diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000..c09ff79 --- /dev/null +++ b/Dockerfile @@ -0,0 +1,21 @@ +## use pytorch images +FROM pytorch/pytorch:2.0.1-cuda11.7-cudnn8-runtime +## lables +LABEL version="v1" +LABEL description="chatglm2-6b docker images" +LABEL maintainer="dengsgo[https://github.com/dengsgo]" +## copy all files +COPY . . +## install tools +RUN apt update && apt install -y git gcc +## install requirements and cudatoolkit +RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/ && \ +pip install icetk -i https://pypi.tuna.tsinghua.edu.cn/simple/ && \ +conda install cudatoolkit=11.7 -c nvidia +## expose port +EXPOSE 7860 +## run +CMD [ "python3","web_demo.py" ] + +## command for docker run +## docker run --rm -it -v /home/dengsgo/models/chatglm2-6b-int4:/workspace/THUDM/chatglm2-6b --gpus=all -e NVIDIA_DRIVER_CAPABILITIES=compute,utility -e NVIDIA_VISIBLE_DEVICES=all -p 7860:7860 chatglm2:v1 \ No newline at end of file diff --git a/README.md b/README.md index 27ce17f..53a3366 100644 --- a/README.md +++ b/README.md @@ -166,6 +166,15 @@ pip install -r requirements.txt ``` 其中 `transformers` 库版本推荐为 `4.30.2`,`torch` 推荐使用 2.0 及以上的版本,以获得最佳的推理性能。 +### Docker webUI +首先需要下载本仓库: +```shell +git clone https://github.com/THUDM/ChatGLM2-6B +cd ChatGLM2-6B +docker build -t chatglm2:v1 . +docker run --rm -it -v /home/dengsgo/models/chatglm2-6b-int4:/workspace/THUDM/chatglm2-6b --gpus=all -e NVIDIA_DRIVER_CAPABILITIES=compute,utility -e NVIDIA_VISIBLE_DEVICES=all -p 7860:7860 chatglm2:v1 +``` + ### 代码调用 可以通过如下代码调用 ChatGLM2-6B 模型来生成对话: diff --git a/web_demo.py b/web_demo.py index 1af24c9..f019d1f 100644 --- a/web_demo.py +++ b/web_demo.py @@ -105,4 +105,4 @@ def reset_state(): emptyBtn.click(reset_state, outputs=[chatbot, history, past_key_values], show_progress=True) -demo.queue().launch(share=False, inbrowser=True) +demo.queue().launch(share=False, inbrowser=True, server_name="0.0.0.0")