Merge pull request #24 from stormdragongardin/main

注释deepspeeds，添加dockerfile，docker-compose启动文件，修改启动脚本可以在局域网内访问

docker/Dockerfile

@@ -0,0 +1,51 @@
+# 使用nvidia/cuda:11.7.1-cudnn8-runtime-ubuntu22.04作为基础镜像
+FROM nvidia/cuda:11.7.1-cudnn8-runtime-ubuntu22.04
+
+# 安装Python编译依赖，下载并编译Python，并设置Python 3.10为默认Python版本
+RUN apt-get update && apt-get install -y \
+    wget \
+    build-essential \
+    libssl-dev \
+    zlib1g-dev \
+    libncurses5-dev \
+    libncursesw5-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    libgdbm-dev \
+    libdb5.3-dev \
+    libbz2-dev \
+    libexpat1-dev \
+    liblzma-dev \
+    libffi-dev \
+    libgdbm-compat-dev \
+    && wget https://www.python.org/ftp/python/3.10.12/Python-3.10.12.tar.xz -O /tmp/Python-3.10.12.tar.xz \
+    && tar xvf /tmp/Python-3.10.12.tar.xz -C /tmp \
+    && cd /tmp/Python-3.10.12 \
+    && ./configure --enable-optimizations --with-ensurepip=install \
+    && make -j $(nproc) \
+    && make altinstall \
+    && update-alternatives --install /usr/bin/python python /usr/local/bin/python3.10 1 \
+    && update-alternatives --install /usr/bin/pip pip /usr/local/bin/pip3.10 1 \
+    && rm -rf /tmp/Python-3.10.12.tar.xz /tmp/Python-3.10.12 \
+    && apt-get install -y git \
+    && curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | bash \
+    && apt-get install -y git-lfs \
+    && pip install --upgrade pip
+
+#设置工作目录
+WORKDIR /root/Llama2-Chinese
+
+# 从git上克隆llama2-chinese仓库
+RUN git clone https://github.com/FlagAlpha/Llama2-Chinese.git /root/Llama2-Chinese 
+
+# 使用pip安装requirements.txt
+RUN pip install -r requirements.txt
+
+#克隆Hugging Face仓库
+RUN  git clone https://huggingface.co/FlagAlpha/Llama2-Chinese-7b-Chat
+
+#开启7860端口
+EXPOSE 7860 
+
+#设置启动命令
+ENTRYPOINT ["python", "examples/chat_gradio.py", "--model_name_or_path", "/root/Llama2-Chinese/Llama2-Chinese-7b-Chat/"]

docker/docker-compose.yml

@@ -0,0 +1,16 @@
+version: '3.7'
+services:
+  app:
+    image: longerhuya/llama2-chinese-7b:gradio # 这里替换为你实际的镜像名
+    volumes:
+      - /usr/local/nvidia:/usr/local/nvidia # 让容器访问主机的NVIDIA驱动
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all # 让容器可以访问所有的NVIDIA GPU
+    ports:
+      - 7860:7860 # 在容器和主机之间映射端口
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              capabilities: [gpu] # 使用Docker的设备请求来让容器使用GPU

examples/chat_gradio.py

@@ -91,4 +91,4 @@ def bot(history,temperature,top_p,slider_context_times):
     streamer = TextIteratorStreamer(tokenizer,skip_prompt=True)
     if torch.__version__ >= "2" and sys.platform != "win32":
         model = torch.compile(model)
-    demo.queue().launch(share=False,debug = True)
+    demo.queue().launch(share=False, debug=True， server_name="0.0.0.0")

requirements.txt

@@ -1,6 +1,6 @@
 bitsandbytes==0.39.0
 accelerate==0.21.0
-deepspeed==0.10.0
+#deepspeed==0.10.0
 git+https://github.com/PanQiWei/AutoGPTQ.git
 scipy
 sentencepiece