课程文档:https://github.com/InternLM/Tutorial/blob/camp2/helloworld/hello_world.md
课程视频:https://www.bilibili.com/video/BV1AH4y1H78d/
课程作业:https://github.com/InternLM/Tutorial/blob/camp2/helloworld/homework.md
1.Demo实战部署 InternLM2-Chat-1.8B
创建Intern Studio 开发机,通过Modelscope下载 InternLM2-Chat-1.8B 模型(B是billion的缩写十亿),这里解释一下Modelscope是一个模型即服务平台,宗旨是汇聚AI社区最先进的机器学习模型,并简化在实际应用中使用AI的流程。
2.实战部署优秀作品 八戒-Chat-1.8B
通过OpenXlab部署XiYou系列八戒-Chat-18.8B模型,完成Web Demo的部署和交互
3.实战进阶运行Lagent 智能体 Demo
实战算力升级之后,以InternLM2-Chat-7B为基础,运行开源框架Lagent的智能体Demo
4.实战进阶 灵笔InternLM-XComposer2
浅唱多模态实践,通过InternLM-XComposer2 模型实现更加复杂的图文生产写作
实战部分
1.首先进入开发机,进入terminal 中输入环境配置命令,
studio-conda -o internlm-base -t demo
#与studio -conda 等效配置的方案
#conda create -n demo python=3.10 -y
#conda activate demo
#conda install pytorch=2.01 torchvision=0.15.2
#激活环境
conda activate demo
2.完成环境包的安装
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
3. 下载 InternLM2-Chat-1.8B 模型
按路径创建文件夹,并且进入到对应的目录文件当中
mkdir -p /root/demo
touch /root/demo/cli_demo.py
touch /root/demo/download_mini.py
cd /root/demo
#执行命令
python /root/demo/download_mini.py
双击 /root/demo/download_mini.py 文件,复制以下代码:
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 保存模型到本地目录
save_dir="/root/models"
snapshot_download("Shanghai_AI_Laboratory/internlm2-chat-1_8b",
cache_dir=save_dir,
revision='v1.1.0'
")
执行命令,下载模型参数文件:
python /root/demo/download_mini.py
2.3 运行 cli_demo
双击打开 /root/demo/cli_demo.py 文件,复制以下代码:
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)
输入命令,执行 Demo 程序:
conda activate demo
python /root/demo/cli_demo.py