InternLM2-Chat-1.8B 模型的部署

1. 进入云服务器

直接最低配置就行

2. 创建项目虚拟环境

# 创建环境
conda create -n demo python=3.10 -y
# 激活环境
conda activate demo
# 安装 torch
conda install pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia -y
# 安装其他依赖
pip install transformers==4.38
pip install sentencepiece==0.1.99
pip install einops==0.8.0
pip install protobuf==5.27.2
pip install accelerate==0.33.0
pip install streamlit==1.37.0

安装过程：

3. 基础代码

在开发机终端：

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

代码:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM


model_name_or_path = "/root/share/new_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)

终端输入：

python /root/demo/cli_demo.py

任务：根据prompt，生成300字小说

效果如图：

4. Streamlit Web 部署 InternLM2-Chat-1.8B 模型可视化

使用 Streamlit 部署 InternLM2-Chat-1.8B 模型。

先把相关代码clone到本地demo文件夹

cd /root/demo
git clone https://github.com/InternLM/Tutorial.git

执行代码
在开发机的vscode里面，配置port 6006，比较方便

cd /root/demo
streamlit run /root/demo/Tutorial/tools/streamlit_demo.py --server.address 127.0.0.1 --server.port 6006

vscode里自动完成端口映射，浏览器访问 http://localhost:6006 。