书生大模型实战营-基础岛第二关 8G 显存玩转书生大模型 Demo

环境配置

本次开发环境使用书生的服务器OpenXlab：OpenXLab-登录

创建10%的开发机，镜像选择为 Cuda-12.2。在输入开发机名称后，点击创建开发机。

 我们首先来为 Demo 创建一个可用的环境。可以用conda，命令放在下面。

# 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

笔者平时使用Poetry来管理环境，如果没有安装poetry可以使用以下命令来安装poetry：

pip install poetry

新建一个环境并安装依赖，需要文件夹里有pyproject.toml：

我们可以将需要的环境告诉GPT让他帮忙生成一个pyproject.toml文件的格式：

poetry new demo

cd demo

poetry env use python310
# 激活环境
poetry shell
# 安装所有依赖
poetry install

 Cli Demo 部署 InternLM2-Chat-1.8B 模型

 之后，我们创建一个目录，用于存放我们的代码。并创建一个 cli_demo.py。

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

 然后，我们将下面的代码复制到 cli_demo.py 中。

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)

接下来，我们便可以通过 python /root/demo/cli_demo.py 来启动我们的 Demo。我们让他写一个短文试试~。