书生浦语大模型实战营第三期基础岛—8G显存玩转InternLM2-Chat-1.8B

8G显存玩转InternLM2-Chat-1.8B

新建环境并进行环境配置

创建环境

conda create -n demo python=3.10 -y

激活环境

conda activate demo

1.1安装 torch

conda install pytorch2.1.2 torchvision0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia -y

1.2 安装其他依赖

pip install transformers4.38
pip install sentencepiece0.1.99
pip install einops0.8.0
pip install protobuf5.27.2
pip install accelerate0.33.0
pip install streamlit1.37.0

Cli Demo 部署 InternLM2-Chat-1.8B 模型

先创建运行文件。

这里主要是一个加载运行internlm2-chat-1_8b编码工具和模型的过程，用死循环模拟对话。

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)

演示示例如下：

Streamlit Web Demo 部署 InternLM2-Chat-1.8B 模型

这里应该是用了可以适配模型的开源webui——streamlit.
将streamlit克隆到本地后，运行他的服务。
ssh -CNg -L 6006:127.0.0.1:6006 root@ssh.intern-ai.org.cn -p 你的 ssh 端口号
加载的时间比较长，耐心等待。第一次还加载失败了，因为我自己下了最新的transformers包，后面重新下载了适配的包过后能正常运行，演示如下：

LMDeploy 部署 InternLM-XComposer2-VL-1.8B 模型

启用gradio服务：lmdeploy serve gradio /share/new_models/Shanghai_AI_Laboratory/internlm-xcomposer2-vl-1_8b --cache-max-entry-count 0.1