# conda create -n demo python==3.10 -y # conda activate demo # conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia -y
pip install huggingface-hub==0.17.3 transformers==4.34 psutil==5.9.8 accelerate==0.24.1 streamlit==1.32.2 matplotlib==3.8.3 modelscope==1.9.5 sentencepiece==0.1.99
mkdir -p /root/demo
touch /root/demo/cli_demo.py
touch /root/demo/download_mini.py
cd /root/demo
download_mini.py:
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')
cli_demo.py:
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)
conda activate demo
python /root/demo/cli_demo.py
请创作一个 300 字的小故事