider}} API ключ недействителен или отсутствует. Пожалуйста, проверьте ключ API {{provider}} и повторите попытку",
+ "InvalidVertexCredentials": "Аутентификация Vertex не прошла, пожалуйста, проверьте учетные данные и попробуйте снова",
"LocationNotSupportError": "Извините, ваше текущее местоположение не поддерживает эту службу модели, возможно из-за ограничений региона или недоступности службы. Пожалуйста, убедитесь, что текущее местоположение поддерживает использование этой службы, или попробуйте использовать другую информацию о местоположении.",
+ "ModelNotFound": "Извините, не удалось запросить соответствующую модель, возможно, модель не существует или у вас нет прав доступа. Пожалуйста, измените API-ключ или настройте права доступа и попробуйте снова.",
"NoOpenAIAPIKey": "Ключ OpenAI API пуст, пожалуйста, добавьте свой собственный ключ OpenAI API",
"OllamaBizError": "Ошибка обращения к сервису Ollama, пожалуйста, проверьте следующую информацию или повторите попытку",
"OllamaServiceUnavailable": "Сервис Ollama недоступен. Пожалуйста, проверьте, работает ли Ollama правильно, и правильно ли настроена его конфигурация для кросс-доменных запросов",
- "OpenAIBizError": "Ошибка обслуживания OpenAI. Пожалуйста, проверьте следующую информацию или повторите попытку",
+ "PermissionDenied": "Извините, у вас нет прав доступа к этой службе. Пожалуйста, проверьте, есть ли у вашего ключа права доступа.",
"PluginApiNotFound": "К сожалению, API не существует в манифесте плагина. Пожалуйста, проверьте, соответствует ли ваш метод запроса API манифеста плагина",
"PluginApiParamsError": "К сожалению, проверка входных параметров для запроса плагина не удалась. Пожалуйста, проверьте, соответствуют ли входные параметры описанию API",
"PluginFailToTransformArguments": "Извините, не удалось преобразовать аргументы вызова плагина. Попробуйте сгенерировать помощь заново или повторите попытку с более мощной моделью искусственного интеллекта для вызова инструментов.",
@@ -81,8 +99,11 @@
"PluginServerError": "Запрос сервера плагина возвратил ошибку. Проверьте файл манифеста плагина, конфигурацию плагина или реализацию сервера на основе информации об ошибке ниже",
"PluginSettingsInvalid": "Этот плагин необходимо правильно настроить, прежде чем его можно будет использовать. Пожалуйста, проверьте правильность вашей конфигурации",
"ProviderBizError": "Ошибка обслуживания {{provider}}. Пожалуйста, проверьте следующую информацию или повторите попытку",
+ "QuotaLimitReached": "Извините, текущий объем токенов или количество запросов достигло предела квоты для этого ключа. Пожалуйста, увеличьте квоту для этого ключа или попробуйте позже.",
"StreamChunkError": "Ошибка разбора блока сообщения потокового запроса. Пожалуйста, проверьте, соответствует ли текущий API стандартам, или свяжитесь с вашим поставщиком API для получения консультации.",
- "SubscriptionPlanLimit": "Вы исчерпали свой лимит подписки и не можете использовать эту функцию. Пожалуйста, перейдите на более высокий план или приобретите дополнительные ресурсы для продолжения использования.",
+ "SubscriptionKeyMismatch": "К сожалению, из-за случайного сбоя в системе текущий объем подписки временно недоступен. Пожалуйста, нажмите кнопку ниже, чтобы восстановить подписку, или свяжитесь с нами по электронной почте для получения поддержки.",
+ "SubscriptionPlanLimit": "Ваши подписочные баллы исчерпаны, вы не можете использовать эту функцию. Пожалуйста, обновите до более высокого плана или настройте API пользовательской модели, чтобы продолжить использование.",
+ "SystemTimeNotMatchError": "Извините, ваше системное время не совпадает с серверным. Пожалуйста, проверьте ваше системное время и попробуйте снова.",
"UnknownChatFetchError": "Извините, произошла неизвестная ошибка запроса. Пожалуйста, проверьте информацию ниже или попробуйте снова."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/ru-RU/metadata.json b/DigitalHumanWeb/locales/ru-RU/metadata.json
index d5ac78f..6c72fb5 100644
--- a/DigitalHumanWeb/locales/ru-RU/metadata.json
+++ b/DigitalHumanWeb/locales/ru-RU/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Постоянно следите за новыми функциями и улучшениями {{appName}}",
+ "title": "Журнал изменений"
+ },
"chat": {
"description": "{{appName}} предлагает вам лучший опыт использования ChatGPT, Claude, Gemini и OLLaMA WebUI",
"title": "{{appName}}: личный инструмент AI для повышения эффективности, дайте себе более умный мозг"
diff --git a/DigitalHumanWeb/locales/ru-RU/modelProvider.json b/DigitalHumanWeb/locales/ru-RU/modelProvider.json
index 0569ef1..ac8a356 100644
--- a/DigitalHumanWeb/locales/ru-RU/modelProvider.json
+++ b/DigitalHumanWeb/locales/ru-RU/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Версия API Azure, формат YYYY-MM-DD, смотрите [последнюю версию](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Получить список",
+ "title": "Версия API Azure"
+ },
+ "endpoint": {
+ "desc": "Найдите конечную точку вывода модели Azure AI в обзоре проекта Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Конечная точка Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Найдите API-ключ в обзоре проекта Azure AI",
+ "placeholder": "Ключ Azure",
+ "title": "Ключ"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Введите ваш AWS Access Key ID",
@@ -51,6 +69,58 @@
"title": "Использовать пользовательскую информацию аутентификации Bedrock"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Пожалуйста, заполните Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Введите ID аккаунта Cloudflare или адрес API по умолчанию",
+ "placeholder": "ID аккаунта Cloudflare / адрес API по умолчанию",
+ "title": "ID аккаунта Cloudflare / адрес API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Пожалуйста, введите ваш API Key",
+ "title": "API Key"
+ },
+ "basicTitle": "Основная информация",
+ "configTitle": "Конфигурационная информация",
+ "confirm": "Создать",
+ "createSuccess": "Создание успешно",
+ "description": {
+ "placeholder": "Описание провайдера (необязательно)",
+ "title": "Описание провайдера"
+ },
+ "id": {
+ "desc": "Уникальный идентификатор для поставщика услуг, который нельзя изменить после создания",
+ "format": "Может содержать только цифры, строчные буквы, дефисы (-) и подчеркивания (_) ",
+ "placeholder": "Рекомендуется использовать строчные буквы, например, openai, после создания изменить нельзя",
+ "required": "Пожалуйста, введите ID провайдера",
+ "title": "ID провайдера"
+ },
+ "logo": {
+ "required": "Пожалуйста, загрузите правильный логотип провайдера",
+ "title": "Логотип провайдера"
+ },
+ "name": {
+ "placeholder": "Пожалуйста, введите отображаемое имя провайдера",
+ "required": "Пожалуйста, введите имя провайдера",
+ "title": "Имя провайдера"
+ },
+ "proxyUrl": {
+ "required": "Пожалуйста, введите адрес прокси",
+ "title": "Адрес прокси"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Пожалуйста, выберите тип SDK",
+ "title": "Формат запроса"
+ },
+ "title": "Создание пользовательского AI провайдера"
+ },
"github": {
"personalAccessToken": {
"desc": "Введите ваш персональный токен доступа GitHub (PAT), нажмите [здесь](https://github.com/settings/tokens), чтобы создать его",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Введите ваш токен HuggingFace, нажмите [здесь](https://huggingface.co/settings/tokens) для создания",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "Токен HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Поставщик не активирован",
+ "enabled": "Поставщик активирован"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Добавить пользовательского провайдера",
+ "all": "Все",
+ "list": {
+ "disabled": "Не активирован",
+ "enabled": "Активирован"
+ },
+ "notFound": "Результаты поиска не найдены",
+ "searchProviders": "Поиск провайдеров...",
+ "sort": "Пользовательская сортировка"
+ },
"ollama": {
"checker": {
"desc": "Проверить правильность адреса прокси",
@@ -69,39 +163,15 @@
"title": "Название кастомных моделей"
},
"download": {
- "desc": "Ollama is downloading the model. Please try not to close this page. The download will resume from where it left off if interrupted.",
- "remainingTime": "Remaining Time",
- "speed": "Download Speed",
- "title": "Downloading model {{model}}"
+ "desc": "Ollama загружает эту модель, пожалуйста, старайтесь не закрывать эту страницу. При повторной загрузке процесс будет продолжен с места остановки",
+ "remainingTime": "Оставшееся время",
+ "speed": "Скорость загрузки",
+ "title": "Загрузка модели {{model}} "
},
"endpoint": {
- "desc": "Введите адрес прокси-интерфейса Ollama, если локально не указано иное, можете оставить пустым",
+ "desc": "Должен содержать http(s)://, если локально не указано иное, можно оставить пустым",
"title": "Адрес прокси-интерфейса"
},
- "setup": {
- "cors": {
- "description": "Из-за ограничений безопасности браузера вам необходимо настроить кросс-доменные запросы для правильной работы Ollama.",
- "linux": {
- "env": "Добавьте переменную среды OLLAMA_ORIGINS в разделе [Service],",
- "reboot": "Перезагрузите systemd и перезапустите Ollama.",
- "systemd": "Вызовите редактирование службы ollama в systemd:"
- },
- "macos": "Откройте приложение \"Терминал\", вставьте и выполните следующую команду, затем нажмите Enter.",
- "reboot": "Пожалуйста, перезагрузите службу Ollama после завершения выполнения команды.",
- "title": "Настройка разрешений на кросс-доменный доступ для Ollama",
- "windows": "На Windows откройте \"Панель управления\", зайдите в настройки системных переменных. Создайте новую переменную среды для вашей учетной записи с именем \"OLLAMA_ORIGINS\" и значением * , затем нажмите \"OK/Применить\" для сохранения."
- },
- "install": {
- "description": "Пожалуйста, убедитесь, что вы установили Ollama. Если вы еще не скачали Ollama, перейдите на официальный сайт <1> для загрузки1>",
- "docker": "Если вы предпочитаете использовать Docker, Ollama также предоставляет официальное образ Docker. Вы можете загрузить его с помощью следующей команды:",
- "linux": {
- "command": "Установите с помощью следующей команды:",
- "manual": "Или вы можете установить его вручную, следуя <1>руководству по установке на Linux1>."
- },
- "title": "Установка и запуск приложения Ollama локально",
- "windowsTab": "Windows (превью)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Cancel Download",
@@ -112,6 +182,156 @@
"title": "Download specified Ollama model"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "Ваши ключи и адрес прокси будут зашифрованы с использованием <1>AES-GCM1>",
+ "apiKey": {
+ "desc": "Пожалуйста, введите ваш {{name}} API Key",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "Должен содержать http(s)://",
+ "invalid": "Пожалуйста, введите действительный URL",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API адрес прокси"
+ },
+ "checker": {
+ "button": "Проверить",
+ "desc": "Проверьте, правильно ли заполнены API Key и адрес прокси",
+ "pass": "Проверка пройдена",
+ "title": "Проверка соединения"
+ },
+ "fetchOnClient": {
+ "desc": "Клиентский режим запросов будет инициировать сессии напрямую из браузера, что может ускорить время отклика",
+ "title": "Использовать клиентский режим запросов"
+ },
+ "helpDoc": "Документация по настройке",
+ "waitingForMore": "Больше моделей находится в <1>планировании подключения1>, ожидайте с нетерпением"
+ },
+ "createNew": {
+ "title": "Создание пользовательской AI модели"
+ },
+ "item": {
+ "config": "Настроить модель",
+ "customModelCards": {
+ "addNew": "Создать и добавить модель {{id}}",
+ "confirmDelete": "Вы собираетесь удалить эту пользовательскую модель, после удаления восстановить ее будет невозможно, будьте осторожны."
+ },
+ "delete": {
+ "confirm": "Подтвердите удаление модели {{displayName}}?",
+ "success": "Удаление успешно",
+ "title": "Удалить модель"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Поле, запрашиваемое в Azure OpenAI",
+ "placeholder": "Пожалуйста, введите имя развертывания модели в Azure",
+ "title": "Имя развертывания модели"
+ },
+ "deployName": {
+ "extra": "Это поле будет использоваться как идентификатор модели при отправке запроса",
+ "placeholder": "Введите фактическое имя или id развертывания модели",
+ "title": "Имя развертывания модели"
+ },
+ "displayName": {
+ "placeholder": "Пожалуйста, введите отображаемое имя модели, например, ChatGPT, GPT-4 и т.д.",
+ "title": "Отображаемое имя модели"
+ },
+ "files": {
+ "extra": "Текущая реализация загрузки файлов является лишь хакерским решением, предназначенным только для самостоятельного тестирования. Полные возможности загрузки файлов ожидайте в будущем.",
+ "title": "Поддержка загрузки файлов"
+ },
+ "functionCall": {
+ "extra": "Эта настройка позволит модели использовать инструменты, что даст возможность добавлять плагины инструментов. Однако возможность фактического использования инструментов полностью зависит от самой модели, пожалуйста, протестируйте их работоспособность самостоятельно",
+ "title": "Поддержка использования инструментов"
+ },
+ "id": {
+ "extra": "После создания изменить нельзя, будет использоваться как идентификатор модели при вызове AI",
+ "placeholder": "Введите идентификатор модели, например, gpt-4o или claude-3.5-sonnet",
+ "title": "ID модели"
+ },
+ "modalTitle": "Настройка пользовательской модели",
+ "reasoning": {
+ "extra": "Эта настройка активирует возможность глубокого мышления модели, конкретный эффект полностью зависит от самой модели, пожалуйста, протестируйте, обладает ли модель доступной способностью к глубокому мышлению",
+ "title": "Поддержка глубокого мышления"
+ },
+ "tokens": {
+ "extra": "Установите максимальное количество токенов, поддерживаемое моделью",
+ "title": "Максимальное окно контекста",
+ "unlimited": "Без ограничений"
+ },
+ "vision": {
+ "extra": "Эта настройка только активирует возможность загрузки изображений в приложении, поддержка распознавания полностью зависит от самой модели, пожалуйста, протестируйте доступность визуального распознавания этой модели.",
+ "title": "Поддержка визуального распознавания"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/изображение",
+ "inputCharts": "${{amount}}/M символов",
+ "inputMinutes": "${{amount}}/минуты",
+ "inputTokens": "Ввод ${{amount}}/М",
+ "outputTokens": "Вывод ${{amount}}/М"
+ },
+ "releasedAt": "Выпущено {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Добавить модель",
+ "disabled": "Не активирован",
+ "disabledActions": {
+ "showMore": "Показать все"
+ },
+ "empty": {
+ "desc": "Пожалуйста, создайте пользовательскую модель или загрузите модель, чтобы начать использовать.",
+ "title": "Нет доступных моделей"
+ },
+ "enabled": "Активирован",
+ "enabledActions": {
+ "disableAll": "Отключить все",
+ "enableAll": "Включить все",
+ "sort": "Сортировка моделей по индивидуальному порядку"
+ },
+ "enabledEmpty": "Нет активированных моделей, пожалуйста, активируйте понравившиеся модели из списка ниже~",
+ "fetcher": {
+ "clear": "Очистить полученные модели",
+ "fetch": "Получить список моделей",
+ "fetching": "Получение списка моделей...",
+ "latestTime": "Последнее обновление: {{time}}",
+ "noLatestTime": "Список еще не получен"
+ },
+ "resetAll": {
+ "conform": "Вы уверены, что хотите сбросить все изменения текущей модели? После сброса список текущих моделей вернется к состоянию по умолчанию",
+ "success": "Сброс выполнен успешно",
+ "title": "Сбросить все изменения"
+ },
+ "search": "Поиск моделей...",
+ "searchResult": "Найдено {{count}} моделей",
+ "title": "Список моделей",
+ "total": "Всего доступно {{count}} моделей"
+ },
+ "searchNotFound": "Результаты поиска не найдены"
+ },
+ "sortModal": {
+ "success": "Сортировка обновлена успешно",
+ "title": "Пользовательская сортировка",
+ "update": "Обновить"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Вы собираетесь удалить этого AI провайдера, после удаления его будет невозможно восстановить, подтвердите, хотите ли вы удалить?",
+ "deleteSuccess": "Удаление успешно",
+ "tooltip": "Обновить базовую конфигурацию провайдера",
+ "updateSuccess": "Обновление успешно"
+ },
+ "updateCustomAiProvider": {
+ "title": "Обновить настройки поставщика пользовательского ИИ"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Введите ваши ключи Vertex AI",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Ключи Vertex AI"
+ }
+ },
"zeroone": {
"title": "01.AI Цифровая Вселенная"
},
diff --git a/DigitalHumanWeb/locales/ru-RU/models.json b/DigitalHumanWeb/locales/ru-RU/models.json
index 1f1740c..23b265f 100644
--- a/DigitalHumanWeb/locales/ru-RU/models.json
+++ b/DigitalHumanWeb/locales/ru-RU/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, с богатым набором обучающих образцов, демонстрирует превосходные результаты в отраслевых приложениях."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat — это вариант серии Yi-1.5, относящийся к открытым моделям для чата. Yi-1.5 является обновленной версией Yi, которая была непрерывно предобучена на 500B высококачественных корпусах и дообучена на более чем 3M разнообразных образцах. По сравнению с Yi, Yi-1.5 демонстрирует более сильные способности в кодировании, математике, выводах и соблюдении инструкций, сохраняя при этом отличные навыки понимания языка, логического вывода и понимания прочитанного. Эта модель имеет версии с длиной контекста 4K, 16K и 32K, с общим объемом предобучения 3.6T токенов."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B поддерживает 16K токенов, обеспечивая эффективные и плавные возможности генерации языка."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "零一万物 — это последняя версия открытой доработанной модели с 34 миллиардами параметров, которая поддерживает различные сценарии диалога, используя высококачественные обучающие данные, соответствующие человеческим предпочтениям."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "零一万物 — это последняя версия открытой доработанной модели с 9 миллиардами параметров, которая поддерживает различные сценарии диалога, используя высококачественные обучающие данные, соответствующие человеческим предпочтениям."
+ },
"360gpt-pro": {
"description": "360GPT Pro, как важный член серии моделей AI от 360, удовлетворяет разнообразные приложения обработки текста с высокой эффективностью, поддерживает понимание длинных текстов и многораундные диалоги."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K акцентирует внимание на семантической безопасности и ответственности, специально разработан для приложений с высокими требованиями к безопасности контента, обеспечивая точность и надежность пользовательского опыта."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 использует дерево поиска для построения цепочек размышлений и вводит механизм рефлексии, обучаясь с помощью усиленного обучения, модель обладает способностью к саморефлексии и исправлению ошибок."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro — это продвинутая модель обработки естественного языка, выпущенная компанией 360, обладающая выдающимися способностями к генерации и пониманию текста, особенно в области генерации и творчества, способная обрабатывать сложные языковые преобразования и ролевые задачи."
},
+ "360zhinao2-o1": {
+ "description": "Модель 360zhinao2-o1 использует дерево поиска для построения цепочки размышлений и включает механизм рефлексии, обучаясь с помощью усиленного обучения, что позволяет модели самостоятельно рефлексировать и исправлять ошибки."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra — это самая мощная версия в серии больших моделей Xinghuo, которая, обновив сетевые поисковые связи, улучшает понимание и обобщение текстового контента. Это всестороннее решение для повышения производительности в офисе и точного реагирования на запросы, являющееся ведущим интеллектуальным продуктом в отрасли."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Модель обладает лучшими возможностями в стране, превосходя зарубежные модели в задачах на знание, длинные тексты и генерацию контента. Также обладает передовыми мультимодальными возможностями и показывает отличные результаты в нескольких авторитетных тестах."
},
+ "Baichuan4-Air": {
+ "description": "Модель обладает лучшими в стране возможностями, превосходя зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и генерация контента. Также обладает передовыми мультимодальными возможностями и демонстрирует отличные результаты в нескольких авторитетных оценочных тестах."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Модель обладает лучшими в стране возможностями, превосходя зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и генерация контента. Также обладает передовыми мультимодальными возможностями и демонстрирует отличные результаты в нескольких авторитетных оценочных тестах."
+ },
+ "DeepSeek-R1": {
+ "description": "Современная эффективная LLM, специализирующаяся на логическом выводе, математике и программировании."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 — более крупная и умная модель в наборе DeepSeek, была дистиллирована в архитектуру Llama 70B. На основе бенчмарков и человеческой оценки эта модель более умная, чем оригинальная Llama 70B, особенно в задачах, требующих математической и фактической точности."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Модель DeepSeek-R1, основанная на Qwen2.5-Math-1.5B, оптимизирует производительность вывода с помощью усиленного обучения и данных холодного старта, обновляя стандарт многозадачности в открытых моделях."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Модель DeepSeek-R1, основанная на Qwen2.5-14B, оптимизирует производительность вывода с помощью усиленного обучения и данных холодного старта, обновляя стандарт многозадачности в открытых моделях."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "Серия DeepSeek-R1 оптимизирует производительность вывода с помощью усиленного обучения и данных холодного старта, обновляя стандарт многозадачности в открытых моделях, превосходя уровень OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Модель DeepSeek-R1, основанная на Qwen2.5-Math-7B, оптимизирует производительность вывода с помощью усиленного обучения и данных холодного старта, обновляя стандарт многозадачности в открытых моделях."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro - совершенно обновленная многомодальная большая модель, поддерживающая распознавание изображений с любым разрешением и экстремальными соотношениями сторон, улучшенная способность визуального вывода, распознавания документов, понимания деталей и соблюдения инструкций."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite обеспечивает выдающуюся скорость отклика и лучшее соотношение цены и качества, предлагая клиентам больше гибкости в различных сценариях. Поддерживает вывод и настройку с 128k контекстным окном."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite обеспечивает выдающуюся скорость отклика и лучшее соотношение цены и качества, предлагая клиентам больше гибкости в различных сценариях. Поддерживает вывод и настройку с 32k контекстным окном."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite обеспечивает выдающуюся скорость отклика и лучшее соотношение цены и качества, предлагая клиентам больше гибкости в различных сценариях. Поддерживает вывод и настройку с 4k контекстным окном."
+ },
+ "Doubao-pro-128k": {
+ "description": "Модель основных характеристик с лучшими показателями, подходит для обработки сложных задач. Хорошо справляется с задачами референсного ответа, резюмирования, творчества, классификации текста, ролевого взаимодействия и т.д. Поддерживает вывод и настройку с 128k контекстным окном."
+ },
+ "Doubao-pro-256k": {
+ "description": "Лучшая модель для основных задач, подходит для обработки сложных задач, демонстрирует отличные результаты в таких сценариях, как ответ на вопросы, резюмирование, творчество, классификация текста и ролевые игры. Поддерживает вывод на 256k контекстных окнах и тонкую настройку."
+ },
+ "Doubao-pro-32k": {
+ "description": "Модель основных характеристик с лучшими показателями, подходит для обработки сложных задач. Хорошо справляется с задачами референсного ответа, резюмирования, творчества, классификации текста, ролевого взаимодействия и т.д. Поддерживает вывод и настройку с 32k контекстным окном."
+ },
+ "Doubao-pro-4k": {
+ "description": "Модель основных характеристик с лучшими показателями, подходит для обработки сложных задач. Хорошо справляется с задачами референсного ответа, резюмирования, творчества, классификации текста, ролевого взаимодействия и т.д. Поддерживает вывод и настройку с 4k контекстным окном."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Модель Doubao-vision - это многомодальная большая модель, представленная Doubao, обладающая мощными способностями понимания и вывода изображений, а также точным пониманием инструкций. Модель демонстрирует выдающуюся производительность в извлечении текстовой информации из изображений и задачах вывода на основе изображений, что позволяет применять ее в более сложных и широких задачах визуального вопроса и ответа."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Модель Doubao-vision - это многомодальная большая модель, представленная Doubao, обладающая мощными способностями понимания и вывода изображений, а также точным пониманием инструкций. Модель демонстрирует выдающуюся производительность в извлечении текстовой информации из изображений и задачах вывода на основе изображений, что позволяет применять ее в более сложных и широких задачах визуального вопроса и ответа."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Флагманская крупномасштабная языковая модель, разработанная Baidu, охватывающая огромные объемы китайских и английских текстов, обладающая мощными универсальными возможностями, способная удовлетворить большинство требований к диалоговым ответам, генерации контента и сценариям использования плагинов; поддерживает автоматическую интеграцию с плагином поиска Baidu, обеспечивая актуальность информации в ответах."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Флагманская крупномасштабная языковая модель, разработанная Baidu, охватывающая огромные объемы китайских и английских текстов, обладающая мощными универсальными возможностями, способная удовлетворить большинство требований к диалоговым ответам, генерации контента и сценариям использования плагинов; поддерживает автоматическую интеграцию с плагином поиска Baidu, обеспечивая актуальность информации в ответах."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Флагманская крупномасштабная языковая модель, разработанная Baidu, охватывающая огромные объемы китайских и английских текстов, обладающая мощными универсальными возможностями, способная удовлетворить большинство требований к диалоговым ответам, генерации контента и сценариям использования плагинов; поддерживает автоматическую интеграцию с плагином поиска Baidu, обеспечивая актуальность информации в ответах."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Флагманская сверхкрупномасштабная языковая модель, разработанная Baidu, которая по сравнению с ERNIE 3.5 обеспечивает полное обновление возможностей модели и широко применяется в сложных задачах в различных областях; поддерживает автоматическую интеграцию с плагином поиска Baidu, обеспечивая актуальность информации в ответах."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Флагманская сверхкрупномасштабная языковая модель, разработанная Baidu, которая по сравнению с ERNIE 3.5 обеспечивает полное обновление возможностей модели и широко применяется в сложных задачах в различных областях; поддерживает автоматическую интеграцию с плагином поиска Baidu, обеспечивая актуальность информации в ответах."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Флагманская 超大型 языковая модель, разработанная Baidu, демонстрирует отличные результаты и хорошо подходит для сложных задач в различных областях; поддерживает автоматическую интеграцию с плагином поиска Baidu, обеспечивая своевременность ответов. По сравнению с ERNIE 4.0 имеет лучшие показатели производительности."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Флагманская сверхкрупномасштабная языковая модель, разработанная Baidu, демонстрирующая отличные результаты в комплексной эффективности, широко применяемая в сложных задачах в различных областях; поддерживает автоматическую интеграцию с плагином поиска Baidu, обеспечивая актуальность информации в ответах. По сравнению с ERNIE 4.0, она демонстрирует лучшие показатели производительности."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Специализированная языковая модель, разработанная Baidu для вертикальных сценариев, подходящая для применения в играх (NPC), диалогах службы поддержки, ролевых играх и других сценариях, обладающая ярко выраженным и согласованным стилем персонажей, высокой способностью следовать инструкциям и отличной производительностью вывода."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Легковесная языковая модель, разработанная Baidu, которая сочетает в себе отличные результаты модели и производительность вывода, превосходя ERNIE Lite, подходит для использования в системах с низкой вычислительной мощностью."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Новая высокопроизводительная языковая модель, разработанная Baidu в 2024 году, обладающая выдающимися универсальными возможностями, подходит для использования в качестве базовой модели для тонкой настройки, лучше справляясь с задачами в специфических сценариях, при этом обладая отличной производительностью вывода."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Новая высокопроизводительная языковая модель, разработанная Baidu в 2024 году, обладающая выдающимися универсальными возможностями, превосходящая ERNIE Speed, подходит для использования в качестве базовой модели для тонкой настройки, лучше справляясь с задачами в специфических сценариях, при этом обладая отличной производительностью вывода."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) — это инновационная модель, подходящая для многообластных приложений и сложных задач."
},
- "Max-32k": {
- "description": "Spark Max 32K оснащен высокой способностью обработки контекста, улучшенным пониманием контекста и логическим выводом, поддерживает текстовый ввод до 32K токенов, подходит для чтения длинных документов, частных вопросов и ответов и других сценариев"
+ "InternVL2-8B": {
+ "description": "InternVL2-8B — это мощная визуально-языковая модель, поддерживающая многомодальную обработку изображений и текста, способная точно распознавать содержимое изображений и генерировать соответствующие описания или ответы."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B — это мощная визуально-языковая модель, поддерживающая многомодальную обработку изображений и текста, способная точно распознавать содержимое изображений и генерировать соответствующие описания или ответы."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Отличные способности к визуальному выводу на изображениях высокого разрешения, подходящие для приложений визуального понимания."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Передовые способности к визуальному выводу, подходящие для приложений визуального понимания."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct — это одна из последних языковых моделей, выпущенных Alibaba Cloud. Эта 72B модель значительно улучшила способности в области кодирования и математики. Модель также поддерживает множество языков, охватывающих более 29 языков, включая китайский и английский. Она значительно улучшила выполнение инструкций, понимание структурированных данных и генерацию структурированных выходных данных (особенно JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct — это одна из последних языковых моделей, выпущенных Alibaba Cloud. Эта 7B модель значительно улучшила способности в области кодирования и математики. Модель также поддерживает множество языков, охватывающих более 29 языков, включая китайский и английский. Она значительно улучшила выполнение инструкций, понимание структурированных данных и генерацию структурированных выходных данных (особенно JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Текстовая модель Llama 3.1 с оптимизацией под инструкции, разработанная для многоязычных диалоговых случаев, показывает отличные результаты по сравнению с многими доступными открытыми и закрытыми чат-моделями на общепринятых отраслевых бенчмарках."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO — это высокоадаптивная многомодельная комбинация, предназначенная для предоставления выдающегося творческого опыта."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Текстовая модель Llama 3.1 с оптимизацией под инструкции, разработанная для многоязычных диалоговых случаев, показывает отличные результаты по сравнению с многими доступными открытыми и закрытыми чат-моделями на общепринятых отраслевых бенчмарках."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Текстовая модель Llama 3.1 с оптимизацией под инструкции, разработанная для многоязычных диалоговых случаев, показывает отличные результаты по сравнению с многими доступными открытыми и закрытыми чат-моделями на общепринятых отраслевых бенчмарках."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Современная передовая компактная языковая модель с выдающимися способностями к пониманию языка, логическому выводу и генерации текста."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Современная передовая компактная языковая модель с выдающимися способностями к пониманию языка, логическому выводу и генерации текста."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 — это самая современная многоязычная открытая языковая модель из серии Llama, которая позволяет получить производительность, сопоставимую с 405B моделями, по крайне низкой цене. Основана на структуре Transformer и улучшена с помощью контролируемой донастройки (SFT) и обучения с подкреплением на основе человеческой обратной связи (RLHF) для повышения полезности и безопасности. Ее версия с оптимизацией под инструкции специально разработана для многоязычных диалогов и показывает лучшие результаты по сравнению с многими открытыми и закрытыми чат-моделями на нескольких отраслевых бенчмарках. Дата окончания знаний — декабрь 2023 года."
+ },
+ "MiniMax-Text-01": {
+ "description": "В серии моделей MiniMax-01 мы сделали смелые инновации: впервые в крупномасштабном масштабе реализован линейный механизм внимания, традиционная архитектура Transformer больше не является единственным выбором. Объем параметров этой модели достигает 456 миллиардов, из которых 45,9 миллиарда активируются за один раз. Комплексная производительность модели сопоставима с ведущими зарубежными моделями, при этом она может эффективно обрабатывать контекст длиной до 4 миллионов токенов, что в 32 раза больше, чем у GPT-4o, и в 20 раз больше, чем у Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) — это высокоточная модель команд, подходящая для сложных вычислений."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) предлагает оптимизированный языковой вывод и разнообразные возможности применения."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Обновление модели Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 демонстрирует превосходные результаты в различных визуально-языковых задачах, включая понимание документов и графиков, понимание текстов сцены, OCR, решение научных и математических задач."
},
"Phi-3-medium-128k-instruct": {
"description": "Та же модель Phi-3-medium, но с большим размером контекста для RAG или нескольких подсказок."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Модель с 7B параметрами, демонстрирующая лучшее качество, чем Phi-3-mini, с акцентом на высококачественные, насыщенные рассуждениями данные."
},
- "Pro-128k": {
- "description": "Spark Pro-128K оснащен возможностями обработки контекста большого объема, способным обрабатывать до 128K контекстной информации, особенно подходит для анализа длинных текстов и обработки долгосрочных логических связей, обеспечивая плавную и последовательную логику и разнообразную поддержку ссылок в сложных текстовых коммуникациях."
+ "Phi-3.5-mini-instruct": {
+ "description": "Обновленная версия модели Phi-3-mini."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Обновленная версия модели Phi-3-vision."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 демонстрирует превосходные результаты в различных визуально-языковых задачах, включая понимание документов и графиков, понимание текстов сцены, OCR, решение научных и математических задач."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct — это языковая модель с дообучением на инструкциях в серии Qwen2, с параметрами 1.5B. Эта модель основана на архитектуре Transformer и использует такие технологии, как активационная функция SwiGLU, смещение внимания QKV и групповой запрос внимания. Она показывает отличные результаты в понимании языка, генерации, многоязычных способностях, кодировании, математике и выводах в различных бенчмарках, превосходя большинство открытых моделей. По сравнению с Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct демонстрирует значительное улучшение производительности в тестах MMLU, HumanEval, GSM8K, C-Eval и IFEval, несмотря на немного меньшее количество параметров."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct — это языковая модель с дообучением на инструкциях в серии Qwen2, с параметрами 7B. Эта модель основана на архитектуре Transformer и использует такие технологии, как активационная функция SwiGLU, смещение внимания QKV и групповой запрос внимания. Она может обрабатывать большие объемы входных данных. Эта модель показывает отличные результаты в понимании языка, генерации, многоязычных способностях, кодировании, математике и выводах в различных бенчмарках, превосходя большинство открытых моделей и демонстрируя конкурентоспособность с проприетарными моделями в некоторых задачах. Qwen2-7B-Instruct показывает значительное улучшение производительности в нескольких оценках по сравнению с Qwen1.5-7B-Chat."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL - это последняя версия модели Qwen-VL, которая достигла передовых результатов в тестировании визуального понимания."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct — это одна из последних языковых моделей, выпущенных Alibaba Cloud. Эта 7B модель значительно улучшила способности в области кодирования и математики. Модель также поддерживает множество языков, охватывающих более 29 языков, включая китайский и английский. Она значительно улучшила выполнение инструкций, понимание структурированных данных и генерацию структурированных выходных данных (особенно JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct — это последняя версия серии языковых моделей, специфичных для кода, выпущенная Alibaba Cloud. Эта модель значительно улучшила способности генерации кода, вывода и исправления на основе Qwen2.5, обучаясь на 5.5 триллионах токенов. Она не только усилила кодирование, но и сохранила преимущества в математике и общих способностях. Модель предоставляет более полную основу для практических приложений, таких как интеллектуальные агенты кода."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat — это открытая версия предобученной модели из серии GLM-4, выпущенная Zhizhu AI. Эта модель показывает отличные результаты в семантике, математике, выводах, коде и знаниях. Кроме поддержки многократных диалогов, GLM-4-9B-Chat также обладает продвинутыми функциями, такими как веб-браузинг, выполнение кода, вызов пользовательских инструментов (Function Call) и вывод длинных текстов. Модель поддерживает 26 языков, включая китайский, английский, японский, корейский и немецкий. В нескольких бенчмарках GLM-4-9B-Chat демонстрирует отличные результаты, такие как AlignBench-v2, MT-Bench, MMLU и C-Eval. Эта модель поддерживает максимальную длину контекста 128K и подходит для академических исследований и коммерческих приложений."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 — это модель вывода, управляемая обучением с подкреплением (RL), которая решает проблемы повторяемости и читаемости в модели. Перед RL DeepSeek-R1 вводит данные холодного старта, что дополнительно оптимизирует производительность вывода. Она показывает сопоставимые результаты с OpenAI-o1 в математических, кодовых и задачах вывода и улучшает общую эффективность благодаря тщательно продуманным методам обучения."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 — это языковая модель с 6710 миллиардами параметров, использующая архитектуру смешанных экспертов (MoE) и многофункциональное внимание (MLA), в сочетании с стратегией балансировки нагрузки без вспомогательных потерь, оптимизирующая эффективность вывода и обучения. После предобучения на 14.8 триллионах высококачественных токенов и последующей контролируемой донастройки и обучения с подкреплением, DeepSeek-V3 превосходит другие открытые модели и приближается к ведущим закрытым моделям."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma — это одна из легковесных, передовых открытых моделей, разработанных Google. Это крупная языковая модель с только декодером, поддерживающая английский язык, предлагающая открытые веса, предобученные варианты и варианты с дообучением на инструкциях. Модель Gemma подходит для различных задач генерации текста, включая вопросы и ответы, резюме и выводы. Эта 9B модель была обучена на 8 триллионах токенов. Ее относительно небольшой размер позволяет развертывать ее в условиях ограниченных ресурсов, таких как ноутбуки, настольные компьютеры или ваша собственная облачная инфраструктура, что позволяет большему количеству людей получить доступ к передовым моделям ИИ и способствовать инновациям."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 — это семейство многоязычных крупных языковых моделей, разработанных Meta, включая предобученные и дообученные на инструкциях варианты с параметрами 8B, 70B и 405B. Эта 8B модель с дообучением на инструкциях оптимизирована для многоязычных диалоговых сценариев и показывает отличные результаты в нескольких отраслевых бенчмарках. Обучение модели использовало более 150 триллионов токенов открытых данных и применяло такие технологии, как контролируемое дообучение и обучение с подкреплением на основе человеческой обратной связи для повышения полезности и безопасности модели. Llama 3.1 поддерживает генерацию текста и кода, с датой окончания знаний в декабре 2023 года."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview — это инновационная модель обработки естественного языка, способная эффективно обрабатывать сложные задачи генерации диалогов и понимания контекста."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview — это исследовательская модель, разработанная командой Qwen, сосредоточенная на способностях визуального вывода, обладающая уникальными преимуществами в понимании сложных сцен и решении визуально связанных математических задач."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Как тестовая версия Qwen2, Qwen1.5 использует большие объемы данных для достижения более точных диалоговых функций."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ — это модель вывода из серии Qwen. В отличие от традиционных моделей, настроенных на инструкции, QwQ обладает способностями к мышлению и рассуждению, что позволяет значительно улучшить производительность в задачах нижнего уровня, особенно при решении сложных проблем. QwQ-32B — это средняя модель вывода, которая демонстрирует конкурентоспособные результаты в сравнении с самыми современными моделями вывода (такими как DeepSeek-R1, o1-mini). Эта модель использует технологии RoPE, SwiGLU, RMSNorm и Attention QKV bias, имеет 64-слойную архитектуру и 40 голов внимания Q (в архитектуре GQA KV составляет 8)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) обеспечивает быстрые ответы и естественные диалоговые возможности, подходящие для многоязычной среды."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview — это последняя экспериментальная исследовательская модель Qwen, сосредоточенная на повышении возможностей вывода ИИ. Исследуя сложные механизмы, такие как смешение языков и рекурсивные выводы, основные преимущества включают мощные аналитические способности, математические и программные навыки. В то же время существуют проблемы с переключением языков, циклом вывода, соображениями безопасности и различиями в других способностях."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct — это языковая модель с дообучением на инструкциях в серии Qwen2, с параметрами 1.5B. Эта модель основана на архитектуре Transformer и использует такие технологии, как активационная функция SwiGLU, смещение внимания QKV и групповой запрос внимания. Она показывает отличные результаты в понимании языка, генерации, многоязычных способностях, кодировании, математике и выводах в различных бенчмарках, превосходя большинство открытых моделей. По сравнению с Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct демонстрирует значительное улучшение производительности в тестах MMLU, HumanEval, GSM8K, C-Eval и IFEval, несмотря на немного меньшее количество параметров."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 — это передовая универсальная языковая модель, поддерживающая множество типов команд."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct — это языковая модель с дообучением на инструкциях в серии Qwen2, с параметрами 72B. Эта модель основана на архитектуре Transformer и использует такие технологии, как активационная функция SwiGLU, смещение внимания QKV и групповой запрос внимания. Она может обрабатывать большие объемы входных данных. Эта модель показывает отличные результаты в понимании языка, генерации, многоязычных способностях, кодировании, математике и выводах в различных бенчмарках, превосходя большинство открытых моделей и демонстрируя конкурентоспособность с проприетарными моделями в некоторых задачах."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL - это последняя версия модели Qwen-VL, которая достигла передовых результатов в тестировании визуального понимания."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 — это новая серия крупных языковых моделей, предназначенная для оптимизации обработки инструктивных задач."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 — это новая серия крупных языковых моделей, предназначенная для оптимизации обработки инструктивных задач."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 — это новая серия крупных языковых моделей с более сильными способностями понимания и генерации."
+ "description": "Большая языковая модель, разработанная командой Alibaba Cloud Tongyi Qianwen."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 - это новая серия крупных языковых моделей с улучшенными способностями понимания и генерации."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 - это новая серия крупных языковых моделей, нацеленная на оптимизацию обработки задач с инструкциями."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 — это новая серия крупных языковых моделей, предназначенная для оптимизации обработки инструктивных задач."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 - это новая серия крупных языковых моделей, нацеленная на оптимизацию обработки задач с инструкциями."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder сосредоточен на написании кода."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math сосредоточен на решении математических задач, предоставляя профессиональные ответы на сложные вопросы."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct — это последняя версия серии языковых моделей, специфичных для кода, выпущенная Alibaba Cloud. Эта модель значительно улучшила способности генерации кода, вывода и исправления на основе Qwen2.5, обучаясь на 5.5 триллионах токенов. Она не только усилила кодирование, но и сохранила преимущества в математике и общих способностях. Модель предоставляет более полную основу для практических приложений, таких как интеллектуальные агенты кода."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 — это последняя серия моделей Qwen, поддерживающая контекст до 128k. По сравнению с текущими лучшими открытыми моделями, Qwen2-72B значительно превосходит ведущие модели по многим аспектам, включая понимание естественного языка, знания, код, математику и многоязычность."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 — это последняя серия моделей Qwen, способная превосходить лучшие открытые модели сопоставимого размера и даже более крупные модели. Qwen2 7B демонстрирует значительные преимущества в нескольких тестах, особенно в понимании кода и китайского языка."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B — это мощная модель визуального языка, поддерживающая многомодальную обработку изображений и текста, способная точно распознавать содержимое изображений и генерировать соответствующие описания или ответы."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct — это языковая модель с 14 миллиардами параметров, с отличными показателями производительности, оптимизированная для китайского и многоязычного контекста, поддерживает интеллектуальные ответы, генерацию контента и другие приложения."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct — это языковая модель с 32 миллиардами параметров, с сбалансированными показателями производительности, оптимизированная для китайского и многоязычного контекста, поддерживает интеллектуальные ответы, генерацию контента и другие приложения."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct поддерживает контекст до 16k, генерируя длинные тексты более 8K. Поддерживает вызовы функций и бесшовное взаимодействие с внешними системами, что значительно повышает гибкость и масштабируемость. Знания модели значительно увеличены, а способности в кодировании и математике значительно улучшены, поддерживает более 29 языков."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct — это языковая модель с 7 миллиардами параметров, поддерживающая вызовы функций и бесшовное взаимодействие с внешними системами, что значительно повышает гибкость и масштабируемость. Оптимизирована для китайского и многоязычного контекста, поддерживает интеллектуальные ответы, генерацию контента и другие приложения."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct — это модель программирования на основе масштабного предварительного обучения, обладающая мощными способностями к пониманию и генерации кода, способная эффективно решать различные задачи программирования, особенно подходит для интеллектуального написания кода, автоматизации скриптов и ответов на программные вопросы."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct — это крупная языковая модель, специально разработанная для генерации кода, понимания кода и эффективных сценариев разработки, с передовым масштабом параметров 32B, способная удовлетворить разнообразные потребности программирования."
+ },
+ "SenseChat": {
+ "description": "Базовая версия модели (V4), длина контекста 4K, обладает мощными универсальными возможностями."
+ },
+ "SenseChat-128K": {
+ "description": "Базовая версия модели (V4), длина контекста 128K, демонстрирует отличные результаты в задачах понимания и генерации длинных текстов."
+ },
+ "SenseChat-32K": {
+ "description": "Базовая версия модели (V4), длина контекста 32K, гибко применяется в различных сценариях."
+ },
+ "SenseChat-5": {
+ "description": "Последняя версия модели (V5.5), длина контекста 128K, значительно улучшенные способности в математическом рассуждении, английских диалогах, следовании инструкциям и понимании длинных текстов, сопоставимые с GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "Это последняя версия на основе V5.5, которая значительно улучшила свои базовые способности в китайском и английском языках, общении, научных знаниях, гуманитарных знаниях, написании, математической логике и контроле количества слов по сравнению с предыдущей версией."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Длина контекста 32K, превосходит GPT-4 в понимании диалогов на кантонском, сопоставим с GPT-4 Turbo в таких областях, как знания, рассуждение, математика и написание кода."
+ },
+ "SenseChat-Character": {
+ "description": "Стандартная версия модели, длина контекста 8K, высокая скорость отклика."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Расширенная версия модели, длина контекста 32K, всеобъемлющие улучшения возможностей, поддерживает диалоги на китайском и английском языках."
+ },
+ "SenseChat-Turbo": {
+ "description": "Подходит для быстрого ответа на вопросы и сценариев тонкой настройки модели."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "Это последняя легковесная версия модели, которая достигает более 90% возможностей полной модели и значительно снижает затраты на вывод."
+ },
+ "SenseChat-Vision": {
+ "description": "Последняя версия модели (V5.5) поддерживает ввод нескольких изображений, полностью реализует оптимизацию базовых возможностей модели и значительно улучшила распознавание свойств объектов, пространственные отношения, распознавание событий, понимание сцен, распознавание эмоций, логическое рассуждение и понимание текста."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Модель второго поколения Skylark (云雀), модель Skylark2-lite имеет высокую скорость отклика, подходит для сценариев с высокими требованиями к оперативности, чувствительных к стоимости и с не такими высокими требованиями к точности модели. Длина контекстного окна составляет 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Модель второго поколения Skylark (云雀), версия Skylark2-pro имеет высокую точность модели, подходит для более сложных сценариев генерации текста, таких как написание специализированной документации, создание романов, высококачественный перевод и т.д. Длина контекстного окна составляет 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Модель второго поколения Skylark (云雀), модель Skylark2-pro имеет высокую точность, подходит для более сложных сценариев генерации текста, таких как специализированная документация, создание романов, высококачественный перевод и т.д. Длина контекстного окна составляет 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Модель второго поколения Skylark (云雀), модель Skylark2-pro-character демонстрирует выдающиеся способности к ролевым взаимодействиям и чатам, умеет играть различные роли в зависимости от требований пользователя, что делает общение естественным и плавным. Подходит для разработки чат-ботов, виртуальных помощников и онлайн-сервисов с высокой скоростью отклика."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Модель второго поколения Skylark (云雀), модель Skylark2-pro-turbo-8k обеспечивает более быструю обработку и сниженные затраты, длина контекстного окна составляет 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B — это открытая модель из серии ChatGLM, разработанная Zhizhu AI. Эта модель сохраняет отличные характеристики предыдущих моделей, такие как плавность диалога и низкий порог развертывания, одновременно вводя новые функции. Она использует более разнообразные обучающие данные, большее количество шагов обучения и более разумную стратегию обучения, показывая отличные результаты среди предобученных моделей объемом менее 10B. ChatGLM3-6B поддерживает многократные диалоги, вызовы инструментов, выполнение кода и задачи агента в сложных сценариях. Кроме диалоговой модели, также открыты базовая модель ChatGLM-6B-Base и модель для длинных текстовых диалогов ChatGLM3-6B-32K. Эта модель полностью открыта для академических исследований и также допускает бесплатное коммерческое использование после регистрации."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B — это открытая версия, обеспечивающая оптимизированный диалоговый опыт для приложений."
},
+ "TeleAI/TeleChat2": {
+ "description": "Модель TeleChat2 была разработана China Telecom с нуля и представляет собой генеративную семантическую модель, поддерживающую функции вопросов и ответов, генерации кода, генерации длинных текстов и т.д., предоставляя пользователям услуги консультаций в диалоговом формате, способную взаимодействовать с пользователями, отвечать на вопросы, помогать в творчестве и эффективно помогать пользователям получать информацию, знания и вдохновение. Модель показывает отличные результаты в решении проблем с галлюцинациями, генерацией длинных текстов и логическим пониманием."
+ },
+ "TeleAI/TeleMM": {
+ "description": "Модель TeleMM — это многомодальная модель, разработанная China Telecom, способная обрабатывать текстовые, графические и другие виды входных данных, поддерживающая функции понимания изображений, анализа графиков и т.д., предоставляя пользователям услуги понимания на разных модальностях. Модель может взаимодействовать с пользователями в многомодальном формате, точно понимая входной контент, отвечая на вопросы, помогая в творчестве и эффективно предоставляя многомодальную информацию и поддержку вдохновения. Она показывает отличные результаты в задачах многомодального восприятия и логического вывода."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct — это одна из последних языковых моделей, выпущенных Alibaba Cloud. Эта 72B модель значительно улучшила способности в области кодирования и математики. Модель также поддерживает множество языков, охватывающих более 29 языков, включая китайский и английский. Она значительно улучшила выполнение инструкций, понимание структурированных данных и генерацию структурированных выходных данных (особенно JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, сохраняя выдающиеся универсальные языковые способности оригинальной серии моделей, значительно улучшила математическую логику и способности к кодированию благодаря инкрементальному обучению на 500 миллиардов высококачественных токенов."
+ },
"abab5.5-chat": {
"description": "Ориентирован на производственные сценарии, поддерживает обработку сложных задач и эффективную генерацию текста, подходит для профессиональных приложений."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Оптимизирован для диалогов на китайском языке, обеспечивая плавную генерацию диалогов, соответствующую китайским языковым привычкам."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Открытая модель вызова функций от Fireworks, обеспечивающая выдающиеся возможности выполнения команд и открытые настраиваемые функции."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2 от компании Fireworks — это высокопроизводительная модель вызова функций, разработанная на основе Llama-3 и оптимизированная для вызова функций, диалогов и выполнения команд."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b — это визуальная языковая модель, способная одновременно обрабатывать изображения и текстовые вводы, обученная на высококачественных данных, подходящая для мультимодальных задач."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 — это передовая большая языковая модель, оптимизированная с помощью обучения с подкреплением и холодных стартовых данных, обладающая выдающимися показателями вывода, математики и программирования."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B для команд, основанная на предыдущих технологиях Google, подходит для ответов на вопросы, резюмирования и вывода текста."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Мощная языковая модель Mixture-of-Experts (MoE) от Deepseek с общим количеством параметров 671B, активирующая 37B параметров на каждый токен."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Модель Llama 3 70B для команд, специально оптимизированная для многоязычных диалогов и понимания естественного языка, превосходит большинство конкурентных моделей."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Модель Llama 3 70B для команд (HF версия), результаты которой совпадают с официальной реализацией, подходит для высококачественных задач выполнения команд."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Модель Llama 3 8B для команд, оптимизированная для диалогов и многоязычных задач, демонстрирует выдающиеся и эффективные результаты."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Модель Llama 3.1 8B для команд, оптимизированная для многоязычных диалогов, способная превосходить большинство открытых и закрытых моделей по общим отраслевым стандартам."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Модель Meta с 11B параметрами, оптимизированная для вывода изображений. Эта модель предназначена для визуального распознавания, вывода изображений, описания изображений и ответа на общие вопросы о изображениях. Эта модель способна понимать визуальные данные, такие как графики и диаграммы, и преодолевать разрыв между визуальным и языковым пониманием, генерируя текстовые описания деталей изображений."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Модель Llama 3.2 3B для инструкций - это компактная многоязычная модель, запущенная Meta. Эта модель предназначена для повышения эффективности и обеспечивает значительное улучшение в задержке и стоимости по сравнению с более крупными моделями. Примеры использования модели включают запросы, переоформление подсказок и помощь в написании."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Модель Meta с 90B параметрами, оптимизированная для вывода изображений. Эта модель предназначена для визуального распознавания, вывода изображений, описания изображений и ответа на общие вопросы о изображениях. Эта модель способна понимать визуальные данные, такие как графики и диаграммы, и преодолевать разрыв между визуальным и языковым пониманием, генерируя текстовые описания деталей изображений."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct — это обновленная версия Llama 3.1 70B от декабря. Эта модель улучшена на основе Llama 3.1 70B (выпущенной в июле 2024 года), с усиленной поддержкой вызовов инструментов, многоязычного текста, математических и программных возможностей. Модель достигла ведущих в отрасли показателей в области вывода, математики и соблюдения инструкций, обеспечивая производительность, сопоставимую с 3.1 405B, при этом обладая значительными преимуществами по скорости и стоимости."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Модель с 24B параметрами, обладающая передовыми возможностями, сопоставимыми с более крупными моделями."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B для команд, с большим количеством параметров и архитектурой с несколькими экспертами, всесторонне поддерживает эффективную обработку сложных задач."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B для команд, архитектура с несколькими экспертами обеспечивает эффективное выполнение и следование командам."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B для команд (HF версия), производительность которой совпадает с официальной реализацией, подходит для множества эффективных задач."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "Модель MythoMax L2 13B, использующая новые технологии объединения, хорошо подходит для повествования и ролевых игр."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision для команд, легковесная мультимодальная модель, способная обрабатывать сложную визуальную и текстовую информацию, обладая высокой способностью к выводу."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "Модель StarCoder 15.5B, поддерживающая сложные задачи программирования, с улучшенными многоязычными возможностями, подходит для генерации и понимания сложного кода."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Модель QwQ — это экспериментальная исследовательская модель, разработанная командой Qwen, сосредоточенная на улучшении возможностей вывода ИИ."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "72B версия модели Qwen-VL — это результат последней итерации Alibaba, представляющий собой инновации почти за год."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "Модель StarCoder 7B, обученная на более чем 80 языках программирования, обладает выдающимися способностями к заполнению кода и пониманию контекста."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 - это серия языковых моделей, содержащая только декодеры, разработанная командой Qwen от Alibaba Cloud. Эти модели предлагаются в различных размерах: 0.5B, 1.5B, 3B, 7B, 14B, 32B и 72B, с вариантами базовой и инструкционной версии."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct — это последняя версия серии языковых моделей, специфичных для кода, выпущенная Alibaba Cloud. Эта модель значительно улучшила способности генерации кода, вывода и исправления на основе Qwen2.5, обучаясь на 5.5 триллионах токенов. Она не только усилила кодирование, но и сохранила преимущества в математике и общих способностях. Модель предоставляет более полную основу для практических приложений, таких как интеллектуальные агенты кода."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Модель Yi-Large, обладающая выдающимися возможностями обработки нескольких языков, подходит для различных задач генерации и понимания языка."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Многоязычная модель с 52B параметрами (12B активных), предлагающая контекстное окно длиной 256K, вызовы функций, структурированный вывод и основанное на фактах генерирование."
},
- "ai21-jamba-instruct": {
- "description": "Модель LLM на основе Mamba, предназначенная для достижения наилучших показателей производительности, качества и экономической эффективности."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet устанавливает новые отраслевые стандарты, превосходя модели конкурентов и Claude 3 Opus, демонстрируя отличные результаты в широком спектре оценок, при этом обладая скоростью и стоимостью наших моделей среднего уровня."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet установил новые стандарты в отрасли, превзойдя модели конкурентов и Claude 3 Opus, продемонстрировав отличные результаты в широкомасштабных оценках, при этом обладая скоростью и стоимостью наших моделей среднего уровня."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku — это самая быстрая и компактная модель от Anthropic, обеспечивающая почти мгновенную скорость ответа. Она может быстро отвечать на простые запросы и запросы. Клиенты смогут создать бесшовный AI-опыт, имитирующий человеческое взаимодействие. Claude 3 Haiku может обрабатывать изображения и возвращать текстовый вывод, имея контекстное окно в 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus — это самая мощная модель от Anthropic для обработки высококомплексных задач. Она демонстрирует выдающиеся результаты по производительности, интеллекту, плавности и пониманию."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku — это самая быстрая модель следующего поколения от Anthropic. По сравнению с Claude 3 Haiku, Claude 3.5 Haiku продемонстрировала улучшения во всех навыках и превзошла предыдущую крупнейшую модель Claude 3 Opus во многих интеллектуальных бенчмарках."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet предлагает возможности, превосходящие Opus, и скорость, превышающую Sonnet, при этом сохраняя ту же цену. Sonnet особенно хорошо справляется с программированием, наукой о данных, визуальной обработкой и агентскими задачами."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet — это самая умная модель от Anthropic на сегодняшний день и первая в мире смешанная модель вывода. Claude 3.7 Sonnet может генерировать почти мгновенные ответы или длительные пошаговые размышления, позволяя пользователям четко видеть эти процессы. Sonnet особенно хорошо справляется с программированием, научными данными, визуальной обработкой и агентскими задачами."
+ },
"aya": {
"description": "Aya 23 — это многоязычная модель, выпущенная Cohere, поддерживающая 23 языка, обеспечивая удобство для многоязычных приложений."
},
"aya:35b": {
"description": "Aya 23 — это многоязычная модель, выпущенная Cohere, поддерживающая 23 языка, обеспечивая удобство для многоязычных приложений."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B — это открытая коммерческая крупная языковая модель с 13 миллиардами параметров, разработанная Baichuan Intelligence, которая показала лучшие результаты среди моделей того же размера на авторитетных бенчмарках на китайском и английском языках."
+ },
"charglm-3": {
"description": "CharGLM-3 разработан для ролевых игр и эмоционального сопровождения, поддерживает сверхдлинную многократную память и персонализированные диалоги, имеет широкое применение."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 предлагает ключевые улучшения для бизнеса, включая ведущие в отрасли 200K токенов контекста, значительное снижение частоты галлюцинаций модели, системные подсказки и новую тестовую функцию: вызов инструментов."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku — это самая быстрая следующая модель от Anthropic. По сравнению с Claude 3 Haiku, Claude 3.5 Haiku продемонстрировала улучшения во всех навыках и превзошла предыдущую крупнейшую модель Claude 3 Opus во многих интеллектуальных тестах."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet предлагает возможности, превосходящие Opus, и скорость, быстрее Sonnet, при этом сохраняя ту же цену. Sonnet особенно хорош в программировании, науке о данных, визуальной обработке и задачах агентов."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet предлагает возможности, превышающие Opus, и скорость, превышающую Sonnet, при этом сохраняя ту же цену. Sonnet особенно хорош в программировании, данных, визуальной обработке и代理задачах."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet — это самая мощная модель от Anthropic, обладающая передовыми характеристиками в области высоко сложных задач. Она может обрабатывать открытые подсказки и невидимые сценарии, демонстрируя отличную плавность и человеческое понимание. Claude 3.7 Sonnet демонстрирует передовые возможности генеративного AI. Claude 3.7 Sonnet может обрабатывать изображения и возвращать текстовый вывод, имея контекстное окно в 200K."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku — это самая быстрая и компактная модель от Anthropic, предназначенная для достижения почти мгновенных ответов. Она обладает быстрой и точной направленной производительностью."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet обеспечивает идеальный баланс между интеллектом и скоростью для корпоративных рабочих нагрузок. Он предлагает максимальную полезность по более низкой цене, надежен и подходит для масштабного развертывания."
},
- "claude-instant-1.2": {
- "description": "Модель Anthropic для текстовой генерации с низкой задержкой и высокой пропускной способностью, поддерживающая генерацию сотен страниц текста."
- },
"codegeex-4": {
"description": "CodeGeeX-4 — это мощный AI помощник по программированию, поддерживающий интеллектуальные ответы и автозаполнение кода на различных языках программирования, повышая эффективность разработки."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B — это многоязычная модель генерации кода, поддерживающая полный спектр функций, включая автозаполнение и генерацию кода, интерпретатор кода, веб-поиск, вызовы функций и вопросы по коду на уровне репозитория, охватывающая различные сценарии разработки программного обеспечения. Это одна из лучших моделей генерации кода с количеством параметров менее 10B."
+ },
"codegemma": {
"description": "CodeGemma — это легковесная языковая модель, специально разработанная для различных задач программирования, поддерживающая быструю итерацию и интеграцию."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama — это LLM, сосредоточенная на генерации и обсуждении кода, поддерживающая широкий спектр языков программирования, подходит для среды разработчиков."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama — это LLM, сосредоточенная на генерации и обсуждении кода, с поддержкой широкого спектра языков программирования, подходящая для среды разработчиков."
+ },
"codellama:13b": {
"description": "Code Llama — это LLM, сосредоточенная на генерации и обсуждении кода, поддерживающая широкий спектр языков программирования, подходит для среды разработчиков."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ — это высокопроизводительная большая языковая модель, специально разработанная для реальных бизнес-сценариев и сложных приложений."
},
+ "dall-e-2": {
+ "description": "Вторая генерация модели DALL·E, поддерживающая более реалистичную и точную генерацию изображений с разрешением в 4 раза выше, чем у первой генерации."
+ },
+ "dall-e-3": {
+ "description": "Последняя модель DALL·E, выпущенная в ноябре 2023 года. Поддерживает более реалистичную и точную генерацию изображений с более сильной детализацией."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct предлагает высокую надежность в обработке команд, поддерживая приложения в различных отраслях."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 — это модель вывода, управляемая методом обучения с подкреплением (RL), которая решает проблемы повторяемости и читаемости модели. Перед применением RL DeepSeek-R1 вводит данные холодного старта, что дополнительно оптимизирует производительность вывода. Она показывает сопоставимые результаты с OpenAI-o1 в математических, кодовых и задачах вывода, а также улучшает общую эффективность благодаря тщательно разработанным методам обучения."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "Модель DeepSeek-R1, дистиллированная с помощью усиленного обучения и данных холодного старта, оптимизирует производительность вывода, обновляя стандарт многозадачности в открытых моделях."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B — это дистиллированная модель, основанная на Llama-3.1-8B. Эта модель была дообучена на образцах, сгенерированных DeepSeek-R1, и демонстрирует отличные способности вывода. Она показала хорошие результаты в нескольких бенчмарках, включая 89.1% точности на MATH-500, 50.4% проходной уровень на AIME 2024 и 1205 баллов на CodeForces, демонстрируя сильные математические и программные способности для модели объемом 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Модель DeepSeek-R1, дистиллированная с помощью усиленного обучения и данных холодного старта, оптимизирует производительность вывода, обновляя стандарт многозадачности в открытых моделях."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Модель DeepSeek-R1, дистиллированная с помощью усиленного обучения и данных холодного старта, оптимизирует производительность вывода, обновляя стандарт многозадачности в открытых моделях."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B — это модель, полученная с помощью дистилляции на основе Qwen2.5-32B. Эта модель была дообучена на 800000 отобранных образцах, сгенерированных DeepSeek-R1, и демонстрирует выдающуюся производительность в таких областях, как математика, программирование и логика. Она показала отличные результаты в нескольких бенчмарках, включая AIME 2024, MATH-500 и GPQA Diamond, достигнув 94.3% точности на MATH-500, демонстрируя мощные способности математического вывода."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B — это модель, полученная с помощью дистилляции на основе Qwen2.5-Math-7B. Эта модель была дообучена на 800000 отобранных образцах, сгенерированных DeepSeek-R1, и демонстрирует отличные способности вывода. Она показала выдающиеся результаты в нескольких бенчмарках, включая 92.8% точности на MATH-500, 55.5% проходной уровень на AIME 2024 и 1189 баллов на CodeForces, демонстрируя сильные математические и программные способности для модели объемом 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 объединяет отличительные черты предыдущих версий, улучшая общие и кодировочные способности."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 — это языковая модель смешанных экспертов (MoE) с 6710 миллиардами параметров, использующая многоголовое потенциальное внимание (MLA) и архитектуру DeepSeekMoE, в сочетании с стратегией балансировки нагрузки без вспомогательных потерь, оптимизирующей эффективность вывода и обучения. После предобучения на 14,8 триллионах высококачественных токенов и последующей супервизионной донастройки и обучения с подкреплением, DeepSeek-V3 превосходит другие открытые модели и приближается к ведущим закрытым моделям."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B — это передовая модель, обученная для высококомплексных диалогов."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "Современная эффективная LLM, специализирующаяся на рассуждениях, математике и программировании."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 — это модель визуального языка, разработанная на основе DeepSeekMoE-27B, использующая архитектуру MoE с разреженной активацией, которая демонстрирует выдающуюся производительность при активации всего 4,5 миллиарда параметров. Эта модель показывает отличные результаты в таких задачах, как визуальные вопросы и ответы, оптическое распознавание символов, понимание документов/таблиц/графиков и визуальная локализация."
+ },
"deepseek-chat": {
"description": "Новая открытая модель, объединяющая общие и кодовые возможности, не только сохраняет общие диалоговые способности оригинальной модели Chat и мощные возможности обработки кода модели Coder, но и лучше согласуется с человеческими предпочтениями. Кроме того, DeepSeek-V2.5 значительно улучшила производительность в таких задачах, как написание текстов и следование инструкциям."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B — это модель языкового кодирования, обученная на 20 триллионах данных, из которых 87% составляют код, а 13% — китайский и английский языки. Модель использует размер окна 16K и задачи заполнения пропусков, предоставляя функции автозаполнения кода и заполнения фрагментов на уровне проектов."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 — это открытая смешанная экспертная модель кода, показывающая отличные результаты в задачах кода, сопоставимая с GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 — это открытая смешанная экспертная модель кода, показывающая отличные результаты в задачах кода, сопоставимая с GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 — это модель вывода, управляемая методом обучения с подкреплением (RL), которая решает проблемы повторяемости и читаемости модели. Перед применением RL DeepSeek-R1 вводит данные холодного старта, что дополнительно оптимизирует производительность вывода. Она показывает сопоставимые результаты с OpenAI-o1 в математических, кодовых и задачах вывода, а также улучшает общую эффективность благодаря тщательно разработанным методам обучения."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 — более крупная и умная модель в наборе DeepSeek, была дистиллирована в архитектуру Llama 70B. На основе бенчмарков и ручной оценки эта модель более умная, особенно в задачах, требующих математической и фактической точности."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Модели серии DeepSeek-R1-Distill были получены с помощью технологии дистилляции знаний, донастраивая образцы, сгенерированные DeepSeek-R1, на открытых моделях, таких как Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Модели серии DeepSeek-R1-Distill были получены с помощью технологии дистилляции знаний, донастраивая образцы, сгенерированные DeepSeek-R1, на открытых моделях, таких как Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Модели серии DeepSeek-R1-Distill были получены с помощью технологии дистилляции знаний, донастраивая образцы, сгенерированные DeepSeek-R1, на открытых моделях, таких как Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Модели серии DeepSeek-R1-Distill были получены с помощью технологии дистилляции знаний, донастраивая образцы, сгенерированные DeepSeek-R1, на открытых моделях, таких как Qwen и Llama."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Модели серии DeepSeek-R1-Distill были получены с помощью технологии дистилляции знаний, донастраивая образцы, сгенерированные DeepSeek-R1, на открытых моделях, таких как Qwen и Llama."
+ },
+ "deepseek-reasoner": {
+ "description": "Модель вывода, представленная DeepSeek. Перед тем как выдать окончательный ответ, модель сначала выводит цепочку размышлений, чтобы повысить точность окончательного ответа."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 — это эффективная языковая модель Mixture-of-Experts, подходящая для экономически эффективных потребностей обработки."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B — это модель кода DeepSeek, обеспечивающая мощные возможности генерации кода."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 — это модель MoE, разработанная компанией Hangzhou DeepSeek AI Technology Research Co., Ltd., которая показывает выдающиеся результаты в нескольких тестах и занимает первое место среди открытых моделей в основных рейтингах. V3 по сравнению с моделью V2.5 увеличила скорость генерации в 3 раза, обеспечивая пользователям более быстрое и плавное использование."
+ },
"deepseek/deepseek-chat": {
"description": "Новая открытая модель, объединяющая общие и кодовые возможности, не только сохраняет общие диалоговые способности оригинальной модели Chat и мощные возможности обработки кода модели Coder, но и лучше соответствует человеческим предпочтениям. Кроме того, DeepSeek-V2.5 значительно улучшила свои результаты в задачах написания, следования инструкциям и других областях."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 значительно улучшила способности модели к рассуждению при наличии лишь очень ограниченных размеченных данных. Перед тем как предоставить окончательный ответ, модель сначала выводит цепочку размышлений, чтобы повысить точность окончательного ответа."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B — это крупная языковая модель на основе Llama3.3 70B, которая использует доработку, полученную от DeepSeek R1, для достижения конкурентоспособной производительности, сопоставимой с крупными передовыми моделями."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B — это дистиллированная большая языковая модель на основе Llama-3.1-8B-Instruct, обученная с использованием выходных данных DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B — это дистиллированная большая языковая модель на основе Qwen 2.5 14B, обученная с использованием выходных данных DeepSeek R1. Эта модель превзошла o1-mini от OpenAI в нескольких бенчмарках, достигнув последних достижений в области плотных моделей (state-of-the-art). Вот некоторые результаты бенчмарков:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nРейтинг CodeForces: 1481\nЭта модель, доработанная на основе выходных данных DeepSeek R1, демонстрирует конкурентоспособную производительность, сопоставимую с более крупными передовыми моделями."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B — это дистиллированная большая языковая модель на основе Qwen 2.5 32B, обученная с использованием выходных данных DeepSeek R1. Эта модель превзошла o1-mini от OpenAI в нескольких бенчмарках, достигнув последних достижений в области плотных моделей (state-of-the-art). Вот некоторые результаты бенчмарков:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nРейтинг CodeForces: 1691\nЭта модель, доработанная на основе выходных данных DeepSeek R1, демонстрирует конкурентоспособную производительность, сопоставимую с более крупными передовыми моделями."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 — это последняя версия открытой модели, выпущенной командой DeepSeek, обладающая выдающимися возможностями вывода, особенно в математических, программных и логических задачах, достигая уровня, сопоставимого с моделью o1 от OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 значительно улучшила способности модели к рассуждению при наличии лишь очень ограниченных размеченных данных. Перед тем как предоставить окончательный ответ, модель сначала выводит цепочку размышлений, чтобы повысить точность окончательного ответа."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 достиг значительного прорыва в скорости вывода по сравнению с предыдущими моделями. Она занимает первое место среди открытых моделей и может соперничать с самыми современными закрытыми моделями в мире. DeepSeek-V3 использует архитектуры многоголового потенциального внимания (MLA) и DeepSeekMoE, которые были полностью проверены в DeepSeek-V2. Кроме того, DeepSeek-V3 внедрила вспомогательную безубыточную стратегию для балансировки нагрузки и установила цели обучения для многомаркерного прогнозирования для достижения более высокой производительности."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 достиг значительного прорыва в скорости вывода по сравнению с предыдущими моделями. Она занимает первое место среди открытых моделей и может соперничать с самыми современными закрытыми моделями в мире. DeepSeek-V3 использует архитектуры многоголового потенциального внимания (MLA) и DeepSeekMoE, которые были полностью проверены в DeepSeek-V2. Кроме того, DeepSeek-V3 внедрила вспомогательную безубыточную стратегию для балансировки нагрузки и установила цели обучения для многомаркерного прогнозирования для достижения более высокой производительности."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite - совершенно новое поколение легкой модели, с максимальной скоростью отклика, результаты и задержка достигают мирового уровня."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k основан на полностью обновленной версии Doubao-1.5-Pro, с общим улучшением на 10%. Поддерживает вывод на 256k контекстных окнах, максимальная длина вывода составляет 12k токенов. Более высокая производительность, большее окно, отличное соотношение цена-качество, подходит для более широкого спектра приложений."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro - совершенно новое поколение основного модели, с полностью обновленной производительностью, выдающимися результатами в области знаний, кода, логики и других аспектов."
+ },
"emohaa": {
"description": "Emohaa — это психологическая модель, обладающая профессиональными консультационными способностями, помогающая пользователям понимать эмоциональные проблемы."
},
+ "ernie-3.5-128k": {
+ "description": "Флагманская большая языковая модель, разработанная Baidu, охватывающая огромные объемы китайских и английских текстов, обладающая мощными универсальными способностями, способная удовлетворить требования большинства сценариев диалогов, генерации контента и применения плагинов; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации."
+ },
+ "ernie-3.5-8k": {
+ "description": "Флагманская большая языковая модель, разработанная Baidu, охватывающая огромные объемы китайских и английских текстов, обладающая мощными универсальными способностями, способная удовлетворить требования большинства сценариев диалогов, генерации контента и применения плагинов; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Флагманская большая языковая модель, разработанная Baidu, охватывающая огромные объемы китайских и английских текстов, обладающая мощными универсальными способностями, способная удовлетворить требования большинства сценариев диалогов, генерации контента и применения плагинов; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Флагманская сверхбольшая языковая модель, разработанная Baidu, по сравнению с ERNIE 3.5 демонстрирует полное обновление возможностей модели, широко применима в сложных задачах различных областей; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Флагманская сверхбольшая языковая модель, разработанная Baidu, по сравнению с ERNIE 3.5 демонстрирует полное обновление возможностей модели, широко применима в сложных задачах различных областей; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Флагманская сверхбольшая языковая модель, разработанная Baidu, демонстрирует отличные результаты в комплексных задачах, широко применима в различных областях; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации. По сравнению с ERNIE 4.0, она показывает лучшие результаты."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Флагманская сверхбольшая языковая модель, разработанная Baidu, демонстрирует отличные результаты в комплексных задачах, широко применима в различных областях; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации. По сравнению с ERNIE 4.0, она показывает лучшие результаты."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Флагманская сверхбольшая языковая модель, разработанная Baidu, демонстрирует отличные результаты в комплексных задачах, широко применима в различных областях; поддерживает автоматическое подключение к плагину поиска Baidu, обеспечивая актуальность информации. По сравнению с ERNIE 4.0, она показывает лучшие результаты."
+ },
+ "ernie-char-8k": {
+ "description": "Специализированная большая языковая модель, разработанная Baidu, подходящая для применения в игровых NPC, диалогах службы поддержки, ролевых играх и других сценариях, с более ярким и последовательным стилем персонажей, более высокой способностью следовать инструкциям и лучшей производительностью вывода."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Специализированная большая языковая модель, разработанная Baidu, подходящая для применения в игровых NPC, диалогах службы поддержки, ролевых играх и других сценариях, с более ярким и последовательным стилем персонажей, более высокой способностью следовать инструкциям и лучшей производительностью вывода."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite — это легковесная большая языковая модель, разработанная Baidu, которая сочетает в себе отличные результаты модели и производительность вывода, подходит для использования на AI-ускорителях с низкой вычислительной мощностью."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Легковесная большая языковая модель, разработанная Baidu, которая сочетает в себе отличные результаты модели и производительность вывода, превосходя ERNIE Lite, подходит для использования на AI-ускорителях с низкой вычислительной мощностью."
+ },
+ "ernie-novel-8k": {
+ "description": "Универсальная большая языковая модель, разработанная Baidu, обладающая явными преимуществами в способности продолжать написание романов, также может использоваться в сценариях коротких пьес и фильмов."
+ },
+ "ernie-speed-128k": {
+ "description": "Новая высокопроизводительная большая языковая модель, разработанная Baidu в 2024 году, обладающая выдающимися универсальными способностями, подходит для использования в качестве базовой модели для тонкой настройки, лучше справляясь с проблемами конкретных сценариев, при этом обладая отличной производительностью вывода."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Новая высокопроизводительная большая языковая модель, разработанная Baidu в 2024 году, обладающая выдающимися универсальными способностями, превосходя ERNIE Speed, подходит для использования в качестве базовой модели для тонкой настройки, лучше справляясь с проблемами конкретных сценариев, при этом обладая отличной производительностью вывода."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny — это сверхвысокопроизводительная большая языковая модель, стоимость развертывания и тонкой настройки которой является самой низкой среди моделей серии Wenxin."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Тюнинг) предлагает стабильную и настраиваемую производительность, что делает её идеальным выбором для решения сложных задач."
},
@@ -329,14 +791,17 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro — это высокопроизводительная модель ИИ от Google, разработанная для масштабирования широкого спектра задач."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash — это последняя многомодальная модель ИИ от Google, обладающая высокой скоростью обработки и поддерживающая текстовые, графические и видеовходы, что делает её эффективной для масштабирования различных задач."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 — это эффективная многомодальная модель, поддерживающая масштабирование для широкого спектра приложений."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 — это эффективная мультимодальная модель, поддерживающая расширенные применения."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 разработан для обработки масштабных задач, обеспечивая непревзойдённую скорость обработки."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B — это высокоэффективная многомодальная модель, поддерживающая широкий спектр приложений."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 — это последняя экспериментальная модель, которая демонстрирует значительное улучшение производительности как в текстовых, так и в мультимодальных задачах."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002 — это последняя модель, готовая к производству, которая обеспечивает более высокое качество вывода, особенно в математических задачах, длинных контекстах и визуальных задачах."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 предлагает выдающиеся возможности многомодальной обработки, обеспечивая большую гибкость для разработки приложений."
+ "description": "Gemini 1.5 Pro 0801 предлагает выдающиеся многомодальные возможности обработки, обеспечивая большую гибкость в разработке приложений."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 сочетает в себе новейшие оптимизационные технологии, обеспечивая более эффективные возможности обработки многомодальных данных."
+ "description": "Gemini 1.5 Pro 0827 сочетает последние технологии оптимизации, обеспечивая более эффективную обработку многомодальных данных."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro поддерживает до 2 миллионов токенов и является идеальным выбором для средних многомодальных моделей, обеспечивая многостороннюю поддержку для сложных задач."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash предлагает функции следующего поколения и улучшения, включая выдающуюся скорость, использование встроенных инструментов, многомодальную генерацию и контекстное окно на 1M токенов."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash предлагает функции следующего поколения и улучшения, включая выдающуюся скорость, использование встроенных инструментов, многомодальную генерацию и контекстное окно на 1M токенов."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Модельный вариант Gemini 2.0 Flash, оптимизированный для достижения таких целей, как экономическая эффективность и низкая задержка."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Модельный вариант Gemini 2.0 Flash, оптимизированный для достижения таких целей, как экономическая эффективность и низкая задержка."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Модель Gemini 2.0 Flash, оптимизированная для экономической эффективности и низкой задержки."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp — это последняя экспериментальная многомодальная AI модель от Google, обладающая следующими поколениями характеристик, выдающейся скоростью, нативным вызовом инструментов и многомодальной генерацией."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp — это последняя экспериментальная многомодальная AI модель от Google, обладающая следующими поколениями характеристик, выдающейся скоростью, нативным вызовом инструментов и многомодальной генерацией."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental — это последняя экспериментальная многомодальная AI модель от Google, которая демонстрирует определенное улучшение качества по сравнению с предыдущими версиями, особенно в области мировых знаний, кода и длинного контекста."
+ },
"gemma-7b-it": {
"description": "Gemma 7B подходит для обработки задач среднего и малого масштаба, обеспечивая экономическую эффективность."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 — это высокоэффективная модель, выпущенная Google, охватывающая широкий спектр приложений от малых до сложных задач обработки данных."
},
- "general": {
- "description": "Spark Lite — это легковесная большая языковая модель с крайне низкой задержкой и высокой эффективностью обработки, полностью бесплатная и открытая, поддерживающая функцию онлайн-поиска в реальном времени. Ее быстрая реакция делает ее выдающимся выбором для применения в низкопроизводительных устройствах и тонкой настройке моделей, обеспечивая пользователям отличное соотношение цены и качества, особенно в задачах на знание, генерацию контента и поисковых сценариях."
- },
"generalv3": {
"description": "Spark Pro — это высокопроизводительная большая языковая модель, оптимизированная для профессиональных областей, таких как математика, программирование, медицина и образование, поддерживающая сетевой поиск и встроенные плагины для погоды, даты и т.д. Оптимизированная модель демонстрирует выдающиеся результаты и высокую эффективность в сложных задачах на знание, понимании языка и высокоуровневом создании текстов, что делает ее идеальным выбором для профессиональных приложений."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 — это последняя версия модели, специально разработанная для высоко сложных и разнообразных задач, демонстрирующая выдающиеся результаты."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat демонстрирует высокую производительность в семантике, математике, логическом мышлении, кодировании и знаниях. Также поддерживает веб-браузинг, выполнение кода, вызовы пользовательских инструментов и длинное текстовое рассуждение. Поддерживает 26 языков, включая японский, корейский и немецкий."
+ },
"glm-4-air": {
"description": "GLM-4-Air — это экономически эффективная версия, производительность которой близка к GLM-4, обеспечивая высокую скорость и доступную цену."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash — это идеальный выбор для обработки простых задач, с самой высокой скоростью и самой низкой ценой."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX — это улучшенная версия Flash с ультрабыстрой скоростью вывода."
+ },
"glm-4-long": {
"description": "GLM-4-Long поддерживает сверхдлинные текстовые вводы, подходит для задач, требующих памяти, и обработки больших документов."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V предлагает мощные способности понимания и вывода изображений, поддерживает множество визуальных задач."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash сосредоточен на эффективном понимании одного изображения, подходит для сценариев быстрого анализа изображений, таких как анализ изображений в реальном времени или пакетная обработка изображений."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus обладает способностью понимать видео-контент и множество изображений, подходит для мультимодальных задач."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 предлагает оптимизированные мультимодальные возможности обработки, подходящие для различных сложных задач."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview обладает мощными способностями к сложному выводу, демонстрируя отличные результаты в области логического вывода, математики и программирования."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash предлагает функции следующего поколения и улучшения, включая выдающуюся скорость, использование встроенных инструментов, многомодальную генерацию и контекстное окно на 1M токенов."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 сочетает в себе новейшие оптимизационные технологии, обеспечивая более эффективную обработку мультимодальных данных."
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental — это последняя экспериментальная многомодальная AI модель от Google, которая демонстрирует определенное улучшение качества по сравнению с предыдущими версиями, особенно в области мировых знаний, кода и длинного контекста."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash предлагает оптимизированные возможности многомодальной обработки, подходящие для различных сложных задач."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro сочетает в себе новейшие технологии оптимизации, обеспечивая более эффективную обработку многомодальных данных."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 — это эффективная модель, представленная Google, охватывающая широкий спектр приложений от небольших до сложных задач обработки данных."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 продолжает концепцию легковесного и эффективного дизайна."
},
+ "google/gemma-2-2b-it": {
+ "description": "Легковесная модель настройки инструкций от Google."
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 — это эффективная модель, представленная Google, охватывающая широкий спектр приложений от небольших до сложных задач обработки данных."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 — это легковесная серия текстовых моделей с открытым исходным кодом от Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo подходит для различных задач генерации и понимания текста, в настоящее время ссылается на gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo — это эффективная модель от OpenAI, предназначенная для задач чата и генерации текста, поддерживающая параллельные вызовы функций."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k — модель для генерации текста с высокой ёмкостью, подходящая для сложных задач."
+ },
"gpt-4": {
"description": "GPT-4 предлагает более широкий контекстный диапазон, способный обрабатывать более длинные текстовые вводы, подходя для сценариев, требующих обширной интеграции информации и анализа данных."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "Последняя модель GPT-4 Turbo обладает визуальными функциями. Теперь визуальные запросы могут использовать JSON-формат и вызовы функций. GPT-4 Turbo — это улучшенная версия, обеспечивающая экономически эффективную поддержку для мультимодальных задач. Она находит баланс между точностью и эффективностью, подходя для приложений, требующих взаимодействия в реальном времени."
},
- "gpt-4-1106-vision-preview": {
- "description": "Последняя модель GPT-4 Turbo обладает визуальными функциями. Теперь визуальные запросы могут использовать JSON-формат и вызовы функций. GPT-4 Turbo — это улучшенная версия, обеспечивающая экономически эффективную поддержку для мультимодальных задач. Она находит баланс между точностью и эффективностью, подходя для приложений, требующих взаимодействия в реальном времени."
- },
"gpt-4-32k": {
"description": "GPT-4 предлагает более широкий контекстный диапазон, способный обрабатывать более длинные текстовые вводы, подходя для сценариев, требующих обширной интеграции информации и анализа данных."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "Последняя модель GPT-4 Turbo обладает визуальными функциями. Теперь визуальные запросы могут использовать JSON-формат и вызовы функций. GPT-4 Turbo — это улучшенная версия, обеспечивающая экономически эффективную поддержку для мультимодальных задач. Она находит баланс между точностью и эффективностью, подходя для приложений, требующих взаимодействия в реальном времени."
},
+ "gpt-4.5-preview": {
+ "description": "Предварительная версия исследования GPT-4.5, это наша самая большая и мощная модель GPT на сегодняшний день. Она обладает обширными знаниями о мире и лучше понимает намерения пользователей, что делает её выдающейся в творческих задачах и автономном планировании. GPT-4.5 принимает текстовые и графические входные данные и генерирует текстовый вывод (включая структурированный вывод). Поддерживает ключевые функции для разработчиков, такие как вызовы функций, пакетный API и потоковый вывод. В задачах, требующих креативного, открытого мышления и диалога (таких как написание, обучение или исследование новых идей), GPT-4.5 особенно эффективен. Дата окончания знаний - октябрь 2023 года."
+ },
"gpt-4o": {
"description": "ChatGPT-4o — это динамическая модель, которая обновляется в реальном времени, чтобы оставаться актуальной. Она сочетает в себе мощное понимание языка и генерацию, подходя для масштабных приложений, включая обслуживание клиентов, образование и техническую поддержку."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o — это динамическая модель, которая обновляется в реальном времени, чтобы оставаться актуальной. Она сочетает в себе мощное понимание языка и генерацию, подходя для масштабных приложений, включая обслуживание клиентов, образование и техническую поддержку."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o — это динамическая модель, которая обновляется в реальном времени для поддержания актуальной версии. Она сочетает в себе мощное понимание языка и генерацию текста, подходя для широкого спектра приложений, включая обслуживание клиентов, образование и техническую поддержку."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Модель GPT-4o Audio, поддерживающая аудиовход и аудиовыход."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini — это последняя модель, выпущенная OpenAI после GPT-4 Omni, поддерживающая ввод изображений и текстов с выводом текста. Как их самый продвинутый компактный модель, она значительно дешевле других недавних передовых моделей и более чем на 60% дешевле GPT-3.5 Turbo. Она сохраняет передовой уровень интеллекта при значительном соотношении цена-качество. GPT-4o mini набрала 82% на тесте MMLU и в настоящее время занимает более высокое место в предпочтениях чата по сравнению с GPT-4."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Реальная версия GPT-4o-mini, поддерживающая аудио и текстовый ввод и вывод в реальном времени."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Реальная версия GPT-4o, поддерживающая аудио и текстовый ввод и вывод в реальном времени."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Реальная версия GPT-4o, поддерживающая аудио и текстовый ввод и вывод в реальном времени."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Реальная версия GPT-4o, поддерживающая аудио и текстовый ввод и вывод в реальном времени."
+ },
+ "grok-2-1212": {
+ "description": "Модель улучшена в точности, соблюдении инструкций и многоязычных возможностях."
+ },
+ "grok-2-vision-1212": {
+ "description": "Модель улучшена в точности, соблюдении инструкций и многоязычных возможностях."
+ },
+ "grok-beta": {
+ "description": "Обладает производительностью, сопоставимой с Grok 2, но с большей эффективностью, скоростью и функциональностью."
+ },
+ "grok-vision-beta": {
+ "description": "Новейшая модель понимания изображений, способная обрабатывать разнообразную визуальную информацию, включая документы, графики, скриншоты и фотографии."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B — это языковая модель, объединяющая креативность и интеллект, основанная на нескольких ведущих моделях."
},
+ "hunyuan-code": {
+ "description": "Последняя модель генерации кода Hunyuan, обученная на базе 200B высококачественных данных кода, прошедшая полгода обучения на высококачественных данных SFT, с увеличенной длиной контекстного окна до 8K, занимает ведущие позиции по автоматическим оценочным показателям генерации кода на пяти языках; по десяти критериям оценки кода на пяти языках, производительность находится в первой группе."
+ },
+ "hunyuan-functioncall": {
+ "description": "Последняя модель Hunyuan с архитектурой MOE FunctionCall, обученная на высококачественных данных FunctionCall, с контекстным окном до 32K, занимает лидирующие позиции по множеству оценочных показателей."
+ },
+ "hunyuan-large": {
+ "description": "Модель Hunyuan-large имеет общее количество параметров около 389B, активных параметров около 52B, что делает её самой крупной и эффективной открытой моделью MoE с архитектурой Transformer в отрасли."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Специализируется на обработке длинных текстовых задач, таких как резюме документов и вопросы и ответы по документам, а также обладает способностью обрабатывать общие задачи генерации текста. Отлично справляется с анализом и генерацией длинных текстов, эффективно справляясь с требованиями к обработке сложного и детального длинного контента."
+ },
+ "hunyuan-lite": {
+ "description": "Обновленная версия с MOE-структурой, контекстное окно составляет 256k, она опережает множество открытых моделей в оценках по NLP, коду, математике и другим областям."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Последняя многомодальная модель Hunyuan с 7B параметрами, окно контекста 32K, поддерживает многомодальный диалог на китайском и английском языках, распознавание объектов на изображениях, понимание документов и таблиц, многомодальную математику и т. д., по многим измерениям превосходит модели конкурентов с 7B параметрами."
+ },
+ "hunyuan-pro": {
+ "description": "Модель длинного текста с параметрами уровня триллиона MOE-32K. Она достигает абсолютного лидерства на различных бенчмарках, обладает сложными инструкциями и выводом, имеет сложные математические способности и поддерживает вызовы функций, с акцентом на оптимизацию в области многоязычного перевода, финансов, права и медицины."
+ },
+ "hunyuan-role": {
+ "description": "Последняя версия модели ролевого взаимодействия Hunyuan, выпущенная с официальной тонкой настройкой, основанная на модели Hunyuan и дополненная данными сценариев ролевого взаимодействия, демонстрирует лучшие базовые результаты в ролевых сценариях."
+ },
+ "hunyuan-standard": {
+ "description": "Использует более оптимальную стратегию маршрутизации, одновременно смягчая проблемы с балансировкой нагрузки и сходимостью экспертов. В области длинных текстов показатель «найти иголку в стоге сена» достигает 99,9%. MOE-32K предлагает более высокую стоимость-эффективность, обеспечивая баланс между качеством и ценой, а также возможность обработки длинных текстовых вводов."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Использует более оптимальную стратегию маршрутизации, одновременно смягчая проблемы с балансировкой нагрузки и сходимостью экспертов. В области длинных текстов показатель «найти иголку в стоге сена» достигает 99,9%. MOE-256K делает дальнейший прорыв в длине и качестве, значительно расширяя допустимую длину ввода."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Последняя многомодальная модель Hunyuan, поддерживающая многоязычные ответы, с сбалансированными способностями на китайском и английском языках."
+ },
+ "hunyuan-translation": {
+ "description": "Поддерживает взаимный перевод на 15 языков, включая китайский, английский, японский, французский, португальский, испанский, турецкий, русский, арабский, корейский, итальянский, немецкий, вьетнамский, малайский и индонезийский, с автоматической оценкой на основе набора тестов для многофункционального перевода COMET, в целом превосходя модели аналогичного масштаба на рынке по способности к взаимному переводу среди более чем десяти распространенных языков."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Модель перевода Хуньюань поддерживает перевод в формате естественного языкового диалога; поддерживает взаимный перевод на 15 языков, включая китайский, английский, японский, французский, португальский, испанский, турецкий, русский, арабский, корейский, итальянский, немецкий, вьетнамский, малайский и индонезийский."
+ },
+ "hunyuan-turbo": {
+ "description": "Предварительная версия нового поколения языковой модели Hunyuan, использующая совершенно новую структуру смешанной экспертной модели (MoE), которая обеспечивает более быструю эффективность вывода и более сильные результаты по сравнению с hunyuan-pro."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Фиксированная версия hunyuan-turbo от 20 ноября 2024 года, промежуточная между hunyuan-turbo и hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Оптимизация этой версии: масштабирование данных и инструкций, значительное повышение общей обобщающей способности модели; значительное улучшение математических, кодовых и логических способностей; оптимизация понимания текста и связанных с ним способностей понимания слов; оптимизация качества генерации контента при создании текста."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Оптимизация общего опыта, включая понимание NLP, создание текста, общение, вопросы и ответы на знания, перевод, области и т. д.; повышение человечности, оптимизация эмоционального интеллекта модели; улучшение способности модели активно прояснять неясные намерения; повышение способности обработки вопросов, связанных с анализом слов; улучшение качества и интерактивности творчества; улучшение многократного взаимодействия."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Флагманская модель нового поколения Hunyuan в области визуального языка, использующая совершенно новую структуру смешанной экспертной модели (MoE), с полным улучшением способностей в области базового распознавания, создания контента, вопросов и ответов на знания, анализа и вывода по сравнению с предыдущей моделью."
+ },
+ "hunyuan-vision": {
+ "description": "Последняя многомодальная модель Hunyuan, поддерживающая ввод изображений и текста для генерации текстового контента."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Инновационная открытая модель InternLM2.5, благодаря большому количеству параметров, повышает интеллектуальность диалогов."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 предлагает интеллектуальные решения для диалогов в различных сценариях."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Модель Llama 3.1 70B для команд, обладающая 70B параметрами, обеспечивает выдающуюся производительность в задачах генерации текста и выполнения команд."
+ "internlm2-pro-chat": {
+ "description": "Старая версия модели, которую мы все еще поддерживаем, доступная с параметрами 7B и 20B."
+ },
+ "internlm2.5-latest": {
+ "description": "Наша последняя серия моделей с выдающимися показателями вывода, поддерживающая длину контекста до 1M и обладающая улучшенными возможностями следования инструкциям и вызова инструментов."
+ },
+ "internlm3-latest": {
+ "description": "Наша последняя серия моделей с выдающейся производительностью вывода, лидирующая среди моделей открытого кода того же уровня. По умолчанию указывает на нашу последнюю выпущенную серию моделей InternLM3."
+ },
+ "jina-deepsearch-v1": {
+ "description": "Глубокий поиск сочетает в себе сетевой поиск, чтение и рассуждение, позволяя проводить всесторонние исследования. Вы можете рассматривать его как агента, который принимает ваши исследовательские задачи — он проводит обширный поиск и проходит через множество итераций, прежде чем предоставить ответ. Этот процесс включает в себя постоянные исследования, рассуждения и решение проблем с разных точек зрения. Это принципиально отличается от стандартных больших моделей, которые генерируют ответы непосредственно из предобученных данных, и от традиционных систем RAG, полагающихся на одноразовый поверхностный поиск."
+ },
+ "kimi-latest": {
+ "description": "Продукт Kimi Smart Assistant использует последнюю модель Kimi, которая может содержать нестабильные функции. Поддерживает понимание изображений и автоматически выбирает модель 8k/32k/128k в качестве модели для выставления счетов в зависимости от длины контекста запроса."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM — это экспериментальная языковая модель, ориентированная на конкретные задачи, обученная в соответствии с принципами науки о обучении, которая может следовать системным инструкциям в учебных и образовательных сценариях, выступая в роли эксперта-наставника и т.д."
+ },
+ "lite": {
+ "description": "Spark Lite — это легковесная большая языковая модель с крайне низкой задержкой и высокой эффективностью обработки, полностью бесплатная и открытая, поддерживающая функции онлайн-поиска в реальном времени. Ее быстрая реакция делает ее отличным выбором для применения в устройствах с низкой вычислительной мощностью и для тонкой настройки моделей, обеспечивая пользователям отличное соотношение цены и качества, особенно в сценариях вопросов и ответов, генерации контента и поиска."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B предлагает более мощные возможности ИИ вывода, подходит для сложных приложений, поддерживает огромное количество вычислительных процессов и гарантирует эффективность и точность."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B — это высокоэффективная модель, обеспечивающая быструю генерацию текста, идеально подходящая для приложений, требующих масштабной эффективности и экономичности."
},
- "llama-3.1-8b-instruct": {
- "description": "Модель Llama 3.1 8B для команд, обладающая 8B параметрами, обеспечивает эффективное выполнение задач с указаниями и предлагает высококачественные возможности генерации текста."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Отличные способности к визуальному пониманию изображений на высоком разрешении, предназначенные для приложений визуального понимания."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Модель Llama 3.1 Sonar Huge Online, обладающая 405B параметрами, поддерживает контекст длиной около 127,000 токенов, предназначена для сложных онлайн-чат-приложений."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 предназначена для обработки задач, сочетающих визуальные и текстовые данные. Она демонстрирует отличные результаты в задачах описания изображений и визуального вопросно-ответного взаимодействия, преодолевая разрыв между генерацией языка и визуальным выводом."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Модель Llama 3.1 Sonar Large Chat, обладающая 70B параметрами, поддерживает контекст длиной около 127,000 токенов, подходит для сложных оффлайн-чатов."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Совершенные возможности визуального понимания для приложения-агента."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Модель Llama 3.1 Sonar Large Online, обладающая 70B параметрами, поддерживает контекст длиной около 127,000 токенов, подходит для задач с высокой нагрузкой и разнообразными чатами."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 предназначена для обработки задач, сочетающих визуальные и текстовые данные. Она демонстрирует отличные результаты в задачах описания изображений и визуального вопросно-ответного взаимодействия, преодолевая разрыв между генерацией языка и визуальным выводом."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Модель Llama 3.1 Sonar Small Chat, обладающая 8B параметрами, специально разработана для оффлайн-чатов и поддерживает контекст длиной около 127,000 токенов."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 — это самая современная многоязычная открытая языковая модель из серии Llama, которая позволяет получить производительность, сопоставимую с 405B моделями, по очень низкой цене. Основана на структуре Transformer и улучшена с помощью контролируемой донастройки (SFT) и обучения с подкреплением на основе человеческой обратной связи (RLHF) для повышения полезности и безопасности. Ее версия с оптимизацией под инструкции специально разработана для многоязычных диалогов и показывает лучшие результаты по сравнению с множеством открытых и закрытых моделей чата на различных отраслевых бенчмарках. Дата окончания знаний — декабрь 2023 года."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Модель Llama 3.1 Sonar Small Online, обладающая 8B параметрами, поддерживает контекст длиной около 127,000 токенов, специально разработана для онлайн-чатов и эффективно обрабатывает различные текстовые взаимодействия."
+ "llama-3.3-70b-versatile": {
+ "description": "Многоязычная большая языковая модель Meta Llama 3.3 (LLM) — это предобученная и откорректированная модель генерации на 70B (текстовый ввод/текстовый вывод). Откорректированная на чистом тексте модель Llama 3.3 оптимизирована для многоязычных диалоговых задач и превосходит многие доступные открытые и закрытые модели чата по общим промышленным стандартам."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B предлагает непревзойдённые возможности обработки сложности, специально разработанные для высоких требований проектов."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral специально разработан для научных исследований и математического вывода, обеспечивая эффективные вычислительные возможности и интерпретацию результатов."
},
+ "max-32k": {
+ "description": "Spark Max 32K обладает большой способностью обработки контекста, улучшенным пониманием контекста и логическим выводом, поддерживает текстовый ввод до 32K токенов, подходит для чтения длинных документов, частных вопросов и ответов и других сценариев."
+ },
"meta-llama-3-70b-instruct": {
"description": "Мощная модель с 70 миллиардами параметров, превосходящая в области рассуждений, кодирования и широких языковых приложений."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) предлагает отличные возможности обработки языка и выдающийся опыт взаимодействия."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 предлагает превосходные способности обработки языка и выдающийся пользовательский опыт."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) — мощная модель для чата, поддерживающая сложные диалоговые запросы."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) предлагает многоязычную поддержку и охватывает широкий спектр областей знаний."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 предназначена для выполнения задач, объединяющих визуальные и текстовые данные. Она отлично справляется с задачами по описанию изображений и визуальному вопросу-ответу, преодолевая разрыв между генерацией языка и визуальным пониманием."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 предназначена для выполнения задач, объединяющих визуальные и текстовые данные. Она отлично справляется с задачами по описанию изображений и визуальному вопросу-ответу, преодолевая разрыв между генерацией языка и визуальным пониманием."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 предназначена для выполнения задач, объединяющих визуальные и текстовые данные. Она отлично справляется с задачами по описанию изображений и визуальному вопросу-ответу, преодолевая разрыв между генерацией языка и визуальным пониманием."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 — это самая современная многоязычная открытая языковая модель серии Llama, позволяющая получить производительность, сопоставимую с 405B моделью, по очень низкой цене. Основана на структуре Transformer и улучшена с помощью контролируемой донастройки (SFT) и обучения с подкреплением на основе человеческой обратной связи (RLHF) для повышения полезности и безопасности. Ее версия с оптимизацией под инструкции специально разработана для многоязычного диалога и показывает лучшие результаты по сравнению с многими открытыми и закрытыми чат-моделями на нескольких отраслевых бенчмарках. Дата окончания знаний — декабрь 2023 года."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Многоязычная большая языковая модель Meta Llama 3.3 (LLM) — это предобученная и настроенная на инструкции генеративная модель объемом 70B (входной/выходной текст). Модель Llama 3.3, настроенная на инструкции, оптимизирована для многоязычных диалоговых случаев и превосходит многие доступные открытые и закрытые модели чата по общим отраслевым бенчмаркам."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 предназначена для выполнения задач, объединяющих визуальные и текстовые данные. Она отлично справляется с задачами по описанию изображений и визуальному вопросу-ответу, преодолевая разрыв между генерацией языка и визуальным пониманием."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite подходит для сред, требующих высокой производительности и низкой задержки."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "Модель Llama 3.1 Turbo 405B предлагает огромную поддержку контекста для обработки больших данных и демонстрирует выдающиеся результаты в масштабных приложениях искусственного интеллекта."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 — это передовая модель, представленная Meta, поддерживающая до 405B параметров, применимая в сложных диалогах, многоязычном переводе и анализе данных."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B предлагает эффективную поддержку диалогов на нескольких языках."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct оптимизирован для высококачественных диалоговых сцен, его производительность превосходит многие закрытые модели."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct — это последняя версия от Meta, оптимизированная для генерации высококачественных диалогов, превосходящая многие ведущие закрытые модели."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct разработан для высококачественных диалогов и показывает выдающиеся результаты в оценках, особенно в высокоинтерактивных сценах."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 предлагает поддержку нескольких языков и является одной из ведущих генеративных моделей в отрасли."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 предназначена для обработки задач, сочетающих визуальные и текстовые данные. Она демонстрирует отличные результаты в задачах описания изображений и визуального вопросно-ответного взаимодействия, преодолевая разрыв между генерацией языка и визуальным выводом."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 предназначена для обработки задач, сочетающих визуальные и текстовые данные. Она демонстрирует отличные результаты в задачах описания изображений и визуального вопросно-ответного взаимодействия, преодолевая разрыв между генерацией языка и визуальным выводом."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 — это самая современная многоязычная открытая языковая модель из серии Llama, которая позволяет получить производительность, сопоставимую с 405B моделями, по очень низкой цене. Основана на структуре Transformer и улучшена с помощью контролируемой донастройки (SFT) и обучения с подкреплением на основе человеческой обратной связи (RLHF) для повышения полезности и безопасности. Ее версия с оптимизацией под инструкции специально разработана для многоязычных диалогов и показывает лучшие результаты по сравнению с множеством открытых и закрытых моделей чата на различных отраслевых бенчмарках. Дата окончания знаний — декабрь 2023 года."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 — это самая современная многоязычная открытая языковая модель из серии Llama, которая позволяет получить производительность, сопоставимую с 405B моделями, по очень низкой цене. Основана на структуре Transformer и улучшена с помощью контролируемой донастройки (SFT) и обучения с подкреплением на основе человеческой обратной связи (RLHF) для повышения полезности и безопасности. Ее версия с оптимизацией под инструкции специально разработана для многоязычных диалогов и показывает лучшие результаты по сравнению с множеством открытых и закрытых моделей чата на различных отраслевых бенчмарках. Дата окончания знаний — декабрь 2023 года."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct — это самая большая и мощная модель в линейке Llama 3.1 Instruct, представляющая собой высокоразвёрнутую модель для диалогового вывода и генерации синтетических данных, также может использоваться в качестве основы для специализированного предобучения или дообучения в определённых областях. Многоязычные большие языковые модели (LLMs), предлагаемые Llama 3.1, представляют собой набор предобученных генеративных моделей с настройкой на инструкции, включая размеры 8B, 70B и 405B (вход/выход текста). Модели текста с настройкой на инструкции Llama 3.1 (8B, 70B, 405B) оптимизированы для многоязычных диалоговых случаев и превосходят многие доступные открытые модели чата в общепринятых отраслевых бенчмарках. Llama 3.1 предназначена для коммерческого и исследовательского использования на нескольких языках. Модели текста с настройкой на инструкции подходят для диалогов, похожих на помощников, в то время как предобученные модели могут адаптироваться к различным задачам генерации естественного языка. Модели Llama 3.1 также поддерживают использование их вывода для улучшения других моделей, включая генерацию синтетических данных и уточнение. Llama 3.1 является саморегрессионной языковой моделью, использующей оптимизированную архитектуру трансформеров. Настроенные версии используют контролируемое дообучение (SFT) и обучение с подкреплением с человеческой обратной связью (RLHF), чтобы соответствовать предпочтениям людей в отношении полезности и безопасности."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 — это открытая большая языковая модель (LLM), ориентированная на разработчиков, исследователей и предприятия, предназначенная для помощи в создании, экспериментировании и ответственном масштабировании их идей по генеративному ИИ. В качестве части базовой системы для инноваций глобального сообщества она идеально подходит для устройств с ограниченными вычислительными мощностями и ресурсами, а также для более быстрого времени обучения."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B — это новая быстрая и легкая модель от Microsoft AI, производительность которой близка к 10-кратной производительности существующих открытых моделей."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "Современная LLM, поддерживающая генерацию синтетических данных, дистилляцию знаний и рассуждения, подходит для чат-ботов, программирования и специализированных задач."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Обеспечивает сложные диалоги, обладая выдающимся пониманием контекста, способностями к рассуждению и генерации текста."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Современная передовая модель, обладающая пониманием языка, выдающимися способностями к рассуждению и генерации текста."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Современная визуально-языковая модель, специализирующаяся на высококачественном рассуждении на основе изображений."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Современная передовая компактная языковая модель, обладающая пониманием языка, выдающимися способностями к рассуждению и генерации текста."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Современная передовая компактная языковая модель, обладающая пониманием языка, выдающимися способностями к рассуждению и генерации текста."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Современная визуально-языковая модель, специализирующаяся на высококачественном рассуждении на основе изображений."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Современная LLM, специализирующаяся на рассуждениях, математике, здравом смысле и вызовах функций."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 — это языковая модель от Microsoft AI, которая особенно хорошо справляется с сложными диалогами, многоязычностью, выводами и интеллектуальными помощниками."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B — это передовая модель Wizard от Microsoft, демонстрирующая исключительно конкурентоспособные результаты."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V — это новое поколение мультимодальной большой модели от OpenBMB, обладающее выдающимися возможностями OCR и мультимодального понимания, поддерживающее широкий спектр приложений."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B - это выдающаяся модель от Mistral."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B - это экономически эффективная модель от Mistral."
+ },
"mistral": {
"description": "Mistral — это 7B модель, выпущенная Mistral AI, подходящая для разнообразных языковых задач."
},
"mistral-large": {
"description": "Mixtral Large — это флагманская модель от Mistral, объединяющая возможности генерации кода, математики и вывода, поддерживающая контекстное окно 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) — это продвинутая модель языка (LLM) с современными способностями рассуждения, знаний и кодирования."
- },
"mistral-large-latest": {
"description": "Mistral Large — это флагманская большая модель, хорошо подходящая для многоязычных задач, сложного вывода и генерации кода, идеальный выбор для высококлассных приложений."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 обеспечивает эффективные вычислительные возможности и понимание естественного языка, подходящие для широкого спектра приложений."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B - это компактная, но высокопроизводительная модель, хорошо подходящая для пакетной обработки и простых задач, таких как классификация и генерация текста, с хорошими способностями к рассуждению."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) — это супер большая языковая модель, поддерживающая крайне высокие требования к обработке."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B — это предобученная модель разреженных смешанных экспертов, предназначенная для универсальных текстовых задач."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B - это разреженная модель эксперта, использующая множество параметров для повышения скорости вывода, подходит для обработки многоязычных и генеративных задач."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct — это высокопроизводительная модель стандартов отрасли, оптимизированная для скорости и поддержки длинного контекста."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K — это модель с возможностями обработки сверхдлинного контекста, подходящая для генерации очень длинных текстов, удовлетворяющая требованиям сложных задач генерации, способная обрабатывать до 128 000 токенов, идеально подходящая для научных исследований, академических и крупных документальных приложений."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Модель визуализации Kimi (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview и др.) может понимать содержимое изображений, включая текст на изображениях, цвета изображений и формы объектов."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K предлагает возможности обработки контекста средней длины, способная обрабатывать 32 768 токенов, особенно подходит для генерации различных длинных документов и сложных диалогов, применяется в создании контента, генерации отчетов и диалоговых систем."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Модель визуализации Kimi (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview и др.) может понимать содержимое изображений, включая текст на изображениях, цвета изображений и формы объектов."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K специально разработан для генерации коротких текстов, обладая высокой производительностью обработки, способный обрабатывать 8 192 токена, идеально подходит для кратких диалогов, стенографирования и быстрой генерации контента."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Модель визуализации Kimi (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview и др.) может понимать содержимое изображений, включая текст на изображениях, цвета изображений и формы объектов."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto может выбирать подходящую модель в зависимости от количества токенов, используемых в текущем контексте."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B — это обновленная версия Nous Hermes 2, содержащая последние внутренние разработанные наборы данных."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B — это крупная языковая модель, созданная NVIDIA, предназначенная для повышения полезности ответов, генерируемых LLM, на запросы пользователей. Эта модель показала отличные результаты в таких бенчмарках, как Arena Hard, AlpacaEval 2 LC и GPT-4-Turbo MT-Bench, и на 1 октября 2024 года занимает первое место во всех трех автоматических тестах на согласование. Модель обучалась с использованием RLHF (в частности, REINFORCE), Llama-3.1-Nemotron-70B-Reward и HelpSteer2-Preference на основе модели Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Уникальная языковая модель, обеспечивающая непревзойденную точность и эффективность."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B — это крупная языковая модель, разработанная NVIDIA, предназначенная для повышения полезности ответов, генерируемых LLM."
+ },
+ "o1": {
+ "description": "Сосредоточена на высокоуровневом выводе и решении сложных задач, включая математические и научные задачи. Идеально подходит для приложений, требующих глубокого понимания контекста и управления рабочими процессами."
+ },
"o1-mini": {
"description": "o1-mini — это быстрое и экономичное модель вывода, разработанная для программирования, математики и научных приложений. Модель имеет контекст 128K и срок знания до октября 2023 года."
},
"o1-preview": {
"description": "o1 — это новая модель вывода от OpenAI, подходящая для сложных задач, требующих обширных общих знаний. Модель имеет контекст 128K и срок знания до октября 2023 года."
},
+ "o3-mini": {
+ "description": "o3-mini — это наша последняя компактная модель вывода, обеспечивающая высокий уровень интеллекта при тех же затратах и задержках, что и o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba — это языковая модель Mamba 2, сосредоточенная на генерации кода, обеспечивающая мощную поддержку для сложных задач по коду и выводу."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B — это разреженная экспертная модель, использующая несколько параметров для повышения скорости вывода, подходит для обработки многоязычных и кодовых задач."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o — это динамическая модель, которая обновляется в реальном времени, чтобы оставаться актуальной. Она сочетает в себе мощные возможности понимания и генерации языка, подходящие для масштабных приложений, включая обслуживание клиентов, образование и техническую поддержку."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o — это динамическая модель, которая обновляется в реальном времени, чтобы оставаться актуальной. Она сочетает в себе мощные способности понимания и генерации языка, подходит для масштабных приложений, включая обслуживание клиентов, образование и техническую поддержку."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini — это последняя модель от OpenAI, выпущенная после GPT-4 Omni, поддерживающая ввод изображений и текста с выводом текста. Как их самый продвинутый компактный модель, она значительно дешевле других недавних передовых моделей и более чем на 60% дешевле GPT-3.5 Turbo. Она сохраняет передовой уровень интеллекта при значительном соотношении цена-качество. GPT-4o mini набрала 82% в тесте MMLU и в настоящее время занимает более высокое место по предпочтениям в чате, чем GPT-4."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Модель Pixtral демонстрирует мощные способности в задачах графиков и понимания изображений, вопросов и ответов по документам, многомодального вывода и соблюдения инструкций, способная обрабатывать изображения в естественном разрешении и соотношении сторон, а также обрабатывать произвольное количество изображений в контекстном окне длиной до 128K токенов."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large — это открытая многомодальная модель с 1240 миллиардами параметров, основанная на Mistral Large 2. Это вторая модель в нашей многомодальной семье, демонстрирующая передовые уровни понимания изображений."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K оснащен огромной способностью обработки контекста, способной обрабатывать до 128K контекстной информации, что делает его особенно подходящим для анализа длинных текстов и обработки долгосрочных логических связей, обеспечивая плавную и последовательную логику и разнообразную поддержку ссылок в сложных текстовых коммуникациях."
+ },
+ "qvq-72b-preview": {
+ "description": "Модель QVQ, разработанная командой Qwen, является экспериментальной исследовательской моделью, сосредоточенной на повышении визуальных способностей рассуждения, особенно в области математического рассуждения."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Модель кода Tongyi Qianwen."
+ },
"qwen-coder-turbo-latest": {
"description": "Модель кода Tongyi Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Математическая модель Tongyi Qwen, специально разработанная для решения математических задач."
},
+ "qwen-max": {
+ "description": "Qwen-Max — это языковая модель масштаба триллиона, поддерживающая входные данные на различных языках, включая китайский и английский. В настоящее время это API, которое стоит за продуктовой версией Qwen 2.5."
+ },
"qwen-max-latest": {
"description": "Модель языка Tongyi Qwen с уровнем масштабирования в триллионы, поддерживающая ввод на различных языках, включая китайский и английский, является API моделью, лежащей в основе продукта Tongyi Qwen 2.5."
},
+ "qwen-omni-turbo-latest": {
+ "description": "Модели серии Qwen-Omni поддерживают ввод данных в различных модальностях, включая видео, аудио, изображения и текст, и могут выводить аудио и текст."
+ },
+ "qwen-plus": {
+ "description": "Улучшенная версия Qwen-Turbo, поддерживающая входные данные на разных языках, включая китайский и английский."
+ },
"qwen-plus-latest": {
"description": "Улучшенная версия модели языка Tongyi Qwen, поддерживающая ввод на различных языках, включая китайский и английский."
},
+ "qwen-turbo": {
+ "description": "Qwen-Turbo — это крупная языковая модель, поддерживающая входные данные на разных языках, включая китайский и английский."
+ },
"qwen-turbo-latest": {
"description": "Модель языка Tongyi Qwen, поддерживающая ввод на различных языках, включая китайский и английский."
},
"qwen-vl-chat-v1": {
"description": "Qwen VL поддерживает гибкие способы взаимодействия, включая многократные изображения, многократные вопросы и ответы, а также творческие способности."
},
- "qwen-vl-max": {
- "description": "Qwen — это сверхмасштабная визуально-языковая модель. По сравнению с улучшенной версией, еще больше улучшены способности визуального вывода и соблюдения инструкций, обеспечивая более высокий уровень визуального восприятия и понимания."
+ "qwen-vl-max-latest": {
+ "description": "Супер масштабная визуально-языковая модель Tongyi Qianwen. По сравнению с улучшенной версией, еще больше повышает способности визуального вывода и соблюдения инструкций, обеспечивая более высокий уровень визуального восприятия и когнитивных способностей."
},
- "qwen-vl-plus": {
- "description": "Qwen — это улучшенная версия крупномасштабной визуально-языковой модели. Существенно улучшена способность распознавания деталей и текстов, поддерживает изображения с разрешением более миллиона пикселей и произвольным соотношением сторон."
+ "qwen-vl-ocr-latest": {
+ "description": "OCR Qwen — это специализированная модель для извлечения текста, сосредоточенная на способности извлекать текст из изображений различных типов, таких как документы, таблицы, тесты и рукописный текст. Она может распознавать множество языков, включая: китайский, английский, французский, японский, корейский, немецкий, русский, итальянский, вьетнамский и арабский."
+ },
+ "qwen-vl-plus-latest": {
+ "description": "Улучшенная версия масштабной визуально-языковой модели Tongyi Qianwen. Значительно повышает способность распознавания деталей и текста, поддерживает разрешение более миллиона пикселей и изображения с произвольным соотношением сторон."
},
"qwen-vl-v1": {
"description": "Инициализированная языковой моделью Qwen-7B, добавлена модель изображения, предобученная модель с разрешением входного изображения 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 — это новая серия больших языковых моделей Qwen. Qwen2 7B — это модель на основе трансформера, которая демонстрирует отличные результаты в понимании языка, многоязычных способностях, программировании, математике и логическом рассуждении."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 — это новая серия крупных языковых моделей с более сильными возможностями понимания и генерации."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL — это последняя итерация модели Qwen-VL, достигшая передовых результатов в бенчмарках визуального понимания, включая MathVista, DocVQA, RealWorldQA и MTVQA. Qwen2-VL может понимать видео продолжительностью более 20 минут для высококачественного видеозапроса, диалога и создания контента. Она также обладает сложными способностями к рассуждению и принятию решений, может интегрироваться с мобильными устройствами, роботами и выполнять автоматические операции на основе визуальной среды и текстовых инструкций. Кроме английского и китайского, Qwen2-VL теперь также поддерживает понимание текста на разных языках в изображениях, включая большинство европейских языков, японский, корейский, арабский и вьетнамский."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct — это одна из последних серий больших языковых моделей, выпущенных Alibaba Cloud. Эта модель 72B демонстрирует значительные улучшения в области кодирования и математики. Модель также поддерживает множество языков, охватывающих более 29 языков, включая китайский и английский. Она значительно улучшила выполнение инструкций, понимание структурированных данных и генерацию структурированных выходных данных (особенно JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct — это одна из последних серий больших языковых моделей, выпущенных Alibaba Cloud. Эта модель 32B демонстрирует значительные улучшения в области кодирования и математики. Модель поддерживает множество языков, охватывающих более 29 языков, включая китайский и английский. Она значительно улучшила выполнение инструкций, понимание структурированных данных и генерацию структурированных выходных данных (особенно JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM, ориентированная на китайский и английский языки, охватывающая области языка, программирования, математики, рассуждений и др."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "Современная LLM, поддерживающая генерацию кода, рассуждения и исправления, охватывающая основные языки программирования."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Мощная средняя модель кода, поддерживающая контекст длиной 32K, специализирующаяся на многоязычном программировании."
+ },
"qwen2": {
"description": "Qwen2 — это новое поколение крупномасштабной языковой модели от Alibaba, обеспечивающее отличные результаты для разнообразных приложений."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 — это новое поколение масштабной языковой модели от Alibaba, обеспечивающее отличные результаты для разнообразных потребностей приложений."
+ },
"qwen2.5-14b-instruct": {
"description": "Модель Tongyi Qwen 2.5 с открытым исходным кодом объемом 14B."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Модель Qwen2.5 с открытым исходным кодом объемом 72B."
+ },
"qwen2.5-32b-instruct": {
"description": "Модель Tongyi Qwen 2.5 с открытым исходным кодом объемом 32B."
},
@@ -824,13 +1599,16 @@
"description": "Модель Tongyi Qwen 2.5 с открытым исходным кодом объемом 7B."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "Открытая версия модели кода Tongyi Qwen."
+ "description": "Открытая версия модели кода Qwen."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Открытая версия модели кода Tongyi Qianwen."
},
"qwen2.5-coder-7b-instruct": {
"description": "Открытая версия модели кода Tongyi Qwen."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Модель Qwen-Math с мощными способностями решения математических задач."
+ "description": "Модель Qwen-Math обладает выдающимися способностями к решению математических задач."
},
"qwen2.5-math-72b-instruct": {
"description": "Модель Qwen-Math с мощными способностями решения математических задач."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Модель Qwen-Math с мощными способностями решения математических задач."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Улучшение следования инструкциям, математики, решения задач и кода, улучшение способности распознавания объектов, поддержка точного позиционирования визуальных элементов в различных форматах, поддержка понимания длинных видеофайлов (максимум 10 минут) и локализация событий на уровне секунд, способность понимать последовательность времени и скорость, поддержка управления агентами ОС или мобильными устройствами на основе аналитических и позиционных возможностей, высокая способность извлечения ключевой информации и вывода в формате Json. Эта версия является 72B, самой мощной в серии."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Улучшение следования инструкциям, математики, решения задач и кода, улучшение способности распознавания объектов, поддержка точного позиционирования визуальных элементов в различных форматах, поддержка понимания длинных видеофайлов (максимум 10 минут) и локализация событий на уровне секунд, способность понимать последовательность времени и скорость, поддержка управления агентами ОС или мобильными устройствами на основе аналитических и позиционных возможностей, высокая способность извлечения ключевой информации и вывода в формате Json. Эта версия является 72B, самой мощной в серии."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 — это новое поколение масштабной языковой модели от Alibaba, обеспечивающее отличные результаты для разнообразных потребностей приложений."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 — это новое поколение масштабной языковой модели от Alibaba, обеспечивающее отличные результаты для разнообразных потребностей приложений."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 — это новое поколение масштабной языковой модели от Alibaba, обеспечивающее отличные результаты для разнообразных потребностей приложений."
+ },
"qwen2:0.5b": {
"description": "Qwen2 — это новое поколение крупномасштабной языковой модели от Alibaba, обеспечивающее отличные результаты для разнообразных приложений."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 — это новое поколение крупномасштабной языковой модели от Alibaba, обеспечивающее отличные результаты для разнообразных приложений."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini — это компактная LLM, производительность которой превосходит GPT-3.5, обладая мощными многоязычными возможностями, поддерживает английский и корейский языки, предлагая эффективное и компактное решение."
+ "qwq": {
+ "description": "QwQ — это экспериментальная исследовательская модель, сосредоточенная на повышении возможностей вывода ИИ."
+ },
+ "qwq-32b": {
+ "description": "Модель вывода QwQ, обученная на модели Qwen2.5-32B, значительно улучшила свои способности вывода благодаря обучению с подкреплением. Основные показатели модели, такие как математический код и другие ключевые метрики (AIME 24/25, LiveCodeBench), а также некоторые общие показатели (IFEval, LiveBench и др.) достигли уровня DeepSeek-R1 в полной мере, при этом все показатели значительно превышают аналогичные показатели DeepSeek-R1-Distill-Qwen-32B, также основанной на Qwen2.5-32B."
+ },
+ "qwq-32b-preview": {
+ "description": "Модель QwQ — это экспериментальная исследовательская модель, разработанная командой Qwen, сосредоточенная на улучшении возможностей вывода ИИ."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) расширяет возможности Solar Mini, сосредоточиваясь на японском языке, при этом сохраняя высокую эффективность и выдающуюся производительность в использовании английского и корейского языков."
+ "qwq-plus-latest": {
+ "description": "Модель вывода QwQ, обученная на модели Qwen2.5, значительно улучшила свои способности вывода благодаря обучению с подкреплением. Основные показатели модели, такие как математический код и другие ключевые метрики (AIME 24/25, LiveCodeBench), а также некоторые общие показатели (IFEval, LiveBench и др.) достигли уровня DeepSeek-R1 в полной мере."
+ },
+ "r1-1776": {
+ "description": "R1-1776 — это версия модели DeepSeek R1, прошедшая дообучение, которая предоставляет непроверенную, беспристрастную фактическую информацию."
+ },
+ "solar-mini": {
+ "description": "Solar Mini — это компактная LLM, которая превосходит GPT-3.5, обладает мощными многоязычными возможностями, поддерживает английский и корейский языки, предлагая эффективное и компактное решение."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) расширяет возможности Solar Mini, сосредотачиваясь на японском языке, при этом поддерживая высокую эффективность и выдающиеся результаты в использовании английского и корейского языков."
},
"solar-pro": {
"description": "Solar Pro — это высокоинтеллектуальная LLM, выпущенная Upstage, сосредоточенная на способности следовать инструкциям на одном GPU, с оценкой IFEval выше 80. В настоящее время поддерживает английский язык, официальная версия запланирована на ноябрь 2024 года, с расширением языковой поддержки и длины контекста."
},
+ "sonar": {
+ "description": "Легковесный продукт поиска на основе контекста, быстрее и дешевле, чем Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Глубокое исследование проводит всесторонние экспертные исследования и сводит их в доступные и практичные отчеты."
+ },
+ "sonar-pro": {
+ "description": "Расширенный продукт поиска, поддерживающий контекст поиска, сложные запросы и последующие действия."
+ },
+ "sonar-reasoning": {
+ "description": "Новый API продукт, поддерживаемый моделью вывода DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Новый API продукт, поддерживаемый моделью вывода DeepSeek."
+ },
"step-1-128k": {
"description": "Балансирует производительность и стоимость, подходит для общих сценариев."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Высокоскоростная модель, подходящая для реального времени диалогов."
},
+ "step-1.5v-mini": {
+ "description": "Эта модель обладает мощными возможностями понимания видео."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Эта модель обладает мощными способностями к пониманию изображений и превосходит 1o в области математики и кода. Модель меньше, чем 1o, и выводит результаты быстрее."
+ },
+ "step-1o-vision-32k": {
+ "description": "Эта модель обладает мощными способностями к пониманию изображений. По сравнению с серией моделей step-1v, она имеет более высокую визуальную производительность."
+ },
"step-1v-32k": {
"description": "Поддерживает визуальный ввод, улучшая мультимодальный опыт взаимодействия."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Поддерживает масштабные взаимодействия контекста, подходит для сложных диалоговых сценариев."
},
+ "step-2-mini": {
+ "description": "Супербыстрая большая модель на основе новой самодельной архитектуры внимания MFA, достигающая аналогичных результатов, как step1, при очень низких затратах, одновременно обеспечивая более высокую пропускную способность и более быстрое время отклика. Способна обрабатывать общие задачи и обладает особыми навыками в кодировании."
+ },
"taichu_llm": {
"description": "Модель языка TaiChu обладает выдающимися способностями к пониманию языка, а также к созданию текстов, ответам на вопросы, программированию, математическим вычислениям, логическому выводу, анализу эмоций и резюмированию текстов. Инновационно сочетает предобучение на больших данных с богатством многопоточных знаний, постоянно совершенствуя алгоритмические технологии и поглощая новые знания о словах, структуре, грамматике и семантике из огромных объемов текстовых данных, обеспечивая пользователям более удобную информацию и услуги, а также более интеллектуальный опыт."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V объединяет возможности понимания изображений, передачи знаний, логического вывода и других, демонстрируя выдающиеся результаты в области вопросов и ответов на основе текста и изображений."
+ "taichu_vl": {
+ "description": "Объединяет способности к пониманию изображений, переносу знаний и логическому выводу, демонстрируя выдающиеся результаты в области вопросов и ответов на основе текста и изображений."
+ },
+ "text-embedding-3-large": {
+ "description": "Самая мощная модель векторизации, подходящая для английских и неанглийских задач."
+ },
+ "text-embedding-3-small": {
+ "description": "Эффективная и экономичная новая генерация модели Embedding, подходящая для поиска знаний, приложений RAG и других сценариев."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Открытая версия последнего поколения предобученной модели GLM-4, выпущенной Zhizhu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) обеспечивает повышенные вычислительные возможности благодаря эффективным стратегиям и архитектуре модели."
},
+ "tts-1": {
+ "description": "Последняя модель преобразования текста в речь, оптимизированная для скорости в реальных сценариях."
+ },
+ "tts-1-hd": {
+ "description": "Последняя модель преобразования текста в речь, оптимизированная для качества."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) подходит для детализированных командных задач, обеспечивая отличные возможности обработки языка."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet устанавливает новые отраслевые стандарты, превосходя модели конкурентов и Claude 3 Opus, демонстрируя отличные результаты в широком спектре оценок, при этом обладая скоростью и стоимостью наших моделей среднего уровня."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet — это самая быстрая модель следующего поколения от Anthropic. По сравнению с Claude 3 Haiku, Claude 3.7 Sonnet продемонстрировала улучшения во всех навыках и превзошла предыдущую крупнейшую модель Claude 3 Opus по многим интеллектуальным бенчмаркам."
+ },
+ "whisper-1": {
+ "description": "Универсальная модель распознавания речи, поддерживающая многоязычное распознавание речи, перевод речи и распознавание языка."
+ },
"wizardlm2": {
"description": "WizardLM 2 — это языковая модель, предоставляемая Microsoft AI, которая особенно хорошо проявляет себя в сложных диалогах, многоязычных задачах, выводе и интеллектуальных помощниках."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Высокая стоимость и выдающаяся производительность. Балансировка высокой точности на основе производительности, скорости вывода и затрат."
},
+ "yi-lightning": {
+ "description": "Новая высокопроизводительная модель, обеспечивающая высокое качество вывода при значительно повышенной скорости вывода."
+ },
+ "yi-lightning-lite": {
+ "description": "Упрощенная версия, рекомендуется использовать yi-lightning."
+ },
"yi-medium": {
"description": "Модель среднего размера с улучшенной настройкой, сбалансированная по возможностям и стоимости. Глубокая оптимизация способности следовать указаниям."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Модель для сложных визуальных задач, обеспечивающая высокую производительность в понимании и анализе изображений."
+ },
+ "yi-vision-v2": {
+ "description": "Модель для сложных визуальных задач, обеспечивающая высокопроизводительное понимание и анализ на основе нескольких изображений."
}
}
diff --git a/DigitalHumanWeb/locales/ru-RU/plugin.json b/DigitalHumanWeb/locales/ru-RU/plugin.json
index 7c8bbde..acd855f 100644
--- a/DigitalHumanWeb/locales/ru-RU/plugin.json
+++ b/DigitalHumanWeb/locales/ru-RU/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Ошибка при обновлении плагина {{name}}",
"urlError": "Ссылка не возвращает данные в формате JSON. Проверьте правильность ссылки"
},
+ "inspector": {
+ "args": "Просмотреть список параметров",
+ "pluginRender": "Просмотреть интерфейс плагина"
+ },
"list": {
"item": {
"deprecated.title": "Устарел",
@@ -130,6 +134,34 @@
"plugin": "Запуск плагина..."
},
"pluginList": "Список плагинов",
+ "search": {
+ "config": {
+ "addKey": "Добавить ключ",
+ "close": "Удалить",
+ "confirm": "Конфигурация завершена, попробуйте снова"
+ },
+ "crawPages": {
+ "crawling": "Идентификация ссылки",
+ "detail": {
+ "preview": "Предварительный просмотр",
+ "raw": "Исходный текст",
+ "tooLong": "Содержимое текста слишком длинное, в контексте диалога сохраняются только первые {{characters}} символов, а остальная часть не учитывается в контексте разговора"
+ },
+ "meta": {
+ "crawler": "Режим обхода",
+ "words": "Количество символов"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Введите",
+ "description": "Введите URL SearchXNG, чтобы начать поиск в сети",
+ "keyPlaceholder": "Введите ключ",
+ "title": "Настройка поисковой системы SearchXNG",
+ "unconfiguredDesc": "Пожалуйста, свяжитесь с администратором для завершения настройки поисковой системы SearchXNG, чтобы начать поиск в сети",
+ "unconfiguredTitle": "Поисковая система SearchXNG еще не настроена"
+ },
+ "title": "Поиск в сети"
+ },
"setting": "Настройка плагина",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/ru-RU/portal.json b/DigitalHumanWeb/locales/ru-RU/portal.json
index 5ffeb14..68b6dc3 100644
--- a/DigitalHumanWeb/locales/ru-RU/portal.json
+++ b/DigitalHumanWeb/locales/ru-RU/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Плагины",
- "actions": {
- "genAiMessage": "Создать сообщение помощника",
- "summary": "Сводка",
- "summaryTooltip": "Сводка текущего содержимого"
- },
"artifacts": {
"display": {
"code": "Код",
diff --git a/DigitalHumanWeb/locales/ru-RU/providers.json b/DigitalHumanWeb/locales/ru-RU/providers.json
index c707f7e..c3aba74 100644
--- a/DigitalHumanWeb/locales/ru-RU/providers.json
+++ b/DigitalHumanWeb/locales/ru-RU/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs создает базовые модели и системы искусственного интеллекта для бизнеса, ускоряя внедрение генеративного ИИ в производстве."
+ },
"ai360": {
"description": "360 AI — это платформа AI-моделей и услуг, запущенная компанией 360, предлагающая множество передовых моделей обработки естественного языка, включая 360GPT2 Pro, 360GPT Pro, 360GPT Turbo и 360GPT Turbo Responsibility 8K. Эти модели сочетают в себе масштабные параметры и мультимодальные возможности, широко применяются в генерации текста, семантическом понимании, диалоговых системах и генерации кода. Благодаря гибкой ценовой политике 360 AI удовлетворяет разнообразные потребности пользователей, поддерживает интеграцию разработчиков и способствует инновациям и развитию интеллектуальных приложений."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure предлагает множество передовых AI-моделей, включая GPT-3.5 и новейшую серию GPT-4, поддерживающих различные типы данных и сложные задачи, с акцентом на безопасность, надежность и устойчивые AI-решения."
},
+ "azureai": {
+ "description": "Azure предлагает множество современных AI моделей, включая GPT-3.5 и последнюю серию GPT-4, поддерживающих различные типы данных и сложные задачи, нацеленных на безопасные, надежные и устойчивые AI решения."
+ },
"baichuan": {
"description": "Baichuan Intelligent — это компания, сосредоточенная на разработке больших моделей искусственного интеллекта, чьи модели показывают выдающиеся результаты в области китайских задач, таких как знаниевые энциклопедии, обработка длинных текстов и генерация контента, превосходя зарубежные модели. Baichuan Intelligent также обладает передовыми мультимодальными возможностями и показала отличные результаты в нескольких авторитетных оценках. Их модели включают Baichuan 4, Baichuan 3 Turbo и Baichuan 3 Turbo 128k, оптимизированные для различных сценариев применения, предлагая высокоэффективные решения."
},
"bedrock": {
"description": "Bedrock — это сервис, предоставляемый Amazon AWS, сосредоточенный на предоставлении предприятиям передовых AI-языковых и визуальных моделей. Его семейство моделей включает серию Claude от Anthropic, серию Llama 3.1 от Meta и другие, охватывающие широкий спектр от легковесных до высокопроизводительных решений, поддерживающих текстовую генерацию, диалоги, обработку изображений и другие задачи, подходящие для предприятий различного масштаба и потребностей."
},
+ "cloudflare": {
+ "description": "Запуск моделей машинного обучения на базе серверов GPU в глобальной сети Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek — это компания, сосредоточенная на исследованиях и применении технологий искусственного интеллекта, ее последняя модель DeepSeek-V2.5 объединяет возможности общего диалога и обработки кода, достигнув значительных улучшений в области согласования с человеческими предпочтениями, написания текстов и выполнения инструкций."
},
+ "doubao": {
+ "description": "Модель большого размера, разработанная ByteDance. Проверенная на более чем 50 внутренних бизнес-сценариях, с ежедневным использованием триллионов токенов, она продолжает совершенствоваться, предлагая множество модальных возможностей и создавая богатый бизнес-опыт для компаний с помощью качественных моделей."
+ },
"fireworksai": {
"description": "Fireworks AI — это ведущий поставщик высококлассных языковых моделей, сосредоточенный на вызовах функций и мультимодальной обработке. Их последняя модель Firefunction V2 основана на Llama-3 и оптимизирована для вызовов функций, диалогов и выполнения инструкций. Модель визуального языка FireLLaVA-13B поддерживает смешанный ввод изображений и текста. Другие заметные модели включают серию Llama и серию Mixtral, предлагая эффективную поддержку многоязычных инструкций и генерации."
},
+ "giteeai": {
+ "description": "API Serverless от Gitee AI предоставляет разработчикам AI сервисы API для рассуждений о больших моделях с открытым доступом."
+ },
"github": {
"description": "С помощью моделей GitHub разработчики могут стать инженерами ИИ и создавать с использованием ведущих моделей ИИ в отрасли."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Инженерный движок LPU от Groq показал выдающиеся результаты в последних независимых бенчмарках больших языковых моделей (LLM), переопределяя стандарты AI-решений благодаря своей удивительной скорости и эффективности. Groq представляет собой образец мгновенной скорости вывода, демонстрируя хорошие результаты в облачных развертываниях."
},
+ "higress": {
+ "description": "Higress — это облачный API шлюз, который был разработан внутри Alibaba для решения проблем, связанных с перезагрузкой Tengine, негативно влияющей на долгосрочные соединения, а также недостаточной способностью балансировки нагрузки для gRPC/Dubbo."
+ },
+ "huggingface": {
+ "description": "API для инференса HuggingFace предоставляет быстрый и бесплатный способ исследовать тысячи моделей для различных задач. Независимо от того, разрабатываете ли вы прототип для нового приложения или пробуете возможности машинного обучения, этот API обеспечивает мгновенный доступ к высокопроизводительным моделям в различных областях."
+ },
+ "hunyuan": {
+ "description": "Большая языковая модель, разработанная Tencent, обладающая мощными способностями к созданию текстов на китайском языке, логическим рассуждениям в сложных контекстах и надежным выполнением задач."
+ },
+ "internlm": {
+ "description": "Открытая организация, занимающаяся исследованием и разработкой инструментов для больших моделей. Предоставляет всем разработчикам ИИ эффективную и удобную открытую платформу, позволяя получить доступ к самым современным технологиям больших моделей и алгоритмов."
+ },
+ "jina": {
+ "description": "Jina AI была основана в 2020 году и является ведущей компанией в области поискового AI. Наша платформа поискового базиса включает векторные модели, реорганизаторы и небольшие языковые модели, которые помогают предприятиям создавать надежные и высококачественные генеративные AI и мультимодальные поисковые приложения."
+ },
+ "lmstudio": {
+ "description": "LM Studio — это настольное приложение для разработки и экспериментов с LLM на вашем компьютере."
+ },
"minimax": {
"description": "MiniMax — это компания по разработке универсального искусственного интеллекта, основанная в 2021 году, стремящаяся к совместному созданию интеллекта с пользователями. MiniMax самостоятельно разработала универсальные большие модели различных модальностей, включая текстовые модели с триллионом параметров, модели речи и модели изображений. Также были запущены приложения, такие как Conch AI."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI — это платформа, предлагающая API-сервисы для различных больших языковых моделей и генерации изображений AI, гибкая, надежная и экономически эффективная. Она поддерживает новейшие открытые модели, такие как Llama3, Mistral и предоставляет комплексные, удобные для пользователя и автоматически масштабируемые API-решения для разработки генеративных AI-приложений, подходящие для быстрого роста AI-стартапов."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ предоставляет контейнеры для самообслуживания GPU-ускоренного вывода микросервисов, поддерживающих развертывание предобученных и пользовательских AI моделей в облаке, центрах обработки данных, на персональных компьютерах RTX™ AI и рабочих станциях."
+ },
"ollama": {
"description": "Модели, предлагаемые Ollama, охватывают широкий спектр областей, включая генерацию кода, математические вычисления, многоязыковую обработку и диалоговое взаимодействие, поддерживая разнообразные потребности в развертывании на уровне предприятий и локализации."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity — это ведущий поставщик моделей генерации диалогов, предлагающий множество передовых моделей Llama 3.1, поддерживающих онлайн и оффлайн приложения, особенно подходящих для сложных задач обработки естественного языка."
},
+ "ppio": {
+ "description": "PPIO Paiouyun предоставляет стабильные и высокоэффективные API-сервисы для открытых моделей, поддерживающие всю серию DeepSeek, Llama, Qwen и другие ведущие модели в отрасли."
+ },
"qwen": {
"description": "Qwen — это сверхбольшая языковая модель, разработанная Alibaba Cloud, обладающая мощными возможностями понимания и генерации естественного языка. Она может отвечать на различные вопросы, создавать текстовый контент, выражать мнения и писать код, играя важную роль в различных областях."
},
+ "sambanova": {
+ "description": "SambaNova Cloud позволяет разработчикам легко использовать лучшие открытые модели и наслаждаться самой быстрой скоростью вывода."
+ },
+ "sensenova": {
+ "description": "SenseNova, опираясь на мощную инфраструктуру SenseTime, предлагает эффективные и удобные услуги полного стека больших моделей."
+ },
"siliconcloud": {
"description": "SiliconFlow стремится ускорить AGI, чтобы принести пользу человечеству, повышая эффективность масштабного AI с помощью простого и экономичного стека GenAI."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "Новая генерация мультимодальных больших моделей, разработанная Институтом автоматизации Китайской академии наук и Институтом искусственного интеллекта Уханя, поддерживает многораундные вопросы и ответы, создание текстов, генерацию изображений, 3D-понимание, анализ сигналов и другие комплексные задачи, обладая более сильными когнитивными, понимательными и творческими способностями, предлагая новый опыт взаимодействия."
},
+ "tencentcloud": {
+ "description": "Атомные возможности движка знаний (LLM Knowledge Engine Atomic Power) основаны на разработке движка знаний и представляют собой полную цепочку возможностей для вопросов и ответов, ориентированную на предприятия и разработчиков. Вы можете создать собственный сервис модели, используя различные атомные возможности, комбинируя такие услуги, как анализ документов, разбиение, встраивание, многократное переписывание и другие, чтобы настроить уникальный AI-бизнес для вашей компании."
+ },
"togetherai": {
"description": "Together AI стремится достичь передовых результатов с помощью инновационных AI-моделей, предлагая широкий спектр возможностей для настройки, включая поддержку быстрого масштабирования и интуитивно понятные процессы развертывания, чтобы удовлетворить различные потребности бизнеса."
},
"upstage": {
"description": "Upstage сосредоточен на разработке AI-моделей для различных бизнес-потребностей, включая Solar LLM и документальный AI, с целью достижения искусственного общего интеллекта (AGI). Создавайте простые диалоговые агенты через Chat API и поддерживайте вызовы функций, переводы, встраивания и приложения в конкретных областях."
},
+ "vertexai": {
+ "description": "Серия Gemini от Google — это самые современные и универсальные AI-модели, разработанные Google DeepMind, специально созданные для мультимодальности, поддерживающие бесшовное понимание и обработку текста, кода, изображений, аудио и видео. Подходят для различных сред, от дата-центров до мобильных устройств, значительно повышая эффективность и универсальность применения AI-моделей."
+ },
+ "vllm": {
+ "description": "vLLM — это быстрая и простая в использовании библиотека для вывода и обслуживания LLM."
+ },
+ "volcengine": {
+ "description": "Платформа разработки сервисов больших моделей, запущенная ByteDance, предлагает функционально богатые, безопасные и конкурентоспособные по цене услуги вызова моделей, а также предоставляет полные функции от данных моделей, тонкой настройки, вывода до оценки, обеспечивая всестороннюю поддержку разработки ваших AI приложений."
+ },
+ "wenxin": {
+ "description": "Корпоративная платформа для разработки и обслуживания крупных моделей и нативных приложений ИИ, предлагающая самый полный и удобный инструментарий для разработки генеративных моделей искусственного интеллекта и полного процесса разработки приложений."
+ },
+ "xai": {
+ "description": "xAI — это компания, занимающаяся разработкой искусственного интеллекта для ускорения научных открытий человечества. Наша миссия — способствовать общему пониманию Вселенной."
+ },
"zeroone": {
"description": "01.AI сосредоточен на технологиях искусственного интеллекта 2.0, активно продвигая инновации и применение \"человек + искусственный интеллект\", используя мощные модели и передовые AI-технологии для повышения производительности человека и реализации технологического потенциала."
},
diff --git a/DigitalHumanWeb/locales/ru-RU/setting.json b/DigitalHumanWeb/locales/ru-RU/setting.json
index bcffd77..1ec5967 100644
--- a/DigitalHumanWeb/locales/ru-RU/setting.json
+++ b/DigitalHumanWeb/locales/ru-RU/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Настройка пользовательской модели",
"tokens": {
- "title": "Максимальное количество токенов",
- "unlimited": "неограниченный"
+ "title": "Максимальное количество токенов"
},
"vision": {
"extra": "Эта конфигурация только активирует возможность загрузки изображений в приложении, поддержка распознавания полностью зависит от самой модели, пожалуйста, протестируйте доступность визуального распознавания этой модели самостоятельно",
@@ -98,6 +97,7 @@
"title": "Использовать режим запроса с клиента"
},
"fetcher": {
+ "clear": "Очистить полученную модель",
"fetch": "Получить список моделей",
"fetching": "Идет получение списка моделей...",
"latestTime": "Последнее обновление: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Автоматическое создание темы во время беседы, работает только во временных темах",
"title": "Автоматическое создание темы"
},
- "enableCompressThreshold": {
- "title": "Включить сжатие истории сообщений"
+ "enableCompressHistory": {
+ "title": "Включить автоматическое резюмирование истории сообщений"
},
"enableHistoryCount": {
"alias": "Без ограничений",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Включить ограничение максимального количества токенов"
},
+ "enableReasoningEffort": {
+ "title": "Включить настройку интенсивности вывода"
+ },
"frequencyPenalty": {
- "desc": "Чем выше значение, тем меньше вероятность повторения слов",
- "title": "Штраф за повторение"
+ "desc": "Чем больше значение, тем разнообразнее и богаче словарный запас; чем меньше значение, тем проще и понятнее слова",
+ "title": "Разнообразие словарного запаса"
},
"maxTokens": {
"desc": "Максимальное количество токенов для одного взаимодействия",
@@ -212,19 +215,31 @@
"desc": "{{provider}} модель",
"title": "Модель"
},
+ "params": {
+ "title": "Расширенные параметры"
+ },
"presencePenalty": {
- "desc": "Чем выше значение, тем больше вероятность перехода на новые темы",
- "title": "Штраф за однообразие"
+ "desc": "Чем больше значение, тем больше склонность к различным выражениям, избегая повторения концепций; чем меньше значение, тем больше склонность к использованию повторяющихся концепций или нарративов, выражение становится более последовательным",
+ "title": "Разнообразие выражений"
+ },
+ "reasoningEffort": {
+ "desc": "Чем больше значение, тем сильнее способность вывода, но это может увеличить время отклика и потребление токенов",
+ "options": {
+ "high": "Высокий",
+ "low": "Низкий",
+ "medium": "Средний"
+ },
+ "title": "Интенсивность вывода"
},
"temperature": {
- "desc": "Чем выше значение, тем более непредсказуемым будет ответ",
- "title": "Непредсказуемость",
- "titleWithValue": "Непредсказуемость {{value}}"
+ "desc": "Чем больше значение, тем более креативными и воображаемыми будут ответы; чем меньше значение, тем более строгими будут ответы",
+ "title": "Креативность",
+ "warning": "Слишком высокое значение креативности может привести к искажению вывода"
},
"title": "Настройки модели",
"topP": {
- "desc": "Похоже на непредсказуемость, но не изменяется вместе с параметром непредсказуемости",
- "title": "Верхний процент P"
+ "desc": "Сколько возможностей учитывать, чем больше значение, тем больше возможных ответов принимается; чем меньше значение, тем больше склонность к выбору наиболее вероятного ответа. Не рекомендуется изменять вместе с креативностью",
+ "title": "Открытость мышления"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Модель, используемая для генерации имени агента, описания, аватара и меток",
"title": "Автоматическое создание информации об агенте"
},
+ "customPrompt": {
+ "addPrompt": "Добавить пользовательский запрос",
+ "desc": "После заполнения система будет использовать пользовательский запрос при генерации контента",
+ "placeholder": "Введите пользовательский запрос",
+ "title": "Пользовательский запрос"
+ },
+ "historyCompress": {
+ "label": "Модель истории беседы",
+ "modelDesc": "Укажите модель, используемую для сжатия истории беседы",
+ "title": "Автоматическое резюмирование истории беседы"
+ },
"queryRewrite": {
"label": "Модель переформулирования вопросов",
"modelDesc": "Модель, предназначенная для оптимизации вопросов пользователей",
- "title": "База знаний"
+ "title": "Переписывание вопросов базы знаний"
+ },
+ "thread": {
+ "label": "Модель именования подтем",
+ "modelDesc": "Модель, используемая для автоматического переименования подтем",
+ "title": "Автоматическое именование подтем"
},
"title": "Системный агент",
"topic": {
@@ -395,6 +426,7 @@
"common": "Общие настройки",
"experiment": "Эксперимент",
"llm": "Языковая модель",
+ "provider": "Поставщик ИИ услуг",
"sync": "Синхронизация с облаком",
"system-agent": "Системный агент",
"tts": "Голосовые услуги"
diff --git a/DigitalHumanWeb/locales/ru-RU/thread.json b/DigitalHumanWeb/locales/ru-RU/thread.json
new file mode 100644
index 0000000..7c3fd72
--- /dev/null
+++ b/DigitalHumanWeb/locales/ru-RU/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Вы собираетесь удалить эту под-тему. После удаления восстановить её будет невозможно, пожалуйста, действуйте осторожно."
+ },
+ "newPortalThread": {
+ "includeContext": "Включить контекст темы",
+ "title": "Открыть новую подтему"
+ },
+ "notSupportMultiModals": "Подтемы в настоящее время не поддерживают загрузку файлов/изображений. Если у вас есть потребность, пожалуйста, оставьте сообщение: <1>💬 Обсуждение1>"
+}
diff --git a/DigitalHumanWeb/locales/ru-RU/tool.json b/DigitalHumanWeb/locales/ru-RU/tool.json
index 94b30e6..aa18756 100644
--- a/DigitalHumanWeb/locales/ru-RU/tool.json
+++ b/DigitalHumanWeb/locales/ru-RU/tool.json
@@ -6,5 +6,23 @@
"generating": "Создание...",
"images": "Изображения:",
"prompt": "подсказка"
+ },
+ "search": {
+ "createNewSearch": "Создать новую запись поиска",
+ "emptyResult": "Результатов не найдено, пожалуйста, измените ключевые слова и попробуйте снова",
+ "genAiMessage": "Создать сообщение помощника",
+ "includedTooltip": "Текущие результаты поиска будут включены в контекст сессии",
+ "keywords": "Ключевые слова:",
+ "scoreTooltip": "Оценка релевантности, чем выше оценка, тем больше соответствие запросу",
+ "searchBar": {
+ "button": "Поиск",
+ "placeholder": "Ключевые слова",
+ "tooltip": "Будет повторно получен результат поиска и создано новое резюме сообщения"
+ },
+ "searchEngine": "Поисковая система:",
+ "searchResult": "Количество результатов:",
+ "summary": "Резюме",
+ "summaryTooltip": "Суммировать текущее содержимое",
+ "viewMoreResults": "Посмотреть еще {{results}} результатов"
}
}
diff --git a/DigitalHumanWeb/locales/ru-RU/topic.json b/DigitalHumanWeb/locales/ru-RU/topic.json
new file mode 100644
index 0000000..e1b924a
--- /dev/null
+++ b/DigitalHumanWeb/locales/ru-RU/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Умное переименование",
+ "confirmRemoveAll": "Вы собираетесь удалить все темы. После удаления их нельзя будет восстановить, пожалуйста, будьте осторожны.",
+ "confirmRemoveTopic": "Вы собираетесь удалить эту тему. После удаления её нельзя будет восстановить, пожалуйста, будьте осторожны.",
+ "confirmRemoveUnstarred": "Вы собираетесь удалить неотмеченные темы. После удаления их нельзя будет восстановить, пожалуйста, будьте осторожны.",
+ "duplicate": "Создать копию",
+ "export": "Экспортировать тему",
+ "removeAll": "Удалить все темы",
+ "removeUnstarred": "Удалить неотмеченные темы"
+ },
+ "defaultTitle": "Тема по умолчанию",
+ "duplicateLoading": "Копирование темы...",
+ "duplicateSuccess": "Тема успешно скопирована",
+ "favorite": "Избранное",
+ "groupMode": {
+ "ascMessages": "По возрастанию общего числа сообщений",
+ "byTime": "Группировка по времени",
+ "descMessages": "По убыванию общего числа сообщений",
+ "flat": "Без группировки"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Этот месяц",
+ "today": "Сегодня",
+ "week": "Эта неделя",
+ "yesterday": "Вчера"
+ }
+ },
+ "guide": {
+ "desc": "Нажмите кнопку слева от отправки, чтобы сохранить текущий разговор как историческую тему и начать новый разговор.",
+ "title": "Список тем"
+ },
+ "searchPlaceholder": "Поиск тем...",
+ "searchResultEmpty": "Нет результатов поиска",
+ "temp": "Временный",
+ "title": "Тема"
+}
diff --git a/DigitalHumanWeb/locales/ru-RU/welcome.json b/DigitalHumanWeb/locales/ru-RU/welcome.json
index 20921f0..db24cd1 100644
--- a/DigitalHumanWeb/locales/ru-RU/welcome.json
+++ b/DigitalHumanWeb/locales/ru-RU/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Импорт конфига",
- "market": "Посетить рынок",
- "start": "Начать"
- },
"guide": {
"agents": {
"replaceBtn": "Заменить",
diff --git a/DigitalHumanWeb/locales/tr-TR/auth.json b/DigitalHumanWeb/locales/tr-TR/auth.json
index ba16da2..155c6c9 100644
--- a/DigitalHumanWeb/locales/tr-TR/auth.json
+++ b/DigitalHumanWeb/locales/tr-TR/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Geçen Ay",
+ "recent30Days": "Son 30 Gün"
+ },
+ "header": {
+ "desc": "Hesap bilgilerinizi yönetin.",
+ "title": "Hesap"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Pasif",
+ "more": "Aktif"
+ },
+ "months": {
+ "apr": "Nis",
+ "aug": "Ağu",
+ "dec": "Ara",
+ "feb": "Şub",
+ "jan": "Oca",
+ "jul": "Tem",
+ "jun": "Haz",
+ "mar": "Mar",
+ "may": "May",
+ "nov": "Kas",
+ "oct": "Eki",
+ "sep": "Eyl"
+ },
+ "tooltip": "{{date}} tarihinde {{count}} mesaj gönderildi",
+ "totalCount": "Geçen yıl toplam {{count}} mesaj gönderildi"
+ },
"login": "Giriş Yap",
"loginOrSignup": "Giriş Yap / Kayıt Ol",
- "profile": "Profil",
- "security": "Güvenlik",
+ "profile": {
+ "avatar": "Avatar",
+ "email": "E-posta Adresi",
+ "sso": {
+ "loading": "Bağlı üçüncü taraf hesapları yükleniyor",
+ "providers": "Bağlı Hesaplar",
+ "unlink": {
+ "description": "Bu hesap ile {{provider}} hesap “{{providerAccountId}}” ilişkisi kesildiğinde giriş yapamayacaksınız. Eğer {{provider}} hesabınızı mevcut hesaba yeniden bağlamak isterseniz, lütfen {{provider}} hesabının e-posta adresinin {{email}} olduğundan emin olun, giriş yaptığınızda otomatik olarak mevcut hesaba bağlanacaktır.",
+ "forbidden": "En az bir üçüncü taraf hesap bağlamaya devam etmelisiniz.",
+ "title": "{{provider}} adlı üçüncü taraf hesabını kaldırmak istiyor musunuz?"
+ }
+ },
+ "username": "Kullanıcı Adı"
+ },
"signout": "Çıkış Yap",
- "signup": "Kaydol"
+ "signup": "Kayıt Ol",
+ "stats": {
+ "aiheatmaps": "Aktivite İndeksi",
+ "assistants": "Asistanlar",
+ "assistantsRank": {
+ "left": "Asistan",
+ "right": "Konu",
+ "title": "Asistan Kullanım Sıralaması"
+ },
+ "createdAt": "Kayıtlı olduğu tarih",
+ "days": "gün",
+ "empty": {
+ "desc": "Görüntülemek için daha fazla sohbet verisi biriktirin",
+ "title": "Veri Yok"
+ },
+ "lastYearActivity": "geçen yılki aktivite",
+ "loginGuide": {
+ "f1": "Ücretsiz kullanım al",
+ "f2": "Çoklu cihazda mesaj senkronizasyonu",
+ "f3": "Zengin asistanlara sahip ol",
+ "f4": "Güçlü eklentileri keşfet",
+ "title": "Giriş yaptıktan sonra şunları yapabilirsiniz:"
+ },
+ "messages": "Mesajlar",
+ "modelsRank": {
+ "left": "Model",
+ "right": "Mesajlar",
+ "title": "Model Kullanım Sıralaması"
+ },
+ "share": {
+ "title": "AI Aktivite İndeksim"
+ },
+ "topics": "Konu",
+ "topicsRank": {
+ "left": "Konu",
+ "right": "Mesajlar",
+ "title": "Konu İçerik Sıralaması"
+ },
+ "updatedAt": "Güncellenme tarihi",
+ "welcome": "{{username}}, bu {{appName}} ile geçirdiğin {{days}} gün.",
+ "words": "Toplam kelime sayısı"
+ },
+ "tab": {
+ "profile": "Profil",
+ "security": "Güvenlik",
+ "stats": "İstatistikler"
+ }
}
diff --git a/DigitalHumanWeb/locales/tr-TR/changelog.json b/DigitalHumanWeb/locales/tr-TR/changelog.json
new file mode 100644
index 0000000..a4f3b74
--- /dev/null
+++ b/DigitalHumanWeb/locales/tr-TR/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Bizi X'te takip edin",
+ "subscribeToUpdates": "Güncellemeleri abone olun",
+ "versions": "Sürüm detayları"
+ },
+ "addedWhileAway": "Siz yokken yeni özellikler ekledik.",
+ "allChangelog": "Tüm güncelleme günlüklerini görüntüle",
+ "description": "{{appName}}'in yeni özelliklerini ve iyileştirmelerini sürekli takip edin",
+ "pagination": {
+ "next": "Sonraki Sayfa",
+ "older": "Geçmiş değişiklikleri görüntüle"
+ },
+ "readDetails": "Detayları okuyun",
+ "title": "Güncelleme Günlüğü",
+ "versionDetails": "Sürüm detayları",
+ "welcomeBack": "Hoş geldiniz!"
+}
diff --git a/DigitalHumanWeb/locales/tr-TR/chat.json b/DigitalHumanWeb/locales/tr-TR/chat.json
index 4fdb187..5f0ab8f 100644
--- a/DigitalHumanWeb/locales/tr-TR/chat.json
+++ b/DigitalHumanWeb/locales/tr-TR/chat.json
@@ -8,6 +8,7 @@
"agents": "Asistan",
"artifact": {
"generating": "Üretiliyor",
+ "inThread": "Alt konu içinde görüntülenemiyor, lütfen ana konuşma alanına geçin",
"thinking": "Düşünülüyor",
"thought": "Düşünce Süreci",
"unknownTitle": "İsimsiz Eser"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Kopya",
"emptyAgent": "Asistan yok",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Tek bir diyalogun üretim maliyeti en fazla %90 oranında düşürülebilir, yanıt hızı 4 kat artar (<1>Daha fazla bilgi edinin1>). Açıldığında, otomatik olarak geçmiş mesaj sayısı sınırı devre dışı bırakılacaktır.",
+ "title": "Bağlam önbelleğini aç"
+ },
+ "enableReasoning": {
+ "desc": "Claude Thinking mekanizmasına dayalı kısıtlamalar (<1>Daha fazla bilgi edinin1>), açıldığında otomatik olarak geçmiş mesaj sayısı sınırı devre dışı bırakılacaktır.",
+ "title": "Derin Düşünmeyi Aç"
+ },
+ "reasoningBudgetToken": {
+ "title": "Düşünme Tüketim Tokeni"
+ },
+ "title": "Model Genişletme Özellikleri"
+ },
+ "history": {
+ "title": "Asistan yalnızca son {{count}} mesajı hatırlayacak"
+ },
"historyRange": "Geçmiş Aralığı",
+ "historySummary": "Tarihsel haber özeti",
"inbox": {
"desc": "Beyin fırtınasını başlatın ve yaratıcı düşünmeye başlayın. Sanal asistanınız burada, her konuda sizinle iletişim kurmak için hazır.",
"title": "Sohbet Et"
@@ -45,6 +64,9 @@
"stop": "Dur",
"warp": "Satır atla"
},
+ "intentUnderstanding": {
+ "title": "Niyetinizi anlama ve analiz etme aşamasındayız..."
+ },
"knowledgeBase": {
"all": "Tüm İçerik",
"allFiles": "Tüm Dosyalar",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Sil ve Yeniden Oluştur",
+ "deleteDisabledByThreads": "Alt konular mevcut, silinemez",
"regenerate": "Yeniden Oluştur"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Kredi",
+ "creditPricing": "Fiyatlandırma",
+ "creditTooltip": "Hesaplamayı kolaylaştırmak için, 1$'ı 1M kredi olarak hesaplıyoruz; örneğin, $3/M token, 3 kredi/token olarak hesaplanır.",
+ "pricing": {
+ "inputCachedTokens": "Önceden yüklenmiş giriş {{amount}}/kredi · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M karakter",
+ "inputMinutes": "${{amount}}/dakika",
+ "inputTokens": "Giriş {{amount}}/kredi · ${{amount}}/M",
+ "outputTokens": "Çıkış {{amount}}/kredi · ${{amount}}/M",
+ "writeCacheInputTokens": "Giriş yazma önbelleği {{amount}}/puan · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Ortalama birim fiyat",
+ "input": "Giriş",
+ "inputAudio": "Ses girişi",
+ "inputCached": "Önceden yüklenmiş giriş",
+ "inputCitation": "Giriş alıntısı",
+ "inputText": "Metin girişi",
+ "inputTitle": "Giriş detayları",
+ "inputUncached": "Önceden yüklenmemiş giriş",
+ "inputWriteCached": "Giriş önbelleği yazma",
+ "output": "Çıkış",
+ "outputAudio": "Ses çıkışı",
+ "outputText": "Metin çıkışı",
+ "outputTitle": "Çıkış detayları",
+ "reasoning": "Derin düşünme",
+ "title": "Üretim detayları",
+ "total": "Toplam tüketim"
+ }
+ },
"newAgent": "Yeni Asistan",
"pin": "Pin",
"pinOff": "Unpin",
@@ -81,6 +137,32 @@
},
"regenerate": "Tekrarla",
"roleAndArchive": "Rol ve Arşiv",
+ "search": {
+ "grounding": {
+ "searchQueries": "Arama Anahtar Kelimeleri",
+ "title": "{{count}} sonuç bulundu"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Sohbet içeriğine göre akıllıca arama gerekip gerekmediğini belirler",
+ "title": "Akıllı Bağlantı"
+ },
+ "off": {
+ "desc": "Sadece modelin temel bilgilerini kullanır, ağ araması yapmaz",
+ "title": "Bağlantıyı Kapat"
+ },
+ "on": {
+ "desc": "Sürekli ağ araması yaparak en güncel bilgileri alır",
+ "title": "Her Zaman Bağlantıda"
+ },
+ "useModelBuiltin": "Modelin yerleşik arama motorunu kullan"
+ },
+ "searchModel": {
+ "desc": "Mevcut model fonksiyon çağrısını desteklemiyor, bu nedenle çevrimiçi arama yapmak için fonksiyon çağrısını destekleyen bir model ile birlikte kullanılması gerekiyor",
+ "title": "Arama Yardımcı Modeli"
+ },
+ "title": "Ağ Araması"
+ },
"searchAgentPlaceholder": "Arama Asistanı...",
"sendPlaceholder": "Mesajınızı buraya yazın...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Grup adı 1-20 karakter arasında olmalıdır"
},
"shareModal": {
+ "copy": "Kopyala",
"download": "Ekran Görüntüsünü İndir",
+ "downloadFile": "Dosyayı İndir",
+ "exportTitle": "Varsayılan Başlık",
"imageType": "Format",
+ "includeTool": "Eklenti mesajını dahil et",
+ "includeUser": "Kullanıcı mesajını dahil et",
"screenshot": "Ekran Görüntüsü",
"settings": "Ayarlar",
- "shareToShareGPT": "ShareGPT Link Oluştur",
+ "text": "Metin",
"withBackground": "Arka Plan",
"withFooter": "Footer",
"withPluginInfo": "Plugin Bilgileri",
+ "withRole": "Mesaj rolünü dahil et",
"withSystemRole": "Asistan Rol"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Tanımlanıyor...",
"prettifying": "İyileştiriliyor..."
},
- "temp": "Geçici",
+ "thread": {
+ "divider": "Alt konu",
+ "threadMessageCount": "{{messageCount}} mesaj",
+ "title": "Alt konu"
+ },
"tokenDetails": {
"chats": "Sohbetler",
+ "historySummary": "Tarih Özeti",
"rest": "Kalan",
"systemRole": "Sistem Rolü",
"title": "Bağlam Detayları",
@@ -131,29 +224,10 @@
"used": "Kullanılan"
},
"topic": {
- "actions": {
- "autoRename": "Akıllı Yeniden Adlandırma",
- "duplicate": "Kopya Oluştur",
- "export": "Konuyu Dışa Aktar"
- },
"checkOpenNewTopic": "Yeni bir konu açılsın mı?",
"checkSaveCurrentMessages": "Mevcut sohbeti konu olarak kaydetmek istiyor musunuz?",
- "confirmRemoveAll": "Tüm konuları silmek üzeresiniz. Bir kere silindiğinde, geri alınamazlar. Lütfen dikkatli bir şekilde devam edin.",
- "confirmRemoveTopic": "Bu konuyu silmek üzeresiniz. Bir kere silindiğinde, geri alınamaz. Lütfen dikkatli bir şekilde devam edin.",
- "confirmRemoveUnstarred": "Yıldızlanmamış konuları silmek üzeresiniz. Bir kere silindiğinde, geri alınamazlar. Lütfen dikkatli bir şekilde devam edin.",
- "defaultTitle": "Konu",
- "duplicateLoading": "Konu kopyalanıyor...",
- "duplicateSuccess": "Konu başarıyla kopyalandı",
- "guide": {
- "desc": "Mevcut oturumu geçmiş konu olarak kaydetmek ve yeni bir oturum başlatmak için sol taraftaki düğmeye tıklayın",
- "title": "Konu Listesi"
- },
"openNewTopic": "Yeni Konu",
- "removeAll": "Tüm Konuları Sil",
- "removeUnstarred": "Tüm Yıldızlanmamış Konuları Sil",
- "saveCurrentMessages": "Mevcut oturumu konu olarak kaydet",
- "searchPlaceholder": "Konuları ara...",
- "title": "Konular"
+ "saveCurrentMessages": "Mevcut oturumu konu olarak kaydet"
},
"translate": {
"action": "Çeviri",
@@ -184,5 +258,6 @@
"processing": "Dosya İşleniyor..."
}
}
- }
+ },
+ "zenMode": "Odak Modu"
}
diff --git a/DigitalHumanWeb/locales/tr-TR/common.json b/DigitalHumanWeb/locales/tr-TR/common.json
index 0c261e9..99de1c3 100644
--- a/DigitalHumanWeb/locales/tr-TR/common.json
+++ b/DigitalHumanWeb/locales/tr-TR/common.json
@@ -9,15 +9,79 @@
"title": "{{name}}'i Denemek İçin Hoş Geldiniz"
}
},
- "appInitializing": "Uygulama başlatılıyor...",
+ "appLoading": {
+ "appIdle": "Başlatılıyor",
+ "appInitializing": "Uygulama başlatılıyor...",
+ "failed": "Üzgünüz, uygulama başlatılırken bir hata oluştu, lütfen ayrıntıları kontrol edin ve sorunu giderin.",
+ "finished": "Veritabanı başlatma tamamlandı",
+ "goToChat": "Sohbet sayfası yükleniyor...",
+ "initAuth": "Kimlik doğrulama servisi başlatılıyor...",
+ "initUser": "Kullanıcı durumu başlatılıyor...",
+ "initializing": "PGlite veritabanı başlatılıyor...",
+ "loadingDependencies": "Bağımlılıklar yükleniyor...",
+ "loadingWasm": "WASM modülü yükleniyor...",
+ "migrating": "Veri tablosu taşınıyor...",
+ "ready": "Veritabanı hazır",
+ "showDetail": "Detayları Görüntüle"
+ },
"autoGenerate": "Otomatik Oluştur",
"autoGenerateTooltip": "Auto-generate agent description based on prompts",
"autoGenerateTooltipDisabled": "Otomatik tamamlama işlevini kullanmadan önce ipucu kelimesini girin",
"back": "Geri",
"batchDelete": "Toplu Sil",
"blog": "Ürün Blogu",
+ "branching": "Alt konu oluştur",
+ "branchingDisable": "«Alt konu» özelliği yalnızca sunucu sürümünde mevcuttur. Bu özelliği kullanmak için lütfen sunucu dağıtım moduna geçin veya LobeChat Cloud'u kullanın.",
"cancel": "İptal",
"changelog": "Changelog",
+ "clientDB": {
+ "autoInit": {
+ "title": "PGlite veritabanı başlatılıyor"
+ },
+ "error": {
+ "desc": "Üzgünüz, Pglite veritabanı başlatma sırasında bir hata oluştu. Lütfen düğmeye tıklayarak tekrar deneyin. Eğer birden fazla denemeden sonra hala hata alıyorsanız, lütfen <1>bir sorun bildirin1>, size en kısa sürede yardımcı olacağız.",
+ "detail": "Hata Nedeni: [{{type}}] {{message}}. Ayrıntılar aşağıda:",
+ "retry": "Tekrar Dene",
+ "title": "Veritabanı başlatma hatası"
+ },
+ "initing": {
+ "error": "Hata oluştu, lütfen tekrar deneyin",
+ "idle": "Başlatma bekleniyor...",
+ "initializing": "Başlatılıyor...",
+ "loadingDependencies": "Bağlantılar yükleniyor...",
+ "loadingWasmModule": "WASM modülü yükleniyor...",
+ "migrating": "Veri tablosu taşınıyor...",
+ "ready": "Veritabanı hazır"
+ },
+ "modal": {
+ "desc": "PGlite istemci veritabanını etkinleştirerek, tarayıcınızda sohbet verilerini kalıcı olarak depolayın ve bilgi bankası gibi gelişmiş özellikleri kullanın.",
+ "enable": "Hemen Etkinleştir",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Kişisel bilgi havuzunuzu oluşturun ve asistanınızla kolayca bilgi havuzu sohbetine başlayın (yakında gelecek)",
+ "title": "Bilgi havuzu sohbetini destekleyin, ikinci beyninizi açın"
+ },
+ "localFirst": {
+ "desc": "Sohbet verileri tamamen tarayıcıda saklanır, verileriniz her zaman sizin kontrolünüzde.",
+ "title": "Yerel öncelik, gizlilik öncelikli"
+ },
+ "pglite": {
+ "desc": "PGlite tabanlı, AI Native yüksek düzey özellikleri (vektör arama) yerel olarak destekler",
+ "title": "Yeni nesil istemci depolama mimarisi"
+ }
+ },
+ "init": {
+ "desc": "Veritabanı başlatılıyor, ağ farklılıklarına bağlı olarak 5-30 saniye sürebilir.",
+ "title": "PGlite veritabanı başlatılıyor"
+ },
+ "title": "İstemci veritabanını aç"
+ },
+ "ready": {
+ "button": "Hemen Kullan",
+ "desc": "Hemen kullanmak istiyorum",
+ "title": "PGlite veritabanı hazır"
+ }
+ },
"close": "Kapat",
"contact": "Bize Ulaşın",
"copy": "Kopyala",
@@ -112,6 +176,7 @@
"en": "İngilizce",
"en-US": "İngilizce",
"es-ES": "İspanyolca",
+ "fa-IR": "Farsça",
"fi-FI": "Fince",
"fr-FR": "Fransızca",
"hi-IN": "Hintçe",
@@ -153,6 +218,7 @@
"pinOff": "Unpin",
"privacy": "Gizlilik Politikası",
"regenerate": "Tekrarla",
+ "releaseNotes": "Sürüm Detayları",
"rename": "Yeniden İsimlendir",
"reset": "Reset",
"retry": "Yeniden Dene",
@@ -209,6 +275,7 @@
},
"temp": "Geçici",
"terms": "Hizmet Koşulları",
+ "update": "Güncelle",
"updateAgent": "Asistan Bilgilerini Güncelle",
"upgradeVersion": {
"action": "Güncelle",
@@ -219,6 +286,7 @@
"anonymousNickName": "Anonim Kullanıcı",
"billing": "Fatura Yönetimi",
"cloud": "{{name}}'i Deneyin",
+ "community": "Topluluk Sürümü",
"data": "Veri Depolama",
"defaultNickname": "Topluluk Kullanıcısı",
"discord": "Topluluk Destek",
@@ -228,7 +296,6 @@
"help": "Yardım Merkezi",
"moveGuide": "Ayarlar düğmesini buraya taşıyın",
"plans": "Planlar",
- "preview": "Önizleme",
"profile": "Hesap Yönetimi",
"setting": "Uygulama Ayarları",
"usages": "Kullanım İstatistikleri"
diff --git a/DigitalHumanWeb/locales/tr-TR/components.json b/DigitalHumanWeb/locales/tr-TR/components.json
index 288a593..bea2cc4 100644
--- a/DigitalHumanWeb/locales/tr-TR/components.json
+++ b/DigitalHumanWeb/locales/tr-TR/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Toplu parçalara ayırma",
"chunking": "Parçalara ayırma",
"chunkingTooltip": "Dosyayı birden fazla metin parçasına ayırıp vektörleştirdikten sonra, anlamsal arama ve dosya diyalogları için kullanılabilir",
+ "chunkingUnsupported": "Bu dosya parça parça yüklemeyi desteklemiyor.",
"confirmDelete": "Bu dosya silinecek, silindikten sonra geri alınamaz, lütfen işleminizi onaylayın",
"confirmDeleteMultiFiles": "Seçilen {{count}} dosya silinecek, silindikten sonra geri alınamaz, lütfen işleminizi onaylayın",
"confirmRemoveFromKnowledgeBase": "Seçilen {{count}} dosya bilgi tabanından kaldırılacak, kaldırıldıktan sonra dosyalar tüm dosyalar arasında görüntülenebilir, lütfen işleminizi onaylayın",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Geri dön"
},
+ "MaxTokenSlider": {
+ "unlimited": "Sınırsız"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Özel model, varsayılan olarak hem fonksiyon çağrısını hem de görüntü tanımayı destekler, yukarıdaki yeteneklerin kullanılabilirliğini doğrulamak için lütfen gerçek durumu kontrol edin",
"file": "Bu model dosya yükleme ve tanımayı destekler",
"functionCall": "Bu model fonksiyon çağrısını destekler",
+ "reasoning": "Bu model derin düşünmeyi destekler",
+ "search": "Bu model çevrimiçi aramayı destekler",
"tokens": "Bu model tek bir oturumda en fazla {{tokens}} Token destekler",
"vision": "Bu model görüntü tanımıyı destekler"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Etkinleştirilmiş model bulunmamaktadır, lütfen ayarlara giderek açın",
+ "emptyProvider": "Etkinleştirilmiş bir sağlayıcı yok, lütfen ayarlara gidin",
+ "goToSettings": "Ayrıntılara git",
"provider": "Sağlayıcı"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Tarayıcı güvenlik kısıtlamaları nedeniyle, Ollama'yı düzgün bir şekilde kullanabilmek için çapraz alan yapılandırması yapmanız gerekmektedir.",
+ "linux": {
+ "env": "[Service] bölümüne `Environment` ekleyin ve OLLAMA_ORIGINS ortam değişkenini ekleyin:",
+ "reboot": "systemd'yi yeniden yükleyin ve Ollama'yı yeniden başlatın",
+ "systemd": "ollama hizmetini düzenlemek için systemd'yi çağırın:"
+ },
+ "macos": "Lütfen 'Terminal' uygulamasını açın, aşağıdaki komutu yapıştırın ve çalıştırmak için Enter tuşuna basın",
+ "reboot": "İşlem tamamlandıktan sonra Ollama hizmetini yeniden başlatın",
+ "title": "Ollama'nın çapraz alan erişimine izin vermek için yapılandırma",
+ "windows": "Windows'ta, 'Denetim Masası'na tıklayın ve sistem ortam değişkenlerini düzenleyin. Kullanıcı hesabınız için 'OLLAMA_ORIGINS' adında bir ortam değişkeni oluşturun, değeri * olarak ayarlayın ve 'Tamam/Uygula'ya tıklayarak kaydedin."
+ },
+ "install": {
+ "description": "Lütfen Ollama'nın açık olduğundan emin olun, eğer Ollama'yı indirmediyseniz, lütfen resmi web sitesinden <1>indirin1>",
+ "docker": "Eğer Docker kullanmayı tercih ediyorsanız, Ollama'nın resmi Docker imajı da mevcuttur, aşağıdaki komutla çekebilirsiniz:",
+ "linux": {
+ "command": "Aşağıdaki komutla kurulum yapın:",
+ "manual": "Alternatif olarak, <1>Linux Manuel Kurulum Kılavuzu1>'na başvurarak kendiniz de kurulum yapabilirsiniz."
+ },
+ "title": "Ollama uygulamasını yerel olarak kurun ve başlatın",
+ "windowsTab": "Windows (önizleme sürümü)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Derin düşünme aşamasında...",
+ "thought": "Derinlemesine düşündüm (geçen süre {{duration}} saniye)",
+ "thoughtWithDuration": "Derinlemesine düşündüm"
}
}
diff --git a/DigitalHumanWeb/locales/tr-TR/discover.json b/DigitalHumanWeb/locales/tr-TR/discover.json
index 0896540..d75758a 100644
--- a/DigitalHumanWeb/locales/tr-TR/discover.json
+++ b/DigitalHumanWeb/locales/tr-TR/discover.json
@@ -126,6 +126,10 @@
"title": "Konu Tazeliği"
},
"range": "Aralık",
+ "reasoning_effort": {
+ "desc": "Bu ayar, modelin yanıt üretmeden önceki akıl yürütme gücünü kontrol etmek için kullanılır. Düşük güç, yanıt hızını önceliklendirir ve Token tasarrufu sağlar; yüksek güç ise daha kapsamlı bir akıl yürütme sunar, ancak daha fazla Token tüketir ve yanıt hızını düşürür. Varsayılan değer orta seviyedir, akıl yürütme doğruluğu ile yanıt hızı arasında bir denge sağlar.",
+ "title": "Akıl Yürütme Gücü"
+ },
"temperature": {
"desc": "Bu ayar, modelin yanıtlarının çeşitliliğini etkiler. Daha düşük değerler daha öngörülebilir ve tipik yanıtlar verirken, daha yüksek değerler daha çeşitli ve nadir yanıtları teşvik eder. Değer 0 olarak ayarlandığında, model belirli bir girdi için her zaman aynı yanıtı verir.",
"title": "Rastgelelik"
diff --git a/DigitalHumanWeb/locales/tr-TR/error.json b/DigitalHumanWeb/locales/tr-TR/error.json
index 6f3f94c..3899d05 100644
--- a/DigitalHumanWeb/locales/tr-TR/error.json
+++ b/DigitalHumanWeb/locales/tr-TR/error.json
@@ -12,8 +12,14 @@
"retry": "Yeniden Yükle",
"title": "Sayfa bir sorunla karşılaştı.."
},
- "fetchError": "İstek başarısız oldu",
- "fetchErrorDetail": "Hata detayı",
+ "fetchError": {
+ "detail": "Hata Detayı",
+ "title": "İstek Başarısız"
+ },
+ "loginRequired": {
+ "desc": "Otomatik olarak giriş sayfasına yönlendirileceksiniz",
+ "title": "Lütfen bu özelliği kullanmadan önce giriş yapın"
+ },
"notFound": {
"backHome": "Ana Sayfaya Dön",
"check": "Lütfen URL'nizin doğru olduğundan emin olun",
@@ -51,22 +57,34 @@
"431": "Üzgünüz, istek başlık alanı çok büyük, sunucu işleyemiyor",
"451": "Üzgünüz, yasal nedenlerle sunucu bu kaynağı sağlamayı reddediyor",
"500": "Üzgünüm, sunucu bazı zorluklar yaşıyor ve geçici olarak isteğinizi tamamlayamıyor. Lütfen daha sonra tekrar deneyin.",
+ "501": "Üzgünüm, sunucu bu isteği nasıl işleyeceğini henüz bilmiyor, lütfen işleminizin doğru olduğundan emin olun",
"502": "Üzgünüm, sunucu kayboldu ve geçici olarak hizmet veremiyor. Lütfen daha sonra tekrar deneyin.",
"503": "Üzgünüm, sunucu şu anda isteğinizi işleyemiyor, muhtemelen aşırı yüklenme veya bakım nedeniyle. Lütfen daha sonra tekrar deneyin.",
"504": "Üzgünüm, sunucu yukarı akış sunucusundan bir yanıt alamadı. Lütfen daha sonra tekrar deneyin.",
+ "505": "Üzgünüm, sunucu kullandığınız HTTP sürümünü desteklemiyor, lütfen güncelleyip tekrar deneyin",
+ "506": "Üzgünüm, sunucu yapılandırmasında bir sorun var, lütfen çözüm için yöneticinizle iletişime geçin",
+ "507": "Üzgünüm, sunucunun depolama alanı yetersiz, isteğinizi işleyemiyor, lütfen daha sonra tekrar deneyin",
+ "509": "Üzgünüm, sunucunun bant genişliği tükendi, lütfen daha sonra tekrar deneyin",
+ "510": "Üzgünüm, sunucu isteğinizi genişletme işlevini desteklemiyor, lütfen yöneticinizle iletişime geçin",
+ "524": "Üzgünüm, sunucu yanıt beklerken zaman aşımına uğradı, bu muhtemelen yanıtın çok yavaş olmasından kaynaklanıyor, lütfen daha sonra tekrar deneyin",
"AgentRuntimeError": "Lobe dil modeli çalışma zamanı hatası, lütfen aşağıdaki bilgilere göre sorunu gidermeye çalışın veya tekrar deneyin",
+ "ConnectionCheckFailed": "İstek boş döndü, lütfen API代理地址ının sonuna `/v1` ekleyip eklemediğinizi kontrol edin.",
+ "ExceededContextWindow": "Mevcut istek içeriği modelin işleyebileceği uzunluğu aşıyor, lütfen içerik miktarını azaltıp tekrar deneyin",
"FreePlanLimit": "Şu anda ücretsiz bir kullanıcısınız, bu özelliği kullanamazsınız. Lütfen devam etmek için bir ücretli plana yükseltin.",
+ "InsufficientQuota": "Üzgünüm, bu anahtarın kotası (quota) dolmuş durumda, lütfen hesap bakiyenizi kontrol edin veya anahtar kotasını artırdıktan sonra tekrar deneyin",
"InvalidAccessCode": "Geçersiz Erişim Kodu: Geçersiz veya boş bir şifre girdiniz. Lütfen doğru erişim şifresini girin veya özel API Anahtarı ekleyin.",
"InvalidBedrockCredentials": "Bedrock kimlik doğrulaması geçersiz, lütfen AccessKeyId/SecretAccessKey bilgilerinizi kontrol edip tekrar deneyin",
"InvalidClerkUser": "Üzgünüz, şu anda giriş yapmadınız. Lütfen işlemlere devam etmeden önce giriş yapın veya hesap oluşturun",
"InvalidGithubToken": "Github Kişisel Erişim Token'ı hatalı veya boş. Lütfen Github Kişisel Erişim Token'ınızı kontrol edin ve tekrar deneyin.",
"InvalidOllamaArgs": "Ollama yapılandırması yanlış, lütfen Ollama yapılandırmasını kontrol edip tekrar deneyin",
"InvalidProviderAPIKey": "{{provider}} API Anahtarı geçersiz veya boş, lütfen {{provider}} API Anahtarını kontrol edip tekrar deneyin",
+ "InvalidVertexCredentials": "Vertex kimlik doğrulaması başarısız oldu, lütfen kimlik bilgilerinizi kontrol edip tekrar deneyin",
"LocationNotSupportError": "Üzgünüz, bulunduğunuz konum bu model hizmetini desteklemiyor, muhtemelen bölge kısıtlamaları veya hizmetin henüz açılmamış olması nedeniyle. Lütfen mevcut konumun bu hizmeti kullanmaya uygun olup olmadığını doğrulayın veya başka bir konum bilgisi kullanmayı deneyin.",
+ "ModelNotFound": "Üzgünüm, ilgili modele erişim sağlanamadı, model mevcut olmayabilir veya erişim izni yoktur. Lütfen API Anahtarınızı değiştirin veya erişim izinlerinizi ayarladıktan sonra tekrar deneyin.",
"NoOpenAIAPIKey": "OpenAI API Anahtarı boş, lütfen özel bir OpenAI API Anahtarı ekleyin",
"OllamaBizError": "Ollama servisine yapılan istekte hata oluştu, lütfen aşağıdaki bilgilere göre sorunu gidermeye çalışın veya tekrar deneyin",
"OllamaServiceUnavailable": "Ollama servisi kullanılamıyor, lütfen Ollama'nın düzgün çalışıp çalışmadığını kontrol edin veya Ollama'nın çapraz kaynak yapılandırmasının doğru olup olmadığını kontrol edin",
- "OpenAIBizError": "OpenAI hizmetinde bir hata oluştu, lütfen aşağıdaki bilgilere göre sorunu giderin veya tekrar deneyin",
+ "PermissionDenied": "Üzgünüm, bu hizmete erişim izniniz yok. Lütfen anahtarınızın erişim iznine sahip olup olmadığını kontrol edin.",
"PluginApiNotFound": "Üzgünüm, eklentinin bildiriminde API mevcut değil. Lütfen istek yönteminizin eklenti bildirim API'sı ile eşleşip eşleşmediğini kontrol edin",
"PluginApiParamsError": "Üzgünüm, eklenti isteği için giriş parametre doğrulaması başarısız oldu. Lütfen giriş parametrelerinin API açıklamasıyla eşleşip eşleşmediğini kontrol edin",
"PluginFailToTransformArguments": "Özür dilerim, eklenti çağrı parametrelerini dönüştürme başarısız oldu, lütfen yardımcı mesajı yeniden oluşturmayı deneyin veya daha güçlü bir AI modeli olan Tools Calling'i değiştirip tekrar deneyin",
@@ -81,8 +99,11 @@
"PluginServerError": "Eklenti sunucusu isteği bir hata ile döndü. Lütfen aşağıdaki hata bilgilerine dayanarak eklenti bildirim dosyanızı, eklenti yapılandırmanızı veya sunucu uygulamanızı kontrol edin",
"PluginSettingsInvalid": "Bu eklenti, kullanılmadan önce doğru şekilde yapılandırılmalıdır. Lütfen yapılandırmanızın doğru olup olmadığını kontrol edin",
"ProviderBizError": "Talep {{provider}} hizmetinde bir hata oluştu, lütfen aşağıdaki bilgilere göre sorunu giderin veya tekrar deneyin",
+ "QuotaLimitReached": "Üzgünüz, mevcut Token kullanımı veya istek sayısı bu anahtarın kota (quota) sınırına ulaştı. Lütfen bu anahtarın kotasını artırın veya daha sonra tekrar deneyin.",
"StreamChunkError": "Akış isteği mesaj parçası çözümleme hatası, lütfen mevcut API arayüzünün standartlara uygun olup olmadığını kontrol edin veya API sağlayıcınızla iletişime geçin.",
- "SubscriptionPlanLimit": "Abonelik kotası tükenmiş, bu özelliği kullanamazsınız. Lütfen daha yüksek bir plana yükseltin veya kaynak paketi satın alarak devam edin.",
+ "SubscriptionKeyMismatch": "Üzgünüz, sistemdeki geçici bir arıza nedeniyle mevcut abonelik kullanımınız geçici olarak devre dışı kalmıştır. Lütfen aşağıdaki düğmeye tıklayarak aboneliğinizi geri yükleyin veya destek almak için bizimle iletişime geçin.",
+ "SubscriptionPlanLimit": "Abonelik puanlarınız tükenmiştir, bu özelliği kullanamazsınız. Lütfen daha yüksek bir plana geçin veya özel model API'sini yapılandırarak devam edin.",
+ "SystemTimeNotMatchError": "Üzgünüm, sistem saatiniz ile sunucu arasında bir uyumsuzluk var, lütfen sistem saatinizi kontrol edip tekrar deneyin",
"UnknownChatFetchError": "Üzgünüm, bilinmeyen bir istek hatasıyla karşılaştık. Lütfen aşağıdaki bilgileri kontrol edin veya tekrar deneyin."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/tr-TR/metadata.json b/DigitalHumanWeb/locales/tr-TR/metadata.json
index 66892ae..1f71c96 100644
--- a/DigitalHumanWeb/locales/tr-TR/metadata.json
+++ b/DigitalHumanWeb/locales/tr-TR/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "{{appName}}'in yeni özelliklerini ve iyileştirmelerini sürekli takip edin",
+ "title": "Güncelleme Geçmişi"
+ },
"chat": {
"description": "{{appName}} size en iyi ChatGPT, Claude, Gemini, OLLaMA WebUI deneyimini sunar",
"title": "{{appName}}: Kişisel AI verimlilik aracı, kendinize daha akıllı bir zihin verin"
diff --git a/DigitalHumanWeb/locales/tr-TR/modelProvider.json b/DigitalHumanWeb/locales/tr-TR/modelProvider.json
index 26aeb8d..fa0ccc7 100644
--- a/DigitalHumanWeb/locales/tr-TR/modelProvider.json
+++ b/DigitalHumanWeb/locales/tr-TR/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Azure API sürümü, YYYY-AA-GG formatına uymaktadır, [en son sürümü](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions) kontrol edin",
+ "fetch": "Listeyi al",
+ "title": "Azure API Sürümü"
+ },
+ "endpoint": {
+ "desc": "Azure AI proje özetinden Azure AI model çıkarım uç noktasını bulun",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AI Uç Noktası"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Azure AI proje özetinden API anahtarını bulun",
+ "placeholder": "Azure Anahtarı",
+ "title": "Anahtar"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "AWS Access Key Id girin",
@@ -51,6 +69,58 @@
"title": "Özel Bedrock Kimlik Bilgilerini Kullan"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Lütfen doldurun Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Cloudflare hesabınızın ID'sini veya özel API adresinizi girin",
+ "placeholder": "Cloudflare Hesap ID / Özel API Adresi",
+ "title": "Cloudflare Hesap ID / API Adresi"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Lütfen API Anahtarınızı girin",
+ "title": "API Anahtarı"
+ },
+ "basicTitle": "Temel Bilgiler",
+ "configTitle": "Yapılandırma Bilgileri",
+ "confirm": "Yeni Oluştur",
+ "createSuccess": "Başarıyla oluşturuldu",
+ "description": {
+ "placeholder": "Hizmet sağlayıcı tanımı (isteğe bağlı)",
+ "title": "Hizmet Sağlayıcı Tanımı"
+ },
+ "id": {
+ "desc": "Hizmet sağlayıcının benzersiz kimliği, oluşturulduktan sonra değiştirilemez",
+ "format": "Sadece rakamlar, küçük harfler, tire (-) ve alt çizgi (_) içerebilir",
+ "placeholder": "Küçük harflerle yazılması önerilir, örneğin openai, oluşturduktan sonra değiştirilemez",
+ "required": "Lütfen hizmet sağlayıcı ID'sini girin",
+ "title": "Hizmet Sağlayıcı ID"
+ },
+ "logo": {
+ "required": "Lütfen geçerli bir hizmet sağlayıcı logosu yükleyin",
+ "title": "Hizmet Sağlayıcı Logosu"
+ },
+ "name": {
+ "placeholder": "Lütfen hizmet sağlayıcının gösterim adını girin",
+ "required": "Lütfen hizmet sağlayıcı adını girin",
+ "title": "Hizmet Sağlayıcı Adı"
+ },
+ "proxyUrl": {
+ "required": "Lütfen proxy adresini girin",
+ "title": "Proxy Adresi"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Lütfen SDK türünü seçin",
+ "title": "İstek Formatı"
+ },
+ "title": "Özel AI Hizmet Sağlayıcısı Oluştur"
+ },
"github": {
"personalAccessToken": {
"desc": "Github PAT'nizi girin, [buraya](https://github.com/settings/tokens) tıklayarak oluşturun",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "HuggingFace Token'inizi buraya girin, [buraya](https://huggingface.co/settings/tokens) tıklayarak oluşturun",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace Token"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Hizmet sağlayıcı devre dışı",
+ "enabled": "Hizmet sağlayıcı etkin"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Özel Hizmet Sağlayıcı Ekle",
+ "all": "Tümü",
+ "list": {
+ "disabled": "Devre Dışı",
+ "enabled": "Aktif"
+ },
+ "notFound": "Arama sonuçları bulunamadı",
+ "searchProviders": "Hizmet sağlayıcıları ara...",
+ "sort": "Özel Sıralama"
+ },
"ollama": {
"checker": {
"desc": "Proxy adresinin doğru girilip girilmediğini test edin",
@@ -75,33 +169,9 @@
"title": "正在下载模型 {{model}} "
},
"endpoint": {
- "desc": "Ollama arayüz proxy adresini girin, yerel olarak belirtilmemişse boş bırakılabilir",
+ "desc": "http(s):// içermelidir, yerel olarak belirtilmemişse boş bırakılabilir",
"title": "Arayüz Proxy Adresi"
},
- "setup": {
- "cors": {
- "description": "Ollama'nın normal şekilde çalışabilmesi için, tarayıcı güvenlik kısıtlamaları nedeniyle Ollama'nın çapraz kaynak isteklerine izin verilmesi gerekmektedir.",
- "linux": {
- "env": "[Service] bölümüne `Environment` ekleyerek OLLAMA_ORIGINS ortam değişkenini ekleyin:",
- "reboot": "systemd'yi yeniden yükleyin ve Ollama'yı yeniden başlatın",
- "systemd": "systemd'yi çağırarak ollama servisini düzenleyin:"
- },
- "macos": "Lütfen 'Terminal' uygulamasını açın ve aşağıdaki komutu yapıştırıp Enter tuşuna basın",
- "reboot": "Komut tamamlandıktan sonra Ollama servisini yeniden başlatın",
- "title": "Ollama'nın çapraz kaynak erişimine izin vermek için yapılandırma",
- "windows": "Windows'ta, 'Control Panel'ı tıklayarak sistem ortam değişkenlerini düzenleyin. Kullanıcı hesabınıza * değerinde 'OLLAMA_ORIGINS' adında bir ortam değişkeni oluşturun ve 'OK/Apply' düğmesine tıklayarak kaydedin"
- },
- "install": {
- "description": "Ollama'nın açık olduğundan emin olun. Ollama'yı indirmediyseniz, lütfen resmi web sitesine giderek <1>indirin1>.",
- "docker": "Docker kullanmayı tercih ediyorsanız, Ollama resmi Docker görüntüsünü aşağıdaki komutla çekebilirsiniz:",
- "linux": {
- "command": "Aşağıdaki komutları kullanarak yükleyin:",
- "manual": "Ya da, <1>Linux için el ile kurulum kılavuzuna1> bakarak kendiniz kurabilirsiniz"
- },
- "title": "Yerel olarak Ollama uygulamasını kurun ve başlatın",
- "windowsTab": "Windows (Önizleme)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "取消下载",
@@ -112,6 +182,156 @@
"title": "下载指定的 Ollama 模型"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "Anahtarınız ve proxy adresi gibi bilgiler <1>AES-GCM1> şifreleme algoritması ile şifrelenecektir",
+ "apiKey": {
+ "desc": "{{name}} API Anahtarınızı girin",
+ "placeholder": "{{name}} API Anahtarı",
+ "title": "API Anahtarı"
+ },
+ "baseURL": {
+ "desc": "http(s):// içermelidir",
+ "invalid": "Lütfen geçerli bir URL girin",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API Proxy Adresi"
+ },
+ "checker": {
+ "button": "Kontrol Et",
+ "desc": "API Anahtarı ve proxy adresinin doğru girilip girilmediğini test edin",
+ "pass": "Kontrol başarılı",
+ "title": "Bağlantı Kontrolü"
+ },
+ "fetchOnClient": {
+ "desc": "İstemci istek modu, tarayıcıdan doğrudan oturum isteği başlatır, yanıt hızını artırabilir",
+ "title": "İstemci İstek Modunu Kullan"
+ },
+ "helpDoc": "Yapılandırma Kılavuzu",
+ "waitingForMore": "Daha fazla model <1>planlanıyor1>, lütfen bekleyin"
+ },
+ "createNew": {
+ "title": "Özel AI Modeli Oluştur"
+ },
+ "item": {
+ "config": "Modeli Yapılandır",
+ "customModelCards": {
+ "addNew": "{{id}} modelini oluştur ve ekle",
+ "confirmDelete": "Bu özel modeli silmek üzeresiniz, silindikten sonra geri alınamaz, lütfen dikkatli olun."
+ },
+ "delete": {
+ "confirm": "{{displayName}} modelini silmek istediğinize emin misiniz?",
+ "success": "Silme işlemi başarılı",
+ "title": "Modeli Sil"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Azure OpenAI'de gerçek istek için alan",
+ "placeholder": "Lütfen Azure'daki model dağıtım adını girin",
+ "title": "Model Dağıtım Adı"
+ },
+ "deployName": {
+ "extra": "Bu alan, isteği gönderirken model kimliği olarak kullanılacaktır",
+ "placeholder": "Modelin gerçek dağıtım adını veya kimliğini girin",
+ "title": "Model Dağıtım Adı"
+ },
+ "displayName": {
+ "placeholder": "Lütfen modelin gösterim adını girin, örneğin ChatGPT, GPT-4 vb.",
+ "title": "Model Gösterim Adı"
+ },
+ "files": {
+ "extra": "Mevcut dosya yükleme uygulaması yalnızca bir Hack çözümüdür, yalnızca denemek için geçerlidir. Tam dosya yükleme yeteneği için lütfen sonraki uygulamayı bekleyin.",
+ "title": "Dosya Yüklemeyi Destekle"
+ },
+ "functionCall": {
+ "extra": "Bu yapılandırma, modelin araçları kullanma yeteneğini açacak ve böylece modele araç sınıfı eklentileri eklenebilecektir. Ancak, gerçek araç kullanımı tamamen modele bağlıdır, kullanılabilirliğini kendiniz test etmelisiniz.",
+ "title": "Araç kullanımını destekle"
+ },
+ "id": {
+ "extra": "Oluşturulduktan sonra değiştirilemez, AI çağrıldığında model kimliği olarak kullanılacaktır",
+ "placeholder": "Model kimliğini girin, örneğin gpt-4o veya claude-3.5-sonnet",
+ "title": "Model ID"
+ },
+ "modalTitle": "Özel Model Yapılandırması",
+ "reasoning": {
+ "extra": "Bu yapılandırma yalnızca modelin derin düşünme yeteneğini açacaktır, belirli etkiler tamamen modelin kendisine bağlıdır, lütfen bu modelin kullanılabilir derin düşünme yeteneğine sahip olup olmadığını kendiniz test edin",
+ "title": "Derin düşünmeyi destekler"
+ },
+ "tokens": {
+ "extra": "Modelin desteklediği maksimum Token sayısını ayarlayın",
+ "title": "Maksimum bağlam penceresi",
+ "unlimited": "Sınırsız"
+ },
+ "vision": {
+ "extra": "Bu yapılandırma yalnızca uygulamadaki resim yükleme yapılandırmasını açacaktır, tanıma desteği tamamen modele bağlıdır, lütfen bu modelin görsel tanıma yeteneğini test edin.",
+ "title": "Görsel Tanımayı Destekle"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/Resim",
+ "inputCharts": "${{amount}}/M Karakter",
+ "inputMinutes": "${{amount}}/Dakika",
+ "inputTokens": "Girdi ${{amount}}/M",
+ "outputTokens": "Çıktı ${{amount}}/M"
+ },
+ "releasedAt": "Yayınlanma tarihi: {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Model Ekle",
+ "disabled": "Devre dışı",
+ "disabledActions": {
+ "showMore": "Hepsini Göster"
+ },
+ "empty": {
+ "desc": "Lütfen özel bir model oluşturun veya kullanmaya başlamadan önce bir model çekin",
+ "title": "Kullanılabilir model yok"
+ },
+ "enabled": "Etkin",
+ "enabledActions": {
+ "disableAll": "Hepsini devre dışı bırak",
+ "enableAll": "Hepsini etkinleştir",
+ "sort": "Özel model sıralaması"
+ },
+ "enabledEmpty": "Etkin model yok, lütfen aşağıdaki listeden beğendiğiniz modeli etkinleştirin~",
+ "fetcher": {
+ "clear": "Alınan modelleri temizle",
+ "fetch": "Model listesini al",
+ "fetching": "Model listesi alınıyor...",
+ "latestTime": "Son güncelleme zamanı: {{time}}",
+ "noLatestTime": "Henüz liste alınmadı"
+ },
+ "resetAll": {
+ "conform": "Mevcut modelin tüm değişikliklerini sıfırlamak istediğinize emin misiniz? Sıfırladıktan sonra mevcut model listesi varsayılan duruma dönecektir.",
+ "success": "Sıfırlama başarılı",
+ "title": "Tüm değişiklikleri sıfırla"
+ },
+ "search": "Model ara...",
+ "searchResult": "{{count}} model bulundu",
+ "title": "Model Listesi",
+ "total": "Toplam {{count}} adet model mevcut"
+ },
+ "searchNotFound": "Arama sonuçları bulunamadı"
+ },
+ "sortModal": {
+ "success": "Sıralama güncellemesi başarılı",
+ "title": "Özel Sıralama",
+ "update": "Güncelle"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Bu AI hizmet sağlayıcısını silmek üzeresiniz, silindikten sonra geri alınamaz, silmek istediğinize emin misiniz?",
+ "deleteSuccess": "Silme işlemi başarılı",
+ "tooltip": "Hizmet sağlayıcının temel yapılandırmasını güncelle",
+ "updateSuccess": "Güncelleme başarılı"
+ },
+ "updateCustomAiProvider": {
+ "title": "Özel AI Sağlayıcı Yapılandırmasını Güncelle"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Vertex AI Anahtarlarınızı buraya girin",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI Anahtarları"
+ }
+ },
"zeroone": {
"title": "01.AI Sıfır Bir"
},
diff --git a/DigitalHumanWeb/locales/tr-TR/models.json b/DigitalHumanWeb/locales/tr-TR/models.json
index 3490407..686cfc5 100644
--- a/DigitalHumanWeb/locales/tr-TR/models.json
+++ b/DigitalHumanWeb/locales/tr-TR/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, zengin eğitim örnekleri ile endüstri uygulamalarında üstün performans sunar."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat, Yi-1.5 serisinin bir varyantıdır ve açık kaynaklı bir sohbet modelidir. Yi-1.5, 500B yüksek kaliteli veri üzerinde sürekli olarak önceden eğitilmiş ve 3M çeşitlendirilmiş ince ayar örnekleri ile ince ayar yapılmıştır. Yi'ye kıyasla, Yi-1.5, kodlama, matematik, akıl yürütme ve talimat takibi yeteneklerinde daha güçlü performans sergilemekte, aynı zamanda mükemmel dil anlama, genel bilgi akıl yürütme ve okuma anlama yeteneklerini korumaktadır. Bu model, 4K, 16K ve 32K bağlam uzunluğu versiyonlarına sahiptir ve toplam önceden eğitim miktarı 3.6T token'a ulaşmaktadır."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B, 16K Token desteği sunar, etkili ve akıcı dil oluşturma yeteneği sağlar."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Everything, en son açık kaynak ince ayar modelidir, 34 milyar parametreye sahiptir, ince ayar çeşitli diyalog senaryolarını destekler, yüksek kaliteli eğitim verileri ile insan tercihleri ile hizalanmıştır."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Everything, en son açık kaynak ince ayar modelidir, 9 milyar parametreye sahiptir, ince ayar çeşitli diyalog senaryolarını destekler, yüksek kaliteli eğitim verileri ile insan tercihleri ile hizalanmıştır."
+ },
"360gpt-pro": {
"description": "360GPT Pro, 360 AI model serisinin önemli bir üyesi olarak, çeşitli doğal dil uygulama senaryolarını karşılamak için etkili metin işleme yeteneği sunar, uzun metin anlama ve çoklu diyalog gibi işlevleri destekler."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K, anlam güvenliği ve sorumluluk odaklılığı vurgular, içerik güvenliği konusunda yüksek gereksinimlere sahip uygulama senaryoları için tasarlanmıştır, kullanıcı deneyiminin doğruluğunu ve sağlamlığını garanti eder."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1, düşünce zincirini ağaç arama ile inşa eder ve yansıtma mekanizmasını entegre eder, pekiştirme öğrenimi ile eğitilir, model kendini yansıtma ve hata düzeltme yeteneğine sahiptir."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro, 360 şirketi tarafından sunulan yüksek düzeyde doğal dil işleme modelidir, mükemmel metin oluşturma ve anlama yeteneğine sahiptir, özellikle oluşturma ve yaratma alanında olağanüstü performans gösterir, karmaşık dil dönüşümleri ve rol canlandırma görevlerini işleyebilir."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1, düşünce zincirini oluşturmak için ağaç araması kullanır ve yansıtma mekanizmasını entegre eder, pekiştirme öğrenimi ile eğitilir, model kendini yansıtma ve hata düzeltme yeteneğine sahiptir."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra, Xinghuo büyük model serisinin en güçlü versiyonudur, çevrimiçi arama bağlantısını yükseltirken, metin içeriğini anlama ve özetleme yeteneğini artırır. Ofis verimliliğini artırmak ve taleplere doğru yanıt vermek için kapsamlı bir çözüm sunar, sektördeki akıllı ürünlerin öncüsüdür."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Model yetenekleri ülke içinde birinci sırada, bilgi ansiklopedisi, uzun metinler, yaratıcı üretim gibi Çince görevlerde yurtdışındaki önde gelen modelleri geride bırakmaktadır. Ayrıca, sektör lideri çok modlu yeteneklere sahiptir ve birçok yetkili değerlendirme kriterinde mükemmel performans göstermektedir."
},
+ "Baichuan4-Air": {
+ "description": "Model yetenekleri ülke içinde birinci, bilgi ansiklopedisi, uzun metinler, yaratıcı üretim gibi Çince görevlerde uluslararası ana akım modelleri aşmaktadır. Ayrıca, sektörde lider çok modlu yeteneklere sahip olup, birçok yetkili değerlendirme ölçütünde mükemmel performans sergilemektedir."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Model yetenekleri ülke içinde birinci, bilgi ansiklopedisi, uzun metinler, yaratıcı üretim gibi Çince görevlerde uluslararası ana akım modelleri aşmaktadır. Ayrıca, sektörde lider çok modlu yeteneklere sahip olup, birçok yetkili değerlendirme ölçütünde mükemmel performans sergilemektedir."
+ },
+ "DeepSeek-R1": {
+ "description": "En gelişmiş verimli LLM, akıl yürütme, matematik ve programlama konularında uzmandır."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 - DeepSeek setindeki daha büyük ve daha akıllı model - Llama 70B mimarisine damıtılmıştır. Kıyaslamalar ve insan değerlendirmelerine dayanarak, bu model orijinal Llama 70B'den daha akıllıdır, özellikle matematik ve gerçeklik doğruluğu gerektiren görevlerde mükemmel performans göstermektedir."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Qwen2.5-Math-1.5B temel alınarak oluşturulmuş DeepSeek-R1 damıtma modeli, pekiştirme öğrenimi ve soğuk başlatma verileri ile çıkarım performansını optimize eder, açık kaynak model çoklu görev standartlarını yeniler."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Qwen2.5-14B temel alınarak oluşturulmuş DeepSeek-R1 damıtma modeli, pekiştirme öğrenimi ve soğuk başlatma verileri ile çıkarım performansını optimize eder, açık kaynak model çoklu görev standartlarını yeniler."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1 serisi, pekiştirme öğrenimi ve soğuk başlatma verileri ile çıkarım performansını optimize eder, açık kaynak model çoklu görev standartlarını yeniler, OpenAI-o1-mini seviyesini aşar."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Qwen2.5-Math-7B temel alınarak oluşturulmuş DeepSeek-R1 damıtma modeli, pekiştirme öğrenimi ve soğuk başlatma verileri ile çıkarım performansını optimize eder, açık kaynak model çoklu görev standartlarını yeniler."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro, tamamen yenilenen çok modlu büyük modeldir, herhangi bir çözünürlük ve aşırı en-boy oranına sahip görüntü tanıma desteği sunar, görsel akıl yürütme, belge tanıma, detay bilgisi anlama ve talimatları takip etme yeteneklerini artırır."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite, mükemmel yanıt hızı ve daha iyi maliyet Performansı ile müşterilere farklı senaryolar için daha esnek seçenekler sunar. 128k bağlam penceresi çıkarım ve ince ayar destekler."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite, mükemmel yanıt hızı ve daha iyi maliyet Performansı ile müşterilere farklı senaryolar için daha esnek seçenekler sunar. 32k bağlam penceresi çıkarım ve ince ayar destekler."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite, mükemmel yanıt hızı ve daha iyi maliyet Performansı ile müşterilere farklı senaryolar için daha esnek seçenekler sunar. 4k bağlam penceresi çıkarım ve ince ayar destekler."
+ },
+ "Doubao-pro-128k": {
+ "description": "En iyi performans gösteren ana model, karmaşık görevleri işlemek için uygundur; referanslı soru-cevap, özetleme, yaratım, metin sınıflandırma, rol yapma gibi senaryolar için iyi sonuçlar verir. 128k bağlam penceresi çıkarım ve ince ayar destekler."
+ },
+ "Doubao-pro-256k": {
+ "description": "En iyi performansa sahip ana modeldir, karmaşık görevleri işlemek için uygundur, referans cevaplama, özetleme, yaratım, metin sınıflandırma, rol oynama gibi senaryolarda oldukça iyi sonuçlar vermektedir. 256k bağlam penceresi ile akıl yürütme ve ince ayar desteği sunmaktadır."
+ },
+ "Doubao-pro-32k": {
+ "description": "En iyi performans gösteren ana model, karmaşık görevleri işlemek için uygundur; referanslı soru-cevap, özetleme, yaratım, metin sınıflandırma, rol yapma gibi senaryolar için iyi sonuçlar verir. 32k bağlam penceresi çıkarım ve ince ayar destekler."
+ },
+ "Doubao-pro-4k": {
+ "description": "En iyi performans gösteren ana model, karmaşık görevleri işlemek için uygundur; referanslı soru-cevap, özetleme, yaratım, metin sınıflandırma, rol yapma gibi senaryolar için iyi sonuçlar verir. 4k bağlam penceresi çıkarım ve ince ayar destekler."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Doubao-vision modeli, Doubao tarafından sunulan çok modlu büyük modeldir, güçlü görüntü anlama ve akıl yürütme yeteneklerine sahip olup, kesin talimat anlama yeteneği sunmaktadır. Model, görüntü metin bilgisi çıkarımı ve görüntü tabanlı akıl yürütme görevlerinde güçlü bir performans sergilemekte, daha karmaşık ve daha geniş görsel soru-cevap görevlerine uygulanabilmektedir."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Doubao-vision modeli, Doubao tarafından sunulan çok modlu büyük modeldir, güçlü görüntü anlama ve akıl yürütme yeteneklerine sahip olup, kesin talimat anlama yeteneği sunmaktadır. Model, görüntü metin bilgisi çıkarımı ve görüntü tabanlı akıl yürütme görevlerinde güçlü bir performans sergilemekte, daha karmaşık ve daha geniş görsel soru-cevap görevlerine uygulanabilmektedir."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Baidu'nun kendi geliştirdiği, büyük ölçekli bir dil modeli olan ERNIE-3.5, geniş bir Çin ve İngilizce veri kümesini kapsar. Güçlü genel yeteneklere sahip olup, çoğu diyalog, soru-cevap, yaratıcı içerik üretimi ve eklenti uygulama senaryolarını karşılayabilir; ayrıca, Baidu arama eklentisi ile otomatik entegrasyonu destekleyerek, soru-cevap bilgilerinin güncelliğini sağlar."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Baidu'nun kendi geliştirdiği, büyük ölçekli bir dil modeli olan ERNIE-3.5, geniş bir Çin ve İngilizce veri kümesini kapsar. Güçlü genel yeteneklere sahip olup, çoğu diyalog, soru-cevap, yaratıcı içerik üretimi ve eklenti uygulama senaryolarını karşılayabilir; ayrıca, Baidu arama eklentisi ile otomatik entegrasyonu destekleyerek, soru-cevap bilgilerinin güncelliğini sağlar."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Baidu'nun kendi geliştirdiği, büyük ölçekli bir dil modeli olan ERNIE-3.5, geniş bir Çin ve İngilizce veri kümesini kapsar. Güçlü genel yeteneklere sahip olup, çoğu diyalog, soru-cevap, yaratıcı içerik üretimi ve eklenti uygulama senaryolarını karşılayabilir; ayrıca, Baidu arama eklentisi ile otomatik entegrasyonu destekleyerek, soru-cevap bilgilerinin güncelliğini sağlar."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Baidu'nun kendi geliştirdiği amiral gemisi ultra büyük ölçekli dil modeli, ERNIE 3.5'e kıyasla model yeteneklerinde kapsamlı bir yükseltme gerçekleştirmiştir, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyonu destekler, yanıt bilgilerini güncel tutar."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Baidu'nun kendi geliştirdiği amiral gemisi ultra büyük ölçekli dil modeli, ERNIE 3.5'e kıyasla model yeteneklerinde kapsamlı bir yükseltme gerçekleştirmiştir, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyonu destekler, yanıt bilgilerini güncel tutar."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Baidu tarafından geliştirilen, geniş ölçekli büyük dil modeli, genel performansı mükemmeldir ve her alanda karmaşık görev sahneleri için geniş bir şekilde kullanılabilir; Baidu arama eklentisi ile otomatik entegrasyonu destekler, yanıt bilgi güncellemelerinin zamanlamasını güvence altına alır. ERNIE 4.0'a kıyasla, performans olarak daha üstündür."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Baidu'nun kendi geliştirdiği amiral gemisi ultra büyük ölçekli dil modeli, genel performansı mükemmel olup, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyonu destekler, yanıt bilgilerini güncel tutar. ERNIE 4.0'a kıyasla performans açısından daha üstündür."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Baidu'nun kendi geliştirdiği dikey senaryo büyük dil modeli, oyun NPC'leri, müşteri hizmetleri diyalogları, diyalog karakter rolü gibi uygulama senaryoları için uygundur, karakter tarzı daha belirgin ve tutarlıdır, talimatları takip etme yeteneği daha güçlüdür ve çıkarım performansı daha iyidir."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Baidu'nun kendi geliştirdiği hafif büyük dil modeli, mükemmel model performansı ve çıkarım yeteneklerini dengeler, ERNIE Lite'dan daha iyi sonuçlar verir, düşük hesaplama gücüne sahip AI hızlandırıcı kartları için uygundur."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Baidu'nun 2024 yılında piyasaya sürdüğü kendi geliştirdiği yüksek performanslı büyük dil modeli, genel yetenekleri mükemmel olup, belirli senaryo sorunlarını daha iyi işlemek için temel model olarak ince ayar yapmak için uygundur ve mükemmel çıkarım performansına sahiptir."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Baidu'nun 2024 yılında piyasaya sürdüğü kendi geliştirdiği yüksek performanslı büyük dil modeli, genel yetenekleri mükemmel olup, ERNIE Speed'den daha iyi sonuçlar verir, belirli senaryo sorunlarını daha iyi işlemek için temel model olarak ince ayar yapmak için uygundur ve mükemmel çıkarım performansına sahiptir."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B), çok alanlı uygulamalar ve karmaşık görevler için uygun yenilikçi bir modeldir."
},
- "Max-32k": {
- "description": "Spark Max 32K, büyük bağlam işleme yeteneği, daha güçlü bağlam anlama ve mantıksal akıl yürütme yeteneği ile donatılmıştır. 32K token'lık metin girişi destekler ve uzun belgelerin okunması, özel bilgi sorgulamaları gibi senaryolar için uygundur."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B, güçlü bir görsel dil modelidir. Görüntü ve metinlerin çok modlu işlenmesini destekler, görüntü içeriğini hassas bir şekilde tanıyabilir ve ilgili açıklamalar veya yanıtlar üretebilir."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B, güçlü bir görsel dil modelidir. Görüntü ve metinlerin çok modlu işlenmesini destekler, görüntü içeriğini hassas bir şekilde tanıyabilir ve ilgili açıklamalar veya yanıtlar üretebilir."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Yüksek çözünürlüklü görüntülerde mükemmel görüntü akıl yürütme yeteneği, görsel anlama uygulamaları için uygundur."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Görsel anlama ajan uygulamaları için gelişmiş görüntü akıl yürütme yeteneği."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct, Alibaba Cloud tarafından yayınlanan en son büyük dil modeli serilerinden biridir. Bu 72B modeli, kodlama ve matematik gibi alanlarda önemli ölçüde geliştirilmiş yeteneklere sahiptir. Model ayrıca, Çince, İngilizce gibi 29'dan fazla dili kapsayan çok dilli destek sunmaktadır. Model, talimat takibi, yapılandırılmış verileri anlama ve yapılandırılmış çıktı (özellikle JSON) üretme konularında önemli iyileştirmeler göstermektedir."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct, Alibaba Cloud tarafından yayınlanan en son büyük dil modeli serilerinden biridir. Bu 7B modeli, kodlama ve matematik gibi alanlarda önemli ölçüde geliştirilmiş yeteneklere sahiptir. Model ayrıca, Çince, İngilizce gibi 29'dan fazla dili kapsayan çok dilli destek sunmaktadır. Model, talimat takibi, yapılandırılmış verileri anlama ve yapılandırılmış çıktı (özellikle JSON) üretme konularında önemli iyileştirmeler göstermektedir."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Llama 3.1 talimat ayarlı metin modeli, çok dilli diyalog kullanım durumları için optimize edilmiştir ve birçok mevcut açık kaynak ve kapalı sohbet modelinde yaygın endüstri kıyaslamalarında mükemmel performans göstermektedir."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO, olağanüstü yaratıcı deneyimler sunmak için tasarlanmış son derece esnek bir çoklu model birleşimidir."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Llama 3.1 talimat ayarlı metin modeli, çok dilli diyalog kullanım durumları için optimize edilmiştir ve birçok mevcut açık kaynak ve kapalı sohbet modelinde yaygın endüstri kıyaslamalarında mükemmel performans göstermektedir."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Llama 3.1 talimat ayarlı metin modeli, çok dilli diyalog kullanım durumları için optimize edilmiştir ve birçok mevcut açık kaynak ve kapalı sohbet modelinde yaygın endüstri kıyaslamalarında mükemmel performans göstermektedir."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Gelişmiş, en son teknolojiye sahip küçük dil modeli, dil anlama, mükemmel akıl yürütme yeteneği ve metin oluşturma yeteneğine sahiptir."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Gelişmiş, en son teknolojiye sahip küçük dil modeli, dil anlama, mükemmel akıl yürütme yeteneği ve metin oluşturma yeteneğine sahiptir."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3, Llama serisinin en gelişmiş çok dilli açık kaynak büyük dil modelidir ve 405B modelinin performansını çok düşük maliyetle deneyimlemenizi sağlar. Transformer yapısına dayanmaktadır ve yararlılığını ve güvenliğini artırmak için denetimli ince ayar (SFT) ve insan geri bildirimi ile güçlendirilmiş öğrenme (RLHF) kullanılmıştır. Talimat ayarlı versiyonu çok dilli diyaloglar için optimize edilmiştir ve birçok endüstri kıyaslamasında birçok açık kaynak ve kapalı sohbet modelinden daha iyi performans göstermektedir. Bilgi kesim tarihi 2023 yılı Aralık ayıdır."
+ },
+ "MiniMax-Text-01": {
+ "description": "MiniMax-01 serisi modellerinde cesur yenilikler yaptık: ilk kez büyük ölçekli lineer dikkat mekanizmasını gerçekleştirdik, geleneksel Transformer mimarisi artık tek seçenek değil. Bu modelin parametre sayısı 456 milyara kadar çıkmakta, tek bir aktivasyonda 45.9 milyar. Modelin genel performansı, yurtdışındaki en iyi modellerle karşılaştırılabilirken, dünya genelinde 4 milyon token uzunluğundaki bağlamı verimli bir şekilde işleyebilir, bu da GPT-4o'nun 32 katı, Claude-3.5-Sonnet'in 20 katıdır."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B), karmaşık hesaplamalar için yüksek hassasiyetli bir talimat modelidir."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B), optimize edilmiş dil çıktısı ve çeşitli uygulama olasılıkları sunar."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Phi-3-mini modelinin yenilenmiş versiyonu."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2, belgelere ve grafiklere anlama, sahne metni anlama, OCR, bilimsel ve matematik soruları çözme gibi çeşitli görsel dil görevlerinde mükemmel performans sergilemiştir."
},
"Phi-3-medium-128k-instruct": {
"description": "Aynı Phi-3-medium modeli, ancak RAG veya az sayıda örnek isteme için daha büyük bir bağlam boyutuna sahiptir."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "7B parametreli bir model, Phi-3-mini'den daha iyi kalite sunar, yüksek kaliteli, akıl yürütme yoğun veriye odaklanır."
},
- "Pro-128k": {
- "description": "Spark Pro-128K, olağanüstü bağlam işleme yeteneği ile donatılmıştır, 128K'ya kadar bağlam bilgisi işleyebilir, özellikle uzun metin içeriklerinde bütünsel analiz ve uzun vadeli mantıksal bağlantı işleme gerektiren durumlar için uygundur, karmaşık metin iletişiminde akıcı ve tutarlı bir mantık ile çeşitli alıntı desteği sunar."
+ "Phi-3.5-mini-instruct": {
+ "description": "Phi-3-mini modelinin güncellenmiş versiyonu."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Phi-3-görsel modelinin güncellenmiş versiyonu."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2, belgelere ve grafiklere anlama, sahne metni anlama, OCR, bilimsel ve matematik soruları çözme gibi çeşitli görsel dil görevlerinde mükemmel performans sergilemiştir."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct, Qwen2 serisindeki talimat ince ayar büyük dil modelidir ve parametre ölçeği 1.5B'dir. Bu model, Transformer mimarisi temelinde, SwiGLU aktivasyon fonksiyonu, dikkat QKV önyargısı ve grup sorgu dikkati gibi teknikler kullanmaktadır. Dil anlama, üretim, çok dilli yetenek, kodlama, matematik ve akıl yürütme gibi birçok standart testte mükemmel performans sergilemekte ve çoğu açık kaynak modelini geride bırakmaktadır. Qwen1.5-1.8B-Chat ile karşılaştırıldığında, Qwen2-1.5B-Instruct, MMLU, HumanEval, GSM8K, C-Eval ve IFEval gibi testlerde belirgin bir performans artışı göstermektedir, parametre sayısı biraz daha az olmasına rağmen."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct, Qwen2 serisindeki talimat ince ayar büyük dil modelidir ve parametre ölçeği 7B'dir. Bu model, Transformer mimarisi temelinde, SwiGLU aktivasyon fonksiyonu, dikkat QKV önyargısı ve grup sorgu dikkati gibi teknikler kullanmaktadır. Büyük ölçekli girişleri işleyebilme yeteneğine sahiptir. Bu model, dil anlama, üretim, çok dilli yetenek, kodlama, matematik ve akıl yürütme gibi birçok standart testte mükemmel performans sergilemekte ve çoğu açık kaynak modelini geride bırakmakta, bazı görevlerde özel modellere karşı rekabet edebilir. Qwen2-7B-Instruct, birçok değerlendirmede Qwen1.5-7B-Chat'ten daha iyi performans göstermekte ve belirgin bir performans artışı sergilemektedir."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL, Qwen-VL modelinin en son yineleme versiyonudur ve görsel anlama kıyaslama testlerinde en gelişmiş performansı sergilemiştir."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct, Alibaba Cloud tarafından yayınlanan en son büyük dil modeli serilerinden biridir. Bu 7B modeli, kodlama ve matematik gibi alanlarda önemli ölçüde geliştirilmiş yeteneklere sahiptir. Model ayrıca, Çince, İngilizce gibi 29'dan fazla dili kapsayan çok dilli destek sunmaktadır. Model, talimat takibi, yapılandırılmış verileri anlama ve yapılandırılmış çıktı (özellikle JSON) üretme konularında önemli iyileştirmeler göstermektedir."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct, Alibaba Cloud tarafından yayınlanan kod odaklı büyük dil modeli serisinin en son versiyonudur. Bu model, Qwen2.5 temelinde, 5.5 trilyon token ile eğitilerek kod üretimi, akıl yürütme ve düzeltme yeteneklerini önemli ölçüde artırmıştır. Hem kodlama yeteneklerini geliştirmiş hem de matematik ve genel yetenek avantajlarını korumuştur. Model, kod akıllı ajanları gibi pratik uygulamalar için daha kapsamlı bir temel sunmaktadır."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat, Zhipu AI tarafından sunulan GLM-4 serisi önceden eğitilmiş modellerin açık kaynak versiyonudur. Bu model, anlam, matematik, akıl yürütme, kod ve bilgi gibi birçok alanda mükemmel performans sergilemektedir. Çoklu diyalogları desteklemenin yanı sıra, GLM-4-9B-Chat, web tarayıcı, kod yürütme, özelleştirilmiş araç çağrısı (Function Call) ve uzun metin akıl yürütme gibi gelişmiş özelliklere de sahiptir. Model, Çince, İngilizce, Japonca, Korece ve Almanca gibi 26 dili desteklemektedir. GLM-4-9B-Chat, AlignBench-v2, MT-Bench, MMLU ve C-Eval gibi birçok standart testte mükemmel performans sergilemiştir. Bu model, maksimum 128K bağlam uzunluğunu desteklemekte olup, akademik araştırmalar ve ticari uygulamalar için uygundur."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1, modeldeki tekrarlılık ve okunabilirlik sorunlarını çözen bir güçlendirilmiş öğrenme (RL) destekli çıkarım modelidir. RL'den önce, DeepSeek-R1 soğuk başlangıç verileri tanıtarak çıkarım performansını daha da optimize etmiştir. Matematik, kod ve çıkarım görevlerinde OpenAI-o1 ile benzer performans göstermektedir ve özenle tasarlanmış eğitim yöntemleri ile genel etkisini artırmıştır."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3, 6710 milyar parametreye sahip bir karma uzman (MoE) dil modelidir ve çok başlı potansiyel dikkat (MLA) ve DeepSeekMoE mimarisini kullanarak, yardımcı kayıplar olmadan yük dengeleme stratejileri ile çıkarım ve eğitim verimliliğini optimize etmektedir. 14.8 trilyon yüksek kaliteli token üzerinde önceden eğitilmiş ve denetimli ince ayar ve güçlendirilmiş öğrenme ile, DeepSeek-V3 performans açısından diğer açık kaynak modelleri geride bırakmakta ve lider kapalı kaynak modellere yaklaşmaktadır."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma, Google tarafından geliştirilen hafif, en son açık model serilerinden biridir. Bu, yalnızca kodlayıcıdan oluşan büyük bir dil modelidir ve İngilizceyi desteklemekte, açık ağırlıklar, önceden eğitilmiş varyantlar ve talimat ince ayar varyantları sunmaktadır. Gemma modeli, soru yanıtlama, özetleme ve akıl yürütme gibi çeşitli metin üretim görevleri için uygundur. Bu 9B modeli, 8 trilyon token ile eğitilmiştir. Göreceli olarak küçük boyutu, onu dizüstü bilgisayarlar, masaüstü bilgisayarlar veya kendi bulut altyapınız gibi kaynak sınırlı ortamlarda dağıtılabilir hale getirir ve daha fazla kişinin en son AI modellerine erişimini sağlar ve yeniliği teşvik eder."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1, Meta tarafından geliştirilen çok dilli büyük dil modeli ailesidir ve 8B, 70B ve 405B olmak üzere üç parametre ölçeği ile önceden eğitilmiş ve talimat ince ayar varyantları içermektedir. Bu 8B talimat ince ayar modeli, çok dilli diyalog senaryoları için optimize edilmiştir ve birçok endüstri standart testinde mükemmel performans sergilemektedir. Model, 15 trilyon token'dan fazla açık veriler kullanılarak eğitilmiş ve modelin faydasını ve güvenliğini artırmak için denetimli ince ayar ve insan geri bildirimi pekiştirmeli öğrenme gibi teknikler kullanılmıştır. Llama 3.1, metin üretimi ve kod üretimini desteklemekte olup, bilgi kesim tarihi 2023 Aralık'tır."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview, karmaşık diyalog oluşturma ve bağlam anlama görevlerini etkili bir şekilde işleyebilen yenilikçi bir doğal dil işleme modelidir."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview, Qwen ekibi tarafından geliştirilen ve görsel çıkarım yeteneklerine odaklanan bir araştırma modelidir. Karmaşık sahne anlayışı ve görsel ile ilgili matematiksel sorunları çözme konusundaki benzersiz avantajları ile dikkat çekmektedir."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Qwen2'nin test sürümü olan Qwen1.5, büyük ölçekli verilerle daha hassas diyalog yetenekleri sunar."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ, Qwen serisinin çıkarım modelidir. Geleneksel talimat ayarlama modellerine kıyasla, QwQ düşünme ve çıkarım yeteneğine sahiptir ve özellikle zor problemleri çözme konusunda önemli ölçüde artırılmış performans sergileyebilir. QwQ-32B, orta ölçekli bir çıkarım modelidir ve en son çıkarım modelleri (örneğin, DeepSeek-R1, o1-mini) ile karşılaştırıldığında rekabetçi bir performans elde edebilir. Bu model, RoPE, SwiGLU, RMSNorm ve Attention QKV bias gibi teknikleri kullanmakta olup, 64 katmanlı bir ağ yapısına ve 40 Q dikkat başlığına (GQA mimarisinde KV 8'dir) sahiptir."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B), hızlı yanıt ve doğal diyalog yetenekleri sunar, çok dilli ortamlara uygundur."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview, Qwen'in en son deneysel araştırma modelidir ve AI akıl yürütme yeteneklerini artırmaya odaklanmaktadır. Dil karışımı, özyinelemeli akıl yürütme gibi karmaşık mekanizmaları keşfederek, güçlü akıl yürütme analizi, matematik ve programlama yetenekleri gibi ana avantajlar sunmaktadır. Bununla birlikte, dil geçiş sorunları, akıl yürütme döngüleri, güvenlik endişeleri ve diğer yetenek farklılıkları gibi zorluklar da bulunmaktadır."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct, Qwen2 serisindeki talimat ince ayar büyük dil modelidir ve parametre ölçeği 1.5B'dir. Bu model, Transformer mimarisi temelinde, SwiGLU aktivasyon fonksiyonu, dikkat QKV önyargısı ve grup sorgu dikkati gibi teknikler kullanmaktadır. Dil anlama, üretim, çok dilli yetenek, kodlama, matematik ve akıl yürütme gibi birçok standart testte mükemmel performans sergilemekte ve çoğu açık kaynak modelini geride bırakmaktadır. Qwen1.5-1.8B-Chat ile karşılaştırıldığında, Qwen2-1.5B-Instruct, MMLU, HumanEval, GSM8K, C-Eval ve IFEval gibi testlerde belirgin bir performans artışı göstermektedir, parametre sayısı biraz daha az olmasına rağmen."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2, çok çeşitli talimat türlerini destekleyen gelişmiş bir genel dil modelidir."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct, Qwen2 serisindeki talimat ince ayar büyük dil modelidir ve parametre ölçeği 72B'dir. Bu model, Transformer mimarisi temelinde, SwiGLU aktivasyon fonksiyonu, dikkat QKV önyargısı ve grup sorgu dikkati gibi teknikler kullanmaktadır. Büyük ölçekli girişleri işleyebilme yeteneğine sahiptir. Bu model, dil anlama, üretim, çok dilli yetenek, kodlama, matematik ve akıl yürütme gibi birçok standart testte mükemmel performans sergilemekte ve çoğu açık kaynak modelini geride bırakmakta, bazı görevlerde özel modellere karşı rekabet edebilir."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL, Qwen-VL modelinin en son yineleme versiyonudur ve görsel anlama kıyaslama testlerinde en gelişmiş performansı sergilemiştir."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5, talimat tabanlı görevlerin işlenmesini optimize etmek için tasarlanmış yeni bir büyük dil modeli serisidir."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5, talimat tabanlı görevlerin işlenmesini optimize etmek için tasarlanmış yeni bir büyük dil modeli serisidir."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5, daha güçlü anlama ve üretim yeteneklerine sahip yeni bir büyük dil modeli serisidir."
+ "description": "Alibaba Cloud Tongyi Qianwen ekibi tarafından geliştirilen büyük bir dil modeli"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5, daha güçlü anlama ve üretim yeteneği ile yeni bir büyük dil modeli serisidir."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5, komut tabanlı görevlerin işlenmesini optimize etmek için tasarlanmış yeni bir büyük dil modeli serisidir."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5, talimat tabanlı görevlerin işlenmesini optimize etmek için tasarlanmış yeni bir büyük dil modeli serisidir."
},
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5, komut tabanlı görevlerin işlenmesini optimize etmek için tasarlanmış yeni bir büyük dil modeli serisidir."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder, kod yazımına odaklanmaktadır."
+ },
"Qwen/Qwen2.5-Coder-7B-Instruct": {
- "description": "Qwen2.5-Coder, kod yazmaya odaklanır."
+ "description": "Qwen2.5-Coder-7B-Instruct, Alibaba Cloud tarafından yayınlanan kod odaklı büyük dil modeli serisinin en son versiyonudur. Bu model, Qwen2.5 temelinde, 5.5 trilyon token ile eğitilerek kod üretimi, akıl yürütme ve düzeltme yeteneklerini önemli ölçüde artırmıştır. Hem kodlama yeteneklerini geliştirmiş hem de matematik ve genel yetenek avantajlarını korumuştur. Model, kod akıllı ajanları gibi pratik uygulamalar için daha kapsamlı bir temel sunmaktadır."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2, Qwen modelinin en yeni serisidir ve 128k bağlamı destekler. Mevcut en iyi açık kaynak modellerle karşılaştırıldığında, Qwen2-72B doğal dil anlama, bilgi, kod, matematik ve çok dilli yetenekler açısından mevcut lider modelleri önemli ölçüde aşmaktadır."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2, Qwen modelinin en yeni serisidir ve eşit ölçekli en iyi açık kaynak modelleri hatta daha büyük ölçekli modelleri aşabilmektedir. Qwen2 7B, birçok değerlendirmede belirgin bir avantaj elde etmiş, özellikle kod ve Çince anlama konusunda."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B, görüntü ve metin için çok modlu işleme desteği sunan güçlü bir görsel dil modelidir, görüntü içeriğini hassas bir şekilde tanıyabilir ve ilgili açıklamalar veya yanıtlar üretebilir."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct, 14 milyar parametreye sahip büyük bir dil modelidir. Performansı mükemmel olup, Çince ve çok dilli senaryoları optimize eder, akıllı soru-cevap, içerik üretimi gibi uygulamaları destekler."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct, 32 milyar parametreye sahip büyük bir dil modelidir. Performans dengeli olup, Çince ve çok dilli senaryoları optimize eder, akıllı soru-cevap, içerik üretimi gibi uygulamaları destekler."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct, 16k bağlamı destekler ve 8K'dan uzun metinler üretebilir. Fonksiyon çağrısı ile dış sistemlerle sorunsuz etkileşim sağlar, esneklik ve ölçeklenebilirliği büyük ölçüde artırır. Modelin bilgisi belirgin şekilde artmış ve kodlama ile matematik yetenekleri büyük ölçüde geliştirilmiştir, 29'dan fazla dil desteği sunmaktadır."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct, 7 milyar parametreye sahip büyük bir dil modelidir. Fonksiyon çağrısı ile dış sistemlerle sorunsuz etkileşim destekler, esneklik ve ölçeklenebilirliği büyük ölçüde artırır. Çince ve çok dilli senaryoları optimize eder, akıllı soru-cevap, içerik üretimi gibi uygulamaları destekler."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct, büyük ölçekli önceden eğitilmiş bir programlama talimat modelidir, güçlü kod anlama ve üretme yeteneğine sahiptir, çeşitli programlama görevlerini verimli bir şekilde işleyebilir, özellikle akıllı kod yazma, otomatik betik oluşturma ve programlama sorunlarına yanıt verme için uygundur."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct, kod üretimi, kod anlama ve verimli geliştirme senaryoları için tasarlanmış büyük bir dil modelidir. Sektördeki en ileri 32B parametre ölçeğini kullanarak çeşitli programlama ihtiyaçlarını karşılayabilir."
+ },
+ "SenseChat": {
+ "description": "Temel sürüm model (V4), 4K bağlam uzunluğu ile genel yetenekleri güçlüdür."
+ },
+ "SenseChat-128K": {
+ "description": "Temel sürüm model (V4), 128K bağlam uzunluğu ile uzun metin anlama ve üretme görevlerinde mükemmel performans sergilemektedir."
+ },
+ "SenseChat-32K": {
+ "description": "Temel sürüm model (V4), 32K bağlam uzunluğu ile çeşitli senaryolarda esnek bir şekilde uygulanabilir."
+ },
+ "SenseChat-5": {
+ "description": "En son sürüm model (V5.5), 128K bağlam uzunluğu, matematiksel akıl yürütme, İngilizce diyalog, talimat takibi ve uzun metin anlama gibi alanlarda önemli gelişmeler göstermektedir ve GPT-4o ile karşılaştırılabilir."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math, matematik alanındaki sorunları çözmeye odaklanır ve yüksek zorlukta sorulara profesyonel yanıtlar sunar."
+ "SenseChat-5-1202": {
+ "description": "V5.5 tabanlı en son versiyondur, önceki versiyona göre Çince ve İngilizce temel yetenekleri, sohbet, fen bilgisi, sosyal bilimler bilgisi, yazım, matematiksel mantık, kelime sayısı kontrolü gibi birkaç boyutta önemli bir gelişim göstermiştir."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "32K bağlam uzunluğu ile, Kantonca diyalog anlama konusunda GPT-4'ü aşmakta, bilgi, akıl yürütme, matematik ve kod yazma gibi birçok alanda GPT-4 Turbo ile rekabet edebilmektedir."
+ },
+ "SenseChat-Character": {
+ "description": "Standart sürüm model, 8K bağlam uzunluğu ile yüksek yanıt hızı sunmaktadır."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Gelişmiş sürüm model, 32K bağlam uzunluğu ile yetenekleri tamamen geliştirilmiş, Çince/İngilizce diyalogları desteklemektedir."
+ },
+ "SenseChat-Turbo": {
+ "description": "Hızlı soru-cevap ve model ince ayar senaryoları için uygundur."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "En son hafif versiyon modelidir, tam modelin %90'ından fazla yetenek sunar ve çıkarım maliyetini önemli ölçüde azaltır."
+ },
+ "SenseChat-Vision": {
+ "description": "En son versiyon modeli (V5.5), çoklu görsel girişi destekler, modelin temel yetenek optimizasyonunu tamamen gerçekleştirir; nesne özellik tanıma, mekansal ilişkiler, hareket olayları tanıma, sahne anlama, duygu tanıma, mantıksal bilgi çıkarımı ve metin anlama üretimi gibi alanlarda önemli gelişmeler sağlamıştır."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Skylark'in (Bulut Şarkıcısı) ikinci nesil modeli, Skylark2-lite modeli yüksek yanıt hızı ile donatılmıştır; gerçek zamanlı talep gereksinimleri yüksek, maliyet duyarlı ve model hassasiyetine daha az ihtiyaç duyulan senaryolar için uygundur; bağlam pencere uzunluğu 8k'dır."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Skylark'in (Bulut Şarkıcısı) ikinci nesil modeli, Skylark2-pro sürümüyle yüksek model hassasiyetine sahiptir; profesyonel alan metin üretimi, roman yazımı, yüksek kaliteli çeviri gibi daha karmaşık metin üretim sahneleri için uygundur ve bağlam pencere uzunluğu 32k'dır."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Skylark'in (Bulut Şarkıcısı) ikinci nesil modeli, Skylark2-pro modeli yüksek model hassasiyetine sahiptir; profesyonel alan metin üretimi, roman yazımı, yüksek kaliteli çeviri gibi daha karmaşık metin üretim sahneleri için uygundur ve bağlam pencere uzunluğu 4k'dır."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Skylark'in (Bulut Şarkıcısı) ikinci nesil modeli, Skylark2-pro-character modeli, mükemmel rol yapma ve sohbet yeteneklerine sahiptir; kullanıcıdan gelen istem taleplerine göre farklı roller üstlenme kabiliyeti ile sohbet edebilir. Rol stili belirgindir ve diyalog içeriği doğal ve akıcıdır. Chatbot, sanal asistan ve çevrimiçi müşteri hizmetleri gibi senaryolar için uygundur ve yüksek yanıt hızı vardır."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Skylark'in (Bulut Şarkıcısı) ikinci nesil modeli, Skylark2-pro-turbo-8k ile daha hızlı çıkarım gerçekleştirir, maliyeti düşüktür ve bağlam pencere uzunluğu 8k'dır."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B, Zhipu AI tarafından geliştirilen ChatGLM serisinin açık kaynak modelidir. Bu model, önceki nesil modellerin mükemmel özelliklerini korurken, yeni özellikler de eklenmiştir. Daha çeşitli eğitim verileri, daha fazla eğitim adımı ve daha mantıklı eğitim stratejileri kullanarak, 10B altındaki önceden eğitilmiş modeller arasında mükemmel performans sergilemektedir. ChatGLM3-6B, çoklu diyalog, araç çağrısı, kod yürütme ve ajan görevleri gibi karmaşık senaryoları desteklemektedir. Diyalog modelinin yanı sıra, temel model ChatGLM-6B-Base ve uzun metin diyalog modeli ChatGLM3-6B-32K da açık kaynak olarak sunulmuştur. Bu model, akademik araştırmalara tamamen açıktır ve kayıt olduktan sonra ücretsiz ticari kullanımına da izin verilmektedir."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B açık kaynak versiyonu, diyalog uygulamaları için optimize edilmiş bir diyalog deneyimi sunar."
},
+ "TeleAI/TeleChat2": {
+ "description": "TeleChat2 büyük modeli, Çin Telekom tarafından sıfırdan geliştirilen jeneratif bir anlam büyük modelidir. Ansiklopedik soru yanıtlama, kod üretimi, uzun metin üretimi gibi işlevleri desteklemekte ve kullanıcılara diyalog danışmanlık hizmeti sunmaktadır. Kullanıcılarla diyalog etme, soruları yanıtlama, yaratımda yardımcı olma gibi yeteneklere sahiptir ve kullanıcıların bilgi, bilgi ve ilham edinmelerine etkin ve kolay bir şekilde yardımcı olmaktadır. Model, yanıltma sorunları, uzun metin üretimi, mantıksal anlama gibi alanlarda oldukça iyi performans sergilemektedir."
+ },
+ "TeleAI/TeleMM": {
+ "description": "TeleMM çok modlu büyük model, Çin Telekom tarafından geliştirilen çok modlu anlama büyük modelidir. Metin, görüntü gibi çeşitli modlu girdileri işleyebilmekte ve görüntü anlama, grafik analizi gibi işlevleri desteklemektedir. Kullanıcılara çok modlu anlama hizmeti sunmakta ve kullanıcılarla çok modlu etkileşimde bulunarak, girdileri doğru bir şekilde anlamakta, soruları yanıtlamakta, yaratımda yardımcı olmakta ve çok modlu bilgi ve ilham desteği sunmaktadır. İnce ayrıntılı algılama, mantıksal akıl yürütme gibi çok modlu görevlerde mükemmel performans sergilemektedir."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct, Alibaba Cloud tarafından yayınlanan en son büyük dil modeli serilerinden biridir. Bu 72B modeli, kodlama ve matematik gibi alanlarda önemli ölçüde geliştirilmiş yeteneklere sahiptir. Model ayrıca, Çince, İngilizce gibi 29'dan fazla dili kapsayan çok dilli destek sunmaktadır. Model, talimat takibi, yapılandırılmış verileri anlama ve yapılandırılmış çıktı (özellikle JSON) üretme konularında önemli iyileştirmeler göstermektedir."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, orijinal model serisinin mükemmel genel dil yeteneklerini korurken, 500 milyar yüksek kaliteli token ile artımlı eğitim sayesinde matematiksel mantık ve kodlama yeteneklerini büyük ölçüde artırmıştır."
+ },
"abab5.5-chat": {
"description": "Üretkenlik senaryoları için tasarlanmış, karmaşık görev işleme ve verimli metin üretimini destekler, profesyonel alan uygulamaları için uygundur."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Çin karakter diyalog senaryoları için optimize edilmiş, akıcı ve Çin ifade alışkanlıklarına uygun diyalog üretim yeteneği sunar."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworks açık kaynak fonksiyon çağrı modeli, mükemmel talimat yürütme yetenekleri ve özelleştirilebilir özellikler sunar."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Fireworks şirketinin en son ürünü Firefunction-v2, Llama-3 tabanlı, fonksiyon çağrıları, diyalog ve talimat takibi gibi senaryolar için özel olarak optimize edilmiş yüksek performanslı bir modeldir."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b, hem görüntü hem de metin girdilerini alabilen, yüksek kaliteli verilerle eğitilmiş bir görsel dil modelidir ve çok modlu görevler için uygundur."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1, güçlendirilmiş öğrenme ve soğuk başlangıç verileri ile optimize edilmiş, mükemmel akıl yürütme, matematik ve programlama performansına sahip en son teknoloji büyük bir dil modelidir."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B talimat modeli, önceki Google teknolojilerine dayanarak, soru yanıtlama, özetleme ve akıl yürütme gibi çeşitli metin üretim görevleri için uygundur."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Deepseek tarafından sunulan güçlü Mixture-of-Experts (MoE) dil modeli, toplamda 671B parametreye sahiptir ve her bir etiket için 37B parametre etkinleştirilmektedir."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Llama 3 70B talimat modeli, çok dilli diyalog ve doğal dil anlama için optimize edilmiştir, çoğu rakip modelden daha iyi performans gösterir."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B talimat modeli (HF versiyonu), resmi uygulama sonuçlarıyla uyumlu olup yüksek kaliteli talimat takibi görevleri için uygundur."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Llama 3 8B talimat modeli, diyalog ve çok dilli görevler için optimize edilmiştir, mükemmel ve etkili performans sunar."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Llama 3.1 8B talimat modeli, çok dilli diyaloglar için optimize edilmiştir ve yaygın endüstri standartlarını aşmaktadır."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Meta'nın 11B parametreli komut ayarlı görüntü akıl yürütme modelidir. Bu model, görsel tanıma, görüntü akıl yürütme, görüntü betimleme ve görüntü hakkında genel sorulara yanıt verme üzerine optimize edilmiştir. Bu model, grafikler ve resimler gibi görsel verileri anlayabilir ve görüntü detaylarını metin olarak betimleyerek görsel ile dil arasındaki boşluğu kapatır."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Llama 3.2 3B komut modeli, Meta tarafından sunulan hafif çok dilli bir modeldir. Bu model, verimliliği artırmak amacıyla daha büyük modellere göre gecikme ve maliyet açısından önemli iyileştirmeler sunar. Bu modelin örnek kullanım alanları arasında sorgulama, öneri yeniden yazma ve yazma desteği bulunmaktadır."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Meta'nın 90B parametreli komut ayarlı görüntü akıl yürütme modelidir. Bu model, görsel tanıma, görüntü akıl yürütme, görüntü betimleme ve görüntü hakkında genel sorulara yanıt verme üzerine optimize edilmiştir. Bu model, grafikler ve resimler gibi görsel verileri anlayabilir ve görüntü detaylarını metin olarak betimleyerek görsel ile dil arasındaki boşluğu kapatır."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct, Llama 3.1 70B'nin Aralık güncellemesi olan bir modeldir. Bu model, Llama 3.1 70B (2024 Temmuz'da piyasaya sürüldü) temel alınarak geliştirilmiş olup, araç çağrıları, çok dilli metin desteği, matematik ve programlama yeteneklerini artırmıştır. Model, akıl yürütme, matematik ve talimat takibi alanlarında sektördeki en yüksek standartlara ulaşmış olup, 3.1 405B ile benzer performans sunarken hız ve maliyet açısından önemli avantajlar sağlamaktadır."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "24B parametreli model, daha büyük modellerle karşılaştırılabilir en son teknoloji yeteneklerine sahiptir."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B talimat modeli, büyük ölçekli parametreler ve çok uzmanlı mimarisi ile karmaşık görevlerin etkili işlenmesini destekler."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B talimat modeli, çok uzmanlı mimarisi ile etkili talimat takibi ve yürütme sunar."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B talimat modeli (HF versiyonu), resmi uygulama ile uyumlu olup çeşitli yüksek verimli görev senaryoları için uygundur."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "MythoMax L2 13B modeli, yenilikçi birleşim teknolojileri ile hikaye anlatımı ve rol yapma konularında uzmandır."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision talimat modeli, karmaşık görsel ve metin bilgilerini işleyebilen hafif çok modlu bir modeldir ve güçlü akıl yürütme yeteneklerine sahiptir."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5B modeli, ileri düzey programlama görevlerini destekler, çok dilli yetenekleri artırır ve karmaşık kod üretimi ve anlama için uygundur."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "QwQ modeli, Qwen ekibi tarafından geliştirilen deneysel bir araştırma modelidir ve AI akıl yürütme yeteneklerini artırmaya odaklanmaktadır."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7B modeli, 80'den fazla programlama dili için eğitilmiş olup, mükemmel programlama tamamlama yetenekleri ve bağlam anlama sunar."
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Qwen-VL modelinin 72B versiyonu, Alibaba'nın en son iterasyonunun bir ürünüdür ve son bir yılın yeniliklerini temsil etmektedir."
+ },
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5, Alibaba Cloud Qwen ekibi tarafından geliştirilen yalnızca kodlayıcı içeren bir dizi dil modelidir. Bu modeller, 0.5B, 1.5B, 3B, 7B, 14B, 32B ve 72B gibi farklı boyutları sunar ve temel (base) ve komut (instruct) versiyonlarına sahiptir."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct, Alibaba Cloud tarafından yayınlanan kod odaklı büyük dil modeli serisinin en son versiyonudur. Bu model, Qwen2.5 temelinde, 5.5 trilyon token ile eğitilerek kod üretimi, akıl yürütme ve düzeltme yeteneklerini önemli ölçüde artırmıştır. Hem kodlama yeteneklerini geliştirmiş hem de matematik ve genel yetenek avantajlarını korumuştur. Model, kod akıllı ajanları gibi pratik uygulamalar için daha kapsamlı bir temel sunmaktadır."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Yi-Large modeli, mükemmel çok dilli işleme yetenekleri sunar ve her türlü dil üretimi ve anlama görevleri için uygundur."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "52B parametreli (12B aktif) çok dilli bir model, 256K uzun bağlam penceresi, fonksiyon çağrısı, yapılandırılmış çıktı ve temellendirilmiş üretim sunar."
},
- "ai21-jamba-instruct": {
- "description": "En iyi performans, kalite ve maliyet verimliliği sağlamak için üretim sınıfı Mamba tabanlı LLM modelidir."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet, endüstri standartlarını yükselterek, rakip modelleri ve Claude 3 Opus'u geride bırakarak geniş bir değerlendirmede mükemmel performans sergilerken, orta seviye modellerimizin hızı ve maliyeti ile birlikte gelir."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet, sektör standartlarını yükselterek, rakip modelleri ve Claude 3 Opus'u geride bırakarak, geniş bir değerlendirme yelpazesinde mükemmel performans sergilemekte, orta seviye modellerimizin hız ve maliyet avantajlarını sunmaktadır."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku, Anthropic'in en hızlı ve en kompakt modelidir, neredeyse anında yanıt hızı sunar. Basit sorgular ve taleplere hızlı bir şekilde yanıt verebilir. Müşteriler, insan etkileşimini taklit eden kesintisiz bir AI deneyimi oluşturabileceklerdir. Claude 3 Haiku, görüntüleri işleyebilir ve metin çıktısı döndürebilir, 200K bağlam penceresine sahiptir."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus, Anthropic'in son derece karmaşık görevleri işlemek için en güçlü modelidir. Performans, zeka, akıcılık ve anlama açısından olağanüstü bir performans sergiler."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku, Anthropic'in en hızlı bir sonraki nesil modelidir. Claude 3 Haiku ile karşılaştırıldığında, Claude 3.5 Haiku, birçok beceride iyileşme göstermiştir ve birçok zeka kıyaslamasında bir önceki neslin en büyük modeli Claude 3 Opus'u geride bırakmıştır."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet, Opus'tan daha fazla yetenek ve Sonnet'ten daha hızlı bir hız sunar; aynı zamanda Sonnet ile aynı fiyatı korur. Sonnet, programlama, veri bilimi, görsel işleme ve ajan görevlerinde özellikle başarılıdır."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet, Anthropic'in şimdiye kadarki en akıllı modeli ve piyasadaki ilk karma akıl yürütme modelidir. Claude 3.7 Sonnet, neredeyse anlık yanıtlar veya uzatılmış adım adım düşünme süreçleri üretebilir; kullanıcılar bu süreçleri net bir şekilde görebilir. Sonnet, programlama, veri bilimi, görsel işleme ve temsilci görevlerde özellikle yeteneklidir."
+ },
"aya": {
"description": "Aya 23, Cohere tarafından sunulan çok dilli bir modeldir, 23 dili destekler ve çok dilli uygulamalar için kolaylık sağlar."
},
"aya:35b": {
"description": "Aya 23, Cohere tarafından sunulan çok dilli bir modeldir, 23 dili destekler ve çok dilli uygulamalar için kolaylık sağlar."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B, Baichuan Zhi Neng tarafından geliştirilen 130 milyar parametreye sahip açık kaynaklı ticari bir büyük dil modelidir ve yetkili Çince ve İngilizce benchmark'larda aynı boyuttaki en iyi sonuçları elde etmiştir."
+ },
"charglm-3": {
"description": "CharGLM-3, rol yapma ve duygusal destek için tasarlanmış, ultra uzun çok turlu bellek ve kişiselleştirilmiş diyalog desteği sunan bir modeldir, geniş bir uygulama yelpazesine sahiptir."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2, işletmelere kritik yeteneklerin ilerlemesini sunar, sektördeki en iyi 200K token bağlamı, model yanılsamalarının önemli ölçüde azaltılması, sistem ipuçları ve yeni bir test özelliği: araç çağrısı içerir."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku, Anthropic'in en hızlı bir sonraki nesil modelidir. Claude 3 Haiku ile karşılaştırıldığında, Claude 3.5 Haiku, tüm becerilerde gelişim göstermiştir ve birçok zeka standart testinde bir önceki neslin en büyük modeli olan Claude 3 Opus'u geride bırakmıştır."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet, Opus'tan daha fazla yetenek ve Sonnet'ten daha hızlı bir performans sunar, aynı zamanda Sonnet ile aynı fiyatı korur. Sonnet, programlama, veri bilimi, görsel işleme ve ajan görevlerinde özellikle başarılıdır."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet, Opus'tan daha fazla yetenek ve Sonnet'ten daha hızlı performans sunarken, aynı fiyatta kalmaktadır. Sonnet, programlama, veri bilimi, görsel işleme ve aracı görevlerde özellikle güçlüdür."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet, endüstri standartlarını yükselterek, rakip modelleri ve Claude 3 Opus'u geride bırakarak, geniş bir değerlendirme yelpazesinde mükemmel performans sergilemekte, orta seviye modellerimizin hız ve maliyet avantajlarını sunmaktadır."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku, Anthropic'in en hızlı ve en kompakt modelidir, neredeyse anlık yanıtlar sağlamak için tasarlanmıştır. Hızlı ve doğru yönlendirme performansına sahiptir."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet, akıllı ve hızlı bir denge sunarak kurumsal iş yükleri için idealdir. Daha düşük bir fiyatla maksimum fayda sağlar, güvenilir ve büyük ölçekli dağıtım için uygundur."
},
- "claude-instant-1.2": {
- "description": "Anthropic'in modeli, düşük gecikme ve yüksek verimlilikte metin üretimi için kullanılır, yüzlerce sayfa metin üretebilir."
- },
"codegeex-4": {
"description": "CodeGeeX-4, çeşitli programlama dillerinde akıllı soru-cevap ve kod tamamlama desteği sunan güçlü bir AI programlama asistanıdır, geliştirme verimliliğini artırır."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B, çok dilli kod üretim modeli olup, kod tamamlama ve üretimi, kod yorumlayıcı, web arama, fonksiyon çağrısı, depo düzeyinde kod soru-cevap gibi kapsamlı işlevleri destekler ve yazılım geliştirme için çeşitli senaryoları kapsar. 10B'den az parametreye sahip en iyi kod üretim modelidir."
+ },
"codegemma": {
"description": "CodeGemma, farklı programlama görevleri için özel olarak tasarlanmış hafif bir dil modelidir, hızlı iterasyon ve entegrasyonu destekler."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama, kod üretimi ve tartışmalarına odaklanan bir LLM'dir, geniş programlama dili desteği ile geliştirici ortamları için uygundur."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama, kod üretimi ve tartışmalarına odaklanan bir LLM'dir ve geniş bir programlama dili desteği sunarak geliştirici ortamları için uygundur."
+ },
"codellama:13b": {
"description": "Code Llama, kod üretimi ve tartışmalarına odaklanan bir LLM'dir, geniş programlama dili desteği ile geliştirici ortamları için uygundur."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+, gerçek işletme senaryoları ve karmaşık uygulamalar için tasarlanmış yüksek performanslı bir büyük dil modelidir."
},
+ "dall-e-2": {
+ "description": "İkinci nesil DALL·E modeli, daha gerçekçi ve doğru görüntü üretimi destekler, çözünürlüğü birinci neslin 4 katıdır."
+ },
+ "dall-e-3": {
+ "description": "En son DALL·E modeli, Kasım 2023'te piyasaya sürüldü. Daha gerçekçi ve doğru görüntü üretimi destekler, daha güçlü detay ifade yeteneğine sahiptir."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct, yüksek güvenilirlikte talimat işleme yetenekleri sunar ve çok çeşitli endüstri uygulamalarını destekler."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1, tekrarlayan öğrenme (RL) destekli bir çıkarım modelidir ve modeldeki tekrarlama ve okunabilirlik sorunlarını çözmektedir. RL'den önce, DeepSeek-R1 soğuk başlangıç verilerini tanıtarak çıkarım performansını daha da optimize etmiştir. Matematik, kod ve çıkarım görevlerinde OpenAI-o1 ile benzer bir performans sergilemekte ve özenle tasarlanmış eğitim yöntemleri ile genel etkisini artırmaktadır."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek-R1 damıtma modeli, pekiştirme öğrenimi ve soğuk başlatma verileri ile çıkarım performansını optimize eder, açık kaynak model çoklu görev standartlarını yeniler."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B, Llama-3.1-8B temel alınarak geliştirilmiş bir damıtma modelidir. Bu model, DeepSeek-R1 tarafından üretilen örneklerle ince ayar yapılmış, mükemmel çıkarım yeteneği sergilemektedir. Birçok referans testinde iyi performans göstermiş, MATH-500'de %89.1 doğruluk oranına, AIME 2024'te %50.4 geçiş oranına ulaşmış, CodeForces'ta 1205 puan alarak 8B ölçeğindeki model olarak güçlü matematik ve programlama yeteneğini göstermiştir."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 damıtma modeli, pekiştirme öğrenimi ve soğuk başlatma verileri ile çıkarım performansını optimize eder, açık kaynak model çoklu görev standartlarını yeniler."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 damıtma modeli, pekiştirme öğrenimi ve soğuk başlatma verileri ile çıkarım performansını optimize eder, açık kaynak model çoklu görev standartlarını yeniler."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B, Qwen2.5-32B temel alınarak bilgi damıtma ile elde edilen bir modeldir. Bu model, DeepSeek-R1 tarafından üretilen 800.000 seçkin örnek ile ince ayar yapılmış, matematik, programlama ve çıkarım gibi birçok alanda olağanüstü performans sergilemektedir. AIME 2024, MATH-500, GPQA Diamond gibi birçok referans testinde mükemmel sonuçlar elde etmiş, MATH-500'de %94.3 doğruluk oranına ulaşarak güçlü matematik çıkarım yeteneğini göstermiştir."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B, Qwen2.5-Math-7B temel alınarak bilgi damıtma ile elde edilen bir modeldir. Bu model, DeepSeek-R1 tarafından üretilen 800.000 seçkin örnek ile ince ayar yapılmış, mükemmel çıkarım yeteneği sergilemektedir. Birçok referans testinde öne çıkmış, MATH-500'de %92.8 doğruluk oranına, AIME 2024'te %55.5 geçiş oranına ulaşmış, CodeForces'ta 1189 puan alarak 7B ölçeğindeki model olarak güçlü matematik ve programlama yeteneğini göstermiştir."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5, önceki sürümlerin mükemmel özelliklerini bir araya getirir, genel ve kodlama yeteneklerini artırır."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3, 6710 milyar parametreye sahip bir karma uzman (MoE) dil modelidir. Çok başlı potansiyel dikkat (MLA) ve DeepSeekMoE mimarisini kullanarak, yardımcı kayıplar olmadan yük dengeleme stratejisi ile çıkarım ve eğitim verimliliğini optimize etmektedir. 14.8 trilyon yüksek kaliteli token üzerinde önceden eğitilmiş ve denetimli ince ayar ile tekrarlayan öğrenme gerçekleştirilmiştir; DeepSeek-V3, performans açısından diğer açık kaynaklı modelleri geride bırakmakta ve lider kapalı kaynaklı modellere yaklaşmaktadır."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B, yüksek karmaşıklıkta diyaloglar için eğitilmiş gelişmiş bir modeldir."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "En son teknolojiye sahip verimli LLM, akıl yürütme, matematik ve programlama konularında uzmandır."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2, DeepSeekMoE-27B tabanlı bir karma uzman (MoE) görsel dil modelidir. Seyrek etkinleştirilen MoE mimarisini kullanarak yalnızca 4.5B parametreyi etkinleştirerek olağanüstü performans sergilemektedir. Bu model, görsel soru yanıtlama, optik karakter tanıma, belge/tablolar/grafikler anlama ve görsel konumlandırma gibi birçok görevde mükemmel sonuçlar elde etmektedir."
+ },
"deepseek-chat": {
"description": "Genel ve kod yeteneklerini birleştiren yeni bir açık kaynak modeli, yalnızca mevcut Chat modelinin genel diyalog yeteneklerini ve Coder modelinin güçlü kod işleme yeteneklerini korumakla kalmaz, aynı zamanda insan tercihleri ile daha iyi hizalanmıştır. Ayrıca, DeepSeek-V2.5 yazım görevleri, talimat takibi gibi birçok alanda büyük iyileştirmeler sağlamıştır."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B, 20 trilyon veri ile eğitilmiş bir kod dili modelidir. Bunun %87'si kod, %13'ü ise Çince ve İngilizce dillerindendir. Model, 16K pencere boyutu ve boşluk doldurma görevini tanıtarak proje düzeyinde kod tamamlama ve parça doldurma işlevi sunmaktadır."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2, açık kaynaklı bir karışık uzman kod modelidir, kod görevlerinde mükemmel performans sergiler ve GPT4-Turbo ile karşılaştırılabilir."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2, açık kaynaklı bir karışık uzman kod modelidir, kod görevlerinde mükemmel performans sergiler ve GPT4-Turbo ile karşılaştırılabilir."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1, tekrarlayan öğrenme (RL) destekli bir çıkarım modelidir ve modeldeki tekrarlama ve okunabilirlik sorunlarını çözmektedir. RL'den önce, DeepSeek-R1 soğuk başlangıç verilerini tanıtarak çıkarım performansını daha da optimize etmiştir. Matematik, kod ve çıkarım görevlerinde OpenAI-o1 ile benzer bir performans sergilemekte ve özenle tasarlanmış eğitim yöntemleri ile genel etkisini artırmaktadır."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - DeepSeek paketindeki daha büyük ve daha akıllı model - Llama 70B mimarisine damıtılmıştır. Referans testleri ve insan değerlendirmelerine dayanarak, bu model orijinal Llama 70B'den daha akıllıdır, özellikle matematik ve gerçeklik doğruluğu gerektiren görevlerde mükemmel performans sergilemektedir."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek-R1-Distill serisi modeller, bilgi damıtma teknolojisi ile DeepSeek-R1 tarafından üretilen örneklerin Qwen, Llama gibi açık kaynak modeller üzerinde ince ayar yapılmasıyla elde edilmiştir."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "DeepSeek-R1-Distill serisi modeller, bilgi damıtma teknolojisi ile DeepSeek-R1 tarafından üretilen örneklerin Qwen, Llama gibi açık kaynak modeller üzerinde ince ayar yapılmasıyla elde edilmiştir."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek-R1-Distill serisi modeller, bilgi damıtma teknolojisi ile DeepSeek-R1 tarafından üretilen örneklerin Qwen, Llama gibi açık kaynak modeller üzerinde ince ayar yapılmasıyla elde edilmiştir."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek-R1-Distill serisi modeller, bilgi damıtma teknolojisi ile DeepSeek-R1 tarafından üretilen örneklerin Qwen, Llama gibi açık kaynak modeller üzerinde ince ayar yapılmasıyla elde edilmiştir."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "DeepSeek-R1-Distill serisi modeller, bilgi damıtma teknolojisi ile DeepSeek-R1 tarafından üretilen örneklerin Qwen, Llama gibi açık kaynak modeller üzerinde ince ayar yapılmasıyla elde edilmiştir."
+ },
+ "deepseek-reasoner": {
+ "description": "DeepSeek tarafından sunulan bir akıl yürütme modeli. Model, nihai yanıtı vermeden önce bir düşünce zinciri içeriği sunarak nihai cevabın doğruluğunu artırır."
+ },
"deepseek-v2": {
"description": "DeepSeek V2, ekonomik ve verimli işleme ihtiyaçları için uygun, etkili bir Mixture-of-Experts dil modelidir."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B, DeepSeek'in tasarım kodu modelidir, güçlü kod üretim yetenekleri sunar."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3, Hangzhou DeepSeek Yapay Zeka Temel Teknoloji Araştırma Şirketi tarafından geliştirilen MoE modelidir, birçok değerlendirme sonucunda öne çıkmakta ve ana akım listelerde açık kaynak modeller arasında birinci sırada yer almaktadır. V3, V2.5 modeline göre üretim hızında 3 kat artış sağlamış, kullanıcılara daha hızlı ve akıcı bir deneyim sunmuştur."
+ },
"deepseek/deepseek-chat": {
"description": "Genel ve kod yeteneklerini birleştiren yeni açık kaynak model, yalnızca mevcut Chat modelinin genel diyalog yeteneklerini ve Coder modelinin güçlü kod işleme yeteneklerini korumakla kalmaz, aynı zamanda insan tercihleriyle daha iyi hizalanmıştır. Ayrıca, DeepSeek-V2.5 yazma görevleri, talimat takibi gibi birçok alanda da büyük iyileştirmeler sağlamıştır."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1, yalnızca çok az etiketli veri ile modelin akıl yürütme yeteneğini büyük ölçüde artırır. Model, nihai yanıtı vermeden önce bir düşünce zinciri içeriği sunarak nihai yanıtın doğruluğunu artırır."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B, Llama3.3 70B tabanlı büyük bir dil modelidir ve DeepSeek R1'in çıktısını kullanarak ince ayar yaparak büyük öncü modellerle rekabet edebilecek bir performans elde etmiştir."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B, Llama-3.1-8B-Instruct tabanlı bir damıtılmış büyük dil modelidir ve DeepSeek R1'in çıktısını kullanarak eğitilmiştir."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B, Qwen 2.5 14B tabanlı bir damıtılmış büyük dil modelidir ve DeepSeek R1'in çıktısını kullanarak eğitilmiştir. Bu model, birçok benchmark testinde OpenAI'nin o1-mini'sini geçerek yoğun modellerin (dense models) en son teknik liderlik başarılarını elde etmiştir. İşte bazı benchmark test sonuçları:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nBu model, DeepSeek R1'in çıktısından ince ayar yaparak daha büyük ölçekli öncü modellerle karşılaştırılabilir bir performans sergilemiştir."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B, Qwen 2.5 32B tabanlı bir damıtılmış büyük dil modelidir ve DeepSeek R1'in çıktısını kullanarak eğitilmiştir. Bu model, birçok benchmark testinde OpenAI'nin o1-mini'sini geçerek yoğun modellerin (dense models) en son teknik liderlik başarılarını elde etmiştir. İşte bazı benchmark test sonuçları:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nBu model, DeepSeek R1'in çıktısından ince ayar yaparak daha büyük ölçekli öncü modellerle karşılaştırılabilir bir performans sergilemiştir."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1, DeepSeek ekibinin yayınladığı en son açık kaynak modelidir ve özellikle matematik, programlama ve akıl yürütme görevlerinde OpenAI'nin o1 modeli ile karşılaştırılabilir bir çıkarım performansına sahiptir."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1, yalnızca çok az etiketli veri ile modelin akıl yürütme yeteneğini büyük ölçüde artırır. Model, nihai yanıtı vermeden önce bir düşünce zinciri içeriği sunarak nihai yanıtın doğruluğunu artırır."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3, çıkarım hızında önceki modellere göre önemli bir atılım gerçekleştirmiştir. Açık kaynak modeller arasında birinci sırada yer almakta ve dünya çapındaki en gelişmiş kapalı kaynak modellerle rekabet edebilmektedir. DeepSeek-V3, DeepSeek-V2'de kapsamlı bir şekilde doğrulanan çok başlı potansiyel dikkat (MLA) ve DeepSeekMoE mimarilerini kullanmaktadır. Ayrıca, DeepSeek-V3, yük dengeleme için yardımcı kayıpsız bir strateji geliştirmiştir ve daha güçlü bir performans elde etmek için çok etiketli tahmin eğitim hedefleri belirlemiştir."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3, çıkarım hızında önceki modellere göre önemli bir atılım gerçekleştirmiştir. Açık kaynak modeller arasında birinci sırada yer almakta ve dünya çapındaki en gelişmiş kapalı kaynak modellerle rekabet edebilmektedir. DeepSeek-V3, DeepSeek-V2'de kapsamlı bir şekilde doğrulanan çok başlı potansiyel dikkat (MLA) ve DeepSeekMoE mimarilerini kullanmaktadır. Ayrıca, DeepSeek-V3, yük dengeleme için yardımcı kayıpsız bir strateji geliştirmiştir ve daha güçlü bir performans elde etmek için çok etiketli tahmin eğitim hedefleri belirlemiştir."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite, tamamen yeni nesil hafif modeldir, olağanüstü yanıt hızı ile etkisi ve gecikmesi dünya standartlarında bir seviyeye ulaşmıştır."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k, Doubao-1.5-Pro'nun kapsamlı bir yükseltmesi olup, genel performans %10 oranında büyük bir artış göstermektedir. 256k bağlam penceresi ile akıl yürütmeyi destekler, çıktı uzunluğu maksimum 12k token'a kadar desteklenmektedir. Daha yüksek performans, daha büyük pencere, yüksek maliyet etkinliği ile daha geniş uygulama alanlarına uygundur."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro, tamamen yeni nesil ana model, performansı tamamen yükseltilmiş olup, bilgi, kod, akıl yürütme gibi alanlarda mükemmel bir performans sergilemektedir."
+ },
"emohaa": {
"description": "Emohaa, duygusal sorunları anlamalarına yardımcı olmak için profesyonel danışmanlık yeteneklerine sahip bir psikolojik modeldir."
},
+ "ernie-3.5-128k": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi büyük ölçekli dil modeli, geniş bir Çince ve İngilizce veri kümesini kapsar, güçlü genel yeteneklere sahiptir ve çoğu diyalog soru-cevap, yaratım, eklenti uygulama senaryolarını karşılayabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar."
+ },
+ "ernie-3.5-8k": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi büyük ölçekli dil modeli, geniş bir Çince ve İngilizce veri kümesini kapsar, güçlü genel yeteneklere sahiptir ve çoğu diyalog soru-cevap, yaratım, eklenti uygulama senaryolarını karşılayabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi büyük ölçekli dil modeli, geniş bir Çince ve İngilizce veri kümesini kapsar, güçlü genel yeteneklere sahiptir ve çoğu diyalog soru-cevap, yaratım, eklenti uygulama senaryolarını karşılayabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi ultra büyük ölçekli dil modeli, ERNIE 3.5'e göre model yeteneklerinde kapsamlı bir yükseltme gerçekleştirmiştir, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi ultra büyük ölçekli dil modeli, ERNIE 3.5'e göre model yeteneklerinde kapsamlı bir yükseltme gerçekleştirmiştir, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi ultra büyük ölçekli dil modeli, genel performansı mükemmel, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar. ERNIE 4.0'a göre performans açısından daha üstündür."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi ultra büyük ölçekli dil modeli, genel performansı mükemmel, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar. ERNIE 4.0'a göre performans açısından daha üstündür."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Baidu tarafından geliştirilen amiral gemisi ultra büyük ölçekli dil modeli, genel performansı mükemmel, çeşitli alanlardaki karmaşık görev senaryolarında geniş bir şekilde uygulanabilir; Baidu arama eklentisi ile otomatik entegrasyon desteği sunarak soru-cevap bilgilerini güncel tutar. ERNIE 4.0'a göre performans açısından daha üstündür."
+ },
+ "ernie-char-8k": {
+ "description": "Baidu tarafından geliştirilen dikey senaryo büyük dil modeli, oyun NPC'leri, müşteri hizmetleri diyalogları, diyalog karakter rolü gibi uygulama senaryolarına uygundur, karakter tarzı daha belirgin ve tutarlıdır, talimat takibi yeteneği daha güçlü, çıkarım performansı daha iyidir."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Baidu tarafından geliştirilen dikey senaryo büyük dil modeli, oyun NPC'leri, müşteri hizmetleri diyalogları, diyalog karakter rolü gibi uygulama senaryolarına uygundur, karakter tarzı daha belirgin ve tutarlıdır, talimat takibi yeteneği daha güçlü, çıkarım performansı daha iyidir."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite, Baidu tarafından geliştirilen hafif büyük dil modelidir, mükemmel model performansı ve çıkarım yeteneği ile düşük hesaplama gücüne sahip AI hızlandırıcı kartları için uygundur."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Baidu tarafından geliştirilen hafif büyük dil modeli, mükemmel model performansı ve çıkarım yeteneği ile ERNIE Lite'dan daha iyi sonuçlar verir, düşük hesaplama gücüne sahip AI hızlandırıcı kartları için uygundur."
+ },
+ "ernie-novel-8k": {
+ "description": "Baidu tarafından geliştirilen genel büyük dil modeli, roman devam ettirme yeteneğinde belirgin bir avantaja sahiptir, aynı zamanda kısa oyun, film gibi senaryolarda da kullanılabilir."
+ },
+ "ernie-speed-128k": {
+ "description": "Baidu'nun 2024 yılında yayımladığı en son yüksek performanslı büyük dil modeli, genel yetenekleri mükemmel, belirli senaryo sorunlarını daha iyi ele almak için temel model olarak ince ayar yapılabilir, aynı zamanda mükemmel çıkarım performansına sahiptir."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Baidu'nun 2024 yılında yayımladığı en son yüksek performanslı büyük dil modeli, genel yetenekleri mükemmel, ERNIE Speed'den daha iyi sonuçlar verir, belirli senaryo sorunlarını daha iyi ele almak için temel model olarak ince ayar yapılabilir, aynı zamanda mükemmel çıkarım performansına sahiptir."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny, Baidu tarafından geliştirilen ultra yüksek performanslı büyük dil modelidir, dağıtım ve ince ayar maliyetleri Wenxin serisi modelleri arasında en düşüktür."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning), kararlı ve ayarlanabilir bir performans sunar, karmaşık görev çözümleri için ideal bir seçimdir."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro, Google'ın yüksek performanslı AI modelidir ve geniş görev genişletmeleri için tasarlanmıştır."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash, Google'ın en son çok modlu AI modelidir, hızlı işleme yeteneğine sahiptir, metin, görüntü ve video girişi destekler, çeşitli görevler için verimli bir şekilde ölçeklenebilir."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001, geniş uygulama alanları için destekleyen verimli bir çok modlu modeldir."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002, geniş uygulama yelpazesini destekleyen verimli bir çok modlu modeldir."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827, büyük ölçekli görev senaryolarını işlemek için tasarlanmış, eşsiz bir işleme hızı sunar."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B, geniş uygulama yelpazesini destekleyen verimli bir çok modlu modeldir."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924, metin ve çok modlu kullanım durumlarında önemli performans artışları sunan en son deneysel modeldir."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827, çeşitli karmaşık görev senaryoları için optimize edilmiş çok modlu işleme yeteneği sunar."
+ "description": "Gemini 1.5 Flash 0827, optimize edilmiş çok modlu işleme yetenekleri sunarak çeşitli karmaşık görev sahnelerine uygundur."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash, Google'ın en son çok modlu AI modelidir, hızlı işleme yeteneğine sahiptir ve metin, görüntü ve video girişi destekler, çeşitli görevlerin verimli bir şekilde genişletilmesine olanak tanır."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002, daha yüksek kaliteli çıktılar sunan en son üretim hazır modeldir; özellikle matematik, uzun bağlam ve görsel görevlerde önemli iyileştirmeler sağlamaktadır."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801, mükemmel çok modlu işleme yeteneği sunar ve uygulama geliştirmeye daha fazla esneklik kazandırır."
+ "description": "Gemini 1.5 Pro 0801, olağanüstü çok modlu işleme yetenekleri sunarak uygulama geliştirmeye daha fazla esneklik getirir."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827, en son optimize edilmiş teknolojileri bir araya getirerek daha verimli çok modlu veri işleme yeteneği sunar."
+ "description": "Gemini 1.5 Pro 0827, en son optimize edilmiş teknolojilerle birleştirilmiş daha verimli çok modlu veri işleme yeteneği sunar."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro, 2 milyon token'a kadar destekler, orta ölçekli çok modlu modeller için ideal bir seçimdir ve karmaşık görevler için çok yönlü destek sunar."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash, mükemmel hız, yerel araç kullanımı, çok modlu üretim ve 1M token bağlam penceresi dahil olmak üzere bir sonraki nesil özellikler ve iyileştirmeler sunar."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash, mükemmel hız, yerel araç kullanımı, çok modlu üretim ve 1M token bağlam penceresi dahil olmak üzere bir sonraki nesil özellikler ve iyileştirmeler sunar."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash model varyantı, maliyet etkinliği ve düşük gecikme gibi hedefler için optimize edilmiştir."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash model varyantı, maliyet etkinliği ve düşük gecikme gibi hedefler için optimize edilmiştir."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Maliyet etkinliği ve düşük gecikme gibi hedefler için optimize edilmiş bir Gemini 2.0 Flash modelidir."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp, Google'ın en son deneysel çok modlu AI modelidir, bir sonraki nesil özelliklere, olağanüstü hıza, yerel araç çağrısına ve çok modlu üretime sahiptir."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp, Google'ın en son deneysel çok modlu AI modelidir, bir sonraki nesil özelliklere, olağanüstü hıza, yerel araç çağrısına ve çok modlu üretime sahiptir."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Deneysel, Google'ın en son deneysel çok modlu AI modelidir ve önceki sürümlere göre belirli bir kalite artışı sağlamaktadır, özellikle dünya bilgisi, kod ve uzun bağlam için."
+ },
"gemma-7b-it": {
"description": "Gemma 7B, orta ölçekli görev işleme için uygundur ve maliyet etkinliği sunar."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2, Google tarafından sunulan verimli bir modeldir, küçük uygulamalardan karmaşık veri işleme senaryolarına kadar çeşitli uygulama alanlarını kapsar."
},
- "general": {
- "description": "Spark Lite, son derece düşük gecikme ve yüksek verimlilik sunan hafif bir büyük dil modelidir, tamamen ücretsiz ve açık olup, gerçek zamanlı çevrimiçi arama işlevini destekler. Hızlı yanıt verme özelliği, düşük hesaplama gücüne sahip cihazlarda çıkarım uygulamaları ve model ince ayarlarında mükemmel performans gösterir, kullanıcılara mükemmel maliyet etkinliği ve akıllı deneyim sunar, özellikle bilgi sorgulama, içerik oluşturma ve arama senaryolarında başarılıdır."
- },
"generalv3": {
"description": "Spark Pro, profesyonel alanlar için optimize edilmiş yüksek performanslı büyük dil modelidir, matematik, programlama, sağlık, eğitim gibi birçok alana odaklanır ve çevrimiçi arama ile yerleşik hava durumu, tarih gibi eklentileri destekler. Optimize edilmiş modeli, karmaşık bilgi sorgulama, dil anlama ve yüksek düzeyde metin oluşturma konularında mükemmel performans ve yüksek verimlilik sergiler, profesyonel uygulama senaryoları için ideal bir seçimdir."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520, son derece karmaşık ve çeşitli görevler için tasarlanmış en yeni model versiyonudur, olağanüstü performans sergiler."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat, anlam, matematik, akıl yürütme, kod ve bilgi gibi birçok alanda yüksek performans göstermektedir. Ayrıca web tarayıcı, kod yürütme, özel araç çağrıları ve uzun metin akıl yürütme yeteneklerine sahiptir. Japonca, Korece, Almanca dahil olmak üzere 26 dil desteği sunmaktadır."
+ },
"glm-4-air": {
"description": "GLM-4-Air, maliyet etkin bir versiyondur, GLM-4'e yakın performans sunar ve hızlı hız ve uygun fiyat sağlar."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash, basit görevleri işlemek için ideal bir seçimdir, en hızlı ve en uygun fiyatlıdır."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX, Flash'ın geliştirilmiş bir versiyonudur ve ultra hızlı çıkarım hızı sunar."
+ },
"glm-4-long": {
"description": "GLM-4-Long, ultra uzun metin girişlerini destekler, bellek tabanlı görevler ve büyük ölçekli belge işleme için uygundur."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V, güçlü görüntü anlama ve akıl yürütme yetenekleri sunar, çeşitli görsel görevleri destekler."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash, hızlı görsel analiz veya toplu görsel işleme gibi sahnelerde, tek bir görüntü anlayışına odaklanarak etkili bir performans sunar."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus, video içeriği ve çoklu görüntüleri anlama yeteneğine sahiptir, çok modlu görevler için uygundur."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827, optimize edilmiş çok modlu işleme yetenekleri sunar ve çeşitli karmaşık görev senaryolarına uygundur."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview, karmaşık akıl yürütme yeteneklerine sahip olup, mantıksal akıl yürütme, matematik, programlama gibi alanlarda mükemmel performans sergilemektedir."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash, mükemmel hız, yerel araç kullanımı, çok modlu üretim ve 1M token bağlam penceresi dahil olmak üzere bir sonraki nesil özellikler ve iyileştirmeler sunar."
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Deneysel, Google'ın en son deneysel çok modlu AI modelidir ve önceki sürümlere göre belirli bir kalite artışı sağlamaktadır, özellikle dünya bilgisi, kod ve uzun bağlam için."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash, optimize edilmiş çok modlu işleme yetenekleri sunar ve çeşitli karmaşık görev senaryolarına uygundur."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827, en son optimize edilmiş teknolojileri birleştirerek daha verimli çok modlu veri işleme yetenekleri sunar."
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro, en son optimize edilmiş teknolojileri birleştirerek daha verimli çok modlu veri işleme yetenekleri sunar."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2, Google tarafından sunulan verimli bir modeldir, küçük uygulamalardan karmaşık veri işleme senaryolarına kadar çeşitli uygulama alanlarını kapsar."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2, hafiflik ve verimlilik tasarım felsefesini sürdürmektedir."
},
+ "google/gemma-2-2b-it": {
+ "description": "Google'ın hafif talimat ayarlama modeli"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2, Google tarafından sunulan verimli bir modeldir, küçük uygulamalardan karmaşık veri işleme senaryolarına kadar çeşitli uygulama alanlarını kapsar."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2, Google'ın hafif açık kaynak metin modeli serisidir."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, çeşitli metin üretimi ve anlama görevleri için uygundur, şu anda gpt-3.5-turbo-0125'e işaret ediyor."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo, OpenAI tarafından sağlanan verimli bir modeldir ve sohbet ve metin üretim görevleri için uygundur, paralel fonksiyon çağrılarını destekler."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k, karmaşık görevler için uygun yüksek kapasiteli bir metin üretim modelidir."
+ },
"gpt-4": {
"description": "GPT-4, daha büyük bir bağlam penceresi sunarak daha uzun metin girişlerini işleyebilir, geniş bilgi entegrasyonu ve veri analizi gerektiren senaryolar için uygundur."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "En son GPT-4 Turbo modeli görsel işlevselliğe sahiptir. Artık görsel talepler JSON formatı ve fonksiyon çağrıları ile işlenebilir. GPT-4 Turbo, çok modlu görevler için maliyet etkin bir destek sunan geliştirilmiş bir versiyondur. Doğruluk ve verimlilik arasında bir denge sağlar, gerçek zamanlı etkileşim gerektiren uygulama senaryoları için uygundur."
},
- "gpt-4-1106-vision-preview": {
- "description": "En son GPT-4 Turbo modeli görsel işlevselliğe sahiptir. Artık görsel talepler JSON formatı ve fonksiyon çağrıları ile işlenebilir. GPT-4 Turbo, çok modlu görevler için maliyet etkin bir destek sunan geliştirilmiş bir versiyondur. Doğruluk ve verimlilik arasında bir denge sağlar, gerçek zamanlı etkileşim gerektiren uygulama senaryoları için uygundur."
- },
"gpt-4-32k": {
"description": "GPT-4, daha büyük bir bağlam penceresi sunarak daha uzun metin girişlerini işleyebilir, geniş bilgi entegrasyonu ve veri analizi gerektiren senaryolar için uygundur."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "En son GPT-4 Turbo modeli görsel işlevselliğe sahiptir. Artık görsel talepler JSON formatı ve fonksiyon çağrıları ile işlenebilir. GPT-4 Turbo, çok modlu görevler için maliyet etkin bir destek sunan geliştirilmiş bir versiyondur. Doğruluk ve verimlilik arasında bir denge sağlar, gerçek zamanlı etkileşim gerektiren uygulama senaryoları için uygundur."
},
+ "gpt-4.5-preview": {
+ "description": "GPT-4.5'in araştırma önizleme sürümü, şimdiye kadar geliştirdiğimiz en büyük ve en güçlü GPT modelidir. Geniş bir dünya bilgisine sahip olup, kullanıcı niyetlerini daha iyi anlayarak yaratıcı görevler ve bağımsız planlama konularında mükemmel bir performans sergilemektedir. GPT-4.5, metin ve görsel girdi alabilir ve metin çıktısı (yapılandırılmış çıktı dahil) üretebilir. Fonksiyon çağrıları, toplu API ve akış çıktısı gibi önemli geliştirici özelliklerini destekler. Yaratıcılık, açık düşünme ve diyalog gerektiren görevlerde (örneğin yazma, öğrenme veya yeni fikirler keşfetme) GPT-4.5 özellikle başarılıdır. Bilgi kesim tarihi Ekim 2023'tür."
+ },
"gpt-4o": {
"description": "ChatGPT-4o, güncel versiyonunu korumak için gerçek zamanlı olarak güncellenen dinamik bir modeldir. Güçlü dil anlama ve üretme yeteneklerini birleştirir, müşteri hizmetleri, eğitim ve teknik destek gibi geniş ölçekli uygulama senaryoları için uygundur."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o, güncel versiyonunu korumak için gerçek zamanlı olarak güncellenen dinamik bir modeldir. Güçlü dil anlama ve üretme yeteneklerini birleştirir, müşteri hizmetleri, eğitim ve teknik destek gibi geniş ölçekli uygulama senaryoları için uygundur."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o, güncel en son sürümü korumak için gerçek zamanlı olarak güncellenen dinamik bir modeldir. Müşteri hizmetleri, eğitim ve teknik destek gibi büyük ölçekli uygulama senaryoları için güçlü dil anlama ve üretme yeteneklerini bir araya getirir."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o Ses modeli, sesli giriş ve çıkış desteği sunar."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini, OpenAI'nin GPT-4 Omni'den sonra tanıttığı en yeni modeldir. Görsel ve metin girişi destekler ve metin çıktısı verir. En gelişmiş küçük model olarak, diğer son zamanlardaki öncü modellere göre çok daha ucuzdur ve GPT-3.5 Turbo'dan %60'tan fazla daha ucuzdur. En son teknolojiyi korurken, önemli bir maliyet etkinliği sunar. GPT-4o mini, MMLU testinde %82 puan almış olup, şu anda sohbet tercihleri açısından GPT-4'ün üzerinde yer almaktadır."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "GPT-4o-mini gerçek zamanlı versiyonu, ses ve metin için gerçek zamanlı giriş ve çıkış desteği sunar."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "GPT-4o gerçek zamanlı versiyonu, ses ve metin için gerçek zamanlı giriş ve çıkış desteği sunar."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "GPT-4o gerçek zamanlı versiyonu, ses ve metin için gerçek zamanlı giriş ve çıkış desteği sunar."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "GPT-4o gerçek zamanlı versiyonu, ses ve metin için gerçek zamanlı giriş ve çıkış desteği sunar."
+ },
+ "grok-2-1212": {
+ "description": "Bu model, doğruluk, talimat takibi ve çok dilli yetenekler açısından geliştirilmiştir."
+ },
+ "grok-2-vision-1212": {
+ "description": "Bu model, doğruluk, talimat takibi ve çok dilli yetenekler açısından geliştirilmiştir."
+ },
+ "grok-beta": {
+ "description": "Grok 2 ile karşılaştırılabilir performansa sahip, ancak daha yüksek verimlilik, hız ve işlevsellik sunar."
+ },
+ "grok-vision-beta": {
+ "description": "En son görüntü anlama modeli, belgeler, grafikler, ekran görüntüleri ve fotoğraflar gibi çeşitli görsel bilgileri işleyebilir."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B, birden fazla üst düzey modelin birleşimiyle yaratıcı ve zeka odaklı bir dil modelidir."
},
+ "hunyuan-code": {
+ "description": "Hunyuan'ın en son kod oluşturma modeli, 200B yüksek kaliteli kod verisi ile artırılmış temel model ile altı ay boyunca yüksek kaliteli SFT verisi eğitimi almıştır. Bağlam penceresi uzunluğu 8K'ya çıkarılmıştır ve beş büyük dil için kod oluşturma otomatik değerlendirme göstergelerinde ön sıralardadır; beş büyük dilde 10 kriterin her yönüyle yüksek kaliteli değerlendirmelerde performansı birinci sıradadır."
+ },
+ "hunyuan-functioncall": {
+ "description": "Hunyuan'ın en son MOE mimarisi FunctionCall modeli, yüksek kaliteli FunctionCall verisi ile eğitilmiş olup, bağlam penceresi 32K'ya ulaşmıştır ve birçok boyutta değerlendirme göstergelerinde lider konumdadır."
+ },
+ "hunyuan-large": {
+ "description": "Hunyuan-large modelinin toplam parametre sayısı yaklaşık 389B, etkin parametre sayısı yaklaşık 52B'dir; bu, mevcut endüstrideki en büyük parametre ölçeğine sahip ve en iyi performansı gösteren Transformer mimarisinin açık kaynaklı MoE modelidir."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Uzun metin görevlerini, örneğin belge özeti ve belge sorgulama gibi, işleme konusunda uzmandır; aynı zamanda genel metin oluşturma görevlerini de yerine getirme yeteneğine sahiptir. Uzun metinlerin analizi ve oluşturulmasında mükemmel bir performans sergiler, karmaşık ve ayrıntılı uzun metin içerik işleme ihtiyaçlarına etkili bir şekilde yanıt verebilir."
+ },
+ "hunyuan-lite": {
+ "description": "MOE yapısına yükseltilmiş, bağlam penceresi 256k, NLP, kod, matematik, endüstri gibi birçok değerlendirme setinde birçok açık kaynak modelden önde."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Hunyuan'ın en son 7B çok modlu modeli, bağlam penceresi 32K, Çince ve İngilizce senaryolarında çok modlu diyalog, görüntü nesne tanıma, belge tablo anlama, çok modlu matematik vb. destekler; birçok boyutta değerlendirme kriterleri 7B rakip modellerden üstündür."
+ },
+ "hunyuan-pro": {
+ "description": "Trilyon seviyesinde parametre ölçeğine sahip MOE-32K uzun metin modeli. Çeşitli benchmarklarda kesin bir liderlik seviyesine ulaşarak, karmaşık talimatlar ve akıl yürütme yetenekleri ile karmaşık matematik yetenekleri sunar, functioncall desteği ile çok dilli çeviri, finans, hukuk ve sağlık gibi alanlarda önemli optimizasyonlar sağlar."
+ },
+ "hunyuan-role": {
+ "description": "Hunyuan'ın en son rol yapma modeli, Hunyuan resmi ince ayar eğitimi ile geliştirilmiş rol yapma modelidir. Hunyuan modeli ile rol yapma senaryosu veri seti birleştirilerek artırılmıştır ve rol yapma senaryolarında daha iyi temel performans sunmaktadır."
+ },
+ "hunyuan-standard": {
+ "description": "Daha iyi bir yönlendirme stratejisi kullanarak, yük dengeleme ve uzman yakınsaması sorunlarını hafifletir. Uzun metinlerde, iğne arama göstergesi %99.9'a ulaşmaktadır. MOE-32K, uzun metin girişlerini işleme yeteneği ile etki ve fiyat dengesini sağlarken, maliyet açısından daha yüksek bir değer sunar."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Daha iyi bir yönlendirme stratejisi kullanarak, yük dengeleme ve uzman yakınsaması sorunlarını hafifletir. Uzun metinlerde, iğne arama göstergesi %99.9'a ulaşmaktadır. MOE-256K, uzunluk ve etki açısından daha fazla bir sıçrama yaparak, girdi uzunluğunu büyük ölçüde genişletir."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Hunyuan'ın en son çok modlu modeli, çok dilli yanıtları destekler, Çince ve İngilizce yetenekleri dengelidir."
+ },
+ "hunyuan-translation": {
+ "description": "Çince ve İngilizce, Japonca, Fransızca, Portekizce, İspanyolca, Türkçe, Rusça, Arapça, Korece, İtalyanca, Almanca, Vietnamca, Malayca, Endonezyaca dahil olmak üzere 15 dil arasında çeviri desteği sunar. Çoklu senaryo çeviri değerlendirme setine dayalı otomatik değerlendirme COMET puanı ile, ondan fazla yaygın dildeki çeviri yetenekleri, pazarın aynı ölçekli modellerine göre genel olarak daha üstündür."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Hunyuan çeviri modeli, doğal dil diyalog tarzı çeviriyi destekler; Çince ve İngilizce, Japonca, Fransızca, Portekizce, İspanyolca, Türkçe, Rusça, Arapça, Korece, İtalyanca, Almanca, Vietnamca, Malayca, Endonezyaca dahil olmak üzere 15 dil arasında çeviri desteği sunar."
+ },
+ "hunyuan-turbo": {
+ "description": "Hunyuan'ın yeni nesil büyük dil modelinin önizleme sürümü, tamamen yeni bir karma uzman modeli (MoE) yapısı kullanır ve hunyuan-pro'ya kıyasla daha hızlı çıkarım verimliliği ve daha güçlü performans sunar."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Hunyuan-turbo 2024 yılı 11 ay 20 günü sabit sürümü, hunyuan-turbo ve hunyuan-turbo-latest arasında bir versiyon."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Bu sürümde yapılan optimizasyonlar: veri talimatı ölçeklendirme, modelin genel genelleme yeteneğini büyük ölçüde artırma; matematik, kodlama, mantıksal akıl yürütme yeteneklerini büyük ölçüde artırma; metin anlama ve kelime anlama ile ilgili yetenekleri optimize etme; metin oluşturma içerik üretim kalitesini optimize etme."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Genel deneyim optimizasyonu, NLP anlama, metin oluşturma, sohbet, bilgi sorgulama, çeviri, alan vb. dahil; insan benzeri özellikleri artırma, modelin duygusal zekasını optimize etme; niyet belirsiz olduğunda modelin aktif olarak netleştirme yeteneğini artırma; kelime ve terim analizi ile ilgili sorunların işlenme yeteneğini artırma; yaratım kalitesini ve etkileşimliğini artırma; çoklu tur deneyimini geliştirme."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Hunyuan'ın yeni nesil görsel dil amiral modeli, tamamen yeni bir karışık uzman modeli (MoE) yapısını benimser; metin ve görüntü anlama ile ilgili temel tanıma, içerik oluşturma, bilgi sorgulama, analiz ve akıl yürütme gibi yeteneklerde bir önceki nesil modele göre kapsamlı bir iyileştirme sağlar."
+ },
+ "hunyuan-vision": {
+ "description": "Hunyuan'ın en son çok modlu modeli, resim + metin girişi ile metin içeriği oluşturmayı destekler."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Yenilikçi açık kaynak modeli InternLM2.5, büyük ölçekli parametreler ile diyalog zekasını artırmıştır."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5, çoklu senaryolarda akıllı diyalog çözümleri sunar."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct modeli, 70B parametreye sahiptir ve büyük metin üretimi ve talimat görevlerinde mükemmel performans sunar."
+ "internlm2-pro-chat": {
+ "description": "Hala bakımını yaptığımız eski sürüm model, 7B ve 20B gibi çeşitli model parametreleri sunmaktadır."
+ },
+ "internlm2.5-latest": {
+ "description": "En son model serimiz, olağanüstü çıkarım performansına sahiptir, 1M bağlam uzunluğunu destekler ve daha güçlü talimat takibi ve araç çağırma yetenekleri sunar."
+ },
+ "internlm3-latest": {
+ "description": "En son model serimiz, olağanüstü çıkarım performansına sahiptir ve aynı ölçekli açık kaynak modeller arasında liderdir. Varsayılan olarak en son yayımlanan InternLM3 serisi modellerine işaret eder."
+ },
+ "jina-deepsearch-v1": {
+ "description": "Derin arama, web araması, okuma ve akıl yürütmeyi birleştirerek kapsamlı bir araştırma yapar. Bunu, araştırma görevlerinizi kabul eden bir ajan olarak düşünebilirsiniz - geniş bir arama yapar ve birden fazla yineleme ile cevap verir. Bu süreç, sürekli araştırma, akıl yürütme ve sorunları çeşitli açılardan çözmeyi içerir. Bu, doğrudan önceden eğitilmiş verilerden cevaplar üreten standart büyük modellerle ve tek seferlik yüzey aramasına dayanan geleneksel RAG sistemleriyle temelde farklıdır."
+ },
+ "kimi-latest": {
+ "description": "Kimi akıllı asistan ürünü, en son Kimi büyük modelini kullanır ve henüz kararlı olmayan özellikler içerebilir. Görüntü anlayışını desteklerken, isteğin bağlam uzunluğuna göre 8k/32k/128k modelini faturalama modeli olarak otomatik olarak seçecektir."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM, öğrenme bilimleri ilkelerine uygun olarak eğitilmiş, görev odaklı deneysel bir dil modelidir. Eğitim ve öğrenim senaryolarında sistem talimatlarını takip edebilir ve uzman bir mentor olarak görev alabilir."
+ },
+ "lite": {
+ "description": "Spark Lite, son derece düşük gecikme süresi ve yüksek verimlilikle çalışan hafif bir büyük dil modelidir. Tamamen ücretsiz ve açık olup, gerçek zamanlı çevrimiçi arama işlevini desteklemektedir. Hızlı yanıt verme özelliği, düşük hesaplama gücüne sahip cihazlarda çıkarım uygulamaları ve model ince ayarlarında mükemmel performans sergileyerek, kullanıcılara maliyet etkinliği ve akıllı deneyim sunmakta, özellikle bilgi sorgulama, içerik oluşturma ve arama senaryolarında başarılı olmaktadır."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B, daha güçlü AI akıl yürütme yeteneği sunar, karmaşık uygulamalar için uygundur ve yüksek verimlilik ve doğruluk sağlamak için çok sayıda hesaplama işlemini destekler."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B, hızlı metin üretim yeteneği sunan yüksek performanslı bir modeldir ve büyük ölçekli verimlilik ve maliyet etkinliği gerektiren uygulama senaryoları için son derece uygundur."
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct modeli, 8B parametreye sahiptir ve görsel talimat görevlerinin etkili bir şekilde yürütülmesini sağlar, kaliteli metin üretim yetenekleri sunar."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Yüksek çözünürlüklü görüntülerde mükemmel görüntü akıl yürütme yeteneği, görsel anlama uygulamaları için uygundur."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Online modeli, 405B parametreye sahiptir ve yaklaşık 127,000 belirteçlik bağlam uzunluğunu destekler, karmaşık çevrimiçi sohbet uygulamaları için tasarlanmıştır."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2, görsel ve metin verilerini birleştiren görevleri işlemek için tasarlanmıştır. Görüntü tanımlama ve görsel soru-cevap gibi görevlerde mükemmel performans sergiler, dil üretimi ile görsel akıl yürütme arasındaki uçurumu aşar."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chat modeli, 70B parametreye sahiptir ve yaklaşık 127,000 belirteçlik bağlam uzunluğunu destekler, karmaşık çevrimdışı sohbet görevleri için uygundur."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Görsel anlayış ajan uygulamaları için ileri düzey görüntü akıl yürütme yeteneği."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Online modeli, 70B parametreye sahiptir ve yaklaşık 127,000 belirteçlik bağlam uzunluğunu destekler, yüksek kapasiteli ve çeşitli sohbet görevleri için uygundur."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2, görsel ve metin verilerini birleştiren görevleri işlemek için tasarlanmıştır. Görüntü tanımlama ve görsel soru-cevap gibi görevlerde mükemmel performans sergiler, dil üretimi ile görsel akıl yürütme arasındaki uçurumu aşar."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chat modeli, 8B parametreye sahiptir ve çevrimdışı sohbet için tasarlanmıştır, yaklaşık 127,000 belirteçlik bağlam uzunluğunu destekler."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3, Llama serisinin en gelişmiş çok dilli açık kaynak büyük dil modelidir ve 405B modelinin performansını çok düşük maliyetle deneyimlemenizi sağlar. Transformer yapısına dayanmaktadır ve denetimli ince ayar (SFT) ve insan geri bildirimi ile güçlendirilmiş öğrenme (RLHF) ile faydalılığını ve güvenliğini artırmıştır. Talimat ayarlı versiyonu, çok dilli diyaloglar için optimize edilmiştir ve birçok endüstri kıyaslamasında birçok açık kaynak ve kapalı sohbet modelinden daha iyi performans göstermektedir. Bilgi kesim tarihi 2023 Aralık'tır."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Online modeli, 8B parametreye sahiptir ve yaklaşık 127,000 belirteçlik bağlam uzunluğunu destekler, çevrimiçi sohbet için tasarlanmıştır ve çeşitli metin etkileşimlerini etkili bir şekilde işler."
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 çok dilli büyük dil modeli (LLM), 70B (metin girişi/metin çıkışı) içindeki önceden eğitilmiş ve talimat ayarlanmış bir üretim modelidir. Llama 3.3 talimat ayarlı saf metin modeli, çok dilli konuşma kullanım durumları için optimize edilmiştir ve yaygın endüstri kıyaslamalarında mevcut birçok açık kaynak ve kapalı sohbet modelinden daha üstündür."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B, eşsiz karmaşıklık işleme yeteneği sunar ve yüksek talepli projeler için özel olarak tasarlanmıştır."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral, bilimsel araştırma ve matematik akıl yürütme için tasarlanmış, etkili hesaplama yetenekleri ve sonuç açıklamaları sunar."
},
+ "max-32k": {
+ "description": "Spark Max 32K, büyük bağlam işleme yeteneği ile donatılmıştır ve daha güçlü bağlam anlama ve mantıksal çıkarım yetenekleri sunmaktadır. 32K token'lık metin girişi desteklemekte olup, uzun belgelerin okunması, özel bilgi sorgulama gibi senaryolar için uygundur."
+ },
"meta-llama-3-70b-instruct": {
"description": "Akıl yürütme, kodlama ve geniş dil uygulamalarında mükemmel bir 70 milyar parametreli model."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B), mükemmel dil işleme yetenekleri ve olağanüstü etkileşim deneyimi sunar."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2, mükemmel dil işleme yeteneği ve üstün etkileşim deneyimi sunar."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B), karmaşık diyalog ihtiyaçlarını destekleyen güçlü bir sohbet modelidir."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B), çok dilli desteği ile zengin alan bilgilerini kapsar."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2, görsel ve metin verilerini bir arada işleme amacıyla tasarlanmıştır. Görüntü betimleme ve görsel soru yanıtlama gibi görevlerde mükemmel performans sergiler, dil üretimi ve görsel akıl yürütme arasındaki boşluğu kapar."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2, görsel ve metin verilerini bir arada işleme amacıyla tasarlanmıştır. Görüntü betimleme ve görsel soru yanıtlama gibi görevlerde mükemmel performans sergiler, dil üretimi ve görsel akıl yürütme arasındaki boşluğu kapar."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2, görsel ve metin verilerini bir arada işleme amacıyla tasarlanmıştır. Görüntü betimleme ve görsel soru yanıtlama gibi görevlerde mükemmel performans sergiler, dil üretimi ve görsel akıl yürütme arasındaki boşluğu kapar."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3, Llama serisinin en gelişmiş çok dilli açık kaynak büyük dil modelidir, 405B modelinin performansını çok düşük maliyetle deneyimleme imkanı sunar. Transformer yapısına dayanır ve denetimli ince ayar (SFT) ve insan geri bildirimi ile güçlendirilmiş öğrenme (RLHF) ile kullanılabilirlik ve güvenliği artırılmıştır. Talimat ayarlı versiyonu çok dilli diyaloglar için optimize edilmiştir ve birçok endüstri standardında birçok açık kaynak ve kapalı sohbet modelinden daha iyi performans göstermektedir. Bilgi kesim tarihi 2023 Aralık'tır."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 çok dilli büyük dil modeli (LLM), 70B (metin girişi/metin çıkışı) içinde önceden eğitilmiş ve talimat ayarlı bir üretim modelidir. Llama 3.3 talimat ayarlı saf metin modeli, çok dilli diyalog kullanım durumları için optimize edilmiştir ve yaygın endüstri standartlarında birçok mevcut açık kaynak ve kapalı sohbet modelinden daha iyi performans göstermektedir."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2, görsel ve metin verilerini bir arada işleme amacıyla tasarlanmıştır. Görüntü betimleme ve görsel soru yanıtlama gibi görevlerde mükemmel performans sergiler, dil üretimi ve görsel akıl yürütme arasındaki boşluğu kapar."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite, yüksek performans ve düşük gecikme gerektiren ortamlara uygundur."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "405B Llama 3.1 Turbo modeli, büyük veri işleme için devasa bağlam desteği sunar ve büyük ölçekli AI uygulamalarında öne çıkar."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1, Meta tarafından sunulan öncü bir modeldir, 405B parametreye kadar destekler ve karmaşık diyaloglar, çok dilli çeviri ve veri analizi alanlarında uygulanabilir."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B, çok dilli yüksek verimli diyalog desteği sunmaktadır."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct, yüksek kaliteli diyalog senaryoları için optimize edilmiştir ve birçok kapalı kaynak modelden daha iyi performans göstermektedir."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct, Meta'nın en son sunduğu versiyon olup, yüksek kaliteli diyalog üretimi için optimize edilmiştir ve birçok önde gelen kapalı kaynak modelden daha iyi performans göstermektedir."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct, yüksek kaliteli diyalog için tasarlanmış olup, insan değerlendirmelerinde öne çıkmakta ve özellikle yüksek etkileşimli senaryolar için uygundur."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1, çok dilli destek sunar ve sektördeki en önde gelen üretim modellerinden biridir."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2, görsel ve metin verilerini birleştiren görevleri işlemek için tasarlanmıştır. Görüntü tanımlama ve görsel soru yanıtlama gibi görevlerde mükemmel performans sergileyerek dil üretimi ve görsel akıl yürütme arasındaki boşluğu kapatmaktadır."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2, görsel ve metin verilerini birleştiren görevleri işlemek için tasarlanmıştır. Görüntü tanımlama ve görsel soru yanıtlama gibi görevlerde mükemmel performans sergileyerek dil üretimi ve görsel akıl yürütme arasındaki boşluğu kapatmaktadır."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3, Llama serisinin en gelişmiş çok dilli açık kaynak büyük dil modelidir ve 405B modelinin performansını çok düşük maliyetle deneyimlemenizi sağlar. Transformer yapısına dayanmaktadır ve denetimli ince ayar (SFT) ve insan geri bildirimi ile güçlendirilmiş öğrenme (RLHF) ile faydalılığını ve güvenliğini artırmıştır. Talimat ayarlı versiyonu, çok dilli diyaloglar için optimize edilmiştir ve birçok endüstri kıyaslamasında birçok açık kaynak ve kapalı sohbet modelinden daha iyi performans göstermektedir. Bilgi kesim tarihi 2023 Aralık'tır."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3, Llama serisinin en gelişmiş çok dilli açık kaynak büyük dil modelidir ve 405B modelinin performansını çok düşük maliyetle deneyimlemenizi sağlar. Transformer yapısına dayanmaktadır ve denetimli ince ayar (SFT) ve insan geri bildirimi ile güçlendirilmiş öğrenme (RLHF) ile faydalılığını ve güvenliğini artırmıştır. Talimat ayarlı versiyonu, çok dilli diyaloglar için optimize edilmiştir ve birçok endüstri kıyaslamasında birçok açık kaynak ve kapalı sohbet modelinden daha iyi performans göstermektedir. Bilgi kesim tarihi 2023 Aralık'tır."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct, Llama 3.1 Instruct modelinin en büyük ve en güçlü versiyonudur. Bu, son derece gelişmiş bir diyalog akıl yürütme ve veri sentezleme modelidir ve belirli alanlarda uzmanlaşmış sürekli ön eğitim veya ince ayar için bir temel olarak da kullanılabilir. Llama 3.1, çok dilli büyük dil modelleri (LLM'ler) sunar ve 8B, 70B ve 405B boyutlarında önceden eğitilmiş, talimat ayarlı üretim modellerinden oluşur (metin girişi/çıkışı). Llama 3.1'in talimat ayarlı metin modelleri (8B, 70B, 405B), çok dilli diyalog kullanım durumları için optimize edilmiştir ve yaygın endüstri benchmark testlerinde birçok mevcut açık kaynaklı sohbet modelini geride bırakmıştır. Llama 3.1, çok dilli ticari ve araştırma amaçları için tasarlanmıştır. Talimat ayarlı metin modelleri, asistan benzeri sohbetler için uygundur, önceden eğitilmiş modeller ise çeşitli doğal dil üretim görevlerine uyum sağlayabilir. Llama 3.1 modeli, diğer modellerin çıktısını iyileştirmek için de kullanılabilir, bu da veri sentezleme ve rafine etme işlemlerini içerir. Llama 3.1, optimize edilmiş bir transformer mimarisi kullanarak oluşturulmuş bir otoregresif dil modelidir. Ayarlanmış versiyon, insan yardımseverliği ve güvenlik tercihleri ile uyumlu hale getirmek için denetimli ince ayar (SFT) ve insan geri bildirimi ile güçlendirilmiş öğrenme (RLHF) kullanır."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3, geliştiriciler, araştırmacılar ve işletmeler için açık bir büyük dil modelidir (LLM) ve onların üretken AI fikirlerini inşa etmelerine, denemelerine ve sorumlu bir şekilde genişletmelerine yardımcı olmak için tasarlanmıştır. Küresel topluluk yeniliğinin temel sistemlerinden biri olarak, sınırlı hesaplama gücü ve kaynaklara sahip, kenar cihazları ve daha hızlı eğitim süreleri için son derece uygundur."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B, Microsoft AI'nın en son hızlı ve hafif modelidir ve mevcut açık kaynak lider modellerin performansına yakın bir performans sunmaktadır."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "Gelişmiş LLM, sentetik veri üretimi, bilgi damıtma ve akıl yürütmeyi destekler, sohbet botları, programlama ve belirli alan görevleri için uygundur."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Karmaşık diyalogları güçlendiren, mükemmel bağlam anlama, akıl yürütme yeteneği ve metin üretimi yeteneğine sahip."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "En son teknolojiye sahip model, dil anlama, mükemmel akıl yürütme yeteneği ve metin üretimi yeteneğine sahiptir."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Gelişmiş görsel-dil modeli, görüntülerden yüksek kaliteli akıl yürütme yapma konusunda uzmandır."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "En son teknolojiye sahip küçük dil modeli, dil anlama, mükemmel akıl yürütme yeteneği ve metin üretimi yeteneğine sahiptir."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "En son teknolojiye sahip küçük dil modeli, dil anlama, mükemmel akıl yürütme yeteneği ve metin üretimi yeteneğine sahiptir."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Gelişmiş görsel-dil modeli, görüntülerden yüksek kaliteli akıl yürütme yapma konusunda uzmandır."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Akıllı LLM, akıl yürütme, matematik, genel bilgi ve fonksiyon çağrılarında uzmandır."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2, Microsoft AI tarafından sağlanan bir dil modelidir ve karmaşık diyaloglar, çok dilli destek, akıl yürütme ve akıllı asistan alanlarında özellikle başarılıdır."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B, Microsoft'un en gelişmiş AI Wizard modelidir ve son derece rekabetçi bir performans sergiler."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V, OpenBMB tarafından sunulan yeni nesil çok modlu büyük bir modeldir; olağanüstü OCR tanıma ve çok modlu anlama yeteneklerine sahiptir ve geniş bir uygulama yelpazesini destekler."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B, Mistral'ın dünya çapında en üst düzey kenar modelidir."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B, Mistral'ın fiyat-performans oranı oldukça yüksek kenar modelidir."
+ },
"mistral": {
"description": "Mistral, Mistral AI tarafından sunulan 7B modelidir, değişken dil işleme ihtiyaçları için uygundur."
},
"mistral-large": {
"description": "Mixtral Large, Mistral'ın amiral gemisi modelidir, kod üretimi, matematik ve akıl yürütme yeteneklerini birleştirir, 128k bağlam penceresini destekler."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407), en son akıl yürütme, bilgi ve kodlama yetenekleri ile gelişmiş bir Büyük Dil Modelidir (LLM)."
- },
"mistral-large-latest": {
"description": "Mistral Large, çok dilli görevler, karmaşık akıl yürütme ve kod üretimi için ideal bir seçimdir ve yüksek uç uygulamalar için tasarlanmıştır."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3, geniş uygulamalar için etkili hesaplama gücü ve doğal dil anlama sunar."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B, kompakt ancak yüksek performanslı bir modeldir, sınıflandırma ve metin üretimi gibi basit görevlerde iyi bir akıl yürütme yeteneği ile yoğun işlem yapma konusunda uzmandır."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B), son derece büyük bir dil modelidir ve çok yüksek işleme taleplerini destekler."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B, genel metin görevleri için kullanılan önceden eğitilmiş seyrek karışık uzman modelidir."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B, birden fazla parametre kullanarak akıl yürütme hızını artıran seyrek uzman modelidir, çok dilli ve kod üretim görevleri için uygundur."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct, hız optimizasyonu ve uzun bağlam desteği sunan yüksek performanslı bir endüstri standart modelidir."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K, ultra uzun bağlam işleme yeteneğine sahip bir modeldir, karmaşık üretim görevlerini karşılamak için ultra uzun metinler üretmekte kullanılabilir, 128,000 token'a kadar içeriği işleyebilir, araştırma, akademik ve büyük belgelerin üretilmesi gibi uygulama senaryoları için son derece uygundur."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Kimi görsel modeli (moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview gibi) resim içeriğini anlayabilir, resim metni, resim rengi ve nesne şekilleri gibi içerikleri kapsar."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K, orta uzunlukta bağlam işleme yeteneği sunar, 32,768 token'ı işleyebilir, çeşitli uzun belgeler ve karmaşık diyaloglar üretmek için özellikle uygundur, içerik oluşturma, rapor üretimi ve diyalog sistemleri gibi alanlarda kullanılabilir."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Kimi görsel modeli (moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview gibi) resim içeriğini anlayabilir, resim metni, resim rengi ve nesne şekilleri gibi içerikleri kapsar."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K, kısa metin görevleri için tasarlanmış, yüksek verimlilikte işleme performansı sunar, 8,192 token'ı işleyebilir, kısa diyaloglar, not alma ve hızlı içerik üretimi için son derece uygundur."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Kimi görsel modeli (moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview gibi) resim içeriğini anlayabilir, resim metni, resim rengi ve nesne şekilleri gibi içerikleri kapsar."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto, mevcut bağlamın kullandığı Token sayısına göre uygun modeli seçebilir."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B, Nous Hermes 2'nin güncellenmiş versiyonudur ve en son iç geliştirme veri setlerini içermektedir."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B, NVIDIA tarafından özelleştirilmiş büyük bir dil modelidir ve LLM tarafından üretilen yanıtların kullanıcı sorgularına yardımcı olma düzeyini artırmayı amaçlamaktadır. Bu model, Arena Hard, AlpacaEval 2 LC ve GPT-4-Turbo MT-Bench gibi standart testlerde mükemmel performans sergilemiştir ve 1 Ekim 2024 itibarıyla tüm üç otomatik hizalama testinde birinci sıradadır. Model, Llama-3.1-70B-Instruct modelinin temelinde RLHF (özellikle REINFORCE), Llama-3.1-Nemotron-70B-Reward ve HelpSteer2-Preference ipuçları kullanılarak eğitilmiştir."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Eşsiz bir dil modeli, benzersiz doğruluk ve verimlilik sunar."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct, NVIDIA'nın özel olarak geliştirdiği büyük dil modelidir ve LLM tarafından üretilen yanıtların yardımcı olmasını artırmayı amaçlar."
+ },
+ "o1": {
+ "description": "Gelişmiş çıkarım ve karmaşık sorunları çözmeye odaklanır, matematik ve bilim görevlerini içerir. Derin bağlam anlayışı ve aracılık iş akışları gerektiren uygulamalar için son derece uygundur."
+ },
"o1-mini": {
"description": "o1-mini, programlama, matematik ve bilim uygulama senaryoları için tasarlanmış hızlı ve ekonomik bir akıl yürütme modelidir. Bu model, 128K bağlam ve Ekim 2023 bilgi kesim tarihi ile donatılmıştır."
},
"o1-preview": {
"description": "o1, OpenAI'nin geniş genel bilgiye ihtiyaç duyan karmaşık görevler için uygun yeni bir akıl yürütme modelidir. Bu model, 128K bağlam ve Ekim 2023 bilgi kesim tarihi ile donatılmıştır."
},
+ "o3-mini": {
+ "description": "o3-mini, aynı maliyet ve gecikme hedefleriyle yüksek zeka sunan en yeni küçük ölçekli çıkarım modelimizdir."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba, kod üretimine odaklanan Mamba 2 dil modelidir ve ileri düzey kod ve akıl yürütme görevlerine güçlü destek sunar."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B, birden fazla parametre kullanarak akıl yürütme hızını artıran seyrek uzman modelidir, çok dilli ve kod üretim görevlerini işlemek için uygundur."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o, dinamik bir modeldir; en güncel versiyonu korumak için gerçek zamanlı olarak güncellenir. Güçlü dil anlama ve üretme yeteneklerini birleştirir, geniş ölçekli uygulama senaryoları için uygundur; müşteri hizmetleri, eğitim ve teknik destek gibi."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o, güncel en son sürümü korumak için gerçek zamanlı olarak güncellenen dinamik bir modeldir. Güçlü dil anlama ve üretme yeteneklerini birleştirir, müşteri hizmetleri, eğitim ve teknik destek gibi büyük ölçekli uygulama senaryoları için uygundur."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini, OpenAI'nin GPT-4 Omni'den sonra sunduğu en son modeldir; görsel ve metin girişi destekler ve metin çıktısı verir. En gelişmiş küçük model olarak, diğer son zamanlardaki öncü modellere göre çok daha ucuzdur ve GPT-3.5 Turbo'dan %60'tan fazla daha ucuzdur. En son teknolojiyi korurken, önemli bir maliyet etkinliği sunar. GPT-4o mini, MMLU testinde %82 puan almış olup, şu anda sohbet tercihleri açısından GPT-4'ün üzerinde bir sıralamaya sahiptir."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Pixtral modeli, grafik ve görüntü anlama, belge yanıtı, çok modlu akıl yürütme ve talimat takibi gibi görevlerde güçlü yetenekler sergiler, doğal çözünürlük ve en boy oranında görüntüleri alabilir ve 128K token uzunluğunda bir bağlam penceresinde herhangi bir sayıda görüntüyü işleyebilir."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large, 1240 milyar parametreye sahip açık kaynaklı çok modlu bir modeldir ve Mistral Large 2 üzerine inşa edilmiştir. Bu, çok modlu ailemizdeki ikinci modeldir ve öncü düzeyde görüntü anlama yetenekleri sergilemektedir."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K, olağanüstü bağlam işleme yeteneği ile donatılmıştır ve 128K'ya kadar bağlam bilgilerini işleyebilir. Özellikle uzun metinlerin bütünsel analizi ve uzun vadeli mantıksal ilişkilerin işlenmesi gereken durumlar için uygundur ve karmaşık metin iletişiminde akıcı ve tutarlı bir mantık ile çeşitli alıntı desteği sunmaktadır."
+ },
+ "qvq-72b-preview": {
+ "description": "QVQ modeli, Qwen ekibi tarafından geliştirilen deneysel bir araştırma modelidir; görsel akıl yürütme yeteneğini artırmaya odaklanır, özellikle matematik akıl yürütme alanında."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Tongyi Qianwen kod modeli."
+ },
"qwen-coder-turbo-latest": {
"description": "Tongyi Qianwen kodlama modeli."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Tongyi Qianwen matematik modeli, matematik problemlerini çözmek için özel olarak tasarlanmış bir dil modelidir."
},
+ "qwen-max": {
+ "description": "Tongyi Qianwen, 100 milyar seviyesinde büyük ölçekli bir dil modelidir ve Çince, İngilizce gibi farklı dil girişlerini destekler; şu anda Tongyi Qianwen 2.5 ürün sürümünün arkasındaki API modelidir."
+ },
"qwen-max-latest": {
"description": "Tongyi Qianwen, 100 milyar seviyesinde büyük bir dil modeli, Çince, İngilizce ve diğer dillerde girişleri destekler, şu anda Tongyi Qianwen 2.5 ürün versiyonunun arkasındaki API modelidir."
},
+ "qwen-omni-turbo-latest": {
+ "description": "Qwen-Omni serisi modeller, video, ses, resim ve metin gibi çeşitli modlarda veri girişi destekler ve ses ile metin çıktısı verir."
+ },
+ "qwen-plus": {
+ "description": "Tongyi Qianwen, Çince, İngilizce gibi farklı dil girişlerini destekleyen geliştirilmiş büyük ölçekli bir dil modelidir."
+ },
"qwen-plus-latest": {
"description": "Tongyi Qianwen'in geliştirilmiş versiyonu, çok dilli girişleri destekler."
},
+ "qwen-turbo": {
+ "description": "Tongyi Qianwen, Çince, İngilizce gibi farklı dil girişlerini destekleyen büyük ölçekli bir dil modelidir."
+ },
"qwen-turbo-latest": {
"description": "Tongyi Qianwen, çok dilli bir dil modeli, Çince, İngilizce ve diğer dillerde girişleri destekler."
},
"qwen-vl-chat-v1": {
"description": "Tongyi Qianwen VL, çoklu görüntü, çok turlu soru-cevap, yaratım gibi esnek etkileşim yöntemlerini destekleyen bir modeldir."
},
- "qwen-vl-max": {
- "description": "Tongyi Qianwen, büyük ölçekli görsel dil modelidir. Geliştirilmiş versiyonuna göre görsel akıl yürütme ve talimatları takip etme yeteneklerini daha da artırır, daha yüksek görsel algı ve biliş düzeyi sunar."
+ "qwen-vl-max-latest": {
+ "description": "Tongyi Qianwen ultra büyük ölçekli görsel dil modeli. Geliştirilmiş versiyona kıyasla, görsel akıl yürütme yeteneğini ve talimatlara uyum yeteneğini bir kez daha artırır, daha yüksek görsel algı ve bilişsel seviyeler sunar."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Tongyi Qianwen OCR, belge, tablo, sınav soruları, el yazısı gibi çeşitli görüntü türlerinden metin çıkarma yeteneğine odaklanan özel bir modeldir. Birçok yazıyı tanıyabilir, şu anda desteklenen diller: Çince, İngilizce, Fransızca, Japonca, Korece, Almanca, Rusça, İtalyanca, Vietnamca, Arapça."
},
- "qwen-vl-plus": {
- "description": "Tongyi Qianwen, büyük ölçekli görsel dil modelinin geliştirilmiş versiyonudur. Detay tanıma ve metin tanıma yeteneklerini önemli ölçüde artırır, bir milyondan fazla piksel çözünürlüğü ve herhangi bir en-boy oranı spesifikasyonunu destekler."
+ "qwen-vl-plus-latest": {
+ "description": "Tongyi Qianwen büyük ölçekli görsel dil modelinin geliştirilmiş versiyonu. Detay tanıma ve metin tanıma yeteneklerini büyük ölçüde artırır, bir milyondan fazla piksel çözünürlüğü ve herhangi bir en-boy oranındaki görüntüleri destekler."
},
"qwen-vl-v1": {
"description": "Qwen-7B dil modeli ile başlatılan, 448 çözünürlükte görüntü girişi olan önceden eğitilmiş bir modeldir."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2, tamamen yeni bir Qwen büyük dil modeli serisidir. Qwen2 7B, dil anlama, çok dilli yetenek, programlama, matematik ve akıl yürütme konularında mükemmel performans sergileyen bir transformer tabanlı modeldir."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2, daha güçlü anlama ve üretme yeteneklerine sahip yeni bir büyük dil modeli serisidir."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL, Qwen-VL modelinin en son yineleme versiyonudur ve MathVista, DocVQA, RealWorldQA ve MTVQA gibi görsel anlama benchmark testlerinde en gelişmiş performansa ulaşmıştır. Qwen2-VL, yüksek kaliteli video tabanlı soru-cevap, diyalog ve içerik oluşturma için 20 dakikadan fazla videoyu anlayabilmektedir. Ayrıca, karmaşık akıl yürütme ve karar verme yeteneklerine sahiptir ve mobil cihazlar, robotlar gibi sistemlerle entegre olarak görsel ortam ve metin talimatlarına dayalı otomatik işlemler gerçekleştirebilmektedir. İngilizce ve Çince'nin yanı sıra, Qwen2-VL artık çoğu Avrupa dili, Japonca, Korece, Arapça ve Vietnamca gibi farklı dillerdeki metinleri de anlayabilmektedir."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct, Alibaba Cloud tarafından yayınlanan en son büyük dil modeli serilerinden biridir. Bu 72B modeli, kodlama ve matematik gibi alanlarda önemli iyileştirmelere sahiptir. Model ayrıca, Çince, İngilizce gibi 29'dan fazla dili kapsayan çok dilli destek sunmaktadır. Model, talimat takibi, yapılandırılmış verileri anlama ve yapılandırılmış çıktı (özellikle JSON) üretme konularında önemli gelişmeler göstermektedir."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct, Alibaba Cloud tarafından yayınlanan en son büyük dil modeli serilerinden biridir. Bu 32B modeli, kodlama ve matematik gibi alanlarda önemli iyileştirmelere sahiptir. Model, Çince, İngilizce gibi 29'dan fazla dili kapsayan çok dilli destek sunmaktadır. Model, talimat takibi, yapılandırılmış verileri anlama ve yapılandırılmış çıktı (özellikle JSON) üretme konularında önemli gelişmeler göstermektedir."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "Çince ve İngilizce'ye yönelik LLM, dil, programlama, matematik, akıl yürütme gibi alanlara odaklanır."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "Gelişmiş LLM, kod üretimi, akıl yürütme ve düzeltme desteği sunar, ana akım programlama dillerini kapsar."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Güçlü orta ölçekli kod modeli, 32K bağlam uzunluğunu destekler, çok dilli programlama konusunda uzmandır."
+ },
"qwen2": {
"description": "Qwen2, Alibaba'nın yeni nesil büyük ölçekli dil modelidir, mükemmel performans ile çeşitli uygulama ihtiyaçlarını destekler."
},
+ "qwen2.5": {
+ "description": "Qwen2.5, Alibaba'nın yeni nesil büyük ölçekli dil modelidir ve mükemmel performansıyla çeşitli uygulama ihtiyaçlarını desteklemektedir."
+ },
"qwen2.5-14b-instruct": {
"description": "Tongyi Qianwen 2.5, halka açık 14B ölçeğinde bir modeldir."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Tongyi Qianwen 2.5, 72B ölçeğinde açık kaynak olarak sunulmuştur."
+ },
"qwen2.5-32b-instruct": {
"description": "Tongyi Qianwen 2.5, halka açık 32B ölçeğinde bir modeldir."
},
@@ -824,13 +1599,16 @@
"description": "Tongyi Qianwen 2.5, halka açık 7B ölçeğinde bir modeldir."
},
"qwen2.5-coder-1.5b-instruct": {
- "description": "Tongyi Qianwen kodlama modelinin açık kaynak versiyonu."
+ "description": "Tongyi Qianwen kodlama modelinin açık kaynak sürümüdür."
+ },
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Tongyi Qianwen kod modeli açık kaynak versiyonu."
},
"qwen2.5-coder-7b-instruct": {
"description": "Tongyi Qianwen kodlama modelinin açık kaynak versiyonu."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Qwen-Math modeli, güçlü matematik problem çözme yeteneklerine sahiptir."
+ "description": "Qwen-Math modeli, güçlü matematiksel problem çözme yeteneklerine sahiptir."
},
"qwen2.5-math-72b-instruct": {
"description": "Qwen-Math modeli, güçlü matematik problem çözme yeteneklerine sahiptir."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Qwen-Math modeli, güçlü matematik problem çözme yeteneklerine sahiptir."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Talimat takibi, matematik, problem çözme, kodlama genelinde iyileştirme, her türlü nesneyi tanıma yeteneği artışı, çeşitli formatları doğrudan hassas bir şekilde görsel unsurları konumlandırma desteği, uzun video dosyalarını (en fazla 10 dakika) anlama ve saniye düzeyinde olay anlarını konumlandırma yeteneği, zaman sıralamasını ve hızını anlama, analiz ve konumlandırma yeteneğine dayanarak OS veya Mobil ajanları kontrol etme desteği, anahtar bilgileri çıkarma yeteneği ve Json formatında çıktı verme yeteneği güçlüdür, bu sürüm 72B versiyonudur, bu serinin en güçlü versiyonudur."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Talimat takibi, matematik, problem çözme, kodlama genelinde iyileştirme, her türlü nesneyi tanıma yeteneği artışı, çeşitli formatları doğrudan hassas bir şekilde görsel unsurları konumlandırma desteği, uzun video dosyalarını (en fazla 10 dakika) anlama ve saniye düzeyinde olay anlarını konumlandırma yeteneği, zaman sıralamasını ve hızını anlama, analiz ve konumlandırma yeteneğine dayanarak OS veya Mobil ajanları kontrol etme desteği, anahtar bilgileri çıkarma yeteneği ve Json formatında çıktı verme yeteneği güçlüdür, bu sürüm 72B versiyonudur, bu serinin en güçlü versiyonudur."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5, Alibaba'nın yeni nesil büyük ölçekli dil modelidir ve mükemmel performansıyla çeşitli uygulama ihtiyaçlarını desteklemektedir."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5, Alibaba'nın yeni nesil büyük ölçekli dil modelidir ve mükemmel performansıyla çeşitli uygulama ihtiyaçlarını desteklemektedir."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5, Alibaba'nın yeni nesil büyük ölçekli dil modelidir ve mükemmel performansıyla çeşitli uygulama ihtiyaçlarını desteklemektedir."
+ },
"qwen2:0.5b": {
"description": "Qwen2, Alibaba'nın yeni nesil büyük ölçekli dil modelidir, mükemmel performans ile çeşitli uygulama ihtiyaçlarını destekler."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2, Alibaba'nın yeni nesil büyük ölçekli dil modelidir, mükemmel performans ile çeşitli uygulama ihtiyaçlarını destekler."
},
- "solar-1-mini-chat": {
- "description": "Solar Mini, kompakt bir LLM'dir, GPT-3.5'ten daha iyi performans gösterir, güçlü çok dilli yeteneklere sahiptir, İngilizce ve Koreceyi destekler, etkili ve hafif bir çözüm sunar."
+ "qwq": {
+ "description": "QwQ, AI akıl yürütme yeteneklerini artırmaya odaklanan deneysel bir araştırma modelidir."
+ },
+ "qwq-32b": {
+ "description": "Qwen2.5-32B modeli üzerine eğitilmiş QwQ çıkarım modeli, pekiştirmeli öğrenme ile modelin çıkarım yeteneğini önemli ölçüde artırmıştır. Modelin matematiksel kodları ve diğer temel göstergeleri (AIME 24/25, LiveCodeBench) ile bazı genel göstergeleri (IFEval, LiveBench vb.) DeepSeek-R1 tam sürüm seviyesine ulaşmıştır ve tüm göstergeler, yine Qwen2.5-32B tabanlı olan DeepSeek-R1-Distill-Qwen-32B'yi önemli ölçüde aşmaktadır."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja), Solar Mini'nin yeteneklerini genişletir, Japonca'ya odaklanır ve İngilizce ile Korece kullanımında yüksek verimlilik ve mükemmel performans sunar."
+ "qwq-32b-preview": {
+ "description": "QwQ modeli, Qwen ekibi tarafından geliştirilen deneysel bir araştırma modelidir ve AI akıl yürütme yeteneklerini artırmaya odaklanmaktadır."
+ },
+ "qwq-plus-latest": {
+ "description": "Qwen2.5 modeli üzerine eğitilmiş QwQ çıkarım modeli, pekiştirmeli öğrenme ile modelin çıkarım yeteneğini önemli ölçüde artırmıştır. Modelin matematiksel kodları ve diğer temel göstergeleri (AIME 24/25, LiveCodeBench) ile bazı genel göstergeleri (IFEval, LiveBench vb.) DeepSeek-R1 tam sürüm seviyesine ulaşmıştır."
+ },
+ "r1-1776": {
+ "description": "R1-1776, DeepSeek R1 modelinin bir versiyonudur ve son eğitimle, sansürsüz, tarafsız gerçek bilgileri sunar."
+ },
+ "solar-mini": {
+ "description": "Solar Mini, GPT-3.5'ten daha iyi performansa sahip kompakt bir LLM'dir, güçlü çok dilli yeteneklere sahiptir, İngilizce ve Korece'yi destekler ve etkili, kompakt çözümler sunar."
+ },
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja), Solar Mini'nin yeteneklerini genişletir, Japonca'ya odaklanır ve İngilizce ile Korece kullanımında yüksek verimlilik ve mükemmel performans sağlar."
},
"solar-pro": {
"description": "Solar Pro, Upstage tarafından sunulan yüksek akıllı LLM'dir, tek GPU talimat takibi yeteneğine odaklanır, IFEval puanı 80'in üzerindedir. Şu anda İngilizceyi desteklemekte olup, resmi versiyonu 2024 Kasım'da piyasaya sürülmesi planlanmaktadır ve dil desteği ile bağlam uzunluğunu genişletecektir."
},
+ "sonar": {
+ "description": "Arama bağlamına dayalı hafif bir arama ürünüdür, Sonar Pro'dan daha hızlı ve daha ucuzdur."
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research, kapsamlı uzman düzeyinde araştırmalar yapar ve bunları erişilebilir, uygulanabilir raporlar haline getirir."
+ },
+ "sonar-pro": {
+ "description": "Gelişmiş sorgular ve takip desteği sunan, arama bağlamını destekleyen bir üst düzey arama ürünüdür."
+ },
+ "sonar-reasoning": {
+ "description": "DeepSeek akıl yürütme modeli tarafından desteklenen yeni API ürünü."
+ },
+ "sonar-reasoning-pro": {
+ "description": "DeepSeek'in akıl yürütme modeli tarafından desteklenen yeni API ürünü."
+ },
"step-1-128k": {
"description": "Performans ve maliyet arasında denge sağlar, genel senaryolar için uygundur."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Yüksek hızlı model, gerçek zamanlı diyaloglar için uygundur."
},
+ "step-1.5v-mini": {
+ "description": "Bu model, güçlü bir video anlama yeteneğine sahiptir."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Bu model, güçlü bir görüntü anlama yeteneğine sahiptir, matematik ve kod alanında 1o'dan daha üstündür. Model, 1o'dan daha küçüktür ve çıktı hızı daha yüksektir."
+ },
+ "step-1o-vision-32k": {
+ "description": "Bu model, güçlü bir görüntü anlama yeteneğine sahiptir. Step-1v serisi modellere kıyasla daha güçlü bir görsel performansa sahiptir."
+ },
"step-1v-32k": {
"description": "Görsel girdi desteği sunar, çok modlu etkileşim deneyimini artırır."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Büyük ölçekli bağlam etkileşimlerini destekler, karmaşık diyalog senaryoları için uygundur."
},
+ "step-2-mini": {
+ "description": "Yeni nesil kendi geliştirdiğimiz MFA Attention mimarisine dayanan hızlı büyük model, çok düşük maliyetle step1 ile benzer sonuçlar elde ederken, daha yüksek bir throughput ve daha hızlı yanıt süresi sağlıyor. Genel görevleri işleyebilme yeteneğine sahip olup, kodlama yeteneklerinde uzmanlık gösteriyor."
+ },
"taichu_llm": {
"description": "Zidong Taichu dil büyük modeli, güçlü dil anlama yeteneği ile metin oluşturma, bilgi sorgulama, kod programlama, matematik hesaplama, mantıksal akıl yürütme, duygu analizi, metin özeti gibi yeteneklere sahiptir. Yenilikçi bir şekilde büyük veri ön eğitimi ile çok kaynaklı zengin bilgiyi birleştirir, algoritma teknolojisini sürekli olarak geliştirir ve büyük metin verilerinden kelime, yapı, dil bilgisi, anlam gibi yeni bilgileri sürekli olarak edinir, modelin performansını sürekli olarak evrimleştirir. Kullanıcılara daha kolay bilgi ve hizmetler sunar ve daha akıllı bir deneyim sağlar."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V, görüntü anlama, bilgi aktarımı, mantıksal çıkarım gibi yetenekleri birleştirerek, metin ve görsel soru-cevap alanında öne çıkmaktadır."
+ "taichu_vl": {
+ "description": "Görüntü anlama, bilgi transferi, mantıksal çıkarım gibi yetenekleri birleştirir ve görsel-işitsel soru-cevap alanında öne çıkar."
+ },
+ "text-embedding-3-large": {
+ "description": "En güçlü vektörleştirme modeli, İngilizce ve diğer dillerdeki görevler için uygundur."
+ },
+ "text-embedding-3-small": {
+ "description": "Verimli ve ekonomik yeni nesil Embedding modeli, bilgi arama, RAG uygulamaları gibi senaryolar için uygundur."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Zhi Pu AI tarafından yayınlanan GLM-4 serisinin en son nesil ön eğitim modelinin açık kaynak versiyonudur."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B), etkili stratejiler ve model mimarisi ile artırılmış hesaplama yetenekleri sunar."
},
+ "tts-1": {
+ "description": "En son metinden sese model, gerçek zamanlı senaryolar için hız optimizasyonu yapılmıştır."
+ },
+ "tts-1-hd": {
+ "description": "En son metinden sese model, kaliteyi optimize etmek için tasarlanmıştır."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B), ince ayar gerektiren talimat görevleri için uygundur ve mükemmel dil işleme yetenekleri sunar."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet, endüstri standartlarını yükselterek, rakip modelleri ve Claude 3 Opus'u aşan performans sergilemekte; geniş değerlendirmelerde mükemmel sonuçlar verirken, orta seviye modellerimizin hız ve maliyetine sahiptir."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet, Anthropic'in en hızlı bir sonraki nesil modelidir. Claude 3 Haiku ile karşılaştırıldığında, Claude 3.7 Sonnet, tüm becerilerde iyileşmeler göstermiştir ve birçok zeka standart testinde bir önceki neslin en büyük modeli olan Claude 3 Opus'u geride bırakmıştır."
+ },
+ "whisper-1": {
+ "description": "Genel ses tanıma modeli, çok dilli ses tanıma, ses çevirisi ve dil tanıma desteği sunar."
+ },
"wizardlm2": {
"description": "WizardLM 2, Microsoft AI tarafından sunulan bir dil modelidir, karmaşık diyaloglar, çok dilli, akıl yürütme ve akıllı asistan alanlarında özellikle başarılıdır."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Son derece yüksek maliyet performansı ve mükemmel performans. Performans ve akıl yürütme hızı, maliyet açısından yüksek hassasiyetli ayarlama yapılır."
},
+ "yi-lightning": {
+ "description": "En yeni yüksek performanslı model, yüksek kaliteli çıktıları garanti ederken akıl yürütme hızını büyük ölçüde artırır."
+ },
+ "yi-lightning-lite": {
+ "description": "Hafif versiyon, yi-lightning kullanımını önerir."
+ },
"yi-medium": {
"description": "Orta boyutlu model, dengeli yetenekler ve yüksek maliyet performansı sunar. Talimat takibi yetenekleri derinlemesine optimize edilmiştir."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Karmaşık görsel görevler için model, yüksek performanslı resim anlama ve analiz yetenekleri sunar."
+ },
+ "yi-vision-v2": {
+ "description": "Karmaşık görsel görevler için model, birden fazla resme dayalı yüksek performanslı anlama ve analiz yetenekleri sunar."
}
}
diff --git a/DigitalHumanWeb/locales/tr-TR/plugin.json b/DigitalHumanWeb/locales/tr-TR/plugin.json
index 45374ab..d96ba0f 100644
--- a/DigitalHumanWeb/locales/tr-TR/plugin.json
+++ b/DigitalHumanWeb/locales/tr-TR/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "{{name}} eklentisi yenilenemedi",
"urlError": "Bağlantı JSON formatında içerik döndürmedi. Lütfen geçerli bir bağlantı olduğundan emin olun"
},
+ "inspector": {
+ "args": "Parametre listesini görüntüle",
+ "pluginRender": "Eklenti arayüzünü görüntüle"
+ },
"list": {
"item": {
"deprecated.title": "Eski",
@@ -130,6 +134,34 @@
"plugin": "Eklenti çalışıyor..."
},
"pluginList": "Eklenti Listesi",
+ "search": {
+ "config": {
+ "addKey": "Anahtar Ekle",
+ "close": "Sil",
+ "confirm": "Yapılandırma tamamlandı ve yeniden denendi"
+ },
+ "crawPages": {
+ "crawling": "Bağlantı tanımlanıyor",
+ "detail": {
+ "preview": "Önizleme",
+ "raw": "Ham metin",
+ "tooLong": "Metin içeriği çok uzun, diyalog bağlamında yalnızca ilk {{characters}} karakter saklanacak, fazlası diyalog bağlamına dahil edilmeyecek."
+ },
+ "meta": {
+ "crawler": "Tarayıcı Modu",
+ "words": "Karakter sayısı"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Lütfen girin",
+ "description": "SearchXNG'nin URL'sini girin, böylece çevrimiçi arama yapmaya başlayabilirsiniz",
+ "keyPlaceholder": "Anahtarı girin",
+ "title": "SearchXNG Arama Motorunu Yapılandır",
+ "unconfiguredDesc": "Lütfen yöneticinizle iletişime geçin ve SearchXNG arama motoru yapılandırmasını tamamlayın, böylece çevrimiçi arama yapmaya başlayabilirsiniz",
+ "unconfiguredTitle": "SearchXNG Arama Motoru Henüz Yapılandırılmadı"
+ },
+ "title": "Çevrimiçi Arama"
+ },
"setting": "Eklenti Ayarları",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/tr-TR/portal.json b/DigitalHumanWeb/locales/tr-TR/portal.json
index 11bcdca..674a4d5 100644
--- a/DigitalHumanWeb/locales/tr-TR/portal.json
+++ b/DigitalHumanWeb/locales/tr-TR/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Eklentiler",
- "actions": {
- "genAiMessage": "Yapay Zeka Mesajı Oluştur",
- "summary": "Özet",
- "summaryTooltip": "Mevcut içeriği özetle"
- },
"artifacts": {
"display": {
"code": "Kod",
diff --git a/DigitalHumanWeb/locales/tr-TR/providers.json b/DigitalHumanWeb/locales/tr-TR/providers.json
index 73a7b3a..47c28e1 100644
--- a/DigitalHumanWeb/locales/tr-TR/providers.json
+++ b/DigitalHumanWeb/locales/tr-TR/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs, işletmeler için temel modeller ve yapay zeka sistemleri geliştirerek, üretimde jeneratif yapay zekanın uygulanmasını hızlandırır."
+ },
"ai360": {
"description": "360 AI, 360 şirketi tarafından sunulan yapay zeka modeli ve hizmet platformudur. 360GPT2 Pro, 360GPT Pro, 360GPT Turbo ve 360GPT Turbo Responsibility 8K gibi çeşitli gelişmiş doğal dil işleme modelleri sunmaktadır. Bu modeller, büyük ölçekli parametreler ve çok modlu yetenekleri birleştirerek metin üretimi, anlamsal anlama, diyalog sistemleri ve kod üretimi gibi alanlarda geniş bir uygulama yelpazesine sahiptir. Esnek fiyatlandırma stratejileri ile 360 AI, çeşitli kullanıcı ihtiyaçlarını karşılamakta ve geliştiricilerin entegrasyonunu destekleyerek akıllı uygulamaların yenilik ve gelişimini teşvik etmektedir."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure, GPT-3.5 ve en son GPT-4 serisi gibi çeşitli gelişmiş yapay zeka modelleri sunar. Farklı veri türlerini ve karmaşık görevleri destekleyerek güvenli, güvenilir ve sürdürülebilir yapay zeka çözümleri sağlamaya odaklanmaktadır."
},
+ "azureai": {
+ "description": "Azure, GPT-3.5 ve en son GPT-4 serisi dahil olmak üzere çeşitli gelişmiş AI modelleri sunar, çeşitli veri türlerini ve karmaşık görevleri destekler, güvenli, güvenilir ve sürdürülebilir AI çözümlerine odaklanır."
+ },
"baichuan": {
"description": "Baichuan Intelligent, yapay zeka büyük modellerinin geliştirilmesine odaklanan bir şirkettir. Modelleri, yerel bilgi ansiklopedisi, uzun metin işleme ve üretim gibi Çince görevlerde mükemmel performans sergilemekte ve uluslararası ana akım modelleri aşmaktadır. Baichuan Intelligent ayrıca sektördeki lider çok modlu yeteneklere sahiptir ve birçok otoriter değerlendirmede mükemmel sonuçlar elde etmiştir. Modelleri, Baichuan 4, Baichuan 3 Turbo ve Baichuan 3 Turbo 128k gibi farklı uygulama senaryolarına yönelik optimize edilmiş yüksek maliyet etkinliği çözümleri sunmaktadır."
},
"bedrock": {
"description": "Bedrock, Amazon AWS tarafından sunulan bir hizmettir ve işletmelere gelişmiş yapay zeka dil modelleri ve görsel modeller sağlamaya odaklanmaktadır. Model ailesi, Anthropic'in Claude serisi, Meta'nın Llama 3.1 serisi gibi seçenekleri içermekte olup, metin üretimi, diyalog, görüntü işleme gibi çeşitli görevleri desteklemektedir. Farklı ölçek ve ihtiyaçlara uygun kurumsal uygulamalar için geniş bir yelpaze sunmaktadır."
},
+ "cloudflare": {
+ "description": "Cloudflare'ın küresel ağı üzerinde sunucusuz GPU destekli makine öğrenimi modelleri çalıştırın."
+ },
"deepseek": {
"description": "DeepSeek, yapay zeka teknolojisi araştırma ve uygulamalarına odaklanan bir şirkettir. En son modeli DeepSeek-V2.5, genel diyalog ve kod işleme yeteneklerini birleştirerek, insan tercihleriyle uyum, yazma görevleri ve talimat takibi gibi alanlarda önemli iyileştirmeler sağlamaktadır."
},
+ "doubao": {
+ "description": "ByteDance tarafından geliştirilen kendi büyük modeli. ByteDance içindeki 50'den fazla iş senaryosunda uygulama doğrulaması ile, günlük trilyon seviyesinde token kullanımı ile sürekli olarak geliştirilmekte, çeşitli modalite yetenekleri sunmakta ve kaliteli model performansı ile işletmelere zengin iş deneyimleri yaratmaktadır."
+ },
"fireworksai": {
"description": "Fireworks AI, işlev çağrısı ve çok modlu işleme üzerine odaklanan önde gelen bir gelişmiş dil modeli hizmet sağlayıcısıdır. En son modeli Firefunction V2, Llama-3 tabanlıdır ve işlev çağrısı, diyalog ve talimat takibi için optimize edilmiştir. Görsel dil modeli FireLLaVA-13B, görüntü ve metin karışık girişi desteklemektedir. Diğer dikkat çekici modeller arasında Llama serisi ve Mixtral serisi bulunmaktadır ve etkili çok dilli talimat takibi ve üretim desteği sunmaktadır."
},
+ "giteeai": {
+ "description": "Gitee AI'nin Sunucusuz API, AI geliştiricileri kutusun dışında büyük modeller infeksiyon API hizmetini sağlar."
+ },
"github": {
"description": "GitHub Modelleri ile geliştiriciler, AI mühendisleri olabilir ve sektörün önde gelen AI modelleri ile inşa edebilirler."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Groq'un LPU çıkarım motoru, en son bağımsız büyük dil modeli (LLM) benchmark testlerinde mükemmel performans sergilemekte ve olağanüstü hız ve verimliliği ile yapay zeka çözümlerinin standartlarını yeniden tanımlamaktadır. Groq, bulut tabanlı dağıtımlarda iyi bir performans sergileyen anlık çıkarım hızının temsilcisidir."
},
+ "higress": {
+ "description": "Higress, uzun süreli bağlantı işlerine zarar veren Tengine yeniden yükleme sorununu ve gRPC/Dubbo yük dengeleme yeteneklerinin yetersizliğini çözmek için Alibaba içinde geliştirilmiş bir bulut yerel API geçididir."
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API, binlerce modeli keşfetmenin hızlı ve ücretsiz bir yolunu sunar, çeşitli görevler için uygundur. Yeni uygulamalar için prototip oluşturuyor ya da makine öğreniminin yeteneklerini deniyorsanız, bu API size birçok alanda yüksek performanslı modellere anında erişim sağlar."
+ },
+ "hunyuan": {
+ "description": "Tencent tarafından geliştirilen büyük bir dil modeli, güçlü Çince yaratım yeteneklerine, karmaşık bağlamlarda mantıksal akıl yürütme yeteneğine ve güvenilir görev yerine getirme yeteneğine sahiptir."
+ },
+ "internlm": {
+ "description": "Büyük model araştırma ve geliştirme araç zincirine adanmış bir açık kaynak organizasyonu. Tüm AI geliştiricilerine verimli ve kullanımı kolay bir açık kaynak platformu sunarak en son büyük model ve algoritma teknolojilerine erişimi kolaylaştırır."
+ },
+ "jina": {
+ "description": "Jina AI, 2020 yılında kurulmuş, önde gelen bir arama AI şirketidir. Arama tabanlı platformumuz, işletmelerin güvenilir ve yüksek kaliteli üretken AI ve çok modlu arama uygulamaları geliştirmelerine yardımcı olan vektör modelleri, yeniden sıralayıcılar ve küçük dil modelleri içerir."
+ },
+ "lmstudio": {
+ "description": "LM Studio, bilgisayarınızda LLM'ler geliştirmek ve denemeler yapmak için bir masaüstü uygulamasıdır."
+ },
"minimax": {
"description": "MiniMax, 2021 yılında kurulan genel yapay zeka teknolojisi şirketidir ve kullanıcılarla birlikte akıllı çözümler yaratmayı hedeflemektedir. MiniMax, farklı modlarda genel büyük modeller geliştirmiştir. Bunlar arasında trilyon parametreli MoE metin büyük modeli, ses büyük modeli ve görüntü büyük modeli bulunmaktadır. Ayrıca, Conch AI gibi uygulamalar da sunmaktadır."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI, çeşitli büyük dil modelleri ve yapay zeka görüntü üretimi API hizmetleri sunan bir platformdur. Esnek, güvenilir ve maliyet etkin bir yapıya sahiptir. Llama3, Mistral gibi en son açık kaynak modelleri desteklemekte ve üretken yapay zeka uygulama geliştirme için kapsamlı, kullanıcı dostu ve otomatik ölçeklenebilir API çözümleri sunmaktadır. Bu, yapay zeka girişimlerinin hızlı gelişimi için uygundur."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™, bulut, veri merkezi, RTX™ AI kişisel bilgisayarlar ve iş istasyonlarında önceden eğitilmiş ve özelleştirilmiş AI modellerinin dağıtımını destekleyen, kendi kendine barındırılan GPU hızlandırmalı çıkarım mikro hizmetleri için konteynerler sunar."
+ },
"ollama": {
"description": "Ollama'nın sunduğu modeller, kod üretimi, matematiksel işlemler, çok dilli işleme ve diyalog etkileşimi gibi alanları kapsamaktadır. Kurumsal düzeyde ve yerelleştirilmiş dağıtım için çeşitli ihtiyaçları desteklemektedir."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity, çeşitli gelişmiş Llama 3.1 modelleri sunan önde gelen bir diyalog üretim modeli sağlayıcısıdır. Hem çevrimiçi hem de çevrimdışı uygulamaları desteklemekte olup, özellikle karmaşık doğal dil işleme görevleri için uygundur."
},
+ "ppio": {
+ "description": "PPIO Paiou Cloud, istikrarlı ve yüksek maliyet etkinliğe sahip açık kaynak model API hizmeti sunar, DeepSeek'in tüm serisi, Llama, Qwen gibi sektörün önde gelen büyük modellerini destekler."
+ },
"qwen": {
"description": "Tongyi Qianwen, Alibaba Cloud tarafından geliştirilen büyük ölçekli bir dil modelidir ve güçlü doğal dil anlama ve üretme yeteneklerine sahiptir. Çeşitli soruları yanıtlayabilir, metin içeriği oluşturabilir, görüşlerini ifade edebilir ve kod yazabilir. Birçok alanda etkili bir şekilde kullanılmaktadır."
},
+ "sambanova": {
+ "description": "SambaNova Cloud, geliştiricilerin en iyi açık kaynak modellerini kolayca kullanmalarını ve en hızlı çıkarım hızından yararlanmalarını sağlar."
+ },
+ "sensenova": {
+ "description": "SenseTime, güçlü altyapısına dayanarak, verimli ve kullanımı kolay tam yığın büyük model hizmetleri sunar."
+ },
"siliconcloud": {
"description": "SiliconFlow, insanlığa fayda sağlamak amacıyla AGI'yi hızlandırmaya odaklanmakta ve kullanıcı dostu ve maliyet etkin GenAI yığınları ile büyük ölçekli yapay zeka verimliliğini artırmayı hedeflemektedir."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "Çin Bilimler Akademisi Otomasyon Araştırma Enstitüsü ve Wuhan Yapay Zeka Araştırma Enstitüsü, çok modlu büyük modelin yeni neslini sunmaktadır. Çoklu soru-cevap, metin oluşturma, görüntü üretimi, 3D anlama, sinyal analizi gibi kapsamlı soru-cevap görevlerini desteklemekte ve daha güçlü bilişsel, anlama ve yaratma yetenekleri sunarak yeni bir etkileşim deneyimi sağlamaktadır."
},
+ "tencentcloud": {
+ "description": "Bilgi motoru atomik yetenekleri (LLM Knowledge Engine Atomic Power), bilgi motoru üzerine geliştirilmiş bilgi sorgulama tam zincir yetenekleri sunar. Bu yetenekler, işletmeler ve geliştiriciler için esnek model uygulamaları oluşturma ve geliştirme imkanı sağlar. Birden fazla atomik yeteneği kullanarak özel model hizmetlerinizi oluşturabilir, belge analizi, parçalama, embedding, çoklu yeniden yazım gibi hizmetleri bir araya getirerek işletmenize özel AI çözümleri tasarlayabilirsiniz."
+ },
"togetherai": {
"description": "Together AI, yenilikçi yapay zeka modelleri aracılığıyla lider performans elde etmeye odaklanmaktadır. Hızlı ölçeklenme desteği ve sezgisel dağıtım süreçleri dahil olmak üzere geniş özelleştirme yetenekleri sunarak işletmelerin çeşitli ihtiyaçlarını karşılamaktadır."
},
"upstage": {
"description": "Upstage, çeşitli ticari ihtiyaçlar için yapay zeka modelleri geliştirmeye odaklanmaktadır. Solar LLM ve belge AI gibi modeller, insan yapımı genel zeka (AGI) hedeflemektedir. Chat API aracılığıyla basit diyalog ajanları oluşturmakta ve işlev çağrısı, çeviri, gömme ve belirli alan uygulamalarını desteklemektedir."
},
+ "vertexai": {
+ "description": "Google'un Gemini serisi, Google DeepMind tarafından geliştirilen en gelişmiş ve genel amaçlı AI modelleridir. Çok modlu tasarım için özel olarak oluşturulmuş olup, metin, kod, görüntü, ses ve video gibi içeriklerin kesintisiz anlaşılması ve işlenmesini destekler. Veri merkezlerinden mobil cihazlara kadar çeşitli ortamlarda kullanılabilir, AI modellerinin verimliliğini ve uygulama kapsamını büyük ölçüde artırır."
+ },
+ "vllm": {
+ "description": "vLLM, LLM çıkarımı ve hizmetleri için hızlı ve kullanımı kolay bir kütüphanedir."
+ },
+ "volcengine": {
+ "description": "ByteDance tarafından sunulan büyük model hizmetleri geliştirme platformu, zengin özellikler, güvenlik ve rekabetçi fiyatlarla model çağırma hizmetleri sunar. Ayrıca model verileri, ince ayar, çıkarım, değerlendirme gibi uçtan uca işlevler sağlar ve AI uygulama geliştirme sürecinizi her yönüyle güvence altına alır."
+ },
+ "wenxin": {
+ "description": "Kurumsal düzeyde tek duraklı büyük model ve AI yerel uygulama geliştirme ve hizmet platformu, en kapsamlı ve kullanımı kolay üretken yapay zeka modeli geliştirme, uygulama geliştirme için tam süreç araç zinciri sunar."
+ },
+ "xai": {
+ "description": "xAI, insan bilimsel keşiflerini hızlandırmak için yapay zeka geliştirmeye adanmış bir şirkettir. Misyonumuz, evrene dair ortak anlayışımızı ilerletmektir."
+ },
"zeroone": {
"description": "01.AI, yapay zeka 2.0 çağının yapay zeka teknolojisine odaklanmakta ve 'insan + yapay zeka' yenilik ve uygulamalarını teşvik etmektedir. Son derece güçlü modeller ve gelişmiş yapay zeka teknolojileri kullanarak insan üretkenliğini artırmayı ve teknolojik güçlendirmeyi hedeflemektedir."
},
diff --git a/DigitalHumanWeb/locales/tr-TR/setting.json b/DigitalHumanWeb/locales/tr-TR/setting.json
index 772eabb..8b82dbb 100644
--- a/DigitalHumanWeb/locales/tr-TR/setting.json
+++ b/DigitalHumanWeb/locales/tr-TR/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Özel Model Yapılandırması",
"tokens": {
- "title": "Maksimum token sayısı",
- "unlimited": "Sınırsız"
+ "title": "Maksimum token sayısı"
},
"vision": {
"extra": "Bu yapılandırma yalnızca uygulamadaki resim yükleme yapılandırmasını açacaktır; tanıma desteği tamamen modele bağlıdır, lütfen bu modelin görsel tanıma yeteneğini kendiniz test edin.",
@@ -98,6 +97,7 @@
"title": "İstemci Tarafından Veri Alımı"
},
"fetcher": {
+ "clear": "Alınan modeli temizle",
"fetch": "Modelleri Al",
"fetching": "Modelleri alınıyor...",
"latestTime": "Son güncelleme zamanı: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Sohbet sırasında otomatik olarak bir konu oluşturup oluşturmayacağınız, yalnızca geçici konularda etkilidir",
"title": "Otomatik Konu Oluştur"
},
- "enableCompressThreshold": {
- "title": "Geçmiş Mesaj Uzunluğu Sıkıştırma Eşiği Kullan"
+ "enableCompressHistory": {
+ "title": "Geçmiş mesajların otomatik özetini aç"
},
"enableHistoryCount": {
"alias": "Sınırsız",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Max Token Sınırlamasını Etkinleştir"
},
+ "enableReasoningEffort": {
+ "title": "Akıl yürütme yoğunluğunu ayarla"
+ },
"frequencyPenalty": {
- "desc": "Değer ne kadar yüksekse, tekrarlayan kelimeleri azaltma olasılığı o kadar yüksektir",
- "title": "Frequency Penalty"
+ "desc": "Değer ne kadar büyükse, kelime dağarcığı o kadar zengin ve çeşitli olur; değer ne kadar düşükse, kelimeler o kadar sade ve basit olur.",
+ "title": "Kelime Zenginliği"
},
"maxTokens": {
"desc": "Her etkileşim için kullanılan maksimum token sayısı",
@@ -212,19 +215,31 @@
"desc": "{{provider}} Model",
"title": "Model"
},
+ "params": {
+ "title": "Gelişmiş Parametreler"
+ },
"presencePenalty": {
- "desc": "Değer ne kadar yüksekse, yeni konulara genişleme olasılığı o kadar yüksektir",
- "title": "Presence Penalty"
+ "desc": "Değer ne kadar büyükse, farklı ifade biçimlerine yönelme eğilimi artar, kavram tekrarından kaçınılır; değer ne kadar küçükse, tekrar eden kavramlar veya anlatımlar kullanma eğilimi artar, ifade daha tutarlı olur.",
+ "title": "İfade Çeşitliliği"
+ },
+ "reasoningEffort": {
+ "desc": "Değer ne kadar yüksekse, akıl yürütme yeteneği o kadar güçlüdür, ancak yanıt süresi ve Token tüketimini artırabilir",
+ "options": {
+ "high": "Yüksek",
+ "low": "Düşük",
+ "medium": "Orta"
+ },
+ "title": "Akıl yürütme yoğunluğu"
},
"temperature": {
- "desc": "Değer ne kadar yüksekse, yanıt o kadar rastgele olur",
- "title": "Randomness",
- "titleWithValue": "temperature {{value}}"
+ "desc": "Değer ne kadar büyükse, cevap o kadar yaratıcı ve hayal gücü dolu olur; değer ne kadar küçükse, cevap o kadar titizdir.",
+ "title": "Yaratıcılık Aktifliği",
+ "warning": "Yaratıcılık aktifliği değeri çok büyükse, çıktı bozulabilir."
},
"title": "Model Ayarları",
"topP": {
- "desc": "temperature gibi, ancak temperature ile birlikte değişmez",
- "title": "Top P"
+ "desc": "Ne kadar olasılığı dikkate alır, değer ne kadar büyükse, daha fazla olası cevabı kabul eder; değer ne kadar küçükse, en olası cevabı seçme eğilimindedir. Yaratıcılık aktifliği ile birlikte değiştirilmesi önerilmez.",
+ "title": "Düşünce Açıklığı"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Asistan adı, açıklaması, avatar ve etiket oluşturmak için belirlenen model",
"title": "Asistan Bilgilerini Otomatik Oluştur"
},
+ "customPrompt": {
+ "addPrompt": "Özel İpucu Ekle",
+ "desc": "Doldurduğunuzda, sistem asistanı içerik oluştururken özel ipucunu kullanacaktır",
+ "placeholder": "Lütfen özel ipucu kelimelerini girin",
+ "title": "Özel İpucu"
+ },
+ "historyCompress": {
+ "label": "Oturum Geçmişi Modeli",
+ "modelDesc": "Oturum geçmişini sıkıştırmak için kullanılan modeli belirtin",
+ "title": "Oturum Geçmişini Otomatik Olarak Özetle"
+ },
"queryRewrite": {
"label": "Soru Yeniden Yazım Modeli",
"modelDesc": "Kullanıcı sorularını optimize etmek için kullanılan model",
- "title": "Bilgi Tabanı"
+ "title": "Bilgi Tabanı Soru Yeniden Yazımı"
+ },
+ "thread": {
+ "label": "Alt konu adlandırma modeli",
+ "modelDesc": "Alt konuların otomatik olarak yeniden adlandırılması için kullanılan model",
+ "title": "Alt konu otomatik adlandırma"
},
"title": "Sistem Asistanı",
"topic": {
@@ -395,6 +426,7 @@
"common": "Genel Ayarlar",
"experiment": "Deney",
"llm": "Modeller",
+ "provider": "Yapay Zeka Hizmet Sağlayıcısı",
"sync": "Bulut Senkronizasyonu",
"system-agent": "Sistem Asistanı",
"tts": "Metin Seslendirme"
diff --git a/DigitalHumanWeb/locales/tr-TR/thread.json b/DigitalHumanWeb/locales/tr-TR/thread.json
new file mode 100644
index 0000000..8e93824
--- /dev/null
+++ b/DigitalHumanWeb/locales/tr-TR/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Bu alt konuyu silmek üzeresiniz. Silindikten sonra geri alınamaz, lütfen dikkatli olun."
+ },
+ "newPortalThread": {
+ "includeContext": "Konu bağlamını dahil et",
+ "title": "Yeni alt konu aç"
+ },
+ "notSupportMultiModals": "Alt konular şu anda dosya/görüntü yüklemeyi desteklemiyor, ihtiyaç duyarsanız lütfen mesaj bırakın: <1>💬 Tartışma Alanı1>"
+}
diff --git a/DigitalHumanWeb/locales/tr-TR/tool.json b/DigitalHumanWeb/locales/tr-TR/tool.json
index 4a5b096..43d1e4f 100644
--- a/DigitalHumanWeb/locales/tr-TR/tool.json
+++ b/DigitalHumanWeb/locales/tr-TR/tool.json
@@ -6,5 +6,23 @@
"generating": "Oluşturuluyor...",
"images": "Görseller:",
"prompt": "İpucu"
+ },
+ "search": {
+ "createNewSearch": "Yeni bir arama kaydı oluştur",
+ "emptyResult": "Sonuç bulunamadı, lütfen anahtar kelimeleri değiştirip tekrar deneyin",
+ "genAiMessage": "Yardımcı mesaj oluştur",
+ "includedTooltip": "Mevcut arama sonuçları oturumun bağlamına dahil edilecektir",
+ "keywords": "Anahtar kelimeler:",
+ "scoreTooltip": "İlgililik puanı, bu puan ne kadar yüksekse, sorgu anahtar kelimesiyle o kadar ilgili demektir",
+ "searchBar": {
+ "button": "Ara",
+ "placeholder": "Anahtar kelime",
+ "tooltip": "Arama sonuçları yeniden alınacak ve yeni bir özet mesajı oluşturulacaktır"
+ },
+ "searchEngine": "Arama motoru:",
+ "searchResult": "Arama sayısı:",
+ "summary": "Özet",
+ "summaryTooltip": "Mevcut içeriği özetle",
+ "viewMoreResults": "Daha fazla {{results}} sonuç görüntüle"
}
}
diff --git a/DigitalHumanWeb/locales/tr-TR/topic.json b/DigitalHumanWeb/locales/tr-TR/topic.json
new file mode 100644
index 0000000..d8ed796
--- /dev/null
+++ b/DigitalHumanWeb/locales/tr-TR/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Akıllı Yeniden Adlandırma",
+ "confirmRemoveAll": "Tüm konular silinecek, silindikten sonra geri alınamaz, lütfen dikkatli olun.",
+ "confirmRemoveTopic": "Bu konu silinecek, silindikten sonra geri alınamaz, lütfen dikkatli olun.",
+ "confirmRemoveUnstarred": "Favori olmayan konular silinecek, silindikten sonra geri alınamaz, lütfen dikkatli olun.",
+ "duplicate": "Kopya Oluştur",
+ "export": "Konuları Dışa Aktar",
+ "removeAll": "Tüm Konuları Sil",
+ "removeUnstarred": "Favori Olmayan Konuları Sil"
+ },
+ "defaultTitle": "Varsayılan Konu",
+ "duplicateLoading": "Konu Kopyalanıyor...",
+ "duplicateSuccess": "Konu Başarıyla Kopyalandı",
+ "favorite": "Favori",
+ "groupMode": {
+ "ascMessages": "Mesaj Sayısına Göre Artan Sıra",
+ "byTime": "Zamana Göre Grupla",
+ "descMessages": "Mesaj Sayısına Göre Azalan Sıra",
+ "flat": "Gruplandırma Yok"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Bu Ay",
+ "today": "Bugün",
+ "week": "Bu Hafta",
+ "yesterday": "Dün"
+ }
+ },
+ "guide": {
+ "desc": "Mevcut sohbeti tarihsel konu olarak kaydetmek ve yeni bir sohbet başlatmak için sol taraftaki gönder butonuna tıklayın.",
+ "title": "Konu Listesi"
+ },
+ "searchPlaceholder": "Konuları Ara...",
+ "searchResultEmpty": "Hiçbir arama sonucu bulunamadı",
+ "temp": "Geçici",
+ "title": "Konu"
+}
diff --git a/DigitalHumanWeb/locales/tr-TR/welcome.json b/DigitalHumanWeb/locales/tr-TR/welcome.json
index 1cfd864..9fded5e 100644
--- a/DigitalHumanWeb/locales/tr-TR/welcome.json
+++ b/DigitalHumanWeb/locales/tr-TR/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "İçe Aktar",
- "market": "Pazara Göz At",
- "start": "Başla"
- },
"guide": {
"agents": {
"replaceBtn": "Başka bir grup",
diff --git a/DigitalHumanWeb/locales/vi-VN/auth.json b/DigitalHumanWeb/locales/vi-VN/auth.json
index 0848222..f88eae3 100644
--- a/DigitalHumanWeb/locales/vi-VN/auth.json
+++ b/DigitalHumanWeb/locales/vi-VN/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "Tháng trước",
+ "recent30Days": "30 ngày qua"
+ },
+ "header": {
+ "desc": "Quản lý thông tin tài khoản của bạn.",
+ "title": "Tài khoản"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "Không hoạt động",
+ "more": "Hoạt động"
+ },
+ "months": {
+ "apr": "Th4",
+ "aug": "Th8",
+ "dec": "Th12",
+ "feb": "Th2",
+ "jan": "Th1",
+ "jul": "Th7",
+ "jun": "Th6",
+ "mar": "Th3",
+ "may": "Th5",
+ "nov": "Th11",
+ "oct": "Th10",
+ "sep": "Th9"
+ },
+ "tooltip": "{{date}} đã gửi {{count}} tin nhắn trong ngày đó",
+ "totalCount": "Tổng cộng {{count}} tin nhắn đã gửi trong năm qua"
+ },
"login": "Đăng nhập",
"loginOrSignup": "Đăng nhập / Đăng ký",
- "profile": "Hồ sơ cá nhân",
- "security": "Bảo mật",
+ "profile": {
+ "avatar": "Ảnh đại diện",
+ "email": "Địa chỉ email",
+ "sso": {
+ "loading": "Đang tải tài khoản bên thứ ba đã liên kết",
+ "providers": "Tài khoản liên kết",
+ "unlink": {
+ "description": "Sau khi hủy liên kết, bạn sẽ không thể sử dụng tài khoản {{provider}} “{{providerAccountId}}” để đăng nhập. Nếu bạn cần liên kết lại tài khoản {{provider}} với tài khoản hiện tại, hãy đảm bảo rằng địa chỉ email của tài khoản {{provider}} là {{email}} , chúng tôi sẽ tự động liên kết nó với tài khoản đăng nhập hiện tại của bạn khi bạn đăng nhập.",
+ "forbidden": "Bạn cần phải giữ lại ít nhất một tài khoản bên thứ ba được liên kết.",
+ "title": "Có chắc chắn muốn hủy liên kết tài khoản bên thứ ba {{provider}}?"
+ }
+ },
+ "username": "Tên người dùng"
+ },
"signout": "Đăng xuất",
- "signup": "Đăng ký"
+ "signup": "Đăng ký",
+ "stats": {
+ "aiheatmaps": "Chỉ số hoạt động",
+ "assistants": "Trợ lý",
+ "assistantsRank": {
+ "left": "Trợ lý",
+ "right": "Chủ đề",
+ "title": "Xếp hạng sử dụng trợ lý"
+ },
+ "createdAt": "Đăng ký vào",
+ "days": "ngày",
+ "empty": {
+ "desc": "Vui lòng tích lũy thêm dữ liệu trò chuyện để xem",
+ "title": "Không có dữ liệu"
+ },
+ "lastYearActivity": "hoạt động trong năm qua",
+ "loginGuide": {
+ "f1": "Nhận lượng sử dụng miễn phí",
+ "f2": "Đồng bộ tin nhắn trên nhiều thiết bị",
+ "f3": "Sở hữu trợ lý phong phú",
+ "f4": "Khám phá các plugin mạnh mẽ",
+ "title": "Sau khi đăng nhập, bạn có thể:"
+ },
+ "messages": "Tin nhắn",
+ "modelsRank": {
+ "left": "Mô hình",
+ "right": "Tin nhắn",
+ "title": "Xếp hạng sử dụng mô hình"
+ },
+ "share": {
+ "title": "Chỉ số hoạt động AI của tôi"
+ },
+ "topics": "Chủ đề",
+ "topicsRank": {
+ "left": "Chủ đề",
+ "right": "Tin nhắn",
+ "title": "Xếp hạng nội dung chủ đề"
+ },
+ "updatedAt": "Cập nhật vào",
+ "welcome": "{{username}}, đây là ngày {{days}} của bạn với {{appName}}",
+ "words": "Từ"
+ },
+ "tab": {
+ "profile": "Hồ sơ",
+ "security": "Bảo mật",
+ "stats": "Thống kê"
+ }
}
diff --git a/DigitalHumanWeb/locales/vi-VN/changelog.json b/DigitalHumanWeb/locales/vi-VN/changelog.json
new file mode 100644
index 0000000..4edf362
--- /dev/null
+++ b/DigitalHumanWeb/locales/vi-VN/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "Theo dõi chúng tôi trên X",
+ "subscribeToUpdates": "Đăng ký nhận cập nhật",
+ "versions": "Chi tiết phiên bản"
+ },
+ "addedWhileAway": "Chúng tôi đã mang đến những tính năng mới trong thời gian bạn vắng mặt.",
+ "allChangelog": "Xem tất cả nhật ký cập nhật",
+ "description": "Theo dõi các tính năng và cải tiến mới của {{appName}}",
+ "pagination": {
+ "next": "Trang tiếp theo",
+ "older": "Xem thay đổi lịch sử"
+ },
+ "readDetails": "Đọc chi tiết",
+ "title": "Nhật ký cập nhật",
+ "versionDetails": "Chi tiết phiên bản",
+ "welcomeBack": "Chào mừng bạn trở lại!"
+}
diff --git a/DigitalHumanWeb/locales/vi-VN/chat.json b/DigitalHumanWeb/locales/vi-VN/chat.json
index f36945b..cca292f 100644
--- a/DigitalHumanWeb/locales/vi-VN/chat.json
+++ b/DigitalHumanWeb/locales/vi-VN/chat.json
@@ -8,6 +8,7 @@
"agents": "Trợ lý",
"artifact": {
"generating": "Đang tạo",
+ "inThread": "Không thể xem trong chủ đề con, vui lòng chuyển sang khu vực đối thoại chính để mở",
"thinking": "Đang suy nghĩ",
"thought": "Quá trình suy nghĩ",
"unknownTitle": "Tác phẩm chưa được đặt tên"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} Bản sao",
"emptyAgent": "Không có trợ lý",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "Chi phí tạo ra một cuộc hội thoại đơn lẻ có thể giảm tới 90%, tốc độ phản hồi tăng gấp 4 lần (<1>Tìm hiểu thêm1>). Khi bật, sẽ tự động vô hiệu hóa giới hạn số lượng tin nhắn lịch sử",
+ "title": "Bật bộ nhớ ngữ cảnh"
+ },
+ "enableReasoning": {
+ "desc": "Giới hạn dựa trên cơ chế Claude Thinking (<1>Tìm hiểu thêm1>), khi bật sẽ tự động vô hiệu hóa giới hạn số lượng tin nhắn lịch sử",
+ "title": "Bật tư duy sâu sắc"
+ },
+ "reasoningBudgetToken": {
+ "title": "Token tiêu tốn cho tư duy"
+ },
+ "title": "Chức năng mở rộng mô hình"
+ },
+ "history": {
+ "title": "Trợ lý sẽ chỉ nhớ {{count}} tin nhắn cuối cùng"
+ },
"historyRange": "Phạm vi lịch sử",
+ "historySummary": "Tóm tắt tin tức lịch sử",
"inbox": {
"desc": "Kích hoạt cụm não, khơi dậy tia lửa tư duy. Trợ lý thông minh của bạn, ở đây để trò chuyện với bạn về mọi thứ.",
"title": "Chuyện phiếm"
@@ -45,6 +64,9 @@
"stop": "Dừng",
"warp": "Xuống dòng"
},
+ "intentUnderstanding": {
+ "title": "Đang hiểu và phân tích ý định của bạn..."
+ },
"knowledgeBase": {
"all": "Tất cả nội dung",
"allFiles": "Tất cả tệp",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "Xóa và tạo lại",
+ "deleteDisabledByThreads": "Có chủ đề con, không thể xóa",
"regenerate": "Tạo lại"
},
+ "messages": {
+ "modelCard": {
+ "credit": "Điểm",
+ "creditPricing": "Định giá",
+ "creditTooltip": "Để thuận tiện cho việc tính toán, chúng tôi quy đổi 1$ thành 1M điểm, ví dụ $3/M token sẽ được quy đổi thành 3 điểm/token",
+ "pricing": {
+ "inputCachedTokens": "Nhập cached {{amount}}/điểm · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M ký tự",
+ "inputMinutes": "${{amount}}/phút",
+ "inputTokens": "Nhập {{amount}}/điểm · ${{amount}}/M",
+ "outputTokens": "Xuất {{amount}}/điểm · ${{amount}}/M",
+ "writeCacheInputTokens": "Ghi vào bộ nhớ đệm đầu vào {{amount}}/điểm · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "Giá trung bình",
+ "input": "Nhập",
+ "inputAudio": "Âm thanh nhập",
+ "inputCached": "Nhập cached",
+ "inputCitation": "Trích dẫn đầu vào",
+ "inputText": "Văn bản nhập",
+ "inputTitle": "Chi tiết nhập",
+ "inputUncached": "Nhập chưa cached",
+ "inputWriteCached": "Ghi vào bộ nhớ đệm đầu vào",
+ "output": "Xuất",
+ "outputAudio": "Âm thanh xuất",
+ "outputText": "Văn bản xuất",
+ "outputTitle": "Chi tiết xuất",
+ "reasoning": "Suy nghĩ sâu sắc",
+ "title": "Chi tiết tạo ra",
+ "total": "Tổng tiêu thụ"
+ }
+ },
"newAgent": "Tạo trợ lý mới",
"pin": "Ghim",
"pinOff": "Bỏ ghim",
@@ -81,6 +137,32 @@
},
"regenerate": "Tạo lại",
"roleAndArchive": "Vai trò và lưu trữ",
+ "search": {
+ "grounding": {
+ "searchQueries": "Từ khóa tìm kiếm",
+ "title": "Đã tìm thấy {{count}} kết quả"
+ },
+ "mode": {
+ "auto": {
+ "desc": "Thông minh xác định xem có cần tìm kiếm dựa trên nội dung cuộc trò chuyện",
+ "title": "Kết nối thông minh"
+ },
+ "off": {
+ "desc": "Chỉ sử dụng kiến thức cơ bản của mô hình, không thực hiện tìm kiếm trên mạng",
+ "title": "Tắt kết nối"
+ },
+ "on": {
+ "desc": "Tiếp tục tìm kiếm trên mạng để có thông tin mới nhất",
+ "title": "Luôn kết nối"
+ },
+ "useModelBuiltin": "Sử dụng công cụ tìm kiếm tích hợp của mô hình"
+ },
+ "searchModel": {
+ "desc": "Mô hình hiện tại không hỗ trợ gọi hàm, vì vậy cần kết hợp với mô hình hỗ trợ gọi hàm để tìm kiếm trực tuyến",
+ "title": "Mô hình hỗ trợ tìm kiếm"
+ },
+ "title": "Tìm kiếm trực tuyến"
+ },
"searchAgentPlaceholder": "Trợ lý tìm kiếm...",
"sendPlaceholder": "Nhập nội dung trò chuyện...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "Tên nhóm phải có độ dài từ 1-20 ký tự"
},
"shareModal": {
+ "copy": "Sao chép",
"download": "Tải xuống ảnh chụp màn hình",
+ "downloadFile": "Tải tệp",
+ "exportTitle": "Tiêu đề mặc định",
"imageType": "Định dạng ảnh",
+ "includeTool": "Bao gồm thông điệp công cụ",
+ "includeUser": "Bao gồm thông điệp người dùng",
"screenshot": "Ảnh chụp màn hình",
"settings": "Cài đặt xuất",
- "shareToShareGPT": "Tạo liên kết chia sẻ ShareGPT",
+ "text": "Văn bản",
"withBackground": "Bao gồm hình nền",
"withFooter": "Bao gồm chân trang",
"withPluginInfo": "Bao gồm thông tin plugin",
+ "withRole": "Bao gồm vai trò thông điệp",
"withSystemRole": "Bao gồm thiết lập vai trò trợ lý"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "Đang nhận dạng...",
"prettifying": "Đang tinh chỉnh..."
},
- "temp": "Tạm thời",
+ "thread": {
+ "divider": "Chủ đề con",
+ "threadMessageCount": "{{messageCount}} tin nhắn",
+ "title": "Chủ đề con"
+ },
"tokenDetails": {
"chats": "Tin nhắn trò chuyện",
+ "historySummary": "Tóm tắt lịch sử",
"rest": "Còn lại",
"systemRole": "Vai trò hệ thống",
"title": "Chi tiết Ngữ cảnh",
@@ -131,29 +224,10 @@
"used": "Đã sử dụng"
},
"topic": {
- "actions": {
- "autoRename": "Đổi tên tự động",
- "duplicate": "Tạo bản sao",
- "export": "Xuất chủ đề"
- },
"checkOpenNewTopic": "Có muốn mở chủ đề mới không?",
"checkSaveCurrentMessages": "Bạn có muốn lưu cuộc trò chuyện hiện tại thành chủ đề không?",
- "confirmRemoveAll": "Bạn sắp xóa tất cả chủ đề. Hành động này không thể hoàn tác, vui lòng xác nhận.",
- "confirmRemoveTopic": "Bạn sắp xóa chủ đề này. Hành động này không thể hoàn tác, vui lòng xác nhận.",
- "confirmRemoveUnstarred": "Bạn sắp xóa các chủ đề chưa được đánh dấu. Hành động này không thể hoàn tác, vui lòng xác nhận.",
- "defaultTitle": "Chủ đề mặc định",
- "duplicateLoading": "Đang sao chép chủ đề...",
- "duplicateSuccess": "Chủ đề đã được sao chép thành công",
- "guide": {
- "desc": "Nhấn vào nút bên trái để lưu cuộc trò chuyện hiện tại như một chủ đề lịch sử và bắt đầu một cuộc trò chuyện mới",
- "title": "Danh sách chủ đề"
- },
"openNewTopic": "Mở chủ đề mới",
- "removeAll": "Xóa tất cả chủ đề",
- "removeUnstarred": "Xóa chủ đề chưa được đánh dấu",
- "saveCurrentMessages": "Lưu cuộc trò chuyện hiện tại thành chủ đề",
- "searchPlaceholder": "Tìm kiếm chủ đề...",
- "title": "Danh sách chủ đề"
+ "saveCurrentMessages": "Lưu cuộc trò chuyện hiện tại thành chủ đề"
},
"translate": {
"action": "Dịch",
@@ -184,5 +258,6 @@
"processing": "Đang xử lý tệp..."
}
}
- }
+ },
+ "zenMode": "Chế độ tập trung"
}
diff --git a/DigitalHumanWeb/locales/vi-VN/common.json b/DigitalHumanWeb/locales/vi-VN/common.json
index 2f27fdf..eab906f 100644
--- a/DigitalHumanWeb/locales/vi-VN/common.json
+++ b/DigitalHumanWeb/locales/vi-VN/common.json
@@ -9,15 +9,79 @@
"title": "Chào mừng bạn trải nghiệm {{name}}"
}
},
- "appInitializing": "Đang khởi động ứng dụng...",
+ "appLoading": {
+ "appIdle": "Sẵn sàng khởi động",
+ "appInitializing": "Đang khởi động ứng dụng...",
+ "failed": "Rất tiếc, ứng dụng không khởi tạo được, vui lòng xem chi tiết để kiểm tra.",
+ "finished": "Khởi tạo cơ sở dữ liệu hoàn tất",
+ "goToChat": "Đang tải trang trò chuyện...",
+ "initAuth": "Đang khởi tạo dịch vụ xác thực...",
+ "initUser": "Đang khởi tạo trạng thái người dùng...",
+ "initializing": "Đang khởi tạo cơ sở dữ liệu PGlite...",
+ "loadingDependencies": "Đang khởi tạo phụ thuộc...",
+ "loadingWasm": "Đang tải mô-đun WASM...",
+ "migrating": "Đang thực hiện di chuyển bảng dữ liệu...",
+ "ready": "Cơ sở dữ liệu đã sẵn sàng",
+ "showDetail": "Xem chi tiết"
+ },
"autoGenerate": "Tự động tạo",
"autoGenerateTooltip": "Tự động hoàn thành mô tả trợ lý dựa trên từ gợi ý",
"autoGenerateTooltipDisabled": "Vui lòng nhập từ gợi ý trước khi sử dụng tính năng tự động hoàn thành",
"back": "Quay lại",
"batchDelete": "Xóa hàng loạt",
"blog": "Blog sản phẩm",
+ "branching": "Tạo chủ đề con",
+ "branchingDisable": "Chức năng «Chủ đề con» chỉ có sẵn trong phiên bản máy chủ. Nếu bạn cần chức năng này, hãy chuyển sang chế độ triển khai máy chủ hoặc sử dụng LobeChat Cloud.",
"cancel": "Hủy",
"changelog": "Nhật ký cập nhật",
+ "clientDB": {
+ "autoInit": {
+ "title": "Khởi tạo cơ sở dữ liệu PGlite"
+ },
+ "error": {
+ "desc": "Xin lỗi, đã xảy ra sự cố trong quá trình khởi tạo cơ sở dữ liệu Pglite. Vui lòng nhấn nút để thử lại. Nếu vẫn gặp lỗi sau nhiều lần thử, vui lòng <1>gửi vấn đề1>, chúng tôi sẽ hỗ trợ bạn kiểm tra ngay lập tức.",
+ "detail": "Lý do lỗi: [{{type}}] {{message}},Chi tiết như sau:",
+ "retry": "Thử lại",
+ "title": "Khởi tạo cơ sở dữ liệu thất bại"
+ },
+ "initing": {
+ "error": "Đã xảy ra lỗi, vui lòng thử lại",
+ "idle": "Đang chờ khởi tạo...",
+ "initializing": "Đang khởi tạo...",
+ "loadingDependencies": "Đang tải phụ thuộc...",
+ "loadingWasmModule": "Đang tải mô-đun WASM...",
+ "migrating": "Đang thực hiện di chuyển bảng dữ liệu...",
+ "ready": "Cơ sở dữ liệu đã sẵn sàng"
+ },
+ "modal": {
+ "desc": "Kích hoạt cơ sở dữ liệu khách hàng PGlite, lưu trữ dữ liệu trò chuyện của bạn trong trình duyệt và sử dụng các tính năng nâng cao như kho kiến thức",
+ "enable": "Kích hoạt ngay",
+ "features": {
+ "knowledgeBase": {
+ "desc": "Xây dựng kho kiến thức cá nhân của bạn và dễ dàng bắt đầu cuộc trò chuyện với trợ lý của bạn (sắp ra mắt)",
+ "title": "Hỗ trợ trò chuyện kho kiến thức, mở ra bộ não thứ hai"
+ },
+ "localFirst": {
+ "desc": "Dữ liệu trò chuyện hoàn toàn được lưu trữ trên trình duyệt, dữ liệu của bạn luôn nằm trong tầm kiểm soát của bạn.",
+ "title": "Ưu tiên địa phương, bảo mật hàng đầu"
+ },
+ "pglite": {
+ "desc": "Xây dựng trên nền tảng PGlite, hỗ trợ nguyên bản các tính năng cao cấp AI Native (tìm kiếm vector)",
+ "title": "Kiến trúc lưu trữ khách hàng thế hệ mới"
+ }
+ },
+ "init": {
+ "desc": "Đang khởi tạo cơ sở dữ liệu, thời gian có thể từ 5~30 giây tùy thuộc vào mạng",
+ "title": "Đang khởi tạo cơ sở dữ liệu PGlite"
+ },
+ "title": "Bật cơ sở dữ liệu khách hàng"
+ },
+ "ready": {
+ "button": "Sử dụng ngay",
+ "desc": "Sử dụng ngay",
+ "title": "Cơ sở dữ liệu PGlite đã sẵn sàng"
+ }
+ },
"close": "Đóng",
"contact": "Liên hệ chúng tôi",
"copy": "Sao chép",
@@ -112,6 +176,7 @@
"en": "Tiếng Anh",
"en-US": "Tiếng Anh (Mỹ)",
"es-ES": "Tiếng Tây Ban Nha",
+ "fa-IR": "Tiếng Ba Tư",
"fi-FI": "Tiếng Phần Lan",
"fr-FR": "Tiếng Pháp",
"hi-IN": "Tiếng Hin-ddi",
@@ -153,6 +218,7 @@
"pinOff": "Bỏ ghim",
"privacy": "Chính sách bảo mật",
"regenerate": "Tạo lại",
+ "releaseNotes": "Chi tiết phiên bản",
"rename": "Đổi tên",
"reset": "Đặt lại",
"retry": "Thử lại",
@@ -209,6 +275,7 @@
},
"temp": "Tạm thời",
"terms": "Điều khoản dịch vụ",
+ "update": "Cập nhật",
"updateAgent": "Cập nhật thông tin trợ lý",
"upgradeVersion": {
"action": "Nâng cấp",
@@ -219,6 +286,7 @@
"anonymousNickName": "Người dùng ẩn danh",
"billing": "Quản lý hóa đơn",
"cloud": "Trải nghiệm {{name}}",
+ "community": "Phiên bản cộng đồng",
"data": "Lưu trữ dữ liệu",
"defaultNickname": "Người dùng phiên bản cộng đồng",
"discord": "Hỗ trợ cộng đồng",
@@ -228,7 +296,6 @@
"help": "Trung tâm trợ giúp",
"moveGuide": "Đã di chuyển nút cài đặt đến đây",
"plans": "Kế hoạch đăng ký",
- "preview": "Phiên bản xem trước",
"profile": "Quản lý tài khoản",
"setting": "Cài đặt ứng dụng",
"usages": "Thống kê sử dụng"
diff --git a/DigitalHumanWeb/locales/vi-VN/components.json b/DigitalHumanWeb/locales/vi-VN/components.json
index d3353d8..4aac813 100644
--- a/DigitalHumanWeb/locales/vi-VN/components.json
+++ b/DigitalHumanWeb/locales/vi-VN/components.json
@@ -12,6 +12,7 @@
"batchChunking": "Chia nhỏ theo lô",
"chunking": "Chia nhỏ",
"chunkingTooltip": "Chia tách tệp thành nhiều khối văn bản và vector hóa, có thể sử dụng cho tìm kiếm ngữ nghĩa và đối thoại tệp",
+ "chunkingUnsupported": "Tập tin này không hỗ trợ phân mảnh",
"confirmDelete": "Bạn sắp xóa tệp này, sau khi xóa sẽ không thể khôi phục, vui lòng xác nhận hành động của bạn",
"confirmDeleteMultiFiles": "Bạn sắp xóa {{count}} tệp đã chọn, sau khi xóa sẽ không thể khôi phục, vui lòng xác nhận hành động của bạn",
"confirmRemoveFromKnowledgeBase": "Bạn sắp xóa {{count}} tệp đã chọn khỏi kho tri thức, sau khi xóa tệp vẫn có thể xem trong tất cả các tệp, vui lòng xác nhận hành động của bạn",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "Quay lại"
},
+ "MaxTokenSlider": {
+ "unlimited": "Không giới hạn"
+ },
"ModelSelect": {
"featureTag": {
"custom": "Mô hình tùy chỉnh, mặc định hỗ trợ cả cuộc gọi hàm và nhận diện hình ảnh, vui lòng xác minh khả năng sử dụng của chúng theo tình hình cụ thể",
"file": "Mô hình này hỗ trợ tải lên và nhận diện tệp",
"functionCall": "Mô hình này hỗ trợ cuộc gọi hàm (Function Call)",
+ "reasoning": "Mô hình này hỗ trợ tư duy sâu sắc",
+ "search": "Mô hình này hỗ trợ tìm kiếm trực tuyến",
"tokens": "Mỗi phiên của mô hình này hỗ trợ tối đa {{tokens}} Tokens",
"vision": "Mô hình này hỗ trợ nhận diện hình ảnh"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "Không có mô hình nào được kích hoạt, vui lòng điều chỉnh trong cài đặt",
+ "emptyProvider": "Không có nhà cung cấp nào được kích hoạt, vui lòng vào cài đặt để bật",
+ "goToSettings": "Đi đến cài đặt",
"provider": "Nhà cung cấp"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "Do hạn chế bảo mật của trình duyệt, bạn cần cấu hình CORS cho Ollama để có thể sử dụng bình thường.",
+ "linux": {
+ "env": "Thêm `Environment` trong phần [Service], thêm biến môi trường OLLAMA_ORIGINS:",
+ "reboot": "Tải lại systemd và khởi động lại Ollama",
+ "systemd": "Gọi systemd để chỉnh sửa dịch vụ ollama:"
+ },
+ "macos": "Vui lòng mở ứng dụng «Terminal» và dán lệnh sau, sau đó nhấn Enter để chạy",
+ "reboot": "Vui lòng khởi động lại dịch vụ Ollama sau khi hoàn thành",
+ "title": "Cấu hình Ollama cho phép truy cập CORS",
+ "windows": "Trên Windows, nhấp vào «Control Panel», vào chỉnh sửa biến môi trường hệ thống. Tạo một biến môi trường mới có tên là «OLLAMA_ORIGINS» cho tài khoản người dùng của bạn, giá trị là *, nhấp «OK/Apply» để lưu"
+ },
+ "install": {
+ "description": "Vui lòng xác nhận rằng bạn đã mở Ollama, nếu chưa tải Ollama, hãy truy cập trang web chính thức <1>tải xuống1>",
+ "docker": "Nếu bạn thích sử dụng Docker, Ollama cũng cung cấp hình ảnh Docker chính thức, bạn có thể kéo xuống bằng lệnh sau:",
+ "linux": {
+ "command": "Cài đặt bằng lệnh sau:",
+ "manual": "Hoặc, bạn cũng có thể tham khảo <1>Hướng dẫn cài đặt thủ công trên Linux1> để tự cài đặt"
+ },
+ "title": "Cài đặt và khởi động ứng dụng Ollama trên máy tính",
+ "windowsTab": "Windows (phiên bản xem trước)"
+ }
+ },
+ "Thinking": {
+ "thinking": "Đang suy nghĩ sâu sắc...",
+ "thought": "Đã suy nghĩ sâu sắc (mất {{duration}} giây)",
+ "thoughtWithDuration": "Đã suy nghĩ sâu sắc"
}
}
diff --git a/DigitalHumanWeb/locales/vi-VN/discover.json b/DigitalHumanWeb/locales/vi-VN/discover.json
index 804488c..726f4a2 100644
--- a/DigitalHumanWeb/locales/vi-VN/discover.json
+++ b/DigitalHumanWeb/locales/vi-VN/discover.json
@@ -126,6 +126,10 @@
"title": "Độ mới của chủ đề"
},
"range": "Phạm vi",
+ "reasoning_effort": {
+ "desc": "Cài đặt này được sử dụng để kiểm soát mức độ suy luận của mô hình trước khi tạo câu trả lời. Mức độ thấp ưu tiên tốc độ phản hồi và tiết kiệm Token, trong khi mức độ cao cung cấp suy luận đầy đủ hơn nhưng tiêu tốn nhiều Token hơn và làm giảm tốc độ phản hồi. Giá trị mặc định là trung bình, cân bằng giữa độ chính xác của suy luận và tốc độ phản hồi.",
+ "title": "Mức độ suy luận"
+ },
"temperature": {
"desc": "Cài đặt này ảnh hưởng đến sự đa dạng trong phản hồi của mô hình. Giá trị thấp hơn dẫn đến phản hồi dễ đoán và điển hình hơn, trong khi giá trị cao hơn khuyến khích phản hồi đa dạng và không thường gặp. Khi giá trị được đặt là 0, mô hình sẽ luôn đưa ra cùng một phản hồi cho đầu vào nhất định.",
"title": "Ngẫu nhiên"
diff --git a/DigitalHumanWeb/locales/vi-VN/error.json b/DigitalHumanWeb/locales/vi-VN/error.json
index 329e4d6..f5ce95b 100644
--- a/DigitalHumanWeb/locales/vi-VN/error.json
+++ b/DigitalHumanWeb/locales/vi-VN/error.json
@@ -12,8 +12,14 @@
"retry": "Thử lại",
"title": "Trang gặp một chút vấn đề.."
},
- "fetchError": "Yêu cầu thất bại",
- "fetchErrorDetail": "Chi tiết lỗi",
+ "fetchError": {
+ "detail": "Chi tiết lỗi",
+ "title": "Yêu cầu thất bại"
+ },
+ "loginRequired": {
+ "desc": "Sẽ tự động chuyển hướng đến trang đăng nhập",
+ "title": "Vui lòng đăng nhập để sử dụng tính năng này"
+ },
"notFound": {
"backHome": "Quay về Trang chủ",
"check": "Vui lòng kiểm tra xem URL của bạn có đúng không",
@@ -51,22 +57,34 @@
"431": "Xin lỗi, trường tiêu đề yêu cầu của bạn quá lớn, máy chủ không thể xử lý",
"451": "Xin lỗi, do lý do pháp lý, máy chủ từ chối cung cấp tài nguyên này",
"500": "Xin lỗi, máy chủ có vẻ gặp một số khó khăn, tạm thời không thể hoàn thành yêu cầu của bạn, vui lòng thử lại sau",
+ "501": "Xin lỗi, máy chủ chưa biết cách xử lý yêu cầu này, vui lòng xác nhận rằng thao tác của bạn là chính xác",
"502": "Xin lỗi, máy chủ có vẻ lạc đường, tạm thời không thể cung cấp dịch vụ, vui lòng thử lại sau",
"503": "Xin lỗi, máy chủ hiện không thể xử lý yêu cầu của bạn, có thể do quá tải hoặc đang bảo trì, vui lòng thử lại sau",
"504": "Xin lỗi, máy chủ không đợi được phản hồi từ máy chủ upstream, vui lòng thử lại sau",
+ "505": "Xin lỗi, máy chủ không hỗ trợ phiên bản HTTP bạn đang sử dụng, vui lòng cập nhật và thử lại",
+ "506": "Xin lỗi, có vấn đề với cấu hình máy chủ, vui lòng liên hệ với quản trị viên để giải quyết",
+ "507": "Xin lỗi, máy chủ không đủ dung lượng lưu trữ để xử lý yêu cầu của bạn, vui lòng thử lại sau",
+ "509": "Xin lỗi, băng thông của máy chủ đã hết, vui lòng thử lại sau",
+ "510": "Xin lỗi, máy chủ không hỗ trợ chức năng mở rộng được yêu cầu, vui lòng liên hệ với quản trị viên",
+ "524": "Xin lỗi, máy chủ đã hết thời gian chờ khi đang chờ phản hồi, có thể do phản hồi quá chậm, vui lòng thử lại sau",
"AgentRuntimeError": "Lobe mô hình ngôn ngữ thực thi gặp lỗi, vui lòng kiểm tra và thử lại dựa trên thông tin dưới đây",
+ "ConnectionCheckFailed": "Yêu cầu trả về trống, xin kiểm tra xem địa chỉ API proxy có đang thiếu `/v1` ở cuối không",
+ "ExceededContextWindow": "Nội dung yêu cầu hiện tại vượt quá độ dài mà mô hình có thể xử lý, vui lòng giảm khối lượng nội dung và thử lại",
"FreePlanLimit": "Hiện tại bạn đang sử dụng tài khoản miễn phí, không thể sử dụng tính năng này. Vui lòng nâng cấp lên gói trả phí để tiếp tục sử dụng.",
+ "InsufficientQuota": "Xin lỗi, hạn mức của khóa này đã đạt giới hạn, vui lòng kiểm tra số dư tài khoản của bạn hoặc tăng hạn mức khóa trước khi thử lại",
"InvalidAccessCode": "Mật khẩu truy cập không hợp lệ hoặc trống, vui lòng nhập mật khẩu truy cập đúng hoặc thêm Khóa API tùy chỉnh",
"InvalidBedrockCredentials": "Xác thực Bedrock không thành công, vui lòng kiểm tra AccessKeyId/SecretAccessKey và thử lại",
"InvalidClerkUser": "Xin lỗi, bạn chưa đăng nhập. Vui lòng đăng nhập hoặc đăng ký tài khoản trước khi tiếp tục.",
"InvalidGithubToken": "Mã truy cập cá nhân Github không chính xác hoặc để trống, vui lòng kiểm tra lại Mã truy cập cá nhân Github và thử lại",
"InvalidOllamaArgs": "Cấu hình Ollama không hợp lệ, vui lòng kiểm tra lại cấu hình Ollama và thử lại",
"InvalidProviderAPIKey": "{{provider}} API Key không hợp lệ hoặc trống, vui lòng kiểm tra và thử lại",
+ "InvalidVertexCredentials": "Xác thực Vertex không thành công, vui lòng kiểm tra lại thông tin xác thực và thử lại",
"LocationNotSupportError": "Xin lỗi, vị trí của bạn không hỗ trợ dịch vụ mô hình này, có thể do hạn chế vùng miền hoặc dịch vụ chưa được mở. Vui lòng xác nhận xem vị trí hiện tại có hỗ trợ sử dụng dịch vụ này không, hoặc thử sử dụng thông tin vị trí khác.",
+ "ModelNotFound": "Xin lỗi, không thể yêu cầu mô hình tương ứng, có thể mô hình không tồn tại hoặc không có quyền truy cập, vui lòng thay đổi API Key hoặc điều chỉnh quyền truy cập rồi thử lại",
"NoOpenAIAPIKey": "Khóa API OpenAI trống, vui lòng thêm Khóa API OpenAI tùy chỉnh",
"OllamaBizError": "Yêu cầu dịch vụ Ollama gặp lỗi, vui lòng kiểm tra thông tin dưới đây hoặc thử lại",
"OllamaServiceUnavailable": "Dịch vụ Ollama không khả dụng, vui lòng kiểm tra xem Ollama có hoạt động bình thường không, hoặc xem xét cấu hình chéo đúng của Ollama",
- "OpenAIBizError": "Yêu cầu dịch vụ OpenAI gặp sự cố, vui lòng kiểm tra thông tin dưới đây hoặc thử lại",
+ "PermissionDenied": "Xin lỗi, bạn không có quyền truy cập dịch vụ này, vui lòng kiểm tra xem khóa của bạn có quyền truy cập hay không",
"PluginApiNotFound": "Xin lỗi, không có API nào trong tệp mô tả plugin, vui lòng kiểm tra phương thức yêu cầu của bạn có khớp với API mô tả plugin không",
"PluginApiParamsError": "Xin lỗi, kiểm tra tham số đầu vào yêu cầu của plugin không thông qua, vui lòng kiểm tra tham số đầu vào có khớp với thông tin mô tả API không",
"PluginFailToTransformArguments": "Xin lỗi, không thể chuyển đổi đối số của plugin, vui lòng thử tạo lại tin nhắn trợ giúp hoặc thay đổi mô hình AI có khả năng gọi Tools mạnh hơn và thử lại",
@@ -81,8 +99,11 @@
"PluginServerError": "Lỗi trả về từ máy chủ plugin, vui lòng kiểm tra tệp mô tả plugin, cấu hình plugin hoặc triển khai máy chủ theo thông tin lỗi dưới đây",
"PluginSettingsInvalid": "Plugin cần phải được cấu hình đúng trước khi sử dụng, vui lòng kiểm tra cấu hình của bạn có đúng không",
"ProviderBizError": "Yêu cầu dịch vụ {{provider}} gặp sự cố, vui lòng kiểm tra thông tin dưới đây hoặc thử lại",
+ "QuotaLimitReached": "Xin lỗi, lượng Token hiện tại hoặc số lần yêu cầu đã đạt đến giới hạn quota của khóa này, vui lòng tăng quota của khóa hoặc thử lại sau.",
"StreamChunkError": "Lỗi phân tích khối tin nhắn yêu cầu luồng, vui lòng kiểm tra xem API hiện tại có tuân thủ tiêu chuẩn hay không, hoặc liên hệ với nhà cung cấp API của bạn để được tư vấn.",
- "SubscriptionPlanLimit": "Số lượng đăng ký của bạn đã hết, không thể sử dụng tính năng này. Vui lòng nâng cấp lên gói cao hơn hoặc mua gói tài nguyên để tiếp tục sử dụng.",
+ "SubscriptionKeyMismatch": "Xin lỗi, do sự cố hệ thống tạm thời, lượng sử dụng đăng ký hiện tại đã không còn hiệu lực. Vui lòng nhấp vào nút bên dưới để khôi phục đăng ký hoặc gửi email cho chúng tôi để nhận hỗ trợ.",
+ "SubscriptionPlanLimit": "Điểm đăng ký của bạn đã hết, không thể sử dụng tính năng này. Vui lòng nâng cấp lên gói cao hơn hoặc cấu hình API mô hình tùy chỉnh để tiếp tục sử dụng.",
+ "SystemTimeNotMatchError": "Xin lỗi, thời gian hệ thống của bạn không khớp với máy chủ, vui lòng kiểm tra lại thời gian hệ thống của bạn và thử lại",
"UnknownChatFetchError": "Xin lỗi, đã xảy ra lỗi yêu cầu không xác định. Vui lòng kiểm tra hoặc thử lại theo thông tin dưới đây."
},
"stt": {
diff --git a/DigitalHumanWeb/locales/vi-VN/metadata.json b/DigitalHumanWeb/locales/vi-VN/metadata.json
index 365a60c..8a21cdc 100644
--- a/DigitalHumanWeb/locales/vi-VN/metadata.json
+++ b/DigitalHumanWeb/locales/vi-VN/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "Theo dõi các tính năng và cải tiến mới của {{appName}}",
+ "title": "Nhật ký cập nhật"
+ },
"chat": {
"description": "{{appName}} mang đến cho bạn trải nghiệm tốt nhất với ChatGPT, Claude, Gemini, OLLaMA WebUI",
"title": "{{appName}}: Công cụ AI cá nhân, giúp bạn có một bộ não thông minh hơn"
diff --git a/DigitalHumanWeb/locales/vi-VN/modelProvider.json b/DigitalHumanWeb/locales/vi-VN/modelProvider.json
index a643f9f..dac4b39 100644
--- a/DigitalHumanWeb/locales/vi-VN/modelProvider.json
+++ b/DigitalHumanWeb/locales/vi-VN/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Phiên bản API của Azure, theo định dạng YYYY-MM-DD, tham khảo [phiên bản mới nhất](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "Lấy danh sách",
+ "title": "Phiên bản API Azure"
+ },
+ "endpoint": {
+ "desc": "Tìm điểm kết thúc suy diễn mô hình Azure AI từ tổng quan dự án Azure AI",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Điểm kết thúc Azure AI"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "Tìm khóa API từ tổng quan dự án Azure AI",
+ "placeholder": "Khóa Azure",
+ "title": "Khóa"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "Nhập AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "Sử dụng Thông tin Xác thực Bedrock tùy chỉnh"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "Vui lòng nhập Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "Nhập ID tài khoản Cloudflare hoặc địa chỉ API tùy chỉnh",
+ "placeholder": "ID tài khoản Cloudflare / địa chỉ API tùy chỉnh",
+ "title": "ID tài khoản Cloudflare / địa chỉ API"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "Vui lòng nhập API Key của bạn",
+ "title": "API Key"
+ },
+ "basicTitle": "Thông tin cơ bản",
+ "configTitle": "Thông tin cấu hình",
+ "confirm": "Tạo mới",
+ "createSuccess": "Tạo mới thành công",
+ "description": {
+ "placeholder": "Giới thiệu về nhà cung cấp (tùy chọn)",
+ "title": "Giới thiệu về nhà cung cấp"
+ },
+ "id": {
+ "desc": "Là định danh duy nhất của nhà cung cấp dịch vụ, không thể sửa đổi sau khi tạo",
+ "format": "Chỉ có thể chứa số, chữ cái thường, dấu gạch ngang (-) và dấu gạch dưới (_) ",
+ "placeholder": "Nên viết toàn bộ bằng chữ thường, ví dụ openai, không thể sửa sau khi tạo",
+ "required": "Vui lòng nhập ID nhà cung cấp",
+ "title": "ID nhà cung cấp"
+ },
+ "logo": {
+ "required": "Vui lòng tải lên Logo nhà cung cấp hợp lệ",
+ "title": "Logo nhà cung cấp"
+ },
+ "name": {
+ "placeholder": "Vui lòng nhập tên hiển thị của nhà cung cấp",
+ "required": "Vui lòng nhập tên nhà cung cấp",
+ "title": "Tên nhà cung cấp"
+ },
+ "proxyUrl": {
+ "required": "Vui lòng nhập địa chỉ proxy",
+ "title": "Địa chỉ proxy"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "Vui lòng chọn loại SDK",
+ "title": "Định dạng yêu cầu"
+ },
+ "title": "Tạo nhà cung cấp AI tùy chỉnh"
+ },
"github": {
"personalAccessToken": {
"desc": "Nhập mã truy cập cá nhân Github của bạn, nhấp vào [đây](https://github.com/settings/tokens) để tạo",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "Nhập mã thông báo HuggingFace của bạn, nhấp vào [đây](https://huggingface.co/settings/tokens) để tạo",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "Mã thông báo HuggingFace"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "Nhà cung cấp chưa được kích hoạt",
+ "enabled": "Nhà cung cấp đã được kích hoạt"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "Thêm nhà cung cấp tùy chỉnh",
+ "all": "Tất cả",
+ "list": {
+ "disabled": "Chưa kích hoạt",
+ "enabled": "Đã kích hoạt"
+ },
+ "notFound": "Không tìm thấy kết quả tìm kiếm",
+ "searchProviders": "Tìm kiếm nhà cung cấp...",
+ "sort": "Sắp xếp tùy chỉnh"
+ },
"ollama": {
"checker": {
"desc": "Kiểm tra địa chỉ proxy có được nhập chính xác không",
@@ -75,33 +169,9 @@
"title": "Đang tải mô hình {{model}}"
},
"endpoint": {
- "desc": "Nhập địa chỉ proxy API của Ollama, có thể để trống nếu không chỉ định cụ thể",
+ "desc": "Phải bao gồm http(s)://, có thể để trống nếu không chỉ định thêm cho địa phương",
"title": "Địa chỉ proxy API"
},
- "setup": {
- "cors": {
- "description": "Do vấn đề về an ninh trình duyệt, bạn cần cấu hình CORS cho Ollama trước khi có thể sử dụng bình thường.",
- "linux": {
- "env": "Trong phần [Service], thêm `Environment`, thêm biến môi trường OLLAMA_ORIGINS:",
- "reboot": "Tải lại systemd và khởi động lại Ollama",
- "systemd": "Gọi systemd để chỉnh sửa dịch vụ ollama:"
- },
- "macos": "Vui lòng mở ứng dụng «Terminal», dán lệnh sau và nhấn Enter để chạy",
- "reboot": "Vui lòng khởi động lại dịch vụ Ollama sau khi hoàn thành",
- "title": "Cấu hình Ollama cho phép truy cập từ xa",
- "windows": "Trên Windows, nhấp vào «Control Panel», vào chỉnh sửa biến môi trường hệ thống. Tạo biến môi trường tên là «OLLAMA_ORIGINS» cho tài khoản người dùng của bạn, giá trị là * , nhấp vào «OK/Áp dụng» để lưu lại"
- },
- "install": {
- "description": "Vui lòng xác nhận rằng bạn đã bật Ollama. Nếu chưa tải Ollama, vui lòng truy cập trang web chính thức để <1>tải xuống1>",
- "docker": "Nếu bạn muốn sử dụng Docker, Ollama cũng cung cấp hình ảnh Docker chính thức, bạn có thể kéo theo lệnh sau:",
- "linux": {
- "command": "Cài đặt bằng lệnh sau:",
- "manual": "Hoặc bạn cũng có thể tham khảo <1>Hướng dẫn cài đặt thủ công trên Linux1> để tự cài đặt"
- },
- "title": "Cài đặt và mở Ollama ứng dụng trên máy cục bộ",
- "windowsTab": "Windows (Bản xem trước)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "Hủy tải xuống",
@@ -112,6 +182,156 @@
"title": "Tải xuống mô hình Ollama đã chỉ định"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "Khóa của bạn và địa chỉ proxy sẽ được mã hóa bằng thuật toán <1>AES-GCM1>",
+ "apiKey": {
+ "desc": "Vui lòng nhập {{name}} API Key của bạn",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "Phải bao gồm http(s)://",
+ "invalid": "Vui lòng nhập một URL hợp lệ",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "Địa chỉ proxy API"
+ },
+ "checker": {
+ "button": "Kiểm tra",
+ "desc": "Kiểm tra xem API Key và địa chỉ proxy có được nhập đúng không",
+ "pass": "Kiểm tra thành công",
+ "title": "Kiểm tra kết nối"
+ },
+ "fetchOnClient": {
+ "desc": "Chế độ yêu cầu từ khách hàng sẽ phát động yêu cầu phiên trực tiếp từ trình duyệt, có thể cải thiện tốc độ phản hồi",
+ "title": "Sử dụng chế độ yêu cầu từ khách hàng"
+ },
+ "helpDoc": "Hướng dẫn cấu hình",
+ "waitingForMore": "Nhiều mô hình hơn đang <1>được lên kế hoạch1>, xin hãy chờ đợi"
+ },
+ "createNew": {
+ "title": "Tạo mô hình AI tùy chỉnh"
+ },
+ "item": {
+ "config": "Cấu hình mô hình",
+ "customModelCards": {
+ "addNew": "Tạo và thêm mô hình {{id}}",
+ "confirmDelete": "Sắp xóa mô hình tùy chỉnh này, sau khi xóa sẽ không thể khôi phục, xin hãy cẩn thận."
+ },
+ "delete": {
+ "confirm": "Xác nhận xóa mô hình {{displayName}}?",
+ "success": "Xóa thành công",
+ "title": "Xóa mô hình"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "Trường thực tế được yêu cầu trong Azure OpenAI",
+ "placeholder": "Vui lòng nhập tên triển khai mô hình trong Azure",
+ "title": "Tên triển khai mô hình"
+ },
+ "deployName": {
+ "extra": "Trường này sẽ được sử dụng làm ID mô hình khi gửi yêu cầu",
+ "placeholder": "Vui lòng nhập tên hoặc ID thực tế của mô hình đã triển khai",
+ "title": "Tên triển khai mô hình"
+ },
+ "displayName": {
+ "placeholder": "Vui lòng nhập tên hiển thị của mô hình, ví dụ ChatGPT, GPT-4, v.v.",
+ "title": "Tên hiển thị mô hình"
+ },
+ "files": {
+ "extra": "Hiện tại, việc tải lên tệp chỉ là một giải pháp Hack, chỉ dành cho thử nghiệm cá nhân. Vui lòng chờ đợi khả năng tải lên tệp hoàn chỉnh trong các bản cập nhật sau.",
+ "title": "Hỗ trợ tải lên tệp"
+ },
+ "functionCall": {
+ "extra": "Cấu hình này chỉ kích hoạt khả năng sử dụng công cụ của mô hình, từ đó có thể thêm các plugin loại công cụ cho mô hình. Tuy nhiên, việc hỗ trợ sử dụng công cụ thực sự hoàn toàn phụ thuộc vào chính mô hình, vui lòng tự kiểm tra tính khả dụng",
+ "title": "Hỗ trợ sử dụng công cụ"
+ },
+ "id": {
+ "extra": "Không thể sửa đổi sau khi tạo, sẽ được sử dụng làm id mô hình khi gọi AI",
+ "placeholder": "Vui lòng nhập id mô hình, ví dụ gpt-4o hoặc claude-3.5-sonnet",
+ "title": "ID mô hình"
+ },
+ "modalTitle": "Cấu hình mô hình tùy chỉnh",
+ "reasoning": {
+ "extra": "Cấu hình này sẽ chỉ kích hoạt khả năng suy nghĩ sâu của mô hình, hiệu quả cụ thể hoàn toàn phụ thuộc vào chính mô hình, vui lòng tự kiểm tra xem mô hình này có khả năng suy nghĩ sâu có thể sử dụng hay không",
+ "title": "Hỗ trợ suy nghĩ sâu"
+ },
+ "tokens": {
+ "extra": "Cài đặt số Token tối đa mà mô hình hỗ trợ",
+ "title": "Cửa sổ ngữ cảnh tối đa",
+ "unlimited": "Không giới hạn"
+ },
+ "vision": {
+ "extra": "Cấu hình này chỉ mở khả năng tải lên hình ảnh trong ứng dụng, việc hỗ trợ nhận diện hoàn toàn phụ thuộc vào mô hình, xin hãy tự kiểm tra khả năng nhận diện hình ảnh của mô hình này.",
+ "title": "Hỗ trợ nhận diện hình ảnh"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/Hình ảnh",
+ "inputCharts": "${{amount}}/Ký tự M",
+ "inputMinutes": "${{amount}}/Phút",
+ "inputTokens": "Nhập ${{amount}}/M",
+ "outputTokens": "Xuất ${{amount}}/M"
+ },
+ "releasedAt": "Phát hành vào {{releasedAt}}"
+ },
+ "list": {
+ "addNew": "Thêm mô hình",
+ "disabled": "Chưa được kích hoạt",
+ "disabledActions": {
+ "showMore": "Hiển thị tất cả"
+ },
+ "empty": {
+ "desc": "Vui lòng tạo mô hình tùy chỉnh hoặc kéo mô hình để bắt đầu sử dụng",
+ "title": "Chưa có mô hình nào khả dụng"
+ },
+ "enabled": "Đã được kích hoạt",
+ "enabledActions": {
+ "disableAll": "Vô hiệu hóa tất cả",
+ "enableAll": "Kích hoạt tất cả",
+ "sort": "Sắp xếp mô hình tùy chỉnh"
+ },
+ "enabledEmpty": "Chưa có mô hình nào được kích hoạt, hãy kích hoạt mô hình bạn yêu thích từ danh sách bên dưới nhé~",
+ "fetcher": {
+ "clear": "Xóa mô hình đã lấy",
+ "fetch": "Lấy danh sách mô hình",
+ "fetching": "Đang lấy danh sách mô hình...",
+ "latestTime": "Thời gian cập nhật lần cuối: {{time}}",
+ "noLatestTime": "Chưa lấy danh sách"
+ },
+ "resetAll": {
+ "conform": "Xác nhận việc đặt lại tất cả các thay đổi của mô hình hiện tại? Sau khi đặt lại, danh sách mô hình hiện tại sẽ trở về trạng thái mặc định",
+ "success": "Đặt lại thành công",
+ "title": "Đặt lại tất cả các thay đổi"
+ },
+ "search": "Tìm kiếm mô hình...",
+ "searchResult": "Tìm thấy {{count}} mô hình",
+ "title": "Danh sách mô hình",
+ "total": "Có tổng cộng {{count}} mô hình khả dụng"
+ },
+ "searchNotFound": "Không tìm thấy kết quả tìm kiếm"
+ },
+ "sortModal": {
+ "success": "Cập nhật sắp xếp thành công",
+ "title": "Sắp xếp tùy chỉnh",
+ "update": "Cập nhật"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "Sắp xóa nhà cung cấp AI này, sau khi xóa sẽ không thể khôi phục, xác nhận có xóa không?",
+ "deleteSuccess": "Xóa thành công",
+ "tooltip": "Cập nhật cấu hình cơ bản của nhà cung cấp",
+ "updateSuccess": "Cập nhật thành công"
+ },
+ "updateCustomAiProvider": {
+ "title": "Cập nhật cấu hình nhà cung cấp AI tùy chỉnh"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "Nhập khóa Vertex AI của bạn",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Khóa Vertex AI"
+ }
+ },
"zeroone": {
"title": "01.AI Zero One"
},
diff --git a/DigitalHumanWeb/locales/vi-VN/models.json b/DigitalHumanWeb/locales/vi-VN/models.json
index 96bab9d..46097a6 100644
--- a/DigitalHumanWeb/locales/vi-VN/models.json
+++ b/DigitalHumanWeb/locales/vi-VN/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B, với mẫu huấn luyện phong phú, cung cấp hiệu suất vượt trội trong ứng dụng ngành."
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat là một biến thể trong loạt Yi-1.5, thuộc về mô hình trò chuyện mã nguồn mở. Yi-1.5 là phiên bản nâng cấp của Yi, đã được tiền huấn luyện trên 500B dữ liệu chất lượng cao và tinh chỉnh trên 3 triệu mẫu đa dạng. So với Yi, Yi-1.5 thể hiện khả năng mạnh mẽ hơn trong mã hóa, toán học, suy luận và tuân theo chỉ dẫn, đồng thời duy trì khả năng hiểu ngôn ngữ, suy luận thông thường và hiểu đọc xuất sắc. Mô hình có các phiên bản độ dài ngữ cảnh 4K, 16K và 32K, với tổng số lượng tiền huấn luyện đạt 3.6T tokens."
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B hỗ trợ 16K Tokens, cung cấp khả năng tạo ngôn ngữ hiệu quả và mượt mà."
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "Zero One Vạn Vật, mô hình tinh chỉnh mã nguồn mở mới nhất với 34 tỷ tham số, hỗ trợ nhiều tình huống đối thoại, dữ liệu đào tạo chất lượng cao, phù hợp với sở thích của con người."
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "Zero One Vạn Vật, mô hình tinh chỉnh mã nguồn mở mới nhất với 9 tỷ tham số, hỗ trợ nhiều tình huống đối thoại, dữ liệu đào tạo chất lượng cao, phù hợp với sở thích của con người."
+ },
"360gpt-pro": {
"description": "360GPT Pro là thành viên quan trọng trong dòng mô hình AI của 360, đáp ứng nhu cầu đa dạng của các ứng dụng ngôn ngữ tự nhiên với khả năng xử lý văn bản hiệu quả, hỗ trợ hiểu văn bản dài và đối thoại nhiều vòng."
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K nhấn mạnh an toàn ngữ nghĩa và định hướng trách nhiệm, được thiết kế đặc biệt cho các tình huống ứng dụng có yêu cầu cao về an toàn nội dung, đảm bảo độ chính xác và độ ổn định trong trải nghiệm người dùng."
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 sử dụng tìm kiếm cây để xây dựng chuỗi tư duy, và đưa vào cơ chế phản hồi, sử dụng học tăng cường để đào tạo, mô hình có khả năng tự phản hồi và sửa lỗi."
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro là mô hình xử lý ngôn ngữ tự nhiên cao cấp do công ty 360 phát hành, có khả năng tạo và hiểu văn bản xuất sắc, đặc biệt trong lĩnh vực tạo ra và sáng tạo, có thể xử lý các nhiệm vụ chuyển đổi ngôn ngữ phức tạp và diễn xuất vai trò."
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 sử dụng tìm kiếm cây để xây dựng chuỗi tư duy, và giới thiệu cơ chế phản hồi, sử dụng học tăng cường để đào tạo, mô hình có khả năng tự phản hồi và sửa lỗi."
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra là phiên bản mạnh mẽ nhất trong dòng mô hình lớn Xinghuo, nâng cao khả năng hiểu và tóm tắt nội dung văn bản trong khi nâng cấp liên kết tìm kiếm trực tuyến. Đây là giải pháp toàn diện nhằm nâng cao năng suất văn phòng và đáp ứng chính xác nhu cầu, là sản phẩm thông minh dẫn đầu ngành."
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "Mô hình có khả năng hàng đầu trong nước, vượt trội hơn các mô hình chính thống nước ngoài trong các nhiệm vụ tiếng Trung như bách khoa toàn thư, văn bản dài, sáng tạo nội dung. Cũng có khả năng đa phương tiện hàng đầu trong ngành, thể hiện xuất sắc trong nhiều tiêu chuẩn đánh giá uy tín."
},
+ "Baichuan4-Air": {
+ "description": "Mô hình có khả năng hàng đầu trong nước, vượt trội hơn các mô hình chính thống nước ngoài trong các nhiệm vụ tiếng Trung như bách khoa toàn thư, văn bản dài và sáng tạo nội dung. Cũng có khả năng đa phương tiện hàng đầu trong ngành, thể hiện xuất sắc trong nhiều tiêu chuẩn đánh giá uy tín."
+ },
+ "Baichuan4-Turbo": {
+ "description": "Mô hình có khả năng hàng đầu trong nước, vượt trội hơn các mô hình chính thống nước ngoài trong các nhiệm vụ tiếng Trung như bách khoa toàn thư, văn bản dài và sáng tạo nội dung. Cũng có khả năng đa phương tiện hàng đầu trong ngành, thể hiện xuất sắc trong nhiều tiêu chuẩn đánh giá uy tín."
+ },
+ "DeepSeek-R1": {
+ "description": "Mô hình LLM hiệu quả tiên tiến nhất, xuất sắc trong suy luận, toán học và lập trình."
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1 - mô hình lớn hơn và thông minh hơn trong bộ công cụ DeepSeek - đã được chưng cất vào kiến trúc Llama 70B. Dựa trên các bài kiểm tra và đánh giá của con người, mô hình này thông minh hơn so với Llama 70B gốc, đặc biệt thể hiện xuất sắc trong các nhiệm vụ yêu cầu độ chính xác về toán học và sự thật."
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Mô hình chưng cất DeepSeek-R1 dựa trên Qwen2.5-Math-1.5B, tối ưu hóa hiệu suất suy luận thông qua học tăng cường và dữ liệu khởi động lạnh, mô hình mã nguồn mở làm mới tiêu chuẩn đa nhiệm."
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Mô hình chưng cất DeepSeek-R1 dựa trên Qwen2.5-14B, tối ưu hóa hiệu suất suy luận thông qua học tăng cường và dữ liệu khởi động lạnh, mô hình mã nguồn mở làm mới tiêu chuẩn đa nhiệm."
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "Dòng DeepSeek-R1 tối ưu hóa hiệu suất suy luận thông qua học tăng cường và dữ liệu khởi động lạnh, mô hình mã nguồn mở làm mới tiêu chuẩn đa nhiệm, vượt qua mức OpenAI-o1-mini."
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "Mô hình chưng cất DeepSeek-R1 dựa trên Qwen2.5-Math-7B, tối ưu hóa hiệu suất suy luận thông qua học tăng cường và dữ liệu khởi động lạnh, mô hình mã nguồn mở làm mới tiêu chuẩn đa nhiệm."
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro là mô hình lớn đa phương thức được nâng cấp hoàn toàn, hỗ trợ nhận diện hình ảnh với bất kỳ độ phân giải nào và tỷ lệ dài rộng cực đoan, tăng cường khả năng suy luận thị giác, nhận diện tài liệu, hiểu thông tin chi tiết và tuân thủ chỉ dẫn."
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite có tốc độ phản hồi cực nhanh, giá trị tốt hơn, cung cấp sự lựa chọn linh hoạt cho khách hàng trong nhiều tình huống khác nhau. Hỗ trợ suy diễn và tinh chỉnh trong ngữ cảnh 128k."
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite có tốc độ phản hồi cực nhanh, giá trị tốt hơn, cung cấp sự lựa chọn linh hoạt cho khách hàng trong nhiều tình huống khác nhau. Hỗ trợ suy diễn và tinh chỉnh trong ngữ cảnh 32k."
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite có tốc độ phản hồi cực nhanh, giá trị tốt hơn, cung cấp sự lựa chọn linh hoạt cho khách hàng trong nhiều tình huống khác nhau. Hỗ trợ suy diễn và tinh chỉnh trong ngữ cảnh 4k."
+ },
+ "Doubao-pro-128k": {
+ "description": "Mô hình chính có hiệu quả tốt nhất, phù hợp để xử lý các nhiệm vụ phức tạp, có hiệu quả tốt trong các tình huống như hỏi đáp tham khảo, tóm tắt, sáng tác, phân loại văn bản, và nhập vai. Hỗ trợ suy diễn và tinh chỉnh trong ngữ cảnh 128k."
+ },
+ "Doubao-pro-256k": {
+ "description": "Mô hình chủ lực có hiệu quả tốt nhất, phù hợp để xử lý các nhiệm vụ phức tạp, có hiệu quả tốt trong các tình huống như hỏi đáp tham khảo, tóm tắt, sáng tác, phân loại văn bản, và nhập vai. Hỗ trợ suy luận và tinh chỉnh với cửa sổ ngữ cảnh 256k."
+ },
+ "Doubao-pro-32k": {
+ "description": "Mô hình chính có hiệu quả tốt nhất, phù hợp để xử lý các nhiệm vụ phức tạp, có hiệu quả tốt trong các tình huống như hỏi đáp tham khảo, tóm tắt, sáng tác, phân loại văn bản, và nhập vai. Hỗ trợ suy diễn và tinh chỉnh trong ngữ cảnh 32k."
+ },
+ "Doubao-pro-4k": {
+ "description": "Mô hình chính có hiệu quả tốt nhất, phù hợp để xử lý các nhiệm vụ phức tạp, có hiệu quả tốt trong các tình huống như hỏi đáp tham khảo, tóm tắt, sáng tác, phân loại văn bản, và nhập vai. Hỗ trợ suy diễn và tinh chỉnh trong ngữ cảnh 4k."
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Mô hình Doubao-vision là mô hình lớn đa phương thức do Doubao phát triển, có khả năng hiểu và suy luận hình ảnh mạnh mẽ, cũng như khả năng hiểu chỉ dẫn chính xác. Mô hình thể hiện hiệu suất mạnh mẽ trong việc trích xuất thông tin văn bản từ hình ảnh và các nhiệm vụ suy luận dựa trên hình ảnh, có thể áp dụng cho các nhiệm vụ hỏi đáp thị giác phức tạp và đa dạng hơn."
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Mô hình Doubao-vision là mô hình lớn đa phương thức do Doubao phát triển, có khả năng hiểu và suy luận hình ảnh mạnh mẽ, cũng như khả năng hiểu chỉ dẫn chính xác. Mô hình thể hiện hiệu suất mạnh mẽ trong việc trích xuất thông tin văn bản từ hình ảnh và các nhiệm vụ suy luận dựa trên hình ảnh, có thể áp dụng cho các nhiệm vụ hỏi đáp thị giác phức tạp và đa dạng hơn."
+ },
+ "ERNIE-3.5-128K": {
+ "description": "Mô hình ngôn ngữ quy mô lớn hàng đầu do Baidu tự phát triển, bao phủ một lượng lớn tài liệu tiếng Trung và tiếng Anh, có khả năng tổng quát mạnh mẽ, có thể đáp ứng hầu hết các yêu cầu về đối thoại, hỏi đáp, sáng tạo nội dung và các tình huống ứng dụng plugin; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp luôn được cập nhật kịp thời."
+ },
+ "ERNIE-3.5-8K": {
+ "description": "Mô hình ngôn ngữ quy mô lớn hàng đầu do Baidu tự phát triển, bao phủ một lượng lớn tài liệu tiếng Trung và tiếng Anh, có khả năng tổng quát mạnh mẽ, có thể đáp ứng hầu hết các yêu cầu về đối thoại, hỏi đáp, sáng tạo nội dung và các tình huống ứng dụng plugin; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp luôn được cập nhật kịp thời."
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "Mô hình ngôn ngữ quy mô lớn hàng đầu do Baidu tự phát triển, bao phủ một lượng lớn tài liệu tiếng Trung và tiếng Anh, có khả năng tổng quát mạnh mẽ, có thể đáp ứng hầu hết các yêu cầu về đối thoại, hỏi đáp, sáng tạo nội dung và các tình huống ứng dụng plugin; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp luôn được cập nhật kịp thời."
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "Mô hình ngôn ngữ quy mô siêu lớn hàng đầu do Baidu tự phát triển, so với ERNIE 3.5 đã nâng cấp toàn diện khả năng của mô hình, phù hợp rộng rãi với các nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm Baidu, đảm bảo thông tin hỏi đáp luôn cập nhật."
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "Mô hình ngôn ngữ quy mô siêu lớn hàng đầu do Baidu tự phát triển, so với ERNIE 3.5 đã nâng cấp toàn diện khả năng của mô hình, phù hợp rộng rãi với các nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm Baidu, đảm bảo thông tin hỏi đáp luôn cập nhật."
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "Mô hình ngôn ngữ quy mô siêu lớn tự phát triển của Baidu, có hiệu suất tổng thể xuất sắc, phù hợp rộng rãi cho các tình huống tác vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo tính kịp thời của thông tin câu hỏi đáp. So với ERNIE 4.0, nó có hiệu suất tốt hơn."
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "Mô hình ngôn ngữ quy mô siêu lớn hàng đầu do Baidu tự phát triển, có hiệu suất tổng thể xuất sắc, phù hợp rộng rãi với các nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm Baidu, đảm bảo thông tin hỏi đáp luôn cập nhật. So với ERNIE 4.0, hiệu suất tốt hơn."
+ },
+ "ERNIE-Character-8K": {
+ "description": "Mô hình ngôn ngữ quy mô lớn cho các tình huống chuyên biệt do Baidu tự phát triển, phù hợp cho các ứng dụng như NPC trong game, đối thoại dịch vụ khách hàng, và vai trò trong đối thoại, phong cách nhân vật rõ ràng và nhất quán hơn, khả năng tuân thủ chỉ dẫn mạnh mẽ, hiệu suất suy diễn tốt hơn."
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "Mô hình ngôn ngữ quy mô lớn nhẹ do Baidu tự phát triển, kết hợp hiệu suất mô hình xuất sắc với khả năng suy diễn, hiệu quả tốt hơn ERNIE Lite, phù hợp cho việc suy diễn trên thẻ tăng tốc AI có công suất thấp."
+ },
+ "ERNIE-Speed-128K": {
+ "description": "Mô hình ngôn ngữ quy mô lớn hiệu suất cao do Baidu phát hành vào năm 2024, có khả năng tổng quát xuất sắc, phù hợp làm mô hình nền để tinh chỉnh, xử lý tốt hơn các vấn đề trong các tình huống cụ thể, đồng thời có khả năng suy diễn tuyệt vời."
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "Mô hình ngôn ngữ quy mô lớn hiệu suất cao do Baidu phát hành vào năm 2024, có khả năng tổng quát xuất sắc, hiệu quả tốt hơn ERNIE Speed, phù hợp làm mô hình nền để tinh chỉnh, xử lý tốt hơn các vấn đề trong các tình huống cụ thể, đồng thời có khả năng suy diễn tuyệt vời."
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) là một mô hình sáng tạo, phù hợp cho nhiều lĩnh vực ứng dụng và nhiệm vụ phức tạp."
},
- "Max-32k": {
- "description": "Spark Max 32K được cấu hình với khả năng xử lý ngữ cảnh lớn, khả năng hiểu ngữ cảnh và lý luận logic mạnh mẽ hơn, hỗ trợ đầu vào văn bản 32K token, phù hợp cho việc đọc tài liệu dài, hỏi đáp kiến thức riêng tư và các tình huống khác."
+ "InternVL2-8B": {
+ "description": "InternVL2-8B là một mô hình ngôn ngữ hình ảnh mạnh mẽ, hỗ trợ xử lý đa phương tiện giữa hình ảnh và văn bản, có khả năng nhận diện chính xác nội dung hình ảnh và tạo ra mô tả hoặc câu trả lời liên quan."
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B là một mô hình ngôn ngữ hình ảnh mạnh mẽ, hỗ trợ xử lý đa phương tiện giữa hình ảnh và văn bản, có khả năng nhận diện chính xác nội dung hình ảnh và tạo ra mô tả hoặc câu trả lời liên quan."
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "Khả năng suy luận hình ảnh xuất sắc trên hình ảnh độ phân giải cao, phù hợp cho các ứng dụng hiểu biết thị giác."
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "Khả năng suy luận hình ảnh cao cấp cho các ứng dụng đại lý hiểu biết thị giác."
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct là một trong những mô hình ngôn ngữ lớn mới nhất do Alibaba Cloud phát hành. Mô hình 72B này có khả năng cải thiện đáng kể trong các lĩnh vực mã hóa và toán học. Mô hình cũng cung cấp hỗ trợ đa ngôn ngữ, bao gồm hơn 29 ngôn ngữ, bao gồm tiếng Trung, tiếng Anh, v.v. Mô hình đã có sự cải thiện đáng kể trong việc tuân theo chỉ dẫn, hiểu dữ liệu có cấu trúc và tạo ra đầu ra có cấu trúc (đặc biệt là JSON)."
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct là một trong những mô hình ngôn ngữ lớn mới nhất do Alibaba Cloud phát hành. Mô hình 7B này có khả năng cải thiện đáng kể trong các lĩnh vực mã hóa và toán học. Mô hình cũng cung cấp hỗ trợ đa ngôn ngữ, bao gồm hơn 29 ngôn ngữ, bao gồm tiếng Trung, tiếng Anh, v.v. Mô hình đã có sự cải thiện đáng kể trong việc tuân theo chỉ dẫn, hiểu dữ liệu có cấu trúc và tạo ra đầu ra có cấu trúc (đặc biệt là JSON)."
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Mô hình văn bản được tinh chỉnh theo chỉ dẫn Llama 3.1, được tối ưu hóa cho các trường hợp sử dụng đối thoại đa ngôn ngữ, thể hiện xuất sắc trong nhiều mô hình trò chuyện mã nguồn mở và đóng có sẵn trên nhiều tiêu chuẩn ngành."
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO là một mô hình kết hợp đa dạng, nhằm cung cấp trải nghiệm sáng tạo xuất sắc."
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Mô hình văn bản được tinh chỉnh theo chỉ dẫn Llama 3.1, được tối ưu hóa cho các trường hợp sử dụng đối thoại đa ngôn ngữ, thể hiện xuất sắc trong nhiều mô hình trò chuyện mã nguồn mở và đóng có sẵn trên nhiều tiêu chuẩn ngành."
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Mô hình văn bản được tinh chỉnh theo chỉ dẫn Llama 3.1, được tối ưu hóa cho các trường hợp sử dụng đối thoại đa ngôn ngữ, thể hiện xuất sắc trong nhiều mô hình trò chuyện mã nguồn mở và đóng có sẵn trên nhiều tiêu chuẩn ngành."
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "Mô hình ngôn ngữ nhỏ tiên tiến nhất, có khả năng hiểu ngôn ngữ, khả năng suy luận xuất sắc và khả năng sinh văn bản."
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "Mô hình ngôn ngữ nhỏ tiên tiến nhất, có khả năng hiểu ngôn ngữ, khả năng suy luận xuất sắc và khả năng sinh văn bản."
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 là mô hình ngôn ngữ lớn mã nguồn mở đa ngôn ngữ tiên tiến nhất trong dòng Llama, mang đến trải nghiệm hiệu suất tương đương mô hình 405B với chi phí cực thấp. Dựa trên cấu trúc Transformer, và được cải thiện tính hữu ích và an toàn thông qua tinh chỉnh giám sát (SFT) và học tăng cường từ phản hồi của con người (RLHF). Phiên bản tinh chỉnh theo chỉ dẫn của nó được tối ưu hóa cho các cuộc đối thoại đa ngôn ngữ, thể hiện tốt hơn nhiều mô hình trò chuyện mã nguồn mở và đóng trong nhiều tiêu chuẩn ngành. Ngày cắt đứt kiến thức là tháng 12 năm 2023."
+ },
+ "MiniMax-Text-01": {
+ "description": "Trong dòng mô hình MiniMax-01, chúng tôi đã thực hiện những đổi mới táo bạo: lần đầu tiên hiện thực hóa quy mô lớn cơ chế chú ý tuyến tính, kiến trúc Transformer truyền thống không còn là lựa chọn duy nhất. Mô hình này có số lượng tham số lên tới 4560 tỷ, trong đó kích hoạt một lần là 45,9 tỷ. Hiệu suất tổng hợp của mô hình tương đương với các mô hình hàng đầu quốc tế, đồng thời có khả năng xử lý hiệu quả ngữ cảnh dài nhất toàn cầu lên tới 4 triệu token, gấp 32 lần GPT-4o và 20 lần Claude-3.5-Sonnet."
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) là mô hình chỉ dẫn chính xác cao, phù hợp cho tính toán phức tạp."
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) cung cấp đầu ra ngôn ngữ tối ưu và khả năng ứng dụng đa dạng."
- },
- "Phi-3-5-mini-instruct": {
- "description": "Cập nhật mô hình Phi-3-mini."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2 đã thể hiện hiệu suất xuất sắc trong nhiều tác vụ ngôn ngữ hình ảnh, bao gồm hiểu tài liệu và biểu đồ, hiểu văn bản trong cảnh, OCR, giải quyết vấn đề khoa học và toán học."
},
"Phi-3-medium-128k-instruct": {
"description": "Mô hình Phi-3-medium giống nhau, nhưng với kích thước ngữ cảnh lớn hơn cho RAG hoặc gợi ý ít."
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "Mô hình 7B tham số, chứng minh chất lượng tốt hơn Phi-3-mini, tập trung vào dữ liệu dày đặc lý luận chất lượng cao."
},
- "Pro-128k": {
- "description": "Spark Pro-128K được cấu hình với khả năng xử lý ngữ cảnh cực lớn, có thể xử lý tới 128K thông tin ngữ cảnh, đặc biệt phù hợp cho việc phân tích toàn bộ và xử lý mối liên hệ logic lâu dài trong nội dung văn bản dài, có thể cung cấp logic mạch lạc và hỗ trợ trích dẫn đa dạng trong giao tiếp văn bản phức tạp."
+ "Phi-3.5-mini-instruct": {
+ "description": "Phi-3-mini là phiên bản cập nhật của mô hình."
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Phi-3-vision là phiên bản cập nhật của mô hình."
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2 đã thể hiện hiệu suất xuất sắc trong nhiều tác vụ ngôn ngữ hình ảnh, bao gồm hiểu tài liệu và biểu đồ, hiểu văn bản trong cảnh, OCR, giải quyết vấn đề khoa học và toán học."
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct là mô hình ngôn ngữ lớn được tinh chỉnh theo chỉ dẫn trong loạt Qwen2, với quy mô tham số là 1.5B. Mô hình này dựa trên kiến trúc Transformer, sử dụng hàm kích hoạt SwiGLU, độ lệch QKV trong chú ý và chú ý theo nhóm. Nó thể hiện xuất sắc trong nhiều bài kiểm tra chuẩn về hiểu ngôn ngữ, sinh ngôn ngữ, khả năng đa ngôn ngữ, mã hóa, toán học và suy luận, vượt qua hầu hết các mô hình mã nguồn mở. So với Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct cho thấy sự cải thiện đáng kể về hiệu suất trong các bài kiểm tra MMLU, HumanEval, GSM8K, C-Eval và IFEval, mặc dù số lượng tham số hơi ít hơn."
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct là mô hình ngôn ngữ lớn được tinh chỉnh theo chỉ dẫn trong loạt Qwen2, với quy mô tham số là 7B. Mô hình này dựa trên kiến trúc Transformer, sử dụng hàm kích hoạt SwiGLU, độ lệch QKV trong chú ý và chú ý theo nhóm. Nó có khả năng xử lý đầu vào quy mô lớn. Mô hình thể hiện xuất sắc trong nhiều bài kiểm tra chuẩn về hiểu ngôn ngữ, sinh ngôn ngữ, khả năng đa ngôn ngữ, mã hóa, toán học và suy luận, vượt qua hầu hết các mô hình mã nguồn mở và thể hiện sức cạnh tranh tương đương với các mô hình độc quyền trong một số nhiệm vụ. Qwen2-7B-Instruct đã thể hiện sự cải thiện đáng kể về hiệu suất trong nhiều bài kiểm tra so với Qwen1.5-7B-Chat."
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL là phiên bản mới nhất của mô hình Qwen-VL, đạt được hiệu suất hàng đầu trong các thử nghiệm chuẩn hiểu biết hình ảnh."
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct là một trong những mô hình ngôn ngữ lớn mới nhất do Alibaba Cloud phát hành. Mô hình 7B này có khả năng cải thiện đáng kể trong các lĩnh vực mã hóa và toán học. Mô hình cũng cung cấp hỗ trợ đa ngôn ngữ, bao gồm hơn 29 ngôn ngữ, bao gồm tiếng Trung, tiếng Anh, v.v. Mô hình đã có sự cải thiện đáng kể trong việc tuân theo chỉ dẫn, hiểu dữ liệu có cấu trúc và tạo ra đầu ra có cấu trúc (đặc biệt là JSON)."
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct là phiên bản mới nhất trong loạt mô hình ngôn ngữ lớn chuyên biệt cho mã do Alibaba Cloud phát hành. Mô hình này được cải thiện đáng kể khả năng tạo mã, suy luận và sửa chữa thông qua việc đào tạo trên 5.5 triệu tỷ tokens, không chỉ nâng cao khả năng lập trình mà còn duy trì lợi thế về khả năng toán học và tổng quát. Mô hình cung cấp nền tảng toàn diện hơn cho các ứng dụng thực tế như tác nhân mã."
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat là phiên bản mã nguồn mở trong loạt mô hình tiền huấn luyện GLM-4 do Zhizhu AI phát hành. Mô hình này thể hiện xuất sắc trong nhiều lĩnh vực như ngữ nghĩa, toán học, suy luận, mã và kiến thức. Ngoài việc hỗ trợ đối thoại nhiều vòng, GLM-4-9B-Chat còn có các tính năng nâng cao như duyệt web, thực thi mã, gọi công cụ tùy chỉnh (Function Call) và suy luận văn bản dài. Mô hình hỗ trợ 26 ngôn ngữ, bao gồm tiếng Trung, tiếng Anh, tiếng Nhật, tiếng Hàn và tiếng Đức. Trong nhiều bài kiểm tra chuẩn, GLM-4-9B-Chat đã thể hiện hiệu suất xuất sắc, như AlignBench-v2, MT-Bench, MMLU và C-Eval. Mô hình hỗ trợ độ dài ngữ cảnh tối đa 128K, phù hợp cho nghiên cứu học thuật và ứng dụng thương mại."
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 là một mô hình suy diễn được điều khiển bởi học tăng cường (RL), giải quyết các vấn đề về tính lặp lại và khả năng đọc trong mô hình. Trước khi áp dụng RL, DeepSeek-R1 đã giới thiệu dữ liệu khởi động lạnh, tối ưu hóa thêm hiệu suất suy diễn. Nó thể hiện hiệu suất tương đương với OpenAI-o1 trong các nhiệm vụ toán học, mã và suy diễn, và thông qua phương pháp đào tạo được thiết kế cẩn thận, nâng cao hiệu quả tổng thể."
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 là một mô hình ngôn ngữ hỗn hợp chuyên gia (MoE) với 6710 tỷ tham số, sử dụng chú ý tiềm ẩn đa đầu (MLA) và kiến trúc DeepSeekMoE, kết hợp chiến lược cân bằng tải không có tổn thất phụ trợ, tối ưu hóa hiệu suất suy diễn và đào tạo. Thông qua việc được tiền huấn luyện trên 14.8 triệu tỷ token chất lượng cao, và thực hiện tinh chỉnh giám sát và học tăng cường, DeepSeek-V3 vượt trội hơn các mô hình mã nguồn mở khác, gần với các mô hình đóng kín hàng đầu."
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma là một trong những loạt mô hình mở tiên tiến nhẹ của Google. Đây là một mô hình ngôn ngữ quy mô lớn chỉ có bộ giải mã, hỗ trợ tiếng Anh, cung cấp trọng số mở, biến thể tiền huấn luyện và biến thể tinh chỉnh theo chỉ dẫn. Mô hình Gemma phù hợp cho nhiều nhiệm vụ sinh văn bản, bao gồm hỏi đáp, tóm tắt và suy luận. Mô hình 9B này được đào tạo trên 8 triệu tỷ tokens. Quy mô tương đối nhỏ của nó cho phép triển khai trong các môi trường hạn chế tài nguyên, như máy tính xách tay, máy tính để bàn hoặc cơ sở hạ tầng đám mây của riêng bạn, giúp nhiều người hơn có thể tiếp cận các mô hình AI tiên tiến và thúc đẩy đổi mới."
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 là một phần của gia đình mô hình ngôn ngữ lớn đa ngôn ngữ do Meta phát triển, bao gồm các biến thể tiền huấn luyện và tinh chỉnh theo chỉ dẫn với quy mô tham số 8B, 70B và 405B. Mô hình 8B này được tối ưu hóa cho các tình huống đối thoại đa ngôn ngữ, thể hiện xuất sắc trong nhiều bài kiểm tra chuẩn ngành. Mô hình được đào tạo bằng hơn 15 triệu tỷ tokens từ dữ liệu công khai và sử dụng các kỹ thuật như tinh chỉnh giám sát và học tăng cường phản hồi của con người để nâng cao tính hữu ích và an toàn của mô hình. Llama 3.1 hỗ trợ sinh văn bản và sinh mã, với thời điểm cắt kiến thức là tháng 12 năm 2023."
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview là một mô hình xử lý ngôn ngữ tự nhiên độc đáo, có khả năng xử lý hiệu quả các nhiệm vụ tạo đối thoại phức tạp và hiểu ngữ cảnh."
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview là một mô hình nghiên cứu do đội ngũ Qwen phát triển, tập trung vào khả năng suy diễn hình ảnh, có lợi thế độc đáo trong việc hiểu các cảnh phức tạp và giải quyết các vấn đề toán học liên quan đến hình ảnh."
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Là phiên bản thử nghiệm của Qwen2, Qwen1.5 sử dụng dữ liệu quy mô lớn để đạt được chức năng đối thoại chính xác hơn."
+ "Qwen/QwQ-32B": {
+ "description": "QwQ là mô hình suy diễn của dòng Qwen. So với các mô hình tinh chỉnh theo chỉ dẫn truyền thống, QwQ có khả năng tư duy và suy diễn, có thể đạt được hiệu suất được cải thiện đáng kể trong các nhiệm vụ hạ nguồn, đặc biệt là trong việc giải quyết các vấn đề khó khăn. QwQ-32B là mô hình suy diễn trung bình, có thể đạt được hiệu suất cạnh tranh khi so sánh với các mô hình suy diễn tiên tiến nhất (như DeepSeek-R1, o1-mini). Mô hình này sử dụng các công nghệ như RoPE, SwiGLU, RMSNorm và Attention QKV bias, có cấu trúc mạng 64 lớp và 40 đầu chú ý Q (trong kiến trúc GQA, KV là 8)."
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) cung cấp phản hồi nhanh và khả năng đối thoại tự nhiên, phù hợp cho môi trường đa ngôn ngữ."
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview là mô hình nghiên cứu thử nghiệm mới nhất của Qwen, tập trung vào việc nâng cao khả năng suy luận của AI. Thông qua việc khám phá các cơ chế phức tạp như trộn ngôn ngữ và suy luận đệ quy, những lợi thế chính bao gồm khả năng phân tích suy luận mạnh mẽ, khả năng toán học và lập trình. Tuy nhiên, cũng có những vấn đề về chuyển đổi ngôn ngữ, vòng lặp suy luận, các vấn đề an toàn và sự khác biệt về các khả năng khác."
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct là mô hình ngôn ngữ lớn được tinh chỉnh theo chỉ dẫn trong loạt Qwen2, với quy mô tham số là 1.5B. Mô hình này dựa trên kiến trúc Transformer, sử dụng hàm kích hoạt SwiGLU, độ lệch QKV trong chú ý và chú ý theo nhóm. Nó thể hiện xuất sắc trong nhiều bài kiểm tra chuẩn về hiểu ngôn ngữ, sinh ngôn ngữ, khả năng đa ngôn ngữ, mã hóa, toán học và suy luận, vượt qua hầu hết các mô hình mã nguồn mở. So với Qwen1.5-1.8B-Chat, Qwen2-1.5B-Instruct cho thấy sự cải thiện đáng kể về hiệu suất trong các bài kiểm tra MMLU, HumanEval, GSM8K, C-Eval và IFEval, mặc dù số lượng tham số hơi ít hơn."
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 là mô hình ngôn ngữ tổng quát tiên tiến, hỗ trợ nhiều loại chỉ dẫn."
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct là mô hình ngôn ngữ lớn được tinh chỉnh theo chỉ dẫn trong loạt Qwen2, với quy mô tham số là 72B. Mô hình này dựa trên kiến trúc Transformer, sử dụng hàm kích hoạt SwiGLU, độ lệch QKV trong chú ý và chú ý theo nhóm. Nó có khả năng xử lý đầu vào quy mô lớn. Mô hình thể hiện xuất sắc trong nhiều bài kiểm tra chuẩn về hiểu ngôn ngữ, sinh ngôn ngữ, khả năng đa ngôn ngữ, mã hóa, toán học và suy luận, vượt qua hầu hết các mô hình mã nguồn mở và thể hiện sức cạnh tranh tương đương với các mô hình độc quyền trong một số nhiệm vụ."
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL là phiên bản mới nhất của mô hình Qwen-VL, đạt được hiệu suất hàng đầu trong các thử nghiệm chuẩn hiểu biết hình ảnh."
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, nhằm tối ưu hóa việc xử lý các nhiệm vụ theo hướng dẫn."
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, nhằm tối ưu hóa việc xử lý các nhiệm vụ theo hướng dẫn."
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, có khả năng hiểu và tạo ra mạnh mẽ hơn."
+ "description": "Mô hình ngôn ngữ lớn được phát triển bởi đội ngũ Qianwen của Alibaba Cloud"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, sở hữu khả năng hiểu và tạo ra mạnh mẽ hơn."
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, được thiết kế để tối ưu hóa việc xử lý các tác vụ chỉ dẫn."
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, nhằm tối ưu hóa việc xử lý các nhiệm vụ theo hướng dẫn."
},
- "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, được thiết kế để tối ưu hóa việc xử lý các tác vụ chỉ dẫn."
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
"description": "Qwen2.5-Coder tập trung vào việc viết mã."
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math tập trung vào việc giải quyết các vấn đề trong lĩnh vực toán học, cung cấp giải pháp chuyên nghiệp cho các bài toán khó."
+ "Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct là phiên bản mới nhất trong loạt mô hình ngôn ngữ lớn chuyên biệt cho mã do Alibaba Cloud phát hành. Mô hình này được cải thiện đáng kể khả năng tạo mã, suy luận và sửa chữa thông qua việc đào tạo trên 5.5 triệu tỷ tokens, không chỉ nâng cao khả năng lập trình mà còn duy trì lợi thế về khả năng toán học và tổng quát. Mô hình cung cấp nền tảng toàn diện hơn cho các ứng dụng thực tế như tác nhân mã."
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 là dòng mô hình mới nhất của Qwen, hỗ trợ ngữ cảnh 128k, so với các mô hình mã nguồn mở tốt nhất hiện tại, Qwen2-72B vượt trội hơn hẳn trong nhiều khả năng như hiểu ngôn ngữ tự nhiên, kiến thức, mã, toán học và đa ngôn ngữ."
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 là dòng mô hình mới nhất của Qwen, có khả năng vượt qua các mô hình mã nguồn mở cùng quy mô hoặc thậm chí lớn hơn, Qwen2 7B đạt được lợi thế đáng kể trong nhiều bài kiểm tra, đặc biệt là trong việc hiểu mã và tiếng Trung."
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B là một mô hình ngôn ngữ hình ảnh mạnh mẽ, hỗ trợ xử lý đa phương thức giữa hình ảnh và văn bản, có khả năng nhận diện chính xác nội dung hình ảnh và sinh ra mô tả hoặc câu trả lời liên quan."
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct là một mô hình ngôn ngữ lớn với 14 tỷ tham số, có hiệu suất xuất sắc, tối ưu cho các tình huống tiếng Trung và đa ngôn ngữ, hỗ trợ các ứng dụng như hỏi đáp thông minh, tạo nội dung."
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct là một mô hình ngôn ngữ lớn với 32 tỷ tham số, có hiệu suất cân bằng, tối ưu cho các tình huống tiếng Trung và đa ngôn ngữ, hỗ trợ các ứng dụng như hỏi đáp thông minh, tạo nội dung."
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct hỗ trợ ngữ cảnh 16k, tạo ra văn bản dài hơn 8K. Hỗ trợ gọi hàm và tương tác liền mạch với hệ thống bên ngoài, nâng cao đáng kể tính linh hoạt và khả năng mở rộng. Kiến thức của mô hình đã tăng lên rõ rệt và khả năng mã hóa cũng như toán học được cải thiện đáng kể, hỗ trợ hơn 29 ngôn ngữ."
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct là một mô hình ngôn ngữ lớn với 7 tỷ tham số, hỗ trợ gọi hàm và tương tác liền mạch với các hệ thống bên ngoài, nâng cao tính linh hoạt và khả năng mở rộng. Tối ưu cho các tình huống tiếng Trung và đa ngôn ngữ, hỗ trợ các ứng dụng như hỏi đáp thông minh, tạo nội dung."
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct là một mô hình hướng dẫn lập trình dựa trên đào tạo trước quy mô lớn, có khả năng hiểu và sinh mã mạnh mẽ, có thể xử lý hiệu quả các nhiệm vụ lập trình khác nhau, đặc biệt phù hợp cho việc viết mã thông minh, tạo kịch bản tự động và giải đáp các vấn đề lập trình."
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct là một mô hình ngôn ngữ lớn được thiết kế đặc biệt cho việc tạo mã, hiểu mã và các tình huống phát triển hiệu quả, với quy mô 32B tham số hàng đầu trong ngành, có thể đáp ứng nhu cầu lập trình đa dạng."
+ },
+ "SenseChat": {
+ "description": "Mô hình phiên bản cơ bản (V4), độ dài ngữ cảnh 4K, khả năng tổng quát mạnh mẽ."
+ },
+ "SenseChat-128K": {
+ "description": "Mô hình phiên bản cơ bản (V4), độ dài ngữ cảnh 128K, thể hiện xuất sắc trong các nhiệm vụ hiểu và sinh văn bản dài."
+ },
+ "SenseChat-32K": {
+ "description": "Mô hình phiên bản cơ bản (V4), độ dài ngữ cảnh 32K, linh hoạt áp dụng trong nhiều tình huống."
+ },
+ "SenseChat-5": {
+ "description": "Phiên bản mô hình mới nhất (V5.5), độ dài ngữ cảnh 128K, khả năng cải thiện đáng kể trong suy luận toán học, đối thoại tiếng Anh, theo dõi chỉ dẫn và hiểu biết văn bản dài, ngang tầm với GPT-4o."
+ },
+ "SenseChat-5-1202": {
+ "description": "Là phiên bản mới nhất dựa trên V5.5, có sự cải thiện đáng kể về khả năng cơ bản giữa tiếng Trung và tiếng Anh, trò chuyện, kiến thức khoa học, kiến thức nhân văn, viết lách, logic toán học, kiểm soát số lượng từ và một số khía cạnh khác so với phiên bản trước."
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "Độ dài ngữ cảnh 32K, vượt qua GPT-4 trong hiểu biết đối thoại tiếng Quảng Đông, có thể so sánh với GPT-4 Turbo trong nhiều lĩnh vực như kiến thức, suy luận, toán học và lập trình mã."
+ },
+ "SenseChat-Character": {
+ "description": "Mô hình phiên bản tiêu chuẩn, độ dài ngữ cảnh 8K, tốc độ phản hồi cao."
+ },
+ "SenseChat-Character-Pro": {
+ "description": "Mô hình phiên bản cao cấp, độ dài ngữ cảnh 32K, khả năng được cải thiện toàn diện, hỗ trợ đối thoại tiếng Trung/tiếng Anh."
+ },
+ "SenseChat-Turbo": {
+ "description": "Phù hợp cho các tình huống hỏi đáp nhanh và tinh chỉnh mô hình."
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "Là phiên bản nhẹ mới nhất của mô hình, đạt được hơn 90% khả năng của mô hình đầy đủ, giảm đáng kể chi phí suy diễn."
+ },
+ "SenseChat-Vision": {
+ "description": "Mô hình phiên bản mới nhất (V5.5), hỗ trợ đầu vào nhiều hình ảnh, hoàn thiện khả năng cơ bản của mô hình, đạt được sự cải thiện lớn trong nhận diện thuộc tính đối tượng, mối quan hệ không gian, nhận diện sự kiện hành động, hiểu cảnh, nhận diện cảm xúc, suy luận kiến thức logic và hiểu sinh ra văn bản."
+ },
+ "Skylark2-lite-8k": {
+ "description": "Mô hình thế hệ thứ hai Skylark, mô hình Skylark2-lite có tốc độ phản hồi cao, phù hợp cho các tình huống yêu cầu tính thời gian thực cao, nhạy cảm với chi phí, không yêu cầu độ chính xác mô hình cao, chiều dài cửa sổ ngữ cảnh là 8k."
+ },
+ "Skylark2-pro-32k": {
+ "description": "Mô hình thế hệ thứ hai Skylark, phiên bản Skylark2-pro có độ chính xác cao hơn, phù hợp cho các tình huống tạo văn bản phức tạp, như tạo nội dung chuyên ngành, sáng tác tiểu thuyết, dịch thuật chất lượng cao, chiều dài cửa sổ ngữ cảnh là 32k."
+ },
+ "Skylark2-pro-4k": {
+ "description": "Mô hình thế hệ thứ hai Skylark, mô hình Skylark2-pro có độ chính xác cao hơn, phù hợp cho các tình huống tạo văn bản phức tạp, như tạo nội dung chuyên ngành, sáng tác tiểu thuyết, dịch thuật chất lượng cao, chiều dài cửa sổ ngữ cảnh là 4k."
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "Mô hình thế hệ thứ hai Skylark, mô hình Skylark2-pro-character có khả năng nhập vai và trò chuyện xuất sắc, giỏi nhập vai theo yêu cầu của người dùng, tạo ra những cuộc trò chuyện tự nhiên, phù hợp để xây dựng chatbot, trợ lý ảo và dịch vụ khách hàng trực tuyến, có tốc độ phản hồi cao."
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "Mô hình thế hệ thứ hai Skylark, mô hình Skylark2-pro-turbo-8k có tốc độ suy diễn nhanh hơn, chi phí thấp hơn, chiều dài cửa sổ ngữ cảnh là 8k."
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B là mô hình mã nguồn mở trong loạt ChatGLM, được phát triển bởi Zhizhu AI. Mô hình này giữ lại những đặc điểm xuất sắc của thế hệ trước, như khả năng đối thoại mượt mà và ngưỡng triển khai thấp, đồng thời giới thiệu các tính năng mới. Nó sử dụng dữ liệu đào tạo đa dạng hơn, số bước đào tạo đầy đủ hơn và chiến lược đào tạo hợp lý hơn, thể hiện xuất sắc trong các mô hình tiền huấn luyện dưới 10B. ChatGLM3-6B hỗ trợ đối thoại nhiều vòng, gọi công cụ, thực thi mã và các nhiệm vụ Agent trong các tình huống phức tạp. Ngoài mô hình đối thoại, còn có mô hình cơ bản ChatGLM-6B-Base và mô hình đối thoại văn bản dài ChatGLM3-6B-32K. Mô hình hoàn toàn mở cho nghiên cứu học thuật và cho phép sử dụng thương mại miễn phí sau khi đăng ký."
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B là phiên bản mã nguồn mở, cung cấp trải nghiệm đối thoại tối ưu cho các ứng dụng hội thoại."
},
+ "TeleAI/TeleChat2": {
+ "description": "Mô hình lớn TeleChat2 được phát triển độc lập từ 0 đến 1 bởi China Telecom, là một mô hình ngữ nghĩa sinh sinh, hỗ trợ các chức năng như hỏi đáp bách khoa, tạo mã, sinh văn bản dài, cung cấp dịch vụ tư vấn đối thoại cho người dùng, có khả năng tương tác đối thoại với người dùng, trả lời câu hỏi, hỗ trợ sáng tạo, giúp người dùng nhanh chóng và hiệu quả trong việc thu thập thông tin, kiến thức và cảm hứng. Mô hình thể hiện xuất sắc trong các vấn đề ảo giác, sinh văn bản dài và hiểu logic."
+ },
+ "TeleAI/TeleMM": {
+ "description": "Mô hình đa phương tiện TeleMM là một mô hình hiểu đa phương tiện do China Telecom phát triển, có khả năng xử lý nhiều loại đầu vào như văn bản và hình ảnh, hỗ trợ các chức năng như hiểu hình ảnh, phân tích biểu đồ, cung cấp dịch vụ hiểu đa phương tiện cho người dùng. Mô hình có khả năng tương tác đa phương tiện với người dùng, hiểu chính xác nội dung đầu vào, trả lời câu hỏi, hỗ trợ sáng tạo và cung cấp thông tin và cảm hứng đa phương tiện một cách hiệu quả. Mô hình thể hiện xuất sắc trong các nhiệm vụ đa phương tiện như nhận thức chi tiết và suy luận logic."
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct là một trong những mô hình ngôn ngữ lớn mới nhất do Alibaba Cloud phát hành. Mô hình 72B này có khả năng cải thiện đáng kể trong các lĩnh vực mã hóa và toán học. Mô hình cũng cung cấp hỗ trợ đa ngôn ngữ, bao gồm hơn 29 ngôn ngữ, bao gồm tiếng Trung, tiếng Anh, v.v. Mô hình đã có sự cải thiện đáng kể trong việc tuân theo chỉ dẫn, hiểu dữ liệu có cấu trúc và tạo ra đầu ra có cấu trúc (đặc biệt là JSON)."
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B, trong khi vẫn giữ được khả năng ngôn ngữ chung xuất sắc của dòng mô hình gốc, đã tăng cường đào tạo với 500 tỷ token chất lượng cao, nâng cao đáng kể khả năng logic toán học và mã."
+ },
"abab5.5-chat": {
"description": "Hướng đến các tình huống sản xuất, hỗ trợ xử lý nhiệm vụ phức tạp và sinh văn bản hiệu quả, phù hợp cho các ứng dụng trong lĩnh vực chuyên môn."
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "Tối ưu hóa cho các tình huống đối thoại bằng tiếng Trung, cung cấp khả năng sinh đối thoại mượt mà và phù hợp với thói quen diễn đạt tiếng Trung."
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Mô hình gọi hàm mã nguồn mở của Fireworks, cung cấp khả năng thực hiện chỉ dẫn xuất sắc và tính năng tùy chỉnh mở."
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Firefunction-v2 mới nhất của công ty Fireworks là một mô hình gọi hàm hiệu suất cao, được phát triển dựa trên Llama-3 và được tối ưu hóa nhiều, đặc biệt phù hợp cho các tình huống gọi hàm, đối thoại và theo dõi chỉ dẫn."
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b là một mô hình ngôn ngữ hình ảnh, có thể nhận cả hình ảnh và văn bản đầu vào, được huấn luyện bằng dữ liệu chất lượng cao, phù hợp cho các nhiệm vụ đa mô hình."
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 là một mô hình ngôn ngữ lớn tiên tiến, được tối ưu hóa thông qua học tăng cường và dữ liệu khởi động lạnh, có hiệu suất suy luận, toán học và lập trình xuất sắc."
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Mô hình chỉ dẫn Gemma 2 9B, dựa trên công nghệ trước đó của Google, phù hợp cho nhiều nhiệm vụ tạo văn bản như trả lời câu hỏi, tóm tắt và suy luận."
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Mô hình ngôn ngữ Mixture-of-Experts (MoE) mạnh mẽ do Deepseek cung cấp, với tổng số tham số là 671B, mỗi ký hiệu kích hoạt 37B tham số."
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Mô hình chỉ dẫn Llama 3 70B, được tối ưu hóa cho đối thoại đa ngôn ngữ và hiểu ngôn ngữ tự nhiên, hiệu suất vượt trội hơn nhiều mô hình cạnh tranh."
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Mô hình chỉ dẫn Llama 3 70B (phiên bản HF), giữ nguyên kết quả với thực hiện chính thức, phù hợp cho các nhiệm vụ theo dõi chỉ dẫn chất lượng cao."
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Mô hình chỉ dẫn Llama 3 8B, được tối ưu hóa cho đối thoại và các nhiệm vụ đa ngôn ngữ, thể hiện hiệu suất xuất sắc và hiệu quả."
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Mô hình chỉ dẫn Llama 3.1 8B, được tối ưu hóa cho đối thoại đa ngôn ngữ, có thể vượt qua hầu hết các mô hình mã nguồn mở và đóng trong các tiêu chuẩn ngành phổ biến."
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Mô hình suy luận hình ảnh chỉ dẫn với 11B tham số của Meta. Mô hình này được tối ưu hóa cho nhận diện hình ảnh, suy luận hình ảnh, mô tả hình ảnh và trả lời các câu hỏi chung liên quan đến hình ảnh. Mô hình có khả năng hiểu dữ liệu hình ảnh như biểu đồ và đồ thị, và thu hẹp khoảng cách giữa hình ảnh và ngôn ngữ thông qua việc tạo mô tả văn bản về chi tiết hình ảnh."
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Mô hình chỉ dẫn Llama 3.2 3B là một mô hình đa ngôn ngữ nhẹ mà Meta phát hành. Mô hình này được thiết kế để tăng cường hiệu quả, mang lại cải tiến đáng kể về độ trễ và chi phí so với các mô hình lớn hơn. Các trường hợp sử dụng ví dụ của mô hình này bao gồm truy vấn, viết lại thông báo và hỗ trợ viết."
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Mô hình suy luận hình ảnh chỉ dẫn với 90B tham số của Meta. Mô hình này được tối ưu hóa cho nhận diện hình ảnh, suy luận hình ảnh, mô tả hình ảnh và trả lời các câu hỏi chung liên quan đến hình ảnh. Mô hình có khả năng hiểu dữ liệu hình ảnh như biểu đồ và đồ thị, và thu hẹp khoảng cách giữa hình ảnh và ngôn ngữ thông qua việc tạo mô tả văn bản về chi tiết hình ảnh."
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct là phiên bản cập nhật tháng 12 của Llama 3.1 70B. Mô hình này được cải tiến dựa trên Llama 3.1 70B (ra mắt vào tháng 7 năm 2024), nâng cao khả năng gọi công cụ, hỗ trợ văn bản đa ngôn ngữ, toán học và lập trình. Mô hình này đạt được trình độ hàng đầu trong ngành về suy luận, toán học và tuân thủ hướng dẫn, đồng thời có thể cung cấp hiệu suất tương tự như 3.1 405B, với lợi thế đáng kể về tốc độ và chi phí."
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "Mô hình 24B tham số, có khả năng tiên tiến tương đương với các mô hình lớn hơn."
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mô hình chỉ dẫn Mixtral MoE 8x22B, với số lượng tham số lớn và kiến trúc nhiều chuyên gia, hỗ trợ toàn diện cho việc xử lý hiệu quả các nhiệm vụ phức tạp."
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mô hình chỉ dẫn Mixtral MoE 8x7B, kiến trúc nhiều chuyên gia cung cấp khả năng theo dõi và thực hiện chỉ dẫn hiệu quả."
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mô hình chỉ dẫn Mixtral MoE 8x7B (phiên bản HF), hiệu suất nhất quán với thực hiện chính thức, phù hợp cho nhiều tình huống nhiệm vụ hiệu quả."
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "Mô hình MythoMax L2 13B, kết hợp công nghệ hợp nhất mới, xuất sắc trong việc kể chuyện và đóng vai."
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Mô hình chỉ dẫn Phi 3 Vision, mô hình đa mô hình nhẹ, có khả năng xử lý thông tin hình ảnh và văn bản phức tạp, với khả năng suy luận mạnh mẽ."
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "Mô hình StarCoder 15.5B, hỗ trợ các nhiệm vụ lập trình nâng cao, khả năng đa ngôn ngữ được cải thiện, phù hợp cho việc tạo và hiểu mã phức tạp."
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Mô hình QwQ là một mô hình nghiên cứu thử nghiệm được phát triển bởi đội ngũ Qwen, tập trung vào việc nâng cao khả năng suy luận của AI."
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Phiên bản 72B của mô hình Qwen-VL là thành quả mới nhất của Alibaba, đại diện cho gần một năm đổi mới."
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "Mô hình StarCoder 7B, được huấn luyện cho hơn 80 ngôn ngữ lập trình, có khả năng điền mã và hiểu ngữ cảnh xuất sắc."
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 là một loạt mô hình ngôn ngữ chỉ chứa bộ giải mã do đội ngũ Qwen của Alibaba Cloud phát triển. Những mô hình này cung cấp các kích thước khác nhau, bao gồm 0.5B, 1.5B, 3B, 7B, 14B, 32B và 72B, và có hai biến thể: phiên bản cơ sở (base) và phiên bản chỉ dẫn (instruct)."
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct là phiên bản mới nhất trong loạt mô hình ngôn ngữ lớn chuyên biệt cho mã do Alibaba Cloud phát hành. Mô hình này được cải thiện đáng kể khả năng tạo mã, suy luận và sửa chữa thông qua việc đào tạo trên 5.5 triệu tỷ tokens, không chỉ nâng cao khả năng lập trình mà còn duy trì lợi thế về khả năng toán học và tổng quát. Mô hình cung cấp nền tảng toàn diện hơn cho các ứng dụng thực tế như tác nhân mã."
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Mô hình Yi-Large, có khả năng xử lý đa ngôn ngữ xuất sắc, có thể được sử dụng cho nhiều nhiệm vụ sinh và hiểu ngôn ngữ."
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "Mô hình đa ngôn ngữ với 52B tham số (12B hoạt động), cung cấp cửa sổ ngữ cảnh dài 256K, gọi hàm, đầu ra có cấu trúc và tạo ra nội dung có căn cứ."
},
- "ai21-jamba-instruct": {
- "description": "Mô hình LLM dựa trên Mamba đạt hiệu suất, chất lượng và hiệu quả chi phí tốt nhất trong ngành."
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet nâng cao tiêu chuẩn ngành, hiệu suất vượt trội hơn các mô hình cạnh tranh và Claude 3 Opus, thể hiện xuất sắc trong nhiều đánh giá, đồng thời có tốc độ và chi phí của mô hình tầm trung của chúng tôi."
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet nâng cao tiêu chuẩn ngành, hiệu suất vượt trội so với các mô hình đối thủ và Claude 3 Opus, thể hiện xuất sắc trong các đánh giá rộng rãi, đồng thời có tốc độ và chi phí tương đương với các mô hình tầm trung của chúng tôi."
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku là mô hình nhanh nhất và gọn nhẹ nhất của Anthropic, cung cấp tốc độ phản hồi gần như ngay lập tức. Nó có thể nhanh chóng trả lời các truy vấn và yêu cầu đơn giản. Khách hàng sẽ có thể xây dựng trải nghiệm AI liền mạch mô phỏng tương tác của con người. Claude 3 Haiku có thể xử lý hình ảnh và trả về đầu ra văn bản, với cửa sổ ngữ cảnh 200K."
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus là mô hình mạnh mẽ nhất của Anthropic, được sử dụng để xử lý các nhiệm vụ phức tạp cao. Nó thể hiện xuất sắc về hiệu suất, trí thông minh, sự trôi chảy và khả năng hiểu biết."
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku là mô hình thế hệ tiếp theo nhanh nhất của Anthropic. So với Claude 3 Haiku, Claude 3.5 Haiku có sự cải thiện trong nhiều kỹ năng và vượt qua mô hình lớn nhất thế hệ trước Claude 3 Opus trong nhiều bài kiểm tra trí tuệ."
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet cung cấp khả năng vượt trội hơn Opus và tốc độ nhanh hơn Sonnet, trong khi vẫn giữ giá tương tự. Sonnet đặc biệt xuất sắc trong lập trình, khoa học dữ liệu, xử lý hình ảnh và các nhiệm vụ đại lý."
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet là mô hình thông minh nhất của Anthropic cho đến nay, và cũng là mô hình suy luận hỗn hợp đầu tiên trên thị trường. Claude 3.7 Sonnet có khả năng tạo ra phản hồi gần như ngay lập tức hoặc suy nghĩ từng bước kéo dài, cho phép người dùng thấy rõ những quá trình này. Sonnet đặc biệt xuất sắc trong lập trình, khoa học dữ liệu, xử lý hình ảnh và các nhiệm vụ đại diện."
+ },
"aya": {
"description": "Aya 23 là mô hình đa ngôn ngữ do Cohere phát hành, hỗ trợ 23 ngôn ngữ, tạo điều kiện thuận lợi cho các ứng dụng ngôn ngữ đa dạng."
},
"aya:35b": {
"description": "Aya 23 là mô hình đa ngôn ngữ do Cohere phát hành, hỗ trợ 23 ngôn ngữ, tạo điều kiện thuận lợi cho các ứng dụng ngôn ngữ đa dạng."
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B là mô hình ngôn ngữ lớn mã nguồn mở có thể thương mại hóa với 130 tỷ tham số, được phát triển bởi Baichuan Intelligence, đã đạt được hiệu suất tốt nhất trong cùng kích thước trên các benchmark tiếng Trung và tiếng Anh."
+ },
"charglm-3": {
"description": "CharGLM-3 được thiết kế đặc biệt cho vai trò và đồng hành cảm xúc, hỗ trợ trí nhớ nhiều vòng siêu dài và đối thoại cá nhân hóa, ứng dụng rộng rãi."
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 cung cấp những tiến bộ quan trọng trong khả năng cho doanh nghiệp, bao gồm ngữ cảnh 200K token hàng đầu trong ngành, giảm đáng kể tỷ lệ ảo giác của mô hình, nhắc nhở hệ thống và một tính năng kiểm tra mới: gọi công cụ."
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku là mô hình thế hệ tiếp theo nhanh nhất của Anthropic. So với Claude 3 Haiku, Claude 3.5 Haiku đã cải thiện ở nhiều kỹ năng và vượt qua mô hình lớn nhất thế hệ trước là Claude 3 Opus trong nhiều bài kiểm tra trí tuệ."
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet cung cấp khả năng vượt trội so với Opus và tốc độ nhanh hơn Sonnet, đồng thời giữ nguyên mức giá như Sonnet. Sonnet đặc biệt xuất sắc trong lập trình, khoa học dữ liệu, xử lý hình ảnh và các nhiệm vụ đại lý."
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet cung cấp khả năng vượt xa Opus và tốc độ nhanh hơn Sonnet, đồng thời giữ mức giá giống như Sonnet. Sonnet đặc biệt xuất sắc trong lập trình, khoa học dữ liệu, xử lý hình ảnh và các nhiệm vụ đại diện."
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet là mô hình AI mạnh nhất của Anthropic, với hiệu suất vượt trội so với các mô hình đối thủ và Claude 3 Opus, thể hiện xuất sắc trong nhiều đánh giá rộng rãi, đồng thời có tốc độ và chi phí tương đương với các mô hình tầm trung của chúng tôi."
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku là mô hình nhanh nhất và gọn nhẹ nhất của Anthropic, được thiết kế để đạt được phản hồi gần như ngay lập tức. Nó có hiệu suất định hướng nhanh và chính xác."
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet cung cấp sự cân bằng lý tưởng giữa trí thông minh và tốc độ cho khối lượng công việc doanh nghiệp. Nó cung cấp hiệu suất tối đa với mức giá thấp hơn, đáng tin cậy và phù hợp cho triển khai quy mô lớn."
},
- "claude-instant-1.2": {
- "description": "Mô hình của Anthropic được sử dụng cho việc sinh văn bản với độ trễ thấp và thông lượng cao, hỗ trợ sinh hàng trăm trang văn bản."
- },
"codegeex-4": {
"description": "CodeGeeX-4 là trợ lý lập trình AI mạnh mẽ, hỗ trợ nhiều ngôn ngữ lập trình với câu hỏi thông minh và hoàn thành mã, nâng cao hiệu suất phát triển."
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B là một mô hình tạo mã đa ngôn ngữ, hỗ trợ đầy đủ các chức năng như hoàn thành và tạo mã, trình giải thích mã, tìm kiếm trên mạng, gọi hàm, và hỏi đáp mã cấp kho, bao phủ nhiều tình huống trong phát triển phần mềm. Đây là mô hình tạo mã hàng đầu với số tham số dưới 10B."
+ },
"codegemma": {
"description": "CodeGemma là mô hình ngôn ngữ nhẹ chuyên dụng cho các nhiệm vụ lập trình khác nhau, hỗ trợ lặp lại và tích hợp nhanh chóng."
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama là một LLM tập trung vào việc sinh và thảo luận mã, kết hợp hỗ trợ cho nhiều ngôn ngữ lập trình, phù hợp cho môi trường phát triển."
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama là một LLM tập trung vào việc tạo mã và thảo luận, kết hợp hỗ trợ nhiều ngôn ngữ lập trình, phù hợp cho môi trường phát triển."
+ },
"codellama:13b": {
"description": "Code Llama là một LLM tập trung vào việc sinh và thảo luận mã, kết hợp hỗ trợ cho nhiều ngôn ngữ lập trình, phù hợp cho môi trường phát triển."
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ là một mô hình ngôn ngữ lớn hiệu suất cao, được thiết kế cho các tình huống doanh nghiệp thực tế và ứng dụng phức tạp."
},
+ "dall-e-2": {
+ "description": "Mô hình DALL·E thế hệ thứ hai, hỗ trợ tạo hình ảnh chân thực và chính xác hơn, với độ phân giải gấp 4 lần thế hệ đầu tiên."
+ },
+ "dall-e-3": {
+ "description": "Mô hình DALL·E mới nhất, phát hành vào tháng 11 năm 2023. Hỗ trợ tạo hình ảnh chân thực và chính xác hơn, với khả năng thể hiện chi tiết mạnh mẽ hơn."
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct cung cấp khả năng xử lý chỉ dẫn đáng tin cậy, hỗ trợ nhiều ứng dụng trong ngành."
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 là một mô hình suy diễn được điều khiển bởi học tăng cường (RL), giải quyết các vấn đề về tính lặp lại và khả năng đọc hiểu trong mô hình. Trước khi áp dụng RL, DeepSeek-R1 đã giới thiệu dữ liệu khởi động lạnh, tối ưu hóa thêm hiệu suất suy diễn. Nó thể hiện hiệu suất tương đương với OpenAI-o1 trong các nhiệm vụ toán học, mã và suy diễn, và thông qua phương pháp đào tạo được thiết kế cẩn thận, nâng cao hiệu quả tổng thể."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "Mô hình chưng cất DeepSeek-R1, tối ưu hóa hiệu suất suy luận thông qua học tăng cường và dữ liệu khởi động lạnh, mô hình mã nguồn mở làm mới tiêu chuẩn đa nhiệm."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B là mô hình chưng cất phát triển từ Llama-3.1-8B. Mô hình này sử dụng các mẫu được tạo ra từ DeepSeek-R1 để tinh chỉnh, thể hiện khả năng suy luận xuất sắc. Trong nhiều bài kiểm tra chuẩn, nó đã thể hiện tốt, trong đó đạt 89.1% độ chính xác trên MATH-500, đạt 50.4% tỷ lệ vượt qua trên AIME 2024, và đạt điểm 1205 trên CodeForces, thể hiện khả năng toán học và lập trình mạnh mẽ cho mô hình quy mô 8B."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "Mô hình chưng cất DeepSeek-R1, tối ưu hóa hiệu suất suy luận thông qua học tăng cường và dữ liệu khởi động lạnh, mô hình mã nguồn mở làm mới tiêu chuẩn đa nhiệm."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "Mô hình chưng cất DeepSeek-R1, tối ưu hóa hiệu suất suy luận thông qua học tăng cường và dữ liệu khởi động lạnh, mô hình mã nguồn mở làm mới tiêu chuẩn đa nhiệm."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B là mô hình được tạo ra từ Qwen2.5-32B thông qua chưng cất kiến thức. Mô hình này sử dụng 800.000 mẫu được chọn lọc từ DeepSeek-R1 để tinh chỉnh, thể hiện hiệu suất xuất sắc trong nhiều lĩnh vực như toán học, lập trình và suy luận. Trong nhiều bài kiểm tra chuẩn như AIME 2024, MATH-500, GPQA Diamond, nó đã đạt được kết quả xuất sắc, trong đó đạt 94.3% độ chính xác trên MATH-500, thể hiện khả năng suy luận toán học mạnh mẽ."
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B là mô hình được tạo ra từ Qwen2.5-Math-7B thông qua chưng cất kiến thức. Mô hình này sử dụng 800.000 mẫu được chọn lọc từ DeepSeek-R1 để tinh chỉnh, thể hiện khả năng suy luận xuất sắc. Trong nhiều bài kiểm tra chuẩn, nó đã thể hiện xuất sắc, trong đó đạt 92.8% độ chính xác trên MATH-500, đạt 55.5% tỷ lệ vượt qua trên AIME 2024, và đạt điểm 1189 trên CodeForces, thể hiện khả năng toán học và lập trình mạnh mẽ cho mô hình quy mô 7B."
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 kết hợp các đặc điểm xuất sắc của các phiên bản trước, tăng cường khả năng tổng quát và mã hóa."
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 là một mô hình ngôn ngữ hỗn hợp chuyên gia (MoE) với 6710 tỷ tham số, sử dụng chú ý tiềm ẩn đa đầu (MLA) và kiến trúc DeepSeekMoE, kết hợp với chiến lược cân bằng tải không có tổn thất phụ trợ, tối ưu hóa hiệu suất suy diễn và đào tạo. Thông qua việc được tiền huấn luyện trên 14.8 triệu tỷ token chất lượng cao, và thực hiện tinh chỉnh giám sát và học tăng cường, DeepSeek-V3 vượt trội về hiệu suất so với các mô hình mã nguồn mở khác, gần gũi với các mô hình đóng nguồn hàng đầu."
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B là mô hình tiên tiến được huấn luyện cho các cuộc đối thoại phức tạp."
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "LLM hiệu quả tiên tiến, xuất sắc trong suy luận, toán học và lập trình."
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 là một mô hình ngôn ngữ hình ảnh hỗn hợp chuyên gia (MoE) được phát triển dựa trên DeepSeekMoE-27B, sử dụng kiến trúc MoE với kích hoạt thưa, đạt được hiệu suất xuất sắc chỉ với 4.5B tham số được kích hoạt. Mô hình này thể hiện xuất sắc trong nhiều nhiệm vụ như hỏi đáp hình ảnh, nhận diện ký tự quang học, hiểu tài liệu/bảng/biểu đồ và định vị hình ảnh."
+ },
"deepseek-chat": {
"description": "Mô hình mã nguồn mở mới kết hợp khả năng tổng quát và mã, không chỉ giữ lại khả năng đối thoại tổng quát của mô hình Chat ban đầu và khả năng xử lý mã mạnh mẽ của mô hình Coder, mà còn tốt hơn trong việc phù hợp với sở thích của con người. Hơn nữa, DeepSeek-V2.5 cũng đã đạt được sự cải thiện lớn trong nhiều khía cạnh như nhiệm vụ viết, theo dõi chỉ dẫn."
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B là một mô hình ngôn ngữ mã, được đào tạo trên 20 triệu tỷ dữ liệu, trong đó 87% là mã và 13% là ngôn ngữ Trung và Anh. Mô hình này giới thiệu kích thước cửa sổ 16K và nhiệm vụ điền chỗ trống, cung cấp chức năng hoàn thành mã và điền đoạn mã ở cấp độ dự án."
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 là mô hình mã nguồn mở hỗn hợp chuyên gia, thể hiện xuất sắc trong các nhiệm vụ mã, tương đương với GPT4-Turbo."
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 là mô hình mã nguồn mở hỗn hợp chuyên gia, thể hiện xuất sắc trong các nhiệm vụ mã, tương đương với GPT4-Turbo."
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 là một mô hình suy diễn được điều khiển bởi học tăng cường (RL), giải quyết các vấn đề về tính lặp lại và khả năng đọc hiểu trong mô hình. Trước khi áp dụng RL, DeepSeek-R1 đã giới thiệu dữ liệu khởi động lạnh, tối ưu hóa thêm hiệu suất suy diễn. Nó thể hiện hiệu suất tương đương với OpenAI-o1 trong các nhiệm vụ toán học, mã và suy diễn, và thông qua phương pháp đào tạo được thiết kế cẩn thận, nâng cao hiệu quả tổng thể."
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 - mô hình lớn hơn và thông minh hơn trong bộ công cụ DeepSeek - đã được chưng cất vào kiến trúc Llama 70B. Dựa trên các bài kiểm tra chuẩn và đánh giá của con người, mô hình này thông minh hơn so với Llama 70B gốc, đặc biệt xuất sắc trong các nhiệm vụ yêu cầu độ chính xác về toán học và sự thật."
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "Mô hình DeepSeek-R1-Distill được tinh chỉnh từ các mẫu do DeepSeek-R1 tạo ra cho các mô hình mã nguồn mở như Qwen, Llama thông qua công nghệ chưng cất kiến thức."
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "Mô hình DeepSeek-R1-Distill được tinh chỉnh từ các mẫu do DeepSeek-R1 tạo ra cho các mô hình mã nguồn mở như Qwen, Llama thông qua công nghệ chưng cất kiến thức."
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "Mô hình DeepSeek-R1-Distill được tinh chỉnh từ các mẫu do DeepSeek-R1 tạo ra cho các mô hình mã nguồn mở như Qwen, Llama thông qua công nghệ chưng cất kiến thức."
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "Mô hình DeepSeek-R1-Distill được tinh chỉnh từ các mẫu do DeepSeek-R1 tạo ra cho các mô hình mã nguồn mở như Qwen, Llama thông qua công nghệ chưng cất kiến thức."
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "Mô hình DeepSeek-R1-Distill được tinh chỉnh từ các mẫu do DeepSeek-R1 tạo ra cho các mô hình mã nguồn mở như Qwen, Llama thông qua công nghệ chưng cất kiến thức."
+ },
+ "deepseek-reasoner": {
+ "description": "Mô hình suy diễn do DeepSeek phát triển. Trước khi đưa ra câu trả lời cuối cùng, mô hình sẽ xuất ra một đoạn nội dung chuỗi suy nghĩ để nâng cao độ chính xác của câu trả lời cuối."
+ },
"deepseek-v2": {
"description": "DeepSeek V2 là mô hình ngôn ngữ Mixture-of-Experts hiệu quả, phù hợp cho các nhu cầu xử lý tiết kiệm."
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B là mô hình mã thiết kế của DeepSeek, cung cấp khả năng sinh mã mạnh mẽ."
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 là mô hình MoE tự phát triển của Công ty Nghiên cứu Công nghệ AI Độ Sâu Hàng Châu, có nhiều thành tích xuất sắc trong các bài kiểm tra, đứng đầu bảng xếp hạng mô hình mã nguồn mở. V3 so với mô hình V2.5 đã cải thiện tốc độ tạo ra gấp 3 lần, mang đến trải nghiệm sử dụng nhanh chóng và mượt mà hơn cho người dùng."
+ },
"deepseek/deepseek-chat": {
"description": "Mô hình mã nguồn mở mới kết hợp khả năng tổng quát và mã, không chỉ giữ lại khả năng đối thoại tổng quát của mô hình Chat ban đầu và khả năng xử lý mã mạnh mẽ của mô hình Coder, mà còn tốt hơn trong việc phù hợp với sở thích của con người. Hơn nữa, DeepSeek-V2.5 cũng đã đạt được sự cải thiện lớn trong nhiều lĩnh vực như nhiệm vụ viết, theo dõi chỉ dẫn."
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 đã nâng cao khả năng suy luận của mô hình một cách đáng kể với rất ít dữ liệu được gán nhãn. Trước khi đưa ra câu trả lời cuối cùng, mô hình sẽ xuất ra một chuỗi suy nghĩ để nâng cao độ chính xác của câu trả lời cuối cùng."
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B là mô hình ngôn ngữ lớn dựa trên Llama3.3 70B, mô hình này sử dụng đầu ra tinh chỉnh từ DeepSeek R1 để đạt được hiệu suất cạnh tranh tương đương với các mô hình tiên tiến lớn."
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B là một mô hình ngôn ngữ lớn đã được tinh chế dựa trên Llama-3.1-8B-Instruct, được đào tạo bằng cách sử dụng đầu ra từ DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B là một mô hình ngôn ngữ lớn đã được tinh chế dựa trên Qwen 2.5 14B, được đào tạo bằng cách sử dụng đầu ra từ DeepSeek R1. Mô hình này đã vượt qua o1-mini của OpenAI trong nhiều bài kiểm tra chuẩn, đạt được những thành tựu công nghệ tiên tiến nhất trong các mô hình dày đặc (dense models). Dưới đây là một số kết quả từ các bài kiểm tra chuẩn:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\nMô hình này đã thể hiện hiệu suất cạnh tranh tương đương với các mô hình tiên tiến lớn hơn thông qua việc tinh chỉnh từ đầu ra của DeepSeek R1."
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B là một mô hình ngôn ngữ lớn đã được tinh chế dựa trên Qwen 2.5 32B, được đào tạo bằng cách sử dụng đầu ra từ DeepSeek R1. Mô hình này đã vượt qua o1-mini của OpenAI trong nhiều bài kiểm tra chuẩn, đạt được những thành tựu công nghệ tiên tiến nhất trong các mô hình dày đặc (dense models). Dưới đây là một số kết quả từ các bài kiểm tra chuẩn:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\nMô hình này đã thể hiện hiệu suất cạnh tranh tương đương với các mô hình tiên tiến lớn hơn thông qua việc tinh chỉnh từ đầu ra của DeepSeek R1."
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1 là mô hình mã nguồn mở mới nhất được phát hành bởi đội ngũ DeepSeek, có hiệu suất suy diễn rất mạnh mẽ, đặc biệt trong các nhiệm vụ toán học, lập trình và suy luận, đạt được mức độ tương đương với mô hình o1 của OpenAI."
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 đã nâng cao khả năng suy luận của mô hình một cách đáng kể với rất ít dữ liệu được gán nhãn. Trước khi đưa ra câu trả lời cuối cùng, mô hình sẽ xuất ra một chuỗi suy nghĩ để nâng cao độ chính xác của câu trả lời cuối cùng."
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3 đã đạt được bước đột phá lớn về tốc độ suy diễn so với các mô hình trước đó. Nó đứng đầu trong số các mô hình mã nguồn mở và có thể so sánh với các mô hình đóng nguồn tiên tiến nhất trên toàn cầu. DeepSeek-V3 sử dụng kiến trúc Attention đa đầu (MLA) và DeepSeekMoE, những kiến trúc này đã được xác thực toàn diện trong DeepSeek-V2. Hơn nữa, DeepSeek-V3 đã sáng tạo ra một chiến lược phụ trợ không mất mát cho cân bằng tải và thiết lập mục tiêu đào tạo dự đoán đa nhãn để đạt được hiệu suất mạnh mẽ hơn."
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3 đã đạt được bước đột phá lớn về tốc độ suy diễn so với các mô hình trước đó. Nó đứng đầu trong số các mô hình mã nguồn mở và có thể so sánh với các mô hình đóng nguồn tiên tiến nhất trên toàn cầu. DeepSeek-V3 sử dụng kiến trúc Attention đa đầu (MLA) và DeepSeekMoE, những kiến trúc này đã được xác thực toàn diện trong DeepSeek-V2. Hơn nữa, DeepSeek-V3 đã sáng tạo ra một chiến lược phụ trợ không mất mát cho cân bằng tải và thiết lập mục tiêu đào tạo dự đoán đa nhãn để đạt được hiệu suất mạnh mẽ hơn."
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite là mô hình phiên bản nhẹ thế hệ mới, tốc độ phản hồi cực nhanh, hiệu quả và độ trễ đạt tiêu chuẩn hàng đầu thế giới."
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k là phiên bản nâng cấp toàn diện dựa trên Doubao-1.5-Pro, hiệu quả tổng thể tăng 10%. Hỗ trợ suy luận với cửa sổ ngữ cảnh 256k, độ dài đầu ra tối đa lên đến 12k tokens. Hiệu suất cao hơn, cửa sổ lớn hơn, giá trị vượt trội, phù hợp với nhiều ứng dụng khác nhau."
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro là mô hình chủ lực thế hệ mới, hiệu suất được nâng cấp toàn diện, thể hiện xuất sắc trong các lĩnh vực kiến thức, mã nguồn, suy luận, và nhiều hơn nữa."
+ },
"emohaa": {
"description": "Emohaa là mô hình tâm lý, có khả năng tư vấn chuyên nghiệp, giúp người dùng hiểu các vấn đề cảm xúc."
},
+ "ernie-3.5-128k": {
+ "description": "Mô hình ngôn ngữ lớn quy mô lớn tự phát triển của Baidu, bao phủ một lượng lớn tài liệu tiếng Trung và tiếng Anh, có khả năng tổng quát mạnh mẽ, đáp ứng hầu hết các yêu cầu về đối thoại hỏi đáp, tạo nội dung, và ứng dụng plugin; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời."
+ },
+ "ernie-3.5-8k": {
+ "description": "Mô hình ngôn ngữ lớn quy mô lớn tự phát triển của Baidu, bao phủ một lượng lớn tài liệu tiếng Trung và tiếng Anh, có khả năng tổng quát mạnh mẽ, đáp ứng hầu hết các yêu cầu về đối thoại hỏi đáp, tạo nội dung, và ứng dụng plugin; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời."
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "Mô hình ngôn ngữ lớn quy mô lớn tự phát triển của Baidu, bao phủ một lượng lớn tài liệu tiếng Trung và tiếng Anh, có khả năng tổng quát mạnh mẽ, đáp ứng hầu hết các yêu cầu về đối thoại hỏi đáp, tạo nội dung, và ứng dụng plugin; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời."
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "Mô hình ngôn ngữ lớn siêu quy mô tự phát triển của Baidu, so với ERNIE 3.5 đã thực hiện nâng cấp toàn diện về khả năng mô hình, phù hợp rộng rãi với các tình huống nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời."
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "Mô hình ngôn ngữ lớn siêu quy mô tự phát triển của Baidu, so với ERNIE 3.5 đã thực hiện nâng cấp toàn diện về khả năng mô hình, phù hợp rộng rãi với các tình huống nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời."
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "Mô hình ngôn ngữ lớn siêu quy mô tự phát triển của Baidu, có hiệu suất tổng thể xuất sắc, phù hợp rộng rãi với các tình huống nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời. So với ERNIE 4.0, hiệu suất tốt hơn."
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "Mô hình ngôn ngữ lớn siêu quy mô tự phát triển của Baidu, có hiệu suất tổng thể xuất sắc, phù hợp rộng rãi với các tình huống nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời. So với ERNIE 4.0, hiệu suất tốt hơn."
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "Mô hình ngôn ngữ lớn siêu quy mô tự phát triển của Baidu, có hiệu suất tổng thể xuất sắc, phù hợp rộng rãi với các tình huống nhiệm vụ phức tạp trong nhiều lĩnh vực; hỗ trợ tự động kết nối với plugin tìm kiếm của Baidu, đảm bảo thông tin hỏi đáp kịp thời. So với ERNIE 4.0, hiệu suất tốt hơn."
+ },
+ "ernie-char-8k": {
+ "description": "Mô hình ngôn ngữ lớn theo ngữ cảnh tự phát triển của Baidu, phù hợp cho các ứng dụng như NPC trong trò chơi, đối thoại dịch vụ khách hàng, và vai trò trong đối thoại, có phong cách nhân vật rõ ràng và nhất quán, khả năng tuân theo lệnh mạnh mẽ, hiệu suất suy luận tốt hơn."
+ },
+ "ernie-char-fiction-8k": {
+ "description": "Mô hình ngôn ngữ lớn theo ngữ cảnh tự phát triển của Baidu, phù hợp cho các ứng dụng như NPC trong trò chơi, đối thoại dịch vụ khách hàng, và vai trò trong đối thoại, có phong cách nhân vật rõ ràng và nhất quán, khả năng tuân theo lệnh mạnh mẽ, hiệu suất suy luận tốt hơn."
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite là mô hình ngôn ngữ lớn nhẹ tự phát triển của Baidu, kết hợp hiệu suất mô hình xuất sắc với hiệu suất suy luận, phù hợp cho việc sử dụng trên thẻ tăng tốc AI với công suất thấp."
+ },
+ "ernie-lite-pro-128k": {
+ "description": "Mô hình ngôn ngữ lớn nhẹ tự phát triển của Baidu, kết hợp hiệu suất mô hình xuất sắc với hiệu suất suy luận, hiệu suất tốt hơn ERNIE Lite, phù hợp cho việc sử dụng trên thẻ tăng tốc AI với công suất thấp."
+ },
+ "ernie-novel-8k": {
+ "description": "Mô hình ngôn ngữ lớn tổng quát tự phát triển của Baidu, có lợi thế rõ rệt trong khả năng viết tiếp tiểu thuyết, cũng có thể được sử dụng trong các tình huống như kịch ngắn, phim ảnh."
+ },
+ "ernie-speed-128k": {
+ "description": "Mô hình ngôn ngữ lớn hiệu suất cao tự phát triển của Baidu, được phát hành vào năm 2024, có khả năng tổng quát xuất sắc, phù hợp làm mô hình nền để tinh chỉnh, xử lý tốt hơn các vấn đề trong tình huống cụ thể, đồng thời có hiệu suất suy luận xuất sắc."
+ },
+ "ernie-speed-pro-128k": {
+ "description": "Mô hình ngôn ngữ lớn hiệu suất cao tự phát triển của Baidu, được phát hành vào năm 2024, có khả năng tổng quát xuất sắc, hiệu suất tốt hơn ERNIE Speed, phù hợp làm mô hình nền để tinh chỉnh, xử lý tốt hơn các vấn đề trong tình huống cụ thể, đồng thời có hiệu suất suy luận xuất sắc."
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny là mô hình ngôn ngữ lớn hiệu suất siêu cao tự phát triển của Baidu, có chi phí triển khai và tinh chỉnh thấp nhất trong dòng sản phẩm văn tâm."
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) cung cấp hiệu suất ổn định và có thể điều chỉnh, là lựa chọn lý tưởng cho các giải pháp nhiệm vụ phức tạp."
},
@@ -329,20 +791,23 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro là mô hình AI hiệu suất cao của Google, được thiết kế để mở rộng cho nhiều nhiệm vụ."
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash là mô hình AI đa phương thức mới nhất của Google, có khả năng xử lý nhanh, hỗ trợ đầu vào văn bản, hình ảnh và video, phù hợp cho việc mở rộng hiệu quả cho nhiều nhiệm vụ."
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 là một mô hình đa phương thức hiệu quả, hỗ trợ mở rộng cho nhiều ứng dụng."
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 là một mô hình đa phương thức hiệu quả, hỗ trợ mở rộng cho nhiều ứng dụng."
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 được thiết kế để xử lý các tình huống nhiệm vụ quy mô lớn, cung cấp tốc độ xử lý vô song."
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B là một mô hình đa phương thức hiệu quả, hỗ trợ mở rộng cho nhiều ứng dụng."
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 là mô hình thử nghiệm mới nhất, có sự cải thiện đáng kể về hiệu suất trong các trường hợp sử dụng văn bản và đa phương thức."
},
"gemini-1.5-flash-exp-0827": {
- "description": "Gemini 1.5 Flash 0827 cung cấp khả năng xử lý đa phương thức được tối ưu hóa, phù hợp cho nhiều tình huống nhiệm vụ phức tạp."
+ "description": "Gemini 1.5 Flash 0827 cung cấp khả năng xử lý đa phương tiện tối ưu, áp dụng cho nhiều tình huống tác vụ phức tạp."
},
"gemini-1.5-flash-latest": {
"description": "Gemini 1.5 Flash là mô hình AI đa phương thức mới nhất của Google, có khả năng xử lý nhanh, hỗ trợ đầu vào văn bản, hình ảnh và video, phù hợp cho việc mở rộng hiệu quả cho nhiều nhiệm vụ."
@@ -354,14 +819,38 @@
"description": "Gemini 1.5 Pro 002 là mô hình sẵn sàng cho sản xuất mới nhất, cung cấp đầu ra chất lượng cao hơn, đặc biệt là trong các nhiệm vụ toán học, ngữ cảnh dài và thị giác."
},
"gemini-1.5-pro-exp-0801": {
- "description": "Gemini 1.5 Pro 0801 cung cấp khả năng xử lý đa phương thức xuất sắc, mang lại sự linh hoạt lớn hơn cho phát triển ứng dụng."
+ "description": "Gemini 1.5 Pro 0801 cung cấp khả năng xử lý đa phương tiện xuất sắc, mang lại tính linh hoạt cao hơn cho việc phát triển ứng dụng."
},
"gemini-1.5-pro-exp-0827": {
- "description": "Gemini 1.5 Pro 0827 kết hợp công nghệ tối ưu hóa mới nhất, mang lại khả năng xử lý dữ liệu đa phương thức hiệu quả hơn."
+ "description": "Gemini 1.5 Pro 0827 kết hợp công nghệ tối ưu hóa mới nhất, mang lại khả năng xử lý dữ liệu đa phương tiện hiệu quả hơn."
},
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro hỗ trợ lên đến 2 triệu tokens, là lựa chọn lý tưởng cho mô hình đa phương thức trung bình, phù hợp cho hỗ trợ đa diện cho các nhiệm vụ phức tạp."
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash cung cấp các tính năng và cải tiến thế hệ tiếp theo, bao gồm tốc độ vượt trội, sử dụng công cụ bản địa, tạo đa phương tiện và cửa sổ ngữ cảnh 1M token."
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash cung cấp các tính năng và cải tiến thế hệ tiếp theo, bao gồm tốc độ vượt trội, sử dụng công cụ bản địa, tạo đa phương tiện và cửa sổ ngữ cảnh 1M token."
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Biến thể mô hình Gemini 2.0 Flash được tối ưu hóa cho hiệu quả chi phí và độ trễ thấp."
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Biến thể mô hình Gemini 2.0 Flash được tối ưu hóa cho hiệu quả chi phí và độ trễ thấp."
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "Một mô hình Gemini 2.0 Flash được tối ưu hóa cho hiệu quả chi phí và độ trễ thấp."
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp là mô hình AI đa phương thức thử nghiệm mới nhất của Google, sở hữu các tính năng thế hệ tiếp theo, tốc độ vượt trội, gọi công cụ bản địa và sinh ra đa phương thức."
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp là mô hình AI đa phương thức thử nghiệm mới nhất của Google, sở hữu các tính năng thế hệ tiếp theo, tốc độ vượt trội, gọi công cụ bản địa và sinh ra đa phương thức."
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental là mô hình AI đa phương tiện thử nghiệm mới nhất của Google, có sự cải thiện chất lượng nhất định so với các phiên bản trước, đặc biệt là về kiến thức thế giới, mã và ngữ cảnh dài."
+ },
"gemma-7b-it": {
"description": "Gemma 7B phù hợp cho việc xử lý các nhiệm vụ quy mô vừa và nhỏ, đồng thời mang lại hiệu quả chi phí."
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 là mô hình hiệu quả do Google phát hành, bao gồm nhiều ứng dụng từ nhỏ đến xử lý dữ liệu phức tạp."
},
- "general": {
- "description": "Spark Lite là một mô hình ngôn ngữ lớn nhẹ, có độ trễ cực thấp và khả năng xử lý hiệu quả, hoàn toàn miễn phí và mở, hỗ trợ chức năng tìm kiếm trực tuyến theo thời gian thực. Đặc điểm phản hồi nhanh giúp nó thể hiện xuất sắc trong các ứng dụng suy luận trên thiết bị có công suất thấp và tinh chỉnh mô hình, mang lại hiệu quả chi phí và trải nghiệm thông minh xuất sắc cho người dùng, đặc biệt trong các tình huống hỏi đáp kiến thức, tạo nội dung và tìm kiếm."
- },
"generalv3": {
"description": "Spark Pro là một mô hình ngôn ngữ lớn hiệu suất cao được tối ưu hóa cho các lĩnh vực chuyên môn, tập trung vào toán học, lập trình, y tế, giáo dục và nhiều lĩnh vực khác, đồng thời hỗ trợ tìm kiếm trực tuyến và các plugin tích hợp như thời tiết, ngày tháng. Mô hình đã được tối ưu hóa thể hiện xuất sắc và hiệu suất cao trong các nhiệm vụ hỏi đáp kiến thức phức tạp, hiểu ngôn ngữ và sáng tạo văn bản cấp cao, là lựa chọn lý tưởng cho các tình huống ứng dụng chuyên nghiệp."
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 là phiên bản mô hình mới nhất, được thiết kế cho các nhiệm vụ phức tạp và đa dạng, thể hiện xuất sắc."
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat thể hiện hiệu suất cao trong nhiều lĩnh vực như ngữ nghĩa, toán học, suy luận, mã và kiến thức. Nó còn có khả năng duyệt web, thực thi mã, gọi công cụ tùy chỉnh và suy luận văn bản dài. Hỗ trợ 26 ngôn ngữ, bao gồm tiếng Nhật, tiếng Hàn và tiếng Đức."
+ },
"glm-4-air": {
"description": "GLM-4-Air là phiên bản có giá trị sử dụng cao, hiệu suất gần giống GLM-4, cung cấp tốc độ nhanh và giá cả phải chăng."
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash là lựa chọn lý tưởng cho các nhiệm vụ đơn giản, tốc độ nhanh nhất và giá cả phải chăng nhất."
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX là phiên bản nâng cấp của Flash, với tốc độ suy diễn siêu nhanh."
+ },
"glm-4-long": {
"description": "GLM-4-Long hỗ trợ đầu vào văn bản siêu dài, phù hợp cho các nhiệm vụ ghi nhớ và xử lý tài liệu quy mô lớn."
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V cung cấp khả năng hiểu và suy luận hình ảnh mạnh mẽ, hỗ trợ nhiều nhiệm vụ hình ảnh."
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash tập trung vào hiểu hình ảnh đơn lẻ một cách hiệu quả, phù hợp cho các tình huống phân tích hình ảnh nhanh chóng, chẳng hạn như phân tích hình ảnh theo thời gian thực hoặc xử lý hình ảnh hàng loạt."
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus có khả năng hiểu nội dung video và nhiều hình ảnh, phù hợp cho các nhiệm vụ đa phương tiện."
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 cung cấp khả năng xử lý đa phương thức tối ưu, phù hợp cho nhiều tình huống nhiệm vụ phức tạp."
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview có khả năng suy luận phức tạp mạnh mẽ, thể hiện xuất sắc trong các lĩnh vực suy luận logic, toán học, lập trình."
+ },
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash cung cấp các tính năng và cải tiến thế hệ tiếp theo, bao gồm tốc độ vượt trội, sử dụng công cụ bản địa, tạo đa phương tiện và cửa sổ ngữ cảnh 1M token."
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 kết hợp công nghệ tối ưu mới nhất, mang lại khả năng xử lý dữ liệu đa phương thức hiệu quả hơn."
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental là mô hình AI đa phương tiện thử nghiệm mới nhất của Google, có sự cải thiện chất lượng nhất định so với các phiên bản trước, đặc biệt là về kiến thức thế giới, mã và ngữ cảnh dài."
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash cung cấp khả năng xử lý đa phương thức được tối ưu hóa, phù hợp cho nhiều tình huống nhiệm vụ phức tạp."
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro kết hợp công nghệ tối ưu hóa mới nhất, mang lại khả năng xử lý dữ liệu đa phương thức hiệu quả hơn."
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 là mô hình hiệu quả do Google phát hành, bao gồm nhiều ứng dụng từ ứng dụng nhỏ đến xử lý dữ liệu phức tạp."
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 tiếp tục triết lý thiết kế nhẹ và hiệu quả."
},
+ "google/gemma-2-2b-it": {
+ "description": "Mô hình tinh chỉnh hướng dẫn nhẹ của Google"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 là mô hình hiệu quả do Google phát hành, bao gồm nhiều ứng dụng từ ứng dụng nhỏ đến xử lý dữ liệu phức tạp."
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 là một loạt mô hình văn bản mã nguồn mở nhẹ của Google."
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo, phù hợp cho nhiều nhiệm vụ sinh và hiểu văn bản, hiện tại trỏ đến gpt-3.5-turbo-0125."
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo, mô hình hiệu quả do OpenAI cung cấp, phù hợp cho các tác vụ trò chuyện và tạo văn bản, hỗ trợ gọi hàm song song."
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k, mô hình tạo văn bản dung lượng cao, phù hợp cho các nhiệm vụ phức tạp."
+ },
"gpt-4": {
"description": "GPT-4 cung cấp một cửa sổ ngữ cảnh lớn hơn, có khả năng xử lý các đầu vào văn bản dài hơn, phù hợp cho các tình huống cần tích hợp thông tin rộng rãi và phân tích dữ liệu."
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "Mô hình GPT-4 Turbo mới nhất có chức năng hình ảnh. Hiện tại, các yêu cầu hình ảnh có thể sử dụng chế độ JSON và gọi hàm. GPT-4 Turbo là một phiên bản nâng cao, cung cấp hỗ trợ chi phí hiệu quả cho các nhiệm vụ đa phương tiện. Nó tìm thấy sự cân bằng giữa độ chính xác và hiệu quả, phù hợp cho các ứng dụng cần tương tác theo thời gian thực."
},
- "gpt-4-1106-vision-preview": {
- "description": "Mô hình GPT-4 Turbo mới nhất có chức năng hình ảnh. Hiện tại, các yêu cầu hình ảnh có thể sử dụng chế độ JSON và gọi hàm. GPT-4 Turbo là một phiên bản nâng cao, cung cấp hỗ trợ chi phí hiệu quả cho các nhiệm vụ đa phương tiện. Nó tìm thấy sự cân bằng giữa độ chính xác và hiệu quả, phù hợp cho các ứng dụng cần tương tác theo thời gian thực."
- },
"gpt-4-32k": {
"description": "GPT-4 cung cấp một cửa sổ ngữ cảnh lớn hơn, có khả năng xử lý các đầu vào văn bản dài hơn, phù hợp cho các tình huống cần tích hợp thông tin rộng rãi và phân tích dữ liệu."
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "Mô hình GPT-4 Turbo mới nhất có chức năng hình ảnh. Hiện tại, các yêu cầu hình ảnh có thể sử dụng chế độ JSON và gọi hàm. GPT-4 Turbo là một phiên bản nâng cao, cung cấp hỗ trợ chi phí hiệu quả cho các nhiệm vụ đa phương tiện. Nó tìm thấy sự cân bằng giữa độ chính xác và hiệu quả, phù hợp cho các ứng dụng cần tương tác theo thời gian thực."
},
+ "gpt-4.5-preview": {
+ "description": "Bản nghiên cứu preview của GPT-4.5, đây là mô hình GPT lớn nhất và mạnh mẽ nhất mà chúng tôi từng phát triển. Nó sở hữu kiến thức rộng lớn về thế giới và có khả năng hiểu ý định của người dùng tốt hơn, giúp nó thể hiện xuất sắc trong các nhiệm vụ sáng tạo và lập kế hoạch tự động. GPT-4.5 có thể chấp nhận đầu vào văn bản và hình ảnh, và tạo ra đầu ra văn bản (bao gồm cả đầu ra có cấu trúc). Hỗ trợ các tính năng quan trọng cho nhà phát triển như gọi hàm, API theo lô và đầu ra theo luồng. Trong các nhiệm vụ cần sự sáng tạo, tư duy mở và đối thoại (như viết lách, học tập hoặc khám phá ý tưởng mới), GPT-4.5 thể hiện đặc biệt xuất sắc. Thời điểm cắt đứt kiến thức là tháng 10 năm 2023."
+ },
"gpt-4o": {
"description": "ChatGPT-4o là một mô hình động, được cập nhật theo thời gian thực để giữ phiên bản mới nhất. Nó kết hợp khả năng hiểu và sinh ngôn ngữ mạnh mẽ, phù hợp cho các ứng dụng quy mô lớn, bao gồm dịch vụ khách hàng, giáo dục và hỗ trợ kỹ thuật."
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o là một mô hình động, được cập nhật theo thời gian thực để giữ phiên bản mới nhất. Nó kết hợp khả năng hiểu và sinh ngôn ngữ mạnh mẽ, phù hợp cho các ứng dụng quy mô lớn, bao gồm dịch vụ khách hàng, giáo dục và hỗ trợ kỹ thuật."
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o là một mô hình động, được cập nhật liên tục để giữ phiên bản mới nhất. Nó kết hợp khả năng hiểu và tạo ngôn ngữ mạnh mẽ, phù hợp cho nhiều ứng dụng quy mô lớn, bao gồm dịch vụ khách hàng, giáo dục và hỗ trợ kỹ thuật."
+ },
+ "gpt-4o-audio-preview": {
+ "description": "Mô hình GPT-4o Audio, hỗ trợ đầu vào và đầu ra âm thanh."
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini là mô hình mới nhất do OpenAI phát hành sau GPT-4 Omni, hỗ trợ đầu vào hình ảnh và đầu ra văn bản. Là mô hình nhỏ gọn tiên tiến nhất của họ, nó rẻ hơn nhiều so với các mô hình tiên tiến gần đây khác và rẻ hơn hơn 60% so với GPT-3.5 Turbo. Nó giữ lại trí thông minh tiên tiến nhất trong khi có giá trị sử dụng đáng kể. GPT-4o mini đạt 82% điểm trong bài kiểm tra MMLU và hiện đứng cao hơn GPT-4 về sở thích trò chuyện."
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "Phiên bản thời gian thực của GPT-4o-mini, hỗ trợ đầu vào và đầu ra âm thanh và văn bản theo thời gian thực."
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "Phiên bản thời gian thực của GPT-4o, hỗ trợ đầu vào và đầu ra âm thanh và văn bản theo thời gian thực."
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "Phiên bản thời gian thực của GPT-4o, hỗ trợ đầu vào và đầu ra âm thanh và văn bản theo thời gian thực."
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "Phiên bản thời gian thực của GPT-4o, hỗ trợ đầu vào và đầu ra âm thanh và văn bản theo thời gian thực."
+ },
+ "grok-2-1212": {
+ "description": "Mô hình này đã được cải thiện về độ chính xác, khả năng tuân thủ hướng dẫn và khả năng đa ngôn ngữ."
+ },
+ "grok-2-vision-1212": {
+ "description": "Mô hình này đã được cải thiện về độ chính xác, khả năng tuân thủ hướng dẫn và khả năng đa ngôn ngữ."
+ },
+ "grok-beta": {
+ "description": "Có hiệu suất tương đương với Grok 2, nhưng hiệu quả, tốc độ và tính năng cao hơn."
+ },
+ "grok-vision-beta": {
+ "description": "Mô hình hiểu hình ảnh mới nhất, có khả năng xử lý nhiều loại thông tin hình ảnh khác nhau, bao gồm tài liệu, biểu đồ, ảnh chụp màn hình và ảnh."
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B là mô hình ngôn ngữ kết hợp giữa sáng tạo và trí thông minh, kết hợp nhiều mô hình hàng đầu."
},
+ "hunyuan-code": {
+ "description": "Mô hình sinh mã mới nhất của Hunyuan, được huấn luyện trên 200B dữ liệu mã chất lượng cao, trải qua nửa năm huấn luyện dữ liệu SFT chất lượng cao, độ dài cửa sổ ngữ cảnh tăng lên 8K, đứng đầu trong các chỉ số đánh giá tự động sinh mã cho năm ngôn ngữ lớn; trong đánh giá chất lượng cao của 10 tiêu chí mã tổng hợp cho năm ngôn ngữ, hiệu suất nằm trong nhóm đầu."
+ },
+ "hunyuan-functioncall": {
+ "description": "Mô hình FunctionCall với cấu trúc MOE mới nhất của Hunyuan, được huấn luyện trên dữ liệu FunctionCall chất lượng cao, với cửa sổ ngữ cảnh đạt 32K, dẫn đầu trong nhiều chỉ số đánh giá."
+ },
+ "hunyuan-large": {
+ "description": "Mô hình Hunyuan-large có tổng số tham số khoảng 389B, số tham số kích hoạt khoảng 52B, là mô hình MoE mã nguồn mở có quy mô tham số lớn nhất và hiệu quả nhất trong ngành hiện nay."
+ },
+ "hunyuan-large-longcontext": {
+ "description": "Chuyên xử lý các nhiệm vụ văn bản dài như tóm tắt tài liệu và hỏi đáp tài liệu, đồng thời cũng có khả năng xử lý các nhiệm vụ tạo văn bản chung. Thể hiện xuất sắc trong phân tích và tạo nội dung văn bản dài, có thể đáp ứng hiệu quả các yêu cầu xử lý nội dung dài phức tạp và chi tiết."
+ },
+ "hunyuan-lite": {
+ "description": "Nâng cấp lên cấu trúc MOE, với cửa sổ ngữ cảnh 256k, dẫn đầu nhiều mô hình mã nguồn mở trong các bộ đánh giá NLP, mã, toán học, ngành nghề, v.v."
+ },
+ "hunyuan-lite-vision": {
+ "description": "Mô hình đa phương thức mới nhất 7B của Hunyuan, cửa sổ ngữ cảnh 32K, hỗ trợ đối thoại đa phương thức trong các tình huống tiếng Trung và tiếng Anh, nhận diện đối tượng hình ảnh, hiểu biết tài liệu và bảng biểu, toán học đa phương thức, v.v., với các chỉ số đánh giá vượt trội hơn các mô hình cạnh tranh 7B ở nhiều khía cạnh."
+ },
+ "hunyuan-pro": {
+ "description": "Mô hình văn bản dài MOE-32K với quy mô hàng triệu tham số. Đạt được mức độ dẫn đầu tuyệt đối trên nhiều benchmark, có khả năng xử lý các lệnh phức tạp và suy diễn, có khả năng toán học phức tạp, hỗ trợ functioncall, được tối ưu hóa cho các lĩnh vực dịch thuật đa ngôn ngữ, tài chính, pháp lý và y tế."
+ },
+ "hunyuan-role": {
+ "description": "Mô hình đóng vai trò mới nhất của Hunyuan, được tinh chỉnh và huấn luyện bởi Hunyuan, dựa trên mô hình Hunyuan kết hợp với bộ dữ liệu tình huống đóng vai trò để tăng cường huấn luyện, có hiệu suất cơ bản tốt hơn trong các tình huống đóng vai trò."
+ },
+ "hunyuan-standard": {
+ "description": "Sử dụng chiến lược định tuyến tốt hơn, đồng thời giảm thiểu vấn đề cân bằng tải và đồng nhất chuyên gia. Về mặt văn bản dài, chỉ số tìm kiếm đạt 99.9%. MOE-32K có giá trị hiệu suất tương đối cao, cân bằng giữa hiệu quả và giá cả, có thể xử lý đầu vào văn bản dài."
+ },
+ "hunyuan-standard-256K": {
+ "description": "Sử dụng chiến lược định tuyến tốt hơn, đồng thời giảm thiểu vấn đề cân bằng tải và đồng nhất chuyên gia. Về mặt văn bản dài, chỉ số tìm kiếm đạt 99.9%. MOE-256K đã có bước đột phá về độ dài và hiệu quả, mở rộng đáng kể độ dài đầu vào có thể."
+ },
+ "hunyuan-standard-vision": {
+ "description": "Mô hình đa phương thức mới nhất của Hunyuan, hỗ trợ trả lời đa ngôn ngữ, khả năng tiếng Trung và tiếng Anh cân bằng."
+ },
+ "hunyuan-translation": {
+ "description": "Hỗ trợ dịch giữa 15 ngôn ngữ bao gồm tiếng Trung, tiếng Anh, tiếng Nhật, tiếng Pháp, tiếng Bồ Đào Nha, tiếng Tây Ban Nha, tiếng Thổ Nhĩ Kỳ, tiếng Nga, tiếng Ả Rập, tiếng Hàn, tiếng Ý, tiếng Đức, tiếng Việt, tiếng Mã Lai và tiếng Indonesia, dựa trên bộ đánh giá dịch tự động hóa COMET, có khả năng dịch giữa các ngôn ngữ phổ biến tốt hơn so với các mô hình cùng quy mô trên thị trường."
+ },
+ "hunyuan-translation-lite": {
+ "description": "Mô hình dịch Hỗn Nguyên hỗ trợ dịch theo kiểu đối thoại ngôn ngữ tự nhiên; hỗ trợ dịch giữa 15 ngôn ngữ bao gồm tiếng Trung, tiếng Anh, tiếng Nhật, tiếng Pháp, tiếng Bồ Đào Nha, tiếng Tây Ban Nha, tiếng Thổ Nhĩ Kỳ, tiếng Nga, tiếng Ả Rập, tiếng Hàn, tiếng Ý, tiếng Đức, tiếng Việt, tiếng Mã Lai và tiếng Indonesia."
+ },
+ "hunyuan-turbo": {
+ "description": "Phiên bản xem trước của thế hệ mới mô hình ngôn ngữ lớn Hunyuan, sử dụng cấu trúc mô hình chuyên gia hỗn hợp (MoE) hoàn toàn mới, so với hunyuan-pro, hiệu suất suy diễn nhanh hơn và hiệu quả mạnh mẽ hơn."
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "Phiên bản cố định hunyuan-turbo ngày 20 tháng 11 năm 2024, là một phiên bản nằm giữa hunyuan-turbo và hunyuan-turbo-latest."
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "Phiên bản này tối ưu hóa: quy mô chỉ thị dữ liệu, nâng cao đáng kể khả năng tổng quát của mô hình; nâng cao đáng kể khả năng toán học, lập trình, và suy luận logic; tối ưu hóa khả năng hiểu biết văn bản và từ ngữ; tối ưu hóa chất lượng tạo nội dung văn bản."
+ },
+ "hunyuan-turbo-latest": {
+ "description": "Tối ưu hóa trải nghiệm chung, bao gồm hiểu biết NLP, sáng tạo văn bản, trò chuyện, hỏi đáp kiến thức, dịch thuật, và các lĩnh vực khác; nâng cao tính nhân văn, tối ưu hóa trí tuệ cảm xúc của mô hình; cải thiện khả năng làm rõ khi ý định không rõ ràng; nâng cao khả năng xử lý các vấn đề phân tích từ ngữ; nâng cao chất lượng và khả năng tương tác trong sáng tạo; cải thiện trải nghiệm đa vòng."
+ },
+ "hunyuan-turbo-vision": {
+ "description": "Mô hình ngôn ngữ hình ảnh thế hệ mới của Hunyuan, sử dụng cấu trúc mô hình chuyên gia hỗn hợp (MoE) hoàn toàn mới, nâng cao toàn diện khả năng nhận diện cơ bản, sáng tạo nội dung, hỏi đáp kiến thức, và phân tích suy luận so với mô hình thế hệ trước."
+ },
+ "hunyuan-vision": {
+ "description": "Mô hình đa phương thức mới nhất của Hunyuan, hỗ trợ đầu vào hình ảnh + văn bản để tạo ra nội dung văn bản."
+ },
"internlm/internlm2_5-20b-chat": {
"description": "Mô hình mã nguồn mở sáng tạo InternLM2.5, thông qua số lượng tham số lớn, nâng cao trí thông minh trong đối thoại."
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 cung cấp giải pháp đối thoại thông minh cho nhiều tình huống."
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Mô hình Llama 3.1 70B Instruct, có 70B tham số, có thể cung cấp hiệu suất xuất sắc trong các nhiệm vụ sinh văn bản và chỉ dẫn lớn."
+ "internlm2-pro-chat": {
+ "description": "Mô hình phiên bản cũ mà chúng tôi vẫn đang duy trì, có sẵn với nhiều tùy chọn tham số 7B và 20B."
+ },
+ "internlm2.5-latest": {
+ "description": "Dòng mô hình mới nhất của chúng tôi, có hiệu suất suy luận xuất sắc, hỗ trợ độ dài ngữ cảnh 1M và khả năng theo dõi chỉ dẫn và gọi công cụ mạnh mẽ hơn."
+ },
+ "internlm3-latest": {
+ "description": "Dòng mô hình mới nhất của chúng tôi, có hiệu suất suy luận xuất sắc, dẫn đầu trong số các mô hình mã nguồn mở cùng cấp. Mặc định chỉ đến mô hình InternLM3 mới nhất mà chúng tôi đã phát hành."
+ },
+ "jina-deepsearch-v1": {
+ "description": "Tìm kiếm sâu kết hợp tìm kiếm trên mạng, đọc và suy luận, có thể thực hiện điều tra toàn diện. Bạn có thể coi nó như một đại lý, nhận nhiệm vụ nghiên cứu của bạn - nó sẽ thực hiện tìm kiếm rộng rãi và qua nhiều lần lặp lại trước khi đưa ra câu trả lời. Quá trình này liên quan đến nghiên cứu liên tục, suy luận và giải quyết vấn đề từ nhiều góc độ. Điều này khác biệt hoàn toàn với việc tạo ra câu trả lời trực tiếp từ dữ liệu đã được huấn luyện trước của các mô hình lớn tiêu chuẩn và các hệ thống RAG truyền thống dựa vào tìm kiếm bề mặt một lần."
+ },
+ "kimi-latest": {
+ "description": "Sản phẩm trợ lý thông minh Kimi sử dụng mô hình lớn Kimi mới nhất, có thể chứa các tính năng chưa ổn định. Hỗ trợ hiểu hình ảnh, đồng thời tự động chọn mô hình 8k/32k/128k làm mô hình tính phí dựa trên độ dài ngữ cảnh yêu cầu."
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM là một mô hình ngôn ngữ thử nghiệm, chuyên biệt cho các nhiệm vụ, được đào tạo để tuân theo các nguyên tắc khoa học học tập, có thể tuân theo các chỉ dẫn hệ thống trong các tình huống giảng dạy và học tập, đóng vai trò như một người hướng dẫn chuyên gia."
+ },
+ "lite": {
+ "description": "Spark Lite là một mô hình ngôn ngữ lớn nhẹ, có độ trễ cực thấp và khả năng xử lý hiệu quả, hoàn toàn miễn phí và mở, hỗ trợ chức năng tìm kiếm trực tuyến theo thời gian thực. Đặc điểm phản hồi nhanh của nó giúp nó nổi bật trong các ứng dụng suy diễn trên thiết bị có công suất thấp và tinh chỉnh mô hình, mang lại hiệu quả chi phí và trải nghiệm thông minh xuất sắc cho người dùng, đặc biệt trong các tình huống hỏi đáp kiến thức, tạo nội dung và tìm kiếm."
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B cung cấp khả năng suy luận AI mạnh mẽ hơn, phù hợp cho các ứng dụng phức tạp, hỗ trợ xử lý tính toán cực lớn và đảm bảo hiệu quả và độ chính xác cao."
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B là một mô hình hiệu suất cao, cung cấp khả năng sinh văn bản nhanh chóng, rất phù hợp cho các tình huống ứng dụng cần hiệu quả quy mô lớn và tiết kiệm chi phí."
},
- "llama-3.1-8b-instruct": {
- "description": "Mô hình Llama 3.1 8B Instruct, có 8B tham số, hỗ trợ thực hiện nhiệm vụ chỉ dẫn hình ảnh hiệu quả, cung cấp khả năng sinh văn bản chất lượng."
+ "llama-3.2-11b-vision-instruct": {
+ "description": "Khả năng suy luận hình ảnh xuất sắc trên hình ảnh độ phân giải cao, phù hợp cho các ứng dụng hiểu biết hình ảnh."
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Mô hình Llama 3.1 Sonar Huge Online, có 405B tham số, hỗ trợ độ dài ngữ cảnh khoảng 127,000 mã, được thiết kế cho các ứng dụng trò chuyện trực tuyến phức tạp."
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 được thiết kế để xử lý các nhiệm vụ kết hợp dữ liệu hình ảnh và văn bản. Nó thể hiện xuất sắc trong các nhiệm vụ mô tả hình ảnh và hỏi đáp hình ảnh, vượt qua rào cản giữa tạo ngôn ngữ và suy luận hình ảnh."
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Mô hình Llama 3.1 Sonar Large Chat, có 70B tham số, hỗ trợ độ dài ngữ cảnh khoảng 127,000 mã, phù hợp cho các nhiệm vụ trò chuyện ngoại tuyến phức tạp."
+ "llama-3.2-90b-vision-instruct": {
+ "description": "Khả năng suy luận hình ảnh tiên tiến dành cho các ứng dụng đại lý hiểu biết hình ảnh."
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Mô hình Llama 3.1 Sonar Large Online, có 70B tham số, hỗ trợ độ dài ngữ cảnh khoảng 127,000 mã, phù hợp cho các nhiệm vụ trò chuyện có dung lượng lớn và đa dạng."
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 được thiết kế để xử lý các nhiệm vụ kết hợp dữ liệu hình ảnh và văn bản. Nó thể hiện xuất sắc trong các nhiệm vụ mô tả hình ảnh và hỏi đáp hình ảnh, vượt qua rào cản giữa tạo ngôn ngữ và suy luận hình ảnh."
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Mô hình Llama 3.1 Sonar Small Chat, có 8B tham số, được thiết kế cho trò chuyện ngoại tuyến, hỗ trợ độ dài ngữ cảnh khoảng 127,000 mã."
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 là mô hình ngôn ngữ lớn mã nguồn mở đa ngôn ngữ tiên tiến nhất trong dòng Llama, mang đến trải nghiệm hiệu suất tương đương với mô hình 405B với chi phí cực thấp. Dựa trên cấu trúc Transformer, và được cải thiện tính hữu ích và an toàn thông qua tinh chỉnh giám sát (SFT) và học tăng cường từ phản hồi của con người (RLHF). Phiên bản tinh chỉnh theo chỉ dẫn của nó được tối ưu hóa cho đối thoại đa ngôn ngữ, thể hiện tốt hơn nhiều mô hình trò chuyện mã nguồn mở và đóng kín trong nhiều tiêu chuẩn ngành. Ngày cắt đứt kiến thức là tháng 12 năm 2023."
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Mô hình Llama 3.1 Sonar Small Online, có 8B tham số, hỗ trợ độ dài ngữ cảnh khoảng 127,000 mã, được thiết kế cho trò chuyện trực tuyến, có khả năng xử lý hiệu quả các tương tác văn bản khác nhau."
+ "llama-3.3-70b-versatile": {
+ "description": "Mô hình ngôn ngữ lớn Meta Llama 3.3 (LLM) đa ngôn ngữ là mô hình tạo ra dựa trên 70B (đầu vào/đầu ra văn bản) đã được huấn luyện và điều chỉnh theo chỉ dẫn. Mô hình thuần văn bản Llama 3.3 được tối ưu hóa cho các trường hợp hội thoại đa ngôn ngữ và vượt trội hơn nhiều mô hình trò chuyện mã nguồn mở và đóng khác trên các tiêu chuẩn ngành thông thường."
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B cung cấp khả năng xử lý phức tạp vô song, được thiết kế riêng cho các dự án yêu cầu cao."
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral được thiết kế cho nghiên cứu khoa học và suy luận toán học, cung cấp khả năng tính toán hiệu quả và giải thích kết quả."
},
+ "max-32k": {
+ "description": "Spark Max 32K được cấu hình với khả năng xử lý ngữ cảnh lớn, có khả năng hiểu ngữ cảnh và suy luận logic mạnh mẽ hơn, hỗ trợ đầu vào văn bản 32K tokens, phù hợp cho việc đọc tài liệu dài, hỏi đáp kiến thức riêng tư và các tình huống khác."
+ },
"meta-llama-3-70b-instruct": {
"description": "Mô hình 70 tỷ tham số mạnh mẽ, xuất sắc trong lý luận, lập trình và các ứng dụng ngôn ngữ rộng lớn."
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) cung cấp khả năng xử lý ngôn ngữ xuất sắc và trải nghiệm tương tác tuyệt vời."
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 cung cấp khả năng xử lý ngôn ngữ tuyệt vời và trải nghiệm tương tác xuất sắc."
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) là mô hình trò chuyện mạnh mẽ, hỗ trợ các nhu cầu đối thoại phức tạp."
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) cung cấp hỗ trợ đa ngôn ngữ, bao gồm nhiều lĩnh vực kiến thức phong phú."
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 được thiết kế để xử lý các tác vụ kết hợp dữ liệu hình ảnh và văn bản. Nó có khả năng xuất sắc trong các tác vụ mô tả hình ảnh và trả lời câu hỏi hình ảnh, vượt qua khoảng cách giữa tạo ngôn ngữ và suy luận hình ảnh."
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 được thiết kế để xử lý các tác vụ kết hợp dữ liệu hình ảnh và văn bản. Nó có khả năng xuất sắc trong các tác vụ mô tả hình ảnh và trả lời câu hỏi hình ảnh, vượt qua khoảng cách giữa tạo ngôn ngữ và suy luận hình ảnh."
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 được thiết kế để xử lý các tác vụ kết hợp dữ liệu hình ảnh và văn bản. Nó có khả năng xuất sắc trong các tác vụ mô tả hình ảnh và trả lời câu hỏi hình ảnh, vượt qua khoảng cách giữa tạo ngôn ngữ và suy luận hình ảnh."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 là mô hình ngôn ngữ lớn mã nguồn mở đa ngôn ngữ tiên tiến nhất trong dòng Llama, mang đến trải nghiệm hiệu suất tương đương mô hình 405B với chi phí cực thấp. Dựa trên cấu trúc Transformer, và được cải thiện tính hữu ích và an toàn thông qua tinh chỉnh giám sát (SFT) và học tăng cường phản hồi từ con người (RLHF). Phiên bản tinh chỉnh theo chỉ dẫn được tối ưu hóa cho đối thoại đa ngôn ngữ, thể hiện tốt hơn nhiều mô hình trò chuyện mã nguồn mở và đóng trong nhiều tiêu chuẩn ngành. Ngày cắt kiến thức là tháng 12 năm 2023."
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Mô hình ngôn ngữ lớn đa ngôn ngữ Meta Llama 3.3 (LLM) là mô hình sinh ra từ 70B (đầu vào văn bản/đầu ra văn bản) với việc điều chỉnh trước và điều chỉnh theo lệnh. Mô hình điều chỉnh theo lệnh Llama 3.3 được tối ưu hóa cho các trường hợp sử dụng đối thoại đa ngôn ngữ và vượt trội hơn nhiều mô hình trò chuyện mã nguồn mở và đóng khác trên các bài kiểm tra chuẩn ngành phổ biến."
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 được thiết kế để xử lý các tác vụ kết hợp dữ liệu hình ảnh và văn bản. Nó có khả năng xuất sắc trong các tác vụ mô tả hình ảnh và trả lời câu hỏi hình ảnh, vượt qua khoảng cách giữa tạo ngôn ngữ và suy luận hình ảnh."
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite phù hợp cho các môi trường cần hiệu suất cao và độ trễ thấp."
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "Mô hình Llama 3.1 Turbo 405B cung cấp hỗ trợ ngữ cảnh dung lượng lớn cho xử lý dữ liệu lớn, thể hiện xuất sắc trong các ứng dụng trí tuệ nhân tạo quy mô lớn."
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 là mô hình hàng đầu do Meta phát hành, hỗ trợ lên đến 405B tham số, có thể áp dụng cho cuộc đối thoại phức tạp, dịch đa ngôn ngữ và phân tích dữ liệu."
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B cung cấp hỗ trợ đối thoại hiệu quả đa ngôn ngữ."
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct tối ưu hóa cho các tình huống đối thoại chất lượng cao, hiệu suất vượt trội hơn nhiều mô hình đóng nguồn."
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct là phiên bản mới nhất do Meta phát hành, tối ưu hóa cho việc tạo ra các cuộc đối thoại chất lượng cao, vượt qua nhiều mô hình đóng nguồn hàng đầu."
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct được thiết kế đặc biệt cho các cuộc đối thoại chất lượng cao, thể hiện xuất sắc trong các đánh giá của con người, đặc biệt phù hợp cho các tình huống tương tác cao."
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 cung cấp hỗ trợ đa ngôn ngữ, là một trong những mô hình sinh hàng đầu trong ngành."
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 được thiết kế để xử lý các nhiệm vụ kết hợp dữ liệu hình ảnh và văn bản. Nó thể hiện xuất sắc trong các nhiệm vụ mô tả hình ảnh và hỏi đáp hình ảnh, vượt qua ranh giới giữa sinh ngôn ngữ và suy diễn hình ảnh."
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 được thiết kế để xử lý các nhiệm vụ kết hợp dữ liệu hình ảnh và văn bản. Nó thể hiện xuất sắc trong các nhiệm vụ mô tả hình ảnh và hỏi đáp hình ảnh, vượt qua ranh giới giữa sinh ngôn ngữ và suy diễn hình ảnh."
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 là mô hình ngôn ngữ lớn mã nguồn mở đa ngôn ngữ tiên tiến nhất trong dòng Llama, mang đến trải nghiệm hiệu suất tương đương với mô hình 405B với chi phí cực thấp. Dựa trên cấu trúc Transformer, và được cải thiện tính hữu ích và an toàn thông qua tinh chỉnh giám sát (SFT) và học tăng cường từ phản hồi của con người (RLHF). Phiên bản tinh chỉnh theo chỉ dẫn của nó được tối ưu hóa cho đối thoại đa ngôn ngữ, thể hiện tốt hơn nhiều mô hình trò chuyện mã nguồn mở và đóng kín trong nhiều tiêu chuẩn ngành. Ngày cắt đứt kiến thức là tháng 12 năm 2023."
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 là mô hình ngôn ngữ lớn mã nguồn mở đa ngôn ngữ tiên tiến nhất trong dòng Llama, mang đến trải nghiệm hiệu suất tương đương với mô hình 405B với chi phí cực thấp. Dựa trên cấu trúc Transformer, và được cải thiện tính hữu ích và an toàn thông qua tinh chỉnh giám sát (SFT) và học tăng cường từ phản hồi của con người (RLHF). Phiên bản tinh chỉnh theo chỉ dẫn của nó được tối ưu hóa cho đối thoại đa ngôn ngữ, thể hiện tốt hơn nhiều mô hình trò chuyện mã nguồn mở và đóng kín trong nhiều tiêu chuẩn ngành. Ngày cắt đứt kiến thức là tháng 12 năm 2023."
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct là mô hình lớn nhất và mạnh mẽ nhất trong mô hình Llama 3.1 Instruct, là một mô hình sinh dữ liệu và suy luận đối thoại tiên tiến, cũng có thể được sử dụng làm nền tảng cho việc tiền huấn luyện hoặc tinh chỉnh chuyên sâu trong các lĩnh vực cụ thể. Các mô hình ngôn ngữ lớn đa ngôn ngữ (LLMs) mà Llama 3.1 cung cấp là một tập hợp các mô hình sinh đã được tiền huấn luyện và điều chỉnh theo chỉ dẫn, bao gồm kích thước 8B, 70B và 405B (đầu vào/đầu ra văn bản). Các mô hình văn bản điều chỉnh theo chỉ dẫn của Llama 3.1 (8B, 70B, 405B) được tối ưu hóa cho các trường hợp đối thoại đa ngôn ngữ và đã vượt qua nhiều mô hình trò chuyện mã nguồn mở có sẵn trong các bài kiểm tra chuẩn ngành phổ biến. Llama 3.1 được thiết kế để sử dụng cho nhiều mục đích thương mại và nghiên cứu bằng nhiều ngôn ngữ. Các mô hình văn bản điều chỉnh theo chỉ dẫn phù hợp cho các cuộc trò chuyện giống như trợ lý, trong khi các mô hình đã được tiền huấn luyện có thể thích ứng với nhiều nhiệm vụ sinh ngôn ngữ tự nhiên khác nhau. Mô hình Llama 3.1 cũng hỗ trợ việc cải thiện các mô hình khác bằng cách sử dụng đầu ra của nó, bao gồm sinh dữ liệu tổng hợp và tinh chỉnh. Llama 3.1 là một mô hình ngôn ngữ tự hồi quy sử dụng kiến trúc biến áp tối ưu. Phiên bản điều chỉnh sử dụng tinh chỉnh có giám sát (SFT) và học tăng cường có phản hồi từ con người (RLHF) để phù hợp với sở thích của con người về tính hữu ích và an toàn."
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 là một mô hình ngôn ngữ lớn (LLM) mở dành cho các nhà phát triển, nhà nghiên cứu và doanh nghiệp, nhằm giúp họ xây dựng, thử nghiệm và mở rộng ý tưởng AI sinh một cách có trách nhiệm. Là một phần của hệ thống cơ sở hạ tầng đổi mới toàn cầu, nó rất phù hợp cho các thiết bị biên và thời gian huấn luyện nhanh hơn với khả năng tính toán và tài nguyên hạn chế."
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B là mô hình nhẹ và nhanh mới nhất của Microsoft AI, hiệu suất gần gấp 10 lần so với các mô hình mở nguồn hiện có."
+ "meta/llama-3.1-405b-instruct": {
+ "description": "LLM cao cấp, hỗ trợ tạo dữ liệu tổng hợp, chưng cất kiến thức và suy luận, phù hợp cho chatbot, lập trình và các nhiệm vụ chuyên biệt."
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "Tăng cường cuộc đối thoại phức tạp, có khả năng hiểu ngữ cảnh xuất sắc, suy luận và sinh văn bản."
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "Mô hình tiên tiến hàng đầu, có khả năng hiểu ngôn ngữ, suy luận xuất sắc và khả năng sinh văn bản."
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "Mô hình thị giác-ngôn ngữ tiên tiến, xuất sắc trong việc suy luận chất lượng cao từ hình ảnh."
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "Mô hình ngôn ngữ nhỏ tiên tiến hàng đầu, có khả năng hiểu ngôn ngữ, suy luận xuất sắc và khả năng sinh văn bản."
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "Mô hình ngôn ngữ nhỏ tiên tiến hàng đầu, có khả năng hiểu ngôn ngữ, suy luận xuất sắc và khả năng sinh văn bản."
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "Mô hình thị giác-ngôn ngữ tiên tiến, xuất sắc trong việc suy luận chất lượng cao từ hình ảnh."
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "Mô hình LLM tiên tiến, xuất sắc trong suy luận, toán học, kiến thức chung và gọi hàm."
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 là mô hình ngôn ngữ do AI của Microsoft cung cấp, thể hiện xuất sắc trong các lĩnh vực đối thoại phức tạp, đa ngôn ngữ, suy luận và trợ lý thông minh."
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B là mô hình Wizard tiên tiến nhất của Microsoft AI, thể hiện hiệu suất cực kỳ cạnh tranh."
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V là mô hình đa phương thức thế hệ mới do OpenBMB phát triển, có khả năng nhận diện OCR xuất sắc và hiểu biết đa phương thức, hỗ trợ nhiều ứng dụng khác nhau."
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B là mô hình hàng đầu thế giới của Mistral về hiệu suất cạnh biên."
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B là mô hình cạnh biên cực kỳ tiết kiệm chi phí của Mistral."
+ },
"mistral": {
"description": "Mistral là mô hình 7B do Mistral AI phát hành, phù hợp cho các nhu cầu xử lý ngôn ngữ đa dạng."
},
"mistral-large": {
"description": "Mixtral Large là mô hình hàng đầu của Mistral, kết hợp khả năng sinh mã, toán học và suy luận, hỗ trợ cửa sổ ngữ cảnh 128k."
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) là một Mô hình Ngôn ngữ Lớn (LLM) tiên tiến với khả năng lý luận, kiến thức và lập trình hiện đại."
- },
"mistral-large-latest": {
"description": "Mistral Large là mô hình lớn hàng đầu, chuyên về các nhiệm vụ đa ngôn ngữ, suy luận phức tạp và sinh mã, là lựa chọn lý tưởng cho các ứng dụng cao cấp."
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 cung cấp khả năng tính toán hiệu quả và hiểu ngôn ngữ tự nhiên, phù hợp cho nhiều ứng dụng."
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B là một mô hình nhỏ gọn nhưng hiệu suất cao, chuyên về xử lý hàng loạt và các tác vụ đơn giản như phân loại và sinh văn bản, với khả năng suy luận tốt."
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) là một mô hình ngôn ngữ lớn siêu cấp, hỗ trợ nhu cầu xử lý cực cao."
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B là mô hình chuyên gia hỗn hợp thưa được tiền huấn luyện, dùng cho các nhiệm vụ văn bản tổng quát."
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B là một mô hình chuyên gia thưa thớt, tận dụng nhiều tham số để tăng tốc độ suy luận, phù hợp để xử lý đa ngôn ngữ và tạo mã."
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct là mô hình tiêu chuẩn ngành với tốc độ tối ưu hóa và hỗ trợ ngữ cảnh dài."
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K là một mô hình có khả năng xử lý ngữ cảnh siêu dài, phù hợp cho việc sinh văn bản siêu dài, đáp ứng nhu cầu nhiệm vụ sinh phức tạp, có thể xử lý nội dung lên đến 128.000 tokens, rất phù hợp cho nghiên cứu, học thuật và sinh tài liệu lớn."
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Mô hình hình ảnh Kimi (bao gồm moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, v.v.) có khả năng hiểu nội dung hình ảnh, bao gồm văn bản hình ảnh, màu sắc hình ảnh và hình dạng vật thể."
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K cung cấp khả năng xử lý ngữ cảnh độ dài trung bình, có thể xử lý 32.768 tokens, đặc biệt phù hợp cho việc sinh các tài liệu dài và đối thoại phức tạp, ứng dụng trong sáng tạo nội dung, sinh báo cáo và hệ thống đối thoại."
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Mô hình hình ảnh Kimi (bao gồm moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, v.v.) có khả năng hiểu nội dung hình ảnh, bao gồm văn bản hình ảnh, màu sắc hình ảnh và hình dạng vật thể."
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K được thiết kế đặc biệt cho các nhiệm vụ sinh văn bản ngắn, có hiệu suất xử lý cao, có thể xử lý 8.192 tokens, rất phù hợp cho các cuộc đối thoại ngắn, ghi chú nhanh và sinh nội dung nhanh chóng."
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Mô hình hình ảnh Kimi (bao gồm moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview, v.v.) có khả năng hiểu nội dung hình ảnh, bao gồm văn bản hình ảnh, màu sắc hình ảnh và hình dạng vật thể."
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto có thể chọn mô hình phù hợp dựa trên số lượng Tokens hiện tại đang chiếm dụng trong ngữ cảnh."
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B là phiên bản nâng cấp của Nous Hermes 2, bao gồm bộ dữ liệu phát triển nội bộ mới nhất."
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B là một mô hình ngôn ngữ quy mô lớn tùy chỉnh bởi NVIDIA, nhằm nâng cao mức độ hỗ trợ của phản hồi do LLM tạo ra đối với các truy vấn của người dùng. Mô hình này đã thể hiện xuất sắc trong các bài kiểm tra chuẩn như Arena Hard, AlpacaEval 2 LC và GPT-4-Turbo MT-Bench, đứng đầu trong cả ba bài kiểm tra tự động cho đến ngày 1 tháng 10 năm 2024. Mô hình sử dụng RLHF (đặc biệt là REINFORCE), Llama-3.1-Nemotron-70B-Reward và HelpSteer2-Preference để đào tạo trên cơ sở mô hình Llama-3.1-70B-Instruct."
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "Mô hình ngôn ngữ độc đáo, cung cấp độ chính xác và hiệu suất không thể sánh kịp."
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B là mô hình ngôn ngữ lớn tùy chỉnh của NVIDIA, nhằm nâng cao tính hữu ích của các phản hồi do LLM tạo ra."
+ },
+ "o1": {
+ "description": "Tập trung vào suy diễn nâng cao và giải quyết các vấn đề phức tạp, bao gồm các nhiệm vụ toán học và khoa học. Rất phù hợp cho các ứng dụng cần hiểu biết sâu sắc về ngữ cảnh và quy trình làm việc đại diện."
+ },
"o1-mini": {
"description": "o1-mini là một mô hình suy diễn nhanh chóng và tiết kiệm chi phí, được thiết kế cho các ứng dụng lập trình, toán học và khoa học. Mô hình này có ngữ cảnh 128K và thời điểm cắt kiến thức vào tháng 10 năm 2023."
},
"o1-preview": {
"description": "o1 là mô hình suy diễn mới của OpenAI, phù hợp cho các nhiệm vụ phức tạp cần kiến thức tổng quát rộng rãi. Mô hình này có ngữ cảnh 128K và thời điểm cắt kiến thức vào tháng 10 năm 2023."
},
+ "o3-mini": {
+ "description": "o3-mini là mô hình suy diễn nhỏ gọn mới nhất của chúng tôi, cung cấp trí thông minh cao với chi phí và độ trễ tương tự như o1-mini."
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba là mô hình ngôn ngữ Mamba 2 tập trung vào sinh mã, cung cấp hỗ trợ mạnh mẽ cho các nhiệm vụ mã và suy luận tiên tiến."
},
@@ -745,8 +1466,8 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B là một mô hình chuyên gia thưa thớt, sử dụng nhiều tham số để tăng tốc độ suy luận, phù hợp cho việc xử lý đa ngôn ngữ và sinh mã."
},
- "openai/gpt-4o-2024-08-06": {
- "description": "ChatGPT-4o là một mô hình động, được cập nhật theo thời gian để giữ phiên bản mới nhất. Nó kết hợp khả năng hiểu và sinh ngôn ngữ mạnh mẽ, phù hợp cho các ứng dụng quy mô lớn, bao gồm dịch vụ khách hàng, giáo dục và hỗ trợ kỹ thuật."
+ "openai/gpt-4o": {
+ "description": "ChatGPT-4o là một mô hình động, cập nhật theo thời gian để giữ phiên bản mới nhất. Nó kết hợp khả năng hiểu và tạo ngôn ngữ mạnh mẽ, phù hợp với các tình huống ứng dụng quy mô lớn, bao gồm dịch vụ khách hàng, giáo dục và hỗ trợ kỹ thuật."
},
"openai/gpt-4o-mini": {
"description": "GPT-4o mini là mô hình mới nhất của OpenAI, được phát hành sau GPT-4 Omni, hỗ trợ đầu vào hình ảnh và văn bản, và đầu ra văn bản. Là mô hình nhỏ tiên tiến nhất của họ, nó rẻ hơn nhiều so với các mô hình tiên tiến gần đây khác và rẻ hơn hơn 60% so với GPT-3.5 Turbo. Nó giữ lại trí thông minh tiên tiến nhất trong khi có giá trị sử dụng đáng kể. GPT-4o mini đạt 82% điểm trong bài kiểm tra MMLU và hiện đứng đầu về sở thích trò chuyện so với GPT-4."
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Mô hình Pixtral thể hiện khả năng mạnh mẽ trong các nhiệm vụ như hiểu biểu đồ và hình ảnh, hỏi đáp tài liệu, suy luận đa phương tiện và tuân thủ hướng dẫn, có khả năng tiếp nhận hình ảnh với độ phân giải và tỷ lệ khung hình tự nhiên, cũng như xử lý bất kỳ số lượng hình ảnh nào trong cửa sổ ngữ cảnh dài lên đến 128K token."
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large là một mô hình đa phương thức mã nguồn mở với 1240 tỷ tham số, được xây dựng dựa trên Mistral Large 2. Đây là mô hình thứ hai trong gia đình đa phương thức của chúng tôi, thể hiện khả năng hiểu hình ảnh ở mức tiên tiến."
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K được cấu hình với khả năng xử lý ngữ cảnh cực lớn, có thể xử lý tới 128K thông tin ngữ cảnh, đặc biệt phù hợp cho việc phân tích toàn bộ và xử lý mối liên hệ logic lâu dài trong nội dung văn bản dài, có thể cung cấp logic mạch lạc và hỗ trợ trích dẫn đa dạng trong giao tiếp văn bản phức tạp."
+ },
+ "qvq-72b-preview": {
+ "description": "Mô hình QVQ là mô hình nghiên cứu thử nghiệm do đội ngũ Qwen phát triển, tập trung vào việc nâng cao khả năng suy luận hình ảnh, đặc biệt trong lĩnh vực suy luận toán học."
+ },
+ "qwen-coder-plus-latest": {
+ "description": "Mô hình mã Qwen."
+ },
"qwen-coder-turbo-latest": {
"description": "Mô hình mã Qwen."
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "Mô hình toán học Qwen được thiết kế đặc biệt để giải quyết các bài toán toán học."
},
+ "qwen-max": {
+ "description": "Mô hình ngôn ngữ quy mô lớn Qwen cấp tỷ, hỗ trợ đầu vào bằng tiếng Trung, tiếng Anh và nhiều ngôn ngữ khác, là mô hình API đằng sau phiên bản sản phẩm Qwen 2.5 hiện tại."
+ },
"qwen-max-latest": {
"description": "Mô hình ngôn ngữ quy mô lớn Qwen với hàng trăm tỷ tham số, hỗ trợ đầu vào bằng tiếng Trung, tiếng Anh và nhiều ngôn ngữ khác, là mô hình API đứng sau phiên bản sản phẩm Qwen 2.5 hiện tại."
},
+ "qwen-omni-turbo-latest": {
+ "description": "Mô hình Qwen-Omni hỗ trợ đầu vào từ nhiều loại dữ liệu khác nhau, bao gồm video, âm thanh, hình ảnh, văn bản, và xuất ra âm thanh và văn bản."
+ },
+ "qwen-plus": {
+ "description": "Mô hình ngôn ngữ quy mô lớn Qwen phiên bản nâng cao, hỗ trợ đầu vào bằng tiếng Trung, tiếng Anh và nhiều ngôn ngữ khác."
+ },
"qwen-plus-latest": {
"description": "Phiên bản nâng cao của mô hình ngôn ngữ quy mô lớn Qwen, hỗ trợ đầu vào bằng tiếng Trung, tiếng Anh và nhiều ngôn ngữ khác."
},
+ "qwen-turbo": {
+ "description": "Mô hình ngôn ngữ quy mô lớn Qwen hỗ trợ đầu vào bằng tiếng Trung, tiếng Anh và nhiều ngôn ngữ khác."
+ },
"qwen-turbo-latest": {
"description": "Mô hình ngôn ngữ quy mô lớn Qwen, hỗ trợ đầu vào bằng tiếng Trung, tiếng Anh và nhiều ngôn ngữ khác."
},
"qwen-vl-chat-v1": {
"description": "Mô hình Qwen VL hỗ trợ các phương thức tương tác linh hoạt, bao gồm nhiều hình ảnh, nhiều vòng hỏi đáp, sáng tạo, v.v."
},
- "qwen-vl-max": {
- "description": "Mô hình ngôn ngữ hình ảnh quy mô lớn Qwen. So với phiên bản nâng cao, nâng cao khả năng suy luận hình ảnh và tuân thủ chỉ dẫn, cung cấp mức độ nhận thức và nhận thức hình ảnh cao hơn."
+ "qwen-vl-max-latest": {
+ "description": "Mô hình ngôn ngữ hình ảnh quy mô siêu lớn của Tongyi Qianwen. So với phiên bản nâng cao, nó lại nâng cao khả năng suy luận hình ảnh và khả năng tuân thủ chỉ dẫn, cung cấp mức độ nhận thức và cảm nhận hình ảnh cao hơn."
+ },
+ "qwen-vl-ocr-latest": {
+ "description": "Công Nghệ Qianwen OCR là mô hình chuyên dụng cho việc trích xuất văn bản, tập trung vào khả năng trích xuất văn bản từ các loại hình ảnh như tài liệu, bảng biểu, đề thi, chữ viết tay, v.v. Nó có thể nhận diện nhiều loại văn bản, hiện hỗ trợ các ngôn ngữ: tiếng Trung, tiếng Anh, tiếng Pháp, tiếng Nhật, tiếng Hàn, tiếng Đức, tiếng Nga, tiếng Ý, tiếng Việt, tiếng Ả Rập."
},
- "qwen-vl-plus": {
- "description": "Mô hình ngôn ngữ hình ảnh quy mô lớn Qwen phiên bản nâng cao. Nâng cao khả năng nhận diện chi tiết và nhận diện văn bản, hỗ trợ độ phân giải hình ảnh trên một triệu pixel và tỷ lệ khung hình tùy ý."
+ "qwen-vl-plus-latest": {
+ "description": "Mô hình ngôn ngữ hình ảnh quy mô lớn phiên bản nâng cao của Tongyi Qianwen. Nâng cao khả năng nhận diện chi tiết và nhận diện văn bản, hỗ trợ độ phân giải trên một triệu pixel và các tỷ lệ chiều dài và chiều rộng tùy ý."
},
"qwen-vl-v1": {
"description": "Mô hình được khởi tạo bằng mô hình ngôn ngữ Qwen-7B, thêm mô hình hình ảnh, mô hình được huấn luyện trước với độ phân giải đầu vào hình ảnh là 448."
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2 là dòng mô hình ngôn ngữ lớn hoàn toàn mới. Qwen2 7B là một mô hình dựa trên transformer, thể hiện xuất sắc trong việc hiểu ngôn ngữ, khả năng đa ngôn ngữ, lập trình, toán học và suy luận."
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 là một loạt mô hình ngôn ngữ lớn hoàn toàn mới, có khả năng hiểu và sinh mạnh mẽ hơn."
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL là phiên bản cải tiến mới nhất của mô hình Qwen-VL, đã đạt được hiệu suất tiên tiến trong các bài kiểm tra hiểu biết thị giác, bao gồm MathVista, DocVQA, RealWorldQA và MTVQA. Qwen2-VL có khả năng hiểu video dài hơn 20 phút, phục vụ cho các câu hỏi, đối thoại và sáng tạo nội dung dựa trên video chất lượng cao. Nó cũng có khả năng suy luận và ra quyết định phức tạp, có thể tích hợp với các thiết bị di động, robot, v.v., để thực hiện các thao tác tự động dựa trên môi trường thị giác và hướng dẫn văn bản. Ngoài tiếng Anh và tiếng Trung, Qwen2-VL hiện cũng hỗ trợ hiểu văn bản trong hình ảnh bằng nhiều ngôn ngữ khác nhau, bao gồm hầu hết các ngôn ngữ châu Âu, tiếng Nhật, tiếng Hàn, tiếng Ả Rập và tiếng Việt."
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct là một trong những mô hình ngôn ngữ lớn mới nhất được phát hành bởi Alibaba Cloud. Mô hình 72B này có khả năng cải thiện đáng kể trong các lĩnh vực như mã hóa và toán học. Mô hình cũng cung cấp hỗ trợ đa ngôn ngữ, bao gồm hơn 29 ngôn ngữ, bao gồm tiếng Trung, tiếng Anh, v.v. Mô hình đã có sự cải thiện đáng kể trong việc theo dõi hướng dẫn, hiểu dữ liệu có cấu trúc và tạo ra đầu ra có cấu trúc (đặc biệt là JSON)."
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct là một trong những mô hình ngôn ngữ lớn mới nhất được phát hành bởi Alibaba Cloud. Mô hình 32B này có khả năng cải thiện đáng kể trong các lĩnh vực như mã hóa và toán học. Mô hình cung cấp hỗ trợ đa ngôn ngữ, bao gồm hơn 29 ngôn ngữ, bao gồm tiếng Trung, tiếng Anh, v.v. Mô hình đã có sự cải thiện đáng kể trong việc theo dõi hướng dẫn, hiểu dữ liệu có cấu trúc và tạo ra đầu ra có cấu trúc (đặc biệt là JSON)."
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "LLM hướng đến tiếng Trung và tiếng Anh, tập trung vào ngôn ngữ, lập trình, toán học, suy luận và các lĩnh vực khác."
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "LLM cao cấp, hỗ trợ tạo mã, suy luận và sửa chữa, bao gồm các ngôn ngữ lập trình phổ biến."
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "Mô hình mã mạnh mẽ cỡ trung, hỗ trợ độ dài ngữ cảnh 32K, xuất sắc trong lập trình đa ngôn ngữ."
+ },
"qwen2": {
"description": "Qwen2 là mô hình ngôn ngữ quy mô lớn thế hệ mới của Alibaba, hỗ trợ các nhu cầu ứng dụng đa dạng với hiệu suất xuất sắc."
},
+ "qwen2.5": {
+ "description": "Qwen2.5 là thế hệ mô hình ngôn ngữ quy mô lớn mới của Alibaba, hỗ trợ các nhu cầu ứng dụng đa dạng với hiệu suất xuất sắc."
+ },
"qwen2.5-14b-instruct": {
"description": "Mô hình 14B quy mô mở nguồn của Qwen 2.5."
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "Mô hình quy mô 72B được mở nguồn từ Qianwen 2.5."
+ },
"qwen2.5-32b-instruct": {
"description": "Mô hình 32B quy mô mở nguồn của Qwen 2.5."
},
@@ -826,11 +1601,14 @@
"qwen2.5-coder-1.5b-instruct": {
"description": "Phiên bản mã nguồn mở của mô hình mã Qwen."
},
+ "qwen2.5-coder-32b-instruct": {
+ "description": "Phiên bản mã nguồn mở của mô hình mã Qwen."
+ },
"qwen2.5-coder-7b-instruct": {
"description": "Phiên bản mã nguồn mở của mô hình mã Qwen."
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Mô hình Qwen-Math có khả năng giải quyết bài toán toán học mạnh mẽ."
+ "description": "Mô hình Qwen-Math có khả năng giải toán mạnh mẽ."
},
"qwen2.5-math-72b-instruct": {
"description": "Mô hình Qwen-Math có khả năng giải quyết bài toán toán học mạnh mẽ."
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Mô hình Qwen-Math có khả năng giải quyết bài toán toán học mạnh mẽ."
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "Nâng cao khả năng theo dõi lệnh, toán học, giải quyết vấn đề, mã hóa, nâng cao khả năng nhận diện mọi thứ, hỗ trợ định vị chính xác các yếu tố thị giác từ nhiều định dạng khác nhau, hỗ trợ hiểu và định vị thời gian sự kiện trong các tệp video dài (tối đa 10 phút), có khả năng hiểu thứ tự thời gian và tốc độ, hỗ trợ điều khiển Agent trên OS hoặc Mobile dựa trên khả năng phân tích và định vị, khả năng trích xuất thông tin quan trọng và xuất định dạng Json mạnh mẽ, phiên bản này là phiên bản 72B, phiên bản mạnh nhất trong dòng sản phẩm này."
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "Nâng cao khả năng theo dõi lệnh, toán học, giải quyết vấn đề, mã hóa, nâng cao khả năng nhận diện mọi thứ, hỗ trợ định vị chính xác các yếu tố thị giác từ nhiều định dạng khác nhau, hỗ trợ hiểu và định vị thời gian sự kiện trong các tệp video dài (tối đa 10 phút), có khả năng hiểu thứ tự thời gian và tốc độ, hỗ trợ điều khiển Agent trên OS hoặc Mobile dựa trên khả năng phân tích và định vị, khả năng trích xuất thông tin quan trọng và xuất định dạng Json mạnh mẽ, phiên bản này là phiên bản 72B, phiên bản mạnh nhất trong dòng sản phẩm này."
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 là thế hệ mô hình ngôn ngữ quy mô lớn mới của Alibaba, hỗ trợ các nhu cầu ứng dụng đa dạng với hiệu suất xuất sắc."
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 là thế hệ mô hình ngôn ngữ quy mô lớn mới của Alibaba, hỗ trợ các nhu cầu ứng dụng đa dạng với hiệu suất xuất sắc."
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 là thế hệ mô hình ngôn ngữ quy mô lớn mới của Alibaba, hỗ trợ các nhu cầu ứng dụng đa dạng với hiệu suất xuất sắc."
+ },
"qwen2:0.5b": {
"description": "Qwen2 là mô hình ngôn ngữ quy mô lớn thế hệ mới của Alibaba, hỗ trợ các nhu cầu ứng dụng đa dạng với hiệu suất xuất sắc."
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 là mô hình ngôn ngữ quy mô lớn thế hệ mới của Alibaba, hỗ trợ các nhu cầu ứng dụng đa dạng với hiệu suất xuất sắc."
},
- "solar-1-mini-chat": {
+ "qwq": {
+ "description": "QwQ là một mô hình nghiên cứu thử nghiệm, tập trung vào việc nâng cao khả năng suy luận của AI."
+ },
+ "qwq-32b": {
+ "description": "Mô hình suy diễn QwQ được đào tạo dựa trên mô hình Qwen2.5-32B, đã được cải thiện đáng kể khả năng suy diễn của mô hình thông qua học tăng cường. Các chỉ số cốt lõi của mô hình như mã toán (AIME 24/25, LiveCodeBench) và một số chỉ số chung (IFEval, LiveBench, v.v.) đạt đến mức độ của phiên bản đầy đủ DeepSeek-R1, tất cả các chỉ số đều vượt trội so với DeepSeek-R1-Distill-Qwen-32B cũng dựa trên Qwen2.5-32B."
+ },
+ "qwq-32b-preview": {
+ "description": "Mô hình QwQ là một mô hình nghiên cứu thử nghiệm được phát triển bởi đội ngũ Qwen, tập trung vào việc nâng cao khả năng suy luận của AI."
+ },
+ "qwq-plus-latest": {
+ "description": "Mô hình suy diễn QwQ được đào tạo dựa trên mô hình Qwen2.5, đã được cải thiện đáng kể khả năng suy diễn của mô hình thông qua học tăng cường. Các chỉ số cốt lõi của mô hình như mã toán (AIME 24/25, LiveCodeBench) và một số chỉ số chung (IFEval, LiveBench, v.v.) đạt đến mức độ của phiên bản đầy đủ DeepSeek-R1."
+ },
+ "r1-1776": {
+ "description": "R1-1776 là một phiên bản của mô hình DeepSeek R1, đã được huấn luyện lại, cung cấp thông tin sự thật chưa được kiểm duyệt và không thiên lệch."
+ },
+ "solar-mini": {
"description": "Solar Mini là một LLM dạng nhỏ gọn, hiệu suất vượt trội hơn GPT-3.5, có khả năng đa ngôn ngữ mạnh mẽ, hỗ trợ tiếng Anh và tiếng Hàn, cung cấp giải pháp hiệu quả và nhỏ gọn."
},
- "solar-1-mini-chat-ja": {
- "description": "Solar Mini (Ja) mở rộng khả năng của Solar Mini, tập trung vào tiếng Nhật, đồng thời duy trì hiệu suất cao và xuất sắc trong việc sử dụng tiếng Anh và tiếng Hàn."
+ "solar-mini-ja": {
+ "description": "Solar Mini (Ja) mở rộng khả năng của Solar Mini, tập trung vào tiếng Nhật, đồng thời duy trì hiệu quả và hiệu suất xuất sắc trong việc sử dụng tiếng Anh và tiếng Hàn."
},
"solar-pro": {
"description": "Solar Pro là một LLM thông minh cao do Upstage phát hành, tập trung vào khả năng tuân theo hướng dẫn trên một GPU, đạt điểm IFEval trên 80. Hiện tại hỗ trợ tiếng Anh, phiên bản chính thức dự kiến ra mắt vào tháng 11 năm 2024, sẽ mở rộng hỗ trợ ngôn ngữ và độ dài ngữ cảnh."
},
+ "sonar": {
+ "description": "Sản phẩm tìm kiếm nhẹ dựa trên ngữ cảnh tìm kiếm, nhanh hơn và rẻ hơn so với Sonar Pro."
+ },
+ "sonar-deep-research": {
+ "description": "Nghiên cứu sâu tiến hành nghiên cứu chuyên gia toàn diện và tổng hợp thành các báo cáo có thể truy cập và có thể hành động."
+ },
+ "sonar-pro": {
+ "description": "Sản phẩm tìm kiếm nâng cao hỗ trợ ngữ cảnh tìm kiếm, cho phép truy vấn và theo dõi nâng cao."
+ },
+ "sonar-reasoning": {
+ "description": "Sản phẩm API mới được hỗ trợ bởi mô hình suy luận của DeepSeek."
+ },
+ "sonar-reasoning-pro": {
+ "description": "Sản phẩm API mới được hỗ trợ bởi mô hình suy diễn DeepSeek."
+ },
"step-1-128k": {
"description": "Cân bằng hiệu suất và chi phí, phù hợp cho các tình huống chung."
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "Mô hình tốc độ cao, phù hợp cho đối thoại thời gian thực."
},
+ "step-1.5v-mini": {
+ "description": "Mô hình này có khả năng hiểu video mạnh mẽ."
+ },
+ "step-1o-turbo-vision": {
+ "description": "Mô hình này có khả năng hiểu hình ảnh mạnh mẽ, vượt trội hơn 1o trong lĩnh vực toán học và mã. Mô hình nhỏ hơn 1o và có tốc độ xuất ra nhanh hơn."
+ },
+ "step-1o-vision-32k": {
+ "description": "Mô hình này có khả năng hiểu hình ảnh mạnh mẽ. So với các mô hình trong series step-1v, nó có hiệu suất thị giác vượt trội hơn."
+ },
"step-1v-32k": {
"description": "Hỗ trợ đầu vào hình ảnh, tăng cường trải nghiệm tương tác đa mô hình."
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "Hỗ trợ tương tác ngữ cảnh quy mô lớn, phù hợp cho các tình huống đối thoại phức tạp."
},
+ "step-2-mini": {
+ "description": "Mô hình lớn siêu tốc dựa trên kiến trúc Attention tự nghiên cứu thế hệ mới MFA, đạt được hiệu quả tương tự như step1 với chi phí rất thấp, đồng thời duy trì thông lượng cao hơn và độ trễ phản hồi nhanh hơn. Có khả năng xử lý các nhiệm vụ chung, đặc biệt có năng lực trong lập trình."
+ },
"taichu_llm": {
"description": "Mô hình ngôn ngữ lớn Taichu có khả năng hiểu ngôn ngữ mạnh mẽ và các khả năng như sáng tạo văn bản, trả lời câu hỏi kiến thức, lập trình mã, tính toán toán học, suy luận logic, phân tích cảm xúc, tóm tắt văn bản. Đổi mới kết hợp giữa đào tạo trước với dữ liệu phong phú từ nhiều nguồn, thông qua việc liên tục cải tiến công nghệ thuật toán và hấp thụ kiến thức mới từ dữ liệu văn bản khổng lồ, giúp mô hình ngày càng hoàn thiện. Cung cấp thông tin và dịch vụ tiện lợi hơn cho người dùng cùng trải nghiệm thông minh hơn."
},
- "taichu_vqa": {
- "description": "Taichu 2.0V kết hợp khả năng hiểu hình ảnh, chuyển giao kiến thức, suy luận logic, v.v., thể hiện xuất sắc trong lĩnh vực hỏi đáp hình ảnh và văn bản."
+ "taichu_vl": {
+ "description": "Kết hợp khả năng hiểu hình ảnh, chuyển giao kiến thức, suy luận logic, thể hiện xuất sắc trong lĩnh vực hỏi đáp hình ảnh và văn bản."
+ },
+ "text-embedding-3-large": {
+ "description": "Mô hình vector hóa mạnh mẽ nhất, phù hợp cho các nhiệm vụ tiếng Anh và không phải tiếng Anh."
+ },
+ "text-embedding-3-small": {
+ "description": "Mô hình Embedding thế hệ mới hiệu quả và tiết kiệm, phù hợp cho tìm kiếm kiến thức, ứng dụng RAG và các tình huống khác."
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "Phiên bản mã nguồn mở của thế hệ mô hình tiền huấn luyện GLM-4 mới nhất được phát hành bởi Zhiyu AI."
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) cung cấp khả năng tính toán nâng cao thông qua chiến lược và kiến trúc mô hình hiệu quả."
},
+ "tts-1": {
+ "description": "Mô hình chuyển văn bản thành giọng nói mới nhất, tối ưu hóa tốc độ cho các tình huống thời gian thực."
+ },
+ "tts-1-hd": {
+ "description": "Mô hình chuyển văn bản thành giọng nói mới nhất, tối ưu hóa cho chất lượng."
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) phù hợp cho các nhiệm vụ chỉ dẫn tinh vi, cung cấp khả năng xử lý ngôn ngữ xuất sắc."
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet nâng cao tiêu chuẩn ngành, hiệu suất vượt trội so với các mô hình cạnh tranh và Claude 3 Opus, thể hiện xuất sắc trong nhiều đánh giá, đồng thời có tốc độ và chi phí tương đương với các mô hình tầm trung của chúng tôi."
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet là mô hình thế hệ tiếp theo nhanh nhất của Anthropic. So với Claude 3 Haiku, Claude 3.7 Sonnet đã cải thiện ở nhiều kỹ năng và vượt qua mô hình lớn nhất thế hệ trước là Claude 3 Opus trong nhiều bài kiểm tra trí tuệ."
+ },
+ "whisper-1": {
+ "description": "Mô hình nhận diện giọng nói đa năng, hỗ trợ nhận diện giọng nói đa ngôn ngữ, dịch giọng nói và nhận diện ngôn ngữ."
+ },
"wizardlm2": {
"description": "WizardLM 2 là mô hình ngôn ngữ do Microsoft AI cung cấp, đặc biệt xuất sắc trong các lĩnh vực đối thoại phức tạp, đa ngôn ngữ, suy luận và trợ lý thông minh."
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "Hiệu suất vượt trội với chi phí hợp lý. Tối ưu hóa độ chính xác cao dựa trên hiệu suất, tốc độ suy luận và chi phí."
},
+ "yi-lightning": {
+ "description": "Mô hình hiệu suất cao mới nhất, đảm bảo đầu ra chất lượng cao trong khi tốc độ suy luận được cải thiện đáng kể."
+ },
+ "yi-lightning-lite": {
+ "description": "Phiên bản nhẹ, được khuyến nghị sử dụng yi-lightning."
+ },
"yi-medium": {
"description": "Mô hình kích thước trung bình được nâng cấp và tinh chỉnh, khả năng cân bằng, chi phí hiệu quả cao. Tối ưu hóa sâu khả năng tuân theo chỉ dẫn."
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "Mô hình cho các nhiệm vụ hình ảnh phức tạp, cung cấp khả năng hiểu và phân tích hình ảnh hiệu suất cao."
+ },
+ "yi-vision-v2": {
+ "description": "Mô hình nhiệm vụ thị giác phức tạp, cung cấp khả năng hiểu và phân tích hiệu suất cao dựa trên nhiều hình ảnh."
}
}
diff --git a/DigitalHumanWeb/locales/vi-VN/plugin.json b/DigitalHumanWeb/locales/vi-VN/plugin.json
index b8631e0..18af552 100644
--- a/DigitalHumanWeb/locales/vi-VN/plugin.json
+++ b/DigitalHumanWeb/locales/vi-VN/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "Làm mới plugin {{name}} thất bại",
"urlError": "Liên kết này không trả về nội dung dạng JSON, vui lòng đảm bảo rằng đó là một liên kết hợp lệ"
},
+ "inspector": {
+ "args": "Xem danh sách tham số",
+ "pluginRender": "Xem giao diện plugin"
+ },
"list": {
"item": {
"deprecated.title": "Đã loại bỏ",
@@ -130,6 +134,34 @@
"plugin": "Plugin đang chạy..."
},
"pluginList": "Danh sách plugin",
+ "search": {
+ "config": {
+ "addKey": "Thêm khóa",
+ "close": "Xóa",
+ "confirm": "Đã hoàn thành cấu hình và thử lại"
+ },
+ "crawPages": {
+ "crawling": "Đang nhận diện liên kết",
+ "detail": {
+ "preview": "Xem trước",
+ "raw": "Văn bản gốc",
+ "tooLong": "Nội dung văn bản quá dài, chỉ giữ lại {{characters}} ký tự đầu tiên trong ngữ cảnh cuộc trò chuyện, phần vượt quá sẽ không được tính vào ngữ cảnh cuộc trò chuyện"
+ },
+ "meta": {
+ "crawler": "Chế độ thu thập",
+ "words": "Số ký tự"
+ }
+ },
+ "searchxng": {
+ "baseURL": "Nhập vào",
+ "description": "Nhập URL của SearchXNG để bắt đầu tìm kiếm trực tuyến",
+ "keyPlaceholder": "Nhập khóa",
+ "title": "Cấu hình công cụ tìm kiếm SearchXNG",
+ "unconfiguredDesc": "Vui lòng liên hệ với quản trị viên để hoàn thành cấu hình công cụ tìm kiếm SearchXNG, để bắt đầu tìm kiếm trực tuyến",
+ "unconfiguredTitle": "Chưa cấu hình công cụ tìm kiếm SearchXNG"
+ },
+ "title": "Tìm kiếm trực tuyến"
+ },
"setting": "Cài đặt plugin",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/vi-VN/portal.json b/DigitalHumanWeb/locales/vi-VN/portal.json
index bfb400c..9729fed 100644
--- a/DigitalHumanWeb/locales/vi-VN/portal.json
+++ b/DigitalHumanWeb/locales/vi-VN/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "Tiện ích",
- "actions": {
- "genAiMessage": "Tạo tin nhắn trợ giúp",
- "summary": "Tóm tắt",
- "summaryTooltip": "Tóm tắt nội dung hiện tại"
- },
"artifacts": {
"display": {
"code": "Mã",
diff --git a/DigitalHumanWeb/locales/vi-VN/providers.json b/DigitalHumanWeb/locales/vi-VN/providers.json
index be0e51f..a9ac40f 100644
--- a/DigitalHumanWeb/locales/vi-VN/providers.json
+++ b/DigitalHumanWeb/locales/vi-VN/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs xây dựng các mô hình cơ bản và hệ thống trí tuệ nhân tạo cho doanh nghiệp, tăng tốc ứng dụng trí tuệ nhân tạo sinh sinh trong sản xuất."
+ },
"ai360": {
"description": "360 AI là nền tảng mô hình và dịch vụ AI do công ty 360 phát hành, cung cấp nhiều mô hình xử lý ngôn ngữ tự nhiên tiên tiến, bao gồm 360GPT2 Pro, 360GPT Pro, 360GPT Turbo và 360GPT Turbo Responsibility 8K. Những mô hình này kết hợp giữa tham số quy mô lớn và khả năng đa phương thức, được ứng dụng rộng rãi trong tạo văn bản, hiểu ngữ nghĩa, hệ thống đối thoại và tạo mã. Thông qua chiến lược giá linh hoạt, 360 AI đáp ứng nhu cầu đa dạng của người dùng, hỗ trợ nhà phát triển tích hợp, thúc đẩy sự đổi mới và phát triển ứng dụng thông minh."
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure cung cấp nhiều mô hình AI tiên tiến, bao gồm GPT-3.5 và dòng GPT-4 mới nhất, hỗ trợ nhiều loại dữ liệu và nhiệm vụ phức tạp, cam kết cung cấp các giải pháp AI an toàn, đáng tin cậy và bền vững."
},
+ "azureai": {
+ "description": "Azure cung cấp nhiều mô hình AI tiên tiến, bao gồm GPT-3.5 và dòng GPT-4 mới nhất, hỗ trợ nhiều loại dữ liệu và nhiệm vụ phức tạp, cam kết cung cấp các giải pháp AI an toàn, đáng tin cậy và bền vững."
+ },
"baichuan": {
"description": "Baichuan Intelligent là công ty tập trung vào nghiên cứu phát triển mô hình ngôn ngữ lớn AI, mô hình của họ thể hiện xuất sắc trong các nhiệm vụ tiếng Trung như bách khoa toàn thư, xử lý văn bản dài và sáng tác, vượt trội hơn so với các mô hình chính thống quốc tế. Baichuan Intelligent còn có khả năng đa phương thức hàng đầu trong ngành, thể hiện xuất sắc trong nhiều bài kiểm tra uy tín. Các mô hình của họ bao gồm Baichuan 4, Baichuan 3 Turbo và Baichuan 3 Turbo 128k, được tối ưu hóa cho các tình huống ứng dụng khác nhau, cung cấp giải pháp hiệu quả về chi phí."
},
"bedrock": {
"description": "Bedrock là dịch vụ do Amazon AWS cung cấp, tập trung vào việc cung cấp các mô hình ngôn ngữ AI và mô hình hình ảnh tiên tiến cho doanh nghiệp. Gia đình mô hình của nó bao gồm dòng Claude của Anthropic, dòng Llama 3.1 của Meta, v.v., bao quát nhiều lựa chọn từ nhẹ đến hiệu suất cao, hỗ trợ nhiều nhiệm vụ như tạo văn bản, đối thoại, xử lý hình ảnh, phù hợp cho các ứng dụng doanh nghiệp với quy mô và nhu cầu khác nhau."
},
+ "cloudflare": {
+ "description": "Chạy các mô hình học máy được hỗ trợ bởi GPU không máy chủ trên mạng lưới toàn cầu của Cloudflare."
+ },
"deepseek": {
"description": "DeepSeek là một công ty tập trung vào nghiên cứu và ứng dụng công nghệ trí tuệ nhân tạo, mô hình mới nhất của họ, DeepSeek-V2.5, kết hợp khả năng đối thoại chung và xử lý mã, đồng thời đạt được sự cải thiện đáng kể trong việc căn chỉnh sở thích của con người, nhiệm vụ viết và tuân theo chỉ dẫn."
},
+ "doubao": {
+ "description": "Mô hình lớn tự phát triển do ByteDance phát triển. Được xác thực qua hơn 50 tình huống kinh doanh nội bộ của ByteDance, với việc sử dụng hàng nghìn tỷ token mỗi ngày để liên tục cải tiến, cung cấp nhiều khả năng đa phương thức, tạo ra trải nghiệm kinh doanh phong phú cho doanh nghiệp với hiệu quả mô hình chất lượng cao."
+ },
"fireworksai": {
"description": "Fireworks AI là nhà cung cấp dịch vụ mô hình ngôn ngữ cao cấp hàng đầu, tập trung vào gọi chức năng và xử lý đa phương thức. Mô hình mới nhất của họ, Firefunction V2, dựa trên Llama-3, được tối ưu hóa cho gọi chức năng, đối thoại và tuân theo chỉ dẫn. Mô hình ngôn ngữ hình ảnh FireLLaVA-13B hỗ trợ đầu vào hỗn hợp hình ảnh và văn bản. Các mô hình đáng chú ý khác bao gồm dòng Llama và dòng Mixtral, cung cấp hỗ trợ cho việc tuân theo và tạo ra chỉ dẫn đa ngôn ngữ hiệu quả."
},
+ "giteeai": {
+ "description": "Serverless API của Gitee AI cung cấp các dịch vụ API lý luận mô hình lớn cho các nhà phát triển AI."
+ },
"github": {
"description": "Với GitHub Models, các nhà phát triển có thể trở thành kỹ sư AI và xây dựng với các mô hình AI hàng đầu trong ngành."
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Bộ máy suy diễn LPU của Groq thể hiện xuất sắc trong các bài kiểm tra chuẩn mô hình ngôn ngữ lớn (LLM) độc lập mới nhất, định nghĩa lại tiêu chuẩn cho các giải pháp AI với tốc độ và hiệu quả đáng kinh ngạc. Groq là đại diện cho tốc độ suy diễn tức thì, thể hiện hiệu suất tốt trong triển khai dựa trên đám mây."
},
+ "higress": {
+ "description": "Higress là một cổng API gốc đám mây, được phát triển trong nội bộ của Alibaba để giải quyết vấn đề Tengine reload ảnh hưởng đến các dịch vụ kết nối dài hạn, cũng như khả năng cân bằng tải gRPC/Dubbo chưa đủ."
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API cung cấp một cách nhanh chóng và miễn phí để bạn khám phá hàng ngàn mô hình cho nhiều nhiệm vụ khác nhau. Dù bạn đang thiết kế nguyên mẫu cho một ứng dụng mới hay đang thử nghiệm khả năng của học máy, API này cho phép bạn truy cập ngay lập tức vào các mô hình hiệu suất cao trong nhiều lĩnh vực."
+ },
+ "hunyuan": {
+ "description": "Mô hình ngôn ngữ lớn được phát triển bởi Tencent, có khả năng sáng tạo tiếng Trung mạnh mẽ, khả năng suy luận logic trong các ngữ cảnh phức tạp, và khả năng thực hiện nhiệm vụ đáng tin cậy."
+ },
+ "internlm": {
+ "description": "Tổ chức mã nguồn mở chuyên nghiên cứu và phát triển công cụ cho mô hình lớn. Cung cấp nền tảng mã nguồn mở hiệu quả, dễ sử dụng cho tất cả các nhà phát triển AI, giúp tiếp cận công nghệ mô hình lớn và thuật toán tiên tiến nhất."
+ },
+ "jina": {
+ "description": "Jina AI được thành lập vào năm 2020, là một công ty hàng đầu trong lĩnh vực AI tìm kiếm. Nền tảng tìm kiếm của chúng tôi bao gồm các mô hình vector, bộ tái sắp xếp và các mô hình ngôn ngữ nhỏ, giúp các doanh nghiệp xây dựng các ứng dụng tìm kiếm sinh tạo và đa phương tiện đáng tin cậy và chất lượng cao."
+ },
+ "lmstudio": {
+ "description": "LM Studio là một ứng dụng máy tính để phát triển và thử nghiệm các LLM trên máy tính của bạn."
+ },
"minimax": {
"description": "MiniMax là công ty công nghệ trí tuệ nhân tạo tổng quát được thành lập vào năm 2021, cam kết cùng người dùng sáng tạo trí thông minh. MiniMax đã tự phát triển nhiều mô hình lớn đa phương thức, bao gồm mô hình văn bản MoE với một triệu tham số, mô hình giọng nói và mô hình hình ảnh. Họ cũng đã phát hành các ứng dụng như AI Hải Lý."
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI là một nền tảng cung cấp dịch vụ API cho nhiều mô hình ngôn ngữ lớn và tạo hình ảnh AI, linh hoạt, đáng tin cậy và hiệu quả về chi phí. Nó hỗ trợ các mô hình mã nguồn mở mới nhất như Llama3, Mistral, và cung cấp giải pháp API toàn diện, thân thiện với người dùng và tự động mở rộng cho phát triển ứng dụng AI, phù hợp cho sự phát triển nhanh chóng của các công ty khởi nghiệp AI."
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ cung cấp các container có thể được sử dụng để tự lưu trữ các dịch vụ vi mô suy diễn GPU tăng tốc, hỗ trợ triển khai các mô hình AI đã được huấn luyện trước và tùy chỉnh trên đám mây, trung tâm dữ liệu, máy tính cá nhân RTX™ AI và trạm làm việc."
+ },
"ollama": {
"description": "Mô hình do Ollama cung cấp bao quát rộng rãi các lĩnh vực như tạo mã, tính toán toán học, xử lý đa ngôn ngữ và tương tác đối thoại, hỗ trợ nhu cầu đa dạng cho triển khai doanh nghiệp và địa phương."
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity là nhà cung cấp mô hình tạo đối thoại hàng đầu, cung cấp nhiều mô hình Llama 3.1 tiên tiến, hỗ trợ ứng dụng trực tuyến và ngoại tuyến, đặc biệt phù hợp cho các nhiệm vụ xử lý ngôn ngữ tự nhiên phức tạp."
},
+ "ppio": {
+ "description": "PPIO派欧云 cung cấp dịch vụ API mô hình mã nguồn mở ổn định, hiệu quả chi phí cao, hỗ trợ toàn bộ dòng sản phẩm DeepSeek, Llama, Qwen và các mô hình lớn hàng đầu trong ngành."
+ },
"qwen": {
"description": "Qwen là mô hình ngôn ngữ quy mô lớn tự phát triển của Alibaba Cloud, có khả năng hiểu và tạo ngôn ngữ tự nhiên mạnh mẽ. Nó có thể trả lời nhiều câu hỏi, sáng tác nội dung văn bản, bày tỏ quan điểm, viết mã, v.v., hoạt động trong nhiều lĩnh vực."
},
+ "sambanova": {
+ "description": "SambaNova Cloud cho phép các nhà phát triển dễ dàng sử dụng các mô hình mã nguồn mở tốt nhất và tận hưởng tốc độ suy diễn nhanh nhất."
+ },
+ "sensenova": {
+ "description": "SenseTime luôn đổi mới, dựa vào nền tảng mạnh mẽ của SenseTime để cung cấp dịch vụ mô hình lớn toàn diện, hiệu quả và dễ sử dụng."
+ },
"siliconcloud": {
"description": "SiliconFlow cam kết tăng tốc AGI để mang lại lợi ích cho nhân loại, nâng cao hiệu quả AI quy mô lớn thông qua một ngăn xếp GenAI dễ sử dụng và chi phí thấp."
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "Viện Nghiên cứu Tự động hóa Trung Quốc và Viện Nghiên cứu Trí tuệ Nhân tạo Vũ Hán đã phát hành mô hình lớn đa phương thức thế hệ mới, hỗ trợ các nhiệm vụ hỏi đáp toàn diện như hỏi đáp nhiều vòng, sáng tác văn bản, tạo hình ảnh, hiểu 3D, phân tích tín hiệu, v.v., với khả năng nhận thức, hiểu biết và sáng tác mạnh mẽ hơn, mang đến trải nghiệm tương tác hoàn toàn mới."
},
+ "tencentcloud": {
+ "description": "Năng lực nguyên tử của động cơ tri thức (LLM Knowledge Engine Atomic Power) được phát triển dựa trên động cơ tri thức, cung cấp khả năng hỏi đáp toàn diện cho doanh nghiệp và nhà phát triển, cho phép xây dựng và phát triển ứng dụng mô hình một cách linh hoạt. Bạn có thể sử dụng nhiều năng lực nguyên tử để tạo ra dịch vụ mô hình riêng của mình, kết hợp các dịch vụ như phân tích tài liệu, tách rời, embedding, và viết lại nhiều vòng để tùy chỉnh các dịch vụ AI đặc thù cho doanh nghiệp."
+ },
"togetherai": {
"description": "Together AI cam kết đạt được hiệu suất hàng đầu thông qua các mô hình AI sáng tạo, cung cấp khả năng tùy chỉnh rộng rãi, bao gồm hỗ trợ mở rộng nhanh chóng và quy trình triển khai trực quan, đáp ứng nhiều nhu cầu của doanh nghiệp."
},
"upstage": {
"description": "Upstage tập trung vào việc phát triển các mô hình AI cho nhiều nhu cầu thương mại khác nhau, bao gồm Solar LLM và AI tài liệu, nhằm đạt được trí thông minh nhân tạo tổng quát (AGI) cho công việc. Tạo ra các đại lý đối thoại đơn giản thông qua Chat API, và hỗ trợ gọi chức năng, dịch thuật, nhúng và ứng dụng trong các lĩnh vực cụ thể."
},
+ "vertexai": {
+ "description": "Dòng sản phẩm Gemini của Google là mô hình AI tiên tiến và đa năng nhất của họ, được phát triển bởi Google DeepMind, được thiết kế đặc biệt cho đa phương thức, hỗ trợ hiểu và xử lý liền mạch văn bản, mã, hình ảnh, âm thanh và video. Phù hợp với nhiều môi trường từ trung tâm dữ liệu đến thiết bị di động, nâng cao đáng kể hiệu quả và tính ứng dụng của mô hình AI."
+ },
+ "vllm": {
+ "description": "vLLM là một thư viện nhanh chóng và dễ sử dụng cho suy diễn và dịch vụ LLM."
+ },
+ "volcengine": {
+ "description": "Nền tảng phát triển dịch vụ mô hình lớn do ByteDance phát triển, cung cấp dịch vụ gọi mô hình phong phú, an toàn và có giá cả cạnh tranh, đồng thời cung cấp dữ liệu mô hình, tinh chỉnh, suy diễn, đánh giá và các chức năng đầu cuối khác, đảm bảo toàn diện cho việc phát triển ứng dụng AI của bạn."
+ },
+ "wenxin": {
+ "description": "Nền tảng phát triển và dịch vụ ứng dụng AI gốc với mô hình lớn một cửa dành cho doanh nghiệp, cung cấp chuỗi công cụ toàn diện và dễ sử dụng cho phát triển mô hình trí tuệ nhân tạo sinh sinh và phát triển ứng dụng."
+ },
+ "xai": {
+ "description": "xAI là một công ty cam kết xây dựng trí tuệ nhân tạo để tăng tốc khám phá khoa học của nhân loại. Sứ mệnh của chúng tôi là thúc đẩy sự hiểu biết chung của chúng ta về vũ trụ."
+ },
"zeroone": {
"description": "01.AI tập trung vào công nghệ trí tuệ nhân tạo trong kỷ nguyên AI 2.0, thúc đẩy mạnh mẽ sự đổi mới và ứng dụng của \"người + trí tuệ nhân tạo\", sử dụng các mô hình mạnh mẽ và công nghệ AI tiên tiến để nâng cao năng suất của con người và thực hiện sự trao quyền công nghệ."
},
diff --git a/DigitalHumanWeb/locales/vi-VN/setting.json b/DigitalHumanWeb/locales/vi-VN/setting.json
index 3e5189d..bf98547 100644
--- a/DigitalHumanWeb/locales/vi-VN/setting.json
+++ b/DigitalHumanWeb/locales/vi-VN/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "Cấu hình mô hình tùy chỉnh",
"tokens": {
- "title": "Số lượng token tối đa",
- "unlimited": "vô hạn"
+ "title": "Số lượng token tối đa"
},
"vision": {
"extra": "Cấu hình này chỉ mở khả năng tải lên hình ảnh trong ứng dụng, việc hỗ trợ nhận diện hoàn toàn phụ thuộc vào chính mô hình, vui lòng tự kiểm tra khả năng nhận diện hình ảnh của mô hình đó.",
@@ -98,6 +97,7 @@
"title": "Sử dụng chế độ yêu cầu từ khách hàng"
},
"fetcher": {
+ "clear": "Xóa mô hình đã lấy",
"fetch": "Lấy danh sách mô hình",
"fetching": "Đang lấy danh sách mô hình...",
"latestTime": "Thời gian cập nhật lần cuối: {{time}}",
@@ -175,8 +175,8 @@
"desc": "Có tự động tạo chủ đề trong quá trình trò chuyện hay không, chỉ áp dụng trong chủ đề tạm thời",
"title": "Tự động tạo chủ đề"
},
- "enableCompressThreshold": {
- "title": "Bật ngưỡng nén độ dài lịch sử"
+ "enableCompressHistory": {
+ "title": "Bật tóm tắt tự động lịch sử tin nhắn"
},
"enableHistoryCount": {
"alias": "Không giới hạn",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "Bật giới hạn phản hồi một lần"
},
+ "enableReasoningEffort": {
+ "title": "Bật điều chỉnh cường độ suy luận"
+ },
"frequencyPenalty": {
- "desc": "Giá trị càng cao, càng có khả năng giảm sự lặp lại của từ/cụm từ",
- "title": "Hình phạt tần suất"
+ "desc": "Giá trị càng lớn, từ ngữ càng phong phú đa dạng; giá trị càng thấp, từ ngữ càng đơn giản mộc mạc",
+ "title": "Độ phong phú từ vựng"
},
"maxTokens": {
"desc": "Số lượng Token tối đa được sử dụng trong mỗi tương tác",
@@ -212,19 +215,31 @@
"desc": "Mô hình {{provider}}",
"title": "Mô hình"
},
+ "params": {
+ "title": "Tham số nâng cao"
+ },
"presencePenalty": {
- "desc": "Giá trị càng cao, càng có khả năng mở rộng đến chủ đề mới",
- "title": "Độ mới của chủ đề"
+ "desc": "Giá trị càng lớn, càng có xu hướng sử dụng các cách diễn đạt khác nhau, tránh lặp lại khái niệm; giá trị càng nhỏ, càng có xu hướng sử dụng các khái niệm hoặc mô tả lặp lại, thể hiện tính nhất quán cao hơn",
+ "title": "Độ phân tán trong diễn đạt"
+ },
+ "reasoningEffort": {
+ "desc": "Giá trị càng lớn, khả năng suy luận càng mạnh, nhưng có thể làm tăng thời gian phản hồi và tiêu tốn Token",
+ "options": {
+ "high": "Cao",
+ "low": "Thấp",
+ "medium": "Trung bình"
+ },
+ "title": "Cường độ suy luận"
},
"temperature": {
- "desc": "Giá trị càng cao, phản hồi càng ngẫu nhiên",
- "title": "Độ ngẫu nhiên",
- "titleWithValue": "Độ ngẫu nhiên {{value}}"
+ "desc": "Giá trị càng lớn, câu trả lời càng sáng tạo và giàu trí tưởng tượng; giá trị càng nhỏ, câu trả lời càng nghiêm ngặt",
+ "title": "Mức độ sáng tạo",
+ "warning": "Giá trị mức độ sáng tạo quá lớn có thể dẫn đến đầu ra bị lỗi"
},
"title": "Cài đặt mô hình",
"topP": {
- "desc": "Tương tự như độ ngẫu nhiên, nhưng không nên thay đổi cùng lúc với độ ngẫu nhiên",
- "title": "Lấy mẫu cốt lõi"
+ "desc": "Xem xét bao nhiêu khả năng, giá trị càng lớn, chấp nhận nhiều câu trả lời khả thi hơn; giá trị càng nhỏ, có xu hướng chọn câu trả lời khả thi nhất. Không khuyến nghị thay đổi cùng với mức độ sáng tạo",
+ "title": "Mức độ mở trong tư duy"
}
},
"settingPlugin": {
@@ -372,10 +387,26 @@
"modelDesc": "Xác định mô hình được sử dụng để tạo tên, mô tả, hình đại diện, nhãn cho trợ lý",
"title": "Tự động tạo thông tin trợ lý"
},
+ "customPrompt": {
+ "addPrompt": "Thêm gợi ý tùy chỉnh",
+ "desc": "Sau khi điền, trợ lý hệ thống sẽ sử dụng gợi ý tùy chỉnh khi tạo nội dung",
+ "placeholder": "Nhập từ gợi ý tùy chỉnh",
+ "title": "Từ gợi ý tùy chỉnh"
+ },
+ "historyCompress": {
+ "label": "Mô hình lịch sử cuộc trò chuyện",
+ "modelDesc": "Chỉ định mô hình được sử dụng để nén lịch sử cuộc trò chuyện",
+ "title": "Tóm tắt tự động lịch sử cuộc trò chuyện"
+ },
"queryRewrite": {
"label": "Mô hình viết lại câu hỏi",
"modelDesc": "Mô hình được chỉ định để tối ưu hóa câu hỏi của người dùng",
- "title": "Kho tri thức"
+ "title": "Viết lại câu hỏi trong kho kiến thức"
+ },
+ "thread": {
+ "label": "Mô hình đặt tên chủ đề phụ",
+ "modelDesc": "Mô hình được chỉ định để tự động đổi tên chủ đề phụ",
+ "title": "Tự động đặt tên chủ đề phụ"
},
"title": "Trợ lý hệ thống",
"topic": {
@@ -395,6 +426,7 @@
"common": "Cài đặt chung",
"experiment": "Thử nghiệm",
"llm": "Mô hình ngôn ngữ",
+ "provider": "Nhà cung cấp AI",
"sync": "Đồng bộ trên đám mây",
"system-agent": "Trợ lý hệ thống",
"tts": "Dịch vụ giọng nói"
diff --git a/DigitalHumanWeb/locales/vi-VN/thread.json b/DigitalHumanWeb/locales/vi-VN/thread.json
new file mode 100644
index 0000000..c5c4ea7
--- /dev/null
+++ b/DigitalHumanWeb/locales/vi-VN/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "Bạn sắp xóa chủ đề con này, sau khi xóa sẽ không thể khôi phục, xin hãy cẩn thận khi thực hiện."
+ },
+ "newPortalThread": {
+ "includeContext": "Bao gồm ngữ cảnh chủ đề",
+ "title": "Mở chủ đề con mới"
+ },
+ "notSupportMultiModals": "Chủ đề con hiện không hỗ trợ tải lên tệp/hình ảnh, nếu có nhu cầu, xin vui lòng để lại tin nhắn: <1>💬 Diễn đàn thảo luận1>"
+}
diff --git a/DigitalHumanWeb/locales/vi-VN/tool.json b/DigitalHumanWeb/locales/vi-VN/tool.json
index 38e997b..88f63c5 100644
--- a/DigitalHumanWeb/locales/vi-VN/tool.json
+++ b/DigitalHumanWeb/locales/vi-VN/tool.json
@@ -6,5 +6,23 @@
"generating": "Đang tạo...",
"images": "Hình ảnh:",
"prompt": "Từ khóa"
+ },
+ "search": {
+ "createNewSearch": "Tạo mới tìm kiếm",
+ "emptyResult": "Không tìm thấy kết quả, vui lòng sửa đổi từ khóa và thử lại",
+ "genAiMessage": "Tạo tin nhắn trợ lý",
+ "includedTooltip": "Kết quả tìm kiếm hiện tại sẽ được đưa vào ngữ cảnh của cuộc hội thoại",
+ "keywords": "Từ khóa:",
+ "scoreTooltip": "Điểm liên quan, điểm số càng cao thì càng liên quan đến từ khóa tìm kiếm",
+ "searchBar": {
+ "button": "Tìm kiếm",
+ "placeholder": "Từ khóa",
+ "tooltip": "Sẽ lấy lại kết quả tìm kiếm và tạo một tin nhắn tóm tắt mới"
+ },
+ "searchEngine": "Công cụ tìm kiếm:",
+ "searchResult": "Số lượng tìm kiếm:",
+ "summary": "Tóm tắt",
+ "summaryTooltip": "Tóm tắt nội dung hiện tại",
+ "viewMoreResults": "Xem thêm {{results}} kết quả"
}
}
diff --git a/DigitalHumanWeb/locales/vi-VN/topic.json b/DigitalHumanWeb/locales/vi-VN/topic.json
new file mode 100644
index 0000000..80ae8b7
--- /dev/null
+++ b/DigitalHumanWeb/locales/vi-VN/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "Đặt tên tự động",
+ "confirmRemoveAll": "Sắp xóa tất cả các chủ đề, sau khi xóa sẽ không thể khôi phục, xin hãy cẩn thận.",
+ "confirmRemoveTopic": "Sắp xóa chủ đề này, sau khi xóa sẽ không thể khôi phục, xin hãy cẩn thận.",
+ "confirmRemoveUnstarred": "Sắp xóa các chủ đề chưa được đánh dấu, sau khi xóa sẽ không thể khôi phục, xin hãy cẩn thận.",
+ "duplicate": "Tạo bản sao",
+ "export": "Xuất chủ đề",
+ "removeAll": "Xóa tất cả các chủ đề",
+ "removeUnstarred": "Xóa các chủ đề chưa được đánh dấu"
+ },
+ "defaultTitle": "Chủ đề mặc định",
+ "duplicateLoading": "Đang sao chép chủ đề...",
+ "duplicateSuccess": "Sao chép chủ đề thành công",
+ "favorite": "Yêu thích",
+ "groupMode": {
+ "ascMessages": "Theo thứ tự tổng số tin nhắn",
+ "byTime": "Theo thời gian",
+ "descMessages": "Theo thứ tự tổng số tin nhắn giảm dần",
+ "flat": "Không phân nhóm"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "Tháng này",
+ "today": "Hôm nay",
+ "week": "Tuần này",
+ "yesterday": "Hôm qua"
+ }
+ },
+ "guide": {
+ "desc": "Nhấn nút bên trái để lưu cuộc trò chuyện hiện tại thành chủ đề lịch sử và bắt đầu một cuộc trò chuyện mới.",
+ "title": "Danh sách chủ đề"
+ },
+ "searchPlaceholder": "Tìm kiếm chủ đề...",
+ "searchResultEmpty": "Không có kết quả tìm kiếm nào",
+ "temp": "Tạm thời",
+ "title": "Chủ đề"
+}
diff --git a/DigitalHumanWeb/locales/vi-VN/welcome.json b/DigitalHumanWeb/locales/vi-VN/welcome.json
index 366675d..497dff8 100644
--- a/DigitalHumanWeb/locales/vi-VN/welcome.json
+++ b/DigitalHumanWeb/locales/vi-VN/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "Nhập Cấu Hình",
- "market": "Thăm Thị trường",
- "start": "Bắt Đầu Ngay"
- },
"guide": {
"agents": {
"replaceBtn": "Thay đổi",
diff --git a/DigitalHumanWeb/locales/zh-CN/auth.json b/DigitalHumanWeb/locales/zh-CN/auth.json
index 08711d7..efd3708 100644
--- a/DigitalHumanWeb/locales/zh-CN/auth.json
+++ b/DigitalHumanWeb/locales/zh-CN/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "上个月",
+ "recent30Days": "最近30天"
+ },
+ "header": {
+ "desc": "管理您的账户信息。",
+ "title": "账户"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "不活跃",
+ "more": "活跃"
+ },
+ "months": {
+ "apr": "四月",
+ "aug": "八月",
+ "dec": "十二月",
+ "feb": "二月",
+ "jan": "一月",
+ "jul": "七月",
+ "jun": "六月",
+ "mar": "三月",
+ "may": "五月",
+ "nov": "十一月",
+ "oct": "十月",
+ "sep": "九月"
+ },
+ "tooltip": "{{date}} 当日发送 {{count}} 条消息",
+ "totalCount": "过去一年共发送 {{count}} 条消息"
+ },
"login": "登录",
"loginOrSignup": "登录 / 注册",
- "profile": "个人资料",
- "security": "安全",
+ "profile": {
+ "avatar": "头像",
+ "email": "电子邮件地址",
+ "sso": {
+ "loading": "正在加载已绑定的第三方账户",
+ "providers": "连接的帐户",
+ "unlink": {
+ "description": "解绑后,您将无法使用 {{provider}} 账户“{{providerAccountId}}”登录。如果您需要重新绑定 {{provider}} 账户到当前账户,请确保 {{provider}} 账户的邮件地址为 {{email}} ,我们会在登陆时为你自动绑定到当前登录账户。",
+ "forbidden": "您至少需要保留一个第三方账户绑定。",
+ "title": "是否解绑该第三方账户 {{provider}} ?"
+ }
+ },
+ "username": "用户名"
+ },
"signout": "退出登录",
- "signup": "注册"
-}
+ "signup": "注册",
+ "stats": {
+ "aiheatmaps": "AI 指数",
+ "assistants": "助手数",
+ "assistantsRank": {
+ "left": "助手名称",
+ "right": "话题数",
+ "title": "助手使用率"
+ },
+ "createdAt": "用户创建于",
+ "days": "天",
+ "empty": {
+ "desc": "请积累更多聊天数据后查看",
+ "title": "暂无数据"
+ },
+ "lastYearActivity": "过去一年活跃度",
+ "loginGuide": {
+ "f1": "获取免费用量",
+ "f2": "多端同步消息",
+ "f3": "拥有丰富助手",
+ "f4": "探索强大插件",
+ "title": "登陆后你可以:"
+ },
+ "messages": "消息数",
+ "modelsRank": {
+ "left": "模型名称",
+ "right": "消息数",
+ "title": "模型使用率"
+ },
+ "share": {
+ "title": "我的 AI 活跃指数"
+ },
+ "topics": "话题数",
+ "topicsRank": {
+ "left": "话题名称",
+ "right": "消息数",
+ "title": "话题内容量"
+ },
+ "updatedAt": "数据更新至",
+ "welcome": "{{username}}, 这是你和 {{appName}} 相伴的第 {{days}} 天",
+ "words": "累计字数"
+ },
+ "tab": {
+ "profile": "个人资料",
+ "security": "安全",
+ "stats": "数据统计"
+ }
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/changelog.json b/DigitalHumanWeb/locales/zh-CN/changelog.json
new file mode 100644
index 0000000..59d8b53
--- /dev/null
+++ b/DigitalHumanWeb/locales/zh-CN/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "在 X 上关注我们",
+ "subscribeToUpdates": "订阅更新",
+ "versions": "版本详情"
+ },
+ "addedWhileAway": "在您离开期间,我们带来了新的特性。",
+ "allChangelog": "查看所有更新日志",
+ "description": "持续追踪 {{appName}} 的新功能和改进",
+ "pagination": {
+ "next": "下一页",
+ "older": "查看历史变更"
+ },
+ "readDetails": "阅读详情",
+ "title": "更新日志",
+ "versionDetails": "版本详情",
+ "welcomeBack": "欢迎回来!"
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/chat.json b/DigitalHumanWeb/locales/zh-CN/chat.json
index 651d793..5408230 100644
--- a/DigitalHumanWeb/locales/zh-CN/chat.json
+++ b/DigitalHumanWeb/locales/zh-CN/chat.json
@@ -8,6 +8,7 @@
"agents": "助手",
"artifact": {
"generating": "生成中",
+ "inThread": "子话题中无法查看,请切换到主对话区打开",
"thinking": "思考中",
"thought": "思考过程",
"unknownTitle": "未命名作品"
@@ -21,7 +22,7 @@
"confirmRemoveSessionItemAlert": "即将删除该助手,删除后该将无法找回,请确认你的操作",
"confirmRemoveSessionSuccess": "助手删除成功",
"defaultAgent": "自定义助手",
- "defaultList": "助手会话列表",
+ "defaultList": "默认列表",
"defaultSession": "自定义助手",
"duplicateSession": {
"loading": "复制中...",
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} 副本",
"emptyAgent": "暂无助手",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "单条对话生成成本最高可降低 90%,响应速度提升 4 倍(<1>了解更多1>)。开启后将自动禁用历史消息数限制",
+ "title": "开启上下文缓存"
+ },
+ "enableReasoning": {
+ "desc": "基于 Claude Thinking 机制限制(<1>了解更多1>),开启后将自动禁用历史消息数限制",
+ "title": "开启深度思考"
+ },
+ "reasoningBudgetToken": {
+ "title": "思考消耗 Token"
+ },
+ "title": "模型扩展功能"
+ },
+ "history": {
+ "title": "助手将只记住最后{{count}}条消息"
+ },
"historyRange": "历史范围",
+ "historySummary": "历史消息总结",
"inbox": {
"desc": "开启大脑集群,激发思维火花。你的智能助理,在这里与你交流一切",
"title": "随便聊聊"
@@ -40,12 +59,14 @@
"addUser": "添加一条用户消息",
"more": "更多",
"send": "发送",
- "clear": "清空内容",
"sendWithCmdEnter": "按 {{meta}} + Enter 键发送",
"sendWithEnter": "按 Enter 键发送",
"stop": "停止",
"warp": "换行"
},
+ "intentUnderstanding": {
+ "title": "正在理解并分析您的意图..."
+ },
"knowledgeBase": {
"all": "所有内容",
"allFiles": "所有文件",
@@ -66,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "删除并重新生成",
+ "deleteDisabledByThreads": "存在子话题,不能删除",
"regenerate": "重新生成"
},
+ "messages": {
+ "modelCard": {
+ "credit": "积分",
+ "creditPricing": "定价",
+ "creditTooltip": "为便于计数,我们将 1$ 折算为 1M 积分,例如 $3/M tokens 即可折算为 3积分/token",
+ "pricing": {
+ "inputCachedTokens": "缓存输入 {{amount}}/积分 · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M 字符",
+ "inputMinutes": "${{amount}}/分钟",
+ "inputTokens": "输入 {{amount}}/积分 · ${{amount}}/M",
+ "outputTokens": "输出 {{amount}}/积分 · ${{amount}}/M",
+ "writeCacheInputTokens": "缓存输入写入 {{amount}}/积分 · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "平均单价",
+ "input": "输入",
+ "inputAudio": "音频输入",
+ "inputCached": "输入缓存",
+ "inputCitation": "引用输入",
+ "inputText": "文本输入",
+ "inputTitle": "输入明细",
+ "inputUncached": "输入未缓存",
+ "inputWriteCached": "输入缓存写入",
+ "output": "输出",
+ "outputAudio": "音频输出",
+ "outputText": "文本输出",
+ "outputTitle": "输出明细",
+ "reasoning": "深度思考",
+ "title": "生成明细",
+ "total": "总计消耗"
+ }
+ },
"newAgent": "新建助手",
"pin": "置顶",
"pinOff": "取消置顶",
@@ -82,6 +137,32 @@
},
"regenerate": "重新生成",
"roleAndArchive": "角色与记录",
+ "search": {
+ "grounding": {
+ "searchQueries": "搜索关键词",
+ "title": "已搜索到 {{count}} 个结果"
+ },
+ "mode": {
+ "auto": {
+ "desc": "根据对话内容智能判断是否需要搜索",
+ "title": "智能联网"
+ },
+ "off": {
+ "desc": "仅使用模型的基础知识,不进行网络搜索",
+ "title": "关闭联网"
+ },
+ "on": {
+ "desc": "持续进行网络搜索,获取最新信息",
+ "title": "始终联网"
+ },
+ "useModelBuiltin": "使用模型内置搜索引擎"
+ },
+ "searchModel": {
+ "desc": "当前模型不支持函数调用,因此需要搭配支持函数调用的模型才能联网搜索",
+ "title": "搜索辅助模型"
+ },
+ "title": "联网搜索"
+ },
"searchAgentPlaceholder": "搜索助手...",
"sendPlaceholder": "输入聊天内容...",
"sessionGroup": {
@@ -101,14 +182,20 @@
"tooLong": "分组名称长度需在 1-20 之内"
},
"shareModal": {
+ "copy": "复制",
"download": "下载截图",
+ "downloadFile": "下载文件",
+ "exportTitle": "默认标题",
"imageType": "图片格式",
+ "includeTool": "包含插件消息",
+ "includeUser": "包含用户消息",
"screenshot": "截图",
"settings": "导出设置",
- "shareToShareGPT": "生成 ShareGPT 分享链接",
+ "text": "文本",
"withBackground": "包含背景图片",
"withFooter": "包含页脚",
"withPluginInfo": "包含插件信息",
+ "withRole": "包含消息角色",
"withSystemRole": "包含助手角色设定"
},
"stt": {
@@ -116,9 +203,14 @@
"loading": "识别中...",
"prettifying": "润色中..."
},
- "temp": "临时",
+ "thread": {
+ "divider": "子话题",
+ "threadMessageCount": "{{messageCount}} 条消息",
+ "title": "子话题"
+ },
"tokenDetails": {
"chats": "会话消息",
+ "historySummary": "历史总结",
"rest": "剩余可用",
"systemRole": "角色设定",
"title": "上下文明细",
@@ -132,29 +224,10 @@
"used": "使用"
},
"topic": {
- "actions": {
- "autoRename": "智能重命名",
- "duplicate": "创建副本",
- "export": "导出话题"
- },
"checkOpenNewTopic": "是否开启新话题?",
"checkSaveCurrentMessages": "是否保存当前会话为话题?",
- "confirmRemoveAll": "即将删除全部话题,删除后将不可恢复,请谨慎操作。",
- "confirmRemoveTopic": "即将删除该话题,删除后将不可恢复,请谨慎操作。",
- "confirmRemoveUnstarred": "即将删除未收藏话题,删除后将不可恢复,请谨慎操作。",
- "defaultTitle": "默认话题",
- "duplicateLoading": "话题复制中...",
- "duplicateSuccess": "话题复制成功",
- "guide": {
- "desc": "点击发送左侧按钮可将当前会话保存为历史话题,并开启新一轮会话",
- "title": "话题列表"
- },
"openNewTopic": "开启新话题",
- "removeAll": "删除全部话题",
- "removeUnstarred": "删除未收藏话题",
- "saveCurrentMessages": "将当前会话保存为话题",
- "searchPlaceholder": "搜索话题...",
- "title": "话题"
+ "saveCurrentMessages": "将当前会话保存为话题"
},
"translate": {
"action": "翻译",
@@ -185,5 +258,6 @@
"processing": "文件处理中..."
}
}
- }
+ },
+ "zenMode": "专注模式"
}
diff --git a/DigitalHumanWeb/locales/zh-CN/clerk.json b/DigitalHumanWeb/locales/zh-CN/clerk.json
index d2c2f4e..28669e6 100644
--- a/DigitalHumanWeb/locales/zh-CN/clerk.json
+++ b/DigitalHumanWeb/locales/zh-CN/clerk.json
@@ -766,4 +766,4 @@
"title": "添加 Web3 钱包"
}
}
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/common.json b/DigitalHumanWeb/locales/zh-CN/common.json
index 503b562..dec1331 100644
--- a/DigitalHumanWeb/locales/zh-CN/common.json
+++ b/DigitalHumanWeb/locales/zh-CN/common.json
@@ -9,15 +9,79 @@
"title": "{{name}} 开始公测"
}
},
- "appInitializing": "应用启动中...",
+ "appLoading": {
+ "appIdle": "准备启动",
+ "appInitializing": "应用启动中...",
+ "failed": "很抱歉,应用初始化失败,请查看详情进行排查",
+ "finished": "数据库初始化完成",
+ "goToChat": "对话页面加载中...",
+ "initAuth": "鉴权服务初始化...",
+ "initUser": "用户状态初始化...",
+ "initializing": "PGlite 数据库初始化...",
+ "loadingDependencies": "初始化依赖...",
+ "loadingWasm": "加载 WASM 模块...",
+ "migrating": "执行数据表迁移...",
+ "ready": "数据库已就绪",
+ "showDetail": "查看详情"
+ },
"autoGenerate": "自动补全",
"autoGenerateTooltip": "基于提示词自动补全助手描述",
"autoGenerateTooltipDisabled": "请填写提示词后使用自动补全功能",
"back": "返回",
"batchDelete": "批量删除",
"blog": "产品博客",
+ "branching": "创建子话题",
+ "branchingDisable": "「子话题」功能在当前模式下不可用,如需该功能,请切换到 Postgres/Pglite DB 模式或使用 LobeChat Cloud",
"cancel": "取消",
"changelog": "更新日志",
+ "clientDB": {
+ "autoInit": {
+ "title": "初始化 PGlite 数据库"
+ },
+ "error": {
+ "desc": "非常抱歉,Pglite 数据库初始化过程发生异常。请点击按钮重试。如多次重试后仍重复出错,请 <1>提交问题1> ,我们将会第一时间帮你排查",
+ "detail": "错误原因:[{{type}}] {{message}},明细如下:",
+ "retry": "重试",
+ "title": "数据库初始化失败"
+ },
+ "initing": {
+ "error": "数据库初始化出错,点击查看详情",
+ "idle": "等待初始化...",
+ "initializing": "正在初始化...",
+ "loadingDependencies": "加载依赖中...",
+ "loadingWasmModule": "加载 WASM 模块中...",
+ "migrating": "执行数据表迁移...",
+ "ready": "数据库已就绪"
+ },
+ "modal": {
+ "desc": "立即启用下一代客户端数据库。在你的浏览器中持久存储聊天数据,并使用知识库等进阶特性。",
+ "enable": "立即启用",
+ "features": {
+ "knowledgeBase": {
+ "desc": "沉淀你的个人知识库,并与你的助手轻松开启知识库对话(即将上线)",
+ "title": "支持知识库对话,开启第二大脑"
+ },
+ "localFirst": {
+ "desc": "聊天数据完全存储在浏览器中,你的数据始终在你的掌握。",
+ "title": "本地优先,隐私至上"
+ },
+ "pglite": {
+ "desc": "基于 PGlite 构建,原生支持 AI Native 高阶特性(向量检索)",
+ "title": "新一代客户端存储架构"
+ }
+ },
+ "init": {
+ "desc": "正在初始化数据库,视网络差异可能会用时 5~30 秒不等",
+ "title": "正在初始化 PGlite 数据库"
+ },
+ "title": "开启客户端数据库"
+ },
+ "ready": {
+ "button": "立即使用",
+ "desc": "立即想用",
+ "title": "PGlite 数据库已就绪"
+ }
+ },
"close": "关闭",
"contact": "联系我们",
"copy": "复制",
@@ -112,6 +176,7 @@
"en": "英语",
"en-US": "英语",
"es-ES": "西班牙语",
+ "fa-IR": "波斯语",
"fi-FI": "芬兰语",
"fr-FR": "法语",
"hi-IN": "印地语",
@@ -153,6 +218,7 @@
"pinOff": "取消置顶",
"privacy": "隐私政策",
"regenerate": "重新生成",
+ "releaseNotes": "版本详情",
"rename": "重命名",
"reset": "重置",
"retry": "重试",
@@ -209,6 +275,7 @@
},
"temp": "临时",
"terms": "服务条款",
+ "update": "更新",
"updateAgent": "更新助理信息",
"upgradeVersion": {
"action": "升级",
@@ -219,6 +286,7 @@
"anonymousNickName": "匿名用户",
"billing": "账单管理",
"cloud": "体验 {{name}}",
+ "community": "社区版",
"data": "数据存储",
"defaultNickname": "社区版用户",
"discord": "社区支持",
@@ -228,10 +296,9 @@
"help": "帮助中心",
"moveGuide": "设置按钮搬到这里啦",
"plans": "订阅方案",
- "preview": "预览版",
"profile": "账户管理",
"setting": "应用设置",
"usages": "用量统计"
},
"version": "版本"
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/components.json b/DigitalHumanWeb/locales/zh-CN/components.json
index 03811f6..3d86874 100644
--- a/DigitalHumanWeb/locales/zh-CN/components.json
+++ b/DigitalHumanWeb/locales/zh-CN/components.json
@@ -12,6 +12,7 @@
"batchChunking": "批量分块",
"chunking": "分块",
"chunkingTooltip": "将文件拆分为多个文本块并向量化后,可用于语义检索和文件对话",
+ "chunkingUnsupported": "该文件不支持分块",
"confirmDelete": "即将删除该文件,删除后该将无法找回,请确认你的操作",
"confirmDeleteMultiFiles": "即将删除选中的 {{count}} 个文件,删除后该将无法找回,请确认你的操作",
"confirmRemoveFromKnowledgeBase": "即将从知识库中移除选中的 {{count}} 个文件,移除后文件仍然可以在全部文件中查看,请确认你的操作",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "返回"
},
+ "MaxTokenSlider": {
+ "unlimited": "无限制"
+ },
"ModelSelect": {
"featureTag": {
"custom": "自定义模型,默认设定同时支持函数调用与视觉识别,请根据实际情况验证上述能力的可用性",
"file": "该模型支持上传文件读取与识别",
"functionCall": "该模型支持函数调用(Function Call)",
+ "reasoning": "该模型支持深度思考",
+ "search": "该模型支持联网搜索",
"tokens": "该模型单个会话最多支持 {{tokens}} Tokens",
"vision": "该模型支持视觉识别"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "没有启用的模型,请前往设置开启",
- "provider": "提供商"
+ "emptyProvider": "没有启用的服务商,请前往设置开启",
+ "goToSettings": "前往设置",
+ "provider": "服务商"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "因浏览器安全限制,你需要为 Ollama 进行跨域配置后方可正常使用。",
+ "linux": {
+ "env": "在 [Service] 部分下添加 `Environment`,添加 OLLAMA_ORIGINS 环境变量:",
+ "reboot": "重载 systemd 并重启 Ollama",
+ "systemd": "调用 systemd 编辑 ollama 服务:"
+ },
+ "macos": "请打开「终端」应用程序,并粘贴以下指令,并按回车运行",
+ "reboot": "请在执行完成后重启 Ollama 服务",
+ "title": "配置 Ollama 允许跨域访问",
+ "windows": "在 Windows 上,点击「控制面板」,进入编辑系统环境变量。为您的用户账户新建名为 「OLLAMA_ORIGINS」 的环境变量,值为 * ,点击 「OK/应用」 保存"
+ },
+ "install": {
+ "description": "请确认你已经开启 Ollama ,如果没有下载 Ollama ,请前往官网<1>下载1>",
+ "docker": "如果你更倾向于使用 Docker,Ollama 也提供了官方 Docker 镜像,你可以通过以下命令拉取:",
+ "linux": {
+ "command": "通过以下命令安装:",
+ "manual": "或者,你也可以参考 <1>Linux 手动安装指南1> 自行安装"
+ },
+ "title": "在本地安装并开启 Ollama 应用",
+ "windowsTab": "Windows (预览版)"
+ }
+ },
+ "Thinking": {
+ "thinking": "深度思考中...",
+ "thought": "已深度思考(用时 {{duration}} 秒)",
+ "thoughtWithDuration": "已深度思考"
}
}
diff --git a/DigitalHumanWeb/locales/zh-CN/discover.json b/DigitalHumanWeb/locales/zh-CN/discover.json
index 632879f..4eb7fa1 100644
--- a/DigitalHumanWeb/locales/zh-CN/discover.json
+++ b/DigitalHumanWeb/locales/zh-CN/discover.json
@@ -19,24 +19,26 @@
"try": "试一下"
},
"back": "返回发现",
- "collectSuccess": "收藏成功",
"category": {
"assistant": {
+ "academic": "学术",
"all": "全部",
- "collect": "收藏",
- "academic": "政务",
- "education": "教育",
- "marketing": "营销",
+ "career": "职业",
+ "copywriting": "文案",
"design": "设计",
- "office": "办公",
- "programming": "编程",
+ "education": "教育",
+ "emotions": "情感",
"entertainment": "娱乐",
+ "games": "游戏",
+ "general": "通用",
"life": "生活",
- "general": "通用"
+ "marketing": "商业",
+ "office": "办公",
+ "programming": "编程",
+ "translation": "翻译"
},
"plugin": {
"all": "全部",
- "collect": "收藏",
"gaming-entertainment": "游戏娱乐",
"life-style": "生活方式",
"media-generate": "媒体生成",
@@ -124,6 +126,10 @@
"title": "话题新鲜度"
},
"range": "范围",
+ "reasoning_effort": {
+ "desc": "此设置用于控制模型在生成回答前的推理强度。低强度优先响应速度并节省 Token,高强度提供更完整的推理,但会消耗更多 Token 并降低响应速度。默认值为中,平衡推理准确性与响应速度。",
+ "title": "推理强度"
+ },
"temperature": {
"desc": "此设置影响模型回应的多样性。较低的值会导致更可预测和典型的回应,而较高的值则鼓励更多样化和不常见的回应。当值设为0时,模型对于给定的输入总是给出相同的回应。",
"title": "随机性"
@@ -199,4 +205,4 @@
"plugins": "插件",
"providers": "模型服务商"
}
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/error.json b/DigitalHumanWeb/locales/zh-CN/error.json
index 14fb419..a372e11 100644
--- a/DigitalHumanWeb/locales/zh-CN/error.json
+++ b/DigitalHumanWeb/locales/zh-CN/error.json
@@ -12,8 +12,14 @@
"retry": "重新加载",
"title": "页面遇到一点问题.."
},
- "fetchError": "请求失败",
- "fetchErrorDetail": "错误详情",
+ "fetchError": {
+ "detail": "错误详情",
+ "title": "请求失败"
+ },
+ "loginRequired": {
+ "desc": "即将自动跳转到登录页面",
+ "title": "请登录后使用该功能"
+ },
"notFound": {
"backHome": "返回首页",
"check": "请检查你的 URL 是否正确",
@@ -51,9 +57,16 @@
"431": "很抱歉,您的请求头字段太大,服务器无法处理",
"451": "很抱歉,由于法律原因,服务器拒绝提供此资源",
"500": "很抱歉,服务器似乎遇到了一些困难,暂时无法完成您的请求,请稍后再试",
+ "501": "很抱歉,服务器还不知道如何处理这个请求,请确认您的操作是否正确",
"502": "很抱歉,服务器似乎迷失了方向,暂时无法提供服务,请稍后再试",
"503": "很抱歉,服务器当前无法处理您的请求,可能是由于过载或正在进行维护,请稍后再试",
"504": "很抱歉,服务器没有等到上游服务器的回应,请稍后再试",
+ "505": "很抱歉,服务器不支持您使用的HTTP版本,请更新后再试",
+ "506": "很抱歉,服务器配置出现问题,请联系管理员解决",
+ "507": "很抱歉,服务器存储空间不足,无法处理您的请求,请稍后再试",
+ "509": "很抱歉,服务器的带宽已用尽,请稍后再试",
+ "510": "很抱歉,服务器不支持请求的扩展功能,请联系管理员",
+ "524": "很抱歉,服务器在等回复时超时了,可能是因为响应太慢,请稍后再试",
"PluginMarketIndexNotFound": "很抱歉,服务器没有找到插件索引,请检查索引地址是否正确",
"PluginMarketIndexInvalid": "很抱歉,插件索引校验未通过,请检查索引文件格式是否规范",
"PluginMetaNotFound": "很抱歉,没有在索引中发现该插件,请插件在索引中的配置信息",
@@ -69,11 +82,18 @@
"PluginFailToTransformArguments": "很抱歉,插件调用参数解析失败,请尝试重新生成助手消息,或更换 Tools Calling 能力更强的 AI 模型后重试",
"InvalidAccessCode": "密码不正确或为空,请输入正确的访问密码,或者添加自定义 API Key",
"InvalidClerkUser": "很抱歉,你当前尚未登录,请先登录或注册账号后继续操作",
+ "SystemTimeNotMatchError": "很抱歉,您的系统时间和服务器不匹配,请检查您的系统时间后重试",
+ "SubscriptionKeyMismatch": "很抱歉,由于系统偶发故障,当前订阅用量暂时失效,请点击下方按钮恢复订阅,或邮件联系我们获取支持",
"LocationNotSupportError": "很抱歉,你的所在地区不支持此模型服务,可能是由于区域限制或服务未开通。请确认当前地区是否支持使用此服务,或尝试使用切换到其他地区后重试。",
+ "InsufficientQuota": "很抱歉,该密钥的配额(quota)已达上限,请检查账户余额是否充足,或增大密钥配额后再试",
+ "ModelNotFound": "很抱歉,无法请求到相应的模型,可能是模型不存在或者没有访问权限导致,请更换 API Key 或调整访问权限后重试",
+ "ExceededContextWindow": "当前请求内容超出模型可处理的长度,请减少内容量后重试",
+ "QuotaLimitReached": "很抱歉,当前 Token 用量或请求次数已达该密钥的配额(quota)上限,请增加该密钥的配额或稍后再试",
+ "PermissionDenied": "很抱歉,你没有权限访问该服务,请检查你的密钥是否有访问权限",
"InvalidProviderAPIKey": "{{provider}} API Key 不正确或为空,请检查 {{provider}} API Key 后重试",
"ProviderBizError": "请求 {{provider}} 服务出错,请根据以下信息排查或重试",
"NoOpenAIAPIKey": "OpenAI API Key 不正确或为空,请添加自定义 OpenAI API Key",
- "OpenAIBizError": "请求 OpenAI 服务出错,请根据以下信息排查或重试",
+ "InvalidVertexCredentials": "Vertex 鉴权未通过,请检查鉴权凭证后重试",
"InvalidBedrockCredentials": "Bedrock 鉴权未通过,请检查 AccessKeyId/SecretAccessKey 后重试",
"StreamChunkError": "流式请求的消息块解析错误,请检查当前 API 接口是否符合标准规范,或联系你的 API 供应商咨询",
"UnknownChatFetchError": "很抱歉,遇到未知请求错误,请根据以下信息排查或重试",
@@ -82,8 +102,9 @@
"OllamaServiceUnavailable": "Ollama 服务连接失败,请检查 Ollama 是否运行正常,或是否正确设置 Ollama 的跨域配置",
"AgentRuntimeError": "Lobe AI Runtime 执行出错,请根据以下信息排查或重试",
"FreePlanLimit": "当前为免费用户,无法使用该功能,请升级到付费计划后继续使用",
- "SubscriptionPlanLimit": "您的订阅额度已用尽,无法使用该功能,请升级到更高计划,或购买资源包后继续使用",
- "InvalidGithubToken": "Github PAT 不正确或为空,请检查 Github PAT 后重试"
+ "SubscriptionPlanLimit": "您的订阅积分已用尽,无法使用该功能,请升级到更高计划,或配置自定义模型 API 后继续使用",
+ "InvalidGithubToken": "Github PAT 不正确或为空,请检查 Github PAT 后重试",
+ "ConnectionCheckFailed": "请求返回为空,请检查 API 代理地址末尾是否未包含 `/v1`"
},
"stt": {
"responseError": "服务请求失败,请检查配置或重试"
diff --git a/DigitalHumanWeb/locales/zh-CN/file.json b/DigitalHumanWeb/locales/zh-CN/file.json
index 236c7d7..134eed4 100644
--- a/DigitalHumanWeb/locales/zh-CN/file.json
+++ b/DigitalHumanWeb/locales/zh-CN/file.json
@@ -91,4 +91,4 @@
"uploading": "正在上传"
}
}
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/knowledgeBase.json b/DigitalHumanWeb/locales/zh-CN/knowledgeBase.json
index 63a5c45..2773110 100644
--- a/DigitalHumanWeb/locales/zh-CN/knowledgeBase.json
+++ b/DigitalHumanWeb/locales/zh-CN/knowledgeBase.json
@@ -29,4 +29,4 @@
"testing": "召回测试"
},
"title": "知识库"
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/metadata.json b/DigitalHumanWeb/locales/zh-CN/metadata.json
index a6fa05b..eaef354 100644
--- a/DigitalHumanWeb/locales/zh-CN/metadata.json
+++ b/DigitalHumanWeb/locales/zh-CN/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "持续追踪 {{appName}} 的新功能和改进",
+ "title": "更新日志"
+ },
"chat": {
"description": "{{appName}} 带给你最好的 ChatGPT, Claude , Gemini, OLLaMA WebUI 使用体验",
"title": "{{appName}}:个人 AI 效能工具,给自己一个更聪明的大脑"
@@ -32,4 +36,4 @@
"description": "{{appName}} 带给你最好的 ChatGPT, Claude , Gemini, OLLaMA WebUI 使用体验",
"title": "欢迎使用 {{appName}}:个人 AI 效能工具,给自己一个更聪明的大脑"
}
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/migration.json b/DigitalHumanWeb/locales/zh-CN/migration.json
index 3c92fe6..1d88055 100644
--- a/DigitalHumanWeb/locales/zh-CN/migration.json
+++ b/DigitalHumanWeb/locales/zh-CN/migration.json
@@ -42,4 +42,4 @@
"missVersion": "导入数据缺少版本号,请检查文件后重试",
"noMigration": "没有找到当前版本对应的迁移方案,请检查版本号后重试。如仍有问题请提交问题反馈"
}
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/modelProvider.json b/DigitalHumanWeb/locales/zh-CN/modelProvider.json
index 760c210..060bbbd 100644
--- a/DigitalHumanWeb/locales/zh-CN/modelProvider.json
+++ b/DigitalHumanWeb/locales/zh-CN/modelProvider.json
@@ -19,9 +19,27 @@
"title": "API Key"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Azure 的 API 版本,遵循 YYYY-MM-DD 格式,查阅[最新版本](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "获取列表",
+ "title": "Azure API Version"
+ },
+ "endpoint": {
+ "desc": "从 Azure AI 项目概述找到 Azure AI 模型推理终结点",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AI 终结点"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "从 Azure AI 项目概述找到 API 密钥",
+ "placeholder": "Azure 密钥",
+ "title": "密钥"
+ }
+ },
"bedrock": {
"accessKeyId": {
- "desc": "填入AWS Access Key Id",
+ "desc": "填入 AWS Access Key Id",
"placeholder": "AWS Access Key Id",
"title": "AWS Access Key Id"
},
@@ -51,13 +69,89 @@
"title": "使用自定义 Bedrock 鉴权信息"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "请填写 Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "填入 Cloudflare 账户 ID 或 自定义 API 地址",
+ "placeholder": "Cloudflare Account ID / custom API URL",
+ "title": "Cloudflare 账户 ID / API 地址"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "请填写你的 API Key",
+ "title": "API Key"
+ },
+ "basicTitle": "基本信息",
+ "configTitle": "配置信息",
+ "confirm": "新建",
+ "createSuccess": "新建成功",
+ "description": {
+ "placeholder": "服务商简介(选填)",
+ "title": "服务商简介"
+ },
+ "id": {
+ "desc": "作为服务商唯一标识,创建后将不可修改",
+ "format": "只能包含数字、小写字母、连字符(-)和下划线(_)",
+ "placeholder": "例如 openai、gemini 等",
+ "required": "请填写服务商 ID",
+ "title": "服务商 ID"
+ },
+ "logo": {
+ "required": "请上传正确的服务商 Logo",
+ "title": "服务商 Logo"
+ },
+ "name": {
+ "placeholder": "请输入服务商的展示名称",
+ "required": "请填写服务商名称",
+ "title": "服务商名称"
+ },
+ "proxyUrl": {
+ "required": "请填写代理地址",
+ "title": "代理地址"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "请选择 SDK 类型",
+ "title": "请求格式"
+ },
+ "title": "创建自定义 AI 服务商"
+ },
"github": {
"personalAccessToken": {
- "desc": "填入你的 Github PAT,点击[这里](https://github.com/settings/tokens) 创建",
+ "desc": "填入你的 Github PAT,点击 [这里](https://github.com/settings/tokens) 创建",
"placeholder": "ghp_xxxxxx",
"title": "Github PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "填入你的 HuggingFace Token,点击 [这里](https://huggingface.co/settings/tokens) 创建",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace Token"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "未启用服务商",
+ "enabled": "已启用服务商"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "添加自定义服务商",
+ "all": "全部",
+ "list": {
+ "disabled": "未启用",
+ "enabled": "已启用"
+ },
+ "notFound": "未找到搜索结果",
+ "searchProviders": "搜索服务商...",
+ "sort": "自定义排序"
+ },
"ollama": {
"checker": {
"desc": "测试代理地址是否正确填写",
@@ -75,33 +169,9 @@
"title": "正在下载模型 {{model}} "
},
"endpoint": {
- "desc": "填入 Ollama 接口代理地址,本地未额外指定可留空",
+ "desc": "必须包含http(s)://,本地未额外指定可留空",
"title": "Ollama 服务地址"
},
- "setup": {
- "cors": {
- "description": "因浏览器安全限制,你需要为 Ollama 进行跨域配置后方可正常使用。",
- "linux": {
- "env": "在 [Service] 部分下添加 `Environment`,添加 OLLAMA_ORIGINS 环境变量:",
- "reboot": "重载 systemd 并重启 Ollama",
- "systemd": "调用 systemd 编辑 ollama 服务:"
- },
- "macos": "请打开「终端」应用程序,并粘贴以下指令,并按回车运行",
- "reboot": "请在执行完成后重启 Ollama 服务",
- "title": "配置 Ollama 允许跨域访问",
- "windows": "在 Windows 上,点击「控制面板」,进入编辑系统环境变量。为您的用户账户新建名为 「OLLAMA_ORIGINS」 的环境变量,值为 * ,点击 「OK/应用」 保存"
- },
- "install": {
- "description": "请确认你已经开启 Ollama ,如果没有下载 Ollama ,请前往官网<1>下载1>",
- "docker": "如果你更倾向于使用 Docker,Ollama 也提供了官方 Docker 镜像,你可以通过以下命令拉取:",
- "linux": {
- "command": "通过以下命令安装:",
- "manual": "或者,你也可以参考 <1>Linux 手动安装指南1> 自行安装"
- },
- "title": "在本地安装并开启 Ollama 应用",
- "windowsTab": "Windows (预览版)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "取消下载",
@@ -112,6 +182,156 @@
"title": "下载指定的 Ollama 模型"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "您的秘钥与代理地址等将使用 <1>AES-GCM1> 加密算法进行加密",
+ "apiKey": {
+ "desc": "请填写你的 {{name}} API Key",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "必须包含 http(s)://",
+ "invalid": "请输入合法的 URL",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API 代理地址"
+ },
+ "checker": {
+ "button": "检查",
+ "desc": "测试 Api Key 与代理地址是否正确填写",
+ "pass": "检查通过",
+ "title": "连通性检查"
+ },
+ "fetchOnClient": {
+ "desc": "客户端请求模式将从浏览器直接发起会话请求,可提升响应速度",
+ "title": "使用客户端请求模式"
+ },
+ "helpDoc": "配置教程",
+ "waitingForMore": "更多模型正在 <1>计划接入1> 中,敬请期待"
+ },
+ "createNew": {
+ "title": "创建自定义 AI 模型"
+ },
+ "item": {
+ "config": "配置模型",
+ "customModelCards": {
+ "addNew": "创建并添加 {{id}} 模型",
+ "confirmDelete": "即将删除该自定义模型,删除后将不可恢复,请谨慎操作。"
+ },
+ "delete": {
+ "confirm": "确认删除模型 {{displayName}}?",
+ "success": "删除成功",
+ "title": "删除模型"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "在 Azure OpenAI 中实际请求的字段",
+ "placeholder": "请输入 Azure 中的模型部署名称",
+ "title": "模型部署名称"
+ },
+ "deployName": {
+ "extra": "发送请求时会将该字段作为模型 ID",
+ "placeholder": "请输入模型实际部署的名称或 id",
+ "title": "模型部署名称"
+ },
+ "displayName": {
+ "placeholder": "请输入模型的展示名称,例如 ChatGPT、GPT-4 等",
+ "title": "模型展示名称"
+ },
+ "files": {
+ "extra": "当前文件上传实现仅为一种 Hack 方案,仅限自行尝试。完整文件上传能力请等待后续实现",
+ "title": "支持文件上传"
+ },
+ "functionCall": {
+ "extra": "此配置将仅开启模型使用工具的能力,进而可以为模型添加工具类的插件。但是否支持真正使用工具完全取决于模型本身,请自行测试的可用性",
+ "title": "支持工具使用"
+ },
+ "id": {
+ "extra": "创建后不可修改,调用 AI 时将作为模型 id 使用",
+ "placeholder": "请输入模型 id,例如 gpt-4o 或 claude-3.5-sonnet",
+ "title": "模型 ID"
+ },
+ "modalTitle": "自定义模型配置",
+ "reasoning": {
+ "extra": "此配置将仅开启模型深度思考的能力,具体效果完全取决于模型本身,请自行测试该模型是否具备可用的深度思考能力",
+ "title": "支持深度思考"
+ },
+ "tokens": {
+ "extra": "设置模型支持的最大 Token 数",
+ "title": "最大上下文窗口",
+ "unlimited": "无限制"
+ },
+ "vision": {
+ "extra": "此配置将仅开启应用中的图片上传配置,是否支持识别完全取决于模型本身,请自行测试该模型的视觉识别能力可用性",
+ "title": "支持视觉识别"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/图片",
+ "inputCharts": "${{amount}}/M 字符",
+ "inputMinutes": "${{amount}}/分钟",
+ "inputTokens": "输入 ${{amount}}/M",
+ "outputTokens": "输出 ${{amount}}/M"
+ },
+ "releasedAt": "发布于{{releasedAt}}"
+ },
+ "list": {
+ "addNew": "添加模型",
+ "disabled": "未启用",
+ "disabledActions": {
+ "showMore": "显示全部"
+ },
+ "empty": {
+ "desc": "请创建自定义模型或拉取模型后开始使用吧",
+ "title": "暂无可用模型"
+ },
+ "enabled": "已启用",
+ "enabledActions": {
+ "disableAll": "全部禁用",
+ "enableAll": "全部启用",
+ "sort": "自定义模型排序"
+ },
+ "enabledEmpty": "暂无启用模型,请从下方列表中启用心仪的模型吧~",
+ "fetcher": {
+ "clear": "清除获取的模型",
+ "fetch": "获取模型列表",
+ "fetching": "正在获取模型列表...",
+ "latestTime": "上次更新时间:{{time}}",
+ "noLatestTime": "暂未获取列表"
+ },
+ "resetAll": {
+ "conform": "确认重置当前模型的所有修改?重置后当前模型列表将会回到默认状态",
+ "success": "重置成功",
+ "title": "重置所有修改"
+ },
+ "search": "搜索模型...",
+ "searchResult": "搜索到 {{count}} 个模型",
+ "title": "模型列表",
+ "total": "共 {{count}} 个模型可用"
+ },
+ "searchNotFound": "未找到搜索结果"
+ },
+ "sortModal": {
+ "success": "排序更新成功",
+ "title": "自定义排序",
+ "update": "更新"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "即将删除该 AI 服务商,删除后将无法找回,确认是否删除?",
+ "deleteSuccess": "删除成功",
+ "tooltip": "更新服务商基础配置",
+ "updateSuccess": "更新成功"
+ },
+ "updateCustomAiProvider": {
+ "title": "更新自定义 AI 服务商配置"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "填入你的 Vertex Ai Keys",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI Keys"
+ }
+ },
"zeroone": {
"title": "01.AI 零一万物"
},
diff --git a/DigitalHumanWeb/locales/zh-CN/models.json b/DigitalHumanWeb/locales/zh-CN/models.json
index a6f862c..c0a7928 100644
--- a/DigitalHumanWeb/locales/zh-CN/models.json
+++ b/DigitalHumanWeb/locales/zh-CN/models.json
@@ -1,9 +1,18 @@
{
"01-ai/Yi-1.5-34B-Chat-16K": {
- "description": "Yi-1.5 34B, 以丰富的训练样本在行业应用中提供优越表现。"
+ "description": "Yi-1.5-34B-Chat-16K 是 Yi-1.5 系列的一个变体,属于开源聊天模型。Yi-1.5 是 Yi 的升级版本,在 500B 个高质量语料上进行了持续预训练,并在 3M 多样化的微调样本上进行了微调。相比于 Yi,Yi-1.5 在编码、数学、推理和指令遵循能力方面表现更强,同时保持了出色的语言理解、常识推理和阅读理解能力。该模型在大多数基准测试中与更大的模型相当或表现更佳,具有 16K 的上下文长度"
+ },
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat 是 Yi-1.5 系列的一个变体,属于开源聊天模型。Yi-1.5 是 Yi 的升级版本,在 500B 个高质量语料上进行了持续预训练,并在 3M 多样化的微调样本上进行了微调。相比于 Yi,Yi-1.5 在编码、数学、推理和指令遵循能力方面表现更强,同时保持了出色的语言理解、常识推理和阅读理解能力。该模型具有 4K、16K 和 32K 的上下文长度版本,预训练总量达到 3.6T 个 token"
},
"01-ai/Yi-1.5-9B-Chat-16K": {
- "description": "Yi-1.5 9B 支持16K Tokens, 提供高效、流畅的语言生成能力。"
+ "description": "Yi-1.5-9B-Chat-16K 是 Yi-1.5 系列的一个变体,属于开源聊天模型。Yi-1.5 是 Yi 的升级版本,在 500B 个高质量语料上进行了持续预训练,并在 3M 多样化的微调样本上进行了微调。相比于 Yi,Yi-1.5 在编码、数学、推理和指令遵循能力方面表现更强,同时保持了出色的语言理解、常识推理和阅读理解能力。该模型在同等规模的开源模型中表现最佳"
+ },
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "零一万物,最新开源微调模型,340亿参数,微调支持多种对话场景,高质量训练数据,对齐人类偏好。"
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "零一万物,最新开源微调模型,90亿参数,微调支持多种对话场景,高质量训练数据,对齐人类偏好。"
},
"360gpt-pro": {
"description": "360GPT Pro 作为 360 AI 模型系列的重要成员,以高效的文本处理能力满足多样化的自然语言应用场景,支持长文本理解和多轮对话等功能。"
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K 强调语义安全和责任导向,专为对内容安全有高度要求的应用场景设计,确保用户体验的准确性与稳健性。"
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 使用树搜索构建思维链,并引入了反思机制,使用强化学习训练,模型具备自我反思与纠错的能力。"
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro 是 360 公司推出的高级自然语言处理模型,具备卓越的文本生成和理解能力,尤其在生成与创作领域表现出色,能够处理复杂的语言转换和角色演绎任务。"
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 使用树搜索构建思维链,并引入了反思机制,使用强化学习训练,模型具备自我反思与纠错的能力。"
+ },
"4.0Ultra": {
"description": "Spark Ultra 是星火大模型系列中最为强大的版本,在升级联网搜索链路同时,提升对文本内容的理解和总结能力。它是用于提升办公生产力和准确响应需求的全方位解决方案,是引领行业的智能产品。"
},
@@ -32,74 +47,341 @@
"Baichuan4": {
"description": "模型能力国内第一,在知识百科、长文本、生成创作等中文任务上超越国外主流模型。还具备行业领先的多模态能力,多项权威评测基准表现优异。"
},
+ "Baichuan4-Air": {
+ "description": "模型能力国内第一,在知识百科、长文本、生成创作等中文任务上超越国外主流模型。还具备行业领先的多模态能力,多项权威评测基准表现优异。"
+ },
+ "Baichuan4-Turbo": {
+ "description": "模型能力国内第一,在知识百科、长文本、生成创作等中文任务上超越国外主流模型。还具备行业领先的多模态能力,多项权威评测基准表现优异。"
+ },
+ "DeepSeek-R1": {
+ "description": "最先进的高效 LLM,擅长推理、数学和编程。"
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1——DeepSeek 套件中更大更智能的模型——被蒸馏到 Llama 70B 架构中。基于基准测试和人工评估,该模型比原始 Llama 70B 更智能,尤其在需要数学和事实精确性的任务上表现出色。"
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "基于 Qwen2.5-Math-1.5B 的 DeepSeek-R1 蒸馏模型,通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆。"
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "基于 Qwen2.5-14B 的 DeepSeek-R1 蒸馏模型,通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆。"
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1 系列通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆,超越 OpenAI-o1-mini 水平。"
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "基于 Qwen2.5-Math-7B 的 DeepSeek-R1 蒸馏模型,通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆。"
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro 全新升级的多模态大模型,支持任意分辨率和极端长宽比图像识别,增强视觉推理、文档识别、细节信息理解和指令遵循能力。"
+ },
+ "Doubao-lite-128k": {
+ "description": "拥有极致的响应速度,更好的性价比,为客户不同场景提供更灵活的选择。支持 128k 上下文窗口的推理和精调。"
+ },
+ "Doubao-lite-32k": {
+ "description": "拥有极致的响应速度,更好的性价比,为客户不同场景提供更灵活的选择。支持 32k 上下文窗口的推理和精调。"
+ },
+ "Doubao-lite-4k": {
+ "description": "拥有极致的响应速度,更好的性价比,为客户不同场景提供更灵活的选择。支持 4k 上下文窗口的推理和精调。"
+ },
+ "Doubao-pro-128k": {
+ "description": "效果最好的主力模型,适合处理复杂任务,在参考问答、总结摘要、创作、文本分类、角色扮演等场景都有很好的效果。支持 128k 上下文窗口的推理和精调。"
+ },
+ "Doubao-pro-256k": {
+ "description": "效果最好的主力模型,适合处理复杂任务,在参考问答、总结摘要、创作、文本分类、角色扮演等场景都有很好的效果。支持 256k 上下文窗口的推理和精调。"
+ },
+ "Doubao-pro-32k": {
+ "description": "效果最好的主力模型,适合处理复杂任务,在参考问答、总结摘要、创作、文本分类、角色扮演等场景都有很好的效果。支持 32k 上下文窗口的推理和精调。"
+ },
+ "Doubao-pro-4k": {
+ "description": "效果最好的主力模型,适合处理复杂任务,在参考问答、总结摘要、创作、文本分类、角色扮演等场景都有很好的效果。支持 4k 上下文窗口的推理和精调。"
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Doubao-vision 模型是豆包推出的多模态大模型,具备强大的图片理解与推理能力,以及精准的指令理解能力。模型在图像文本信息抽取、基于图像的推理任务上有展现出了强大的性能,能够应用于更复杂、更广泛的视觉问答任务。"
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Doubao-vision 模型是豆包推出的多模态大模型,具备强大的图片理解与推理能力,以及精准的指令理解能力。模型在图像文本信息抽取、基于图像的推理任务上有展现出了强大的性能,能够应用于更复杂、更广泛的视觉问答任务。"
+ },
+ "ERNIE-3.5-128K": {
+ "description": "百度自研的旗舰级大规模⼤语⾔模型,覆盖海量中英文语料,具有强大的通用能力,可满足绝大部分对话问答、创作生成、插件应用场景要求;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ERNIE-3.5-8K": {
+ "description": "百度自研的旗舰级大规模⼤语⾔模型,覆盖海量中英文语料,具有强大的通用能力,可满足绝大部分对话问答、创作生成、插件应用场景要求;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "百度自研的旗舰级大规模⼤语⾔模型,覆盖海量中英文语料,具有强大的通用能力,可满足绝大部分对话问答、创作生成、插件应用场景要求;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,相较ERNIE 3.5实现了模型能力全面升级,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,相较ERNIE 3.5实现了模型能力全面升级,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,综合效果表现出色,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。相较于ERNIE 4.0在性能表现上更优秀"
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,综合效果表现出色,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。相较于ERNIE 4.0在性能表现上更优秀"
+ },
+ "ERNIE-Character-8K": {
+ "description": "百度自研的垂直场景大语言模型,适合游戏NPC、客服对话、对话角色扮演等应用场景,人设风格更为鲜明、一致,指令遵循能力更强,推理性能更优。"
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "百度自研的轻量级大语言模型,兼顾优异的模型效果与推理性能,效果比ERNIE Lite更优,适合低算力AI加速卡推理使用。"
+ },
+ "ERNIE-Speed-128K": {
+ "description": "百度2024年最新发布的自研高性能大语言模型,通用能力优异,适合作为基座模型进行精调,更好地处理特定场景问题,同时具备极佳的推理性能。"
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "百度2024年最新发布的自研高性能大语言模型,通用能力优异,效果比ERNIE Speed更优,适合作为基座模型进行精调,更好地处理特定场景问题,同时具备极佳的推理性能。"
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) 是一种创新模型,适合多领域应用和复杂任务。"
},
- "Max-32k": {
- "description": "Spark Max 32K 配置了大上下文处理能力,更强的上下文理解和逻辑推理能力,支持32K tokens的文本输入,适用于长文档阅读、私有知识问答等场景"
+ "InternVL2-8B": {
+ "description": "InternVL2-8B 是一款强大的视觉语言模型,支持图像与文本的多模态处理,能够精确识别图像内容并生成相关描述或回答。"
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B 是一款强大的视觉语言模型,支持图像与文本的多模态处理,能够精确识别图像内容并生成相关描述或回答。"
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "在高分辨率图像上表现出色的图像推理能力,适用于视觉理解应用。"
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "适用于视觉理解代理应用的高级图像推理能力。"
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct 是阿里云发布的最新大语言模型系列之一。该 72B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct 是阿里云发布的最新大语言模型系列之一。该 7B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Llama 3.1指令调优的文本模型,针对多语言对话用例进行了优化,在许多可用的开源和封闭聊天模型中,在常见行业基准上表现优异。"
+ },
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Llama 3.1指令调优的文本模型,针对多语言对话用例进行了优化,在许多可用的开源和封闭聊天模型中,在常见行业基准上表现优异。"
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO 是一款高度灵活的多模型合并,旨在提供卓越的创造性体验。"
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Llama 3.1指令调优的文本模型,针对多语言对话用例进行了优化,在许多可用的开源和封闭聊天模型中,在常见行业基准上表现优异。"
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "先进的最尖端小型语言模型,具备语言理解、卓越的推理能力和文本生成能力。"
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "先进的最尖端小型语言模型,具备语言理解、卓越的推理能力和文本生成能力。"
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先进的多语言开源大型语言模型,以极低成本体验媲美 405B 模型的性能。基于 Transformer 结构,并通过监督微调(SFT)和人类反馈强化学习(RLHF)提升有用性和安全性。其指令调优版本专为多语言对话优化,在多项行业基准上表现优于众多开源和封闭聊天模型。知识截止日期为 2023 年 12 月"
+ },
+ "MiniMax-Text-01": {
+ "description": "在 MiniMax-01系列模型中,我们做了大胆创新:首次大规模实现线性注意力机制,传统 Transformer架构不再是唯一的选择。这个模型的参数量高达4560亿,其中单次激活459亿。模型综合性能比肩海外顶尖模型,同时能够高效处理全球最长400万token的上下文,是GPT-4o的32倍,Claude-3.5-Sonnet的20倍。"
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) 是高精度的指令模型,适用于复杂计算。"
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) 提供优化的语言输出和多样化的应用可能。"
- },
- "Phi-3-5-mini-instruct": {
- "description": "Refresh of Phi-3-mini model."
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2-26B 是 InternVL 2.0 系列多模态大语言模型中的一员。该模型由 InternViT-6B-448px-V1-5 视觉模型、MLP 投影层和 internlm2-chat-20b 语言模型组成。它在各种视觉语言任务上展现出了卓越的性能,包括文档和图表理解、场景文本理解、OCR、科学和数学问题解决等。InternVL2-26B 使用 8K 上下文窗口训练,能够处理长文本、多图像和视频输入,显著提升了模型在这些任务上的处理能力"
},
"Phi-3-medium-128k-instruct": {
- "description": "Same Phi-3-medium model, but with a larger context size for RAG or few shot prompting."
+ "description": "相同的Phi-3-medium模型,但具有更大的上下文大小,适用于RAG或少量提示。"
},
"Phi-3-medium-4k-instruct": {
- "description": "A 14B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data."
+ "description": "一个140亿参数模型,质量优于Phi-3-mini,重点关注高质量、推理密集型数据。"
},
"Phi-3-mini-128k-instruct": {
- "description": "Same Phi-3-mini model, but with a larger context size for RAG or few shot prompting."
+ "description": "相同的Phi-3-mini模型,但具有更大的上下文大小,适用于RAG或少量提示。"
},
"Phi-3-mini-4k-instruct": {
- "description": "Tiniest member of the Phi-3 family. Optimized for both quality and low latency."
+ "description": "Phi-3家族中最小的成员,针对质量和低延迟进行了优化。"
},
"Phi-3-small-128k-instruct": {
- "description": "Same Phi-3-small model, but with a larger context size for RAG or few shot prompting."
+ "description": "相同的Phi-3-small模型,但具有更大的上下文大小,适用于RAG或少量提示。"
},
"Phi-3-small-8k-instruct": {
- "description": "A 7B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data."
+ "description": "一个70亿参数模型,质量优于Phi-3-mini,重点关注高质量、推理密集型数据。"
},
- "Pro-128k": {
- "description": "Spark Pro 128K 配置了特大上下文处理能力,能够处理多达128K的上下文信息,特别适合需通篇分析和长期逻辑关联处理的长文内容,可在复杂文本沟通中提供流畅一致的逻辑与多样的引用支持。"
+ "Phi-3.5-mini-instruct": {
+ "description": "Phi-3-mini模型的更新版。"
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Phi-3-vision模型的更新版。"
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2-8B 是 InternVL 2.0 系列多模态大语言模型中的一员。该模型由 InternViT-300M-448px 视觉模型、MLP 投影层和 internlm2_5-7b-chat 语言模型组成。它在各种视觉语言任务上展现出了卓越的性能,包括文档和图表理解、场景文本理解、OCR、科学和数学问题解决等。InternVL2-8B 使用 8K 上下文窗口训练,能够处理长文本、多图像和视频输入,显著提升了模型在这些任务上的处理能力"
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct 是 Qwen2 系列中的指令微调大语言模型,参数规模为 1.5B。该模型基于 Transformer 架构,采用了 SwiGLU 激活函数、注意力 QKV 偏置和组查询注意力等技术。它在语言理解、生成、多语言能力、编码、数学和推理等多个基准测试中表现出色,超越了大多数开源模型。与 Qwen1.5-1.8B-Chat 相比,Qwen2-1.5B-Instruct 在 MMLU、HumanEval、GSM8K、C-Eval 和 IFEval 等测试中均显示出显著的性能提升,尽管参数量略少"
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct 是 Qwen2 系列中的指令微调大语言模型,参数规模为 7B。该模型基于 Transformer 架构,采用了 SwiGLU 激活函数、注意力 QKV 偏置和组查询注意力等技术。它能够处理大规模输入。该模型在语言理解、生成、多语言能力、编码、数学和推理等多个基准测试中表现出色,超越了大多数开源模型,并在某些任务上展现出与专有模型相当的竞争力。Qwen2-7B-Instruct 在多项评测中均优于 Qwen1.5-7B-Chat,显示出显著的性能提升"
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL-7B-Instruct 是 Qwen-VL 模型的最新迭代版本,在视觉理解基准测试中达到了最先进的性能,包括 MathVista、DocVQA、RealWorldQA 和 MTVQA 等。Qwen2-VL 能够用于高质量的基于视频的问答、对话和内容创作,还具备复杂推理和决策能力,可以与移动设备、机器人等集成,基于视觉环境和文本指令进行自动操作。除了英语和中文,Qwen2-VL 现在还支持理解图像中不同语言的文本,包括大多数欧洲语言、日语、韩语、阿拉伯语和越南语等"
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "Qwen 1.5 Chat (110B) 是一款高效能的对话模型,支持复杂对话场景。"
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct 是阿里云发布的最新大语言模型系列之一。该 7B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) 提供快速响应和自然对话能力,适合多语言环境。"
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct 是阿里云发布的代码特定大语言模型系列的最新版本。该模型在 Qwen2.5 的基础上,通过 5.5 万亿个 tokens 的训练,显著提升了代码生成、推理和修复能力。它不仅增强了编码能力,还保持了数学和通用能力的优势。模型为代码智能体等实际应用提供了更全面的基础"
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat 是智谱 AI 推出的 GLM-4 系列预训练模型中的开源版本。该模型在语义、数学、推理、代码和知识等多个方面表现出色。除了支持多轮对话外,GLM-4-9B-Chat 还具备网页浏览、代码执行、自定义工具调用(Function Call)和长文本推理等高级功能。模型支持 26 种语言,包括中文、英文、日语、韩语和德语等。在多项基准测试中,GLM-4-9B-Chat 展现了优秀的性能,如 AlignBench-v2、MT-Bench、MMLU 和 C-Eval 等。该模型支持最大 128K 的上下文长度,适用于学术研究和商业应用"
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 是一款强化学习(RL)驱动的推理模型,解决了模型中的重复性和可读性问题。在 RL 之前,DeepSeek-R1 引入了冷启动数据,进一步优化了推理性能。它在数学、代码和推理任务中与 OpenAI-o1 表现相当,并且通过精心设计的训练方法,提升了整体效果。"
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 是一款拥有 6710 亿参数的混合专家(MoE)语言模型,采用多头潜在注意力(MLA)和 DeepSeekMoE 架构,结合无辅助损失的负载平衡策略,优化推理和训练效率。通过在 14.8 万亿高质量tokens上预训练,并进行监督微调和强化学习,DeepSeek-V3 在性能上超越其他开源模型,接近领先闭源模型。"
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma 是 Google 开发的轻量级、最先进的开放模型系列之一。它是一个仅解码器的大型语言模型,支持英语,提供开放权重、预训练变体和指令微调变体。Gemma 模型适用于各种文本生成任务,包括问答、摘要和推理。该 9B 模型是通过 8 万亿个 tokens 训练而成。其相对较小的规模使其可以在资源有限的环境中部署,如笔记本电脑、台式机或您自己的云基础设施,从而使更多人能够访问最先进的 AI 模型并促进创新"
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 是由 Meta 开发的多语言大型语言模型家族,包括 8B、70B 和 405B 三种参数规模的预训练和指令微调变体。该 8B 指令微调模型针对多语言对话场景进行了优化,在多项行业基准测试中表现优异。模型训练使用了超过 15 万亿个 tokens 的公开数据,并采用了监督微调和人类反馈强化学习等技术来提升模型的有用性和安全性。Llama 3.1 支持文本生成和代码生成,知识截止日期为 2023 年 12 月"
+ },
+ "QwQ-32B-Preview": {
+ "description": "Qwen QwQ 是由 Qwen 团队开发的实验研究模型,专注于提升AI推理能力。"
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview 是由 Qwen 团队开发的专注于视觉推理能力的研究型模型,其在复杂场景理解和解决视觉相关的数学问题方面具有独特优势。"
+ },
+ "Qwen/QwQ-32B": {
+ "description": "QwQ 是 Qwen 系列的推理模型。与传统的指令调优模型相比,QwQ 具备思考和推理能力,能够在下游任务中实现显著增强的性能,尤其是在解决困难问题方面。QwQ-32B 是中型推理模型,能够在与最先进的推理模型(如 DeepSeek-R1、o1-mini)的对比中取得有竞争力的性能。该模型采用 RoPE、SwiGLU、RMSNorm 和 Attention QKV bias 等技术,具有 64 层网络结构和 40 个 Q 注意力头(GQA 架构中 KV 为 8 个)。"
+ },
+ "Qwen/QwQ-32B-Preview": {
+ "description": "Qwen QwQ 是由 Qwen 团队开发的实验研究模型,专注于提升AI推理能力。"
+ },
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct 是 Qwen2 系列中的指令微调大语言模型,参数规模为 1.5B。该模型基于 Transformer 架构,采用了 SwiGLU 激活函数、注意力 QKV 偏置和组查询注意力等技术。它在语言理解、生成、多语言能力、编码、数学和推理等多个基准测试中表现出色,超越了大多数开源模型。与 Qwen1.5-1.8B-Chat 相比,Qwen2-1.5B-Instruct 在 MMLU、HumanEval、GSM8K、C-Eval 和 IFEval 等测试中均显示出显著的性能提升,尽管参数量略少"
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen 2 Instruct (72B) 为企业级应用提供精准的指令理解和响应。"
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct 是 Qwen2 系列中的指令微调大语言模型,参数规模为 7B。该模型基于 Transformer 架构,采用了 SwiGLU 激活函数、注意力 QKV 偏置和组查询注意力等技术。它能够处理大规模输入。该模型在语言理解、生成、多语言能力、编码、数学和推理等多个基准测试中表现出色,超越了大多数开源模型,并在某些任务上展现出与专有模型相当的竞争力。Qwen2-7B-Instruct 在多项评测中均优于 Qwen1.5-7B-Chat,显示出显著的性能提升"
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL 是 Qwen-VL 模型的最新迭代版本,在视觉理解基准测试中达到了最先进的性能,包括 MathVista、DocVQA、RealWorldQA 和 MTVQA 等。Qwen2-VL 能够理解超过 20 分钟的视频,用于高质量的基于视频的问答、对话和内容创作。它还具备复杂推理和决策能力,可以与移动设备、机器人等集成,基于视觉环境和文本指令进行自动操作。除了英语和中文,Qwen2-VL 现在还支持理解图像中不同语言的文本,包括大多数欧洲语言、日语、韩语、阿拉伯语和越南语等"
+ },
"Qwen/Qwen2.5-14B-Instruct": {
- "description": "Qwen2.5 是全新的大型语言模型系列,旨在优化指令式任务的处理。"
+ "description": "Qwen2.5-14B-Instruct 是阿里云发布的最新大语言模型系列之一。该 14B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
},
"Qwen/Qwen2.5-32B-Instruct": {
- "description": "Qwen2.5 是全新的大型语言模型系列,旨在优化指令式任务的处理。"
+ "description": "Qwen2.5-32B-Instruct 是阿里云发布的最新大语言模型系列之一。该 32B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5 是全新的大型语言模型系列,具有更强的理解和生成能力。"
+ "description": "Qwen2.5-72B-Instruct 是阿里云发布的最新大语言模型系列之一。该 72B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5-72B-Instruct 是阿里云发布的最新大语言模型系列之一。该 72B 模型在编码和数学等领域具有显著改进的能力。它支持长达 128K tokens 的输入,可以生成超过 8K tokens 的长文本。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 是全新的大型语言模型系列,旨在优化指令式任务的处理。"
},
"Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct 是阿里云发布的最新大语言模型系列之一。该 7B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
+ },
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
"description": "Qwen2.5 是全新的大型语言模型系列,旨在优化指令式任务的处理。"
},
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct 是阿里云发布的代码特定大语言模型系列的最新版本。该模型在 Qwen2.5 的基础上,通过 5.5 万亿个 tokens 的训练,显著提升了代码生成、推理和修复能力。它不仅增强了编码能力,还保持了数学和通用能力的优势。模型为代码智能体等实际应用提供了更全面的基础"
+ },
"Qwen/Qwen2.5-Coder-7B-Instruct": {
- "description": "Qwen2.5-Coder 专注于代码编写。"
+ "description": "Qwen2.5-Coder-7B-Instruct 是阿里云发布的代码特定大语言模型系列的最新版本。该模型在 Qwen2.5 的基础上,通过 5.5 万亿个 tokens 的训练,显著提升了代码生成、推理和修复能力。它不仅增强了编码能力,还保持了数学和通用能力的优势。模型为代码智能体等实际应用提供了更全面的基础"
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 是 Qwen 模型的最新系列,支持 128k 上下文,对比当前最优的开源模型,Qwen2-72B 在自然语言理解、知识、代码、数学及多语言等多项能力上均显著超越当前领先的模型。"
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 是 Qwen 模型的最新系列,能够超越同等规模的最优开源模型甚至更大规模的模型,Qwen2 7B 在多个评测上取得显著的优势,尤其是代码及中文理解上。"
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B是一款强大的视觉语言模型,支持图像与文本的多模态处理,能够精确识别图像内容并生成相关描述或回答。"
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct 是一款 140 亿参数的大语言模型,性能表现优秀,优化中文和多语言场景,支持智能问答、内容生成等应用。"
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct 是一款 320 亿参数的大语言模型,性能表现均衡,优化中文和多语言场景,支持智能问答、内容生成等应用。"
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "面向中文和英文的 LLM,针对语言、编程、数学、推理等领域。"
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct 是一款 70 亿参数的大语言模型,支持 function call 与外部系统无缝交互,极大提升了灵活性和扩展性。优化中文和多语言场景,支持智能问答、内容生成等应用。"
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct 是一款基于大规模预训练的编程指令模型,具备强大的代码理解和生成能力,能够高效地处理各种编程任务,特别适合智能代码编写、自动化脚本生成和编程问题解答。"
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "高级 LLM,支持代码生成、推理和修复,涵盖主流编程语言。"
+ },
+ "SenseChat": {
+ "description": "基础版本模型 (V4),4K上下文长度,通用能力强大"
+ },
+ "SenseChat-128K": {
+ "description": "基础版本模型 (V4),128K上下文长度,在长文本理解及生成等任务中表现出色"
+ },
+ "SenseChat-32K": {
+ "description": "基础版本模型 (V4),32K上下文长度,灵活应用于各类场景"
+ },
+ "SenseChat-5": {
+ "description": "最新版本模型 (V5.5),128K上下文长度,在数学推理、英文对话、指令跟随以及长文本理解等领域能力显著提升,比肩GPT-4o。"
+ },
+ "SenseChat-5-1202": {
+ "description": "是基于V5.5的最新版本,较上版本在中英文基础能力,聊天,理科知识, 文科知识,写作,数理逻辑,字数控制 等几个维度的表现有显著提升。"
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math 专注于数学领域的问题求解,为高难度题提供专业解答。"
+ "SenseChat-5-Cantonese": {
+ "description": "专门为适应香港地区的对话习惯、俚语及本地知识而设计,在粤语的对话理解上超越了GPT-4,在知识、推理、数学及代码编写等多个领域均能与GPT-4 Turbo相媲美。"
+ },
+ "SenseChat-Character": {
+ "description": "拟人对话标准版模型,8K上下文长度,高响应速度"
+ },
+ "SenseChat-Character-Pro": {
+ "description": "拟人对话高级版模型,32K上下文长度,能力全面提升,支持中/英文对话"
+ },
+ "SenseChat-Turbo": {
+ "description": "适用于快速问答、模型微调场景"
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "是最新的轻量版本模型,达到全量模型90%以上能力,显著降低推理成本。"
+ },
+ "SenseChat-Vision": {
+ "description": "最新版本模型 (V5.5),支持多图的输入,全面实现模型基础能力优化,在对象属性识别、空间关系、动作事件识别、场景理解、情感识别、逻辑常识推理和文本理解生成上都实现了较大提升。"
+ },
+ "Skylark2-lite-8k": {
+ "description": "云雀(Skylark)第二代模型,Skylark2-lite模型有较高的响应速度,适用于实时性要求高、成本敏感、对模型精度要求不高的场景,上下文窗口长度为8k。"
+ },
+ "Skylark2-pro-32k": {
+ "description": "云雀(Skylark)第二代模型,Skylark2-pro版本有较高的模型精度,适用于较为复杂的文本生成场景,如专业领域文案生成、小说创作、高质量翻译等,上下文窗口长度为32k。"
+ },
+ "Skylark2-pro-4k": {
+ "description": "云雀(Skylark)第二代模型,Skylark2-pro模型有较高的模型精度,适用于较为复杂的文本生成场景,如专业领域文案生成、小说创作、高质量翻译等,上下文窗口长度为4k。"
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "云雀(Skylark)第二代模型,Skylark2-pro-character模型具有优秀的角色扮演和聊天能力,擅长根据用户prompt要求扮演不同角色与用户展开聊天,角色风格突出,对话内容自然流畅,适用于构建聊天机器人、虚拟助手和在线客服等场景,有较高的响应速度。"
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "云雀(Skylark)第二代模型,Skylark2-pro-turbo-8k推理更快,成本更低,上下文窗口长度为8k。"
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B 是 ChatGLM 系列的开源模型,由智谱 AI 开发。该模型保留了前代模型的优秀特性,如对话流畅和部署门槛低,同时引入了新的特性。它采用了更多样的训练数据、更充分的训练步数和更合理的训练策略,在 10B 以下的预训练模型中表现出色。ChatGLM3-6B 支持多轮对话、工具调用、代码执行和 Agent 任务等复杂场景。除对话模型外,还开源了基础模型 ChatGLM-6B-Base 和长文本对话模型 ChatGLM3-6B-32K。该模型对学术研究完全开放,在登记后也允许免费商业使用"
},
"THUDM/glm-4-9b-chat": {
- "description": "GLM-4 9B 开放源码版本,为会话应用提供优化后的对话体验。"
+ "description": "GLM-4-9B-Chat 是智谱 AI 推出的 GLM-4 系列预训练模型中的开源版本。该模型在语义、数学、推理、代码和知识等多个方面表现出色。除了支持多轮对话外,GLM-4-9B-Chat 还具备网页浏览、代码执行、自定义工具调用(Function Call)和长文本推理等高级功能。模型支持 26 种语言,包括中文、英文、日语、韩语和德语等。在多项基准测试中,GLM-4-9B-Chat 展现了优秀的性能,如 AlignBench-v2、MT-Bench、MMLU 和 C-Eval 等。该模型支持最大 128K 的上下文长度,适用于学术研究和商业应用"
+ },
+ "TeleAI/TeleChat2": {
+ "description": "TeleChat2大模型是由中国电信从0到1自主研发的生成式语义大模型,支持百科问答、代码生成、长文生成等功能,为用户提供对话咨询服务,能够与用户进行对话互动,回答问题,协助创作,高效便捷地帮助用户获取信息、知识和灵感。模型在幻觉问题、长文生成、逻辑理解等方面均有较出色表现。"
+ },
+ "TeleAI/TeleMM": {
+ "description": "TeleMM多模态大模型是由中国电信自主研发的多模态理解大模型,能够处理文本、图像等多种模态输入,支持图像理解、图表分析等功能,为用户提供跨模态的理解服务。模型能够与用户进行多模态交互,准确理解输入内容,回答问题、协助创作,并高效提供多模态信息和灵感支持。在细粒度感知,逻辑推理等多模态任务上有出色表现"
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct 是阿里云发布的最新大语言模型系列之一。该 72B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升"
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B 在保持原系列模型优秀的通用语言能力的前提下,通过增量训练 5 千亿高质量 token,大幅提高了数学逻辑、代码能力。"
},
"abab5.5-chat": {
"description": "面向生产力场景,支持复杂任务处理和高效文本生成,适用于专业领域应用。"
@@ -116,75 +398,84 @@
"abab6.5t-chat": {
"description": "针对中文人设对话场景优化,提供流畅且符合中文表达习惯的对话生成能力。"
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworks 开源函数调用模型,提供卓越的指令执行能力和开放可定制的特性。"
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Fireworks 公司最新推出的 Firefunction-v2 是一款性能卓越的函数调用模型,基于 Llama-3 开发,并通过大量优化,特别适用于函数调用、对话及指令跟随等场景。"
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b 是一款视觉语言模型,可以同时接收图像和文本输入,经过高质量数据训练,适合多模态任务。"
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 是一款最先进的大型语言模型,经过强化学习和冷启动数据的优化,具有出色的推理、数学和编程性能。"
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B 指令模型,基于之前的Google技术,适合回答问题、总结和推理等多种文本生成任务。"
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Deepseek 提供的强大 Mixture-of-Experts (MoE) 语言模型,总参数量为 671B,每个标记激活 37B 参数。"
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
- "description": "Llama 3 70B 指令模型,专为多语言对话和自然语言理解优化,性能优于多数竞争模型。"
- },
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B 指令模型(HF 版本),与官方实现结果保持一致,适合高质量的指令跟随任务。"
+ "description": "Meta 开发并发布了 Meta Llama 3 系列大语言模型(LLM),该系列包含 8B 和 70B 参数规模的预训练和指令微调生成文本模型。Llama 3 指令微调模型专为对话应用场景优化,并在常见的行业基准测试中优于许多现有的开源聊天模型。"
},
"accounts/fireworks/models/llama-v3-8b-instruct": {
- "description": "Llama 3 8B 指令模型,优化用于对话及多语言任务,表现卓越且高效。"
+ "description": "Meta 开发并发布了 Meta Llama 3 系列大语言模型(LLM),这是一个包含 8B 和 70B 参数规模的预训练和指令微调生成文本模型的集合。Llama 3 指令微调模型专为对话应用场景优化,并在常见的行业基准测试中优于许多现有的开源聊天模型。"
},
"accounts/fireworks/models/llama-v3-8b-instruct-hf": {
- "description": "Llama 3 8B 指令模型(HF 版本),与官方实现结果一致,具备高度一致性和跨平台兼容性。"
+ "description": "Meta Llama 3 指令微调模型专为对话应用场景优化,并在常见的行业基准测试中优于许多现有的开源聊天模型。Llama 3 8B Instruct(HF 版本)是 Llama 3 8B Instruct 的原始 FP16 版本,其结果应与官方 Hugging Face 实现一致。"
},
"accounts/fireworks/models/llama-v3p1-405b-instruct": {
- "description": "Llama 3.1 405B 指令模型,具备超大规模参数,适合复杂任务和高负载场景下的指令跟随。"
+ "description": "Meta Llama 3.1 系列是多语言大语言模型(LLM)集合,包含 8B、70B 和 405B 参数规模的预训练和指令微调生成模型。Llama 3.1 指令微调文本模型(8B、70B、405B)专为多语言对话场景优化,在常见的行业基准测试中优于许多现有的开源和闭源聊天模型。405B 是 Llama 3.1 家族中能力最强的模型。该模型采用 FP8 进行推理,与参考实现高度匹配。"
},
"accounts/fireworks/models/llama-v3p1-70b-instruct": {
- "description": "Llama 3.1 70B 指令模型,提供卓越的自然语言理解和生成能力,是对话及分析任务的理想选择。"
+ "description": "Meta Llama 3.1 系列是多语言大语言模型(LLM)集合,包含 8B、70B 和 405B 三种参数规模的预训练和指令微调生成模型。Llama 3.1 指令微调文本模型(8B、70B、405B)专为多语言对话应用优化,并在常见的行业基准测试中优于许多现有的开源和闭源聊天模型。"
},
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
- "description": "Llama 3.1 8B 指令模型,专为多语言对话优化,能够在常见行业基准上超越多数开源及闭源模型。"
+ "description": "Meta Llama 3.1 系列是多语言大语言模型(LLM)集合,包含 8B、70B 和 405B 三种参数规模的预训练和指令微调生成模型。Llama 3.1 指令微调文本模型(8B、70B、405B)专为多语言对话应用优化,并在常见的行业基准测试中优于许多现有的开源和闭源聊天模型。"
+ },
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Meta 推出的指令微调图像推理模型,拥有 110 亿参数。该模型针对视觉识别、图像推理、图片字幕生成以及图片相关的常规问答进行了优化。它能够理解视觉数据,如图表和图形,并通过生成文本描述图像细节,弥合视觉与语言之间的鸿沟。"
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Llama 3.2 3B Instruct 是 Meta 推出的轻量级多语言模型。该模型专为高效运行而设计,相较于更大型的模型,具有显著的延迟和成本优势。其典型应用场景包括查询和提示重写,以及写作辅助。"
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Meta 推出的指令微调图像推理模型,拥有 900 亿参数。该模型针对视觉识别、图像推理、图片字幕生成以及图片相关的常规问答进行了优化。它能够理解视觉数据,如图表和图形,并通过生成文本描述图像细节,弥合视觉与语言之间的鸿沟。注意:该模型目前作为无服务器模型进行实验性提供。如果用于生产环境,请注意 Fireworks 可能会在短时间内取消部署该模型。"
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct 是 Llama 3.1 70B 的 12 月更新版本。该模型在 Llama 3.1 70B(于 2024 年 7 月发布)的基础上进行了改进,增强了工具调用、多语言文本支持、数学和编程能力。该模型在推理、数学和指令遵循方面达到了行业领先水平,并且能够提供与 3.1 405B 相似的性能,同时在速度和成本上具有显著优势。"
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "24B 参数模型,具备与更大型模型相当的最先进能力。"
},
"accounts/fireworks/models/mixtral-8x22b-instruct": {
- "description": "Mixtral MoE 8x22B 指令模型,大规模参数和多专家架构,全方位支持复杂任务的高效处理。"
+ "description": "Mixtral MoE 8x22B Instruct v0.1 是 Mixtral MoE 8x22B v0.1 的指令微调版本,已启用聊天完成功能 API。"
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
- "description": "Mixtral MoE 8x7B 指令模型,多专家架构提供高效的指令跟随及执行。"
- },
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B 指令模型(HF 版本),性能与官方实现一致,适合多种高效任务场景。"
+ "description": "Mixtral MoE 8x7B Instruct 是 Mixtral MoE 8x7B 的指令微调版本,已启用聊天完成功能 API。"
},
"accounts/fireworks/models/mythomax-l2-13b": {
- "description": "MythoMax L2 13B 模型,结合新颖的合并技术,擅长叙事和角色扮演。"
+ "description": "MythoMix 的改进版,可能是其更为完善的变体,是 MythoLogic-L2 和 Huginn 的合并,采用了高度实验性的张量类型合并技术。由于其独特的性质,该模型在讲故事和角色扮演方面表现出色。"
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
- "description": "Phi 3 Vision 指令模型,轻量级多模态模型,能够处理复杂的视觉和文本信息,具备较强的推理能力。"
+ "description": "Phi-3-Vision-128K-Instruct 是一个轻量级的、最先进的开放多模态模型,基于包括合成数据和筛选后的公开网站数据集构建,重点关注文本和视觉方面的高质量、推理密集型数据。该模型属于 Phi-3 模型家族,其多模态版本支持 128K 上下文长度(以标记为单位)。该模型经过严格的增强过程,包括监督微调和直接偏好优化,以确保精确的指令遵循和强大的安全措施。"
+ },
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "Qwen QwQ 模型专注于推动 AI 推理,并展示了开放模型在推理能力上与闭源前沿模型匹敌的力量。QwQ-32B-Preview 是一个实验性发布版本,在 GPQA、AIME、MATH-500 和 LiveCodeBench 基准测试中,在分析和推理能力上可与 o1 相媲美,并超越 GPT-4o 和 Claude 3.5 Sonnet。注意:该模型目前作为无服务器模型进行实验性提供。如果用于生产环境,请注意 Fireworks 可能会在短时间内取消部署该模型。"
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5B 模型,支持高级编程任务,多语言能力增强,适合复杂代码生成和理解。"
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Qwen-VL 模型的 72B 版本是阿里巴巴最新迭代的成果,代表了近一年的创新。"
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7B 模型,针对80多种编程语言训练,拥有出色的编程填充能力和语境理解。"
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 是由 Qwen 团队和阿里云开发的一系列仅解码语言模型,提供 0.5B、1.5B、3B、7B、14B、32B 和 72B 不同参数规模,并包含基础版和指令微调版。"
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5-Coder 是最新一代专为代码设计的 Qwen 大型语言模型(前称为 CodeQwen)。注意:该模型目前作为无服务器模型进行实验性提供。如果用于生产环境,请注意 Fireworks 可能会在短时间内取消部署该模型。"
},
"accounts/yi-01-ai/models/yi-large": {
- "description": "Yi-Large 模型,具备卓越的多语言处理能力,可用于各类语言生成和理解任务。"
+ "description": "Yi-Large 是顶尖的大型语言模型之一,在 LMSYS 基准测试排行榜上,其表现仅次于 GPT-4、Gemini 1.5 Pro 和 Claude 3 Opus。它在多语言能力方面表现卓越,特别是在西班牙语、中文、日语、德语和法语方面。Yi-Large 还具有用户友好性,采用与 OpenAI 相同的 API 定义,便于集成。"
},
"ai21-jamba-1.5-large": {
- "description": "A 398B parameters (94B active) multilingual model, offering a 256K long context window, function calling, structured output, and grounded generation."
+ "description": "一个398B参数(94B活跃)的多语言模型,提供256K长上下文窗口、函数调用、结构化输出和基于事实的生成。"
},
"ai21-jamba-1.5-mini": {
- "description": "A 52B parameters (12B active) multilingual model, offering a 256K long context window, function calling, structured output, and grounded generation."
- },
- "ai21-jamba-instruct": {
- "description": "A production-grade Mamba-based LLM model to achieve best-in-class performance, quality, and cost efficiency."
+ "description": "一个52B参数(12B活跃)的多语言模型,提供256K长上下文窗口、函数调用、结构化输出和基于事实的生成。"
},
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet 提升了行业标准,性能超过竞争对手模型和 Claude 3 Opus,在广泛的评估中表现出色,同时具有我们中等层级模型的速度和成本。"
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet 提升了行业标准,性能超过竞争对手模型和 Claude 3 Opus,在广泛的评估中表现出色,同时具有我们中等层级模型的速度和成本。"
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku 是 Anthropic 最快、最紧凑的模型,提供近乎即时的响应速度。它可以快速回答简单的查询和请求。客户将能够构建模仿人类互动的无缝 AI 体验。Claude 3 Haiku 可以处理图像并返回文本输出,具有 200K 的上下文窗口。"
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus 是 Anthropic 用于处理高度复杂任务的最强大模型。它在性能、智能、流畅性和理解力方面表现卓越。"
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku 是 Anthropic 最快的下一代模型。与 Claude 3 Haiku 相比,Claude 3.5 Haiku 在各项技能上都有所提升,并在许多智力基准测试中超越了上一代最大的模型 Claude 3 Opus。"
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度,同时保持与 Sonnet 相同的价格。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。"
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet 是 Anthropic 迄今为止最智能的模型,也是市场上首个混合推理模型。Claude 3.7 Sonnet 可以产生近乎即时的响应或延长的逐步思考,用户可以清晰地看到这些过程。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。"
+ },
"aya": {
"description": "Aya 23 是 Cohere 推出的多语言模型,支持 23 种语言,为多元化语言应用提供便利。"
},
"aya:35b": {
"description": "Aya 23 是 Cohere 推出的多语言模型,支持 23 种语言,为多元化语言应用提供便利。"
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B 百川智能开发的包含 130 亿参数的开源可商用的大规模语言模型,在权威的中文和英文 benchmark 上均取得同尺寸最好的效果"
+ },
"charglm-3": {
"description": "CharGLM-3 专为角色扮演与情感陪伴设计,支持超长多轮记忆与个性化对话,应用广泛。"
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 为企业提供了关键能力的进步,包括业界领先的 200K token 上下文、大幅降低模型幻觉的发生率、系统提示以及一个新的测试功能:工具调用。"
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku 是 Anthropic 最快的下一代模型。与 Claude 3 Haiku 相比,Claude 3.5 Haiku 在各项技能上都有所提升,并在许多智力基准测试中超越了上一代最大的模型 Claude 3 Opus。"
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度,同时保持与 Sonnet 相同的价格。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。"
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度,同时保持与 Sonnet 相同的价格。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。"
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet 是 Anthropic 迄今为止最智能的模型,也是市场上首个混合推理模型。Claude 3.7 Sonnet 可以产生近乎即时的响应或延长的逐步思考,用户可以清晰地看到这些过程。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。"
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku 是 Anthropic 的最快且最紧凑的模型,旨在实现近乎即时的响应。它具有快速且准确的定向性能。"
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet 在智能和速度方面为企业工作负载提供了理想的平衡。它以更低的价格提供最大效用,可靠且适合大规模部署。"
},
- "claude-instant-1.2": {
- "description": "Anthropic 的模型用于低延迟、高吞吐量的文本生成,支持生成数百页的文本。"
- },
"codegeex-4": {
"description": "CodeGeeX-4 是强大的AI编程助手,支持多种编程语言的智能问答与代码补全,提升开发效率。"
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B 是一个多语言代码生成模型,支持包括代码补全和生成、代码解释器、网络搜索、函数调用、仓库级代码问答在内的全面功能,覆盖软件开发的各种场景。是参数少于 10B 的顶尖代码生成模型。"
+ },
"codegemma": {
"description": "CodeGemma 专用于不同编程任务的轻量级语言模型,支持快速迭代和集成。"
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama 是一款专注于代码生成和讨论的 LLM,结合广泛的编程语言支持,适用于开发者环境。"
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama 是一款专注于代码生成和讨论的 LLM,结合广泛的编程语言支持,适用于开发者环境。"
+ },
"codellama:13b": {
"description": "Code Llama 是一款专注于代码生成和讨论的 LLM,结合广泛的编程语言支持,适用于开发者环境。"
},
@@ -273,16 +585,16 @@
"description": "Codestral 是 Mistral AI 的首款代码模型,为代码生成任务提供优异支持。"
},
"codestral-latest": {
- "description": "Codestral是专注于代码生成的尖端生成模型,优化了中间填充和代码补全任务。"
+ "description": "Codestral 是我们最先进的编码语言模型,第二个版本于2025年1月发布,专门从事低延迟、高频任务如中间填充(RST)、代码纠正和测试生成。"
},
"cognitivecomputations/dolphin-mixtral-8x22b": {
"description": "Dolphin Mixtral 8x22B 是一款为指令遵循、对话和编程设计的模型。"
},
"cohere-command-r": {
- "description": "Command R is a scalable generative model targeting RAG and Tool Use to enable production-scale AI for enterprise."
+ "description": "Command R是一个可扩展的生成模型,旨在针对RAG和工具使用,使企业能够实现生产级AI。"
},
"cohere-command-r-plus": {
- "description": "Command R+ is a state-of-the-art RAG-optimized model designed to tackle enterprise-grade workloads."
+ "description": "Command R+是一个最先进的RAG优化模型,旨在应对企业级工作负载。"
},
"command-r": {
"description": "Command R 是优化用于对话和长上下文任务的LLM,特别适合动态交互与知识管理。"
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ 是一款高性能的大型语言模型,专为真实企业场景和复杂应用而设计。"
},
+ "dall-e-2": {
+ "description": "第二代 DALL·E 模型,支持更真实、准确的图像生成,分辨率是第一代的4倍"
+ },
+ "dall-e-3": {
+ "description": "最新的 DALL·E 模型,于2023年11月发布。支持更真实、准确的图像生成,具有更强的细节表现力"
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct 提供高可靠性的指令处理能力,支持多行业应用。"
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 系列通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆,超越 OpenAI-o1-mini 水平。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek-R1 蒸馏模型,通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B 是基于 Llama-3.1-8B 开发的蒸馏模型。该模型使用 DeepSeek-R1 生成的样本进行微调,展现出优秀的推理能力。在多个基准测试中表现不俗,其中在 MATH-500 上达到了 89.1% 的准确率,在 AIME 2024 上达到了 50.4% 的通过率,在 CodeForces 上获得了 1205 的评分,作为 8B 规模的模型展示了较强的数学和编程能力。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 蒸馏模型,通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 蒸馏模型,通过强化学习与冷启动数据优化推理性能,开源模型刷新多任务标杆。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B 是基于 Qwen2.5-32B 通过知识蒸馏得到的模型。该模型使用 DeepSeek-R1 生成的 80 万个精选样本进行微调,在数学、编程和推理等多个领域展现出卓越的性能。在 AIME 2024、MATH-500、GPQA Diamond 等多个基准测试中都取得了优异成绩,其中在 MATH-500 上达到了 94.3% 的准确率,展现出强大的数学推理能力。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B 是基于 Qwen2.5-Math-7B 通过知识蒸馏得到的模型。该模型使用 DeepSeek-R1 生成的 80 万个精选样本进行微调,展现出优秀的推理能力。在多个基准测试中表现出色,其中在 MATH-500 上达到了 92.8% 的准确率,在 AIME 2024 上达到了 55.5% 的通过率,在 CodeForces 上获得了 1189 的评分,作为 7B 规模的模型展示了较强的数学和编程能力。"
+ },
"deepseek-ai/DeepSeek-V2.5": {
- "description": "DeepSeek V2.5 集合了先前版本的优秀特征,增强了通用和编码能力。"
+ "description": "DeepSeek-V2.5 是 DeepSeek-V2-Chat 和 DeepSeek-Coder-V2-Instruct 的升级版本,集成了两个先前版本的通用和编码能力。该模型在多个方面进行了优化,包括写作和指令跟随能力,更好地与人类偏好保持一致。DeepSeek-V2.5 在各种评估基准上都取得了显著的提升,如 AlpacaEval 2.0、ArenaHard、AlignBench 和 MT-Bench 等。"
+ },
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 是一款拥有 6710 亿参数的混合专家(MoE)语言模型,采用多头潜在注意力(MLA)和 DeepSeekMoE 架构,结合无辅助损失的负载平衡策略,优化推理和训练效率。通过在 14.8 万亿高质量tokens上预训练,并进行监督微调和强化学习,DeepSeek-V3 在性能上超越其他开源模型,接近领先闭源模型。"
},
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek LLM Chat (67B) 是创新的 AI 模型 提供深度语言理解和互动能力。"
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "最先进的高效 LLM,擅长推理、数学和编程。"
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 是一个基于 DeepSeekMoE-27B 开发的混合专家(MoE)视觉语言模型,采用稀疏激活的 MoE 架构,在仅激活 4.5B 参数的情况下实现了卓越性能。该模型在视觉问答、光学字符识别、文档/表格/图表理解和视觉定位等多个任务中表现优异。"
+ },
"deepseek-chat": {
"description": "融合通用与代码能力的全新开源模型, 不仅保留了原有 Chat 模型的通用对话能力和 Coder 模型的强大代码处理能力,还更好地对齐了人类偏好。此外,DeepSeek-V2.5 在写作任务、指令跟随等多个方面也实现了大幅提升。"
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B 是一个代码语言模型, 基于 2 万亿数据训练而成,其中 87% 为代码, 13% 为中英文语言。模型引入 16K 窗口大小和填空任务,提供项目级别的代码补全和片段填充功能。"
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 是开源的混合专家代码模型,在代码任务方面表现优异,与 GPT4-Turbo 相媲美。"
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 是开源的混合专家代码模型,在代码任务方面表现优异,与 GPT4-Turbo 相媲美。"
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 在后训练阶段大规模使用了强化学习技术,在仅有极少标注数据的情况下,极大提升了模型推理能力。在数学、代码、自然语言推理等任务上,性能比肩 OpenAI o1 正式版。"
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek-R1-Distill-Llama-70B 是一个基于 Llama-3.3-70B-Instruct 的蒸馏大型语言模型,使用了 DeepSeek R1 的输出。"
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek-R1-Distill-Llama-8B 是一个基于 Llama-3.1-8B 的蒸馏大型语言模型,使用了 DeepSeek R1 的输出。"
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "DeepSeek-R1-Distill-Qwen-1.5B 是一个基于 Qwen2.5-Math-1.5B 的蒸馏大型语言模型,使用了 DeepSeek R1 的输出。"
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek-R1-Distill-Qwen-14B 是一个基于 Qwen2.5-14B 的蒸馏大型语言模型,使用了 DeepSeek R1 的输出。"
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek-R1-Distill 模型是在开源模型的基础上通过微调训练得到的,训练过程中使用了由 DeepSeek-R1 生成的样本数据。"
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "DeepSeek-R1-Distill 模型是在开源模型的基础上通过微调训练得到的,训练过程中使用了由 DeepSeek-R1 生成的样本数据。"
+ },
+ "deepseek-reasoner": {
+ "description": "DeepSeek 推出的推理模型。在输出最终回答之前,模型会先输出一段思维链内容,以提升最终答案的准确性。"
+ },
"deepseek-v2": {
"description": "DeepSeek V2 是高效的 Mixture-of-Experts 语言模型,适用于经济高效的处理需求。"
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B 是 DeepSeek 的设计代码模型,提供强大的代码生成能力。"
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 为杭州深度求索人工智能基础技术研究有限公司自研的 MoE 模型,其多项评测成绩突出,在主流榜单中位列开源模型榜首。V3 相比 V2.5 模型生成速度实现 3 倍提升,为用户带来更加迅速流畅的使用体验。"
+ },
"deepseek/deepseek-chat": {
"description": "融合通用与代码能力的全新开源模型, 不仅保留了原有 Chat 模型的通用对话能力和 Coder 模型的强大代码处理能力,还更好地对齐了人类偏好。此外,DeepSeek-V2.5 在写作任务、指令跟随等多个方面也实现了大幅提升。"
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek R1是DeepSeek团队发布的最新开源模型,具备非常强悍的推理性能,尤其在数学、编程和推理任务上达到了与OpenAI的o1模型相当的水平。"
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B是基于Llama3.3 70B的大型语言模型,该模型利用DeepSeek R1输出的微调,实现了与大型前沿模型相当的竞争性能。"
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B 是一种基于 Llama-3.1-8B-Instruct 的蒸馏大语言模型,通过使用 DeepSeek R1 的输出进行训练而得。"
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B 是一种基于 Qwen 2.5 14B 的蒸馏大语言模型,通过使用 DeepSeek R1 的输出进行训练而得。该模型在多个基准测试中超越了 OpenAI 的 o1-mini,取得了密集模型(dense models)的最新技术领先成果(state-of-the-art)。以下是一些基准测试的结果:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\n该模型通过从 DeepSeek R1 的输出中进行微调,展现了与更大规模的前沿模型相当的竞争性能。"
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B 是一种基于 Qwen 2.5 32B 的蒸馏大语言模型,通过使用 DeepSeek R1 的输出进行训练而得。该模型在多个基准测试中超越了 OpenAI 的 o1-mini,取得了密集模型(dense models)的最新技术领先成果(state-of-the-art)。以下是一些基准测试的结果:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\n该模型通过从 DeepSeek R1 的输出中进行微调,展现了与更大规模的前沿模型相当的竞争性能。"
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1是DeepSeek团队发布的最新开源模型,具备非常强悍的推理性能,尤其在数学、编程和推理任务上达到了与OpenAI的o1模型相当的水平。"
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 在仅有极少标注数据的情况下,极大提升了模型推理能力。在输出最终回答之前,模型会先输出一段思维链内容,以提升最终答案的准确性。"
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3在推理速度方面实现了比之前模型的重大突破。在开源模型中排名第一,并可与全球最先进的闭源模型相媲美。DeepSeek-V3 采用了多头潜在注意力 (MLA) 和 DeepSeekMoE 架构,这些架构在 DeepSeek-V2 中得到了全面验证。此外,DeepSeek-V3 开创了一种用于负载均衡的辅助无损策略,并设定了多标记预测训练目标以获得更强的性能。"
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3在推理速度方面实现了比之前模型的重大突破。在开源模型中排名第一,并可与全球最先进的闭源模型相媲美。DeepSeek-V3 采用了多头潜在注意力 (MLA) 和 DeepSeekMoE 架构,这些架构在 DeepSeek-V2 中得到了全面验证。此外,DeepSeek-V3 开创了一种用于负载均衡的辅助无损策略,并设定了多标记预测训练目标以获得更强的性能。"
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite 全新一代轻量版模型,极致响应速度,效果与时延均达到全球一流水平。"
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k 基于 Doubao-1.5-Pro 全面升级版,整体效果大幅提升 10%。支持 256k 上下文窗口的推理,输出长度支持最大 12k tokens。更高性能、更大窗口、超高性价比,适用于更广泛的应用场景。"
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro 全新一代主力模型,性能全面升级,在知识、代码、推理、等方面表现卓越。"
+ },
"emohaa": {
"description": "Emohaa 是心理模型,具备专业咨询能力,帮助用户理解情感问题。"
},
+ "ernie-3.5-128k": {
+ "description": "百度自研的旗舰级大规模⼤语⾔模型,覆盖海量中英文语料,具有强大的通用能力,可满足绝大部分对话问答、创作生成、插件应用场景要求;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ernie-3.5-8k": {
+ "description": "百度自研的旗舰级大规模⼤语⾔模型,覆盖海量中英文语料,具有强大的通用能力,可满足绝大部分对话问答、创作生成、插件应用场景要求;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "百度自研的旗舰级大规模⼤语⾔模型,覆盖海量中英文语料,具有强大的通用能力,可满足绝大部分对话问答、创作生成、插件应用场景要求;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,相较ERNIE 3.5实现了模型能力全面升级,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,相较ERNIE 3.5实现了模型能力全面升级,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。"
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,综合效果表现出色,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。相较于ERNIE 4.0在性能表现上更优秀"
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,综合效果表现出色,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。相较于ERNIE 4.0在性能表现上更优秀"
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "百度自研的旗舰级超大规模⼤语⾔模型,综合效果表现出色,广泛适用于各领域复杂任务场景;支持自动对接百度搜索插件,保障问答信息时效。相较于ERNIE 4.0在性能表现上更优秀"
+ },
+ "ernie-char-8k": {
+ "description": "百度自研的垂直场景大语言模型,适合游戏NPC、客服对话、对话角色扮演等应用场景,人设风格更为鲜明、一致,指令遵循能力更强,推理性能更优。"
+ },
+ "ernie-char-fiction-8k": {
+ "description": "百度自研的垂直场景大语言模型,适合游戏NPC、客服对话、对话角色扮演等应用场景,人设风格更为鲜明、一致,指令遵循能力更强,推理性能更优。"
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite是百度自研的轻量级大语言模型,兼顾优异的模型效果与推理性能,适合低算力AI加速卡推理使用。"
+ },
+ "ernie-lite-pro-128k": {
+ "description": "百度自研的轻量级大语言模型,兼顾优异的模型效果与推理性能,效果比ERNIE Lite更优,适合低算力AI加速卡推理使用。"
+ },
+ "ernie-novel-8k": {
+ "description": "百度自研通用大语言模型,在小说续写能力上有明显优势,也可用在短剧、电影等场景。"
+ },
+ "ernie-speed-128k": {
+ "description": "百度2024年最新发布的自研高性能大语言模型,通用能力优异,适合作为基座模型进行精调,更好地处理特定场景问题,同时具备极佳的推理性能。"
+ },
+ "ernie-speed-pro-128k": {
+ "description": "百度2024年最新发布的自研高性能大语言模型,通用能力优异,效果比ERNIE Speed更优,适合作为基座模型进行精调,更好地处理特定场景问题,同时具备极佳的推理性能。"
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny是百度自研的超高性能大语言模型,部署与精调成本在文心系列模型中最低。"
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) 提供稳定并可调优的性能,是复杂任务解决方案的理想选择。"
},
@@ -329,14 +791,17 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro 是Google的高性能AI模型,专为广泛任务扩展而设计。"
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash 是Google最新的多模态AI模型,具备快速处理能力,支持文本、图像和视频输入,适用于多种任务的高效扩展。"
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 是一款高效的多模态模型,支持广泛应用的扩展。"
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 是一款高效的多模态模型,支持广泛应用的扩展。"
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 专为处理大规模任务场景设计,提供无与伦比的处理速度。"
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B 是一款高效的多模态模型,支持广泛应用的扩展。"
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 是最新的实验性模型,在文本和多模态用例中都有显著的性能提升。"
@@ -362,6 +827,30 @@
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro 支持高达200万个tokens,是中型多模态模型的理想选择,适用于复杂任务的多方面支持。"
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash 提供下一代功能和改进,包括卓越的速度、原生工具使用、多模态生成和1M令牌上下文窗口。"
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash 提供下一代功能和改进,包括卓越的速度、原生工具使用、多模态生成和1M令牌上下文窗口。"
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash 模型变体,针对成本效益和低延迟等目标进行了优化。"
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash 模型变体,针对成本效益和低延迟等目标进行了优化。"
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "一个 Gemini 2.0 Flash 模型,针对成本效益和低延迟等目标进行了优化。"
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Thinking Exp 是 Google 的实验性多模态推理AI模型,能对复杂问题进行推理,拥有新的思维能力。"
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Thinking Exp 是 Google 的实验性多模态推理AI模型,能对复杂问题进行推理,拥有新的思维能力。"
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental 是 Google 最新的实验性多模态AI模型,与历史版本相比有一定的质量提升,特别是对于世界知识、代码和长上下文。"
+ },
"gemma-7b-it": {
"description": "Gemma 7B 适合中小规模任务处理,兼具成本效益。"
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 是 Google 推出的高效模型,涵盖从小型应用到复杂数据处理的多种应用场景。"
},
- "general": {
- "description": "Spark Lite 是一款轻量级大语言模型,具备极低的延迟与高效的处理能力,完全免费开放,支持实时在线搜索功能。其快速响应的特性使其在低算力设备上的推理应用和模型微调中表现出色,为用户带来出色的成本效益和智能体验,尤其在知识问答、内容生成及搜索场景下表现不俗。"
- },
"generalv3": {
"description": "Spark Pro 是一款为专业领域优化的高性能大语言模型,专注数学、编程、医疗、教育等多个领域,并支持联网搜索及内置天气、日期等插件。其优化后模型在复杂知识问答、语言理解及高层次文本创作中展现出色表现和高效性能,是适合专业应用场景的理想选择。"
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520 是最新模型版本,专为高度复杂和多样化任务设计,表现卓越。"
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat 在语义、数学、推理、代码和知识等多方面均表现出较高性能。还具备网页浏览、代码执行、自定义工具调用和长文本推理。 支持包括日语,韩语,德语在内的 26 种语言。"
+ },
"glm-4-air": {
"description": "GLM-4-Air 是性价比高的版本,性能接近GLM-4,提供快速度和实惠的价格。"
},
@@ -402,7 +891,10 @@
"description": "GLM-4-AllTools 是一个多功能智能体模型,优化以支持复杂指令规划与工具调用,如网络浏览、代码解释和文本生成,适用于多任务执行。"
},
"glm-4-flash": {
- "description": "GLM-4-Flash 是处理简单任务的理想选择,速度最快且价格最优惠。"
+ "description": "GLM-4-Flash 是处理简单任务的理想选择,速度最快且免费。"
+ },
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX 是Flash的增强版本,超快推理速度。"
},
"glm-4-long": {
"description": "GLM-4-Long 支持超长文本输入,适合记忆型任务与大规模文档处理。"
@@ -413,20 +905,41 @@
"glm-4v": {
"description": "GLM-4V 提供强大的图像理解与推理能力,支持多种视觉任务。"
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash 专注于高效的单一图像理解,适用于快速图像解析的场景,例如实时图像分析或批量图像处理。"
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus 具备对视频内容及多图片的理解能力,适合多模态任务。"
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 提供了优化后的多模态处理能力,适用多种复杂任务场景。"
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview具备强大的复杂推理能力,在逻辑推理、数学、编程等领域表现优异。"
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 结合最新优化技术,带来更高效的多模态数据处理能力。"
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash 提供下一代功能和改进,包括卓越的速度、原生工具使用、多模态生成和1M令牌上下文窗口。"
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental 是 Google 最新的实验性多模态AI模型,与历史版本相比有一定的质量提升,特别是对于世界知识、代码和长上下文。"
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash 提供了优化后的多模态处理能力,适用多种复杂任务场景。"
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro 结合最新优化技术,带来更高效的多模态数据处理能力。"
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 是 Google 推出的高效模型,涵盖从小型应用到复杂数据处理的多种应用场景。"
},
"google/gemma-2-27b-it": {
- "description": "Gemma 2 延续了轻量化与高效的设计理念。"
+ "description": "Gemma 2 27B 是一款通用大语言模型,具有优异的性能和广泛的应用场景。"
+ },
+ "google/gemma-2-2b-it": {
+ "description": "面向边缘应用的高级小型语言生成 AI 模型。"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 是 Google 推出的高效模型,涵盖从小型应用到复杂数据处理的多种应用场景。"
},
"google/gemma-2-9b-it": {
- "description": "Gemma 2 是Google轻量化的开源文本模型系列。"
+ "description": "Gemma 2 9B 由Google开发,提供高效的指令响应和综合能力。"
},
"google/gemma-2-9b-it:free": {
"description": "Gemma 2 是Google轻量化的开源文本模型系列。"
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo,适用于各种文本生成和理解任务,Currently points to gpt-3.5-turbo-0125"
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo,OpenAI提供的高效模型,适用于聊天和文本生成任务,支持并行函数调用。"
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k,高容量文本生成模型,适合复杂任务。"
+ },
"gpt-4": {
"description": "GPT-4 提供了一个更大的上下文窗口,能够处理更长的文本输入,适用于需要广泛信息整合和数据分析的场景。"
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "最新的 GPT-4 Turbo 模型具备视觉功能。现在,视觉请求可以使用 JSON 模式和函数调用。 GPT-4 Turbo 是一个增强版本,为多模态任务提供成本效益高的支持。它在准确性和效率之间找到平衡,适合需要进行实时交互的应用程序场景。"
},
- "gpt-4-1106-vision-preview": {
- "description": "最新的 GPT-4 Turbo 模型具备视觉功能。现在,视觉请求可以使用 JSON 模式和函数调用。 GPT-4 Turbo 是一个增强版本,为多模态任务提供成本效益高的支持。它在准确性和效率之间找到平衡,适合需要进行实时交互的应用程序场景。"
- },
"gpt-4-32k": {
"description": "GPT-4 提供了一个更大的上下文窗口,能够处理更长的文本输入,适用于需要广泛信息整合和数据分析的场景。"
},
@@ -477,10 +993,13 @@
"description": "最新的 GPT-4 Turbo 模型具备视觉功能。现在,视觉请求可以使用 JSON 模式和函数调用。 GPT-4 Turbo 是一个增强版本,为多模态任务提供成本效益高的支持。它在准确性和效率之间找到平衡,适合需要进行实时交互的应用程序场景。"
},
"gpt-4-vision-preview": {
- "description": "最新的 GPT-4 Turbo 模型具备视觉功能。现在,视觉请求可以使用 JSON 模式和函数调用。 GPT-4 Turbo 是一个增强版本,为多模态任务提供成本效益高的支持。它在准确性和效率之间找到平衡,适合需要进行实时交互的应用程序场景。"
+ "description": "GPT-4 视觉预览版,专为图像分析和处理任务设计。"
+ },
+ "gpt-4.5-preview": {
+ "description": "GPT-4.5 的研究预览版,它是我们迄今为止最大、最强大的 GPT 模型。它拥有广泛的世界知识,并能更好地理解用户意图,使其在创造性任务和自主规划方面表现出色。GPT-4.5 可接受文本和图像输入,并生成文本输出(包括结构化输出)。支持关键的开发者功能,如函数调用、批量 API 和流式输出。在需要创造性、开放式思考和对话的任务(如写作、学习或探索新想法)中,GPT-4.5 表现尤为出色。知识截止日期为 2023 年 10 月。"
},
"gpt-4o": {
- "description": "OpenAI's most advanced multimodal model in the GPT-4 family. Can handle both text and image inputs."
+ "description": "ChatGPT-4o 是一款动态模型,实时更新以保持当前最新版本。它结合了强大的语言理解与生成能力,适合于大规模应用场景,包括客户服务、教育和技术支持。"
},
"gpt-4o-2024-05-13": {
"description": "ChatGPT-4o 是一款动态模型,实时更新以保持当前最新版本。它结合了强大的语言理解与生成能力,适合于大规模应用场景,包括客户服务、教育和技术支持。"
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o 是一款动态模型,实时更新以保持当前最新版本。它结合了强大的语言理解与生成能力,适合于大规模应用场景,包括客户服务、教育和技术支持。"
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o 是一款动态模型,实时更新以保持当前最新版本。它结合了强大的语言理解与生成能力,适合于大规模应用场景,包括客户服务、教育和技术支持。"
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o Audio 模型,支持音频输入输出"
+ },
"gpt-4o-mini": {
- "description": "An affordable, efficient AI solution for diverse text and image tasks."
+ "description": "GPT-4o mini是OpenAI在GPT-4 Omni之后推出的最新模型,支持图文输入并输出文本。作为他们最先进的小型模型,它比其他近期的前沿模型便宜很多,并且比GPT-3.5 Turbo便宜超过60%。它保持了最先进的智能,同时具有显著的性价比。GPT-4o mini在MMLU测试中获得了 82% 的得分,目前在聊天偏好上排名高于 GPT-4。"
+ },
+ "gpt-4o-mini-realtime-preview": {
+ "description": "GPT-4o-mini 实时版本,支持音频和文本实时输入输出"
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "GPT-4o 实时版本,支持音频和文本实时输入输出"
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "GPT-4o 实时版本,支持音频和文本实时输入输出"
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "GPT-4o 实时版本,支持音频和文本实时输入输出"
+ },
+ "grok-2-1212": {
+ "description": "该模型在准确性、指令遵循和多语言能力方面有所改进。"
+ },
+ "grok-2-vision-1212": {
+ "description": "该模型在准确性、指令遵循和多语言能力方面有所改进。"
+ },
+ "grok-beta": {
+ "description": "拥有与 Grok 2 相当的性能,但具有更高的效率、速度和功能。"
+ },
+ "grok-vision-beta": {
+ "description": "最新的图像理解模型,可以处理各种各样的视觉信息,包括文档、图表、截图和照片等。"
},
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B 是一款合并了多个顶尖模型的创意与智能相结合的语言模型。"
},
+ "hunyuan-code": {
+ "description": "混元最新代码生成模型,经过 200B 高质量代码数据增训基座模型,迭代半年高质量 SFT 数据训练,上下文长窗口长度增大到 8K,五大语言代码生成自动评测指标上位居前列;五大语言10项考量各方面综合代码任务人工高质量评测上,性能处于第一梯队"
+ },
+ "hunyuan-functioncall": {
+ "description": "混元最新 MOE 架构 FunctionCall 模型,经过高质量的 FunctionCall 数据训练,上下文窗口达 32K,在多个维度的评测指标上处于领先。"
+ },
+ "hunyuan-large": {
+ "description": "Hunyuan-large 模型总参数量约 389B,激活参数量约 52B,是当前业界参数规模最大、效果最好的 Transformer 架构的开源 MoE 模型。"
+ },
+ "hunyuan-large-longcontext": {
+ "description": "擅长处理长文任务如文档摘要和文档问答等,同时也具备处理通用文本生成任务的能力。在长文本的分析和生成上表现优异,能有效应对复杂和详尽的长文内容处理需求。"
+ },
+ "hunyuan-lite": {
+ "description": "升级为 MOE 结构,上下文窗口为 256k ,在 NLP,代码,数学,行业等多项评测集上领先众多开源模型。"
+ },
+ "hunyuan-lite-vision": {
+ "description": "混元最新7B多模态模型,上下文窗口32K,支持中英文场景的多模态对话、图像物体识别、文档表格理解、多模态数学等,在多个维度上评测指标优于7B竞品模型。"
+ },
+ "hunyuan-pro": {
+ "description": "万亿级参数规模 MOE-32K 长文模型。在各种 benchmark 上达到绝对领先的水平,复杂指令和推理,具备复杂数学能力,支持 functioncall,在多语言翻译、金融法律医疗等领域应用重点优化。"
+ },
+ "hunyuan-role": {
+ "description": "混元最新版角色扮演模型,混元官方精调训练推出的角色扮演模型,基于混元模型结合角色扮演场景数据集进行增训,在角色扮演场景具有更好的基础效果。"
+ },
+ "hunyuan-standard": {
+ "description": "采用更优的路由策略,同时缓解了负载均衡和专家趋同的问题。长文方面,大海捞针指标达到99.9%。MOE-32K 性价比相对更高,在平衡效果、价格的同时,可对实现对长文本输入的处理。"
+ },
+ "hunyuan-standard-256K": {
+ "description": "采用更优的路由策略,同时缓解了负载均衡和专家趋同的问题。长文方面,大海捞针指标达到99.9%。MOE-256K 在长度和效果上进一步突破,极大的扩展了可输入长度。"
+ },
+ "hunyuan-standard-vision": {
+ "description": "混元最新多模态模型,支持多语种作答,中英文能力均衡。"
+ },
+ "hunyuan-translation": {
+ "description": "支持中文和英语、日语、法语、葡萄牙语、西班牙语、土耳其语、俄语、阿拉伯语、韩语、意大利语、德语、越南语、马来语、印尼语15种语言互译,基于多场景翻译评测集自动化评估COMET评分,在十余种常用语种中外互译能力上整体优于市场同规模模型。"
+ },
+ "hunyuan-translation-lite": {
+ "description": "混元翻译模型支持自然语言对话式翻译;支持中文和英语、日语、法语、葡萄牙语、西班牙语、土耳其语、俄语、阿拉伯语、韩语、意大利语、德语、越南语、马来语、印尼语15种语言互译。"
+ },
+ "hunyuan-turbo": {
+ "description": "本版本优化:数据指令scaling,大幅提升模型通用泛化能力;大幅提升数学、代码、逻辑推理能力;优化文本理解字词理解相关能力;优化文本创作内容生成质量"
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "hunyuan-turbo 2024 年 11 月 20 日固定版本,介于 hunyuan-turbo 和 hunyuan-turbo-latest 之间的一个版本。"
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "本版本优化:数据指令scaling,大幅提升模型通用泛化能力;大幅提升数学、代码、逻辑推理能力;优化文本理解字词理解相关能力;优化文本创作内容生成质量"
+ },
+ "hunyuan-turbo-latest": {
+ "description": "通用体验优化,包括NLP理解、文本创作、闲聊、知识问答、翻译、领域等;提升拟人性,优化模型情商;提升意图模糊时模型主动澄清能力;提升字词解析类问题的处理能力;提升创作的质量和可互动性;提升多轮体验。"
+ },
+ "hunyuan-turbo-vision": {
+ "description": "混元新一代视觉语言旗舰大模型,采用全新的混合专家模型(MoE)结构,在图文理解相关的基础识别、内容创作、知识问答、分析推理等能力上相比前一代模型全面提升。"
+ },
+ "hunyuan-vision": {
+ "description": "混元最新多模态模型,支持图片+文本输入生成文本内容。"
+ },
"internlm/internlm2_5-20b-chat": {
- "description": "创新的开源模型InternLM2.5,通过大规模的参数提高了对话智能。"
+ "description": "InternLM2.5-20B-Chat 是一个开源的大规模对话模型,基于 InternLM2 架构开发。该模型拥有 200 亿参数,在数学推理方面表现出色,超越了同量级的 Llama3 和 Gemma2-27B 模型。InternLM2.5-20B-Chat 在工具调用能力方面有显著提升,支持从上百个网页收集信息进行分析推理,并具备更强的指令理解、工具选择和结果反思能力。它适用于构建复杂智能体,可进行多轮工具调用以完成复杂任务"
},
"internlm/internlm2_5-7b-chat": {
- "description": "InternLM2.5 提供多场景下的智能对话解决方案。"
+ "description": "InternLM2.5-7B-Chat 是一个开源的对话模型,基于 InternLM2 架构开发。该 7B 参数规模的模型专注于对话生成任务,支持中英双语交互。模型采用了最新的训练技术,旨在提供流畅、智能的对话体验。InternLM2.5-7B-Chat 适用于各种对话应用场景,包括但不限于智能客服、个人助手等领域"
+ },
+ "internlm2-pro-chat": {
+ "description": "InternLM2 版本最大的模型,专注于高度复杂的任务"
+ },
+ "internlm2.5-latest": {
+ "description": "我们仍在维护的老版本模型,经过多轮迭代有着极其优异且稳定的性能,包含 7B、20B 多种模型参数量可选,支持 1M 的上下文长度以及更强的指令跟随和工具调用能力。默认指向我们最新发布的 InternLM2.5 系列模型,当前指向 internlm2.5-20b-chat。"
+ },
+ "internlm3-latest": {
+ "description": "我们最新的模型系列,有着卓越的推理性能,领跑同量级开源模型。默认指向我们最新发布的 InternLM3 系列模型,当前指向 internlm3-8b-instruct。"
+ },
+ "jina-deepsearch-v1": {
+ "description": "深度搜索结合了网络搜索、阅读和推理,可进行全面调查。您可以将其视为一个代理,接受您的研究任务 - 它会进行广泛搜索并经过多次迭代,然后才能给出答案。这个过程涉及持续的研究、推理和从各个角度解决问题。这与直接从预训练数据生成答案的标准大模型以及依赖一次性表面搜索的传统 RAG 系统有着根本的不同。"
+ },
+ "kimi-latest": {
+ "description": "Kimi 智能助手产品使用最新的 Kimi 大模型,可能包含尚未稳定的特性。支持图片理解,同时会自动根据请求的上下文长度选择 8k/32k/128k 模型作为计费模型"
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct 模型,具备70B参数,能在大型文本生成和指示任务中提供卓越性能。"
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM 是一个实验性的、特定于任务的语言模型,经过训练以符合学习科学原则,可在教学和学习场景中遵循系统指令,充当专家导师等。"
+ },
+ "lite": {
+ "description": "Spark Lite 是一款轻量级大语言模型,具备极低的延迟与高效的处理能力,完全免费开放,支持实时在线搜索功能。其快速响应的特性使其在低算力设备上的推理应用和模型微调中表现出色,为用户带来出色的成本效益和智能体验,尤其在知识问答、内容生成及搜索场景下表现不俗。"
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B 提供更强大的AI推理能力,适合复杂应用,支持超多的计算处理并保证高效和准确率。"
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B 是一款高效能模型,提供了快速的文本生成能力,非常适合需要大规模效率和成本效益的应用场景。"
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct 模型,具备8B参数,支持画面指示任务的高效执行,提供优质的文本生成能力。"
+ "llama-3.2-11b-vision-instruct": {
+ "description": "在高分辨率图像上表现出色的图像推理能力,适用于视觉理解应用。"
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Online 模型,具备405B参数,支持约127,000个标记的上下文长度,设计用于复杂的在线聊天应用。"
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chat 模型,具备70B参数,支持约127,000个标记的上下文长度,适合于复杂的离线聊天任务。"
+ "llama-3.2-90b-vision-instruct": {
+ "description": "适用于视觉理解代理应用的高级图像推理能力。"
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Online 模型,具备70B参数,支持约127,000个标记的上下文长度,适用于高容量和多样化聊天任务。"
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chat 模型,具备8B参数,专为离线聊天设计,支持约127,000个标记的上下文长度。"
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先进的多语言开源大型语言模型,以极低成本体验媲美 405B 模型的性能。基于 Transformer 结构,并通过监督微调(SFT)和人类反馈强化学习(RLHF)提升有用性和安全性。其指令调优版本专为多语言对话优化,在多项行业基准上表现优于众多开源和封闭聊天模型。知识截止日期为 2023 年 12 月"
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Online 模型,具备8B参数,支持约127,000个标记的上下文长度,专为在线聊天设计,能高效处理各种文本交互。"
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 多语言大语言模型 ( LLM ) 是 70B(文本输入/文本输出)中的预训练和指令调整生成模型。 Llama 3.3 指令调整的纯文本模型针对多语言对话用例进行了优化,并且在常见行业基准上优于许多可用的开源和封闭式聊天模型。"
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B 提供无与伦比的复杂性处理能力,为高要求项目量身定制。"
@@ -565,29 +1187,53 @@
"mathstral": {
"description": "MathΣtral 专为科学研究和数学推理设计,提供有效的计算能力和结果解释。"
},
+ "max-32k": {
+ "description": "Spark Max 32K 配置了大上下文处理能力,更强的上下文理解和逻辑推理能力,支持32K tokens的文本输入,适用于长文档阅读、私有知识问答等场景"
+ },
"meta-llama-3-70b-instruct": {
- "description": "A powerful 70-billion parameter model excelling in reasoning, coding, and broad language applications."
+ "description": "一个强大的700亿参数模型,在推理、编码和广泛的语言应用方面表现出色。"
},
"meta-llama-3-8b-instruct": {
- "description": "A versatile 8-billion parameter model optimized for dialogue and text generation tasks."
+ "description": "一个多功能的80亿参数模型,针对对话和文本生成任务进行了优化。"
},
"meta-llama-3.1-405b-instruct": {
- "description": "The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks."
+ "description": "Llama 3.1指令调优的文本模型,针对多语言对话用例进行了优化,在许多可用的开源和封闭聊天模型中,在常见行业基准上表现优异。"
},
"meta-llama-3.1-70b-instruct": {
- "description": "The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks."
+ "description": "Llama 3.1指令调优的文本模型,针对多语言对话用例进行了优化,在许多可用的开源和封闭聊天模型中,在常见行业基准上表现优异。"
},
"meta-llama-3.1-8b-instruct": {
- "description": "The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks."
+ "description": "Llama 3.1指令调优的文本模型,针对多语言对话用例进行了优化,在许多可用的开源和封闭聊天模型中,在常见行业基准上表现优异。"
},
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) 提供优秀的语言处理能力和出色的交互体验。"
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 提供优秀的语言处理能力和出色的交互体验。"
+ },
"meta-llama/Llama-3-70b-chat-hf": {
- "description": "LLaMA-3 Chat (70B) 是功能强大的聊天模型,支持复杂的对话需求。"
+ "description": "Llama 3 70B Instruct Reference 是功能强大的聊天模型,支持复杂的对话需求。"
},
"meta-llama/Llama-3-8b-chat-hf": {
- "description": "LLaMA-3 Chat (8B) 提供多语言支持,涵盖丰富的领域知识。"
+ "description": "Llama 3 8B Instruct Reference 提供多语言支持,涵盖丰富的领域知识。"
+ },
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先进的多语言开源大型语言模型,以极低成本体验媲美 405B 模型的性能。基于 Transformer 结构,并通过监督微调(SFT)和人类反馈强化学习(RLHF)提升有用性和安全性。其指令调优版本专为多语言对话优化,在多项行业基准上表现优于众多开源和封闭聊天模型。知识截止日期为 2023 年 12 月"
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 多语言大语言模型 ( LLM ) 是 70B(文本输入/文本输出)中的预训练和指令调整生成模型。 Llama 3.3 指令调整的纯文本模型针对多语言对话用例进行了优化,并且在常见行业基准上优于许多可用的开源和封闭式聊天模型。"
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
},
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite 适合需要高效能和低延迟的环境。"
@@ -602,19 +1248,22 @@
"description": "Llama 3 8B Instruct Turbo 是一款高效能的大语言模型,支持广泛的应用场景。"
},
"meta-llama/Meta-Llama-3.1-405B-Instruct": {
- "description": "LLaMA 3.1 405B 指令微调模型针对多语言对话场景进行了优化。"
+ "description": "Llama 3.1 是 Meta 推出的领先模型,支持高达 405B 参数,可应用于复杂对话、多语言翻译和数据分析领域。"
},
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "405B 的 Llama 3.1 Turbo 模型,为大数据处理提供超大容量的上下文支持,在超大规模的人工智能应用中表现突出。"
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 是 Meta 推出的领先模型,支持高达 405B 参数,可应用于复杂对话、多语言翻译和数据分析领域。"
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
- "description": "LLaMA 3.1 70B 提供多语言的高效对话支持。"
+ "description": "Meta Llama 3.1 是由 Meta 开发的多语言大型语言模型家族,包括 8B、70B 和 405B 三种参数规模的预训练和指令微调变体。该 70B 指令微调模型针对多语言对话场景进行了优化,在多项行业基准测试中表现优异。模型训练使用了超过 15 万亿个 tokens 的公开数据,并采用了监督微调和人类反馈强化学习等技术来提升模型的有用性和安全性。Llama 3.1 支持文本生成和代码生成,知识截止日期为 2023 年 12 月"
},
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
"description": "Llama 3.1 70B 模型经过精细调整,适用于高负载应用,量化至FP8提供更高效的计算能力和准确性,确保在复杂场景中的卓越表现。"
},
"meta-llama/Meta-Llama-3.1-8B-Instruct": {
- "description": "LLaMA 3.1 提供多语言支持,是业界领先的生成模型之一。"
+ "description": "Meta Llama 3.1 是由 Meta 开发的多语言大型语言模型家族,包括 8B、70B 和 405B 三种参数规模的预训练和指令微调变体。该 8B 指令微调模型针对多语言对话场景进行了优化,在多项行业基准测试中表现优异。模型训练使用了超过 15 万亿个 tokens 的公开数据,并采用了监督微调和人类反馈强化学习等技术来提升模型的有用性和安全性。Llama 3.1 支持文本生成和代码生成,知识截止日期为 2023 年 12 月"
},
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
"description": "Llama 3.1 8B 模型采用FP8量化,支持高达131,072个上下文标记,是开源模型中的佼佼者,适合复杂任务,表现优异于许多行业基准。"
@@ -625,18 +1274,30 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct 优化了高质量对话场景,性能优于许多闭源模型。"
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct 是 Meta最新推出的版本,优化用于生成高质量对话,超越了许多领导闭源模型。"
- },
"meta-llama/llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct 专为高质量对话而设计,在人类评估中表现突出,特别适合高交互场景。"
+ "description": "Meta最新一代的Llama 3.1模型系列,70B(700亿参数)的指令微调版本针对高质量对话场景进行了优化。在业界评估中,与领先的闭源模型相比,它展现出了强劲的性能。(仅针对企业实名认证通过主体开放)"
},
"meta-llama/llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct 是 Meta 推出的最新版本,优化了高质量对话场景,表现优于许多领先的闭源模型。"
+ "description": "Meta最新一代的Llama 3.1模型系列,8B(80亿参数)的指令微调版本特别快速高效。在业界评估中,表现出强劲的性能,超越了很多领先的闭源模型。(仅针对企业实名认证通过主体开放)"
},
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 提供多语言支持,是业界领先的生成模型之一。"
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 旨在处理结合视觉和文本数据的任务。它在图像描述和视觉问答等任务中表现出色,跨越了语言生成和视觉推理之间的鸿沟。"
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先进的多语言开源大型语言模型,以极低成本体验媲美 405B 模型的性能。基于 Transformer 结构,并通过监督微调(SFT)和人类反馈强化学习(RLHF)提升有用性和安全性。其指令调优版本专为多语言对话优化,在多项行业基准上表现优于众多开源和封闭聊天模型。知识截止日期为 2023 年 12 月"
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 是 Llama 系列最先进的多语言开源大型语言模型,以极低成本体验媲美 405B 模型的性能。基于 Transformer 结构,并通过监督微调(SFT)和人类反馈强化学习(RLHF)提升有用性和安全性。其指令调优版本专为多语言对话优化,在多项行业基准上表现优于众多开源和封闭聊天模型。知识截止日期为 2023 年 12 月"
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct 是 Llama 3.1 Instruct 模型中最大、最强大的模型,是一款高度先进的对话推理和合成数据生成模型,也可以用作在特定领域进行专业持续预训练或微调的基础。Llama 3.1 提供的多语言大型语言模型 (LLMs) 是一组预训练的、指令调整的生成模型,包括 8B、70B 和 405B 大小 (文本输入/输出)。Llama 3.1 指令调整的文本模型 (8B、70B、405B) 专为多语言对话用例进行了优化,并在常见的行业基准测试中超过了许多可用的开源聊天模型。Llama 3.1 旨在用于多种语言的商业和研究用途。指令调整的文本模型适用于类似助手的聊天,而预训练模型可以适应各种自然语言生成任务。Llama 3.1 模型还支持利用其模型的输出来改进其他模型,包括合成数据生成和精炼。Llama 3.1 是使用优化的变压器架构的自回归语言模型。调整版本使用监督微调 (SFT) 和带有人类反馈的强化学习 (RLHF) 来符合人类对帮助性和安全性的偏好。"
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 是一款面向开发者、研究人员和企业的开放大型语言模型 (LLM),旨在帮助他们构建、实验并负责任地扩展他们的生成 AI 想法。作为全球社区创新的基础系统的一部分,它非常适合计算能力和资源有限、边缘设备和更快的训练时间。"
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B 是微软AI最新的快速轻量化模型,性能接近于现有开源领导模型的10倍。"
+ "meta/llama-3.1-405b-instruct": {
+ "description": "高级 LLM,支持合成数据生成、知识蒸馏和推理,适用于聊天机器人、编程和特定领域任务。"
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "赋能复杂对话,具备卓越的上下文理解、推理能力和文本生成能力。"
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "先进的最尖端模型,具备语言理解、卓越的推理能力和文本生成能力。"
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "尖端的视觉-语言模型,擅长从图像中进行高质量推理。"
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "先进的最尖端小型语言模型,具备语言理解、卓越的推理能力和文本生成能力。"
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "先进的最尖端小型语言模型,具备语言理解、卓越的推理能力和文本生成能力。"
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "尖端的视觉-语言模型,擅长从图像中进行高质量推理。"
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "先进的 LLM,擅长推理、数学、常识和函数调用。"
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 是微软AI提供的语言模型,在复杂对话、多语言、推理和智能助手领域表现尤为出色。"
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B 是微软AI最先进的Wizard模型,显示出极其竞争力的表现。"
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V 是 OpenBMB 推出的新一代多模态大模型,具备卓越的 OCR 识别和多模态理解能力,支持广泛的应用场景。"
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B 是Mistral的世界顶级边缘模型。"
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B 是Mistral的性价比极高的边缘模型。"
+ },
"mistral": {
"description": "Mistral 是 Mistral AI 发布的 7B 模型,适合多变的语言处理需求。"
},
"mistral-large": {
"description": "Mixtral Large 是 Mistral 的旗舰模型,结合代码生成、数学和推理的能力,支持 128k 上下文窗口。"
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407) is an advanced Large Language Model (LLM) with state-of-the-art reasoning, knowledge and coding capabilities."
- },
"mistral-large-latest": {
"description": "Mistral Large是旗舰大模型,擅长多语言任务、复杂推理和代码生成,是高端应用的理想选择。"
},
@@ -677,7 +1365,7 @@
"description": "Mistral Nemo 由 Mistral AI 和 NVIDIA 合作推出,是高效性能的 12B 模型。"
},
"mistral-small": {
- "description": "Mistral Small can be used on any language-based task that requires high efficiency and low latency."
+ "description": "Mistral Small可用于任何需要高效率和低延迟的基于语言的任务。"
},
"mistral-small-latest": {
"description": "Mistral Small是成本效益高、快速且可靠的选项,适用于翻译、摘要和情感分析等用例。"
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 提供高效的计算能力和自然语言理解,适合广泛的应用。"
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B是一款紧凑但高性能的模型,擅长批量处理和简单任务,如分类和文本生成,具有良好的推理能力。"
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) 是一款超级大语言模型,支持极高的处理需求。"
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral-8x7B Instruct (46.7B) 提供高容量的计算框架,适合大规模数据处理。"
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B是一个稀疏专家模型,利用多个参数提高推理速度,适合处理多语言和代码生成任务。"
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct 是一款兼有速度优化和长上下文支持的高性能行业标准模型。"
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K 是一款拥有超长上下文处理能力的模型,适用于生成超长文本,满足复杂的生成任务需求,能够处理多达128,000个tokens的内容,非常适合科研、学术和大型文档生成等应用场景。"
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Kimi 视觉模型(包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 等)能够理解图片内容,包括图片文字、图片颜色和物体形状等内容。"
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K 提供中等长度的上下文处理能力,能够处理32,768个tokens,特别适合生成各种长文档和复杂对话,应用于内容创作、报告生成和对话系统等领域。"
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Kimi 视觉模型(包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 等)能够理解图片内容,包括图片文字、图片颜色和物体形状等内容。"
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K 专为生成短文本任务设计,具有高效的处理性能,能够处理8,192个tokens,非常适合简短对话、速记和快速内容生成。"
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Kimi 视觉模型(包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 等)能够理解图片内容,包括图片文字、图片颜色和物体形状等内容。"
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto 可以根据当前上下文占用的 Tokens 数量来选择合适的模型"
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B 是 Nous Hermes 2的升级版本,包含最新的内部开发的数据集。"
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B 是由 NVIDIA 定制的大型语言模型,旨在提高 LLM 生成的响应对用户查询的帮助程度。该模型在 Arena Hard、AlpacaEval 2 LC 和 GPT-4-Turbo MT-Bench 等基准测试中表现出色,截至 2024 年 10 月 1 日,在所有三个自动对齐基准测试中排名第一。该模型使用 RLHF(特别是 REINFORCE)、Llama-3.1-Nemotron-70B-Reward 和 HelpSteer2-Preference 提示在 Llama-3.1-70B-Instruct 模型基础上进行训练"
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "独特的语言模型,提供无与伦比的准确性和效率表现。"
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 定制的大型语言模型,旨在提高 LLM 生成的响应的帮助性。"
+ },
+ "o1": {
+ "description": "o1是OpenAI新的推理模型,支持图文输入并输出文本,适用于需要广泛通用知识的复杂任务。该模型具有200K上下文和2023年10月的知识截止日期。"
+ },
"o1-mini": {
"description": "o1-mini是一款针对编程、数学和科学应用场景而设计的快速、经济高效的推理模型。该模型具有128K上下文和2023年10月的知识截止日期。"
},
"o1-preview": {
"description": "o1是OpenAI新的推理模型,适用于需要广泛通用知识的复杂任务。该模型具有128K上下文和2023年10月的知识截止日期。"
},
+ "o3-mini": {
+ "description": "o3-mini 是我们最新的小型推理模型,在与 o1-mini 相同的成本和延迟目标下提供高智能。"
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba是专注于代码生成的Mamba 2语言模型,为先进的代码和推理任务提供强力支持。"
},
@@ -745,7 +1466,7 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B是一个稀疏专家模型,利用多个参数提高推理速度,适合处理多语言和代码生成任务。"
},
- "openai/gpt-4o-2024-08-06": {
+ "openai/gpt-4o": {
"description": "ChatGPT-4o 是一款动态模型,实时更新以保持当前最新版本。它结合了强大的语言理解与生成能力,适合于大规模应用场景,包括客户服务、教育和技术支持。"
},
"openai/gpt-4o-mini": {
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Pixtral 模型在图表和图理解、文档问答、多模态推理和指令遵循等任务上表现出强大的能力,能够以自然分辨率和宽高比摄入图像,还能够在长达 128K 令牌的长上下文窗口中处理任意数量的图像。"
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large 是一款拥有 1240 亿参数的开源多模态模型,基于 Mistral Large 2 构建。这是我们多模态家族中的第二款模型,展现了前沿水平的图像理解能力。"
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K 配置了特大上下文处理能力,能够处理多达128K的上下文信息,特别适合需通篇分析和长期逻辑关联处理的长文内容,可在复杂文本沟通中提供流畅一致的逻辑与多样的引用支持。"
+ },
+ "qvq-72b-preview": {
+ "description": "QVQ模型是由 Qwen 团队开发的实验性研究模型,专注于提升视觉推理能力,尤其在数学推理领域。"
+ },
+ "qwen-coder-plus-latest": {
+ "description": "通义千问代码模型。"
+ },
"qwen-coder-turbo-latest": {
"description": "通义千问代码模型。"
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "通义千问数学模型是专门用于数学解题的语言模型。"
},
+ "qwen-max": {
+ "description": "通义千问千亿级别超大规模语言模型,支持中文、英文等不同语言输入,当前通义千问2.5产品版本背后的API模型。"
+ },
"qwen-max-latest": {
"description": "通义千问千亿级别超大规模语言模型,支持中文、英文等不同语言输入,当前通义千问2.5产品版本背后的API模型。"
},
+ "qwen-omni-turbo-latest": {
+ "description": "Qwen-Omni 系列模型支持输入多种模态的数据,包括视频、音频、图片、文本,并输出音频与文本。"
+ },
+ "qwen-plus": {
+ "description": "通义千问超大规模语言模型增强版,支持中文、英文等不同语言输入。"
+ },
"qwen-plus-latest": {
"description": "通义千问超大规模语言模型增强版,支持中文、英文等不同语言输入。"
},
+ "qwen-turbo": {
+ "description": "通义千问超大规模语言模型,支持中文、英文等不同语言输入。"
+ },
"qwen-turbo-latest": {
"description": "通义千问超大规模语言模型,支持中文、英文等不同语言输入。"
},
"qwen-vl-chat-v1": {
"description": "通义千问VL支持灵活的交互方式,包括多图、多轮问答、创作等能力的模型。"
},
- "qwen-vl-max": {
+ "qwen-vl-max-latest": {
"description": "通义千问超大规模视觉语言模型。相比增强版,再次提升视觉推理能力和指令遵循能力,提供更高的视觉感知和认知水平。"
},
- "qwen-vl-plus": {
+ "qwen-vl-ocr-latest": {
+ "description": "通义千问OCR是文字提取专有模型,专注于文档、表格、试题、手写体文字等类型图像的文字提取能力。它能够识别多种文字,目前支持的语言有:汉语、英语、法语、日语、韩语、德语、俄语、意大利语、越南语、阿拉伯语。"
+ },
+ "qwen-vl-plus-latest": {
"description": "通义千问大规模视觉语言模型增强版。大幅提升细节识别能力和文字识别能力,支持超百万像素分辨率和任意长宽比规格的图像。"
},
"qwen-vl-v1": {
"description": "以 Qwen-7B 语言模型初始化,添加图像模型,图像输入分辨率为448的预训练模型。"
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2是全新的Qwen大型语言模型系列。Qwen2 7B是一个基于transformer的模型,在语言理解、多语言能力、编程、数学和推理方面表现出色。"
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 是全新的大型语言模型系列,具有更强的理解和生成能力。"
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL 是 Qwen-VL 模型的最新迭代版本,在视觉理解基准测试中达到了最先进的性能,包括 MathVista、DocVQA、RealWorldQA 和 MTVQA 等。Qwen2-VL 能够理解超过 20 分钟的视频,用于高质量的基于视频的问答、对话和内容创作。它还具备复杂推理和决策能力,可以与移动设备、机器人等集成,基于视觉环境和文本指令进行自动操作。除了英语和中文,Qwen2-VL 现在还支持理解图像中不同语言的文本,包括大多数欧洲语言、日语、韩语、阿拉伯语和越南语等"
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct 是阿里云发布的最新大语言模型系列之一。该 72B 模型在编码和数学等领域具有显著改进的能力。该模型还提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升。"
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct 是阿里云发布的最新大语言模型系列之一。该 32B 模型在编码和数学等领域具有显著改进的能力。该模型提供了多语言支持,覆盖超过 29 种语言,包括中文、英文等。模型在指令跟随、理解结构化数据以及生成结构化输出(尤其是 JSON)方面都有显著提升。"
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "面向中文和英文的 LLM,针对语言、编程、数学、推理等领域。"
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "高级 LLM,支持代码生成、推理和修复,涵盖主流编程语言。"
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "强大的中型代码模型,支持 32K 上下文长度,擅长多语言编程。"
+ },
"qwen2": {
"description": "Qwen2 是阿里巴巴的新一代大规模语言模型,以优异的性能支持多元化的应用需求。"
},
+ "qwen2.5": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大规模语言模型,以优异的性能支持多元化的应用需求。"
+ },
"qwen2.5-14b-instruct": {
"description": "通义千问2.5对外开源的14B规模的模型。"
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "通义千问2.5对外开源的72B规模的模型。"
+ },
"qwen2.5-32b-instruct": {
"description": "通义千问2.5对外开源的32B规模的模型。"
},
@@ -826,6 +1601,9 @@
"qwen2.5-coder-1.5b-instruct": {
"description": "通义千问代码模型开源版。"
},
+ "qwen2.5-coder-32b-instruct": {
+ "description": "通义千问代码模型开源版。"
+ },
"qwen2.5-coder-7b-instruct": {
"description": "通义千问代码模型开源版。"
},
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Qwen-Math 模型具有强大的数学解题能力。"
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "指令跟随、数学、解题、代码整体提升,万物识别能力提升,支持多样格式直接精准定位视觉元素,支持对长视频文件(最长10分钟)进行理解和秒级别的事件时刻定位,能理解时间先后和快慢,基于解析和定位能力支持操控OS或Mobile的Agent,关键信息抽取能力和Json格式输出能力强,此版本为72B版本,本系列能力最强的版本。"
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "指令跟随、数学、解题、代码整体提升,万物识别能力提升,支持多样格式直接精准定位视觉元素,支持对长视频文件(最长10分钟)进行理解和秒级别的事件时刻定位,能理解时间先后和快慢,基于解析和定位能力支持操控OS或Mobile的Agent,关键信息抽取能力和Json格式输出能力强,此版本为72B版本,本系列能力最强的版本。"
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大规模语言模型,以优异的性能支持多元化的应用需求。"
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大规模语言模型,以优异的性能支持多元化的应用需求。"
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大规模语言模型,以优异的性能支持多元化的应用需求。"
+ },
"qwen2:0.5b": {
"description": "Qwen2 是阿里巴巴的新一代大规模语言模型,以优异的性能支持多元化的应用需求。"
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 是阿里巴巴的新一代大规模语言模型,以优异的性能支持多元化的应用需求。"
},
- "solar-1-mini-chat": {
+ "qwq": {
+ "description": "QwQ 是一个实验研究模型,专注于提高 AI 推理能力。"
+ },
+ "qwq-32b": {
+ "description": "基于 Qwen2.5-32B 模型训练的 QwQ 推理模型,通过强化学习大幅度提升了模型推理能力。模型数学代码等核心指标(AIME 24/25、LiveCodeBench)以及部分通用指标(IFEval、LiveBench等)达到DeepSeek-R1 满血版水平,各指标均显著超过同样基于 Qwen2.5-32B 的 DeepSeek-R1-Distill-Qwen-32B。"
+ },
+ "qwq-32b-preview": {
+ "description": "QwQ模型是由 Qwen 团队开发的实验性研究模型,专注于增强 AI 推理能力。"
+ },
+ "qwq-plus-latest": {
+ "description": "基于 Qwen2.5 模型训练的 QwQ 推理模型,通过强化学习大幅度提升了模型推理能力。模型数学代码等核心指标(AIME 24/25、LiveCodeBench)以及部分通用指标(IFEval、LiveBench等)达到DeepSeek-R1 满血版水平。"
+ },
+ "r1-1776": {
+ "description": "R1-1776 是 DeepSeek R1 模型的一个版本,经过后训练,可提供未经审查、无偏见的事实信息。"
+ },
+ "solar-mini": {
"description": "Solar Mini 是一种紧凑型 LLM,性能优于 GPT-3.5,具备强大的多语言能力,支持英语和韩语,提供高效小巧的解决方案。"
},
- "solar-1-mini-chat-ja": {
+ "solar-mini-ja": {
"description": "Solar Mini (Ja) 扩展了 Solar Mini 的能力,专注于日语,同时在英语和韩语的使用中保持高效和卓越性能。"
},
"solar-pro": {
"description": "Solar Pro 是 Upstage 推出的一款高智能LLM,专注于单GPU的指令跟随能力,IFEval得分80以上。目前支持英语,正式版本计划于2024年11月推出,将扩展语言支持和上下文长度。"
},
+ "sonar": {
+ "description": "基于搜索上下文的轻量级搜索产品,比 Sonar Pro 更快、更便宜。"
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research 进行全面的专家级研究,并将其综合成可访问、可作的报告。"
+ },
+ "sonar-pro": {
+ "description": "支持搜索上下文的高级搜索产品,支持高级查询和跟进。"
+ },
+ "sonar-reasoning": {
+ "description": "支持搜索上下文的高级搜索产品,支持高级查询和跟进。"
+ },
+ "sonar-reasoning-pro": {
+ "description": "支持搜索上下文的高级搜索产品,支持高级查询和跟进。"
+ },
"step-1-128k": {
"description": "平衡性能与成本,适合一般场景。"
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "高速模型,适合实时对话。"
},
+ "step-1.5v-mini": {
+ "description": "该模型拥有强大的视频理解能力。"
+ },
+ "step-1o-turbo-vision": {
+ "description": "该模型拥有强大的图像理解能力,在数理、代码领域强于1o。模型比1o更小,输出速度更快。"
+ },
+ "step-1o-vision-32k": {
+ "description": "该模型拥有强大的图像理解能力。相比于 step-1v 系列模型,拥有更强的视觉性能。"
+ },
"step-1v-32k": {
"description": "支持视觉输入,增强多模态交互体验。"
},
@@ -878,20 +1710,47 @@
"description": "小型视觉模型,适合基本的图文任务。"
},
"step-2-16k": {
- "description": "支持大规模上下文交互,适合复杂对话场景。"
+ "description": "step-2模型的实验版本,包含最新的特性,滚动更新中。不推荐在正式生产环境使用。"
+ },
+ "step-2-mini": {
+ "description": "基于新一代自研Attention架构MFA的极速大模型,用极低成本达到和step1类似的效果,同时保持了更高的吞吐和更快响应时延。能够处理通用任务,在代码能力上具备特长。"
},
"taichu_llm": {
- "description": "Taichu 2.0 基于海量高质数据训练,具有更强的文本理解、内容创作、对话问答等能力"
+ "description": "基于海量高质数据训练,具有更强的文本理解、内容创作、对话问答等能力"
+ },
+ "taichu_vl": {
+ "description": "融合了图像理解、知识迁移、逻辑归因等能力,在图文问答领域表现突出"
+ },
+ "text-embedding-3-large": {
+ "description": "最强大的向量化模型,适用于英文和非英文任务"
},
- "taichu_vqa": {
- "description": "Taichu 2.0V 融合了图像理解、知识迁移、逻辑归因等能力,在图文问答领域表现突出"
+ "text-embedding-3-small": {
+ "description": "高效且经济的新一代 Embedding 模型,适用于知识检索、RAG 应用等场景"
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "智谱AI发布的GLM-4系列最新一代预训练模型的开源版本。"
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) 通过高效的策略和模型架构,提供增强的计算能力。"
},
+ "tts-1": {
+ "description": "最新的文本转语音模型,针对实时场景优化速度"
+ },
+ "tts-1-hd": {
+ "description": "最新的文本转语音模型,针对质量进行优化"
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) 适用于精细化指令任务,提供出色的语言处理能力。"
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet 提升了行业标准,性能超过竞争对手模型和 Claude 3 Opus,在广泛的评估中表现出色,同时具有我们中等层级模型的速度和成本。"
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet 是 Anthropic 最快的下一代模型。与 Claude 3 Haiku 相比,Claude 3.7 Sonnet 在各项技能上都有所提升,并在许多智力基准测试中超越了上一代最大的模型 Claude 3 Opus。"
+ },
+ "whisper-1": {
+ "description": "通用语音识别模型,支持多语言语音识别、语音翻译和语言识别"
+ },
"wizardlm2": {
"description": "WizardLM 2 是微软AI提供的语言模型,在复杂对话、多语言、推理和智能助手领域表现尤为出色。"
},
@@ -905,7 +1764,7 @@
"description": "在 yi-large 模型的基础上支持并强化了工具调用的能力,适用于各种需要搭建 agent 或 workflow 的业务场景。"
},
"yi-large-preview": {
- "description": "初期版本,推荐使用 yi-large(新版本)"
+ "description": "初期版本,推荐使用 yi-large(新版本)。"
},
"yi-large-rag": {
"description": "基于 yi-large 超强模型的高阶服务,结合检索与生成技术提供精准答案,实时全网检索信息服务。"
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "超高性价比、卓越性能。根据性能和推理速度、成本,进行平衡性高精度调优。"
},
+ "yi-lightning": {
+ "description": "最新高性能模型,保证高质量输出同时,推理速度大幅提升。"
+ },
+ "yi-lightning-lite": {
+ "description": "轻量化版本,推荐使用 yi-lightning。"
+ },
"yi-medium": {
"description": "中型尺寸模型升级微调,能力均衡,性价比高。深度优化指令遵循能力。"
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "复杂视觉任务模型,提供高性能图片理解、分析能力。"
+ },
+ "yi-vision-v2": {
+ "description": "复杂视觉任务模型,提供基于多张图片的高性能理解、分析能力。"
}
}
diff --git a/DigitalHumanWeb/locales/zh-CN/plugin.json b/DigitalHumanWeb/locales/zh-CN/plugin.json
index 2e34b69..8142c53 100644
--- a/DigitalHumanWeb/locales/zh-CN/plugin.json
+++ b/DigitalHumanWeb/locales/zh-CN/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "插件 {{name}} 刷新失败",
"urlError": "该链接没有返回 JSON 格式的内容, 请确保是有效的链接"
},
+ "inspector": {
+ "args": "查看参数列表",
+ "pluginRender": "查看插件界面"
+ },
"list": {
"item": {
"deprecated.title": "已删除",
@@ -130,6 +134,34 @@
"plugin": "插件运行中..."
},
"pluginList": "插件列表",
+ "search": {
+ "config": {
+ "addKey": "添加秘钥",
+ "close": "删除",
+ "confirm": "已完成配置并重试"
+ },
+ "crawPages": {
+ "crawling": "链接识别中",
+ "detail": {
+ "preview": "预览",
+ "raw": "原始文本",
+ "tooLong": "文本内容过长,对话上下文仅保留前 {{characters}} 字符,超过部分不计入会话上下文"
+ },
+ "meta": {
+ "crawler": "抓取模式",
+ "words": "字符数"
+ }
+ },
+ "searchxng": {
+ "baseURL": "请输入",
+ "description": "请输入 SearchXNG 的网址,即可开始联网搜索",
+ "keyPlaceholder": "请输入秘钥",
+ "title": "配置 SearchXNG 搜索引擎",
+ "unconfiguredDesc": "请联系管理员完成 SearchXNG 搜索引擎配置,即可开始联网搜索",
+ "unconfiguredTitle": "暂未配置 SearchXNG 搜索引擎"
+ },
+ "title": "联网搜索"
+ },
"setting": "插件设置",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/zh-CN/portal.json b/DigitalHumanWeb/locales/zh-CN/portal.json
index 666b4c3..19d917f 100644
--- a/DigitalHumanWeb/locales/zh-CN/portal.json
+++ b/DigitalHumanWeb/locales/zh-CN/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "插件",
- "actions": {
- "genAiMessage": "创建助手消息",
- "summary": "总结",
- "summaryTooltip": "总结当前内容"
- },
"artifacts": {
"display": {
"code": "代码",
diff --git a/DigitalHumanWeb/locales/zh-CN/providers.json b/DigitalHumanWeb/locales/zh-CN/providers.json
index 9b74fb2..dcd0483 100644
--- a/DigitalHumanWeb/locales/zh-CN/providers.json
+++ b/DigitalHumanWeb/locales/zh-CN/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs 为企业构建基础模型和人工智能系统,加速生成性人工智能在生产中的应用。"
+ },
"ai360": {
"description": "360 AI 是 360 公司推出的 AI 模型和服务平台,提供多种先进的自然语言处理模型,包括 360GPT2 Pro、360GPT Pro、360GPT Turbo 和 360GPT Turbo Responsibility 8K。这些模型结合了大规模参数和多模态能力,广泛应用于文本生成、语义理解、对话系统与代码生成等领域。通过灵活的定价策略,360 AI 满足多样化用户需求,支持开发者集成,推动智能化应用的革新和发展。"
},
@@ -9,27 +11,57 @@
"azure": {
"description": "Azure 提供多种先进的AI模型,包括GPT-3.5和最新的GPT-4系列,支持多种数据类型和复杂任务,致力于安全、可靠和可持续的AI解决方案。"
},
+ "azureai": {
+ "description": "Azure 提供多种先进的AI模型,包括GPT-3.5和最新的GPT-4系列,支持多种数据类型和复杂任务,致力于安全、可靠和可持续的AI解决方案。"
+ },
"baichuan": {
"description": "百川智能是一家专注于人工智能大模型研发的公司,其模型在国内知识百科、长文本处理和生成创作等中文任务上表现卓越,超越了国外主流模型。百川智能还具备行业领先的多模态能力,在多项权威评测中表现优异。其模型包括 Baichuan 4、Baichuan 3 Turbo 和 Baichuan 3 Turbo 128k 等,分别针对不同应用场景进行优化,提供高性价比的解决方案。"
},
"bedrock": {
"description": "Bedrock 是亚马逊 AWS 提供的一项服务,专注于为企业提供先进的 AI 语言模型和视觉模型。其模型家族包括 Anthropic 的 Claude 系列、Meta 的 Llama 3.1 系列等,涵盖从轻量级到高性能的多种选择,支持文本生成、对话、图像处理等多种任务,适用于不同规模和需求的企业应用。"
},
+ "cloudflare": {
+ "description": "在 Cloudflare 的全球网络上运行由无服务器 GPU 驱动的机器学习模型。"
+ },
"deepseek": {
- "description": "DeepSeek 是一家专注于人工智能技术研究和应用的公司,其最新模型 DeepSeek-V2.5 融合了通用对话和代码处理能力,并在人类偏好对齐、写作任务和指令跟随等方面实现了显著提升。"
+ "description": "DeepSeek 是一家专注于人工智能技术研究和应用的公司,其最新模型 DeepSeek-V3 多项评测成绩超越 Qwen2.5-72B 和 Llama-3.1-405B 等开源模型,性能对齐领军闭源模型 GPT-4o 与 Claude-3.5-Sonnet。"
+ },
+ "doubao": {
+ "description": "字节跳动推出的自研大模型。通过字节跳动内部50+业务场景实践验证,每日万亿级tokens大使用量持续打磨,提供多种模态能力,以优质模型效果为企业打造丰富的业务体验。"
},
"fireworksai": {
"description": "Fireworks AI 是一家领先的高级语言模型服务商,专注于功能调用和多模态处理。其最新模型 Firefunction V2 基于 Llama-3,优化用于函数调用、对话及指令跟随。视觉语言模型 FireLLaVA-13B 支持图像和文本混合输入。其他 notable 模型包括 Llama 系列和 Mixtral 系列,提供高效的多语言指令跟随与生成支持。"
},
+ "giteeai": {
+ "description": "Gitee AI 的 Serverless API 为 AI 开发者提供开箱即用的大模型推理 API 服务。"
+ },
"github": {
- "description": "With GitHub Models, developers can become AI engineers and build with the industry's leading AI models."
+ "description": "通过GitHub模型,开发人员可以成为AI工程师,并使用行业领先的AI模型进行构建。"
},
"google": {
- "description": "Google 的 Gemini 系列是其最先进、通用的 A I模型,由 Google DeepMind 打造,专为多模态设计,支持文本、代码、图像、音频和视频的无缝理解与处理。适用于从数据中心到移动设备的多种环境,极大提升了AI模型的效率与应用广泛性。"
+ "description": "Google 的 Gemini 系列是其最先进、通用的 AI模型,由 Google DeepMind 打造,专为多模态设计,支持文本、代码、图像、音频和视频的无缝理解与处理。适用于从数据中心到移动设备的多种环境,极大提升了AI模型的效率与应用广泛性。"
},
"groq": {
"description": "Groq 的 LPU 推理引擎在最新的独立大语言模型(LLM)基准测试中表现卓越,以其惊人的速度和效率重新定义了 AI 解决方案的标准。Groq 是一种即时推理速度的代表,在基于云的部署中展现了良好的性能。"
},
+ "higress": {
+ "description": "Higress 是一款云原生 API 网关,在阿里内部为解决 Tengine reload 对长连接业务有损,以及 gRPC/Dubbo 负载均衡能力不足而诞生。"
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API 提供了一种快速且免费的方式,让您可以探索成千上万种模型,适用于各种任务。无论您是在为新应用程序进行原型设计,还是在尝试机器学习的功能,这个 API 都能让您即时访问多个领域的高性能模型。"
+ },
+ "hunyuan": {
+ "description": "由腾讯研发的大语言模型,具备强大的中文创作能力,复杂语境下的逻辑推理能力,以及可靠的任务执行能力"
+ },
+ "internlm": {
+ "description": "致力于大模型研究与开发工具链的开源组织。为所有 AI 开发者提供高效、易用的开源平台,让最前沿的大模型与算法技术触手可及"
+ },
+ "jina": {
+ "description": "Jina AI 成立于 2020 年,是一家领先的搜索 AI 公司。我们的搜索底座平台包含了向量模型、重排器和小语言模型,可帮助企业构建可靠且高质量的生成式AI和多模态的搜索应用。"
+ },
+ "lmstudio": {
+ "description": "LM Studio 是一个用于在您的计算机上开发和实验 LLMs 的桌面应用程序。"
+ },
"minimax": {
"description": "MiniMax 是 2021 年成立的通用人工智能科技公司,致力于与用户共创智能。MiniMax 自主研发了不同模态的通用大模型,其中包括万亿参数的 MoE 文本大模型、语音大模型以及图像大模型。并推出了海螺 AI 等应用。"
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI 是一个提供多种大语言模型与 AI 图像生成的 API 服务的平台,灵活、可靠且具有成本效益。它支持 Llama3、Mistral 等最新的开源模型,并为生成式 AI 应用开发提供了全面、用户友好且自动扩展的 API 解决方案,适合 AI 初创公司的快速发展。"
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ 提供容器,可用于自托管 GPU 加速推理微服务,支持在云端、数据中心、RTX™ AI 个人电脑和工作站上部署预训练和自定义 AI 模型。"
+ },
"ollama": {
"description": "Ollama 提供的模型广泛涵盖代码生成、数学运算、多语种处理和对话互动等领域,支持企业级和本地化部署的多样化需求。"
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity 是一家领先的对话生成模型提供商,提供多种先进的Llama 3.1模型,支持在线和离线应用,特别适用于复杂的自然语言处理任务。"
},
+ "ppio": {
+ "description": "PPIO 派欧云提供稳定、高性价比的开源模型 API 服务,支持 DeepSeek 全系列、Llama、Qwen 等行业领先大模型。"
+ },
"qwen": {
"description": "通义千问是阿里云自主研发的超大规模语言模型,具有强大的自然语言理解和生成能力。它可以回答各种问题、创作文字内容、表达观点看法、撰写代码等,在多个领域发挥作用。"
},
+ "sambanova": {
+ "description": "SambaNova Cloud 可让开发者轻松使用最佳的开源模型,并享受最快的推理速度。"
+ },
+ "sensenova": {
+ "description": "商汤日日新,依托商汤大装置的强大的基础支撑,提供高效易用的全栈大模型服务。"
+ },
"siliconcloud": {
"description": "SiliconCloud,基于优秀开源基础模型的高性价比 GenAI 云服务"
},
@@ -69,14 +113,32 @@
"taichu": {
"description": "中科院自动化研究所和武汉人工智能研究院推出新一代多模态大模型,支持多轮问答、文本创作、图像生成、3D理解、信号分析等全面问答任务,拥有更强的认知、理解、创作能力,带来全新互动体验。"
},
+ "tencentcloud": {
+ "description": "知识引擎原子能力(LLM Knowledge Engine Atomic Power)基于知识引擎研发的知识问答全链路能力,面向企业及开发者,提供灵活组建及开发模型应用的能力。您可通过多款原子能力组建您专属的模型服务,调用文档解析、拆分、embedding、多轮改写等服务进行组装,定制企业专属 AI 业务。"
+ },
"togetherai": {
"description": "Together AI 致力于通过创新的 AI 模型实现领先的性能,提供广泛的自定义能力,包括快速扩展支持和直观的部署流程,满足企业的各种需求。"
},
"upstage": {
"description": "Upstage 专注于为各种商业需求开发AI模型,包括 Solar LLM 和文档 AI,旨在实现工作的人造通用智能(AGI)。通过 Chat API 创建简单的对话代理,并支持功能调用、翻译、嵌入以及特定领域应用。"
},
+ "vertexai": {
+ "description": "Google 的 Gemini 系列是其最先进、通用的 AI模型,由 Google DeepMind 打造,专为多模态设计,支持文本、代码、图像、音频和视频的无缝理解与处理。适用于从数据中心到移动设备的多种环境,极大提升了AI模型的效率与应用广泛性。"
+ },
+ "vllm": {
+ "description": "vLLM 是一个快速且易于使用的库,用于 LLM 推理和服务。"
+ },
+ "volcengine": {
+ "description": "字节跳动推出的大模型服务的开发平台,提供功能丰富、安全以及具备价格竞争力的模型调用服务,同时提供模型数据、精调、推理、评测等端到端功能,全方位保障您的 AI 应用开发落地。"
+ },
+ "wenxin": {
+ "description": "企业级一站式大模型与AI原生应用开发及服务平台,提供最全面易用的生成式人工智能模型开发、应用开发全流程工具链"
+ },
+ "xai": {
+ "description": "xAI 是一家致力于构建人工智能以加速人类科学发现的公司。我们的使命是推动我们对宇宙的共同理解。"
+ },
"zeroone": {
- "description": "01.AI 专注于AI 2.0时代的人工智能技术,大力推动“人+人工智能”的创新和应用,采用超强大模型和先进AI技术以提升人类生产力,实现技术赋能。"
+ "description": "零一万物致力于推动以人为本的AI 2.0技术革命,旨在通过大语言模型创造巨大的经济和社会价值,并开创新的AI生态与商业模式。"
},
"zhipu": {
"description": "智谱 AI 提供多模态与语言模型的开放平台,支持广泛的AI应用场景,包括文本处理、图像理解与编程辅助等。"
diff --git a/DigitalHumanWeb/locales/zh-CN/ragEval.json b/DigitalHumanWeb/locales/zh-CN/ragEval.json
index b6d8b10..5ba5140 100644
--- a/DigitalHumanWeb/locales/zh-CN/ragEval.json
+++ b/DigitalHumanWeb/locales/zh-CN/ragEval.json
@@ -88,4 +88,4 @@
"title": "评测任务列表"
}
}
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/setting.json b/DigitalHumanWeb/locales/zh-CN/setting.json
index fd18a5b..48eb3dc 100644
--- a/DigitalHumanWeb/locales/zh-CN/setting.json
+++ b/DigitalHumanWeb/locales/zh-CN/setting.json
@@ -1,6 +1,6 @@
{
"about": {
- "title": "插件设置"
+ "title": "关于"
},
"agentTab": {
"chat": "聊天偏好",
@@ -84,8 +84,7 @@
},
"modalTitle": "自定义模型配置",
"tokens": {
- "title": "最大 token 数",
- "unlimited": "无限制"
+ "title": "最大 token 数"
},
"vision": {
"extra": "此配置将仅开启应用中的图片上传配置,是否支持识别完全取决于模型本身,请自行测试该模型的视觉识别能力可用性",
@@ -98,6 +97,7 @@
"title": "使用客户端请求模式"
},
"fetcher": {
+ "clear": "清除获取的模型",
"fetch": "获取模型列表",
"fetching": "正在获取模型列表...",
"latestTime": "上次更新时间:{{time}}",
@@ -175,8 +175,8 @@
"desc": "会话过程中是否自动创建话题,仅在临时话题中生效",
"title": "自动创建话题"
},
- "enableCompressThreshold": {
- "title": "是否开启历史消息长度压缩阈值"
+ "enableCompressHistory": {
+ "title": "开启历史消息自动总结"
},
"enableHistoryCount": {
"alias": "不限制",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "开启单次回复限制"
},
+ "enableReasoningEffort": {
+ "title": "开启推理强度调整"
+ },
"frequencyPenalty": {
- "desc": "值越大,越有可能降低重复字词",
- "title": "频率惩罚度"
+ "desc": "值越大,用词越丰富多样;值越低,用词更朴实简单",
+ "title": "词汇丰富度"
},
"maxTokens": {
"desc": "单次交互所用的最大 Token 数",
@@ -212,19 +215,31 @@
"desc": "{{provider}} 模型",
"title": "模型"
},
+ "params": {
+ "title": "高级参数"
+ },
"presencePenalty": {
- "desc": "值越大,越有可能扩展到新话题",
- "title": "话题新鲜度"
+ "desc": "值越大,越倾向不同的表达方式,避免概念重复;值越小,越倾向使用重复的概念或叙述,表达更具一致性",
+ "title": "表述发散度"
+ },
+ "reasoningEffort": {
+ "desc": "值越大,推理能力越强,但可能会增加响应时间和 Token 消耗",
+ "options": {
+ "high": "高",
+ "low": "低",
+ "medium": "中"
+ },
+ "title": "推理强度"
},
"temperature": {
- "desc": "值越大,回复越随机",
- "title": "随机性",
- "titleWithValue": "随机性 {{value}}"
+ "desc": "数值越大,回答越有创意和想象力;数值越小,回答越严谨",
+ "title": "创意活跃度",
+ "warning": "创意活跃度数值过大,输出可能会产生乱码"
},
"title": "模型设置",
"topP": {
- "desc": "与随机性类似,但不要和随机性一起更改",
- "title": "核采样"
+ "desc": "考虑多少种可能性,值越大,接受更多可能的回答;值越小,倾向选择最可能的回答。不推荐和创意活跃度一起更改",
+ "title": "思维开放度"
}
},
"settingPlugin": {
@@ -274,7 +289,7 @@
"title": "语音识别语种"
},
"sttService": {
- "desc": "其中 broswer 为浏览器原生的语音识别服务",
+ "desc": "其中 browser 为浏览器原生的语音识别服务",
"title": "语音识别服务"
},
"title": "语音服务",
@@ -372,10 +387,26 @@
"modelDesc": "指定用于生成助理名称、描述、头像、标签的模型",
"title": "自动生成助理信息"
},
+ "customPrompt": {
+ "addPrompt": "添加自定义提示",
+ "desc": "填写后,系统助理将在生成内容时使用自定义提示",
+ "placeholder": "请输入自定义提示词",
+ "title": "自定义提示词"
+ },
+ "historyCompress": {
+ "label": "会话历史模型",
+ "modelDesc": "指定用于压缩会话历史的模型",
+ "title": "自动总结会话历史"
+ },
"queryRewrite": {
"label": "提问重写模型",
"modelDesc": "指定用于优化用户提问的模型",
- "title": "知识库"
+ "title": "知识库提问重写"
+ },
+ "thread": {
+ "label": "子话题命名模型",
+ "modelDesc": "指定用于子话题自动重命名的模型",
+ "title": "子话题自动命名"
},
"title": "系统助手",
"topic": {
@@ -392,11 +423,12 @@
"tab": {
"about": "关于",
"agent": "默认助手",
- "common": "角色设定",
+ "common": "通用设置",
"experiment": "实验",
- "llm": "模型设置",
+ "llm": "语言模型",
+ "provider": "AI 服务商",
"sync": "云端同步",
- "system-agent": "聊天偏好",
+ "system-agent": "系统助手",
"tts": "语音服务"
},
"tools": {
diff --git a/DigitalHumanWeb/locales/zh-CN/thread.json b/DigitalHumanWeb/locales/zh-CN/thread.json
new file mode 100644
index 0000000..06c7e69
--- /dev/null
+++ b/DigitalHumanWeb/locales/zh-CN/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "即将删除该子话题,删除后将不可恢复,请谨慎操作。"
+ },
+ "newPortalThread": {
+ "includeContext": "包含话题上下文",
+ "title": "开启新的子话题"
+ },
+ "notSupportMultiModals": "子话题暂不支持文件/图片上传,如有需求,欢迎留言:<1>💬 讨论区1>"
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-CN/tool.json b/DigitalHumanWeb/locales/zh-CN/tool.json
index 3f459aa..ae58008 100644
--- a/DigitalHumanWeb/locales/zh-CN/tool.json
+++ b/DigitalHumanWeb/locales/zh-CN/tool.json
@@ -6,5 +6,23 @@
"generating": "生成中...",
"images": "图片:",
"prompt": "提示词"
+ },
+ "search": {
+ "createNewSearch": "创建新的搜索记录",
+ "emptyResult": "没有搜索到结果,请修改关键词后重试",
+ "genAiMessage": "创建助手消息",
+ "includedTooltip": "当前搜索结果会进入会话的上下文中",
+ "keywords": "关键词:",
+ "scoreTooltip": "相关性分数,该分数越高说明与查询关键词越相关",
+ "searchBar": {
+ "button": "搜索",
+ "placeholder": "关键词",
+ "tooltip": "将会重新获取搜索结果,并创建一条新的总结消息"
+ },
+ "searchEngine": "搜索引擎:",
+ "searchResult": "搜索数量:",
+ "summary": "总结",
+ "summaryTooltip": "总结当前内容",
+ "viewMoreResults": "查看更多 {{results}} 个结果"
}
}
diff --git a/DigitalHumanWeb/locales/zh-CN/topic.json b/DigitalHumanWeb/locales/zh-CN/topic.json
new file mode 100644
index 0000000..7a2d99f
--- /dev/null
+++ b/DigitalHumanWeb/locales/zh-CN/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "智能重命名",
+ "confirmRemoveAll": "即将删除全部话题,删除后将不可恢复,请谨慎操作。",
+ "confirmRemoveTopic": "即将删除该话题,删除后将不可恢复,请谨慎操作。",
+ "confirmRemoveUnstarred": "即将删除未收藏话题,删除后将不可恢复,请谨慎操作。",
+ "duplicate": "创建副本",
+ "export": "导出话题",
+ "removeAll": "删除全部话题",
+ "removeUnstarred": "删除未收藏话题"
+ },
+ "defaultTitle": "默认话题",
+ "duplicateLoading": "话题复制中...",
+ "duplicateSuccess": "话题复制成功",
+ "favorite": "收藏",
+ "groupMode": {
+ "ascMessages": "按消息总数顺序",
+ "byTime": "按时间分组",
+ "descMessages": "按消息总数倒序",
+ "flat": "不分组"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "本月",
+ "today": "今天",
+ "week": "本周",
+ "yesterday": "昨天"
+ }
+ },
+ "guide": {
+ "desc": "点击发送左侧按钮可将当前会话保存为历史话题,并开启新一轮会话",
+ "title": "话题列表"
+ },
+ "searchPlaceholder": "搜索话题...",
+ "searchResultEmpty": "暂无搜索结果",
+ "temp": "临时",
+ "title": "话题"
+}
diff --git a/DigitalHumanWeb/locales/zh-CN/welcome.json b/DigitalHumanWeb/locales/zh-CN/welcome.json
index 993551e..54cf0a5 100644
--- a/DigitalHumanWeb/locales/zh-CN/welcome.json
+++ b/DigitalHumanWeb/locales/zh-CN/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "导入配置",
- "market": "逛逛市场",
- "start": "立即开始"
- },
"guide": {
"agents": {
"replaceBtn": "换一批",
@@ -47,4 +42,4 @@
"desc2": "创建你的第一个助手,让我们开始吧~",
"title": "给自己一个更聪明的大脑"
}
-}
+}
\ No newline at end of file
diff --git a/DigitalHumanWeb/locales/zh-TW/auth.json b/DigitalHumanWeb/locales/zh-TW/auth.json
index b9c5c61..439cd78 100644
--- a/DigitalHumanWeb/locales/zh-TW/auth.json
+++ b/DigitalHumanWeb/locales/zh-TW/auth.json
@@ -1,8 +1,96 @@
{
+ "date": {
+ "prevMonth": "上個月",
+ "recent30Days": "最近30天"
+ },
+ "header": {
+ "desc": "管理您的帳戶資訊。",
+ "title": "帳戶"
+ },
+ "heatmaps": {
+ "legend": {
+ "less": "不活躍",
+ "more": "活躍"
+ },
+ "months": {
+ "apr": "四月",
+ "aug": "八月",
+ "dec": "十二月",
+ "feb": "二月",
+ "jan": "一月",
+ "jul": "七月",
+ "jun": "六月",
+ "mar": "三月",
+ "may": "五月",
+ "nov": "十一月",
+ "oct": "十月",
+ "sep": "九月"
+ },
+ "tooltip": "{{date}} 當日發送 {{count}} 條消息",
+ "totalCount": "過去一年共發送 {{count}} 條消息"
+ },
"login": "登入",
"loginOrSignup": "登入 / 註冊",
- "profile": "個人檔案",
- "security": "安全",
+ "profile": {
+ "avatar": "頭像",
+ "email": "電子郵件地址",
+ "sso": {
+ "loading": "正在載入已綁定的第三方帳戶",
+ "providers": "連結的帳戶",
+ "unlink": {
+ "description": "解除綁定後,您將無法使用 {{provider}} 帳戶「{{providerAccountId}}」登入。如果您需要重新綁定 {{provider}} 帳戶到當前帳戶,請確保 {{provider}} 帳戶的電子郵件地址為 {{email}},我們會在登入時為您自動綁定到當前登入帳戶。",
+ "forbidden": "您至少需要保留一個第三方帳戶綁定。",
+ "title": "是否解除綁定該第三方帳戶 {{provider}} ?"
+ }
+ },
+ "username": "用戶名"
+ },
"signout": "登出",
- "signup": "註冊"
+ "signup": "註冊",
+ "stats": {
+ "aiheatmaps": "AI 指數",
+ "assistants": "助手數",
+ "assistantsRank": {
+ "left": "助手名稱",
+ "right": "話題數",
+ "title": "助手使用率"
+ },
+ "createdAt": "用戶創建於",
+ "days": "天",
+ "empty": {
+ "desc": "請累積更多聊天數據後查看",
+ "title": "暫無數據"
+ },
+ "lastYearActivity": "過去一年活躍度",
+ "loginGuide": {
+ "f1": "獲取免費用量",
+ "f2": "多端同步消息",
+ "f3": "擁有豐富助手",
+ "f4": "探索強大插件",
+ "title": "登錄後你可以:"
+ },
+ "messages": "消息數",
+ "modelsRank": {
+ "left": "模型名稱",
+ "right": "消息數",
+ "title": "模型使用率"
+ },
+ "share": {
+ "title": "我的 AI 活躍指數"
+ },
+ "topics": "話題數",
+ "topicsRank": {
+ "left": "話題名稱",
+ "right": "消息數",
+ "title": "話題內容量"
+ },
+ "updatedAt": "數據更新至",
+ "welcome": "{{username}}, 這是你和 {{appName}} 相伴的第 {{days}} 天",
+ "words": "總字數"
+ },
+ "tab": {
+ "profile": "個人資料",
+ "security": "安全",
+ "stats": "數據統計"
+ }
}
diff --git a/DigitalHumanWeb/locales/zh-TW/changelog.json b/DigitalHumanWeb/locales/zh-TW/changelog.json
new file mode 100644
index 0000000..bdd1f70
--- /dev/null
+++ b/DigitalHumanWeb/locales/zh-TW/changelog.json
@@ -0,0 +1,18 @@
+{
+ "actions": {
+ "followOnX": "在 X 上關注我們",
+ "subscribeToUpdates": "訂閱更新",
+ "versions": "版本詳情"
+ },
+ "addedWhileAway": "在您離開期間,我們帶來了新的特性。",
+ "allChangelog": "查看所有更新日誌",
+ "description": "持續追蹤 {{appName}} 的新功能和改進",
+ "pagination": {
+ "next": "下一頁",
+ "older": "查看歷史變更"
+ },
+ "readDetails": "閱讀詳情",
+ "title": "更新日誌",
+ "versionDetails": "版本詳情",
+ "welcomeBack": "歡迎回來!"
+}
diff --git a/DigitalHumanWeb/locales/zh-TW/chat.json b/DigitalHumanWeb/locales/zh-TW/chat.json
index b6fb803..05c209a 100644
--- a/DigitalHumanWeb/locales/zh-TW/chat.json
+++ b/DigitalHumanWeb/locales/zh-TW/chat.json
@@ -8,6 +8,7 @@
"agents": "助手",
"artifact": {
"generating": "生成中",
+ "inThread": "子話題中無法查看,請切換到主對話區打開",
"thinking": "思考中",
"thought": "思考過程",
"unknownTitle": "未命名作品"
@@ -30,7 +31,25 @@
},
"duplicateTitle": "{{title}} 副本",
"emptyAgent": "暫無助手",
+ "extendParams": {
+ "disableContextCaching": {
+ "desc": "單條對話生成成本最高可降低 90%,響應速度提升 4 倍(<1>了解更多1>)。開啟後將自動禁用歷史消息數限制",
+ "title": "開啟上下文快取"
+ },
+ "enableReasoning": {
+ "desc": "基於 Claude Thinking 機制限制(<1>了解更多1>),開啟後將自動禁用歷史消息數限制",
+ "title": "開啟深度思考"
+ },
+ "reasoningBudgetToken": {
+ "title": "思考消耗 Token"
+ },
+ "title": "模型擴展功能"
+ },
+ "history": {
+ "title": "助手將只記住最後{{count}}條消息"
+ },
"historyRange": "歷史範圍",
+ "historySummary": "歷史消息總結",
"inbox": {
"desc": "開啟大腦集群,激發思維火花。你的智能助理,在這裡與你交流一切",
"title": "隨便聊聊"
@@ -45,6 +64,9 @@
"stop": "停止",
"warp": "換行"
},
+ "intentUnderstanding": {
+ "title": "正在理解並分析您的意圖..."
+ },
"knowledgeBase": {
"all": "所有內容",
"allFiles": "所有檔案",
@@ -65,8 +87,42 @@
},
"messageAction": {
"delAndRegenerate": "刪除並重新生成",
+ "deleteDisabledByThreads": "存在子話題,無法刪除",
"regenerate": "重新生成"
},
+ "messages": {
+ "modelCard": {
+ "credit": "積分",
+ "creditPricing": "定價",
+ "creditTooltip": "為便於計算,我們將 1$ 折算為 1M 積分,例如 $3/M tokens 即可折算為 3積分/token",
+ "pricing": {
+ "inputCachedTokens": "快取輸入 {{amount}}/積分 · ${{amount}}/M",
+ "inputCharts": "${{amount}}/M 字元",
+ "inputMinutes": "${{amount}}/分鐘",
+ "inputTokens": "輸入 {{amount}}/積分 · ${{amount}}/M",
+ "outputTokens": "輸出 {{amount}}/積分 · ${{amount}}/M",
+ "writeCacheInputTokens": "快取輸入寫入 {{amount}}/積分 · ${{amount}}/M"
+ }
+ },
+ "tokenDetails": {
+ "average": "平均單價",
+ "input": "輸入",
+ "inputAudio": "音頻輸入",
+ "inputCached": "輸入快取",
+ "inputCitation": "引用輸入",
+ "inputText": "文本輸入",
+ "inputTitle": "輸入明細",
+ "inputUncached": "輸入未快取",
+ "inputWriteCached": "輸入快取寫入",
+ "output": "輸出",
+ "outputAudio": "音頻輸出",
+ "outputText": "文本輸出",
+ "outputTitle": "輸出明細",
+ "reasoning": "深度思考",
+ "title": "生成明細",
+ "total": "總計消耗"
+ }
+ },
"newAgent": "新建助手",
"pin": "置頂",
"pinOff": "取消置頂",
@@ -81,6 +137,32 @@
},
"regenerate": "重新生成",
"roleAndArchive": "角色與記錄",
+ "search": {
+ "grounding": {
+ "searchQueries": "搜尋關鍵字",
+ "title": "已搜尋到 {{count}} 個結果"
+ },
+ "mode": {
+ "auto": {
+ "desc": "根據對話內容智能判斷是否需要搜尋",
+ "title": "智能連網"
+ },
+ "off": {
+ "desc": "僅使用模型的基礎知識,不進行網路搜尋",
+ "title": "關閉連網"
+ },
+ "on": {
+ "desc": "持續進行網路搜尋,獲取最新資訊",
+ "title": "始終連網"
+ },
+ "useModelBuiltin": "使用模型內建搜尋引擎"
+ },
+ "searchModel": {
+ "desc": "當前模型不支持函數調用,因此需要搭配支持函數調用的模型才能聯網搜索",
+ "title": "搜索輔助模型"
+ },
+ "title": "連網搜尋"
+ },
"searchAgentPlaceholder": "搜尋助手...",
"sendPlaceholder": "輸入聊天內容...",
"sessionGroup": {
@@ -100,14 +182,20 @@
"tooLong": "分組名稱長度需在 1-20 之內"
},
"shareModal": {
+ "copy": "複製",
"download": "下載截圖",
+ "downloadFile": "下載檔案",
+ "exportTitle": "預設標題",
"imageType": "圖片格式",
+ "includeTool": "包含插件訊息",
+ "includeUser": "包含使用者訊息",
"screenshot": "截圖",
"settings": "導出設置",
- "shareToShareGPT": "生成 ShareGPT 分享鏈接",
+ "text": "文本",
"withBackground": "包含背景圖片",
"withFooter": "包含頁腳",
"withPluginInfo": "包含插件信息",
+ "withRole": "包含訊息角色",
"withSystemRole": "包含助手角色設定"
},
"stt": {
@@ -115,9 +203,14 @@
"loading": "識別中...",
"prettifying": "潤色中..."
},
- "temp": "臨時",
+ "thread": {
+ "divider": "子話題",
+ "threadMessageCount": "{{messageCount}} 條消息",
+ "title": "子話題"
+ },
"tokenDetails": {
"chats": "聊天訊息",
+ "historySummary": "歷史總結",
"rest": "剩餘可用",
"systemRole": "角色設定",
"title": "上下文詳細資訊",
@@ -131,29 +224,10 @@
"used": "使用"
},
"topic": {
- "actions": {
- "autoRename": "智能重新命名",
- "duplicate": "建立副本",
- "export": "匯出主題"
- },
"checkOpenNewTopic": "是否開啟新主題?",
"checkSaveCurrentMessages": "是否將當前對話保存為話題?",
- "confirmRemoveAll": "即將刪除全部話題,刪除後將不可恢復,請謹慎操作。",
- "confirmRemoveTopic": "即將刪除該話題,刪除後將不可恢復,請謹慎操作。",
- "confirmRemoveUnstarred": "即將刪除未收藏話題,刪除後將不可恢復,請謹慎操作。",
- "defaultTitle": "默認話題",
- "duplicateLoading": "話題複製中...",
- "duplicateSuccess": "話題複製成功",
- "guide": {
- "desc": "點擊發送左側按鈕可將當前對話保存為歷史話題,並開啟新一輪對話",
- "title": "話題列表"
- },
"openNewTopic": "開啟新話題",
- "removeAll": "刪除全部話題",
- "removeUnstarred": "刪除未收藏話題",
- "saveCurrentMessages": "將當前對話保存為話題",
- "searchPlaceholder": "搜索話題...",
- "title": "話題列表"
+ "saveCurrentMessages": "將當前對話保存為話題"
},
"translate": {
"action": "翻譯",
@@ -184,5 +258,6 @@
"processing": "檔案處理中..."
}
}
- }
+ },
+ "zenMode": "專注模式"
}
diff --git a/DigitalHumanWeb/locales/zh-TW/common.json b/DigitalHumanWeb/locales/zh-TW/common.json
index 889d069..5220c16 100644
--- a/DigitalHumanWeb/locales/zh-TW/common.json
+++ b/DigitalHumanWeb/locales/zh-TW/common.json
@@ -9,15 +9,79 @@
"title": "歡迎體驗 {{name}}"
}
},
- "appInitializing": "應用啟動中...",
+ "appLoading": {
+ "appIdle": "準備啟動",
+ "appInitializing": "應用啟動中...",
+ "failed": "很抱歉,應用初始化失敗,請查看詳情進行排查",
+ "finished": "資料庫初始化完成",
+ "goToChat": "對話頁面加載中...",
+ "initAuth": "鑑權服務初始化...",
+ "initUser": "用戶狀態初始化...",
+ "initializing": "PGlite 資料庫初始化...",
+ "loadingDependencies": "初始化依賴...",
+ "loadingWasm": "加載 WASM 模組...",
+ "migrating": "執行資料表遷移...",
+ "ready": "資料庫已就緒",
+ "showDetail": "查看詳情"
+ },
"autoGenerate": "自動生成",
"autoGenerateTooltip": "基於提示詞自動生成助手描述",
"autoGenerateTooltipDisabled": "請填寫提示詞後使用自動補全功能",
"back": "返回",
"batchDelete": "批次刪除",
"blog": "產品部落格",
+ "branching": "建立子主題",
+ "branchingDisable": "「子主題」功能僅在伺服器端版本可用,如需該功能,請切換到伺服器端部署模式或使用 LobeChat Cloud",
"cancel": "取消",
"changelog": "變更日誌",
+ "clientDB": {
+ "autoInit": {
+ "title": "初始化 PGlite 數據庫"
+ },
+ "error": {
+ "desc": "非常抱歉,Pglite 資料庫初始化過程發生異常。請點擊按鈕重試。如多次重試後仍重複出錯,請 <1>提交問題1> ,我們將會第一時間幫你排查",
+ "detail": "錯誤原因:[{{type}}] {{message}},明細如下:",
+ "retry": "重試",
+ "title": "資料庫初始化失敗"
+ },
+ "initing": {
+ "error": "發生錯誤,請重試",
+ "idle": "等待初始化...",
+ "initializing": "正在初始化...",
+ "loadingDependencies": "載入依賴中...",
+ "loadingWasmModule": "載入 WASM 模組中...",
+ "migrating": "執行資料表遷移...",
+ "ready": "數據庫已就緒"
+ },
+ "modal": {
+ "desc": "啟用 PGlite 客戶端數據庫,在你的瀏覽器中持久存儲聊天數據,並使用知識庫等進階特性",
+ "enable": "立即啟用",
+ "features": {
+ "knowledgeBase": {
+ "desc": "沉澱你的個人知識庫,並與你的助手輕鬆開啟知識庫對話(即將上線)",
+ "title": "支持知識庫對話,開啟第二大腦"
+ },
+ "localFirst": {
+ "desc": "聊天數據完全存儲在瀏覽器中,你的數據始終在你的掌握。",
+ "title": "本地優先,隱私至上"
+ },
+ "pglite": {
+ "desc": "基於 PGlite 構建,原生支持 AI Native 高階特性(向量檢索)",
+ "title": "新一代客戶端存儲架構"
+ }
+ },
+ "init": {
+ "desc": "正在初始化數據庫,視網絡差異可能會用時 5~30 秒不等",
+ "title": "正在初始化 PGlite 數據庫"
+ },
+ "title": "開啟客戶端數據庫"
+ },
+ "ready": {
+ "button": "立即使用",
+ "desc": "立即想用",
+ "title": "PGlite 數據庫已就緒"
+ }
+ },
"close": "關閉",
"contact": "聯繫我們",
"copy": "複製",
@@ -112,6 +176,7 @@
"en": "英文",
"en-US": "英文",
"es-ES": "西班牙語",
+ "fa-IR": "波斯語",
"fi-FI": "芬蘭語",
"fr-FR": "法語",
"hi-IN": "印地語",
@@ -153,6 +218,7 @@
"pinOff": "取消置頂",
"privacy": "隱私政策",
"regenerate": "重新生成",
+ "releaseNotes": "版本詳細",
"rename": "重新命名",
"reset": "重置",
"retry": "重試",
@@ -209,6 +275,7 @@
},
"temp": "臨時",
"terms": "服務條款",
+ "update": "更新",
"updateAgent": "更新助理資訊",
"upgradeVersion": {
"action": "升級",
@@ -219,6 +286,7 @@
"anonymousNickName": "匿名使用者",
"billing": "帳單管理",
"cloud": "體驗 {{name}}",
+ "community": "社區版",
"data": "資料儲存",
"defaultNickname": "社群版使用者",
"discord": "社區支援",
@@ -228,7 +296,6 @@
"help": "幫助中心",
"moveGuide": "設置按鈕搬到這裡啦",
"plans": "訂閱方案",
- "preview": "預覽",
"profile": "帳戶管理",
"setting": "應用設定",
"usages": "用量統計"
diff --git a/DigitalHumanWeb/locales/zh-TW/components.json b/DigitalHumanWeb/locales/zh-TW/components.json
index 8a05c43..24029d7 100644
--- a/DigitalHumanWeb/locales/zh-TW/components.json
+++ b/DigitalHumanWeb/locales/zh-TW/components.json
@@ -12,6 +12,7 @@
"batchChunking": "批量分塊",
"chunking": "分塊",
"chunkingTooltip": "將文件拆分為多個文本塊並向量化後,可用於語義檢索和文件對話",
+ "chunkingUnsupported": "該檔案不支援分塊",
"confirmDelete": "即將刪除該文件,刪除後將無法找回,請確認你的操作",
"confirmDeleteMultiFiles": "即將刪除選中的 {{count}} 個文件,刪除後將無法找回,請確認你的操作",
"confirmRemoveFromKnowledgeBase": "即將從知識庫中移除選中的 {{count}} 個文件,移除後文件仍然可以在全部文件中查看,請確認你的操作",
@@ -67,11 +68,16 @@
"GoBack": {
"back": "返回"
},
+ "MaxTokenSlider": {
+ "unlimited": "無限制"
+ },
"ModelSelect": {
"featureTag": {
"custom": "自訂模型,預設支援函式呼叫與視覺辨識,請根據實際情況驗證上述能力的可用性",
"file": "該模型支援上傳檔案讀取與辨識",
"functionCall": "該模型支援函式呼叫(Function Call)",
+ "reasoning": "該模型支持深度思考",
+ "search": "該模型支援聯網搜尋",
"tokens": "該模型單一會話最多支援 {{tokens}} Tokens",
"vision": "該模型支援視覺辨識"
},
@@ -79,6 +85,37 @@
},
"ModelSwitchPanel": {
"emptyModel": "沒有啟用的模型,請前往設定開啟",
+ "emptyProvider": "沒有啟用的服務商,請前往設定開啟",
+ "goToSettings": "前往設定",
"provider": "提供商"
+ },
+ "OllamaSetupGuide": {
+ "cors": {
+ "description": "因瀏覽器安全限制,你需要為 Ollama 進行跨域配置後方可正常使用。",
+ "linux": {
+ "env": "在 [Service] 部分下添加 `Environment`,添加 OLLAMA_ORIGINS 環境變數:",
+ "reboot": "重載 systemd 並重啟 Ollama",
+ "systemd": "調用 systemd 編輯 ollama 服務:"
+ },
+ "macos": "請打開「終端」應用程式,並粘貼以下指令,然後按回車執行",
+ "reboot": "請在執行完成後重啟 Ollama 服務",
+ "title": "配置 Ollama 允許跨域訪問",
+ "windows": "在 Windows 上,點擊「控制面板」,進入編輯系統環境變數。為您的用戶帳戶新建名為「OLLAMA_ORIGINS」的環境變數,值為 *,點擊「確定/應用」保存"
+ },
+ "install": {
+ "description": "請確認你已經啟動 Ollama,如果沒有下載 Ollama,請前往官網<1>下載1>",
+ "docker": "如果你更傾向於使用 Docker,Ollama 也提供了官方 Docker 映像,你可以通過以下命令拉取:",
+ "linux": {
+ "command": "通過以下命令安裝:",
+ "manual": "或者,你也可以參考 <1>Linux 手動安裝指南1> 自行安裝"
+ },
+ "title": "在本地安裝並啟動 Ollama 應用",
+ "windowsTab": "Windows (預覽版)"
+ }
+ },
+ "Thinking": {
+ "thinking": "深度思考中...",
+ "thought": "已深度思考(用時 {{duration}} 秒)",
+ "thoughtWithDuration": "已深度思考"
}
}
diff --git a/DigitalHumanWeb/locales/zh-TW/discover.json b/DigitalHumanWeb/locales/zh-TW/discover.json
index b96b8a5..cdb81fd 100644
--- a/DigitalHumanWeb/locales/zh-TW/discover.json
+++ b/DigitalHumanWeb/locales/zh-TW/discover.json
@@ -19,7 +19,6 @@
"try": "試一下"
},
"back": "返回發現",
- "collectSuccess": "收藏成功",
"category": {
"assistant": {
"academic": "學術",
@@ -127,6 +126,10 @@
"title": "話題新鮮度"
},
"range": "範圍",
+ "reasoning_effort": {
+ "desc": "此設定用於控制模型在生成回答前的推理強度。低強度優先響應速度並節省 Token,高強度提供更完整的推理,但會消耗更多 Token 並降低響應速度。預設值為中,平衡推理準確性與響應速度。",
+ "title": "推理強度"
+ },
"temperature": {
"desc": "此設置影響模型回應的多樣性。較低的值會導致更可預測和典型的回應,而較高的值則鼓勵更多樣化和不常見的回應。當值設為0時,模型對於給定的輸入總是給出相同的回應。",
"title": "隨機性"
diff --git a/DigitalHumanWeb/locales/zh-TW/error.json b/DigitalHumanWeb/locales/zh-TW/error.json
index 938947f..ef1a3bd 100644
--- a/DigitalHumanWeb/locales/zh-TW/error.json
+++ b/DigitalHumanWeb/locales/zh-TW/error.json
@@ -12,8 +12,14 @@
"retry": "重新加載",
"title": "頁面遇到一點問題.."
},
- "fetchError": "請求失敗",
- "fetchErrorDetail": "錯誤詳情",
+ "fetchError": {
+ "detail": "錯誤詳情",
+ "title": "請求失敗"
+ },
+ "loginRequired": {
+ "desc": "即將自動跳轉到登入頁面",
+ "title": "請登入後使用該功能"
+ },
"notFound": {
"backHome": "返回首頁",
"check": "請檢查你的 URL 是否正確",
@@ -51,22 +57,34 @@
"431": "很抱歉,您的請求頭字段太大,伺服器無法處理",
"451": "很抱歉,由於法律原因,伺服器拒絕提供此資源",
"500": "抱歉,伺服器似乎遇到一些困難,暫時無法完成您的請求。請稍後再試。",
+ "501": "很抱歉,伺服器尚未知道如何處理此請求,請確認您的操作是否正確",
"502": "抱歉,伺服器似乎迷失了方向,暫時無法提供服務。請稍後再試。",
"503": "抱歉,伺服器目前無法處理您的請求,可能是因為過載或正在進行維護。請稍後再試。",
"504": "抱歉,伺服器沒有收到上游伺服器的回應。請稍後再試。",
+ "505": "很抱歉,伺服器不支援您使用的HTTP版本,請更新後再試",
+ "506": "很抱歉,伺服器配置出現問題,請聯繫管理員解決",
+ "507": "很抱歉,伺服器儲存空間不足,無法處理您的請求,請稍後再試",
+ "509": "很抱歉,伺服器的頻寬已用盡,請稍後再試",
+ "510": "很抱歉,伺服器不支援請求的擴展功能,請聯繫管理員",
+ "524": "很抱歉,伺服器在等待回覆時超時,可能是因為回應太慢,請稍後再試",
"AgentRuntimeError": "Lobe 語言模型運行時執行出錯,請根據以下信息排查或重試",
+ "ConnectionCheckFailed": "請求返回為空,請檢查 API 代理地址末尾是否未包含 `/v1`",
+ "ExceededContextWindow": "當前請求內容超出模型可處理的長度,請減少內容量後重試",
"FreePlanLimit": "目前為免費用戶,無法使用該功能,請升級到付費計劃後繼續使用",
+ "InsufficientQuota": "很抱歉,該金鑰的配額已達上限,請檢查帳戶餘額是否充足,或增加金鑰配額後再試",
"InvalidAccessCode": "密碼不正確或為空,請輸入正確的訪問密碼,或添加自定義 API 金鑰",
"InvalidBedrockCredentials": "Bedrock 驗證未通過,請檢查 AccessKeyId/SecretAccessKey 後重試",
"InvalidClerkUser": "很抱歉,你當前尚未登錄,請先登錄或註冊帳號後繼續操作",
"InvalidGithubToken": "Github 個人存取權杖不正確或為空,請檢查 Github 個人存取權杖後再試一次",
"InvalidOllamaArgs": "Ollama 配置不正確,請檢查 Ollama 配置後重試",
"InvalidProviderAPIKey": "{{provider}} API 金鑰不正確或為空,請檢查 {{provider}} API 金鑰後重試",
+ "InvalidVertexCredentials": "Vertex 認證未通過,請檢查認證憑證後重試",
"LocationNotSupportError": "很抱歉,你的所在位置不支持此模型服務,可能是由於地區限制或服務未開通。請確認當前位置是否支持使用此服務,或嘗試使用其他位置信息。",
+ "ModelNotFound": "很抱歉,無法請求到相應的模型,可能是模型不存在或沒有訪問權限導致,請更換 API Key 或調整訪問權限後重試",
"NoOpenAIAPIKey": "OpenAI API 金鑰為空,請添加自訂 OpenAI API 金鑰",
"OllamaBizError": "請求 Ollama 服務出錯,請根據以下資訊排查或重試",
"OllamaServiceUnavailable": "Ollama 服務暫時無法使用,請檢查 Ollama 是否運作正常,或是否正確設定 Ollama 的跨域配置",
- "OpenAIBizError": "請求 OpenAI 服務出錯,請根據以下資訊排查或重試",
+ "PermissionDenied": "很抱歉,您沒有權限訪問該服務,請檢查您的金鑰是否具有訪問權限",
"PluginApiNotFound": "抱歉,外掛描述檔案中不存在該 API。請檢查您的請求方法與外掛清單 API 是否相符",
"PluginApiParamsError": "抱歉,該外掛請求的輸入參數驗證失敗。請檢查輸入參數與 API 描述資訊是否相符",
"PluginFailToTransformArguments": "很抱歉,插件無法轉換參數,請嘗試重新生成助手消息,或更換功能更強大的 AI 模型後重試",
@@ -81,8 +99,11 @@
"PluginServerError": "外掛伺服器請求回傳錯誤。請根據下面的錯誤資訊檢查您的外掛描述檔案、外掛設定或伺服器實作",
"PluginSettingsInvalid": "該外掛需要正確設定後才可以使用。請檢查您的設定是否正確",
"ProviderBizError": "請求 {{provider}} 服務出錯,請根據以下資訊排查或重試",
+ "QuotaLimitReached": "很抱歉,當前 Token 用量或請求次數已達該金鑰的配額上限,請增加該金鑰的配額或稍後再試",
"StreamChunkError": "流式請求的消息塊解析錯誤,請檢查當前 API 介面是否符合標準規範,或聯繫你的 API 供應商諮詢",
- "SubscriptionPlanLimit": "您的訂閱額度已用盡,無法使用該功能,請升級到更高的計劃,或購買資源包後繼續使用",
+ "SubscriptionKeyMismatch": "很抱歉,由於系統偶發故障,當前訂閱用量暫時失效,請點擊下方按鈕恢復訂閱,或郵件聯繫我們獲取支持",
+ "SubscriptionPlanLimit": "您的訂閱積分已用盡,無法使用該功能,請升級到更高計劃,或配置自訂模型 API 後繼續使用",
+ "SystemTimeNotMatchError": "很抱歉,您的系統時間與伺服器不匹配,請檢查您的系統時間後重試",
"UnknownChatFetchError": "很抱歉,遇到未知請求錯誤,請根據以下資訊排查或重試"
},
"stt": {
diff --git a/DigitalHumanWeb/locales/zh-TW/metadata.json b/DigitalHumanWeb/locales/zh-TW/metadata.json
index c59b51e..d856fbc 100644
--- a/DigitalHumanWeb/locales/zh-TW/metadata.json
+++ b/DigitalHumanWeb/locales/zh-TW/metadata.json
@@ -1,4 +1,8 @@
{
+ "changelog": {
+ "description": "持續追蹤 {{appName}} 的新功能和改進",
+ "title": "更新日誌"
+ },
"chat": {
"description": "{{appName}} 帶給你最好的 ChatGPT, Claude, Gemini, OLLaMA WebUI 使用體驗",
"title": "{{appName}}:個人 AI 效能工具,給自己一個更聰明的大腦"
diff --git a/DigitalHumanWeb/locales/zh-TW/modelProvider.json b/DigitalHumanWeb/locales/zh-TW/modelProvider.json
index f453e73..6f50475 100644
--- a/DigitalHumanWeb/locales/zh-TW/modelProvider.json
+++ b/DigitalHumanWeb/locales/zh-TW/modelProvider.json
@@ -19,6 +19,24 @@
"title": "API 金鑰"
}
},
+ "azureai": {
+ "azureApiVersion": {
+ "desc": "Azure 的 API 版本,遵循 YYYY-MM-DD 格式,查閱[最新版本](https://learn.microsoft.com/zh-tw/azure/ai-services/openai/reference#chat-completions)",
+ "fetch": "獲取列表",
+ "title": "Azure API 版本"
+ },
+ "endpoint": {
+ "desc": "從 Azure AI 專案概述找到 Azure AI 模型推理終結點",
+ "placeholder": "https://ai-userxxxxxxxxxx.services.ai.azure.com/models",
+ "title": "Azure AI 終結點"
+ },
+ "title": "Azure OpenAI",
+ "token": {
+ "desc": "從 Azure AI 專案概述找到 API 密鑰",
+ "placeholder": "Azure 密鑰",
+ "title": "密鑰"
+ }
+ },
"bedrock": {
"accessKeyId": {
"desc": "填入AWS Access Key Id",
@@ -51,6 +69,58 @@
"title": "使用自定義 Bedrock 驗證資訊"
}
},
+ "cloudflare": {
+ "apiKey": {
+ "desc": "請填入 Cloudflare API Key",
+ "placeholder": "Cloudflare API Key",
+ "title": "Cloudflare API Key"
+ },
+ "baseURLOrAccountID": {
+ "desc": "填入 Cloudflare 帳戶 ID 或 自定義 API 位址",
+ "placeholder": "Cloudflare 帳戶 ID / 自定義 API 位址",
+ "title": "Cloudflare 帳戶 ID / API 位址"
+ }
+ },
+ "createNewAiProvider": {
+ "apiKey": {
+ "placeholder": "請填寫你的 API Key",
+ "title": "API Key"
+ },
+ "basicTitle": "基本資訊",
+ "configTitle": "配置信息",
+ "confirm": "新建",
+ "createSuccess": "新建成功",
+ "description": {
+ "placeholder": "服務商簡介(選填)",
+ "title": "服務商簡介"
+ },
+ "id": {
+ "desc": "作為服務商唯一標識,創建後將不可修改",
+ "format": "只能包含數字、小寫字母、連字符(-)和底線(_)",
+ "placeholder": "建議全小寫,例如 openai,創建後將不可修改",
+ "required": "請填寫服務商 ID",
+ "title": "服務商 ID"
+ },
+ "logo": {
+ "required": "請上傳正確的服務商 Logo",
+ "title": "服務商 Logo"
+ },
+ "name": {
+ "placeholder": "請輸入服務商的展示名稱",
+ "required": "請填寫服務商名稱",
+ "title": "服務商名稱"
+ },
+ "proxyUrl": {
+ "required": "請填寫代理地址",
+ "title": "代理地址"
+ },
+ "sdkType": {
+ "placeholder": "openai/anthropic/azureai/ollama/...",
+ "required": "請選擇 SDK 類型",
+ "title": "請求格式"
+ },
+ "title": "創建自定義 AI 服務商"
+ },
"github": {
"personalAccessToken": {
"desc": "填入你的 Github 個人存取權杖,點擊[這裡](https://github.com/settings/tokens) 創建",
@@ -58,6 +128,30 @@
"title": "GitHub PAT"
}
},
+ "huggingface": {
+ "accessToken": {
+ "desc": "填入你的 HuggingFace Token,點擊 [這裡](https://huggingface.co/settings/tokens) 創建",
+ "placeholder": "hf_xxxxxxxxx",
+ "title": "HuggingFace Token"
+ }
+ },
+ "list": {
+ "title": {
+ "disabled": "未啟用服務商",
+ "enabled": "已啟用服務商"
+ }
+ },
+ "menu": {
+ "addCustomProvider": "添加自定義服務商",
+ "all": "全部",
+ "list": {
+ "disabled": "未啟用",
+ "enabled": "已啟用"
+ },
+ "notFound": "未找到搜索結果",
+ "searchProviders": "搜索服務商...",
+ "sort": "自定義排序"
+ },
"ollama": {
"checker": {
"desc": "測試代理地址是否正確填寫",
@@ -75,33 +169,9 @@
"title": "正在下載模型 {{model}}"
},
"endpoint": {
- "desc": "填入 Ollama 接口代理地址,本地未額外指定可留空",
+ "desc": "必須包含http(s)://,本地未額外指定可留空",
"title": "接口代理地址"
},
- "setup": {
- "cors": {
- "description": "因瀏覽器安全限制,您需要為 Ollama 進行跨域配置後才能正常使用。",
- "linux": {
- "env": "在 [Service] 部分下添加 `Environment`,新增 OLLAMA_ORIGINS 環境變數:",
- "reboot": "重新載入 systemd 並重新啟動 Ollama",
- "systemd": "呼叫 systemd 編輯 ollama 服務:"
- },
- "macos": "請開啟「終端」應用程式,貼上以下指令,然後按 Enter 執行",
- "reboot": "執行完成後請重新啟動 Ollama 服務",
- "title": "配置 Ollama 允許跨域訪問",
- "windows": "在 Windows 上,點擊「控制面板」,進入編輯系統環境變數。為您的使用者帳戶新增名為「OLLAMA_ORIGINS」的環境變數,值為 *,點擊「確定/應用」保存"
- },
- "install": {
- "description": "請確認您已經啟用 Ollama,如果尚未下載 Ollama,請前往官網<1>下載1>",
- "docker": "如果您更傾向於使用 Docker,Ollama 也提供了官方 Docker 映像,您可以透過以下命令拉取:",
- "linux": {
- "command": "透過以下命令安裝:",
- "manual": "或者,您也可以參考 <1>Linux 手動安裝指南1> 自行安裝"
- },
- "title": "在本地安裝並啟動 Ollama 應用",
- "windowsTab": "Windows (預覽版)"
- }
- },
"title": "Ollama",
"unlock": {
"cancel": "取消下載",
@@ -112,6 +182,156 @@
"title": "下載指定的 Ollama 模型"
}
},
+ "providerModels": {
+ "config": {
+ "aesGcm": "您的秘鑰與代理地址等將使用 <1>AES-GCM1> 加密算法進行加密",
+ "apiKey": {
+ "desc": "請填寫你的 {{name}} API Key",
+ "placeholder": "{{name}} API Key",
+ "title": "API Key"
+ },
+ "baseURL": {
+ "desc": "必須包含 http(s)://",
+ "invalid": "請輸入合法的 URL",
+ "placeholder": "https://your-proxy-url.com/v1",
+ "title": "API 代理地址"
+ },
+ "checker": {
+ "button": "檢查",
+ "desc": "測試 Api Key 與代理地址是否正確填寫",
+ "pass": "檢查通過",
+ "title": "連通性檢查"
+ },
+ "fetchOnClient": {
+ "desc": "客戶端請求模式將從瀏覽器直接發起會話請求,可提升響應速度",
+ "title": "使用客戶端請求模式"
+ },
+ "helpDoc": "配置教程",
+ "waitingForMore": "更多模型正在 <1>計劃接入1> 中,敬請期待"
+ },
+ "createNew": {
+ "title": "創建自定義 AI 模型"
+ },
+ "item": {
+ "config": "配置模型",
+ "customModelCards": {
+ "addNew": "創建並添加 {{id}} 模型",
+ "confirmDelete": "即將刪除該自定義模型,刪除後將不可恢復,請謹慎操作。"
+ },
+ "delete": {
+ "confirm": "確認刪除模型 {{displayName}}?",
+ "success": "刪除成功",
+ "title": "刪除模型"
+ },
+ "modelConfig": {
+ "azureDeployName": {
+ "extra": "在 Azure OpenAI 中實際請求的字段",
+ "placeholder": "請輸入 Azure 中的模型部署名稱",
+ "title": "模型部署名稱"
+ },
+ "deployName": {
+ "extra": "發送請求時會將該字段作為模型 ID",
+ "placeholder": "請輸入模型實際部署的名稱或 id",
+ "title": "模型部署名稱"
+ },
+ "displayName": {
+ "placeholder": "請輸入模型的展示名稱,例如 ChatGPT、GPT-4 等",
+ "title": "模型展示名稱"
+ },
+ "files": {
+ "extra": "當前文件上傳實現僅為一種 Hack 方案,僅限自行嘗試。完整文件上傳能力請等待後續實現",
+ "title": "支持文件上傳"
+ },
+ "functionCall": {
+ "extra": "此配置將僅開啟模型使用工具的能力,進而可以為模型添加工具類的插件。但是否支持真正使用工具完全取決於模型本身,請自行測試其可用性",
+ "title": "支持工具使用"
+ },
+ "id": {
+ "extra": "創建後不可修改,調用 AI 時將作為模型 id 使用",
+ "placeholder": "請輸入模型 id,例如 gpt-4o 或 claude-3.5-sonnet",
+ "title": "模型 ID"
+ },
+ "modalTitle": "自定義模型配置",
+ "reasoning": {
+ "extra": "此配置將僅開啟模型深度思考的能力,具體效果完全取決於模型本身,請自行測試該模型是否具備可用的深度思考能力",
+ "title": "支持深度思考"
+ },
+ "tokens": {
+ "extra": "設定模型支持的最大 Token 數",
+ "title": "最大上下文窗口",
+ "unlimited": "無限制"
+ },
+ "vision": {
+ "extra": "此配置將僅開啟應用中的圖片上傳配置,是否支持識別完全取決於模型本身,請自行測試該模型的視覺識別能力可用性",
+ "title": "支持視覺識別"
+ }
+ },
+ "pricing": {
+ "image": "${{amount}}/圖片",
+ "inputCharts": "${{amount}}/M 字符",
+ "inputMinutes": "${{amount}}/分鐘",
+ "inputTokens": "輸入 ${{amount}}/M",
+ "outputTokens": "輸出 ${{amount}}/M"
+ },
+ "releasedAt": "發佈於{{releasedAt}}"
+ },
+ "list": {
+ "addNew": "新增模型",
+ "disabled": "未啟用",
+ "disabledActions": {
+ "showMore": "顯示全部"
+ },
+ "empty": {
+ "desc": "請創建自定義模型或拉取模型後開始使用吧",
+ "title": "暫無可用模型"
+ },
+ "enabled": "已啟用",
+ "enabledActions": {
+ "disableAll": "全部禁用",
+ "enableAll": "全部啟用",
+ "sort": "自訂模型排序"
+ },
+ "enabledEmpty": "暫無啟用模型,請從下方列表中啟用心儀的模型吧~",
+ "fetcher": {
+ "clear": "清除取得的模型",
+ "fetch": "取得模型列表",
+ "fetching": "正在取得模型列表...",
+ "latestTime": "上次更新時間:{{time}}",
+ "noLatestTime": "尚未取得列表"
+ },
+ "resetAll": {
+ "conform": "確認重置當前模型的所有修改?重置後當前模型列表將會回到預設狀態",
+ "success": "重置成功",
+ "title": "重置所有修改"
+ },
+ "search": "搜尋模型...",
+ "searchResult": "搜尋到 {{count}} 個模型",
+ "title": "模型列表",
+ "total": "共 {{count}} 個模型可用"
+ },
+ "searchNotFound": "未找到搜尋結果"
+ },
+ "sortModal": {
+ "success": "排序更新成功",
+ "title": "自定義排序",
+ "update": "更新"
+ },
+ "updateAiProvider": {
+ "confirmDelete": "即將刪除該 AI 服務商,刪除後將無法找回,確認是否刪除?",
+ "deleteSuccess": "刪除成功",
+ "tooltip": "更新服務商基礎配置",
+ "updateSuccess": "更新成功"
+ },
+ "updateCustomAiProvider": {
+ "title": "更新自訂 AI 服務商配置"
+ },
+ "vertexai": {
+ "apiKey": {
+ "desc": "填入你的 Vertex AI 金鑰",
+ "placeholder": "{ \"type\": \"service_account\", \"project_id\": \"xxx\", \"private_key_id\": ... }",
+ "title": "Vertex AI 金鑰"
+ }
+ },
"zeroone": {
"title": "01.AI 零一萬物"
},
diff --git a/DigitalHumanWeb/locales/zh-TW/models.json b/DigitalHumanWeb/locales/zh-TW/models.json
index 7262251..c144899 100644
--- a/DigitalHumanWeb/locales/zh-TW/models.json
+++ b/DigitalHumanWeb/locales/zh-TW/models.json
@@ -2,9 +2,18 @@
"01-ai/Yi-1.5-34B-Chat-16K": {
"description": "Yi-1.5 34B,以豐富的訓練樣本在行業應用中提供優越表現。"
},
+ "01-ai/Yi-1.5-6B-Chat": {
+ "description": "Yi-1.5-6B-Chat 是 Yi-1.5 系列的一個變體,屬於開源聊天模型。Yi-1.5 是 Yi 的升級版本,在 500B 個高質量語料上進行了持續預訓練,並在 3M 多樣化的微調樣本上進行了微調。相比於 Yi,Yi-1.5 在編碼、數學、推理和指令遵循能力方面表現更強,同時保持了出色的語言理解、常識推理和閱讀理解能力。該模型具有 4K、16K 和 32K 的上下文長度版本,預訓練總量達到 3.6T 個 token"
+ },
"01-ai/Yi-1.5-9B-Chat-16K": {
"description": "Yi-1.5 9B 支持16K Tokens,提供高效、流暢的語言生成能力。"
},
+ "01-ai/yi-1.5-34b-chat": {
+ "description": "零一萬物,最新開源微調模型,340億參數,微調支持多種對話場景,高質量訓練數據,對齊人類偏好。"
+ },
+ "01-ai/yi-1.5-9b-chat": {
+ "description": "零一萬物,最新開源微調模型,90億參數,微調支持多種對話場景,高質量訓練數據,對齊人類偏好。"
+ },
"360gpt-pro": {
"description": "360GPT Pro 作為 360 AI 模型系列的重要成員,以高效的文本處理能力滿足多樣化的自然語言應用場景,支持長文本理解和多輪對話等功能。"
},
@@ -14,9 +23,15 @@
"360gpt-turbo-responsibility-8k": {
"description": "360GPT Turbo Responsibility 8K 強調語義安全和責任導向,專為對內容安全有高度要求的應用場景設計,確保用戶體驗的準確性與穩健性。"
},
+ "360gpt2-o1": {
+ "description": "360gpt2-o1 使用樹搜索構建思維鏈,並引入了反思機制,使用強化學習訓練,模型具備自我反思與糾錯的能力。"
+ },
"360gpt2-pro": {
"description": "360GPT2 Pro 是 360 公司推出的高級自然語言處理模型,具備卓越的文本生成和理解能力,尤其在生成與創作領域表現出色,能夠處理複雜的語言轉換和角色演繹任務。"
},
+ "360zhinao2-o1": {
+ "description": "360zhinao2-o1 使用樹搜索構建思維鏈,並引入了反思機制,使用強化學習訓練,模型具備自我反思與糾錯的能力。"
+ },
"4.0Ultra": {
"description": "Spark4.0 Ultra 是星火大模型系列中最為強大的版本,在升級聯網搜索鏈路同時,提升對文本內容的理解和總結能力。它是用於提升辦公生產力和準確響應需求的全方位解決方案,是引領行業的智能產品。"
},
@@ -32,23 +47,140 @@
"Baichuan4": {
"description": "模型能力國內第一,在知識百科、長文本、生成創作等中文任務上超越國外主流模型。還具備行業領先的多模態能力,多項權威評測基準表現優異。"
},
+ "Baichuan4-Air": {
+ "description": "模型能力國內第一,在知識百科、長文本、生成創作等中文任務上超越國外主流模型。還具備行業領先的多模態能力,多項權威評測基準表現優異。"
+ },
+ "Baichuan4-Turbo": {
+ "description": "模型能力國內第一,在知識百科、長文本、生成創作等中文任務上超越國外主流模型。還具備行業領先的多模態能力,多項權威評測基準表現優異。"
+ },
+ "DeepSeek-R1": {
+ "description": "最先進的高效 LLM,擅長推理、數學和程式設計。"
+ },
+ "DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek R1——DeepSeek 套件中更大更智能的模型——被蒸餾到 Llama 70B 架構中。基於基準測試和人工評估,該模型比原始 Llama 70B 更智能,尤其在需要數學和事實精確性的任務上表現出色。"
+ },
+ "DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "基於 Qwen2.5-Math-1.5B 的 DeepSeek-R1 蒸餾模型,通過強化學習與冷啟動數據優化推理性能,開源模型刷新多任務標杆。"
+ },
+ "DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "基於 Qwen2.5-14B 的 DeepSeek-R1 蒸餾模型,通過強化學習與冷啟動數據優化推理性能,開源模型刷新多任務標杆。"
+ },
+ "DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1 系列通過強化學習與冷啟動數據優化推理性能,開源模型刷新多任務標杆,超越 OpenAI-o1-mini 水平。"
+ },
+ "DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "基於 Qwen2.5-Math-7B 的 DeepSeek-R1 蒸餾模型,通過強化學習與冷啟動數據優化推理性能,開源模型刷新多任務標杆。"
+ },
+ "Doubao-1.5-vision-pro-32k": {
+ "description": "Doubao-1.5-vision-pro 全新升級的多模態大模型,支持任意解析度和極端長寬比圖像識別,增強視覺推理、文檔識別、細節信息理解和指令遵循能力。"
+ },
+ "Doubao-lite-128k": {
+ "description": "Doubao-lite 擁有極致的回應速度,更好的性價比,為客戶不同場景提供更靈活的選擇。支持 128k 上下文窗口的推理和精調。"
+ },
+ "Doubao-lite-32k": {
+ "description": "Doubao-lite 擁有極致的回應速度,更好的性價比,為客戶不同場景提供更靈活的選擇。支持 32k 上下文窗口的推理和精調。"
+ },
+ "Doubao-lite-4k": {
+ "description": "Doubao-lite 擁有極致的回應速度,更好的性價比,為客戶不同場景提供更靈活的選擇。支持 4k 上下文窗口的推理和精調。"
+ },
+ "Doubao-pro-128k": {
+ "description": "效果最好的主力模型,適合處理複雜任務,在參考問答、總結摘要、創作、文本分類、角色扮演等場景都有很好的效果。支持 128k 上下文窗口的推理和精調。"
+ },
+ "Doubao-pro-256k": {
+ "description": "效果最好的主力模型,適合處理複雜任務,在參考問答、總結摘要、創作、文本分類、角色扮演等場景都有很好的效果。支持 256k 上下文窗口的推理和精調。"
+ },
+ "Doubao-pro-32k": {
+ "description": "效果最好的主力模型,適合處理複雜任務,在參考問答、總結摘要、創作、文本分類、角色扮演等場景都有很好的效果。支持 32k 上下文窗口的推理和精調。"
+ },
+ "Doubao-pro-4k": {
+ "description": "效果最好的主力模型,適合處理複雜任務,在參考問答、總結摘要、創作、文本分類、角色扮演等場景都有很好的效果。支持 4k 上下文窗口的推理和精調。"
+ },
+ "Doubao-vision-lite-32k": {
+ "description": "Doubao-vision 模型是豆包推出的多模態大模型,具備強大的圖片理解與推理能力,以及精準的指令理解能力。模型在圖像文本信息抽取、基於圖像的推理任務上展現出強大的性能,能夠應用於更複雜、更廣泛的視覺問答任務。"
+ },
+ "Doubao-vision-pro-32k": {
+ "description": "Doubao-vision 模型是豆包推出的多模態大模型,具備強大的圖片理解與推理能力,以及精準的指令理解能力。模型在圖像文本信息抽取、基於圖像的推理任務上展現出強大的性能,能夠應用於更複雜、更廣泛的視覺問答任務。"
+ },
+ "ERNIE-3.5-128K": {
+ "description": "百度自研的旗艦級大規模語言模型,覆蓋海量中英文語料,具有強大的通用能力,可滿足絕大部分對話問答、創作生成、插件應用場景要求;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ERNIE-3.5-8K": {
+ "description": "百度自研的旗艦級大規模語言模型,覆蓋海量中英文語料,具有強大的通用能力,可滿足絕大部分對話問答、創作生成、插件應用場景要求;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ERNIE-3.5-8K-Preview": {
+ "description": "百度自研的旗艦級大規模語言模型,覆蓋海量中英文語料,具有強大的通用能力,可滿足絕大部分對話問答、創作生成、插件應用場景要求;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ERNIE-4.0-8K-Latest": {
+ "description": "百度自研的旗艦級超大規模語言模型,相較ERNIE 3.5實現了模型能力全面升級,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ERNIE-4.0-8K-Preview": {
+ "description": "百度自研的旗艦級超大規模語言模型,相較ERNIE 3.5實現了模型能力全面升級,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ERNIE-4.0-Turbo-8K-Latest": {
+ "description": "百度自研的旗艦級超大規模大語言模型,綜合效果表現優異,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。相較於 ERNIE 4.0 在性能表現上更為優秀。"
+ },
+ "ERNIE-4.0-Turbo-8K-Preview": {
+ "description": "百度自研的旗艦級超大規模語言模型,綜合效果表現出色,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。相較於ERNIE 4.0在性能表現上更優秀。"
+ },
+ "ERNIE-Character-8K": {
+ "description": "百度自研的垂直場景大語言模型,適合遊戲NPC、客服對話、對話角色扮演等應用場景,人設風格更為鮮明、一致,指令遵循能力更強,推理性能更優。"
+ },
+ "ERNIE-Lite-Pro-128K": {
+ "description": "百度自研的輕量級大語言模型,兼顧優異的模型效果與推理性能,效果比ERNIE Lite更優,適合低算力AI加速卡推理使用。"
+ },
+ "ERNIE-Speed-128K": {
+ "description": "百度2024年最新發布的自研高性能大語言模型,通用能力優異,適合作為基座模型進行精調,更好地處理特定場景問題,同時具備極佳的推理性能。"
+ },
+ "ERNIE-Speed-Pro-128K": {
+ "description": "百度2024年最新發布的自研高性能大語言模型,通用能力優異,效果比ERNIE Speed更優,適合作為基座模型進行精調,更好地處理特定場景問題,同時具備極佳的推理性能。"
+ },
"Gryphe/MythoMax-L2-13b": {
"description": "MythoMax-L2 (13B) 是一種創新模型,適合多領域應用和複雜任務。"
},
- "Max-32k": {
- "description": "Spark Max 32K 配備了更強大的上下文處理能力,具備更佳的上下文理解和邏輯推理能力,支持32K tokens的文本輸入,適用於長文檔閱讀、私有知識問答等場景"
+ "InternVL2-8B": {
+ "description": "InternVL2-8B 是一款強大的視覺語言模型,支持圖像與文本的多模態處理,能夠精確識別圖像內容並生成相關描述或回答。"
+ },
+ "InternVL2.5-26B": {
+ "description": "InternVL2.5-26B 是一款強大的視覺語言模型,支持圖像與文本的多模態處理,能夠精確識別圖像內容並生成相關描述或回答。"
+ },
+ "Llama-3.2-11B-Vision-Instruct": {
+ "description": "在高解析度圖像上表現出色的圖像推理能力,適用於視覺理解應用。"
+ },
+ "Llama-3.2-90B-Vision-Instruct\t": {
+ "description": "適用於視覺理解代理應用的高級圖像推理能力。"
+ },
+ "LoRA/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct 是阿里雲發布的最新大語言模型系列之一。該 72B 模型在編碼和數學等領域具有顯著改進的能力。該模型還提供了多語言支持,覆蓋超過 29 種語言,包括中文、英文等。模型在指令跟隨、理解結構化數據以及生成結構化輸出(尤其是 JSON)方面都有顯著提升"
+ },
+ "LoRA/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct 是阿里雲發布的最新大語言模型系列之一。該 7B 模型在編碼和數學等領域具有顯著改進的能力。該模型還提供了多語言支持,覆蓋超過 29 種語言,包括中文、英文等。模型在指令跟隨、理解結構化數據以及生成結構化輸出(尤其是 JSON)方面都有顯著提升"
+ },
+ "Meta-Llama-3.1-405B-Instruct": {
+ "description": "Llama 3.1指令調優的文本模型,針對多語言對話用例進行了優化,在許多可用的開源和封閉聊天模型中,在常見行業基準上表現優異。"
},
- "Nous-Hermes-2-Mixtral-8x7B-DPO": {
- "description": "Hermes 2 Mixtral 8x7B DPO 是一款高度靈活的多模型合併,旨在提供卓越的創造性體驗。"
+ "Meta-Llama-3.1-70B-Instruct": {
+ "description": "Llama 3.1指令調優的文本模型,針對多語言對話用例進行了優化,在許多可用的開源和封閉聊天模型中,在常見行業基準上表現優異。"
+ },
+ "Meta-Llama-3.1-8B-Instruct": {
+ "description": "Llama 3.1指令調優的文本模型,針對多語言對話用例進行了優化,在許多可用的開源和封閉聊天模型中,在常見行業基準上表現優異。"
+ },
+ "Meta-Llama-3.2-1B-Instruct": {
+ "description": "先進的最尖端小型語言模型,具備語言理解、卓越的推理能力和文本生成能力。"
+ },
+ "Meta-Llama-3.2-3B-Instruct": {
+ "description": "先進的最尖端小型語言模型,具備語言理解、卓越的推理能力和文本生成能力。"
+ },
+ "Meta-Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先進的多語言開源大型語言模型,以極低成本體驗媲美 405B 模型的性能。基於 Transformer 結構,並透過監督微調(SFT)和人類反饋強化學習(RLHF)提升有用性和安全性。其指令調優版本專為多語言對話優化,在多項行業基準上表現優於眾多開源和封閉聊天模型。知識截止日期為 2023 年 12 月"
+ },
+ "MiniMax-Text-01": {
+ "description": "在 MiniMax-01系列模型中,我們做了大膽創新:首次大規模實現線性注意力機制,傳統 Transformer架構不再是唯一的選擇。這個模型的參數量高達4560億,其中單次激活459億。模型綜合性能比肩海外頂尖模型,同時能夠高效處理全球最長400萬token的上下文,是GPT-4o的32倍,Claude-3.5-Sonnet的20倍。"
},
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) 是高精度的指令模型,適用於複雜計算。"
},
- "NousResearch/Nous-Hermes-2-Yi-34B": {
- "description": "Nous Hermes-2 Yi (34B) 提供優化的語言輸出和多樣化的應用可能。"
- },
- "Phi-3-5-mini-instruct": {
- "description": "Phi-3-mini模型的更新版本。"
+ "OpenGVLab/InternVL2-26B": {
+ "description": "InternVL2在各種視覺語言任務上展現出了卓越的性能,包括文檔和圖表理解、場景文本理解、OCR、科學和數學問題解決等。"
},
"Phi-3-medium-128k-instruct": {
"description": "相同的Phi-3-medium模型,但具有更大的上下文大小,適用於RAG或少量提示。"
@@ -68,18 +200,69 @@
"Phi-3-small-8k-instruct": {
"description": "一個7B參數模型,質量優於Phi-3-mini,專注於高質量、推理密集型數據。"
},
- "Pro-128k": {
- "description": "Spark Pro-128K 配置了特大上下文處理能力,能夠處理多達128K的上下文信息,特別適合需通篇分析和長期邏輯關聯處理的長文內容,可在複雜文本溝通中提供流暢一致的邏輯與多樣的引用支持。"
+ "Phi-3.5-mini-instruct": {
+ "description": "Phi-3-mini模型的更新版。"
+ },
+ "Phi-3.5-vision-instrust": {
+ "description": "Phi-3-vision模型的更新版。"
+ },
+ "Pro/OpenGVLab/InternVL2-8B": {
+ "description": "InternVL2在各種視覺語言任務上展現出了卓越的性能,包括文檔和圖表理解、場景文本理解、OCR、科學和數學問題解決等。"
+ },
+ "Pro/Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct 是 Qwen2 系列中的指令微調大語言模型,參數規模為 1.5B。該模型基於 Transformer 架構,採用了 SwiGLU 激活函數、注意力 QKV 偏置和組查詢注意力等技術。它在語言理解、生成、多語言能力、編碼、數學和推理等多個基準測試中表現出色,超越了大多數開源模型。與 Qwen1.5-1.8B-Chat 相比,Qwen2-1.5B-Instruct 在 MMLU、HumanEval、GSM8K、C-Eval 和 IFEval 等測試中均顯示出顯著的性能提升,儘管參數量略少"
+ },
+ "Pro/Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-7B-Instruct 是 Qwen2 系列中的指令微調大語言模型,參數規模為 7B。該模型基於 Transformer 架構,採用了 SwiGLU 激活函數、注意力 QKV 偏置和組查詢注意力等技術。它能夠處理大規模輸入。該模型在語言理解、生成、多語言能力、編碼、數學和推理等多個基準測試中表現出色,超越了大多數開源模型,並在某些任務上展現出與專有模型相當的競爭力。Qwen2-7B-Instruct 在多項評測中均優於 Qwen1.5-7B-Chat,顯示出顯著的性能提升"
+ },
+ "Pro/Qwen/Qwen2-VL-7B-Instruct": {
+ "description": "Qwen2-VL 是 Qwen-VL 模型的最新迭代版本,在視覺理解基準測試中達到了最先進的性能。"
+ },
+ "Pro/Qwen/Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct 是阿里雲發布的最新大語言模型系列之一。該 7B 模型在編碼和數學等領域具有顯著改進的能力。該模型還提供了多語言支持,覆蓋超過 29 種語言,包括中文、英文等。模型在指令跟隨、理解結構化數據以及生成結構化輸出(尤其是 JSON)方面都有顯著提升"
+ },
+ "Pro/Qwen/Qwen2.5-Coder-7B-Instruct": {
+ "description": "Qwen2.5-Coder-7B-Instruct 是阿里雲發布的代碼特定大語言模型系列的最新版本。該模型在 Qwen2.5 的基礎上,通過 5.5 萬億個 tokens 的訓練,顯著提升了代碼生成、推理和修復能力。它不僅增強了編碼能力,還保持了數學和通用能力的優勢。模型為代碼智能體等實際應用提供了更全面的基礎"
+ },
+ "Pro/THUDM/glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat 是智譜 AI 推出的 GLM-4 系列預訓練模型中的開源版本。該模型在語義、數學、推理、代碼和知識等多個方面表現出色。除了支持多輪對話外,GLM-4-9B-Chat 還具備網頁瀏覽、代碼執行、自定義工具調用(Function Call)和長文本推理等高級功能。模型支持 26 種語言,包括中文、英文、日文、韓文和德文等。在多項基準測試中,GLM-4-9B-Chat 展現了優秀的性能,如 AlignBench-v2、MT-Bench、MMLU 和 C-Eval 等。該模型支持最大 128K 的上下文長度,適用於學術研究和商業應用"
+ },
+ "Pro/deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 是一款強化學習(RL)驅動的推理模型,解決了模型中的重複性和可讀性問題。在 RL 之前,DeepSeek-R1 引入了冷啟動數據,進一步優化了推理性能。它在數學、代碼和推理任務中與 OpenAI-o1 表現相當,並且透過精心設計的訓練方法,提升了整體效果。"
+ },
+ "Pro/deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 是一款擁有 6710 億參數的混合專家(MoE)語言模型,採用多頭潛在注意力(MLA)和 DeepSeekMoE 架構,結合無輔助損失的負載平衡策略,優化推理和訓練效率。透過在 14.8 萬億高質量tokens上預訓練,並進行監督微調和強化學習,DeepSeek-V3 在性能上超越其他開源模型,接近領先閉源模型。"
+ },
+ "Pro/google/gemma-2-9b-it": {
+ "description": "Gemma 是 Google 開發的輕量級、最先進的開放模型系列之一。它是一個僅解碼器的大型語言模型,支持英語,提供開放權重、預訓練變體和指令微調變體。Gemma 模型適用於各種文本生成任務,包括問答、摘要和推理。該 9B 模型是通過 8 萬億個 tokens 訓練而成。其相對較小的規模使其可以在資源有限的環境中部署,如筆記本電腦、桌面電腦或您自己的雲基礎設施,從而使更多人能夠訪問最先進的 AI 模型並促進創新"
+ },
+ "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct": {
+ "description": "Meta Llama 3.1 是由 Meta 開發的多語言大型語言模型家族,包括 8B、70B 和 405B 三種參數規模的預訓練和指令微調變體。該 8B 指令微調模型針對多語言對話場景進行了優化,在多項行業基準測試中表現優異。模型訓練使用了超過 15 萬億個 tokens 的公開數據,並採用了監督微調和人類反饋強化學習等技術來提升模型的有用性和安全性。Llama 3.1 支持文本生成和代碼生成,知識截止日期為 2023 年 12 月"
+ },
+ "QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview 是一款獨具創新的自然語言處理模型,能夠高效處理複雜的對話生成與上下文理解任務。"
+ },
+ "Qwen/QVQ-72B-Preview": {
+ "description": "QVQ-72B-Preview 是由 Qwen 團隊開發的專注於視覺推理能力的研究型模型,其在複雜場景理解和解決視覺相關的數學問題方面具有獨特優勢。"
+ },
+ "Qwen/QwQ-32B": {
+ "description": "QwQ 是 Qwen 系列的推理模型。與傳統的指令調優模型相比,QwQ 具備思考和推理能力,能夠在下游任務中實現顯著增強的性能,尤其是在解決困難問題方面。QwQ-32B 是中型推理模型,能夠在與最先進的推理模型(如 DeepSeek-R1、o1-mini)的對比中取得有競爭力的性能。該模型採用 RoPE、SwiGLU、RMSNorm 和 Attention QKV bias 等技術,具有 64 層網絡結構和 40 個 Q 注意力頭(GQA 架構中 KV 為 8 個)。"
},
- "Qwen/Qwen1.5-110B-Chat": {
- "description": "作為 Qwen2 的測試版,Qwen1.5 使用大規模數據實現了更精確的對話功能。"
+ "Qwen/QwQ-32B-Preview": {
+ "description": "QwQ-32B-Preview是Qwen 最新的實驗性研究模型,專注於提升AI推理能力。通過探索語言混合、遞歸推理等複雜機制,主要優勢包括強大的推理分析能力、數學和編程能力。與此同時,也存在語言切換問題、推理循環、安全性考量、其他能力方面的差異。"
},
- "Qwen/Qwen1.5-72B-Chat": {
- "description": "Qwen 1.5 Chat (72B) 提供快速響應和自然對話能力,適合多語言環境。"
+ "Qwen/Qwen2-1.5B-Instruct": {
+ "description": "Qwen2-1.5B-Instruct 是 Qwen2 系列中的指令微調大語言模型,參數規模為 1.5B。該模型基於 Transformer 架構,採用了 SwiGLU 激活函數、注意力 QKV 偏置和組查詢注意力等技術。它在語言理解、生成、多語言能力、編碼、數學和推理等多個基準測試中表現出色,超越了大多數開源模型。與 Qwen1.5-1.8B-Chat 相比,Qwen2-1.5B-Instruct 在 MMLU、HumanEval、GSM8K、C-Eval 和 IFEval 等測試中均顯示出顯著的性能提升,儘管參數量略少"
},
"Qwen/Qwen2-72B-Instruct": {
"description": "Qwen2 是先進的通用語言模型,支持多種指令類型。"
},
+ "Qwen/Qwen2-7B-Instruct": {
+ "description": "Qwen2-72B-Instruct 是 Qwen2 系列中的指令微調大語言模型,參數規模為 72B。該模型基於 Transformer 架構,採用了 SwiGLU 激活函數、注意力 QKV 偏置和組查詢注意力等技術。它能夠處理大規模輸入。該模型在語言理解、生成、多語言能力、編碼、數學和推理等多個基準測試中表現出色,超越了大多數開源模型,並在某些任務上展現出與專有模型相當的競爭力"
+ },
+ "Qwen/Qwen2-VL-72B-Instruct": {
+ "description": "Qwen2-VL 是 Qwen-VL 模型的最新迭代版本,在視覺理解基準測試中達到了最先進的性能。"
+ },
"Qwen/Qwen2.5-14B-Instruct": {
"description": "Qwen2.5是全新的大型語言模型系列,旨在優化指令式任務的處理。"
},
@@ -87,20 +270,119 @@
"description": "Qwen2.5是全新的大型語言模型系列,旨在優化指令式任務的處理。"
},
"Qwen/Qwen2.5-72B-Instruct": {
- "description": "Qwen2.5是全新的大型語言模型系列,具有更強的理解和生成能力。"
+ "description": "阿里雲通義千問團隊開發的大型語言模型"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-128K": {
+ "description": "Qwen2.5 是全新的大型語言模型系列,具有更強的理解和生成能力。"
+ },
+ "Qwen/Qwen2.5-72B-Instruct-Turbo": {
+ "description": "Qwen2.5 是全新的大型語言模型系列,旨在優化指令式任務的處理。"
},
"Qwen/Qwen2.5-7B-Instruct": {
"description": "Qwen2.5是全新的大型語言模型系列,旨在優化指令式任務的處理。"
},
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
+ "description": "Qwen2.5 是全新的大型語言模型系列,旨在優化指令式任務的處理。"
+ },
+ "Qwen/Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder 專注於代碼編寫。"
+ },
"Qwen/Qwen2.5-Coder-7B-Instruct": {
- "description": "Qwen2.5-Coder專注於代碼編寫。"
+ "description": "Qwen2.5-Coder-7B-Instruct 是阿里雲發布的代碼特定大語言模型系列的最新版本。該模型在 Qwen2.5 的基礎上,通過 5.5 萬億個 tokens 的訓練,顯著提升了代碼生成、推理和修復能力。它不僅增強了編碼能力,還保持了數學和通用能力的優勢。模型為代碼智能體等實際應用提供了更全面的基礎"
+ },
+ "Qwen2-72B-Instruct": {
+ "description": "Qwen2 是 Qwen 模型的最新系列,支持 128k 上下文,對比當前最優的開源模型,Qwen2-72B 在自然語言理解、知識、代碼、數學及多語言等多項能力上均顯著超越當前領先的模型。"
+ },
+ "Qwen2-7B-Instruct": {
+ "description": "Qwen2 是 Qwen 模型的最新系列,能夠超越同等規模的最優開源模型甚至更大規模的模型,Qwen2 7B 在多個評測上取得顯著的優勢,尤其是在代碼及中文理解上。"
+ },
+ "Qwen2-VL-72B": {
+ "description": "Qwen2-VL-72B是一款強大的視覺語言模型,支持圖像與文本的多模態處理,能夠精確識別圖像內容並生成相關描述或回答。"
+ },
+ "Qwen2.5-14B-Instruct": {
+ "description": "Qwen2.5-14B-Instruct 是一款140億參數的大語言模型,性能表現優秀,優化中文和多語言場景,支持智能問答、內容生成等應用。"
+ },
+ "Qwen2.5-32B-Instruct": {
+ "description": "Qwen2.5-32B-Instruct 是一款320億參數的大語言模型,性能表現均衡,優化中文和多語言場景,支持智能問答、內容生成等應用。"
+ },
+ "Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct 支持 16k 上下文,生成長文本超過 8K。支持 function call 與外部系統無縫互動,極大提升了靈活性和擴展性。模型知識明顯增加,並且大幅提高了編碼和數學能力,多語言支持超過 29 種。"
+ },
+ "Qwen2.5-7B-Instruct": {
+ "description": "Qwen2.5-7B-Instruct 是一款70億參數的大語言模型,支持函數調用與外部系統無縫互動,極大提升了靈活性和擴展性。優化中文和多語言場景,支持智能問答、內容生成等應用。"
+ },
+ "Qwen2.5-Coder-14B-Instruct": {
+ "description": "Qwen2.5-Coder-14B-Instruct 是一款基於大規模預訓練的程式指令模型,具備強大的程式理解和生成能力,能夠高效地處理各種程式任務,特別適合智能程式編寫、自動化腳本生成和程式問題解答。"
+ },
+ "Qwen2.5-Coder-32B-Instruct": {
+ "description": "Qwen2.5-Coder-32B-Instruct 是一款專為代碼生成、代碼理解和高效開發場景設計的大型語言模型,採用了業界領先的32B參數規模,能夠滿足多樣化的程式需求。"
+ },
+ "SenseChat": {
+ "description": "基礎版本模型 (V4),4K上下文長度,通用能力強大"
+ },
+ "SenseChat-128K": {
+ "description": "基礎版本模型 (V4),128K上下文長度,在長文本理解及生成等任務中表現出色"
+ },
+ "SenseChat-32K": {
+ "description": "基礎版本模型 (V4),32K上下文長度,靈活應用於各類場景"
+ },
+ "SenseChat-5": {
+ "description": "最新版本模型 (V5.5),128K上下文長度,在數學推理、英文對話、指令跟隨以及長文本理解等領域能力顯著提升,比肩GPT-4o"
+ },
+ "SenseChat-5-1202": {
+ "description": "是基於V5.5的最新版本,較上版本在中英文基礎能力、聊天、理科知識、文科知識、寫作、數理邏輯、字數控制等幾個維度的表現有顯著提升。"
+ },
+ "SenseChat-5-Cantonese": {
+ "description": "32K上下文長度,在粵語的對話理解上超越了GPT-4,在知識、推理、數學及程式編寫等多個領域均能與GPT-4 Turbo相媲美"
},
- "Qwen/Qwen2.5-Math-72B-Instruct": {
- "description": "Qwen2.5-Math專注於數學領域的問題求解,為高難度題提供專業解答。"
+ "SenseChat-Character": {
+ "description": "標準版模型,8K上下文長度,高響應速度"
+ },
+ "SenseChat-Character-Pro": {
+ "description": "高級版模型,32K上下文長度,能力全面提升,支持中/英文對話"
+ },
+ "SenseChat-Turbo": {
+ "description": "適用於快速問答、模型微調場景"
+ },
+ "SenseChat-Turbo-1202": {
+ "description": "是最新的輕量版本模型,達到全量模型90%以上能力,顯著降低推理成本。"
+ },
+ "SenseChat-Vision": {
+ "description": "最新版本模型 (V5.5),支持多圖的輸入,全面實現模型基礎能力優化,在對象屬性識別、空間關係、動作事件識別、場景理解、情感識別、邏輯常識推理和文本理解生成上都實現了較大提升。"
+ },
+ "Skylark2-lite-8k": {
+ "description": "雲雀(Skylark)第二代模型,Skylark2-lite 模型有較高的回應速度,適用於實時性要求高、成本敏感、對模型精度要求不高的場景,上下文窗口長度為 8k。"
+ },
+ "Skylark2-pro-32k": {
+ "description": "雲雀(Skylark)第二代模型,Skylark2-pro 版本有較高的模型精度,適用於較為複雜的文本生成場景,如專業領域文案生成、小說創作、高品質翻譯等,上下文窗口長度為 32k。"
+ },
+ "Skylark2-pro-4k": {
+ "description": "雲雀(Skylark)第二代模型,Skylark2-pro 模型有較高的模型精度,適用於較為複雜的文本生成場景,如專業領域文案生成、小說創作、高品質翻譯等,上下文窗口長度為 4k。"
+ },
+ "Skylark2-pro-character-4k": {
+ "description": "雲雀(Skylark)第二代模型,Skylark2-pro-character 模型具有優秀的角色扮演和聊天能力,擅長根據用戶 prompt 要求扮演不同角色與用戶展開聊天,角色風格突出,對話內容自然流暢,適用於構建聊天機器人、虛擬助手和在線客服等場景,有較高的回應速度。"
+ },
+ "Skylark2-pro-turbo-8k": {
+ "description": "雲雀(Skylark)第二代模型,Skylark2-pro-turbo-8k 推理更快,成本更低,上下文窗口長度為 8k。"
+ },
+ "THUDM/chatglm3-6b": {
+ "description": "ChatGLM3-6B 是 ChatGLM 系列的開源模型,由智譜 AI 開發。該模型保留了前代模型的優秀特性,如對話流暢和部署門檻低,同時引入了新的特性。它採用了更多樣的訓練數據、更充分的訓練步數和更合理的訓練策略,在 10B 以下的預訓練模型中表現出色。ChatGLM3-6B 支持多輪對話、工具調用、代碼執行和 Agent 任務等複雜場景。除對話模型外,還開源了基礎模型 ChatGLM-6B-Base 和長文本對話模型 ChatGLM3-6B-32K。該模型對學術研究完全開放,在登記後也允許免費商業使用"
},
"THUDM/glm-4-9b-chat": {
"description": "GLM-4 9B 開放源碼版本,為會話應用提供優化後的對話體驗。"
},
+ "TeleAI/TeleChat2": {
+ "description": "TeleChat2大模型是由中國電信從0到1自主研發的生成式語義大模型,支持百科問答、代碼生成、長文生成等功能,為用戶提供對話諮詢服務,能夠與用戶進行對話互動,回答問題,協助創作,高效便捷地幫助用戶獲取信息、知識和靈感。模型在幻覺問題、長文生成、邏輯理解等方面均有較出色表現。"
+ },
+ "TeleAI/TeleMM": {
+ "description": "TeleMM多模態大模型是由中國電信自主研發的多模態理解大模型,能夠處理文本、圖像等多種模態輸入,支持圖像理解、圖表分析等功能,為用戶提供跨模態的理解服務。模型能夠與用戶進行多模態互動,準確理解輸入內容,回答問題、協助創作,並高效提供多模態信息和靈感支持。在細粒度感知,邏輯推理等多模態任務上有出色表現"
+ },
+ "Vendor-A/Qwen/Qwen2.5-72B-Instruct": {
+ "description": "Qwen2.5-72B-Instruct 是阿里雲發布的最新大語言模型系列之一。該 72B 模型在編碼和數學等領域具有顯著改進的能力。該模型還提供了多語言支持,覆蓋超過 29 種語言,包括中文、英文等。模型在指令跟隨、理解結構化數據以及生成結構化輸出(尤其是 JSON)方面都有顯著提升"
+ },
+ "Yi-34B-Chat": {
+ "description": "Yi-1.5-34B 在保持原系列模型優秀的通用語言能力的前提下,通過增量訓練 5 千億高質量 token,大幅提高了數學邏輯和代碼能力。"
+ },
"abab5.5-chat": {
"description": "面向生產力場景,支持複雜任務處理和高效文本生成,適用於專業領域應用。"
},
@@ -116,24 +398,15 @@
"abab6.5t-chat": {
"description": "針對中文人設對話場景優化,提供流暢且符合中文表達習慣的對話生成能力。"
},
- "accounts/fireworks/models/firefunction-v1": {
- "description": "Fireworks 開源函數調用模型,提供卓越的指令執行能力和開放可定制的特性。"
- },
- "accounts/fireworks/models/firefunction-v2": {
- "description": "Fireworks 公司最新推出的 Firefunction-v2 是一款性能卓越的函數調用模型,基於 Llama-3 開發,並通過大量優化,特別適用於函數調用、對話及指令跟隨等場景。"
- },
- "accounts/fireworks/models/firellava-13b": {
- "description": "fireworks-ai/FireLLaVA-13b 是一款視覺語言模型,可以同時接收圖像和文本輸入,經過高質量數據訓練,適合多模態任務。"
+ "accounts/fireworks/models/deepseek-r1": {
+ "description": "DeepSeek-R1 是一款最先進的大型語言模型,經過強化學習和冷啟動數據的優化,具有出色的推理、數學和編程性能。"
},
- "accounts/fireworks/models/gemma2-9b-it": {
- "description": "Gemma 2 9B 指令模型,基於之前的 Google 技術,適合回答問題、總結和推理等多種文本生成任務。"
+ "accounts/fireworks/models/deepseek-v3": {
+ "description": "Deepseek 提供的強大 Mixture-of-Experts (MoE) 語言模型,總參數量為 671B,每個標記激活 37B 參數。"
},
"accounts/fireworks/models/llama-v3-70b-instruct": {
"description": "Llama 3 70B 指令模型,專為多語言對話和自然語言理解優化,性能優於多數競爭模型。"
},
- "accounts/fireworks/models/llama-v3-70b-instruct-hf": {
- "description": "Llama 3 70B 指令模型(HF 版本),與官方實現結果保持一致,適合高質量的指令跟隨任務。"
- },
"accounts/fireworks/models/llama-v3-8b-instruct": {
"description": "Llama 3 8B 指令模型,優化用於對話及多語言任務,表現卓越且高效。"
},
@@ -149,26 +422,44 @@
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
"description": "Llama 3.1 8B 指令模型,專為多語言對話優化,能夠在常見行業基準上超越多數開源及閉源模型。"
},
+ "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
+ "description": "Meta的11B參數指令調整圖像推理模型。該模型針對視覺識別、圖像推理、圖像描述和回答關於圖像的一般性問題進行了優化。該模型能夠理解視覺數據,如圖表和圖形,並通過生成文本描述圖像細節來弥合視覺與語言之間的差距。"
+ },
+ "accounts/fireworks/models/llama-v3p2-3b-instruct": {
+ "description": "Llama 3.2 3B 指令模型是Meta推出的一款輕量級多語言模型。該模型旨在提高效率,與更大型的模型相比,在延遲和成本方面提供了顯著的改進。該模型的示例用例包括查詢和提示重寫以及寫作輔助。"
+ },
+ "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
+ "description": "Meta的90B參數指令調整圖像推理模型。該模型針對視覺識別、圖像推理、圖像描述和回答關於圖像的一般性問題進行了優化。該模型能夠理解視覺數據,如圖表和圖形,並通過生成文本描述圖像細節來弥合視覺與語言之間的差距。"
+ },
+ "accounts/fireworks/models/llama-v3p3-70b-instruct": {
+ "description": "Llama 3.3 70B Instruct 是 Llama 3.1 70B 的 12 月更新版本。該模型在 Llama 3.1 70B(於 2024 年 7 月發布)的基礎上進行了改進,增強了工具調用、多語言文本支持、數學和編程能力。該模型在推理、數學和指令遵循方面達到了行業領先水平,並且能夠提供與 3.1 405B 相似的性能,同時在速度和成本上具有顯著優勢。"
+ },
+ "accounts/fireworks/models/mistral-small-24b-instruct-2501": {
+ "description": "24B 參數模型,具備與更大型模型相當的最先進能力。"
+ },
"accounts/fireworks/models/mixtral-8x22b-instruct": {
"description": "Mixtral MoE 8x22B 指令模型,大規模參數和多專家架構,全方位支持複雜任務的高效處理。"
},
"accounts/fireworks/models/mixtral-8x7b-instruct": {
"description": "Mixtral MoE 8x7B 指令模型,多專家架構提供高效的指令跟隨及執行。"
},
- "accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
- "description": "Mixtral MoE 8x7B 指令模型(HF 版本),性能與官方實現一致,適合多種高效任務場景。"
- },
"accounts/fireworks/models/mythomax-l2-13b": {
"description": "MythoMax L2 13B 模型,結合新穎的合併技術,擅長敘事和角色扮演。"
},
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
"description": "Phi 3 Vision 指令模型,輕量級多模態模型,能夠處理複雜的視覺和文本信息,具備較強的推理能力。"
},
- "accounts/fireworks/models/starcoder-16b": {
- "description": "StarCoder 15.5B 模型,支持高級編程任務,多語言能力增強,適合複雜代碼生成和理解。"
+ "accounts/fireworks/models/qwen-qwq-32b-preview": {
+ "description": "QwQ模型是由 Qwen 團隊開發的實驗性研究模型,專注於增強 AI 推理能力。"
+ },
+ "accounts/fireworks/models/qwen2-vl-72b-instruct": {
+ "description": "Qwen-VL 模型的 72B 版本是阿里巴巴最新迭代的成果,代表了近一年的創新。"
},
- "accounts/fireworks/models/starcoder-7b": {
- "description": "StarCoder 7B 模型,針對 80 多種編程語言訓練,擁有出色的編程填充能力和語境理解。"
+ "accounts/fireworks/models/qwen2p5-72b-instruct": {
+ "description": "Qwen2.5 是由阿里雲 Qwen 團隊開發的一系列僅包含解碼器的語言模型。這些模型提供不同的大小,包括 0.5B、1.5B、3B、7B、14B、32B 和 72B,並且有基礎版(base)和指令版(instruct)兩種變體。"
+ },
+ "accounts/fireworks/models/qwen2p5-coder-32b-instruct": {
+ "description": "Qwen2.5 Coder 32B Instruct 是阿里雲發布的代碼特定大語言模型系列的最新版本。該模型在 Qwen2.5 的基礎上,通過 5.5 萬億個 tokens 的訓練,顯著提升了代碼生成、推理和修復能力。它不僅增強了編碼能力,還保持了數學和通用能力的優勢。模型為代碼智能體等實際應用提供了更全面的基礎"
},
"accounts/yi-01-ai/models/yi-large": {
"description": "Yi-Large 模型,具備卓越的多語言處理能力,可用於各類語言生成和理解任務。"
@@ -179,12 +470,12 @@
"ai21-jamba-1.5-mini": {
"description": "一個52B參數(12B活躍)多語言模型,提供256K長上下文窗口、函數調用、結構化輸出和基於實體的生成。"
},
- "ai21-jamba-instruct": {
- "description": "一個生產級的基於Mamba的LLM模型,以實現最佳性能、質量和成本效率。"
- },
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
"description": "Claude 3.5 Sonnet提升了行業標準,性能超過競爭對手模型和Claude 3 Opus,在廣泛的評估中表現出色,同時具有我們中等層級模型的速度和成本。"
},
+ "anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet 提升了行業標準,性能超越競爭對手模型和 Claude 3 Opus,在廣泛的評估中表現出色,同時具備我們中等層級模型的速度和成本。"
+ },
"anthropic.claude-3-haiku-20240307-v1:0": {
"description": "Claude 3 Haiku是Anthropic最快、最緊湊的模型,提供近乎即時的響應速度。它可以快速回答簡單的查詢和請求。客戶將能夠構建模仿人類互動的無縫AI體驗。Claude 3 Haiku可以處理圖像並返回文本輸出,具有200K的上下文窗口。"
},
@@ -209,15 +500,24 @@
"anthropic/claude-3-opus": {
"description": "Claude 3 Opus 是 Anthropic 用於處理高度複雜任務的最強大模型。它在性能、智能、流暢性和理解力方面表現卓越。"
},
+ "anthropic/claude-3.5-haiku": {
+ "description": "Claude 3.5 Haiku 是 Anthropic 最快的下一代模型。與 Claude 3 Haiku 相比,Claude 3.5 Haiku 在各項技能上都有所提升,並在許多智力基準測試中超越了上一代最大的模型 Claude 3 Opus。"
+ },
"anthropic/claude-3.5-sonnet": {
"description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度,同時保持與 Sonnet 相同的價格。Sonnet 特別擅長程式設計、數據科學、視覺處理、代理任務。"
},
+ "anthropic/claude-3.7-sonnet": {
+ "description": "Claude 3.7 Sonnet 是 Anthropic 迄今為止最智能的模型,也是市場上首個混合推理模型。Claude 3.7 Sonnet 可以產生近乎即時的回應或延長的逐步思考,使用者可以清晰地看到這些過程。Sonnet 特別擅長程式設計、數據科學、視覺處理、代理任務。"
+ },
"aya": {
"description": "Aya 23 是 Cohere 推出的多語言模型,支持 23 種語言,為多元化語言應用提供便利。"
},
"aya:35b": {
"description": "Aya 23 是 Cohere 推出的多語言模型,支持 23 種語言,為多元化語言應用提供便利。"
},
+ "baichuan/baichuan2-13b-chat": {
+ "description": "Baichuan-13B百川智能開發的包含130億參數的開源可商用的大規模語言模型,在權威的中文和英文benchmark上均取得同尺寸最好的效果。"
+ },
"charglm-3": {
"description": "CharGLM-3專為角色扮演與情感陪伴設計,支持超長多輪記憶與個性化對話,應用廣泛。"
},
@@ -230,9 +530,18 @@
"claude-2.1": {
"description": "Claude 2 為企業提供了關鍵能力的進步,包括業界領先的 200K token 上下文、大幅降低模型幻覺的發生率、系統提示以及一個新的測試功能:工具調用。"
},
+ "claude-3-5-haiku-20241022": {
+ "description": "Claude 3.5 Haiku 是 Anthropic 最快的下一代模型。與 Claude 3 Haiku 相比,Claude 3.5 Haiku 在各項技能上都有所提升,並在許多智力基準測試中超越了上一代最大的模型 Claude 3 Opus。"
+ },
"claude-3-5-sonnet-20240620": {
"description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度,同時保持與 Sonnet 相同的價格。Sonnet 特別擅長編程、數據科學、視覺處理、代理任務。"
},
+ "claude-3-5-sonnet-20241022": {
+ "description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度,同時保持與 Sonnet 相同的價格。Sonnet 特別擅長編程、數據科學、視覺處理、代理任務。"
+ },
+ "claude-3-7-sonnet-20250219": {
+ "description": "Claude 3.7 Sonnet 提升了行業標準,性能超越競爭對手模型和 Claude 3 Opus,在廣泛的評估中表現出色,同時具備我們中等層級模型的速度和成本。"
+ },
"claude-3-haiku-20240307": {
"description": "Claude 3 Haiku 是 Anthropic 的最快且最緊湊的模型,旨在實現近乎即時的響應。它具有快速且準確的定向性能。"
},
@@ -242,12 +551,12 @@
"claude-3-sonnet-20240229": {
"description": "Claude 3 Sonnet 在智能和速度方面為企業工作負載提供了理想的平衡。它以更低的價格提供最大效用,可靠且適合大規模部署。"
},
- "claude-instant-1.2": {
- "description": "Anthropic 的模型用於低延遲、高吞吐量的文本生成,支持生成數百頁的文本。"
- },
"codegeex-4": {
"description": "CodeGeeX-4是一個強大的AI編程助手,支持多種編程語言的智能問答與代碼補全,提升開發效率。"
},
+ "codegeex4-all-9b": {
+ "description": "CodeGeeX4-ALL-9B 是一個多語言代碼生成模型,支持包括代碼補全和生成、代碼解釋器、網絡搜索、函數調用、倉庫級代碼問答在內的全面功能,覆蓋軟件開發的各種場景。是參數少於 10B 的頂尖代碼生成模型。"
+ },
"codegemma": {
"description": "CodeGemma 專用于不同編程任務的輕量級語言模型,支持快速迭代和集成。"
},
@@ -257,6 +566,9 @@
"codellama": {
"description": "Code Llama 是一款專注於代碼生成和討論的 LLM,結合廣泛的編程語言支持,適用於開發者環境。"
},
+ "codellama/CodeLlama-34b-Instruct-hf": {
+ "description": "Code Llama 是一款專注於代碼生成和討論的 LLM,結合廣泛的編程語言支持,適用於開發者環境。"
+ },
"codellama:13b": {
"description": "Code Llama 是一款專注於代碼生成和討論的 LLM,結合廣泛的編程語言支持,適用於開發者環境。"
},
@@ -290,36 +602,186 @@
"command-r-plus": {
"description": "Command R+ 是一款高性能的大型語言模型,專為真實企業場景和複雜應用而設計。"
},
+ "dall-e-2": {
+ "description": "第二代 DALL·E 模型,支持更真實、準確的圖像生成,解析度是第一代的4倍"
+ },
+ "dall-e-3": {
+ "description": "最新的 DALL·E 模型,於2023年11月發布。支持更真實、準確的圖像生成,具有更強的細節表現力"
+ },
"databricks/dbrx-instruct": {
"description": "DBRX Instruct 提供高可靠性的指令處理能力,支持多行業應用。"
},
+ "deepseek-ai/DeepSeek-R1": {
+ "description": "DeepSeek-R1 是一款強化學習(RL)驅動的推理模型,解決了模型中的重複性和可讀性問題。在 RL 之前,DeepSeek-R1 引入了冷啟動數據,進一步優化了推理性能。它在數學、程式碼和推理任務中與 OpenAI-o1 表現相當,並且通過精心設計的訓練方法,提升了整體效果。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+ "description": "DeepSeek-R1 蒸餾模型,通過強化學習與冷啟動數據優化推理性能,開源模型刷新多任務標杆。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
+ "description": "DeepSeek-R1-Distill-Llama-8B 是基於 Llama-3.1-8B 開發的蒸餾模型。該模型使用 DeepSeek-R1 生成的樣本進行微調,展現出優秀的推理能力。在多個基準測試中表現不俗,其中在 MATH-500 上達到了 89.1% 的準確率,在 AIME 2024 上達到了 50.4% 的通過率,在 CodeForces 上獲得了 1205 的評分,作為 8B 規模的模型展示了較強的數學和編程能力。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+ "description": "DeepSeek-R1 蒸餾模型,通過強化學習與冷啟動數據優化推理性能,開源模型刷新多任務標杆。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+ "description": "DeepSeek-R1 蒸餾模型,通過強化學習與冷啟動數據優化推理性能,開源模型刷新多任務標杆。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
+ "description": "DeepSeek-R1-Distill-Qwen-32B 是基於 Qwen2.5-32B 通過知識蒸餾得到的模型。該模型使用 DeepSeek-R1 生成的 80 萬個精選樣本進行微調,在數學、編程和推理等多個領域展現出卓越的性能。在 AIME 2024、MATH-500、GPQA Diamond 等多個基準測試中都取得了優異成績,其中在 MATH-500 上達到了 94.3% 的準確率,展現出強大的數學推理能力。"
+ },
+ "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
+ "description": "DeepSeek-R1-Distill-Qwen-7B 是基於 Qwen2.5-Math-7B 通過知識蒸餾得到的模型。該模型使用 DeepSeek-R1 生成的 80 萬個精選樣本進行微調,展現出優秀的推理能力。在多個基準測試中表現出色,其中在 MATH-500 上達到了 92.8% 的準確率,在 AIME 2024 上達到了 55.5% 的通過率,在 CodeForces 上獲得了 1189 的評分,作為 7B 規模的模型展示了較強的數學和編程能力。"
+ },
"deepseek-ai/DeepSeek-V2.5": {
"description": "DeepSeek V2.5 集合了先前版本的優秀特徵,增強了通用和編碼能力。"
},
+ "deepseek-ai/DeepSeek-V3": {
+ "description": "DeepSeek-V3 是一款擁有 6710 億參數的混合專家(MoE)語言模型,採用多頭潛在注意力(MLA)和 DeepSeekMoE 架構,結合無輔助損失的負載平衡策略,優化推理和訓練效率。通過在 14.8 萬億高品質 tokens 上預訓練,並進行監督微調和強化學習,DeepSeek-V3 在性能上超越其他開源模型,接近領先閉源模型。"
+ },
"deepseek-ai/deepseek-llm-67b-chat": {
"description": "DeepSeek 67B 是為高複雜性對話訓練的先進模型。"
},
+ "deepseek-ai/deepseek-r1": {
+ "description": "最先進的高效 LLM,擅長推理、數學和編程。"
+ },
+ "deepseek-ai/deepseek-vl2": {
+ "description": "DeepSeek-VL2 是一個基於 DeepSeekMoE-27B 開發的混合專家(MoE)視覺語言模型,採用稀疏激活的 MoE 架構,在僅激活 4.5B 參數的情況下實現了卓越性能。該模型在視覺問答、光學字符識別、文檔/表格/圖表理解和視覺定位等多個任務中表現優異。"
+ },
"deepseek-chat": {
"description": "融合通用與代碼能力的全新開源模型,不僅保留了原有 Chat 模型的通用對話能力和 Coder 模型的強大代碼處理能力,還更好地對齊了人類偏好。此外,DeepSeek-V2.5 在寫作任務、指令跟隨等多個方面也實現了大幅提升。"
},
+ "deepseek-coder-33B-instruct": {
+ "description": "DeepSeek Coder 33B 是一個代碼語言模型,基於 2 萬億數據訓練而成,其中 87% 為代碼,13% 為中英文語言。模型引入 16K 窗口大小和填空任務,提供項目級別的代碼補全和片段填充功能。"
+ },
"deepseek-coder-v2": {
"description": "DeepSeek Coder V2 是開源的混合專家代碼模型,在代碼任務方面表現優異,與 GPT4-Turbo 相媲美。"
},
"deepseek-coder-v2:236b": {
"description": "DeepSeek Coder V2 是開源的混合專家代碼模型,在代碼任務方面表現優異,與 GPT4-Turbo 相媲美。"
},
+ "deepseek-r1": {
+ "description": "DeepSeek-R1 是一款強化學習(RL)驅動的推理模型,解決了模型中的重複性和可讀性問題。在 RL 之前,DeepSeek-R1 引入了冷啟動數據,進一步優化了推理性能。它在數學、程式碼和推理任務中與 OpenAI-o1 表現相當,並且通過精心設計的訓練方法,提升了整體效果。"
+ },
+ "deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1——DeepSeek 套件中更大更智能的模型——被蒸餾到 Llama 70B 架構中。基於基準測試和人工評估,該模型比原始 Llama 70B 更智能,尤其在需要數學和事實精確性的任務上表現出色。"
+ },
+ "deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek-R1-Distill 系列模型透過知識蒸餾技術,將 DeepSeek-R1 生成的樣本對 Qwen、Llama 等開源模型進行微調後得到。"
+ },
+ "deepseek-r1-distill-qwen-1.5b": {
+ "description": "DeepSeek-R1-Distill 系列模型透過知識蒸餾技術,將 DeepSeek-R1 生成的樣本對 Qwen、Llama 等開源模型進行微調後得到。"
+ },
+ "deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek-R1-Distill 系列模型透過知識蒸餾技術,將 DeepSeek-R1 生成的樣本對 Qwen、Llama 等開源模型進行微調後得到。"
+ },
+ "deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek-R1-Distill 系列模型透過知識蒸餾技術,將 DeepSeek-R1 生成的樣本對 Qwen、Llama 等開源模型進行微調後得到。"
+ },
+ "deepseek-r1-distill-qwen-7b": {
+ "description": "DeepSeek-R1-Distill 系列模型透過知識蒸餾技術,將 DeepSeek-R1 生成的樣本對 Qwen、Llama 等開源模型進行微調後得到。"
+ },
+ "deepseek-reasoner": {
+ "description": "DeepSeek 推出的推理模型。在輸出最終回答之前,模型會先輸出一段思維鏈內容,以提升最終答案的準確性。"
+ },
"deepseek-v2": {
"description": "DeepSeek V2 是高效的 Mixture-of-Experts 語言模型,適用於經濟高效的處理需求。"
},
"deepseek-v2:236b": {
"description": "DeepSeek V2 236B 是 DeepSeek 的設計代碼模型,提供強大的代碼生成能力。"
},
+ "deepseek-v3": {
+ "description": "DeepSeek-V3 為杭州深度求索人工智能基礎技術研究有限公司自研的 MoE 模型,其多項評測成績突出,在主流榜單中位列開源模型榜首。V3 相較 V2.5 模型生成速度實現 3 倍提升,為用戶帶來更加迅速流暢的使用體驗。"
+ },
"deepseek/deepseek-chat": {
"description": "融合通用與代碼能力的全新開源模型,不僅保留了原有 Chat 模型的通用對話能力和 Coder 模型的強大代碼處理能力,還更好地對齊了人類偏好。此外,DeepSeek-V2.5 在寫作任務、指令跟隨等多個方面也實現了大幅提升。"
},
+ "deepseek/deepseek-r1": {
+ "description": "DeepSeek-R1 在僅有極少標註數據的情況下,極大提升了模型推理能力。在輸出最終回答之前,模型會先輸出一段思維鏈內容,以提升最終答案的準確性。"
+ },
+ "deepseek/deepseek-r1-distill-llama-70b": {
+ "description": "DeepSeek R1 Distill Llama 70B是基於Llama3.3 70B的大型語言模型,該模型利用DeepSeek R1輸出的微調,實現了與大型前沿模型相當的競爭性能。"
+ },
+ "deepseek/deepseek-r1-distill-llama-8b": {
+ "description": "DeepSeek R1 Distill Llama 8B是一種基於Llama-3.1-8B-Instruct的蒸餾大語言模型,通過使用DeepSeek R1的輸出進行訓練而得。"
+ },
+ "deepseek/deepseek-r1-distill-qwen-14b": {
+ "description": "DeepSeek R1 Distill Qwen 14B是一種基於Qwen 2.5 14B的蒸餾大語言模型,通過使用DeepSeek R1的輸出進行訓練而得。該模型在多個基準測試中超越了OpenAI的o1-mini,取得了密集模型(dense models)的最新技術領先成果(state-of-the-art)。以下是一些基準測試的結果:\nAIME 2024 pass@1: 69.7\nMATH-500 pass@1: 93.9\nCodeForces Rating: 1481\n該模型通過從DeepSeek R1的輸出中進行微調,展現了與更大規模的前沿模型相當的競爭性能。"
+ },
+ "deepseek/deepseek-r1-distill-qwen-32b": {
+ "description": "DeepSeek R1 Distill Qwen 32B是一種基於Qwen 2.5 32B的蒸餾大語言模型,通過使用DeepSeek R1的輸出進行訓練而得。該模型在多個基準測試中超越了OpenAI的o1-mini,取得了密集模型(dense models)的最新技術領先成果(state-of-the-art)。以下是一些基準測試的結果:\nAIME 2024 pass@1: 72.6\nMATH-500 pass@1: 94.3\nCodeForces Rating: 1691\n該模型通過從DeepSeek R1的輸出中進行微調,展現了與更大規模的前沿模型相當的競爭性能。"
+ },
+ "deepseek/deepseek-r1/community": {
+ "description": "DeepSeek R1是DeepSeek團隊發布的最新開源模型,具備非常強悍的推理性能,尤其在數學、編程和推理任務上達到了與OpenAI的o1模型相當的水平。"
+ },
+ "deepseek/deepseek-r1:free": {
+ "description": "DeepSeek-R1 在僅有極少標註數據的情況下,極大提升了模型推理能力。在輸出最終回答之前,模型會先輸出一段思維鏈內容,以提升最終答案的準確性。"
+ },
+ "deepseek/deepseek-v3": {
+ "description": "DeepSeek-V3在推理速度方面實現了比之前模型的重大突破。在開源模型中排名第一,並可與全球最先進的閉源模型相媲美。DeepSeek-V3 采用了多頭潛在注意力(MLA)和DeepSeekMoE架構,這些架構在DeepSeek-V2中得到了全面驗證。此外,DeepSeek-V3開創了一種用於負載均衡的輔助無損策略,並設定了多標記預測訓練目標以獲得更強的性能。"
+ },
+ "deepseek/deepseek-v3/community": {
+ "description": "DeepSeek-V3在推理速度方面實現了比之前模型的重大突破。在開源模型中排名第一,並可與全球最先進的閉源模型相媲美。DeepSeek-V3 采用了多頭潛在注意力(MLA)和DeepSeekMoE架構,這些架構在DeepSeek-V2中得到了全面驗證。此外,DeepSeek-V3開創了一種用於負載均衡的輔助無損策略,並設定了多標記預測訓練目標以獲得更強的性能。"
+ },
+ "doubao-1.5-lite-32k": {
+ "description": "Doubao-1.5-lite 全新一代輕量版模型,極致響應速度,效果與時延均達到全球一流水平。"
+ },
+ "doubao-1.5-pro-256k": {
+ "description": "Doubao-1.5-pro-256k 基於 Doubao-1.5-Pro 全面升級版,整體效果大幅提升 10%。支持 256k 上下文窗口的推理,輸出長度支持最大 12k tokens。更高性能、更大窗口、超高性價比,適用於更廣泛的應用場景。"
+ },
+ "doubao-1.5-pro-32k": {
+ "description": "Doubao-1.5-pro 全新一代主力模型,性能全面升級,在知識、程式碼、推理等方面表現卓越。"
+ },
"emohaa": {
"description": "Emohaa是一個心理模型,具備專業諮詢能力,幫助用戶理解情感問題。"
},
+ "ernie-3.5-128k": {
+ "description": "百度自研的旗艦級大規模大語言模型,覆蓋海量中英文語料,具有強大的通用能力,可滿足絕大部分對話問答、創作生成、插件應用場景要求;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ernie-3.5-8k": {
+ "description": "百度自研的旗艦級大規模大語言模型,覆蓋海量中英文語料,具有強大的通用能力,可滿足絕大部分對話問答、創作生成、插件應用場景要求;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ernie-3.5-8k-preview": {
+ "description": "百度自研的旗艦級大規模大語言模型,覆蓋海量中英文語料,具有強大的通用能力,可滿足絕大部分對話問答、創作生成、插件應用場景要求;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ernie-4.0-8k-latest": {
+ "description": "百度自研的旗艦級超大規模大語言模型,相較ERNIE 3.5實現了模型能力全面升級,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ernie-4.0-8k-preview": {
+ "description": "百度自研的旗艦級超大規模大語言模型,相較ERNIE 3.5實現了模型能力全面升級,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。"
+ },
+ "ernie-4.0-turbo-128k": {
+ "description": "百度自研的旗艦級超大規模大語言模型,綜合效果表現出色,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。相較於ERNIE 4.0在性能表現上更優秀"
+ },
+ "ernie-4.0-turbo-8k-latest": {
+ "description": "百度自研的旗艦級超大規模大語言模型,綜合效果表現出色,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。相較於ERNIE 4.0在性能表現上更優秀"
+ },
+ "ernie-4.0-turbo-8k-preview": {
+ "description": "百度自研的旗艦級超大規模大語言模型,綜合效果表現出色,廣泛適用於各領域複雜任務場景;支持自動對接百度搜索插件,保障問答信息時效。相較於ERNIE 4.0在性能表現上更優秀"
+ },
+ "ernie-char-8k": {
+ "description": "百度自研的垂直場景大語言模型,適合遊戲NPC、客服對話、對話角色扮演等應用場景,人設風格更為鮮明、一致,指令遵循能力更強,推理性能更優。"
+ },
+ "ernie-char-fiction-8k": {
+ "description": "百度自研的垂直場景大語言模型,適合遊戲NPC、客服對話、對話角色扮演等應用場景,人設風格更為鮮明、一致,指令遵循能力更強,推理性能更優。"
+ },
+ "ernie-lite-8k": {
+ "description": "ERNIE Lite是百度自研的輕量級大語言模型,兼顧優異的模型效果與推理性能,適合低算力AI加速卡推理使用。"
+ },
+ "ernie-lite-pro-128k": {
+ "description": "百度自研的輕量級大語言模型,兼顧優異的模型效果與推理性能,效果比ERNIE Lite更優,適合低算力AI加速卡推理使用。"
+ },
+ "ernie-novel-8k": {
+ "description": "百度自研通用大語言模型,在小說續寫能力上有明顯優勢,也可用在短劇、電影等場景。"
+ },
+ "ernie-speed-128k": {
+ "description": "百度2024年最新發布的自研高性能大語言模型,通用能力優異,適合作為基座模型進行精調,更好地處理特定場景問題,同時具備極佳的推理性能。"
+ },
+ "ernie-speed-pro-128k": {
+ "description": "百度2024年最新發布的自研高性能大語言模型,通用能力優異,效果比ERNIE Speed更優,適合作為基座模型進行精調,更好地處理特定場景問題,同時具備極佳的推理性能。"
+ },
+ "ernie-tiny-8k": {
+ "description": "ERNIE Tiny是百度自研的超高性能大語言模型,部署與精調成本在文心系列模型中最低。"
+ },
"gemini-1.0-pro-001": {
"description": "Gemini 1.0 Pro 001 (Tuning) 提供穩定並可調優的性能,是複雜任務解決方案的理想選擇。"
},
@@ -329,14 +791,17 @@
"gemini-1.0-pro-latest": {
"description": "Gemini 1.0 Pro 是 Google 的高性能 AI 模型,專為廣泛任務擴展而設計。"
},
+ "gemini-1.5-flash": {
+ "description": "Gemini 1.5 Flash 是 Google 最新的多模態 AI 模型,具備快速處理能力,支持文本、圖像和視頻輸入,適用於多種任務的高效擴展。"
+ },
"gemini-1.5-flash-001": {
"description": "Gemini 1.5 Flash 001 是一款高效的多模態模型,支持廣泛應用的擴展。"
},
"gemini-1.5-flash-002": {
"description": "Gemini 1.5 Flash 002 是一款高效的多模態模型,支持廣泛應用的擴展。"
},
- "gemini-1.5-flash-8b-exp-0827": {
- "description": "Gemini 1.5 Flash 8B 0827 專為處理大規模任務場景設計,提供無與倫比的處理速度。"
+ "gemini-1.5-flash-8b": {
+ "description": "Gemini 1.5 Flash 8B 是一款高效的多模態模型,支持廣泛應用的擴展。"
},
"gemini-1.5-flash-8b-exp-0924": {
"description": "Gemini 1.5 Flash 8B 0924 是最新的實驗性模型,在文本和多模態用例中都有顯著的性能提升。"
@@ -362,6 +827,30 @@
"gemini-1.5-pro-latest": {
"description": "Gemini 1.5 Pro 支持高達 200 萬個 tokens,是中型多模態模型的理想選擇,適用於複雜任務的多方面支持。"
},
+ "gemini-2.0-flash": {
+ "description": "Gemini 2.0 Flash 提供下一代功能和改進,包括卓越的速度、原生工具使用、多模態生成和1M令牌上下文窗口。"
+ },
+ "gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash 提供下一代功能和改進,包括卓越的速度、原生工具使用、多模態生成和1M令牌上下文窗口。"
+ },
+ "gemini-2.0-flash-lite": {
+ "description": "Gemini 2.0 Flash 模型變體,針對成本效益和低延遲等目標進行了優化。"
+ },
+ "gemini-2.0-flash-lite-001": {
+ "description": "Gemini 2.0 Flash 模型變體,針對成本效益和低延遲等目標進行了優化。"
+ },
+ "gemini-2.0-flash-lite-preview-02-05": {
+ "description": "一個 Gemini 2.0 Flash 模型,針對成本效益和低延遲等目標進行了優化。"
+ },
+ "gemini-2.0-flash-thinking-exp": {
+ "description": "Gemini 2.0 Flash Exp 是 Google 最新的實驗性多模態AI模型,擁有下一代特性,卓越的速度,原生工具調用以及多模態生成。"
+ },
+ "gemini-2.0-flash-thinking-exp-01-21": {
+ "description": "Gemini 2.0 Flash Exp 是 Google 最新的實驗性多模態AI模型,擁有下一代特性,卓越的速度,原生工具調用以及多模態生成。"
+ },
+ "gemini-2.0-pro-exp-02-05": {
+ "description": "Gemini 2.0 Pro Experimental 是 Google 最新的實驗性多模態AI模型,與歷史版本相比有一定的質量提升,特別是對於世界知識、代碼和長上下文。"
+ },
"gemma-7b-it": {
"description": "Gemma 7B 適合中小規模任務處理,兼具成本效益。"
},
@@ -377,9 +866,6 @@
"gemma2:2b": {
"description": "Gemma 2 是 Google 推出的高效模型,涵蓋從小型應用到複雜數據處理的多種應用場景。"
},
- "general": {
- "description": "Spark Lite 是一款輕量級大語言模型,具備極低的延遲與高效的處理能力,完全免費開放,支持即時在線搜索功能。其快速響應的特性使其在低算力設備上的推理應用和模型微調中表現出色,為用戶帶來出色的成本效益和智能體驗,尤其在知識問答、內容生成及搜索場景下表現不俗。"
- },
"generalv3": {
"description": "Spark Pro 是一款為專業領域優化的高性能大語言模型,專注數學、編程、醫療、教育等多個領域,並支持聯網搜索及內置天氣、日期等插件。其優化後模型在複雜知識問答、語言理解及高層次文本創作中展現出色表現和高效性能,是適合專業應用場景的理想選擇。"
},
@@ -392,6 +878,9 @@
"glm-4-0520": {
"description": "GLM-4-0520是最新模型版本,專為高度複雜和多樣化任務設計,表現卓越。"
},
+ "glm-4-9b-chat": {
+ "description": "GLM-4-9B-Chat 在語義、數學、推理、代碼和知識等多方面均表現出較高性能。還具備網頁瀏覽、代碼執行、自定義工具調用和長文本推理。支持包括日語、韓語、德語在內的 26 種語言。"
+ },
"glm-4-air": {
"description": "GLM-4-Air是性價比高的版本,性能接近GLM-4,提供快速度和實惠的價格。"
},
@@ -404,6 +893,9 @@
"glm-4-flash": {
"description": "GLM-4-Flash是處理簡單任務的理想選擇,速度最快且價格最優惠。"
},
+ "glm-4-flashx": {
+ "description": "GLM-4-FlashX 是 Flash 的增強版本,具備超快的推理速度。"
+ },
"glm-4-long": {
"description": "GLM-4-Long支持超長文本輸入,適合記憶型任務與大規模文檔處理。"
},
@@ -413,18 +905,39 @@
"glm-4v": {
"description": "GLM-4V提供強大的圖像理解與推理能力,支持多種視覺任務。"
},
+ "glm-4v-flash": {
+ "description": "GLM-4V-Flash 專注於高效的單一圖像理解,適用於快速圖像解析的場景,例如即時圖像分析或批量圖像處理。"
+ },
"glm-4v-plus": {
"description": "GLM-4V-Plus具備對視頻內容及多圖片的理解能力,適合多模態任務。"
},
- "google/gemini-flash-1.5-exp": {
- "description": "Gemini 1.5 Flash 0827 提供了優化後的多模態處理能力,適用多種複雜任務場景。"
+ "glm-zero-preview": {
+ "description": "GLM-Zero-Preview具備強大的複雜推理能力,在邏輯推理、數學、程式設計等領域表現優異。"
},
- "google/gemini-pro-1.5-exp": {
- "description": "Gemini 1.5 Pro 0827 結合最新優化技術,帶來更高效的多模態數據處理能力。"
+ "google/gemini-2.0-flash-001": {
+ "description": "Gemini 2.0 Flash 提供下一代功能和改進,包括卓越的速度、原生工具使用、多模態生成和1M令牌上下文窗口。"
+ },
+ "google/gemini-2.0-pro-exp-02-05:free": {
+ "description": "Gemini 2.0 Pro Experimental 是 Google 最新的實驗性多模態AI模型,與歷史版本相比有一定的質量提升,特別是對於世界知識、代碼和長上下文。"
+ },
+ "google/gemini-flash-1.5": {
+ "description": "Gemini 1.5 Flash 提供了優化後的多模態處理能力,適用於多種複雜任務場景。"
+ },
+ "google/gemini-pro-1.5": {
+ "description": "Gemini 1.5 Pro 結合最新的優化技術,帶來更高效的多模態數據處理能力。"
+ },
+ "google/gemma-2-27b": {
+ "description": "Gemma 2 是 Google 推出的高效模型,涵蓋從小型應用到複雜數據處理的多種應用場景。"
},
"google/gemma-2-27b-it": {
"description": "Gemma 2 延續了輕量化與高效的設計理念。"
},
+ "google/gemma-2-2b-it": {
+ "description": "Google的輕量級指令調優模型"
+ },
+ "google/gemma-2-9b": {
+ "description": "Gemma 2 是 Google 推出的高效模型,涵蓋從小型應用到複雜數據處理的多種應用場景。"
+ },
"google/gemma-2-9b-it": {
"description": "Gemma 2 是 Google 輕量化的開源文本模型系列。"
},
@@ -446,6 +959,12 @@
"gpt-3.5-turbo-instruct": {
"description": "GPT 3.5 Turbo,適用於各種文本生成和理解任務,Currently points to gpt-3.5-turbo-0125"
},
+ "gpt-35-turbo": {
+ "description": "GPT 3.5 Turbo,OpenAI 提供的高效模型,適用於聊天和文本生成任務,支持並行函數調用。"
+ },
+ "gpt-35-turbo-16k": {
+ "description": "GPT 3.5 Turbo 16k,高容量文本生成模型,適合複雜任務。"
+ },
"gpt-4": {
"description": "GPT-4提供了一個更大的上下文窗口,能夠處理更長的文本輸入,適用於需要廣泛信息整合和數據分析的場景。"
},
@@ -458,9 +977,6 @@
"gpt-4-1106-preview": {
"description": "最新的GPT-4 Turbo模型具備視覺功能。現在,視覺請求可以使用JSON模式和函數調用。GPT-4 Turbo是一個增強版本,為多模態任務提供成本效益高的支持。它在準確性和效率之間找到平衡,適合需要進行實時交互的應用程序場景。"
},
- "gpt-4-1106-vision-preview": {
- "description": "最新的GPT-4 Turbo模型具備視覺功能。現在,視覺請求可以使用JSON模式和函數調用。GPT-4 Turbo是一個增強版本,為多模態任務提供成本效益高的支持。它在準確性和效率之間找到平衡,適合需要進行實時交互的應用程序場景。"
- },
"gpt-4-32k": {
"description": "GPT-4提供了一個更大的上下文窗口,能夠處理更長的文本輸入,適用於需要廣泛信息整合和數據分析的場景。"
},
@@ -479,6 +995,9 @@
"gpt-4-vision-preview": {
"description": "最新的GPT-4 Turbo模型具備視覺功能。現在,視覺請求可以使用JSON模式和函數調用。GPT-4 Turbo是一個增強版本,為多模態任務提供成本效益高的支持。它在準確性和效率之間找到平衡,適合需要進行實時交互的應用程序場景。"
},
+ "gpt-4.5-preview": {
+ "description": "GPT-4.5 的研究預覽版,它是我們迄今為止最大、最強大的 GPT 模型。它擁有廣泛的世界知識,並能更好地理解用戶意圖,使其在創造性任務和自主規劃方面表現出色。GPT-4.5 可接受文本和圖像輸入,並生成文本輸出(包括結構化輸出)。支持關鍵的開發者功能,如函數調用、批量 API 和串流輸出。在需要創造性、開放式思考和對話的任務(如寫作、學習或探索新想法)中,GPT-4.5 表現尤為出色。知識截止日期為 2023 年 10 月。"
+ },
"gpt-4o": {
"description": "ChatGPT-4o是一款動態模型,實時更新以保持當前最新版本。它結合了強大的語言理解與生成能力,適合於大規模應用場景,包括客戶服務、教育和技術支持。"
},
@@ -488,22 +1007,125 @@
"gpt-4o-2024-08-06": {
"description": "ChatGPT-4o是一款動態模型,實時更新以保持當前最新版本。它結合了強大的語言理解與生成能力,適合於大規模應用場景,包括客戶服務、教育和技術支持。"
},
+ "gpt-4o-2024-11-20": {
+ "description": "ChatGPT-4o 是一款動態模型,實時更新以保持當前最新版本。它結合了強大的語言理解與生成能力,適合於大規模應用場景,包括客戶服務、教育和技術支持。"
+ },
+ "gpt-4o-audio-preview": {
+ "description": "GPT-4o Audio 模型,支持音頻輸入輸出"
+ },
"gpt-4o-mini": {
"description": "GPT-4o mini是OpenAI在GPT-4 Omni之後推出的最新模型,支持圖文輸入並輸出文本。作為他們最先進的小型模型,它比其他近期的前沿模型便宜很多,並且比GPT-3.5 Turbo便宜超過60%。它保持了最先進的智能,同時具有顯著的性價比。GPT-4o mini在MMLU測試中獲得了82%的得分,目前在聊天偏好上排名高於GPT-4。"
},
+ "gpt-4o-mini-realtime-preview": {
+ "description": "GPT-4o-mini 實時版本,支持音頻和文本實時輸入輸出"
+ },
+ "gpt-4o-realtime-preview": {
+ "description": "GPT-4o 實時版本,支持音頻和文本實時輸入輸出"
+ },
+ "gpt-4o-realtime-preview-2024-10-01": {
+ "description": "GPT-4o 實時版本,支持音頻和文本實時輸入輸出"
+ },
+ "gpt-4o-realtime-preview-2024-12-17": {
+ "description": "GPT-4o 實時版本,支持音頻和文本實時輸入輸出"
+ },
+ "grok-2-1212": {
+ "description": "該模型在準確性、指令遵循和多語言能力方面有所改進。"
+ },
+ "grok-2-vision-1212": {
+ "description": "該模型在準確性、指令遵循和多語言能力方面有所改進。"
+ },
+ "grok-beta": {
+ "description": "擁有與 Grok 2 相當的性能,但具備更高的效率、速度和功能。"
+ },
+ "grok-vision-beta": {
+ "description": "最新的圖像理解模型,可以處理各種各樣的視覺信息,包括文檔、圖表、截圖和照片等。"
+ },
"gryphe/mythomax-l2-13b": {
"description": "MythoMax l2 13B 是一款合併了多個頂尖模型的創意與智能相結合的語言模型。"
},
+ "hunyuan-code": {
+ "description": "混元最新代碼生成模型,經過 200B 高質量代碼數據增訓基座模型,迭代半年高質量 SFT 數據訓練,上下文長窗口長度增大到 8K,五大語言代碼生成自動評測指標上位居前列;五大語言 10 項考量各方面綜合代碼任務人工高質量評測上,性能處於第一梯隊。"
+ },
+ "hunyuan-functioncall": {
+ "description": "混元最新 MOE 架構 FunctionCall 模型,經過高質量的 FunctionCall 數據訓練,上下文窗口達 32K,在多個維度的評測指標上處於領先。"
+ },
+ "hunyuan-large": {
+ "description": "Hunyuan-large 模型總參數量約 389B,激活參數量約 52B,是當前業界參數規模最大、效果最好的 Transformer 架構的開源 MoE 模型。"
+ },
+ "hunyuan-large-longcontext": {
+ "description": "擅長處理長文任務如文檔摘要和文檔問答等,同時也具備處理通用文本生成任務的能力。在長文本的分析和生成上表現優異,能有效應對複雜和詳盡的長文內容處理需求。"
+ },
+ "hunyuan-lite": {
+ "description": "升級為 MOE 結構,上下文窗口為 256k,在 NLP、代碼、數學、行業等多項評測集上領先眾多開源模型。"
+ },
+ "hunyuan-lite-vision": {
+ "description": "混元最新7B多模態模型,上下文窗口32K,支持中英文場景的多模態對話、圖像物體識別、文檔表格理解、多模態數學等,在多個維度上評測指標優於7B競品模型。"
+ },
+ "hunyuan-pro": {
+ "description": "萬億級參數規模 MOE-32K 長文模型。在各種 benchmark 上達到絕對領先的水平,具備複雜指令和推理能力,支持 functioncall,在多語言翻譯、金融法律醫療等領域應用重點優化。"
+ },
+ "hunyuan-role": {
+ "description": "混元最新版角色扮演模型,混元官方精調訓練推出的角色扮演模型,基於混元模型結合角色扮演場景數據集進行增訓,在角色扮演場景具有更好的基礎效果。"
+ },
+ "hunyuan-standard": {
+ "description": "採用更優的路由策略,同時緩解了負載均衡和專家趨同的問題。長文方面,大海撈針指標達到 99.9%。MOE-32K 性價比相對更高,在平衡效果和價格的同時,可實現對長文本輸入的處理。"
+ },
+ "hunyuan-standard-256K": {
+ "description": "採用更優的路由策略,同時緩解了負載均衡和專家趨同的問題。長文方面,大海撈針指標達到 99.9%。MOE-256K 在長度和效果上進一步突破,極大地擴展了可輸入長度。"
+ },
+ "hunyuan-standard-vision": {
+ "description": "混元最新多模態模型,支持多語種作答,中英文能力均衡。"
+ },
+ "hunyuan-translation": {
+ "description": "支持中文和英語、日語、法語、葡萄牙語、西班牙語、土耳其語、俄語、阿拉伯語、韓語、義大利語、德語、越南語、馬來語、印尼語15種語言互譯,基於多場景翻譯評測集自動化評估COMET評分,在十餘種常用語種中外互譯能力上整體優於市場同規模模型。"
+ },
+ "hunyuan-translation-lite": {
+ "description": "混元翻譯模型支持自然語言對話式翻譯;支持中文和英語、日語、法語、葡萄牙語、西班牙語、土耳其語、俄語、阿拉伯語、韓語、義大利語、德語、越南語、馬來語、印尼語15種語言互譯。"
+ },
+ "hunyuan-turbo": {
+ "description": "混元全新一代大語言模型的預覽版,採用全新的混合專家模型(MoE)結構,相較於 hunyuan-pro 推理效率更快,效果表現更強。"
+ },
+ "hunyuan-turbo-20241120": {
+ "description": "hunyuan-turbo 2024 年 11 月 20 日固定版本,介於 hunyuan-turbo 和 hunyuan-turbo-latest 之間的一個版本。"
+ },
+ "hunyuan-turbo-20241223": {
+ "description": "本版本優化:數據指令scaling,大幅提升模型通用泛化能力;大幅提升數學、程式碼、邏輯推理能力;優化文本理解字詞理解相關能力;優化文本創作內容生成質量"
+ },
+ "hunyuan-turbo-latest": {
+ "description": "通用體驗優化,包括NLP理解、文本創作、閒聊、知識問答、翻譯、領域等;提升擬人性,優化模型情商;提升意圖模糊時模型主動澄清能力;提升字詞解析類問題的處理能力;提升創作的質量和可互動性;提升多輪體驗。"
+ },
+ "hunyuan-turbo-vision": {
+ "description": "混元新一代視覺語言旗艦大模型,採用全新的混合專家模型(MoE)結構,在圖文理解相關的基礎識別、內容創作、知識問答、分析推理等能力上相比前一代模型全面提升。"
+ },
+ "hunyuan-vision": {
+ "description": "混元最新多模態模型,支持圖片 + 文本輸入生成文本內容。"
+ },
"internlm/internlm2_5-20b-chat": {
"description": "創新的開源模型InternLM2.5,通過大規模的參數提高了對話智能。"
},
"internlm/internlm2_5-7b-chat": {
"description": "InternLM2.5 提供多場景下的智能對話解決方案。"
},
- "jamba-1.5-large": {},
- "jamba-1.5-mini": {},
- "llama-3.1-70b-instruct": {
- "description": "Llama 3.1 70B Instruct 模型,具備 70B 參數,能在大型文本生成和指示任務中提供卓越性能。"
+ "internlm2-pro-chat": {
+ "description": "我們仍在維護的舊版本模型,有 7B、20B 多種模型參數量可選。"
+ },
+ "internlm2.5-latest": {
+ "description": "我們最新的模型系列,有著卓越的推理性能,支持 1M 的上下文長度以及更強的指令跟隨和工具調用能力。"
+ },
+ "internlm3-latest": {
+ "description": "我們最新的模型系列,有著卓越的推理性能,領跑同量級開源模型。默認指向我們最新發布的 InternLM3 系列模型"
+ },
+ "jina-deepsearch-v1": {
+ "description": "深度搜索結合了網路搜索、閱讀和推理,可進行全面調查。您可以將其視為一個代理,接受您的研究任務 - 它會進行廣泛搜索並經過多次迭代,然後才能給出答案。這個過程涉及持續的研究、推理和從各個角度解決問題。這與直接從預訓練數據生成答案的標準大模型以及依賴一次性表面搜索的傳統 RAG 系統有著根本的不同。"
+ },
+ "kimi-latest": {
+ "description": "Kimi 智能助手產品使用最新的 Kimi 大模型,可能包含尚未穩定的特性。支持圖片理解,同時會自動根據請求的上下文長度選擇 8k/32k/128k 模型作為計費模型"
+ },
+ "learnlm-1.5-pro-experimental": {
+ "description": "LearnLM 是一個實驗性的、特定於任務的語言模型,經過訓練以符合學習科學原則,可在教學和學習場景中遵循系統指令,充當專家導師等。"
+ },
+ "lite": {
+ "description": "Spark Lite 是一款輕量級大語言模型,具備極低的延遲與高效的處理能力,完全免費開放,支持即時在線搜索功能。其快速響應的特性使其在低算力設備上的推理應用和模型微調中表現出色,為用戶帶來出色的成本效益和智能體驗,尤其在知識問答、內容生成及搜索場景下表現不俗。"
},
"llama-3.1-70b-versatile": {
"description": "Llama 3.1 70B 提供更強大的 AI 推理能力,適合複雜應用,支持超多的計算處理並保證高效和準確率。"
@@ -511,23 +1133,23 @@
"llama-3.1-8b-instant": {
"description": "Llama 3.1 8B 是一款高效能模型,提供了快速的文本生成能力,非常適合需要大規模效率和成本效益的應用場景。"
},
- "llama-3.1-8b-instruct": {
- "description": "Llama 3.1 8B Instruct 模型,具備 8B 參數,支持畫面指示任務的高效執行,提供優質的文本生成能力。"
+ "llama-3.2-11b-vision-instruct": {
+ "description": "在高解析度圖像上表現優異的圖像推理能力,適用於視覺理解應用。"
},
- "llama-3.1-sonar-huge-128k-online": {
- "description": "Llama 3.1 Sonar Huge Online 模型,具備 405B 參數,支持約 127,000 個標記的上下文長度,設計用於複雜的在線聊天應用。"
+ "llama-3.2-11b-vision-preview": {
+ "description": "Llama 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
},
- "llama-3.1-sonar-large-128k-chat": {
- "description": "Llama 3.1 Sonar Large Chat 模型,具備 70B 參數,支持約 127,000 個標記的上下文長度,適合於複雜的離線聊天任務。"
+ "llama-3.2-90b-vision-instruct": {
+ "description": "適合視覺理解代理應用的高階圖像推理能力。"
},
- "llama-3.1-sonar-large-128k-online": {
- "description": "Llama 3.1 Sonar Large Online 模型,具備 70B 參數,支持約 127,000 個標記的上下文長度,適用於高容量和多樣化聊天任務。"
+ "llama-3.2-90b-vision-preview": {
+ "description": "Llama 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
},
- "llama-3.1-sonar-small-128k-chat": {
- "description": "Llama 3.1 Sonar Small Chat 模型,具備 8B 參數,專為離線聊天設計,支持約 127,000 個標記的上下文長度。"
+ "llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先進的多語言開源大型語言模型,以極低成本體驗媲美 405B 模型的性能。基於 Transformer 結構,並透過監督微調(SFT)和人類反饋強化學習(RLHF)提升有用性和安全性。其指令調優版本專為多語言對話優化,在多項行業基準上表現優於眾多開源和封閉聊天模型。知識截止日期為 2023 年 12 月"
},
- "llama-3.1-sonar-small-128k-online": {
- "description": "Llama 3.1 Sonar Small Online 模型,具備 8B 參數,支持約 127,000 個標記的上下文長度,專為在線聊天設計,能高效處理各種文本交互。"
+ "llama-3.3-70b-versatile": {
+ "description": "Meta Llama 3.3 多語言大語言模型 (LLM) 是 70B(文本輸入/文本輸出)中的預訓練和指令調整生成模型。Llama 3.3 指令調整的純文本模型針對多語言對話用例進行了優化,並且在常見行業基準上優於許多可用的開源和封閉式聊天模型。"
},
"llama3-70b-8192": {
"description": "Meta Llama 3 70B 提供無與倫比的複雜性處理能力,為高要求項目量身定制。"
@@ -565,6 +1187,9 @@
"mathstral": {
"description": "MathΣtral 專為科學研究和數學推理設計,提供有效的計算能力和結果解釋。"
},
+ "max-32k": {
+ "description": "Spark Max 32K 配置了大上下文處理能力,更強的上下文理解和邏輯推理能力,支持32K tokens的文本輸入,適用於長文檔閱讀、私有知識問答等場景。"
+ },
"meta-llama-3-70b-instruct": {
"description": "一個強大的70億參數模型,在推理、編碼和廣泛的語言應用中表現出色。"
},
@@ -583,12 +1208,33 @@
"meta-llama/Llama-2-13b-chat-hf": {
"description": "LLaMA-2 Chat (13B) 提供優秀的語言處理能力和出色的互動體驗。"
},
+ "meta-llama/Llama-2-70b-hf": {
+ "description": "LLaMA-2 提供優秀的語言處理能力和出色的互動體驗。"
+ },
"meta-llama/Llama-3-70b-chat-hf": {
"description": "LLaMA-3 Chat (70B) 是功能強大的聊天模型,支持複雜的對話需求。"
},
"meta-llama/Llama-3-8b-chat-hf": {
"description": "LLaMA-3 Chat (8B) 提供多語言支持,涵蓋豐富的領域知識。"
},
+ "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
+ },
+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": {
+ "description": "LLaMA 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
+ },
+ "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": {
+ "description": "LLaMA 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
+ },
+ "meta-llama/Llama-3.3-70B-Instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先進的多語言開源大型語言模型,以極低成本體驗媲美 405B 模型的性能。基於 Transformer 結構,並通過監督微調(SFT)和人類反饋強化學習(RLHF)提升有用性和安全性。其指令調優版本專為多語言對話優化,在多項行業基準上表現優於眾多開源和封閉聊天模型。知識截止日期為 2023 年 12 月"
+ },
+ "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+ "description": "Meta Llama 3.3 多語言大語言模型 ( LLM ) 是 70B(文本輸入/文本輸出)中的預訓練和指令調整生成模型。 Llama 3.3 指令調整的純文本模型針對多語言對話用例進行了優化,並且在常見行業基準上優於許多可用的開源和封閉式聊天模型。"
+ },
+ "meta-llama/Llama-Vision-Free": {
+ "description": "LLaMA 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
+ },
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
"description": "Llama 3 70B Instruct Lite 適合需要高效能和低延遲的環境。"
},
@@ -607,6 +1253,9 @@
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"description": "405B 的 Llama 3.1 Turbo 模型,為大數據處理提供超大容量的上下文支持,在超大規模的人工智慧應用中表現突出。"
},
+ "meta-llama/Meta-Llama-3.1-70B": {
+ "description": "Llama 3.1 是 Meta 推出的領先模型,支持高達 405B 參數,可應用於複雜對話、多語言翻譯和數據分析領域。"
+ },
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
"description": "LLaMA 3.1 70B 提供多語言的高效對話支持。"
},
@@ -625,9 +1274,6 @@
"meta-llama/llama-3-8b-instruct": {
"description": "Llama 3 8B Instruct 優化了高品質對話場景,性能優於許多閉源模型。"
},
- "meta-llama/llama-3.1-405b-instruct": {
- "description": "Llama 3.1 405B Instruct 是 Meta 最新推出的版本,優化用於生成高品質對話,超越了許多領先的閉源模型。"
- },
"meta-llama/llama-3.1-70b-instruct": {
"description": "Llama 3.1 70B Instruct 專為高品質對話而設計,在人類評估中表現突出,特別適合高互動場景。"
},
@@ -637,6 +1283,21 @@
"meta-llama/llama-3.1-8b-instruct:free": {
"description": "LLaMA 3.1 提供多語言支持,是業界領先的生成模型之一。"
},
+ "meta-llama/llama-3.2-11b-vision-instruct": {
+ "description": "LLaMA 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
+ },
+ "meta-llama/llama-3.2-3b-instruct": {
+ "description": "meta-llama/llama-3.2-3b-instruct"
+ },
+ "meta-llama/llama-3.2-90b-vision-instruct": {
+ "description": "LLaMA 3.2 旨在處理結合視覺和文本數據的任務。它在圖像描述和視覺問答等任務中表現出色,跨越了語言生成和視覺推理之間的鴻溝。"
+ },
+ "meta-llama/llama-3.3-70b-instruct": {
+ "description": "Llama 3.3 是 Llama 系列最先進的多語言開源大型語言模型,以極低成本體驗媲美 405B 模型的性能。基於 Transformer 結構,並透過監督微調(SFT)和人類反饋強化學習(RLHF)提升有用性和安全性。其指令調優版本專為多語言對話優化,在多項行業基準上表現優於眾多開源和封閉聊天模型。知識截止日期為 2023 年 12 月"
+ },
+ "meta-llama/llama-3.3-70b-instruct:free": {
+ "description": "Llama 3.3 是 Llama 系列最先進的多語言開源大型語言模型,以極低成本體驗媲美 405B 模型的性能。基於 Transformer 結構,並透過監督微調(SFT)和人類反饋強化學習(RLHF)提升有用性和安全性。其指令調優版本專為多語言對話優化,在多項行業基準上表現優於眾多開源和封閉聊天模型。知識截止日期為 2023 年 12 月"
+ },
"meta.llama3-1-405b-instruct-v1:0": {
"description": "Meta Llama 3.1 405B Instruct 是 Llama 3.1 Instruct 模型中最大、最強大的模型,是一款高度先進的對話推理和合成數據生成模型,也可以用作在特定領域進行專業持續預訓練或微調的基礎。Llama 3.1 提供的多語言大型語言模型 (LLMs) 是一組預訓練的、指令調整的生成模型,包括 8B、70B 和 405B 大小 (文本輸入/輸出)。Llama 3.1 指令調整的文本模型 (8B、70B、405B) 專為多語言對話用例進行了優化,並在常見的行業基準測試中超過了許多可用的開源聊天模型。Llama 3.1 旨在用於多種語言的商業和研究用途。指令調整的文本模型適用於類似助手的聊天,而預訓練模型可以適應各種自然語言生成任務。Llama 3.1 模型還支持利用其模型的輸出來改進其他模型,包括合成數據生成和精煉。Llama 3.1 是使用優化的變壓器架構的自回歸語言模型。調整版本使用監督微調 (SFT) 和帶有人類反饋的強化學習 (RLHF) 來符合人類對幫助性和安全性的偏好。"
},
@@ -652,8 +1313,32 @@
"meta.llama3-8b-instruct-v1:0": {
"description": "Meta Llama 3 是一款面向開發者、研究人員和企業的開放大型語言模型 (LLM),旨在幫助他們構建、實驗並負責任地擴展他們的生成 AI 想法。作為全球社區創新的基礎系統的一部分,它非常適合計算能力和資源有限、邊緣設備和更快的訓練時間。"
},
- "microsoft/wizardlm 2-7b": {
- "description": "WizardLM 2 7B 是微軟AI最新的快速輕量化模型,性能接近於現有開源領導模型的10倍。"
+ "meta/llama-3.1-405b-instruct": {
+ "description": "高級 LLM,支持合成數據生成、知識蒸餾和推理,適用於聊天機器人、編程和特定領域任務。"
+ },
+ "meta/llama-3.1-70b-instruct": {
+ "description": "賦能複雜對話,具備卓越的上下文理解、推理能力和文本生成能力。"
+ },
+ "meta/llama-3.1-8b-instruct": {
+ "description": "先進的最尖端模型,具備語言理解、卓越的推理能力和文本生成能力。"
+ },
+ "meta/llama-3.2-11b-vision-instruct": {
+ "description": "尖端的視覺-語言模型,擅長從圖像中進行高品質推理。"
+ },
+ "meta/llama-3.2-1b-instruct": {
+ "description": "先進的最尖端小型語言模型,具備語言理解、卓越的推理能力和文本生成能力。"
+ },
+ "meta/llama-3.2-3b-instruct": {
+ "description": "先進的最尖端小型語言模型,具備語言理解、卓越的推理能力和文本生成能力。"
+ },
+ "meta/llama-3.2-90b-vision-instruct": {
+ "description": "尖端的視覺-語言模型,擅長從圖像中進行高品質推理。"
+ },
+ "meta/llama-3.3-70b-instruct": {
+ "description": "先進的 LLM,擅長推理、數學、常識和函數調用。"
+ },
+ "microsoft/WizardLM-2-8x22B": {
+ "description": "WizardLM 2 是微軟AI提供的語言模型,在複雜對話、多語言、推理和智能助手領域表現尤為出色。"
},
"microsoft/wizardlm-2-8x22b": {
"description": "WizardLM-2 8x22B 是微軟 AI 最先進的 Wizard 模型,顯示出極其競爭力的表現。"
@@ -661,15 +1346,18 @@
"minicpm-v": {
"description": "MiniCPM-V 是 OpenBMB 推出的新一代多模態大模型,具備卓越的 OCR 識別和多模態理解能力,支持廣泛的應用場景。"
},
+ "ministral-3b-latest": {
+ "description": "Ministral 3B 是 Mistral 的全球頂尖邊緣模型。"
+ },
+ "ministral-8b-latest": {
+ "description": "Ministral 8B 是 Mistral 的性價比極高的邊緣模型。"
+ },
"mistral": {
"description": "Mistral 是 Mistral AI 發布的 7B 模型,適合多變的語言處理需求。"
},
"mistral-large": {
"description": "Mixtral Large 是 Mistral 的旗艦模型,結合代碼生成、數學和推理的能力,支持 128k 上下文窗口。"
},
- "mistral-large-2407": {
- "description": "Mistral Large (2407)是一個先進的大型語言模型(LLM),具有最先進的推理、知識和編碼能力。"
- },
"mistral-large-latest": {
"description": "Mistral Large 是旗艦大模型,擅長多語言任務、複雜推理和代碼生成,是高端應用的理想選擇。"
},
@@ -691,12 +1379,18 @@
"mistralai/Mistral-7B-Instruct-v0.3": {
"description": "Mistral (7B) Instruct v0.3 提供高效的計算能力和自然語言理解,適合廣泛的應用。"
},
+ "mistralai/Mistral-7B-v0.1": {
+ "description": "Mistral 7B 是一款緊湊但高效能的模型,擅長批次處理和簡單任務,如分類和文本生成,具有良好的推理能力。"
+ },
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"description": "Mixtral-8x22B Instruct (141B) 是一款超級大語言模型,支持極高的處理需求。"
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"description": "Mixtral 8x7B 是預訓練的稀疏混合專家模型,用於通用性文本任務。"
},
+ "mistralai/Mixtral-8x7B-v0.1": {
+ "description": "Mixtral 8x7B 是一個稀疏專家模型,利用多個參數提高推理速度,適合處理多語言和代碼生成任務。"
+ },
"mistralai/mistral-7b-instruct": {
"description": "Mistral 7B Instruct 是一款兼具速度優化和長上下文支持的高性能行業標準模型。"
},
@@ -715,21 +1409,48 @@
"moonshot-v1-128k": {
"description": "Moonshot V1 128K 是一款擁有超長上下文處理能力的模型,適用於生成超長文本,滿足複雜的生成任務需求,能夠處理多達 128,000 個 tokens 的內容,非常適合科研、學術和大型文檔生成等應用場景。"
},
+ "moonshot-v1-128k-vision-preview": {
+ "description": "Kimi 視覺模型(包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 等)能夠理解圖片內容,包括圖片文字、圖片顏色和物體形狀等內容。"
+ },
"moonshot-v1-32k": {
"description": "Moonshot V1 32K 提供中等長度的上下文處理能力,能夠處理 32,768 個 tokens,特別適合生成各種長文檔和複雜對話,應用於內容創作、報告生成和對話系統等領域。"
},
+ "moonshot-v1-32k-vision-preview": {
+ "description": "Kimi 視覺模型(包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 等)能夠理解圖片內容,包括圖片文字、圖片顏色和物體形狀等內容。"
+ },
"moonshot-v1-8k": {
"description": "Moonshot V1 8K 專為生成短文本任務設計,具有高效的處理性能,能夠處理 8,192 個 tokens,非常適合簡短對話、速記和快速內容生成。"
},
+ "moonshot-v1-8k-vision-preview": {
+ "description": "Kimi 視覺模型(包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview 等)能夠理解圖片內容,包括圖片文字、圖片顏色和物體形狀等內容。"
+ },
+ "moonshot-v1-auto": {
+ "description": "Moonshot V1 Auto 可以根據當前上下文佔用的 Tokens 數量來選擇合適的模型"
+ },
"nousresearch/hermes-2-pro-llama-3-8b": {
"description": "Hermes 2 Pro Llama 3 8B 是 Nous Hermes 2 的升級版本,包含最新的內部開發的數據集。"
},
+ "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+ "description": "Llama 3.1 Nemotron 70B 是由 NVIDIA 定制的大型語言模型,旨在提高 LLM 生成的回應對用戶查詢的幫助程度。該模型在 Arena Hard、AlpacaEval 2 LC 和 GPT-4-Turbo MT-Bench 等基準測試中表現出色,截至 2024 年 10 月 1 日,在所有三個自動對齊基準測試中排名第一。該模型使用 RLHF(特別是 REINFORCE)、Llama-3.1-Nemotron-70B-Reward 和 HelpSteer2-Preference 提示在 Llama-3.1-70B-Instruct 模型基礎上進行訓練"
+ },
+ "nvidia/llama-3.1-nemotron-51b-instruct": {
+ "description": "獨特的語言模型,提供無與倫比的準確性和效率表現。"
+ },
+ "nvidia/llama-3.1-nemotron-70b-instruct": {
+ "description": "Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 定制的大型語言模型,旨在提高 LLM 生成的響應的幫助性。"
+ },
+ "o1": {
+ "description": "專注於高級推理和解決複雜問題,包括數學和科學任務。非常適合需要深入上下文理解和代理工作流程的應用程序。"
+ },
"o1-mini": {
"description": "o1-mini是一款針對程式設計、數學和科學應用場景而設計的快速、經濟高效的推理模型。該模型具有128K上下文和2023年10月的知識截止日期。"
},
"o1-preview": {
"description": "o1是OpenAI新的推理模型,適用於需要廣泛通用知識的複雜任務。該模型具有128K上下文和2023年10月的知識截止日期。"
},
+ "o3-mini": {
+ "description": "o3-mini 是我們最新的小型推理模型,在與 o1-mini 相同的成本和延遲目標下提供高智能。"
+ },
"open-codestral-mamba": {
"description": "Codestral Mamba 是專注於代碼生成的 Mamba 2 語言模型,為先進的代碼和推理任務提供強力支持。"
},
@@ -745,7 +1466,7 @@
"open-mixtral-8x7b": {
"description": "Mixtral 8x7B 是一個稀疏專家模型,利用多個參數提高推理速度,適合處理多語言和代碼生成任務。"
},
- "openai/gpt-4o-2024-08-06": {
+ "openai/gpt-4o": {
"description": "ChatGPT-4o 是一款動態模型,實時更新以保持當前最新版本。它結合了強大的語言理解與生成能力,適合於大規模應用場景,包括客戶服務、教育和技術支持。"
},
"openai/gpt-4o-mini": {
@@ -772,6 +1493,18 @@
"pixtral-12b-2409": {
"description": "Pixtral模型在圖表和圖理解、文檔問答、多模態推理和指令遵循等任務上表現出強大的能力,能夠以自然分辨率和寬高比攝入圖像,還能夠在長達128K令牌的長上下文窗口中處理任意數量的圖像。"
},
+ "pixtral-large-latest": {
+ "description": "Pixtral Large 是一款擁有 1240 億參數的開源多模態模型,基於 Mistral Large 2 構建。這是我們多模態家族中的第二款模型,展現了前沿水平的圖像理解能力。"
+ },
+ "pro-128k": {
+ "description": "Spark Pro 128K 配置了特大上下文處理能力,能夠處理多達128K的上下文信息,特別適合需通篇分析和長期邏輯關聯處理的長文內容,可在複雜文本溝通中提供流暢一致的邏輯與多樣的引用支持。"
+ },
+ "qvq-72b-preview": {
+ "description": "QVQ模型是由 Qwen 團隊開發的實驗性研究模型,專注於提升視覺推理能力,尤其在數學推理領域。"
+ },
+ "qwen-coder-plus-latest": {
+ "description": "通義千問代碼模型。"
+ },
"qwen-coder-turbo-latest": {
"description": "通義千問代碼模型。"
},
@@ -784,36 +1517,78 @@
"qwen-math-turbo-latest": {
"description": "通義千問數學模型是專門用於數學解題的語言模型。"
},
+ "qwen-max": {
+ "description": "通義千問千億級別超大規模語言模型,支持中文、英文等不同語言輸入,當前通義千問 2.5 產品版本背後的 API 模型。"
+ },
"qwen-max-latest": {
"description": "通義千問千億級別超大規模語言模型,支持中文、英文等不同語言輸入,當前通義千問2.5產品版本背後的API模型。"
},
+ "qwen-omni-turbo-latest": {
+ "description": "Qwen-Omni 系列模型支持輸入多種模態的數據,包括視頻、音頻、圖片、文本,並輸出音頻與文本。"
+ },
+ "qwen-plus": {
+ "description": "通義千問超大規模語言模型增強版,支持中文、英文等不同語言輸入。"
+ },
"qwen-plus-latest": {
"description": "通義千問超大規模語言模型增強版,支持中文、英文等不同語言輸入。"
},
+ "qwen-turbo": {
+ "description": "通義千問超大規模語言模型,支持中文、英文等不同語言輸入。"
+ },
"qwen-turbo-latest": {
"description": "通義千問超大規模語言模型,支持中文、英文等不同語言輸入。"
},
"qwen-vl-chat-v1": {
"description": "通義千問VL支持靈活的交互方式,包括多圖、多輪問答、創作等能力的模型。"
},
- "qwen-vl-max": {
+ "qwen-vl-max-latest": {
"description": "通義千問超大規模視覺語言模型。相比增強版,再次提升視覺推理能力和指令遵循能力,提供更高的視覺感知和認知水平。"
},
- "qwen-vl-plus": {
- "description": "通義千問大規模視覺語言模型增強版。大幅提升細節識別能力和文字識別能力,支持超百萬像素分辨率和任意長寬比規格的圖像。"
+ "qwen-vl-ocr-latest": {
+ "description": "通義千問OCR是文字提取專有模型,專注於文檔、表格、試題、手寫體文字等類型圖像的文字提取能力。它能夠識別多種文字,目前支持的語言有:漢語、英語、法語、日語、韓語、德語、俄語、意大利語、越南語、阿拉伯語。"
+ },
+ "qwen-vl-plus-latest": {
+ "description": "通義千問大規模視覺語言模型增強版。大幅提升細節識別能力和文字識別能力,支持超百萬像素解析度和任意長寬比規格的圖像。"
},
"qwen-vl-v1": {
"description": "以Qwen-7B語言模型初始化,添加圖像模型,圖像輸入分辨率為448的預訓練模型。"
},
+ "qwen/qwen-2-7b-instruct": {
+ "description": "Qwen2是全新的Qwen大型語言模型系列。Qwen2 7B是一個基於transformer的模型,在語言理解、多語言能力、編程、數學和推理方面表現出色。"
+ },
"qwen/qwen-2-7b-instruct:free": {
"description": "Qwen2 是全新的大型語言模型系列,具有更強的理解和生成能力。"
},
+ "qwen/qwen-2-vl-72b-instruct": {
+ "description": "Qwen2-VL是Qwen-VL模型的最新迭代版本,在視覺理解基準測試中達到了最先進的性能,包括MathVista、DocVQA、RealWorldQA和MTVQA等。Qwen2-VL能夠理解超過20分鐘的視頻,用於高質量的基於視頻的問答、對話和內容創作。它還具備複雜推理和決策能力,可以與移動設備、機器人等集成,基於視覺環境和文本指令進行自動操作。除了英語和中文,Qwen2-VL現在還支持理解圖像中不同語言的文本,包括大多數歐洲語言、日語、韓語、阿拉伯語和越南語等。"
+ },
+ "qwen/qwen-2.5-72b-instruct": {
+ "description": "Qwen2.5-72B-Instruct是阿里雲發布的最新大語言模型系列之一。該72B模型在編碼和數學等領域具有顯著改進的能力。該模型還提供了多語言支持,覆蓋超過29種語言,包括中文、英文等。模型在指令跟隨、理解結構化數據以及生成結構化輸出(尤其是JSON)方面都有顯著提升。"
+ },
+ "qwen/qwen2.5-32b-instruct": {
+ "description": "Qwen2.5-32B-Instruct是阿里雲發布的最新大語言模型系列之一。該32B模型在編碼和數學等領域具有顯著改進的能力。該模型提供了多語言支持,覆蓋超過29種語言,包括中文、英文等。模型在指令跟隨、理解結構化數據以及生成結構化輸出(尤其是JSON)方面都有顯著提升。"
+ },
+ "qwen/qwen2.5-7b-instruct": {
+ "description": "面向中文和英文的 LLM,針對語言、編程、數學、推理等領域。"
+ },
+ "qwen/qwen2.5-coder-32b-instruct": {
+ "description": "高級 LLM,支持代碼生成、推理和修復,涵蓋主流編程語言。"
+ },
+ "qwen/qwen2.5-coder-7b-instruct": {
+ "description": "強大的中型代碼模型,支持 32K 上下文長度,擅長多語言編程。"
+ },
"qwen2": {
"description": "Qwen2 是阿里巴巴的新一代大規模語言模型,以優異的性能支持多元化的應用需求。"
},
+ "qwen2.5": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大規模語言模型,以優異的性能支持多元化的應用需求。"
+ },
"qwen2.5-14b-instruct": {
"description": "通義千問2.5對外開源的14B規模的模型。"
},
+ "qwen2.5-14b-instruct-1m": {
+ "description": "通義千問2.5對外開源的72B規模的模型。"
+ },
"qwen2.5-32b-instruct": {
"description": "通義千問2.5對外開源的32B規模的模型。"
},
@@ -826,11 +1601,14 @@
"qwen2.5-coder-1.5b-instruct": {
"description": "通義千問代碼模型開源版。"
},
+ "qwen2.5-coder-32b-instruct": {
+ "description": "通義千問代碼模型開源版。"
+ },
"qwen2.5-coder-7b-instruct": {
"description": "通義千問代碼模型開源版。"
},
"qwen2.5-math-1.5b-instruct": {
- "description": "Qwen-Math模型具有強大的數學解題能力。"
+ "description": "Qwen-Math 模型具有強大的數學解題能力。"
},
"qwen2.5-math-72b-instruct": {
"description": "Qwen-Math模型具有強大的數學解題能力。"
@@ -838,6 +1616,21 @@
"qwen2.5-math-7b-instruct": {
"description": "Qwen-Math模型具有強大的數學解題能力。"
},
+ "qwen2.5-vl-72b-instruct": {
+ "description": "指令跟隨、數學、解題、代碼整體提升,萬物識別能力提升,支持多樣格式直接精準定位視覺元素,支持對長視頻文件(最長10分鐘)進行理解和秒級別的事件時刻定位,能理解時間先後和快慢,基於解析和定位能力支持操控OS或Mobile的Agent,關鍵信息抽取能力和Json格式輸出能力強,此版本為72B版本,本系列能力最強的版本。"
+ },
+ "qwen2.5-vl-7b-instruct": {
+ "description": "指令跟隨、數學、解題、代碼整體提升,萬物識別能力提升,支持多樣格式直接精準定位視覺元素,支持對長視頻文件(最長10分鐘)進行理解和秒級別的事件時刻定位,能理解時間先後和快慢,基於解析和定位能力支持操控OS或Mobile的Agent,關鍵信息抽取能力和Json格式輸出能力強,此版本為72B版本,本系列能力最強的版本。"
+ },
+ "qwen2.5:0.5b": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大規模語言模型,以優異的性能支持多元化的應用需求。"
+ },
+ "qwen2.5:1.5b": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大規模語言模型,以優異的性能支持多元化的應用需求。"
+ },
+ "qwen2.5:72b": {
+ "description": "Qwen2.5 是阿里巴巴的新一代大規模語言模型,以優異的性能支持多元化的應用需求。"
+ },
"qwen2:0.5b": {
"description": "Qwen2 是阿里巴巴的新一代大規模語言模型,以優異的性能支持多元化的應用需求。"
},
@@ -847,15 +1640,45 @@
"qwen2:72b": {
"description": "Qwen2 是阿里巴巴的新一代大規模語言模型,以優異的性能支持多元化的應用需求。"
},
- "solar-1-mini-chat": {
+ "qwq": {
+ "description": "QwQ 是一個實驗研究模型,專注於提高 AI 推理能力。"
+ },
+ "qwq-32b": {
+ "description": "基於 Qwen2.5-32B 模型訓練的 QwQ 推理模型,通過強化學習大幅度提升了模型推理能力。模型數學代碼等核心指標(AIME 24/25、LiveCodeBench)以及部分通用指標(IFEval、LiveBench等)達到 DeepSeek-R1 滿血版水平,各指標均顯著超過同樣基於 Qwen2.5-32B 的 DeepSeek-R1-Distill-Qwen-32B。"
+ },
+ "qwq-32b-preview": {
+ "description": "QwQ模型是由 Qwen 團隊開發的實驗性研究模型,專注於增強 AI 推理能力。"
+ },
+ "qwq-plus-latest": {
+ "description": "基於 Qwen2.5 模型訓練的 QwQ 推理模型,通過強化學習大幅度提升了模型推理能力。模型數學代碼等核心指標(AIME 24/25、LiveCodeBench)以及部分通用指標(IFEval、LiveBench等)達到 DeepSeek-R1 滿血版水平。"
+ },
+ "r1-1776": {
+ "description": "R1-1776 是 DeepSeek R1 模型的一個版本,經過後訓練,可提供未經審查、無偏見的事實資訊。"
+ },
+ "solar-mini": {
"description": "Solar Mini 是一種緊湊型 LLM,性能優於 GPT-3.5,具備強大的多語言能力,支持英語和韓語,提供高效小巧的解決方案。"
},
- "solar-1-mini-chat-ja": {
+ "solar-mini-ja": {
"description": "Solar Mini (Ja) 擴展了 Solar Mini 的能力,專注於日語,同時在英語和韓語的使用中保持高效和卓越性能。"
},
"solar-pro": {
"description": "Solar Pro 是 Upstage 推出的一款高智能LLM,專注於單GPU的指令跟隨能力,IFEval得分80以上。目前支持英語,正式版本計劃於2024年11月推出,將擴展語言支持和上下文長度。"
},
+ "sonar": {
+ "description": "基於搜索上下文的輕量級搜索產品,比 Sonar Pro 更快、更便宜。"
+ },
+ "sonar-deep-research": {
+ "description": "Deep Research 進行全面的專家級研究,並將其綜合成可訪問、可行的報告。"
+ },
+ "sonar-pro": {
+ "description": "支持搜索上下文的高級搜索產品,支持高級查詢和跟進。"
+ },
+ "sonar-reasoning": {
+ "description": "由 DeepSeek 推理模型提供支持的新 API 產品。"
+ },
+ "sonar-reasoning-pro": {
+ "description": "由 DeepSeek 推理模型提供支援的新 API 產品。"
+ },
"step-1-128k": {
"description": "平衡性能與成本,適合一般場景。"
},
@@ -871,6 +1694,15 @@
"step-1-flash": {
"description": "高速模型,適合實時對話。"
},
+ "step-1.5v-mini": {
+ "description": "該模型擁有強大的視頻理解能力。"
+ },
+ "step-1o-turbo-vision": {
+ "description": "該模型擁有強大的圖像理解能力,在數理、代碼領域強於1o。模型比1o更小,輸出速度更快。"
+ },
+ "step-1o-vision-32k": {
+ "description": "該模型擁有強大的圖像理解能力。相比於 step-1v 系列模型,擁有更強的視覺性能。"
+ },
"step-1v-32k": {
"description": "支持視覺輸入,增強多模態交互體驗。"
},
@@ -880,18 +1712,45 @@
"step-2-16k": {
"description": "支持大規模上下文交互,適合複雜對話場景。"
},
+ "step-2-mini": {
+ "description": "基於新一代自研Attention架構MFA的極速大模型,用極低成本達到和step1類似的效果,同時保持了更高的吞吐和更快響應時延。能夠處理通用任務,在程式碼能力上具備特長。"
+ },
"taichu_llm": {
"description": "紫東太初語言大模型具備超強語言理解能力以及文本創作、知識問答、代碼編程、數學計算、邏輯推理、情感分析、文本摘要等能力。創新性地將大數據預訓練與多源豐富知識相結合,通過持續打磨算法技術,並不斷吸收海量文本數據中詞彙、結構、語法、語義等方面的新知識,實現模型效果不斷進化。為用戶提供更加便捷的信息和服務以及更為智能化的體驗。"
},
- "taichu_vqa": {
- "description": "Taichu 2.0V 融合了圖像理解、知識遷移、邏輯歸因等能力,在圖文問答領域表現突出。"
+ "taichu_vl": {
+ "description": "融合了圖像理解、知識遷移、邏輯歸因等能力,在圖文問答領域表現突出。"
+ },
+ "text-embedding-3-large": {
+ "description": "最強大的向量化模型,適用於英文和非英文任務"
+ },
+ "text-embedding-3-small": {
+ "description": "高效且經濟的新一代 Embedding 模型,適用於知識檢索、RAG 應用等場景"
+ },
+ "thudm/glm-4-9b-chat": {
+ "description": "智譜AI發布的GLM-4系列最新一代預訓練模型的開源版本。"
},
"togethercomputer/StripedHyena-Nous-7B": {
"description": "StripedHyena Nous (7B) 通過高效的策略和模型架構,提供增強的計算能力。"
},
+ "tts-1": {
+ "description": "最新的文本轉語音模型,針對即時場景優化速度"
+ },
+ "tts-1-hd": {
+ "description": "最新的文本轉語音模型,針對品質進行優化"
+ },
"upstage/SOLAR-10.7B-Instruct-v1.0": {
"description": "Upstage SOLAR Instruct v1 (11B) 適用於精細化指令任務,提供出色的語言處理能力。"
},
+ "us.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+ "description": "Claude 3.5 Sonnet 提升了行業標準,性能超越競爭對手模型和 Claude 3 Opus,在廣泛的評估中表現出色,同時具備我們中等層級模型的速度和成本。"
+ },
+ "us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
+ "description": "Claude 3.7 sonnet 是 Anthropic 最快速的下一代模型。與 Claude 3 Haiku 相比,Claude 3.7 Sonnet 在各項技能上都有所提升,並在許多智力基準測試中超越了上一代最大的模型 Claude 3 Opus。"
+ },
+ "whisper-1": {
+ "description": "通用語音識別模型,支持多語言語音識別、語音翻譯和語言識別"
+ },
"wizardlm2": {
"description": "WizardLM 2 是微軟 AI 提供的語言模型,在複雜對話、多語言、推理和智能助手領域表現尤為出色。"
},
@@ -913,6 +1772,12 @@
"yi-large-turbo": {
"description": "超高性價比、卓越性能。根據性能和推理速度、成本,進行平衡性高精度調優。"
},
+ "yi-lightning": {
+ "description": "最新高性能模型,保證高品質輸出同時,推理速度大幅提升。"
+ },
+ "yi-lightning-lite": {
+ "description": "輕量化版本,推薦使用 yi-lightning。"
+ },
"yi-medium": {
"description": "中型尺寸模型升級微調,能力均衡,性價比高。深度優化指令遵循能力。"
},
@@ -924,5 +1789,8 @@
},
"yi-vision": {
"description": "複雜視覺任務模型,提供高性能圖片理解、分析能力。"
+ },
+ "yi-vision-v2": {
+ "description": "複雜視覺任務模型,提供基於多張圖片的高性能理解、分析能力。"
}
}
diff --git a/DigitalHumanWeb/locales/zh-TW/plugin.json b/DigitalHumanWeb/locales/zh-TW/plugin.json
index 87259c4..c8727bc 100644
--- a/DigitalHumanWeb/locales/zh-TW/plugin.json
+++ b/DigitalHumanWeb/locales/zh-TW/plugin.json
@@ -118,6 +118,10 @@
"reinstallError": "插件 {{name}} 刷新失敗",
"urlError": "該連結沒有返回 JSON 格式的內容, 請確保是有效的連結"
},
+ "inspector": {
+ "args": "查看參數列表",
+ "pluginRender": "查看插件介面"
+ },
"list": {
"item": {
"deprecated.title": "已刪除",
@@ -130,6 +134,34 @@
"plugin": "外掛執行中..."
},
"pluginList": "外掛清單",
+ "search": {
+ "config": {
+ "addKey": "添加密鑰",
+ "close": "刪除",
+ "confirm": "已完成配置並重試"
+ },
+ "crawPages": {
+ "crawling": "連結識別中",
+ "detail": {
+ "preview": "預覽",
+ "raw": "原始文本",
+ "tooLong": "文本內容過長,對話上下文僅保留前 {{characters}} 字元,超過部分不計入會話上下文"
+ },
+ "meta": {
+ "crawler": "抓取模式",
+ "words": "字元數"
+ }
+ },
+ "searchxng": {
+ "baseURL": "請輸入",
+ "description": "請輸入 SearchXNG 的網址,即可開始聯網搜索",
+ "keyPlaceholder": "請輸入密鑰",
+ "title": "配置 SearchXNG 搜索引擎",
+ "unconfiguredDesc": "請聯繫管理員完成 SearchXNG 搜索引擎配置,即可開始聯網搜索",
+ "unconfiguredTitle": "暫未配置 SearchXNG 搜索引擎"
+ },
+ "title": "聯網搜索"
+ },
"setting": "插件設置",
"settings": {
"indexUrl": {
diff --git a/DigitalHumanWeb/locales/zh-TW/portal.json b/DigitalHumanWeb/locales/zh-TW/portal.json
index 75079c2..66234e0 100644
--- a/DigitalHumanWeb/locales/zh-TW/portal.json
+++ b/DigitalHumanWeb/locales/zh-TW/portal.json
@@ -7,11 +7,6 @@
}
},
"Plugins": "外掛",
- "actions": {
- "genAiMessage": "生成助手訊息",
- "summary": "摘要",
- "summaryTooltip": "總結目前內容"
- },
"artifacts": {
"display": {
"code": "程式碼",
diff --git a/DigitalHumanWeb/locales/zh-TW/providers.json b/DigitalHumanWeb/locales/zh-TW/providers.json
index 74132fe..5ae6caf 100644
--- a/DigitalHumanWeb/locales/zh-TW/providers.json
+++ b/DigitalHumanWeb/locales/zh-TW/providers.json
@@ -1,5 +1,7 @@
{
- "ai21": {},
+ "ai21": {
+ "description": "AI21 Labs 為企業構建基礎模型和人工智慧系統,加速生成性人工智慧在生產中的應用。"
+ },
"ai360": {
"description": "360 AI 是 360 公司推出的 AI 模型和服務平台,提供多種先進的自然語言處理模型,包括 360GPT2 Pro、360GPT Pro、360GPT Turbo 和 360GPT Turbo Responsibility 8K。這些模型結合了大規模參數和多模態能力,廣泛應用於文本生成、語義理解、對話系統與代碼生成等領域。通過靈活的定價策略,360 AI 滿足多樣化用戶需求,支持開發者集成,推動智能化應用的革新和發展。"
},
@@ -9,18 +11,30 @@
"azure": {
"description": "Azure 提供多種先進的 AI 模型,包括 GPT-3.5 和最新的 GPT-4 系列,支持多種數據類型和複雜任務,致力於安全、可靠和可持續的 AI 解決方案。"
},
+ "azureai": {
+ "description": "Azure 提供多種先進的 AI 模型,包括 GPT-3.5 和最新的 GPT-4 系列,支持多種數據類型和複雜任務,致力於安全、可靠和可持續的 AI 解決方案。"
+ },
"baichuan": {
"description": "百川智能是一家專注於人工智慧大模型研發的公司,其模型在國內知識百科、長文本處理和生成創作等中文任務上表現卓越,超越了國外主流模型。百川智能還具備行業領先的多模態能力,在多項權威評測中表現優異。其模型包括 Baichuan 4、Baichuan 3 Turbo 和 Baichuan 3 Turbo 128k 等,分別針對不同應用場景進行優化,提供高性價比的解決方案。"
},
"bedrock": {
"description": "Bedrock 是亞馬遜 AWS 提供的一項服務,專注於為企業提供先進的 AI 語言模型和視覺模型。其模型家族包括 Anthropic 的 Claude 系列、Meta 的 Llama 3.1 系列等,涵蓋從輕量級到高性能的多種選擇,支持文本生成、對話、圖像處理等多種任務,適用於不同規模和需求的企業應用。"
},
+ "cloudflare": {
+ "description": "在 Cloudflare 的全球網絡上運行由無伺服器 GPU 驅動的機器學習模型。"
+ },
"deepseek": {
"description": "DeepSeek 是一家專注於人工智慧技術研究和應用的公司,其最新模型 DeepSeek-V2.5 融合了通用對話和代碼處理能力,並在人類偏好對齊、寫作任務和指令跟隨等方面實現了顯著提升。"
},
+ "doubao": {
+ "description": "字節跳動推出的自研大模型。透過字節跳動內部50+業務場景實踐驗證,每日萬億級tokens大使用量持續打磨,提供多種模態能力,以優質模型效果為企業打造豐富的業務體驗。"
+ },
"fireworksai": {
"description": "Fireworks AI 是一家領先的高級語言模型服務商,專注於功能調用和多模態處理。其最新模型 Firefunction V2 基於 Llama-3,優化用於函數調用、對話及指令跟隨。視覺語言模型 FireLLaVA-13B 支持圖像和文本混合輸入。其他 notable 模型包括 Llama 系列和 Mixtral 系列,提供高效的多語言指令跟隨與生成支持。"
},
+ "giteeai": {
+ "description": "Gitee AI 的 Serverless API 為 AI 開發者提供開箱即用的大模型推理 API 服務。"
+ },
"github": {
"description": "透過 GitHub 模型,開發者可以成為 AI 工程師,並使用業界領先的 AI 模型進行建設。"
},
@@ -30,6 +44,24 @@
"groq": {
"description": "Groq 的 LPU 推理引擎在最新的獨立大語言模型(LLM)基準測試中表現卓越,以其驚人的速度和效率重新定義了 AI 解決方案的標準。Groq 是一種即時推理速度的代表,在基於雲的部署中展現了良好的性能。"
},
+ "higress": {
+ "description": "Higress 是一款雲原生 API 網關,為了解決 Tengine reload 對長連接業務的影響,以及 gRPC/Dubbo 負載均衡能力不足而在阿里內部誕生。"
+ },
+ "huggingface": {
+ "description": "HuggingFace Inference API 提供了一種快速且免費的方式,讓您可以探索成千上萬種模型,適用於各種任務。無論您是在為新應用程式進行原型設計,還是在嘗試機器學習的功能,這個 API 都能讓您即時訪問多個領域的高性能模型。"
+ },
+ "hunyuan": {
+ "description": "由騰訊研發的大語言模型,具備強大的中文創作能力、複雜語境下的邏輯推理能力,以及可靠的任務執行能力"
+ },
+ "internlm": {
+ "description": "致力於大模型研究與開發工具鏈的開源組織。為所有 AI 開發者提供高效、易用的開源平台,讓最前沿的大模型與算法技術觸手可及"
+ },
+ "jina": {
+ "description": "Jina AI 成立於 2020 年,是一家領先的搜索 AI 公司。我們的搜索底座平台包含了向量模型、重排器和小語言模型,可幫助企業構建可靠且高品質的生成式 AI 和多模態的搜索應用。"
+ },
+ "lmstudio": {
+ "description": "LM Studio 是一個用於在您的電腦上開發和實驗 LLMs 的桌面應用程式。"
+ },
"minimax": {
"description": "MiniMax 是 2021 年成立的通用人工智慧科技公司,致力於與用戶共創智能。MiniMax 自主研發了不同模態的通用大模型,其中包括萬億參數的 MoE 文本大模型、語音大模型以及圖像大模型。並推出了海螺 AI 等應用。"
},
@@ -42,6 +74,9 @@
"novita": {
"description": "Novita AI 是一個提供多種大語言模型與 AI 圖像生成的 API 服務的平台,靈活、可靠且具有成本效益。它支持 Llama3、Mistral 等最新的開源模型,並為生成式 AI 應用開發提供了全面、用戶友好且自動擴展的 API 解決方案,適合 AI 初創公司的快速發展。"
},
+ "nvidia": {
+ "description": "NVIDIA NIM™ 提供容器,可用於自托管 GPU 加速推理微服務,支持在雲端、數據中心、RTX™ AI 個人電腦和工作站上部署預訓練和自定義 AI 模型。"
+ },
"ollama": {
"description": "Ollama 提供的模型廣泛涵蓋代碼生成、數學運算、多語種處理和對話互動等領域,支持企業級和本地化部署的多樣化需求。"
},
@@ -54,9 +89,18 @@
"perplexity": {
"description": "Perplexity 是一家領先的對話生成模型提供商,提供多種先進的 Llama 3.1 模型,支持在線和離線應用,特別適用於複雜的自然語言處理任務。"
},
+ "ppio": {
+ "description": "PPIO 派歐雲提供穩定、高性價比的開源模型 API 服務,支持 DeepSeek 全系列、Llama、Qwen 等行業領先的大模型。"
+ },
"qwen": {
"description": "通義千問是阿里雲自主研發的超大規模語言模型,具有強大的自然語言理解和生成能力。它可以回答各種問題、創作文字內容、表達觀點看法、撰寫代碼等,在多個領域發揮作用。"
},
+ "sambanova": {
+ "description": "SambaNova Cloud 讓開發者輕鬆使用最佳的開源模型,並享受最快的推理速度。"
+ },
+ "sensenova": {
+ "description": "商湯日日新,依托商湯大裝置的強大基礎支撐,提供高效易用的全棧大模型服務。"
+ },
"siliconcloud": {
"description": "SiliconFlow 致力於加速 AGI,以惠及人類,通過易用與成本低的 GenAI 堆疊提升大規模 AI 效率。"
},
@@ -69,12 +113,30 @@
"taichu": {
"description": "中科院自動化研究所和武漢人工智慧研究院推出新一代多模態大模型,支持多輪問答、文本創作、圖像生成、3D理解、信號分析等全面問答任務,擁有更強的認知、理解、創作能力,帶來全新互動體驗。"
},
+ "tencentcloud": {
+ "description": "知識引擎原子能力(LLM Knowledge Engine Atomic Power)基於知識引擎研發的知識問答全鏈路能力,面向企業及開發者,提供靈活組建及開發模型應用的能力。您可透過多款原子能力組建您專屬的模型服務,調用文檔解析、拆分、embedding、多輪改寫等服務進行組裝,定制企業專屬 AI 業務。"
+ },
"togetherai": {
"description": "Together AI 致力於透過創新的 AI 模型實現領先的性能,提供廣泛的自定義能力,包括快速擴展支持和直觀的部署流程,滿足企業的各種需求。"
},
"upstage": {
"description": "Upstage 專注於為各種商業需求開發 AI 模型,包括 Solar LLM 和文檔 AI,旨在實現工作的人工通用智能(AGI)。通過 Chat API 創建簡單的對話代理,並支持功能調用、翻譯、嵌入以及特定領域應用。"
},
+ "vertexai": {
+ "description": "Google 的 Gemini 系列是其最先進、通用的 AI 模型,由 Google DeepMind 打造,專為多模態設計,支持文本、程式碼、圖像、音訊和視頻的無縫理解與處理。適用於從數據中心到行動裝置的多種環境,極大提升了 AI 模型的效率與應用廣泛性。"
+ },
+ "vllm": {
+ "description": "vLLM 是一個快速且易於使用的庫,用於 LLM 推理和服務。"
+ },
+ "volcengine": {
+ "description": "字節跳動推出的大模型服務的開發平台,提供功能豐富、安全以及具備價格競爭力的模型調用服務,同時提供模型數據、精調、推理、評測等端到端功能,全方位保障您的 AI 應用開發落地。"
+ },
+ "wenxin": {
+ "description": "企業級一站式大模型與AI原生應用開發及服務平台,提供最全面易用的生成式人工智慧模型開發、應用開發全流程工具鏈"
+ },
+ "xai": {
+ "description": "xAI 是一家致力於構建人工智慧以加速人類科學發現的公司。我們的使命是推動我們對宇宙的共同理解。"
+ },
"zeroone": {
"description": "01.AI 專注於 AI 2.0 時代的人工智慧技術,大力推動「人+人工智慧」的創新和應用,採用超強大模型和先進 AI 技術以提升人類生產力,實現技術賦能。"
},
diff --git a/DigitalHumanWeb/locales/zh-TW/setting.json b/DigitalHumanWeb/locales/zh-TW/setting.json
index 5cbbae7..3808816 100644
--- a/DigitalHumanWeb/locales/zh-TW/setting.json
+++ b/DigitalHumanWeb/locales/zh-TW/setting.json
@@ -84,8 +84,7 @@
},
"modalTitle": "自定義模型配置",
"tokens": {
- "title": "最大 token 數",
- "unlimited": "無限制"
+ "title": "最大 token 數"
},
"vision": {
"extra": "此配置將僅開啟應用中的圖片上傳配置,是否支持識別完全取決於模型本身,請自行測試該模型的視覺識別能力可用性",
@@ -98,6 +97,7 @@
"title": "使用客戶端請求模式"
},
"fetcher": {
+ "clear": "清除獲取的模型",
"fetch": "獲取模型列表",
"fetching": "正在獲取模型列表...",
"latestTime": "上次更新時間:{{time}}",
@@ -175,8 +175,8 @@
"desc": "對話過程中是否自動建立話題,僅在臨時話題中生效",
"title": "自動建立話題"
},
- "enableCompressThreshold": {
- "title": "是否開啟歷史訊息長度壓縮閾值"
+ "enableCompressHistory": {
+ "title": "開啟歷史消息自動總結"
},
"enableHistoryCount": {
"alias": "不限制",
@@ -200,9 +200,12 @@
"enableMaxTokens": {
"title": "啟用單次回覆限制"
},
+ "enableReasoningEffort": {
+ "title": "開啟推理強度調整"
+ },
"frequencyPenalty": {
- "desc": "數值越大,越有可能降低重複字詞",
- "title": "頻率懲罰度"
+ "desc": "值越大,用詞越豐富多樣;值越低,用詞更樸實簡單",
+ "title": "詞彙豐富度"
},
"maxTokens": {
"desc": "單次互動所使用的最大 Token 數",
@@ -212,19 +215,31 @@
"desc": "{{provider}} 模型",
"title": "模型"
},
+ "params": {
+ "title": "高級參數"
+ },
"presencePenalty": {
- "desc": "數值越大,越有可能擴展到新話題",
- "title": "話題新鮮度"
+ "desc": "值越大,越傾向不同的表達方式,避免概念重複;值越小,越傾向使用重複的概念或敘述,表達更具一致性",
+ "title": "表述發散度"
+ },
+ "reasoningEffort": {
+ "desc": "值越大,推理能力越強,但可能會增加回應時間和 Token 消耗",
+ "options": {
+ "high": "高",
+ "low": "低",
+ "medium": "中"
+ },
+ "title": "推理強度"
},
"temperature": {
- "desc": "數值越大,回覆越隨機",
- "title": "隨機性",
- "titleWithValue": "隨機性 {{value}}"
+ "desc": "數值越大,回答越有創意和想像力;數值越小,回答越嚴謹",
+ "title": "創意活躍度",
+ "warning": "創意活躍度數值過大,輸出可能會產生亂碼"
},
"title": "模型設定",
"topP": {
- "desc": "與隨機性類似,但不要和隨機性一起更改",
- "title": "核採樣"
+ "desc": "考慮多少種可能性,值越大,接受更多可能的回答;值越小,傾向選擇最可能的回答。不推薦和創意活躍度一起更改",
+ "title": "思維開放度"
}
},
"settingPlugin": {
@@ -274,7 +289,7 @@
"title": "語音識別語種"
},
"sttService": {
- "desc": "其中 broswer 為瀏覽器原生的語音識別服務",
+ "desc": "其中 browser 為瀏覽器原生的語音識別服務",
"title": "語音識別服務"
},
"title": "語音服務",
@@ -372,10 +387,26 @@
"modelDesc": "指定用於生成助理名稱、描述、頭像、標籤的模型",
"title": "自動生成助理資訊"
},
+ "customPrompt": {
+ "addPrompt": "新增自訂提示",
+ "desc": "填寫後,系統助理將在生成內容時使用自訂提示",
+ "placeholder": "請輸入自訂提示詞",
+ "title": "自訂提示詞"
+ },
+ "historyCompress": {
+ "label": "會話歷史模型",
+ "modelDesc": "指定用於壓縮會話歷史的模型",
+ "title": "自動總結會話歷史"
+ },
"queryRewrite": {
"label": "提問重寫模型",
"modelDesc": "指定用於優化用戶提問的模型",
- "title": "知識庫"
+ "title": "知識庫提問重寫"
+ },
+ "thread": {
+ "label": "子主題命名模型",
+ "modelDesc": "指定用於子主題自動重命名的模型",
+ "title": "子主題自動命名"
},
"title": "系統助手",
"topic": {
@@ -395,6 +426,7 @@
"common": "通用設置",
"experiment": "實驗",
"llm": "語言模型",
+ "provider": "AI 服務商",
"sync": "雲端同步",
"system-agent": "系統助手",
"tts": "語音服務"
diff --git a/DigitalHumanWeb/locales/zh-TW/thread.json b/DigitalHumanWeb/locales/zh-TW/thread.json
new file mode 100644
index 0000000..e9e9ce7
--- /dev/null
+++ b/DigitalHumanWeb/locales/zh-TW/thread.json
@@ -0,0 +1,10 @@
+{
+ "actions": {
+ "confirmRemoveThread": "即將刪除該子話題,刪除後將無法恢復,請謹慎操作。"
+ },
+ "newPortalThread": {
+ "includeContext": "包含主題上下文",
+ "title": "開啟新的子主題"
+ },
+ "notSupportMultiModals": "子主題暫不支持文件/圖片上傳,如有需求,歡迎留言:<1>💬 討論區1>"
+}
diff --git a/DigitalHumanWeb/locales/zh-TW/tool.json b/DigitalHumanWeb/locales/zh-TW/tool.json
index b1c3c53..8328746 100644
--- a/DigitalHumanWeb/locales/zh-TW/tool.json
+++ b/DigitalHumanWeb/locales/zh-TW/tool.json
@@ -6,5 +6,23 @@
"generating": "生成中...",
"images": "圖片:",
"prompt": "提示詞"
+ },
+ "search": {
+ "createNewSearch": "建立新的搜尋紀錄",
+ "emptyResult": "沒有搜尋到結果,請修改關鍵字後重試",
+ "genAiMessage": "創建助手消息",
+ "includedTooltip": "當前搜尋結果會進入會話的上下文中",
+ "keywords": "關鍵字:",
+ "scoreTooltip": "相關性分數,該分數越高說明與查詢關鍵字越相關",
+ "searchBar": {
+ "button": "搜尋",
+ "placeholder": "關鍵字",
+ "tooltip": "將會重新獲取搜尋結果,並建立一條新的總結消息"
+ },
+ "searchEngine": "搜尋引擎:",
+ "searchResult": "搜尋數量:",
+ "summary": "總結",
+ "summaryTooltip": "總結當前內容",
+ "viewMoreResults": "查看更多 {{results}} 個結果"
}
}
diff --git a/DigitalHumanWeb/locales/zh-TW/topic.json b/DigitalHumanWeb/locales/zh-TW/topic.json
new file mode 100644
index 0000000..338e92f
--- /dev/null
+++ b/DigitalHumanWeb/locales/zh-TW/topic.json
@@ -0,0 +1,38 @@
+{
+ "actions": {
+ "autoRename": "智能重命名",
+ "confirmRemoveAll": "即將刪除全部話題,刪除後將不可恢復,請謹慎操作。",
+ "confirmRemoveTopic": "即將刪除該話題,刪除後將不可恢復,請謹慎操作。",
+ "confirmRemoveUnstarred": "即將刪除未收藏話題,刪除後將不可恢復,請謹慎操作。",
+ "duplicate": "創建副本",
+ "export": "匯出話題",
+ "removeAll": "刪除全部話題",
+ "removeUnstarred": "刪除未收藏話題"
+ },
+ "defaultTitle": "預設話題",
+ "duplicateLoading": "話題複製中...",
+ "duplicateSuccess": "話題複製成功",
+ "favorite": "收藏",
+ "groupMode": {
+ "ascMessages": "按消息總數順序",
+ "byTime": "按時間分組",
+ "descMessages": "按消息總數倒序",
+ "flat": "不分組"
+ },
+ "groupTitle": {
+ "byTime": {
+ "month": "本月",
+ "today": "今天",
+ "week": "本週",
+ "yesterday": "昨天"
+ }
+ },
+ "guide": {
+ "desc": "點擊發送左側按鈕可將當前會話保存為歷史話題,並開啟新一輪會話",
+ "title": "話題列表"
+ },
+ "searchPlaceholder": "搜尋話題...",
+ "searchResultEmpty": "目前沒有搜尋結果",
+ "temp": "臨時",
+ "title": "話題"
+}
diff --git a/DigitalHumanWeb/locales/zh-TW/welcome.json b/DigitalHumanWeb/locales/zh-TW/welcome.json
index 26a5140..fbc0a82 100644
--- a/DigitalHumanWeb/locales/zh-TW/welcome.json
+++ b/DigitalHumanWeb/locales/zh-TW/welcome.json
@@ -1,9 +1,4 @@
{
- "button": {
- "import": "匯入設定檔",
- "market": "逛逛市場",
- "start": "馬上開始"
- },
"guide": {
"agents": {
"replaceBtn": "換一批",
diff --git a/DigitalHumanWeb/netlify.toml b/DigitalHumanWeb/netlify.toml
index 865bf1e..0546e7e 100644
--- a/DigitalHumanWeb/netlify.toml
+++ b/DigitalHumanWeb/netlify.toml
@@ -1,9 +1,9 @@
[build]
-command = "pnpm run build"
+command = "rm -rf .next node_modules/.cache && pnpm run build"
publish = ".next"
[build.environment]
-NODE_OPTIONS = "--max_old_space_size=8192"
+NODE_OPTIONS = "--max-old-space-size=4096"
[template.environment]
OPENAI_API_KEY = "set your OpenAI API Key"
diff --git a/DigitalHumanWeb/next.config.mjs b/DigitalHumanWeb/next.config.mjs
deleted file mode 100644
index 9b9a578..0000000
--- a/DigitalHumanWeb/next.config.mjs
+++ /dev/null
@@ -1,248 +0,0 @@
-import analyzer from '@next/bundle-analyzer';
-import { withSentryConfig } from '@sentry/nextjs';
-import withSerwistInit from '@serwist/next';
-
-const isProd = process.env.NODE_ENV === 'production';
-const buildWithDocker = process.env.DOCKER === 'true';
-
-// if you need to proxy the api endpoint to remote server
-const API_PROXY_ENDPOINT = process.env.API_PROXY_ENDPOINT || '';
-
-const basePath = process.env.NEXT_PUBLIC_BASE_PATH;
-
-/** @type {import('next').NextConfig} */
-const nextConfig = {
- basePath,
- compress: isProd,
- experimental: {
- optimizePackageImports: [
- 'emoji-mart',
- '@emoji-mart/react',
- '@emoji-mart/data',
- '@icons-pack/react-simple-icons',
- '@lobehub/ui',
- 'gpt-tokenizer',
- 'chroma-js',
- ],
- webVitalsAttribution: ['CLS', 'LCP'],
- },
- typescript: {
- ignoreBuildErrors: true
- },
- async headers() {
- return [
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/icons/(.*).(png|jpe?g|gif|svg|ico|webp)',
- },
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/images/(.*).(png|jpe?g|gif|svg|ico|webp)',
- },
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/videos/(.*).(mp4|webm|ogg|avi|mov|wmv|flv|mkv)',
- },
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/screenshots/(.*).(png|jpe?g|gif|svg|ico|webp)',
- },
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/og/(.*).(png|jpe?g|gif|svg|ico|webp)',
- },
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/favicon.ico',
- },
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/favicon-32x32.ico',
- },
- {
- headers: [
- {
- key: 'Cache-Control',
- value: 'public, max-age=31536000, immutable',
- },
- ],
- source: '/apple-touch-icon.png',
- },
- ];
- },
-
- output: buildWithDocker ? 'standalone' : undefined,
- reactStrictMode: true,
- redirects: async () => [
- {
- destination: '/sitemap-index.xml',
- permanent: true,
- source: '/sitemap.xml',
- },
- {
- destination: '/manifest.webmanifest',
- permanent: true,
- source: '/manifest.json',
- },
- {
- destination: '/discover/assistant/:slug',
- has: [
- {
- key: 'agent',
- type: 'query',
- value: '(?.*)',
- },
- ],
- permanent: true,
- source: '/market',
- },
- {
- destination: '/discover/assistants',
- permanent: true,
- source: '/discover/assistant',
- },
- {
- destination: '/discover/models',
- permanent: true,
- source: '/discover/model',
- },
- {
- destination: '/discover/plugins',
- permanent: true,
- source: '/discover/plugin',
- },
- {
- destination: '/discover/providers',
- permanent: true,
- source: '/discover/provider',
- },
- {
- destination: '/settings/common',
- permanent: true,
- source: '/settings',
- },
- ],
-
- rewrites: async () => [
- // due to google api not work correct in some countries
- // we need a proxy to bypass the restriction
- { destination: `${API_PROXY_ENDPOINT}/api/chat/google`, source: '/api/chat/google' },
- ],
-
- webpack(config) {
- config.experiments = {
- asyncWebAssembly: true,
- layers: true,
- };
-
- // to fix shikiji compile error
- // refs: https://github.com/antfu/shikiji/issues/23
- config.module.rules.push({
- resolve: {
- fullySpecified: false,
- },
- test: /\.m?js$/,
- type: 'javascript/auto',
- });
-
- // https://github.com/pinojs/pino/issues/688#issuecomment-637763276
- config.externals.push('pino-pretty');
-
- config.resolve.alias.canvas = false;
-
- return config;
- },
-};
-
-const noWrapper = (config) => config;
-
-const withBundleAnalyzer = process.env.ANALYZE === 'true' ? analyzer() : noWrapper;
-
-const withPWA = isProd
- ? withSerwistInit({
- register: false,
- swDest: 'public/sw.js',
- swSrc: 'src/app/sw.ts',
- })
- : noWrapper;
-
-const hasSentry = !!process.env.NEXT_PUBLIC_SENTRY_DSN;
-const withSentry =
- isProd && hasSentry
- ? (c) =>
- withSentryConfig(
- c,
- {
- org: process.env.SENTRY_ORG,
-
- project: process.env.SENTRY_PROJECT,
- // For all available options, see:
- // https://github.com/getsentry/sentry-webpack-plugin#options
- // Suppresses source map uploading logs during build
- silent: true,
- },
- {
- // Enables automatic instrumentation of Vercel Cron Monitors.
- // See the following for more information:
- // https://docs.sentry.io/product/crons/
- // https://vercel.com/docs/cron-jobs
- automaticVercelMonitors: true,
-
- // Automatically tree-shake Sentry logger statements to reduce bundle size
- disableLogger: true,
-
- // Hides source maps from generated client bundles
- hideSourceMaps: true,
-
- // Transpiles SDK to be compatible with IE11 (increases bundle size)
- transpileClientSDK: true,
-
- // Routes browser requests to Sentry through a Next.js rewrite to circumvent ad-blockers. (increases server load)
- // Note: Check that the configured route will not match with your Next.js middleware, otherwise reporting of client-
- // side errors will fail.
- tunnelRoute: '/monitoring',
-
- // For all available options, see:
- // https://docs.sentry.io/platforms/javascript/guides/nextjs/manual-setup/
- // Upload a larger set of source maps for prettier stack traces (increases build time)
- widenClientFileUpload: true,
- },
- )
- : noWrapper;
-
-export default withBundleAnalyzer(withPWA(withSentry(nextConfig)));
diff --git a/DigitalHumanWeb/next.config.ts b/DigitalHumanWeb/next.config.ts
new file mode 100644
index 0000000..4d51c19
--- /dev/null
+++ b/DigitalHumanWeb/next.config.ts
@@ -0,0 +1,286 @@
+import analyzer from '@next/bundle-analyzer';
+import { withSentryConfig } from '@sentry/nextjs';
+import withSerwistInit from '@serwist/next';
+import type { NextConfig } from 'next';
+import ReactComponentName from 'react-scan/react-component-name/webpack';
+
+const isProd = process.env.NODE_ENV === 'production';
+const buildWithDocker = process.env.DOCKER === 'true';
+const enableReactScan = !!process.env.REACT_SCAN_MONITOR_API_KEY;
+const isUsePglite = process.env.NEXT_PUBLIC_CLIENT_DB === 'pglite';
+
+// if you need to proxy the api endpoint to remote server
+
+const basePath = process.env.NEXT_PUBLIC_BASE_PATH;
+
+const nextConfig: NextConfig = {
+ basePath,
+ compress: isProd,
+ experimental: {
+ optimizePackageImports: [
+ 'emoji-mart',
+ '@emoji-mart/react',
+ '@emoji-mart/data',
+ '@icons-pack/react-simple-icons',
+ '@lobehub/ui',
+ 'gpt-tokenizer',
+ ],
+ webVitalsAttribution: ['CLS', 'LCP'],
+ webpackMemoryOptimizations: true,
+ },
+ async headers() {
+ return [
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/icons/(.*).(png|jpe?g|gif|svg|ico|webp)',
+ },
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/images/(.*).(png|jpe?g|gif|svg|ico|webp)',
+ },
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/videos/(.*).(mp4|webm|ogg|avi|mov|wmv|flv|mkv)',
+ },
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/screenshots/(.*).(png|jpe?g|gif|svg|ico|webp)',
+ },
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/og/(.*).(png|jpe?g|gif|svg|ico|webp)',
+ },
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/favicon.ico',
+ },
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/favicon-32x32.ico',
+ },
+ {
+ headers: [
+ {
+ key: 'Cache-Control',
+ value: 'public, max-age=31536000, immutable',
+ },
+ ],
+ source: '/apple-touch-icon.png',
+ },
+ ];
+ },
+ logging: {
+ fetches: {
+ fullUrl: true,
+ hmrRefreshes: true,
+ },
+ },
+ output: buildWithDocker ? 'standalone' : undefined,
+ outputFileTracingIncludes: buildWithDocker
+ ? { '*': ['public/**/*', '.next/static/**/*'] }
+ : undefined,
+ reactStrictMode: true,
+ redirects: async () => [
+ {
+ destination: '/sitemap-index.xml',
+ permanent: true,
+ source: '/sitemap.xml',
+ },
+ {
+ destination: '/sitemap-index.xml',
+ permanent: true,
+ source: '/sitemap-0.xml',
+ },
+ {
+ destination: '/manifest.webmanifest',
+ permanent: true,
+ source: '/manifest.json',
+ },
+ {
+ destination: '/discover/assistant/:slug',
+ has: [
+ {
+ key: 'agent',
+ type: 'query',
+ value: '(?.*)',
+ },
+ ],
+ permanent: true,
+ source: '/market',
+ },
+ {
+ destination: '/discover/assistants',
+ permanent: true,
+ source: '/discover/assistant',
+ },
+ {
+ destination: '/discover/models',
+ permanent: true,
+ source: '/discover/model',
+ },
+ {
+ destination: '/discover/plugins',
+ permanent: true,
+ source: '/discover/plugin',
+ },
+ {
+ destination: '/discover/providers',
+ permanent: true,
+ source: '/discover/provider',
+ },
+ {
+ destination: '/settings/common',
+ permanent: true,
+ source: '/settings',
+ },
+ {
+ destination: '/chat',
+ permanent: true,
+ source: '/welcome',
+ },
+ // TODO: 等 V2 做强制跳转吧
+ // {
+ // destination: '/settings/provider/volcengine',
+ // permanent: true,
+ // source: '/settings/provider/doubao',
+ // },
+ // we need back /repos url in the further
+ {
+ destination: '/files',
+ permanent: false,
+ source: '/repos',
+ },
+ ],
+ // when external packages in dev mode with turbopack, this config will lead to bundle error
+ serverExternalPackages: isProd ? ['@electric-sql/pglite'] : undefined,
+
+ transpilePackages: ['pdfjs-dist', 'mermaid'],
+
+ webpack(config) {
+ config.experiments = {
+ asyncWebAssembly: true,
+ layers: true,
+ };
+
+ // 开启该插件会导致 pglite 的 fs bundler 被改表
+ if (enableReactScan && !isUsePglite) {
+ config.plugins.push(ReactComponentName({}));
+ }
+
+ // to fix shikiji compile error
+ // refs: https://github.com/antfu/shikiji/issues/23
+ config.module.rules.push({
+ resolve: {
+ fullySpecified: false,
+ },
+ test: /\.m?js$/,
+ type: 'javascript/auto',
+ });
+
+ // https://github.com/pinojs/pino/issues/688#issuecomment-637763276
+ config.externals.push('pino-pretty');
+
+ config.resolve.alias.canvas = false;
+
+ // to ignore epub2 compile error
+ // refs: https://github.com/lobehub/lobe-chat/discussions/6769
+ config.resolve.fallback = {
+ ...config.resolve.fallback,
+ zipfile: false,
+ };
+ return config;
+ },
+};
+
+const noWrapper = (config: NextConfig) => config;
+
+const withBundleAnalyzer = process.env.ANALYZE === 'true' ? analyzer() : noWrapper;
+
+const withPWA = isProd
+ ? withSerwistInit({
+ register: false,
+ swDest: 'public/sw.js',
+ swSrc: 'src/app/sw.ts',
+ })
+ : noWrapper;
+
+const hasSentry = !!process.env.NEXT_PUBLIC_SENTRY_DSN;
+const withSentry =
+ isProd && hasSentry
+ ? (c: NextConfig) =>
+ withSentryConfig(
+ c,
+ {
+ org: process.env.SENTRY_ORG,
+
+ project: process.env.SENTRY_PROJECT,
+ // For all available options, see:
+ // https://github.com/getsentry/sentry-webpack-plugin#options
+ // Suppresses source map uploading logs during build
+ silent: true,
+ },
+ {
+ // Enables automatic instrumentation of Vercel Cron Monitors.
+ // See the following for more information:
+ // https://docs.sentry.io/product/crons/
+ // https://vercel.com/docs/cron-jobs
+ automaticVercelMonitors: true,
+
+ // Automatically tree-shake Sentry logger statements to reduce bundle size
+ disableLogger: true,
+
+ // Hides source maps from generated client bundles
+ hideSourceMaps: true,
+
+ // Transpiles SDK to be compatible with IE11 (increases bundle size)
+ transpileClientSDK: true,
+
+ // Routes browser requests to Sentry through a Next.js rewrite to circumvent ad-blockers. (increases server load)
+ // Note: Check that the configured route will not match with your Next.js middleware, otherwise reporting of client-
+ // side errors will fail.
+ tunnelRoute: '/monitoring',
+
+ // For all available options, see:
+ // https://docs.sentry.io/platforms/javascript/guides/nextjs/manual-setup/
+ // Upload a larger set of source maps for prettier stack traces (increases build time)
+ widenClientFileUpload: true,
+ },
+ )
+ : noWrapper;
+
+export default withBundleAnalyzer(withPWA(withSentry(nextConfig) as NextConfig));
diff --git a/DigitalHumanWeb/package.json b/DigitalHumanWeb/package.json
index 7f52e35..594912c 100644
--- a/DigitalHumanWeb/package.json
+++ b/DigitalHumanWeb/package.json
@@ -1,6 +1,6 @@
{
"name": "@lobehub/chat",
- "version": "1.19.33",
+ "version": "1.70.10",
"description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
"keywords": [
"framework",
@@ -25,6 +25,9 @@
"license": "MIT",
"author": "LobeHub ",
"sideEffects": false,
+ "workspaces": [
+ "packages/*"
+ ],
"scripts": {
"build": "next build",
"postbuild": "npm run build-sitemap && npm run build-migrate-db",
@@ -32,20 +35,21 @@
"build-sitemap": "tsx ./scripts/buildSitemapIndex/index.ts",
"build:analyze": "ANALYZE=true next build",
"build:docker": "DOCKER=true next build && npm run build-sitemap",
- "db:generate": "drizzle-kit generate",
+ "db:generate": "drizzle-kit generate && npm run db:generate-client",
+ "db:generate-client": "tsx ./scripts/migrateClientDB/compile-migrations.ts",
"db:migrate": "MIGRATION_DB=1 tsx ./scripts/migrateServerDB/index.ts",
"db:push": "drizzle-kit push",
"db:push-test": "NODE_ENV=test drizzle-kit push",
"db:studio": "drizzle-kit studio",
"db:z-pull": "drizzle-kit introspect",
- "dev": "next dev -p 3210",
- "docs:i18n": "lobe-i18n md && npm run lint:mdx",
+ "dev": "next dev --turbopack -p 3210",
+ "docs:i18n": "lobe-i18n md && npm run lint:md && npm run lint:mdx",
"docs:seo": "lobe-seo && npm run lint:mdx",
"i18n": "npm run workflow:i18n && lobe-i18n",
"lint": "npm run lint:ts && npm run lint:style && npm run type-check && npm run lint:circular",
- "lint:circular": "dpdm src/**/*.ts --warning false --tree false --exit-code circular:1 -T true --skip-dynamic-imports circular",
- "lint:md": "remark . --quiet --frail --output",
- "lint:mdx": "npm run workflow:mdx-with-lint && prettier -c --write \"{src,docs}/**/*.mdx\" && npm run workflow:mdx-with-lint",
+ "lint:circular": "dpdm src/**/*.ts --no-warning --no-tree --exit-code circular:1 --no-progress -T true --skip-dynamic-imports circular",
+ "lint:md": "remark . --silent --output",
+ "lint:mdx": "npm run workflow:mdx && remark \"docs/**/*.mdx\" -r ./.remarkrc.mdx.js --silent --output && eslint \"docs/**/*.mdx\" --quiet --fix",
"lint:style": "stylelint \"{src,tests}/**/*.{js,jsx,ts,tsx}\" --fix",
"lint:ts": "eslint \"{src,tests}/**/*.{js,jsx,ts,tsx}\" --fix",
"prepare": "husky",
@@ -65,19 +69,21 @@
"test:update": "vitest -u",
"type-check": "tsc --noEmit",
"webhook:ngrok": "ngrok http http://localhost:3011",
+ "workflow:cdn": "tsx ./scripts/cdnWorkflow/index.ts",
+ "workflow:changelog": "tsx ./scripts/changelogWorkflow/index.ts",
+ "workflow:countCharters": "tsx scripts/countEnWord.ts",
"workflow:docs": "tsx ./scripts/docsWorkflow/index.ts",
"workflow:i18n": "tsx ./scripts/i18nWorkflow/index.ts",
"workflow:mdx": "tsx ./scripts/mdxWorkflow/index.ts",
- "workflow:mdx-with-lint": "tsx ./scripts/mdxWorkflow/index.ts && eslint \"docs/**/*.mdx\" --quiet --fix",
"workflow:readme": "tsx ./scripts/readmeWorkflow/index.ts"
},
"lint-staged": {
"*.md": [
- "remark --quiet --output --",
+ "remark --silent --output --",
"prettier --write --no-error-on-unmatched-pattern"
],
"*.mdx": [
- "npm run workflow:mdx",
+ "remark -r ./.remarkrc.mdx.js --silent --output --",
"eslint --quiet --fix"
],
"*.json": [
@@ -99,214 +105,245 @@
]
},
"dependencies": {
- "@ant-design/icons": "^5.4.0",
- "@ant-design/pro-components": "^2.7.10",
- "@anthropic-ai/sdk": "^0.27.0",
- "@auth/core": "^0.34.2",
- "@aws-sdk/client-bedrock-runtime": "^3.637.0",
- "@aws-sdk/client-s3": "^3.637.0",
- "@aws-sdk/s3-request-presigner": "^3.637.0",
- "@azure/core-rest-pipeline": "1.16.0",
- "@azure/openai": "1.0.0-beta.12",
- "@cfworker/json-schema": "^2.0.0",
- "@chevrotain/regexp-to-ast": "^11.0.3",
- "@clerk/localizations": "^3.0.4",
- "@clerk/nextjs": "^5.3.3",
- "@clerk/themes": "^2.1.27",
- "@codesandbox/sandpack-react": "^2.19.8",
- "@cyntler/react-doc-viewer": "^1.16.6",
- "@google/generative-ai": "^0.16.0",
+ "@ant-design/icons": "^5.5.2",
+ "@ant-design/pro-components": "^2.8.3",
+ "@anthropic-ai/sdk": "^0.39.0",
+ "@auth/core": "^0.38.0",
+ "@aws-sdk/client-bedrock-runtime": "^3.723.0",
+ "@aws-sdk/client-s3": "^3.723.0",
+ "@aws-sdk/s3-request-presigner": "^3.723.0",
+ "@azure-rest/ai-inference": "1.0.0-beta.5",
+ "@azure/core-auth": "^1.9.0",
+ "@cfworker/json-schema": "^4.1.0",
+ "@clerk/localizations": "^3.9.6",
+ "@clerk/nextjs": "^6.10.6",
+ "@clerk/themes": "^2.2.4",
+ "@codesandbox/sandpack-react": "^2.19.10",
+ "@cyntler/react-doc-viewer": "^1.17.0",
+ "@electric-sql/pglite": "0.2.17",
+ "@google-cloud/vertexai": "^1.9.2",
+ "@google/generative-ai": "^0.24.0",
+ "@huggingface/inference": "^2.8.1",
"@icons-pack/react-simple-icons": "9.6.0",
- "@khmyznikov/pwa-install": "^0.3.9",
- "@langchain/community": "^0.2.31",
+ "@khmyznikov/pwa-install": "0.3.9",
+ "@langchain/community": "^0.3.22",
+ "@lobechat/web-crawler": "workspace:*",
+ "@lobehub/charts": "^1.12.0",
"@lobehub/chat-plugin-sdk": "^1.32.4",
"@lobehub/chat-plugins-gateway": "^1.9.0",
- "@lobehub/icons": "^1.33.7",
- "@lobehub/tts": "^1.24.3",
- "@lobehub/ui": "1.150.3",
- "@neondatabase/serverless": "^0.9.4",
- "@next/third-parties": "^14.2.6",
- "@react-spring/web": "^9.7.3",
- "@sentry/nextjs": "^7.119.0",
- "@serwist/next": "^9.0.8",
- "@t3-oss/env-nextjs": "^0.11.0",
- "@tanstack/react-query": "^5.52.1",
+ "@lobehub/icons": "^1.73.1",
+ "@lobehub/tts": "^1.28.0",
+ "@lobehub/ui": "^1.165.5",
+ "@neondatabase/serverless": "^0.10.4",
+ "@next/third-parties": "^15.2.0",
+ "@react-spring/web": "^9.7.5",
+ "@sentry/nextjs": "^7.120.2",
+ "@serwist/next": "^9.0.11",
+ "@t3-oss/env-nextjs": "^0.12.0",
+ "@tanstack/react-query": "^5.62.16",
"@trpc/client": "next",
"@trpc/next": "next",
"@trpc/react-query": "next",
"@trpc/server": "next",
- "@vercel/analytics": "^1.3.1",
- "@vercel/edge-config": "^1.2.1",
- "@vercel/speed-insights": "^1.0.12",
- "ahooks": "^3.8.1",
- "ai": "^3.3.16",
- "antd": "^5.20.2",
- "antd-style": "^3.6.2",
- "axios": "^1.7.9",
+ "@vercel/analytics": "^1.4.1",
+ "@vercel/edge-config": "^1.4.0",
+ "@vercel/functions": "^2",
+ "@vercel/speed-insights": "^1.1.0",
+ "ahooks": "^3.8.4",
+ "ai": "^3.4.33",
+ "antd": "^5.23.0",
+ "antd-style": "^3.7.1",
"brotli-wasm": "^3.0.1",
- "chroma-js": "^2.6.0",
- "csv-string": "^4.1.1",
- "csv-stringify": "^6.5.2",
+ "chroma-js": "^3.1.2",
+ "countries-and-timezones": "^3.7.2",
"dayjs": "^1.11.13",
- "debug": "^4.3.6",
+ "debug": "^4.4.0",
"dexie": "^3.2.7",
- "diff": "^5.2.0",
- "drizzle-orm": "^0.33.0",
+ "diff": "^7.0.0",
+ "drizzle-orm": "^0.40.0",
"drizzle-zod": "^0.5.1",
+ "epub2": "^3.0.2",
"fast-deep-equal": "^3.1.3",
- "file-type": "^19.4.1",
- "framer-motion": "^11.2.6",
- "gpt-tokenizer": "^2.2.1",
- "i18next": "^23.14.0",
- "i18next-browser-languagedetector": "^7.2.1",
+ "file-type": "^20.0.0",
+ "framer-motion": "^12.0.0",
+ "gpt-tokenizer": "^2.8.1",
+ "html-to-text": "^9.0.5",
+ "i18next": "^24.2.1",
+ "i18next-browser-languagedetector": "^8.0.2",
"i18next-resources-to-backend": "^1.2.1",
"idb-keyval": "^6.2.1",
"immer": "^10.1.1",
- "ip": "^2.0.1",
- "jose": "^5.7.0",
+ "jose": "^5.10.0",
"js-sha256": "^0.11.0",
"jsonl-parse-stringify": "^1.0.3",
- "langchain": "^0.2.17",
- "langfuse": "^3.19.0",
- "langfuse-core": "^3.19.0",
+ "langchain": "^0.3.10",
+ "langfuse": "3.29.1",
+ "langfuse-core": "3.29.1",
"lodash-es": "^4.17.21",
- "lucide-react": "latest",
- "mammoth": "^1.8.0",
- "modern-screenshot": "^4.4.39",
- "nanoid": "^5.0.7",
- "next": "14.2.8",
+ "lucide-react": "^0.479.0",
+ "mammoth": "^1.9.0",
+ "mdast-util-to-markdown": "^2.1.2",
+ "modern-screenshot": "^4.5.5",
+ "nanoid": "^5.0.9",
+ "next": "^15.2.0",
"next-auth": "beta",
- "next-mdx-remote": "^4.4.1",
- "nextjs-toploader": "^3.6.15",
+ "next-mdx-remote": "^5.0.0",
+ "nextjs-toploader": "^3.7.15",
"numeral": "^2.0.6",
- "nuqs": "^1.17.8",
- "officeparser": "^4.1.1",
- "ollama": "^0.5.8",
- "openai": "^4.56.0",
- "openapi-fetch": "^0.9.7",
+ "nuqs": "^1.20.0",
+ "officeparser": "^5.1.1",
+ "ollama": "^0.5.11",
+ "openai": "^4.77.3",
+ "openapi-fetch": "^0.9.8",
"partial-json": "^0.1.7",
"pdf-parse": "^1.1.1",
- "pdfjs-dist": "4.4.168",
- "pg": "^8.12.0",
- "pino": "^9.3.2",
+ "pdfjs-dist": "4.8.69",
+ "pg": "^8.13.1",
+ "pino": "^9.6.0",
+ "plaiceholder": "^3.0.0",
"polished": "^4.3.1",
- "posthog-js": "^1.157.2",
- "pwa-install-handler": "^2.6.0",
- "query-string": "^9.1.0",
+ "posthog-js": "^1.205.0",
+ "pwa-install-handler": "^2.6.2",
+ "query-string": "^9.1.1",
"random-words": "^2.0.1",
- "react": "^18.3.1",
- "react-confetti": "^6.1.0",
- "react-dom": "^18.3.1",
+ "react": "^19.0.0",
+ "react-confetti": "^6.2.2",
+ "react-dom": "^19.0.0",
"react-fast-marquee": "^1.6.5",
- "react-hotkeys-hook": "^4.5.0",
- "react-i18next": "14.0.2",
- "react-layout-kit": "^1.9.0",
+ "react-hotkeys-hook": "^4.6.1",
+ "react-i18next": "^15.4.0",
+ "react-layout-kit": "^1.9.1",
"react-lazy-load": "^4.0.1",
- "react-pdf": "^9.1.0",
- "react-virtuoso": "^4.10.1",
+ "react-pdf": "^9.2.1",
+ "react-rnd": "^10.4.14",
+ "react-scan": "^0.2.0",
+ "react-virtuoso": "^4.12.3",
"react-wrap-balancer": "^1.1.1",
- "remark": "^14.0.3",
- "remark-gfm": "^3.0.1",
- "remark-html": "^15.0.2",
+ "remark": "^15.0.1",
+ "remark-gfm": "^4.0.0",
+ "remark-html": "^16.0.1",
"request-filtering-agent": "^2.0.1",
- "resolve-accept-language": "^3.1.5",
+ "resolve-accept-language": "^3.1.10",
"rtl-detect": "^1.1.2",
"semver": "^7.6.3",
"sharp": "^0.33.5",
- "shiki": "1.17.7",
- "stripe": "^15.8.0",
- "superjson": "^2.2.1",
- "svix": "^1.30.0",
- "swr": "^2.2.5",
+ "shiki": "^1.26.1",
+ "stripe": "^16.12.0",
+ "superjson": "^2.2.2",
+ "svix": "^1.59.1",
+ "swr": "^2.3.0",
"systemjs": "^6.15.1",
"ts-md5": "^1.3.1",
- "ua-parser-js": "^1.0.38",
- "unstructured-client": "^0.16.0",
+ "ua-parser-js": "^1.0.40",
+ "unstructured-client": "^0.19.0",
"url-join": "^5.0.0",
"use-merge-value": "^1.2.0",
"utility-types": "^3.11.0",
- "uuid": "^10.0.0",
+ "uuid": "^11.0.4",
"ws": "^8.18.0",
"y-protocols": "^1.0.6",
"y-webrtc": "^10.3.0",
- "yaml": "^2.5.0",
- "yjs": "^13.6.18",
+ "yaml": "^2.7.0",
+ "yjs": "^13.6.21",
"zod": "^3.24.1",
- "zustand": "^4.5.5",
- "zustand-utils": "^1.3.2"
+ "zustand": "^5.0.3",
+ "zustand-utils": "^2"
},
"devDependencies": {
- "@commitlint/cli": "^19.4.0",
- "@edge-runtime/vm": "^4.0.2",
- "@lobehub/i18n-cli": "^1.19.1",
- "@lobehub/lint": "^1.24.4",
- "@lobehub/seo-cli": "^1.4.2",
- "@next/bundle-analyzer": "^14.2.6",
- "@next/eslint-plugin-next": "^14.2.6",
+ "@commitlint/cli": "^19.6.1",
+ "@edge-runtime/vm": "^5.0.0",
+ "@huggingface/tasks": "^0.15.0",
+ "@lobehub/i18n-cli": "^1.20.3",
+ "@lobehub/lint": "^1.25.5",
+ "@lobehub/seo-cli": "^1.4.3",
+ "@next/bundle-analyzer": "^15.2.0",
+ "@next/eslint-plugin-next": "^15.2.0",
"@peculiar/webcrypto": "^1.5.0",
- "@testing-library/jest-dom": "^6.4.8",
- "@testing-library/react": "^16.0.0",
- "@types/axios": "^0.14.4",
- "@types/chroma-js": "^2.4.4",
+ "@semantic-release/exec": "^6.0.3",
+ "@testing-library/jest-dom": "^6.6.3",
+ "@testing-library/react": "^16.1.0",
+ "@testing-library/user-event": "^14.6.1",
+ "@types/chroma-js": "^3.1.0",
+ "@types/crypto-js": "^4.2.2",
"@types/debug": "^4.1.12",
- "@types/diff": "^5.2.1",
+ "@types/diff": "^7.0.0",
+ "@types/fs-extra": "^11.0.4",
"@types/ip": "^1.1.3",
"@types/json-schema": "^7.0.15",
- "@types/lodash": "^4.17.7",
+ "@types/lodash": "^4.17.14",
"@types/lodash-es": "^4.17.12",
- "@types/node": "^20.16.1",
+ "@types/node": "^22.10.5",
"@types/numeral": "^2.0.5",
- "@types/pg": "^8.11.6",
- "@types/react": "^18.3.4",
- "@types/react-dom": "^18.3.0",
+ "@types/pg": "^8.11.10",
+ "@types/react": "^19.0.10",
+ "@types/react-dom": "^19.0.4",
"@types/rtl-detect": "^1.0.3",
"@types/semver": "^7.5.8",
- "@types/systemjs": "^6.13.5",
+ "@types/systemjs": "^6.15.1",
"@types/ua-parser-js": "^0.7.39",
"@types/unist": "^3.0.3",
"@types/uuid": "^10.0.0",
- "@types/ws": "^8.5.12",
+ "@types/ws": "^8.5.13",
"@vitest/coverage-v8": "~1.2.2",
"ajv-keywords": "^5.1.0",
- "commitlint": "^19.4.0",
- "consola": "^3.2.3",
- "dotenv": "^16.4.5",
- "dpdm": "^3.14.0",
- "drizzle-kit": "^0.24.0",
- "eslint": "^8.57.0",
- "eslint-plugin-mdx": "^2.3.4",
- "eslint-plugin-unused-imports": "4.0.1",
+ "commitlint": "^19.6.1",
+ "consola": "^3.3.3",
+ "crypto-js": "^4.2.0",
+ "dotenv": "^16.4.7",
+ "dpdm-fast": "^1.0.7",
+ "drizzle-kit": "^0.30.1",
+ "eslint": "^8.57.1",
+ "eslint-plugin-mdx": "^3.1.5",
"fake-indexeddb": "^6.0.0",
+ "fs-extra": "^11.2.0",
"glob": "^11.0.0",
"gray-matter": "^4.0.3",
- "happy-dom": "^15.0.0",
- "husky": "^9.1.5",
+ "happy-dom": "^17.0.0",
+ "husky": "^9.1.7",
"just-diff": "^6.0.2",
- "lint-staged": "^15.2.9",
+ "lint-staged": "^15.3.0",
"lodash": "^4.17.21",
- "markdown-table": "^3.0.3",
+ "markdown-table": "^3.0.4",
+ "markdown-to-txt": "^2.0.1",
+ "mime": "^4.0.6",
"node-fetch": "^3.3.2",
- "node-gyp": "^10.2.0",
- "openapi-typescript": "^6.7.6",
- "p-map": "^7.0.2",
- "prettier": "^3.3.3",
- "remark-cli": "^11.0.0",
- "remark-parse": "^10.0.2",
+ "node-gyp": "^11.0.0",
+ "openapi-typescript": "^7.5.2",
+ "p-map": "^7.0.3",
+ "prettier": "^3.4.2",
+ "remark-cli": "^12.0.1",
+ "remark-frontmatter": "^5.0.0",
+ "remark-mdx": "^3.1.0",
+ "remark-parse": "^11.0.0",
"semantic-release": "^21.1.2",
- "serwist": "^9.0.8",
+ "serwist": "^9.0.11",
"stylelint": "^15.11.0",
- "supports-color": "8",
- "tsx": "^4.17.0",
- "typescript": "^5.5.4",
+ "tsx": "^4.19.2",
+ "typescript": "^5.7.2",
"unified": "^11.0.5",
"unist-util-visit": "^5.0.0",
- "vite": "^5.4.2",
+ "vite": "^5.4.11",
"vitest": "~1.2.2",
"vitest-canvas-mock": "^0.3.3"
},
- "packageManager": "pnpm@9.15.0",
+ "packageManager": "pnpm@9.15.7",
"publishConfig": {
"access": "public",
"registry": "https://registry.npmjs.org"
+ },
+ "pnpm": {
+ "overrides": {
+ "mdast-util-gfm-autolink-literal": "2.0.0"
+ },
+ "packageExtensions": {
+ "@inkjs/ui": {
+ "dependencies": {
+ "react": "^18"
+ }
+ }
+ }
+ },
+ "overrides": {
+ "mdast-util-gfm-autolink-literal": "2.0.0"
}
}
diff --git a/DigitalHumanWeb/packages/web-crawler/README.md b/DigitalHumanWeb/packages/web-crawler/README.md
new file mode 100644
index 0000000..d21e9bc
--- /dev/null
+++ b/DigitalHumanWeb/packages/web-crawler/README.md
@@ -0,0 +1,61 @@
+# @lobechat/web-crawler
+
+LobeChat's built-in web crawling module for intelligent extraction of web content and conversion to Markdown format.
+
+## 📝 Introduction
+
+`@lobechat/web-crawler` is a core component of LobeChat responsible for intelligent web content crawling and processing. It extracts valuable content from various webpages, filters out distracting elements, and generates structured Markdown text.
+
+## 🛠️ Core Features
+
+- **Intelligent Content Extraction**: Identifies main content based on Mozilla Readability algorithm
+- **Multi-level Crawling Strategy**: Supports multiple crawling implementations including basic crawling, Jina, and Browserless rendering
+- **Custom URL Rules**: Handles specific website crawling logic through a flexible rule system
+
+## 🤝 Contribution
+
+Web structures are diverse and complex. We welcome community contributions for specific website crawling rules. You can participate in improvements through:
+
+### How to Contribute URL Rules
+
+1. Add new rules to the [urlRules.ts](https://github.com/lobehub/lobe-chat/blob/main/packages/web-crawler/src/urlRules.ts) file
+2. Rule example:
+
+```typescript
+// Example: handling specific websites
+const url = [
+ // ... other URL matching rules
+ {
+ // URL matching pattern, supports regex
+ urlPattern: 'https://example.com/articles/(.*)',
+
+ // Optional: URL transformation, redirects to an easier-to-crawl version
+ urlTransform: 'https://example.com/print/$1',
+
+ // Optional: specify crawling implementation, supports 'naive', 'jina', and 'browserless'
+ impls: ['naive', 'jina', 'browserless'],
+
+ // Optional: content filtering configuration
+ filterOptions: {
+ // Whether to enable Readability algorithm for filtering distracting elements
+ enableReadability: true,
+ // Whether to convert to plain text
+ pureText: false,
+ },
+ },
+];
+```
+
+### Rule Submission Process
+
+1. Fork the [LobeChat repository](https://github.com/lobehub/lobe-chat)
+2. Add or modify URL rules
+3. Submit a Pull Request describing:
+
+- Target website characteristics
+- Problems solved by the rule
+- Test cases (example URLs)
+
+## 📌 Note
+
+This is an internal module of LobeHub (`"private": true`), designed specifically for LobeChat and not published as a standalone package.
diff --git a/DigitalHumanWeb/packages/web-crawler/README.zh-CN.md b/DigitalHumanWeb/packages/web-crawler/README.zh-CN.md
new file mode 100644
index 0000000..c480cc6
--- /dev/null
+++ b/DigitalHumanWeb/packages/web-crawler/README.zh-CN.md
@@ -0,0 +1,61 @@
+# @lobechat/web-crawler
+
+LobeChat 内置的网页抓取模块,用于智能提取网页内容并转换为 Markdown 格式。
+
+## 📝 简介
+
+`@lobechat/web-crawler` 是 LobeChat 的核心组件,负责网页内容的智能抓取与处理。它能够从各类网页中提取有价值的内容,过滤掉干扰元素,并生成结构化的 Markdown 文本。
+
+## 🛠️ 核心功能
+
+- **智能内容提取**:基于 Mozilla Readability 算法识别主要内容
+- **多级抓取策略**:支持多种抓取实现,包括基础抓取、Jina 和 Browserless 渲染抓取
+- **自定义 URL 规则**:通过灵活的规则系统处理特定网站的抓取逻辑
+
+## 🤝 参与共建
+
+网页结构多样复杂,我们欢迎社区贡献特定网站的抓取规则。您可以通过以下方式参与改进:
+
+### 如何贡献 URL 规则
+
+1. 在 [urlRules.ts](https://github.com/lobehub/lobe-chat/blob/main/packages/web-crawler/src/urlRules.ts) 文件中添加新规则
+2. 规则示例:
+
+```typescript
+// 示例:处理特定网站
+const url = [
+ // ... 其他 url 匹配规则
+ {
+ // URL 匹配模式,仅支持正则表达式
+ urlPattern: 'https://example.com/articles/(.*)',
+
+ // 可选:URL 转换,用于重定向到更易抓取的版本
+ urlTransform: 'https://example.com/print/$1',
+
+ // 可选:指定抓取实现方式,支持 'naive'、'jina' 和 'browserless' 三种
+ impls: ['naive', 'jina', 'browserless'],
+
+ // 可选:内容过滤配置
+ filterOptions: {
+ // 是否启用 Readability 算法,用于过滤干扰元素
+ enableReadability: true,
+ // 是否转换为纯文本
+ pureText: false,
+ },
+ },
+];
+```
+
+### 规则提交流程
+
+1. Fork [LobeChat 仓库](https://github.com/lobehub/lobe-chat)
+2. 添加或修改 URL 规则
+3. 提交 Pull Request 并描述:
+
+- 目标网站特点
+- 规则解决的问题
+- 测试用例(示例 URL)
+
+## 📌 注意事项
+
+这是 LobeHub 的内部模块(`"private": true`),专为 LobeChat 设计,不作为独立包发布使用。
diff --git a/DigitalHumanWeb/packages/web-crawler/package.json b/DigitalHumanWeb/packages/web-crawler/package.json
new file mode 100644
index 0000000..692c0b0
--- /dev/null
+++ b/DigitalHumanWeb/packages/web-crawler/package.json
@@ -0,0 +1,14 @@
+{
+ "name": "@lobechat/web-crawler",
+ "version": "1.0.0",
+ "private": true,
+ "main": "src/index.ts",
+ "types": "src/index.ts",
+ "dependencies": {
+ "@mozilla/readability": "^0.6.0",
+ "happy-dom": "^17.0.0",
+ "node-html-markdown": "^1.3.0",
+ "query-string": "^9.1.1",
+ "url-join": "^5"
+ }
+}
diff --git a/DigitalHumanWeb/packages/web-crawler/src/__tests__/crawler.test.ts b/DigitalHumanWeb/packages/web-crawler/src/__tests__/crawler.test.ts
new file mode 100644
index 0000000..a7868f7
--- /dev/null
+++ b/DigitalHumanWeb/packages/web-crawler/src/__tests__/crawler.test.ts
@@ -0,0 +1,207 @@
+import { describe, expect, it, vi } from 'vitest';
+
+import { Crawler } from '../crawler';
+
+// Move mocks outside of test cases to avoid hoisting issues
+vi.mock('../crawImpl', () => ({
+ crawlImpls: {
+ naive: vi.fn(),
+ jina: vi.fn(),
+ browserless: vi.fn(),
+ },
+}));
+
+vi.mock('../utils/appUrlRules', () => ({
+ applyUrlRules: vi.fn().mockReturnValue({
+ transformedUrl: 'https://example.com',
+ filterOptions: {},
+ }),
+}));
+
+describe('Crawler', () => {
+ const crawler = new Crawler();
+
+ it('should crawl successfully with default impls', async () => {
+ const mockResult = {
+ content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
+ contentType: 'text' as const,
+ url: 'https://example.com',
+ };
+
+ const { crawlImpls } = await import('../crawImpl');
+ vi.mocked(crawlImpls.naive).mockResolvedValue(mockResult);
+
+ const result = await crawler.crawl({
+ url: 'https://example.com',
+ });
+
+ expect(result).toEqual({
+ crawler: 'naive',
+ data: mockResult,
+ originalUrl: 'https://example.com',
+ transformedUrl: undefined,
+ });
+ });
+
+ it('should use user provided impls', async () => {
+ const mockResult = {
+ content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
+ contentType: 'text' as const,
+ url: 'https://example.com',
+ };
+
+ const { crawlImpls } = await import('../crawImpl');
+ vi.mocked(crawlImpls.jina).mockResolvedValue(mockResult);
+
+ const result = await crawler.crawl({
+ impls: ['jina'],
+ url: 'https://example.com',
+ });
+
+ expect(result).toEqual({
+ crawler: 'jina',
+ data: mockResult,
+ originalUrl: 'https://example.com',
+ transformedUrl: undefined,
+ });
+ });
+
+ it('should handle crawl errors', async () => {
+ const mockError = new Error('Crawl failed');
+ mockError.name = 'CrawlError';
+
+ const { crawlImpls } = await import('../crawImpl');
+ vi.mocked(crawlImpls.naive).mockRejectedValue(mockError);
+ vi.mocked(crawlImpls.jina).mockRejectedValue(mockError);
+ vi.mocked(crawlImpls.browserless).mockRejectedValue(mockError);
+
+ const result = await crawler.crawl({
+ url: 'https://example.com',
+ });
+
+ expect(result).toEqual({
+ crawler: 'browserless',
+ data: {
+ content: 'Fail to crawl the page. Error type: CrawlError, error message: Crawl failed',
+ errorMessage: 'Crawl failed',
+ errorType: 'CrawlError',
+ },
+ originalUrl: 'https://example.com',
+ transformedUrl: undefined,
+ });
+ });
+
+ it('should handle transformed urls', async () => {
+ const mockResult = {
+ content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
+ contentType: 'text' as const,
+ url: 'https://transformed.example.com',
+ };
+
+ const { crawlImpls } = await import('../crawImpl');
+ vi.mocked(crawlImpls.naive).mockResolvedValue(mockResult);
+
+ const { applyUrlRules } = await import('../utils/appUrlRules');
+ vi.mocked(applyUrlRules).mockReturnValue({
+ transformedUrl: 'https://transformed.example.com',
+ filterOptions: {},
+ });
+
+ const result = await crawler.crawl({
+ url: 'https://example.com',
+ });
+
+ expect(result).toEqual({
+ crawler: 'naive',
+ data: mockResult,
+ originalUrl: 'https://example.com',
+ transformedUrl: 'https://transformed.example.com',
+ });
+ });
+
+ it('should merge filter options correctly', async () => {
+ const mockResult = {
+ content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
+ contentType: 'text' as const,
+ url: 'https://example.com',
+ };
+
+ const { crawlImpls } = await import('../crawImpl');
+ const mockCrawlImpl = vi.mocked(crawlImpls.naive).mockResolvedValue(mockResult);
+
+ const { applyUrlRules } = await import('../utils/appUrlRules');
+ vi.mocked(applyUrlRules).mockReturnValue({
+ transformedUrl: 'https://example.com',
+ filterOptions: { pureText: true },
+ });
+
+ await crawler.crawl({
+ url: 'https://example.com',
+ filterOptions: { enableReadability: true },
+ });
+
+ expect(mockCrawlImpl).toHaveBeenCalledWith('https://example.com', {
+ filterOptions: {
+ pureText: true,
+ enableReadability: true,
+ },
+ });
+ });
+
+ it('should use rule impls when provided', async () => {
+ const mockResult = {
+ content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
+ contentType: 'text' as const,
+ url: 'https://example.com',
+ };
+
+ const { crawlImpls } = await import('../crawImpl');
+ vi.mocked(crawlImpls.jina).mockResolvedValue(mockResult);
+
+ const { applyUrlRules } = await import('../utils/appUrlRules');
+ vi.mocked(applyUrlRules).mockReturnValue({
+ transformedUrl: 'https://example.com',
+ filterOptions: {},
+ impls: ['jina'],
+ });
+
+ const result = await crawler.crawl({
+ url: 'https://example.com',
+ });
+
+ expect(result).toEqual({
+ crawler: 'jina',
+ data: mockResult,
+ originalUrl: 'https://example.com',
+ transformedUrl: undefined,
+ });
+ });
+
+ it('should skip results with content length <= 100', async () => {
+ const mockResult = {
+ content: 'short content', // Content length <= 100
+ contentType: 'text' as const,
+ url: 'https://example.com',
+ };
+
+ const { crawlImpls } = await import('../crawImpl');
+ vi.mocked(crawlImpls.naive).mockResolvedValue(mockResult);
+ vi.mocked(crawlImpls.jina).mockResolvedValue(mockResult);
+ vi.mocked(crawlImpls.browserless).mockResolvedValue(mockResult);
+
+ const result = await crawler.crawl({
+ url: 'https://example.com',
+ });
+
+ expect(result).toEqual({
+ crawler: undefined,
+ data: {
+ content: 'Fail to crawl the page. Error type: UnknownError, error message: undefined',
+ errorMessage: undefined,
+ errorType: 'UnknownError',
+ },
+ originalUrl: 'https://example.com',
+ transformedUrl: undefined,
+ });
+ });
+});
diff --git a/DigitalHumanWeb/packages/web-crawler/src/crawImpl/__tests__/browserless.test.ts b/DigitalHumanWeb/packages/web-crawler/src/crawImpl/__tests__/browserless.test.ts
new file mode 100644
index 0000000..03d8e88
--- /dev/null
+++ b/DigitalHumanWeb/packages/web-crawler/src/crawImpl/__tests__/browserless.test.ts
@@ -0,0 +1,94 @@
+import { describe, expect, it, vi } from 'vitest';
+
+import { browserless } from '../browserless';
+
+describe('browserless', () => {
+ it('should throw BrowserlessInitError when env vars not set', async () => {
+ const originalEnv = { ...process.env };
+ process.env = { ...originalEnv };
+ delete process.env.BROWSERLESS_URL;
+ delete process.env.BROWSERLESS_TOKEN;
+
+ await expect(browserless('https://example.com', { filterOptions: {} })).rejects.toThrow(
+ '`BROWSERLESS_URL` or `BROWSERLESS_TOKEN` are required',
+ );
+
+ process.env = originalEnv;
+ });
+
+ it('should return undefined on fetch error', async () => {
+ process.env.BROWSERLESS_TOKEN = 'test-token';
+ global.fetch = vi.fn().mockRejectedValue(new Error('Fetch error'));
+
+ const result = await browserless('https://example.com', { filterOptions: {} });
+ expect(result).toBeUndefined();
+ });
+
+ it('should return undefined when content is empty', async () => {
+ process.env.BROWSERLESS_TOKEN = 'test-token';
+ global.fetch = vi.fn().mockResolvedValue({
+ text: vi.fn().mockResolvedValue(''),
+ } as any);
+
+ const result = await browserless('https://example.com', { filterOptions: {} });
+ expect(result).toBeUndefined();
+ });
+
+ it('should return undefined when title is "Just a moment..."', async () => {
+ process.env.BROWSERLESS_TOKEN = 'test-token';
+ global.fetch = vi.fn().mockResolvedValue({
+ text: vi.fn().mockResolvedValue('Just a moment...'),
+ } as any);
+
+ const result = await browserless('https://example.com', { filterOptions: {} });
+ expect(result).toBeUndefined();
+ });
+
+ it('should return crawl result on successful fetch', async () => {
+ process.env.BROWSERLESS_TOKEN = 'test-token';
+ global.fetch = vi.fn().mockResolvedValue({
+ text: vi.fn().mockResolvedValue(`
+
+
+ Test Title
+
+
+
+
+ Welcome to LobeHub! Please carefully read the following Terms of Use (hereinafter
+ referred to as the "Agreement"). This Agreement constitutes a legally binding
+ agreement between You and LobeHub regarding the access and use of the LobeHub
+ software applications, services, and websites (collectively referred to as the
+ "Services").
+
+
+ By accessing or using the Services in any way, You acknowledge that You have read,
+ understood, and agreed to be bound by all the terms of this Agreement. If You do not
+ agree to any part of this Agreement, You are not permitted to continue accessing or
+ using the Services.
+
+
+ Definitions
+
+
+ The words of which the initial letter is capitalized have meanings defined under the
+ following conditions. The following definitions shall have the same meaning
+ regardless of whether they appear in singular or in plural.
+
+
+
+ Affiliate means an entity that controls, is controlled by or is
+ under common control with a party, where "control" means ownership of 50% or more
+ of the shares, equity interest or other securities entitled to vote for election
+ of directors or other managing authority.
+
+
Agreement means this Terms of Use Agreement.
+
+ Company (referred to as either "the Company", "We", "Us" or "Our"
+ in this Agreement) refers to LobeHub LLC.
+
+
+ Service means the LobeHub software applications, services, and
+ website.
+
+
+ You means the individual accessing or using the Services, or the
+ company, or other legal entity on behalf of which such individual is accessing or
+ using the Services, as applicable.
+
+
+
+ Our Services
+
+
+ LobeHub provides a platform and interface that enables users to interact with
+ artificial intelligence technologies, including but not limited to natural language
+ processing models or content generation models developed independently or provided
+ by third parties such as Google, Microsoft, OpenAI, and other commercial companies
+ as well as open-source communities. The Service facilitates functions such as
+ information retrieval, content creation, and automation through user interaction
+ with AI systems. Additionally, it utilizes cloud technology to provide capabilities
+ like data synchronization, vector data storage, server-side functionalities, etc.,
+ to enhance the interactive experience with AI models.
+
+
+ Eligibility
+
+
+ By accessing or using the Services, You represent and warrant to the Company that
+ You: (1)Are of legal age (18 years and above). (2)Have legal capacity and agree to
+ abide by these terms. (3)Will use the Services in accordance with this Agreement and
+ all applicable laws. (4)Will not use the Services for any illegal, harmful,
+ dangerous, or offensive purposes.
+
+
Examples of prohibited activities include but are not limited to:
+
+
Illegal activities
+
Infringement of intellectual property rights
+
Generating harmful, unsafe, deceptive, or illegal content
+
Impersonation, fraud
+
+
+ If You do not comply with the usage conditions, We reserve the right to suspend or
+ terminate Your account and refuse any and all current or future use of the Services
+ (or any part thereof).
+
+
+ Account Registration
+
+
+ To access the Services, You must register an account by providing true, accurate,
+ up-to-date, and complete information. You are solely responsible for all activities
+ that occur under Your account, including maintaining the security of Your account
+ and restricting access. You must immediately notify LobeHub of any unauthorized
+ account use or other security breaches.
+
+
+ Please ensure to keep Your password secure and take responsibility for all use of
+ Your account and password. If We deem the chosen username inappropriate, containing
+ obscene content, or otherwise offensive, We reserve the right to delete, revoke, or
+ modify that username.
+
+
+ Purchases and Payments
+
+
+ You agree to provide current, complete, and accurate purchase and account
+ information for all purchases made using the Services. You also agree to promptly
+ update Your account and payment information, including email address, payment
+ method, and payment card expiration date, to allow us to complete Your transactions
+ and contact You when necessary. Sales tax will be added to the purchase price as
+ required by law.
+
+
+ You agree to pay all charges at the current purchase price and authorize us to
+ charge any such amounts to Your chosen payment provider at the time of purchase. If
+ Your order requires recurring charges, You agree that We may charge Your payment
+ method on a recurring basis at the specified intervals without obtaining prior
+ approval for each recurring charge until the relevant order is canceled. We reserve
+ the right to correct any errors or pricing errors even after payment has been
+ requested or accepted.
+
+
+ We may utilize third-party payment processing services (such as Stripe) for payment
+ processing. You may use a valid card (credit or debit card) for payment, subject to
+ verification and authorization by Your card issuer. We will not be liable for any
+ delays or failure to provide Services resulting from payment failures due to
+ authorization issues or any reasons related to third-party payment providers.
+
+
+ We reserve the right to refuse or cancel Your order at any time for certain reasons,
+ including but not limited to: (1) Service availability, (2) errors in Service
+ description or pricing, (3) order errors, (4) suspected fraud or unauthorized or
+ illegal transactions. We reserve the right, at our sole discretion, to limit or
+ prohibit orders placed by dealers, resellers, or distributors.
+
+
+ Fee Changes
+
+
+ We reserve the right to adjust the Service fees at our discretion and at any time.
+ Any changes in fees will take effect immediately upon the change. Services that have
+ already been paid for and purchased will not be affected.
+
+
+ If Your order requires recurring automatic billing, the revised price will take
+ effect on the next billing cycle. We will notify You in advance of any fee
+ adjustments so that You have the opportunity to cancel the order before the
+ adjustment takes effect. If You do not cancel the order and continue to use the
+ Services, You agree to pay the revised fee amount.
+
+
+ Refunds
+
+
+ For Services that have been purchased but not used, We support refunds within 30
+ days of payment. However, for Services that have been used or purchased for more
+ than 30 days, We will not accept refund requests.
+
+
+ For subscription-based Services where partial usage has occurred, Your refund
+ request will be reviewed on a case-by-case basis, and the final decision on
+ approving the refund will be at the Company's discretion.
+
+
+ Content
+
+
+ Our Services allows You to generate and publish content. You are responsible for the
+ legality, reliability, and appropriateness of the content generated using the AI
+ ability. We do not assume responsibility for user-generated content on the Services.
+ You explicitly understand and agree that You are solely responsible for the content
+ You post and all activities conducted under Your account, whether by Yourself or by
+ third parties using Your account.
+
+
+ By generating and publishing content in the Services, You grant us the rights and
+ licenses necessary to use, modify, publicly perform, publicly display, copy, and
+ distribute such content within the Services. You retain full ownership of all
+ content created, published, or displayed within the Services and are responsible for
+ maintaining these rights. You agree that this license includes the permission for us
+ to provide Your content to other Service users for their use under these terms.
+ Additionally, You declare and warrant that: (1) the content is owned by You or You
+ have the legal right to use and authorize it to us under this agreement. (2) posting
+ the shared information in the Services will not infringe upon the privacy rights,
+ image rights, copyrights, contractual relationships, or other individual rights of
+ others.
+
+
+ All content generated by You is by default stored locally on the client-side, and
+ You are responsible for the storage and backup of Your content.
+
+
+ Additionally, We offer optional cloud sync content functionality. By using this
+ feature, You agree that We may retain complete and accurate copies of any content in
+ locations independent of the Services in our manner. However, We cannot guarantee
+ that data will not be lost or damaged. Data or content loss or damage can occur due
+ to various reasons, such as pre-existing damage before synchronization or changes
+ during synchronization.
+
+
+ We do not assume any responsibility for the security and integrity of content in the
+ event of content damage or loss under any circumstances.
+
+
+ Intellectual Property Rights
+
+
+ LobeHub reserves all rights to the technology, software, first-party content, and
+ data within the Services, including but not limited to patents, trademarks, trade
+ secrets, copyrights, and other intellectual property rights. Your permission to use
+ the Services does not grant You any ownership or title. You are not permitted to
+ copy, modify, adapt, translate, create derivative works, reverse engineer,
+ disassemble, or decompile the Services or any part thereof. If You wish to
+ participate in collaborative technical development, please engage through our GitHub
+ open-source community and adhere to the relevant open-source licenses.
+
+
+ Privacy and Security
+
+
+ LobeHub employs industry-standard technical, managerial, and physical security
+ measures to protect the security, confidentiality, and integrity of Your data.
+ However, We cannot guarantee that unauthorized access, hacking attacks, data loss,
+ or other breaches will never occur. LobeHub is not liable for any damages or
+ liabilities related to security incidents. Please refer to our Privacy Policy for
+ more detailed information.
+
+
+ Termination of Services
+
+
+ You may close Your account and cease using the Services at any time. In the event of
+ a violation of the terms of the agreement, LobeHub may immediately suspend or
+ terminate Your access to the Services. Upon termination, You will immediately lose
+ the right to access or use the Services. LobeHub will not be liable to You or any
+ third party for the termination of the Services.
+
+
+ Disclaimer of Warranties
+
+
+ The Services provided by LobeHub are provided on an "as-is" basis, and without any
+ form of guarantee. We explicitly disclaim all warranties, whether express, implied,
+ statutory, or otherwise, including but not limited to warranties of merchantability,
+ fitness for a particular purpose, and non-infringement. Your use of the Services is
+ at Your own risk.
+
+
+ Limitation of Liability
+
+
+ In no event shall LobeHub, its Affiliates, directors, employees, or agents be liable
+ for any direct, indirect, punitive, incidental, special, or consequential damages
+ arising from or related to Your use or inability to use the Services. This
+ limitation applies regardless of the basis or form of action.
+
+
+ Modification of Terms
+
+
+ We may revise this agreement periodically, and the new version of the agreement will
+ replace the previous version. We will indicate the "last updated" date at the
+ beginning and provide notice within the Services to inform You of significant
+ changes. It is Your responsibility to regularly review these legal terms to stay
+ informed of any updates. By continuing to use the Services after the revised legal
+ terms are posted, You will be deemed to have understood and accepted any changes to
+ the revised legal terms.
+
+
+ Governing Law and Jurisdiction
+
+
+ This agreement shall be governed by the laws of the State of Delaware, and You agree
+ to submit to the exclusive jurisdiction of the state and federal courts located in
+ Delaware for the resolution of any disputes related to this agreement or the
+ Services. You may also be required to comply with the laws of Your local
+ jurisdiction, state, country, or international laws when using the Services.
+
+
+ Conclusion
+
+
+ This agreement represents the entire agreement between You and LobeHub regarding the
+ use of the Services. It supersedes any prior agreements or understandings. The
+ failure of LobeHub to enforce any provision of this agreement does not constitute a
+ waiver of its rights.
+
+
+ By accessing or using the LobeHub Services, You acknowledge that You have read,
+ understood, and agreed to be bound by this agreement. If You have any questions
+ regarding this agreement, please contact us at
+ support@lobehub.com.
+