轻松玩转书生·浦语大模型趣味 Demo

github: https://github.com/InternLM/Tutorial/blob/camp2/helloworld/hello_world.md
视频：

轻松玩转书生·浦语大模型趣味 Demo_哔哩哔哩_bilibili
书生·浦语大模型角色扮演 SIG 小组长那路带来《轻松书生·浦语大模型趣味 Demo》的实战课程玩
 
https://www.bilibili.com/video/BV1AH4y1H78d/?spm_id_from=333.788&vd_source=04b3ecb8035d8149c057dc0cf58920db
 

环境配置
Bash
Copy
# 进入开发机
# 选择 terminal

# 1. 创建conda环境
studio-conda -o internlm-base -t demo

# 与 studio-conda 等效的配置方案
# 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

# 2. 进入conda环境
conda activate demo

# 3. 其他依赖安装
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

模型下载
Bash
Copy
# 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 # 在/root/demo目录下创建download_mini.py 输入 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') # 执行 python /root/demo/download_mini.py 

模型推理
Bash
Copy
# 打开/root/demo/cli_demo.py 替换为下面代码 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 conda activate demo python /root/demo/cli_demo.py 

部署
4. 1 部署 八戒-Chat-1.8B
Bash
Copy
conda activate demo
cd /root/
git clone https://gitee.com/InternLM/Tutorial -b camp2
# git clone https://github.com/InternLM/Tutorial -b camp2
cd /root/Tutorial
#下载模型
python /root/Tutorial/helloworld/bajie_download.py

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

# 从本地使用 ssh 连接 studio 端口
# 将下方端口号 38374 替换成自己的端口号
ssh -CNg -L 6006:127.0.0.1:6006 root@ssh.intern-ai.org.cn -p 38374

4.2 
JavaScript
Copy
cd /root/demo/lagent
ln -s /root/share/new_models/Shanghai_AI_Laboratory/internlm2-chat-7b /root/models/internlm2-chat-7b

打开 lagent 路径下 examples/internlm2_agent_web_demo_hf.py 文件，并修改对应位置 (71行左右) 代码：
# 其他代码...
value='/root/models/internlm2-chat-7b'
# 其他代码...

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

# 从本地使用 ssh 连接 studio 端口
# 将下方端口号 40759 替换成自己的端口号
ssh -CNg -L 6006:127.0.0.1:6006 root@ssh.intern-ai.org.cn -p 40759

4.3 部署 浦语·灵笔2
JavaScript
Copy
conda activate demo
# 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

#下载 InternLM-XComposer 仓库 相关的代码资源
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

#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

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

# 从本地使用 ssh 连接 studio 端口
# 将下方端口号 40759 替换成自己的端口号
ssh -CNg -L 6006:127.0.0.1:6006 root@ssh.intern-ai.org.cn -p 40759

作业
Tips:
八戒-Chat-1.8B temperature 不能设置为0，会报错
 
5.1 基础作业 (结营必做)
使用 InternLM2-Chat-1.8B 模型生成 300 字的小故事（需截图）

5.2 进阶作业 (优秀学员必做)
熟悉 huggingface 下载功能，使用 huggingface_hub python 包，下载 InternLM2-Chat-7B 的 config.json 文件到本地（需截图下载过程）
 
完成 浦语·灵笔2 的 图文创作 及 视觉问答 部署（需截图）
完成 Lagent 工具调用 数据分析 Demo 部署（需截图）
解数学题：成功