InternLM2-Chat-1.8B 模型测试

在interStudio进行InternLM2-Chat-1.8B模型访问，进入开发机后

配置基础环境
新建conda环境并且进入
conda create -n demo python3.10 -y
conda activate demo
下载pytorch等相关包
conda install pytorch2.0.1 torchvision0.15.2 torchaudio2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install huggingface-hub0.17.3
pip install transformers4.34
pip install psutil5.9.8
pip install accelerate0.24.1
pip install streamlit1.32.2
pip install matplotlib3.8.3
pip install modelscope1.9.5
pip install sentencepiece0.1.99
创建下载模型的文件，并下载模型

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是模型保存到本地的目录
save_dir="/root/models"

snapshot_download("Shanghai_AI_Laboratory/internlm2-chat-1_8b", 
                  cache_dir=save_dir, 
                  revision='v1.1.0')

创建执行文件

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)