L1-8G 显存玩转书生大模型 Demo
闯关
8G cli_demo部署
1 .首先下载完权重,使用download_mini.py代码,内容如何
- 现在完成后,按照教程部署,cli_demo代码简单
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)
生成300故事