8G 显存玩转书生大模型 Demo
Cli Demo 部署 InternLM2-Chat-1.8B 模型
1.创建开发机
这里就不讲了之前的文章有
2.环境配置
已经有预置好的环境在 /root/share/pre_envs
中的icamp3_demo
激活命令为
conda activate /root/share/pre_envs/icamp3_demo
我们创建一个目录,用于存放我们的代码。并创建一个 cli_demo.py
。内容为:
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.=============")
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)
然后运行demo 命令python /root/demo/cli_demo.py
效果如下
Streamlit Web Demo 部署 InternLM2-Chat-1.8B 模型
输入
streamlit run /root/demo/Tutorial/tools/streamlit_demo.py --server.address 127.0.0.1 --server.port 6006
同时在powershell输入
ssh -CNg -L 6006:127.0.0.1:6006 root@ssh.intern-ai.org.cn -p 你的 ssh 端口号
然后打开网址就可以了
LMDeploy 部署 InternLM-XComposer2-VL-1.8B 模型
输入命令
lmdeploy serve gradio /share/new_models/Shanghai_AI_Laboratory/internlm-xcomposer2-vl-1_8b --cache-max-entry-count 0.1
打开网址就可以用了
LMDeploy 部署 InternVL2-2B 模型
输入命令:
lmdeploy serve gradio /share/new_models/OpenGVLab/InternVL2-2B --cache-max-entry-count 0.1
有警告 不理它
打开网址就可以用了