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.=============")whileTrue:
input_text =input("\nUser >>> ")
input_text = input_text.replace(' ','')if input_text =="exit":break
length =0for response, _ in model.stream_chat(tokenizer, input_text, messages):if response isnotNone:print(response[length:], flush=True, end="")
length =len(response)