InternLM 大模型实战营笔记-4

最新推荐文章于 2024-10-06 21:18:37 发布

Dylan_TAI

最新推荐文章于 2024-10-06 21:18:37 发布

阅读量413

点赞数 14

文章标签：笔记

本文链接：https://blog.csdn.net/Dylan_TAI/article/details/141927353

版权

基础岛第2关 8G 显存玩转书生大模型 Demo

1. InternLM2-Chat-1.8B 模型的部署

步骤

1、创建开发机，名称为Gryffinor，cuda12.2，ubuntu 20.04，A100 10%配置
在这里插入图片描述
2、激活预置环境icamp3_demo
conda activate /root/share/pre_envs/icamp3_demo

3、创建目录/demo，存放代码文件cli_demo.py
mkdir -p /root/demo
touch /root/demo/cli_demo.py
在cli_demo.py中写入以下代码：

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)

4、运行上面的代码：python /root/demo/cli_demo.py
在这里插入图片描述
5、Streamlit Web Demo 部署 InternLM2-Chat-1.8B 模型
把本教程仓库 clone 到本地
cd /root/demo
git clone https://github.com/InternLM/Tutorial.git
执行如下代码来启动一个 Streamlit 服务:
cd /root/demo
streamlit run /root/demo/Tutorial/tools/streamlit_demo.py --server.address 127.0.0.1 --server.port 6006
假设自己的开发机端口是XXXXX，在自己本地电脑上执行端口映射
ssh -CNg -L 6006:127.0.0.1:6006 root@ssh.intern-ai.org.cn -p XXXXX
在完成端口映射后，我们便可以通过浏览器访问 http://localhost:6006 来启动我们的 Demo，如下所示
在这里插入图片描述
使用该模型写一个关于哈利波特的300字的小故事