01 Llama3部署

Llama3部署
### 1. 配置环境
```python
conda create -n llama3 python=3.10
conda activate llama3
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia
```

### 2. 下载模型
由于在本地部署，使用官网的下载链接下载失败，所以去了modelscope下载了模型
```python
# 先下载git
conda install git-lfs
git-lfs install

# 再创建model目录拉取Meta-Llama-3-8B-Instruct
mkdir model
cd model
git clone https://www.modelscope.cn/LLM-Research/Meta-Llama-3-8B-Instruct.git
```

### 3. 部署Web Demo
最后安装提供的Web demo
```python

# 安装Web Demo
cd ~
git clone https://github.com/SmartFlowAI/Llama3-Tutorial

# 安装XTuner
git clone -b v0.1.18 https://github.com/InternLM/XTuner
cd CTuner
# 安装依赖项
pip install -e .
```

运行web_demo.py
```python
cd ~
git clone -b v0.1.18 https://github.com/InternLM/XTuner
cd XTuner
pip install -e .
```

运行成功
![[Pasted image 20240504232541.png]]![[Pasted image 20240504232607.png]]