【书生·浦语大模型实战营】第2节：轻松玩转书生·浦语趣味Demo

【书生·浦语大模型实战营】第2节：轻松玩转书生·浦语趣味Demo

部署InternLM2-Chat-1.8B

内容：

• 环境配置
• 下载InternLM2-Chat-1.8B模型
• 部署本地Client Demo

1. 环境配置

   ## 配置环境
   studio-conda -o internlm-base -t demo
   # 或：
   # conda create -n demo python==3.10 -y
   # conda activate demo
   # conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia
   
   ## 进入环境
   conda activate demo
   
   ## 安装依赖
   pip install huggingface-hub==0.17.3
   pip install transformers==4.34 
   pip install psutil==5.9.8
   pip install accelerate==0.24.1
   pip install streamlit==1.32.2 
   pip install matplotlib==3.8.3 
   pip install modelscope==1.9.5
   pip install sentencepiece==0.1.99
   

2. 下载InternLM2-Chat-1.8B模型

   mkdir -p /root/demo
   touch /root/demo/cli_demo.py
   touch /root/demo/download_mini.py
   cd /root/demo
   

   进入所创建的文件夹，在download_mini.py文件中输入以下内容并保存。

   

   ## download_mini.py
   ## 下载模型参数
   import os
   from modelscope.hub.snapshot_download import snapshot_download
   
   # 创建保存模型目录
   os.system("mkdir /root/models")
   
   # save_dir是模型保存到本地的目录
   save_dir="/root/models"
   
   snapshot_download("Shanghai_AI_Laboratory/internlm2-chat-1_8b", 
                     cache_dir=save_dir, 
                     revision='v1.1.0')
   
   

   完成后在终端执行命令以下载模型参数文件

   python /root/demo/download_mini.py
   

   

3. 部署本地Client Demo

   在cli_demo.py中输入以下内容并保存

   ## cli_demo.py
   import torch
   from transformers import AutoTokenizer, AutoModelForCausalLM
   
   
   model_name_or_path = "/root/models/Shanghai_AI_Laboratory/internlm2-chat-1_8b"
   
   tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True, device_map='cuda:0')
   model = AutoModelForCausalLM.from_pretrained(model_name_or_path, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map='cuda:0')
   model = model.eval()
   
   system_prompt = """You are an AI assistant whose name is InternLM (书生·浦语).
   - InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.
   - InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文.
   """
   
   messages = [(system_prompt, '')]
   
   print("=============Welcome to InternLM chatbot, type 'exit' to exit.=============")
   
   while True:
       input_text = input("\nUser  >>> ")
       input_text = input_text.replace(' ', '')
       if input_text == "exit":
           break
   
       length = 0
       for response, _ in model.stream_chat(tokenizer, input_text, messages):
           if response is not None:
               print(response[length:], flush=True, end="")
               length = len(response)
   
   

   执行Demo，并等待模型加载完成

   conda activate demo
   python /root/demo/cli_demo.py
   

   完成后可以实现对话，输入exit可结束对话

   

部署八戒-Chat-1.8B

内容：

• 本模型为第一期实战营优秀作品
• 了解如何部署自定义模型

1. 环境配置

   conda activate demo
   
   # 获取项目文件
   cd /root/
   git clone https://gitee.com/InternLM/Tutorial -b camp2
   # git clone https://github.com/InternLM/Tutorial -b camp2
   cd /root/Tutorial
   

   下载完成后执行以下命令下载程序

   python /root/Tutorial/helloworld/bajie_download.py
   

2. 运行Chat-八戒 Demo

   运行命令

   streamlit run /root/Tutorial/helloworld/bajie_chat.py --server.address 127.0.0.1 --server.port 6006
   

   配置本地端口环境（本地打开服务器上的连接才需要）
   

   

   

运行Lagent Demo

内容：

• 进一步了解Lagent智能体
• 部署InternLM2-Chat-7B
• 体验与Lagent Demo的聊天互动

1. Lagent相关知识

   略

2. 部署InternLM2-Chat-7B

   ## 环境配置
   conda activate demo
   
   cd /root/demo
   
   git clone https://gitee.com/internlm/lagent.git
   # git clone https://github.com/internlm/lagent.git
   cd /root/demo/lagent
   git checkout 581d9fb8987a5d9b72bb9ebd37a95efd47d479ac
   pip install -e . # 源码安装
   

   若使用书生·浦语的开发机，则可使用share文件夹中的模型资源

   cd /root/demo/lagent
   
   # 构造软链接快捷访问方式
   ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b /root/models/internlm2-chat-7b
   

   若使用Huggingface_hub下载相关文件，可使用huggingface_hub包

   ## huggingface_hub包使用示例
   from huggingface_hub import hf_hub_download
   hf_hub_download(repo_id='internlm/internlm2-chat-7b',filename="config.json",local_dir='/root/test')
   

   

   

   完成后修改lagent下example/internlm2_agent_web_demo_huf.py文件，修改后如下所示

   

3. 与Lagent Demo互动
   运行命令

   streamlit run /root/demo/lagent/examples/internlm2_agent_web_demo_hf.py --server.address 127.0.0.1 --server.port 6006
   

   

部署InternLM-XComposer2

内容：

• 部署InternLM-XComposer2
• 尝试视觉问答和图文生成

本部分对GPU资源要求更高，资源有限暂未实际操作本部分

1. 部署InternLM-XComposer2

   conda activate demo # demo环境同上
   
   # 补充环境包
   pip install timm==0.4.12 sentencepiece==0.1.99 markdown2==2.4.10 xlsxwriter==3.1.2 gradio==4.13.0 modelscope==1.9.5
   
   # 获取项目代码
   cd /root/demo
   git clone https://gitee.com/internlm/InternLM-XComposer.git
   # git clone https://github.com/internlm/InternLM-XComposer.git
   cd /root/demo/InternLM-XComposer
   git checkout f31220eddca2cf6246ee2ddf8e375a40457ff626
   

   InternStudio算力平台可以使用share路径下的资源，构造软链接快捷访问方式

   ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm-xcomposer2-7b /root/models/internlm-xcomposer2-7b
   ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm-xcomposer2-vl-7b /root/models/internlm-xcomposer2-vl-7b
   

2. 图文写作

   # InternLM-XComposer 启动命令
   cd /root/demo/InternLM-XComposer
   python /root/demo/InternLM-XComposer/examples/gradio_demo_composition.py  \
   --code_path /root/models/internlm-xcomposer2-7b \
   --private \
   --num_gpus 1 \
   --port 6006
   

   
   

3. 图文理解

   # 启动命令
   conda activate demo
   
   cd /root/demo/InternLM-XComposer
   python /root/demo/InternLM-XComposer/examples/gradio_demo_chat.py  \
   --code_path /root/models/internlm-xcomposer2-vl-7b \
   --private \
   --num_gpus 1 \
   --port 6006