8G 显存玩转书生大模型 Demo

用到的模型和环境(/root/share/pre_envs/icamp3_demo)都在开发机的share目录下

Cli Demo 部署 InternLM2-Chat-1.8B 模型

客户端部署chat模型:
cli_demo.py:

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python cli_demo.py 即可

Streamlit Web Demo 部署 InternLM2-Chat-1.8B 模型

web网页端部署chat模型：

git clone https://github.com/InternLM/Tutorial.git
streamlit run /root/demo/Tutorial/tools/streamlit_demo.py --server.address 127.0.0.1 --server.port 6006

可以直接在vscode 远程端口设置里面设置映射,后续模型用到的映射端口默认都是6006。

LMDeploy 部署 InternLM-XComposer2-VL-1.8B 模型

#先激活环境并安装包
conda activate /root/share/pre_envs/icamp3_demo
pip install lmdeploy[all]==0.5.1
pip install timm==1.0.7
lmdeploy serve gradio /share/new_models/Shanghai_AI_Laboratory/internlm-xcomposer2-vl-1_8b --cache-max-entry-count 0.1

LMDeploy 部署 InternVL2-2B 模型

web网页端部署文生图模型:

lmdeploy serve gradio /share/new_models/OpenGVLab/InternVL2-2B --cache-max-entry-count 0.1