|
|
---
|
|
|
title: Using Local Qwen Model in LobeChat
|
|
|
description: 通过LobeChat和Ollama的集成，您可以轻松在LobeChat中使用Qwen。本文将指导您如何在LobeChat中使用本地部署版本的Qwen。
|
|
|
tags:
|
|
|
- Qwen
|
|
|
- LobeChat
|
|
|
- Ollama
|
|
|
- 本地部署
|
|
|
- AI大模型
|
|
|
---
|
|
|
|
|
|
# Using the Local Qwen Model
|
|
|
|
|
|
<Image
|
|
|
alt={'Using Qwen in LobeChat'}
|
|
|
cover
|
|
|
src={'https://github.com/lobehub/lobe-chat/assets/17870709/b4a01219-e7b1-48a0-888c-f0271b18e3a6'}
|
|
|
/>
|
|
|
|
|
|
[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.
|
|
|
|
|
|
<Video src="https://github.com/lobehub/lobe-chat/assets/28616219/31e5f625-8dc4-4a5f-a5fd-d28d0457782d" />
|
|
|
|
|
|
Now, through the integration of LobeChat and [Ollama](https://ollama.com/), you can easily use Qwen in LobeChat. This document will guide you on how to use the local deployment version of Qwen in LobeChat:
|
|
|
|
|
|
<Steps>
|
|
|
## 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).
|
|
|
|
|
|
## 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:
|
|
|
|
|
|
```bash
|
|
|
ollama pull qwen:14b
|
|
|
```
|
|
|
|
|
|
<Callout type={'info'}>
|
|
|
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.
|
|
|
</Callout>
|
|
|
|
|
|
<Image
|
|
|
alt={'Use Ollama Pull Qwen Model'}
|
|
|
height={473}
|
|
|
inStep
|
|
|
src={'https://github.com/lobehub/lobe-chat/assets/1845053/fe34fdfe-c2e4-4d6a-84d7-4ebc61b2516a'}
|
|
|
/>
|
|
|
|
|
|
### Select the Qwen Model
|
|
|
|
|
|
In the LobeChat conversation page, open the model selection panel, and then select the Qwen model.
|
|
|
|
|
|
<Image
|
|
|
alt={'Choose Qwen Model'}
|
|
|
height={430}
|
|
|
inStep
|
|
|
src={'https://github.com/lobehub/lobe-chat/assets/28616219/e0608cca-f62f-414a-bc55-28a61ba21f14'}
|
|
|
/>
|
|
|
|
|
|
<Callout type={'info'}>
|
|
|
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.
|
|
|
|
|
|
</Callout>
|
|
|
</Steps>
|
|
|
|
|
|
Next, you can have a conversation with the local Qwen model in LobeChat.
|
