mirror of https://github.com/THUDM/ChatGLM2-6B
Merge d187e8ac97
into cb8e8b43c0
commit
3f45e5dedb
|
@ -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
|
|
@ -185,6 +185,15 @@ 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:
|
||||
|
|
|
@ -105,4 +105,4 @@ with gr.Blocks() as demo:
|
|||
|
||||
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")
|
||||
|
|
Loading…
Reference in New Issue