8G 显存玩转书生大模型 Demo
- 基础任务
- 进阶作业一：
- 进阶作业二：
基础任务
- 使用 Cli Demo 完成 InternLM2-Chat-1.8B 模型的部署，并生成 300 字小故事，记录复现过程并截图。
创建conda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
创建文件夹DEMO存放课程相关的文件
mkdir DEMO
cd DEMO
创建requirements.txt，写入依赖包
transformers==4.38
sentencepiece==0.1.99
einops==0.8.0
protobuf==5.27.2
accelerate==0.33.0
streamlit==1.37.0
安装依赖包
pip install -r requirements.txt
创建cli_demo.py
touch cli_demo.py
将以下代码复制到cli_demo.py中
import torch
from transformers import AutoTokenizer, AutoModelForCausalLMmodel_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":breaklength = 0for response, _ in model.stream_chat(tokenizer, input_text, messages):if response is not None:print(response[length:], flush=True, end="")length = len(response)
然后就可以DEMO，启动
python cli_demo.py
生成300字的小故事
进阶作业一：
- 使用 LMDeploy 完成 InternLM-XComposer2-VL-1.8B 的部署，并完成一次图文理解对话，记录复现过程并截图。
安装lmdeploy
pip install lmdeploy[all]==0.5.1
pip install timm==1.0.7
部署xcomposer
lmdeploy serve gradio /share/new_models/Shanghai_AI_Laboratory/internlm-xcomposer2-vl-1_8b --cache-max-entry-count 0.1
部署完成
在浏览器上访问 http://localhost:6006/ 体验xcomposer
进阶作业二：
- 使用 LMDeploy 完成 InternVL2-2B 的部署，并完成一次图文理解对话，记录复现过程并截图。
因为依赖前面已经安装过了，所以直接部署
部署IntenVL2-2B
lmdeploy serve gradio /share/new_models/OpenGVLab/InternVL2-2B --cache-max-entry-count 0.1
在浏览器上访问 http://localhost:6006/ 体验internVL2-2B
对比xcomposer，internVL2-2B不知道就是不知道，不会编个答案
