From d7207e8ad10c7df6dcb1f5e59ff8eb06f9d77e67 Mon Sep 17 00:00:00 2001
From: MengqingCao <cmq0113@163.com>
Date: Mon, 24 Jun 2024 10:57:36 +0000
Subject: [PATCH 1/8] update docker files

  1. add docker-npu (Dockerfile and docker-compose.yml)
  2. move cuda docker to docker-cuda and tiny changes to adapt to the new path
---
 README.md                                     | 61 +++++++++++++++++--
 README_zh.md                                  | 58 ++++++++++++++++--
 Dockerfile => docker/docker-cuda/Dockerfile   | 10 +--
 .../docker-cuda/docker-compose.yml            |  6 +-
 docker/docker-npu/Dockerfile                  | 40 ++++++++++++
 docker/docker-npu/docker-compose.yml          | 31 ++++++++++
 6 files changed, 187 insertions(+), 19 deletions(-)
 rename Dockerfile => docker/docker-cuda/Dockerfile (87%)
 rename docker-compose.yml => docker/docker-cuda/docker-compose.yml (80%)
 create mode 100644 docker/docker-npu/Dockerfile
 create mode 100644 docker/docker-npu/docker-compose.yml

diff --git a/README.md b/README.md
index 9462964c..1107ae0b 100644
--- a/README.md
+++ b/README.md
@@ -383,10 +383,11 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 | torch-npu    | 2.1.0   | 2.1.0.post3 |
 | deepspeed    | 0.13.2  | 0.13.2      |
 
-Docker image:
+Docker users please refer to [Build Docker](#Build-Docker).
 
-- 32GB: [Download page](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html)
-- 64GB: [Download page](http://mirrors.cn-central-221.ovaijisuan.com/detail/131.html)
+**NOTE**
+
+The default docker image is [cosdt/cann:8.0.rc1-910b-ubuntu22.04](https://hub.docker.com/layers/cosdt/cann/8.0.rc1-910b-ubuntu22.04/images/sha256-29ef8aacf6b2babd292f06f00b9190c212e7c79a947411e213135e4d41a178a9?context=explore). More options can be found at [cosdt/cann](https://hub.docker.com/r/cosdt/cann/tags).
 
 Remember to use `ASCEND_RT_VISIBLE_DEVICES` instead of `CUDA_VISIBLE_DEVICES` to specify the device to use.
 
@@ -426,7 +427,10 @@ llamafactory-cli webui
 
 #### Use Docker
 
+<details><summary>For NVIDIA GPU users:</summary>
+
 ```bash
+cd ./docker/docker-cuda
 docker build -f ./Dockerfile \
     --build-arg INSTALL_BNB=false \
     --build-arg INSTALL_VLLM=false \
@@ -435,18 +439,63 @@ docker build -f ./Dockerfile \
     -t llamafactory:latest .
 
 docker run -it --gpus=all \
-    -v ./hf_cache:/root/.cache/huggingface/ \
-    -v ./data:/app/data \
-    -v ./output:/app/output \
+    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
+    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
+    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
     -p 7860:7860 \
     -p 8000:8000 \
     --shm-size 16G \
     --name llamafactory \
     llamafactory:latest
 ```
+</details>
+
+<details><summary>For Ascend NPU users:</summary>
+
+```bash
+cd ./docker/docker-npu
+docker build -f ./Dockerfile \
+    --build-arg INSTALL_DEEPSPEED=false \
+    --build-arg PIP_INDEX=https://pypi.org/simple \
+    -t llamafactory:latest .
+
+# add --device for multi-npu usage
+# or modify --device to change npu card
+docker run -it \
+    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
+    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
+    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
+    -v /usr/local/dcmi:/usr/local/dcmi \
+    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
+    -v /usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64 \
+    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
+    -v /etc/ascend_install.info:/etc/ascend_install.info \
+    -p 7860:7860 \
+    -p 8000:8000 \
+    --device /dev/davinci0 \
+    --device /dev/davinci_manager \
+    --device /dev/devmm_svm \
+    --device /dev/hisi_hdc \
+    --shm-size 16G \
+    --name llamafactory \
+    llamafactory:latest
+```
+</details>
 
 #### Use Docker Compose
 
+Firstly enter your docker path:
+
+```bash
+# for NVIDIA GPU users
+cd ./docker/docker-cuda
+
+# for Ascend NPU users
+cd ./docker/docker-npu
+```
+
+Then run the following command to build docker image and start the container:
+
 ```bash
 docker-compose up -d
 docker-compose exec llamafactory bash
diff --git a/README_zh.md b/README_zh.md
index 8b77e91e..6326c0b5 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -383,10 +383,11 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 | torch-npu    | 2.1.0   | 2.1.0.post3 |
 | deepspeed    | 0.13.2  | 0.13.2      |
 
-Docker 镜像：
+Docker用户请参考 [构建 Docker](#构建-Docker).
 
-- 32GB：[下载地址](http://mirrors.cn-central-221.ovaijisuan.com/detail/130.html)
-- 64GB：[下载地址](http://mirrors.cn-central-221.ovaijisuan.com/detail/131.html)
+**NOTE**
+
+默认镜像为 [cosdt/cann:8.0.rc1-910b-ubuntu22.04](https://hub.docker.com/layers/cosdt/cann/8.0.rc1-910b-ubuntu22.04/images/sha256-29ef8aacf6b2babd292f06f00b9190c212e7c79a947411e213135e4d41a178a9?context=explore). 更多选择见 [cosdt/cann](https://hub.docker.com/r/cosdt/cann/tags).
 
 请使用 `ASCEND_RT_VISIBLE_DEVICES` 而非 `CUDA_VISIBLE_DEVICES` 来指定运算设备。
 
@@ -426,7 +427,10 @@ llamafactory-cli webui
 
 #### 使用 Docker
 
+<details><summary>NVIDIA GPU 用户：</summary>
+
 ```bash
+cd ./docker/docker-cuda
 docker build -f ./Dockerfile \
     --build-arg INSTALL_BNB=false \
     --build-arg INSTALL_VLLM=false \
@@ -435,18 +439,60 @@ docker build -f ./Dockerfile \
     -t llamafactory:latest .
 
 docker run -it --gpus=all \
-    -v ./hf_cache:/root/.cache/huggingface/ \
-    -v ./data:/app/data \
-    -v ./output:/app/output \
+    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
+    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
+    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
     -p 7860:7860 \
     -p 8000:8000 \
     --shm-size 16G \
     --name llamafactory \
     llamafactory:latest
 ```
+</details>
+
+<details><summary>Ascend NPU 用户：</summary>
+
+```bash
+cd ./docker/docker-npu
+docker build -f ./Dockerfile \
+    --build-arg INSTALL_DEEPSPEED=false \
+    --build-arg PIP_INDEX=https://pypi.org/simple \
+    -t llamafactory:latest .
+
+# 增加 --device 来使用多卡 NPU 或修改第一个 --device 来更改 NPU 卡
+docker run -it \
+    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
+    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
+    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
+    -v /usr/local/dcmi:/usr/local/dcmi \
+    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
+    -v /usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64 \
+    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
+    -v /etc/ascend_install.info:/etc/ascend_install.info \
+    -p 7860:7860 \
+    -p 8000:8000 \
+    --device /dev/davinci0 \
+    --device /dev/davinci_manager \
+    --device /dev/devmm_svm \
+    --device /dev/hisi_hdc \
+    --shm-size 16G \
+    --name llamafactory \
+    llamafactory:latest
+```
+</details>
 
 #### 使用 Docker Compose
 
+首先进入 docker 目录：
+```bash
+# NVIDIA GPU 用户
+cd ./docker/docker-cuda
+
+# Ascend NPU 用户
+cd ./docker/docker-npu
+```
+然后运行以下命令创建 docker 镜像并启动容器:
+
 ```bash
 docker-compose up -d
 docker-compose exec llamafactory bash
diff --git a/Dockerfile b/docker/docker-cuda/Dockerfile
similarity index 87%
rename from Dockerfile
rename to docker/docker-cuda/Dockerfile
index 61d58005..72797a26 100644
--- a/Dockerfile
+++ b/docker/docker-cuda/Dockerfile
@@ -9,16 +9,18 @@ ARG INSTALL_DEEPSPEED=false
 ARG PIP_INDEX=https://pypi.org/simple
 
 # Set the working directory
-WORKDIR /app
+WORKDIR /app/LLaMA-Factory
+
+RUN cd /app && \
+    git config --global http.version HTTP/1.1 && \
+    git clone https://github.com/hiyouga/LLaMA-Factory.git && \
+    cd /app/LLaMA-Factory
 
 # Install the requirements
-COPY requirements.txt /app/
 RUN pip config set global.index-url $PIP_INDEX
 RUN python -m pip install --upgrade pip
 RUN python -m pip install -r requirements.txt
 
-# Copy the rest of the application into the image
-COPY . /app/
 
 # Install the LLaMA Factory
 RUN EXTRA_PACKAGES="metrics"; \
diff --git a/docker-compose.yml b/docker/docker-cuda/docker-compose.yml
similarity index 80%
rename from docker-compose.yml
rename to docker/docker-cuda/docker-compose.yml
index c5dc34e9..a470aa60 100644
--- a/docker-compose.yml
+++ b/docker/docker-cuda/docker-compose.yml
@@ -10,9 +10,9 @@ services:
         PIP_INDEX: https://pypi.org/simple
     container_name: llamafactory
     volumes:
-      - ./hf_cache:/root/.cache/huggingface/
-      - ./data:/app/data
-      - ./output:/app/output
+      - ../../hf_cache:/root/.cache/huggingface/
+      - ../../data:/app/LLaMA-Factory/data
+      - ../../output:/app/LLaMA-Factory/output
     ports:
       - "7860:7860"
       - "8000:8000"
diff --git a/docker/docker-npu/Dockerfile b/docker/docker-npu/Dockerfile
new file mode 100644
index 00000000..9456bcbf
--- /dev/null
+++ b/docker/docker-npu/Dockerfile
@@ -0,0 +1,40 @@
+# Using ubuntu 22.04 images with cann 8.0.rc1
+# More options can be found at https://hub.docker.com/r/cosdt/cann/tags
+FROM cosdt/cann:8.0.rc1-910b-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Define installation arguments
+ARG INSTALL_DEEPSPEED=false
+ARG PIP_INDEX=https://pypi.org/simple
+
+# Set the working directory
+WORKDIR /app/LLaMA-Factory
+
+RUN cd /app && \
+    git config --global http.version HTTP/1.1 && \
+    git clone https://github.com/hiyouga/LLaMA-Factory.git && \
+    cd /app/LLaMA-Factory
+
+RUN pip config set global.index-url $PIP_INDEX
+RUN python3 -m pip install --upgrade pip
+
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="torch-npu,metrics"; \
+    if [ "$INSTALL_DEEPSPEED" = "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    pip install -e .[$EXTRA_PACKAGES] && \
+    pip uninstall -y transformer-engine flash-attn
+
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface/", "/app/data", "/app/output" ]
+
+# Expose port 7860 for the LLaMA Board
+EXPOSE 7860
+
+# Expose port 8000 for the API service
+EXPOSE 8000
+
+# Launch LLaMA Board
+CMD [ "llamafactory-cli", "webui" ]
diff --git a/docker/docker-npu/docker-compose.yml b/docker/docker-npu/docker-compose.yml
new file mode 100644
index 00000000..93eb6718
--- /dev/null
+++ b/docker/docker-npu/docker-compose.yml
@@ -0,0 +1,31 @@
+services:
+  llamafactory:
+    build:
+      dockerfile: Dockerfile
+      context: .
+      args:
+        INSTALL_DEEPSPEED: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface/
+      - ../../data:/app/LLaMA-Factory/data
+      - ../../output:/app/LLaMA-Factory/output
+      - /usr/local/dcmi:/usr/local/dcmi
+      - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
+      - /usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64
+      - /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info
+      - /etc/ascend_install.info:/etc/ascend_install.info
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    stdin_open: true
+    command: bash
+    devices:
+      - /dev/davinci0
+      - /dev/davinci_manager
+      - /dev/devmm_svm
+      - /dev/hisi_hdc
+    restart: unless-stopped

From dcc2e24f5cd441a242829f2fb090506db507babd Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Mon, 24 Jun 2024 23:41:35 +0800
Subject: [PATCH 2/8] Update Dockerfile

---
 docker/docker-cuda/Dockerfile | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/docker/docker-cuda/Dockerfile b/docker/docker-cuda/Dockerfile
index 72797a26..61d58005 100644
--- a/docker/docker-cuda/Dockerfile
+++ b/docker/docker-cuda/Dockerfile
@@ -9,18 +9,16 @@ ARG INSTALL_DEEPSPEED=false
 ARG PIP_INDEX=https://pypi.org/simple
 
 # Set the working directory
-WORKDIR /app/LLaMA-Factory
-
-RUN cd /app && \
-    git config --global http.version HTTP/1.1 && \
-    git clone https://github.com/hiyouga/LLaMA-Factory.git && \
-    cd /app/LLaMA-Factory
+WORKDIR /app
 
 # Install the requirements
+COPY requirements.txt /app/
 RUN pip config set global.index-url $PIP_INDEX
 RUN python -m pip install --upgrade pip
 RUN python -m pip install -r requirements.txt
 
+# Copy the rest of the application into the image
+COPY . /app/
 
 # Install the LLaMA Factory
 RUN EXTRA_PACKAGES="metrics"; \

From fce146ab681a5682d3f96254e3863f70aca8a4af Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 25 Jun 2024 00:46:08 +0800
Subject: [PATCH 3/8] Update Dockerfile

---
 docker/docker-cuda/Dockerfile | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docker/docker-cuda/Dockerfile b/docker/docker-cuda/Dockerfile
index 61d58005..2d20bfe4 100644
--- a/docker/docker-cuda/Dockerfile
+++ b/docker/docker-cuda/Dockerfile
@@ -12,13 +12,14 @@ ARG PIP_INDEX=https://pypi.org/simple
 WORKDIR /app
 
 # Install the requirements
-COPY requirements.txt /app/
+COPY requirements.txt /app
 RUN pip config set global.index-url $PIP_INDEX
+RUN pip config set global.extra-index-url $PIP_INDEX
 RUN python -m pip install --upgrade pip
 RUN python -m pip install -r requirements.txt
 
 # Copy the rest of the application into the image
-COPY . /app/
+COPY . /app
 
 # Install the LLaMA Factory
 RUN EXTRA_PACKAGES="metrics"; \
@@ -38,10 +39,9 @@ RUN EXTRA_PACKAGES="metrics"; \
 VOLUME [ "/root/.cache/huggingface/", "/app/data", "/app/output" ]
 
 # Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
 EXPOSE 7860
 
 # Expose port 8000 for the API service
+ENV API_PORT 8000
 EXPOSE 8000
-
-# Launch LLaMA Board
-CMD [ "llamafactory-cli", "webui" ]

From 15608d055827e41b44fb8a381b1fe5a1230afcb0 Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 25 Jun 2024 00:46:47 +0800
Subject: [PATCH 4/8] Update docker-compose.yml

---
 docker/docker-cuda/docker-compose.yml | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docker/docker-cuda/docker-compose.yml b/docker/docker-cuda/docker-compose.yml
index a470aa60..04d6531a 100644
--- a/docker/docker-cuda/docker-compose.yml
+++ b/docker/docker-cuda/docker-compose.yml
@@ -1,8 +1,8 @@
 services:
   llamafactory:
     build:
-      dockerfile: Dockerfile
-      context: .
+      dockerfile: ./docker/docker-cuda/Dockerfile
+      context: ../..
       args:
         INSTALL_BNB: false
         INSTALL_VLLM: false
@@ -10,9 +10,9 @@ services:
         PIP_INDEX: https://pypi.org/simple
     container_name: llamafactory
     volumes:
-      - ../../hf_cache:/root/.cache/huggingface/
-      - ../../data:/app/LLaMA-Factory/data
-      - ../../output:/app/LLaMA-Factory/output
+      - ./hf_cache:/root/.cache/huggingface/
+      - ./data:/app/data
+      - ./output:/app/output
     ports:
       - "7860:7860"
       - "8000:8000"

From 3af936a76d726c73d14ff6cf8c3088bda5b904c3 Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 25 Jun 2024 00:50:34 +0800
Subject: [PATCH 5/8] Update Dockerfile

---
 docker/docker-npu/Dockerfile | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/docker/docker-npu/Dockerfile b/docker/docker-npu/Dockerfile
index 9456bcbf..0fdd4472 100644
--- a/docker/docker-npu/Dockerfile
+++ b/docker/docker-npu/Dockerfile
@@ -1,5 +1,5 @@
-# Using ubuntu 22.04 images with cann 8.0.rc1
-# More options can be found at https://hub.docker.com/r/cosdt/cann/tags
+# Use the Ubuntu 22.04 image with CANN 8.0.rc1
+# More versions can be found at https://hub.docker.com/r/cosdt/cann/tags
 FROM cosdt/cann:8.0.rc1-910b-ubuntu22.04
 
 ENV DEBIAN_FRONTEND=noninteractive
@@ -9,15 +9,17 @@ ARG INSTALL_DEEPSPEED=false
 ARG PIP_INDEX=https://pypi.org/simple
 
 # Set the working directory
-WORKDIR /app/LLaMA-Factory
-
-RUN cd /app && \
-    git config --global http.version HTTP/1.1 && \
-    git clone https://github.com/hiyouga/LLaMA-Factory.git && \
-    cd /app/LLaMA-Factory
+WORKDIR /app
 
+# Install the requirements
+COPY requirements.txt /app
 RUN pip config set global.index-url $PIP_INDEX
-RUN python3 -m pip install --upgrade pip
+RUN pip config set global.extra-index-url $PIP_INDEX
+RUN python -m pip install --upgrade pip
+RUN python -m pip install -r requirements.txt
+
+# Copy the rest of the application into the image
+COPY . /app
 
 # Install the LLaMA Factory
 RUN EXTRA_PACKAGES="torch-npu,metrics"; \
@@ -31,10 +33,9 @@ RUN EXTRA_PACKAGES="torch-npu,metrics"; \
 VOLUME [ "/root/.cache/huggingface/", "/app/data", "/app/output" ]
 
 # Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
 EXPOSE 7860
 
 # Expose port 8000 for the API service
+ENV API_PORT 8000
 EXPOSE 8000
-
-# Launch LLaMA Board
-CMD [ "llamafactory-cli", "webui" ]

From 721acd87688b3edd41d2e1890971eb387afc1b6e Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 25 Jun 2024 00:54:28 +0800
Subject: [PATCH 6/8] Update docker-compose.yml

---
 docker/docker-npu/docker-compose.yml | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/docker/docker-npu/docker-compose.yml b/docker/docker-npu/docker-compose.yml
index 93eb6718..7fff6e73 100644
--- a/docker/docker-npu/docker-compose.yml
+++ b/docker/docker-npu/docker-compose.yml
@@ -1,20 +1,19 @@
 services:
   llamafactory:
     build:
-      dockerfile: Dockerfile
-      context: .
+      dockerfile: ./docker/docker-npu/Dockerfile
+      context: ../..
       args:
         INSTALL_DEEPSPEED: false
         PIP_INDEX: https://pypi.org/simple
     container_name: llamafactory
     volumes:
-      - ../../hf_cache:/root/.cache/huggingface/
-      - ../../data:/app/LLaMA-Factory/data
-      - ../../output:/app/LLaMA-Factory/output
+      - ./hf_cache:/root/.cache/huggingface/
+      - ./data:/app/data
+      - ./output:/app/output
       - /usr/local/dcmi:/usr/local/dcmi
       - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
-      - /usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64
-      - /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info
+      - /usr/local/Ascend/driver:/usr/local/Ascend/driver
       - /etc/ascend_install.info:/etc/ascend_install.info
     ports:
       - "7860:7860"

From 5dc8fa647e9af2c6d666c9559553c05d1c4860b3 Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 25 Jun 2024 01:03:38 +0800
Subject: [PATCH 7/8] Update README.md

---
 README.md | 84 ++++++++++++++++++++++++-------------------------------
 1 file changed, 37 insertions(+), 47 deletions(-)

diff --git a/README.md b/README.md
index 1107ae0b..a20b848b 100644
--- a/README.md
+++ b/README.md
@@ -383,12 +383,6 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 | torch-npu    | 2.1.0   | 2.1.0.post3 |
 | deepspeed    | 0.13.2  | 0.13.2      |
 
-Docker users please refer to [Build Docker](#Build-Docker).
-
-**NOTE**
-
-The default docker image is [cosdt/cann:8.0.rc1-910b-ubuntu22.04](https://hub.docker.com/layers/cosdt/cann/8.0.rc1-910b-ubuntu22.04/images/sha256-29ef8aacf6b2babd292f06f00b9190c212e7c79a947411e213135e4d41a178a9?context=explore). More options can be found at [cosdt/cann](https://hub.docker.com/r/cosdt/cann/tags).
-
 Remember to use `ASCEND_RT_VISIBLE_DEVICES` instead of `CUDA_VISIBLE_DEVICES` to specify the device to use.
 
 If you cannot infer model on NPU devices, try setting `do_sample: false` in the configurations.
@@ -425,50 +419,62 @@ llamafactory-cli webui
 
 ### Build Docker
 
-#### Use Docker
-
-<details><summary>For NVIDIA GPU users:</summary>
+For CUDA users:
 
 ```bash
-cd ./docker/docker-cuda
-docker build -f ./Dockerfile \
+docker-compose -f ./docker/docker-cuda/docker-compose.yml up -d
+docker-compose exec llamafactory bash
+```
+
+For Ascend NPU users:
+
+```bash
+docker-compose -f ./docker/docker-npu/docker-compose.yml up -d
+docker-compose exec llamafactory bash
+```
+
+<details><summary>Build without Docker Compose</summary>
+
+For CUDA users:
+
+```bash
+docker build -f ./docker/docker-cuda/Dockerfile \
     --build-arg INSTALL_BNB=false \
     --build-arg INSTALL_VLLM=false \
     --build-arg INSTALL_DEEPSPEED=false \
     --build-arg PIP_INDEX=https://pypi.org/simple \
     -t llamafactory:latest .
 
-docker run -it --gpus=all \
-    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
-    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
-    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
+docker run -dit --gpus=all \
+    -v ./hf_cache:/root/.cache/huggingface/ \
+    -v ./data:/app/data \
+    -v ./output:/app/output \
     -p 7860:7860 \
     -p 8000:8000 \
     --shm-size 16G \
     --name llamafactory \
     llamafactory:latest
-```
-</details>
 
-<details><summary>For Ascend NPU users:</summary>
+docker exec -it llamafactory bash
+```
+
+For Ascend NPU users:
 
 ```bash
-cd ./docker/docker-npu
-docker build -f ./Dockerfile \
+# Change docker image upon your environment
+docker build -f ./docker/docker-npu/Dockerfile \
     --build-arg INSTALL_DEEPSPEED=false \
     --build-arg PIP_INDEX=https://pypi.org/simple \
     -t llamafactory:latest .
 
-# add --device for multi-npu usage
-# or modify --device to change npu card
-docker run -it \
-    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
-    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
-    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
+# Change `device` upon your resources
+docker run -dit \
+    -v ./hf_cache:/root/.cache/huggingface/ \
+    -v ./data:/app/data \
+    -v ./output:/app/output \
     -v /usr/local/dcmi:/usr/local/dcmi \
     -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-    -v /usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64 \
-    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
+    -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
     -v /etc/ascend_install.info:/etc/ascend_install.info \
     -p 7860:7860 \
     -p 8000:8000 \
@@ -479,28 +485,12 @@ docker run -it \
     --shm-size 16G \
     --name llamafactory \
     llamafactory:latest
+
+docker exec -it llamafactory bash
 ```
+
 </details>
 
-#### Use Docker Compose
-
-Firstly enter your docker path:
-
-```bash
-# for NVIDIA GPU users
-cd ./docker/docker-cuda
-
-# for Ascend NPU users
-cd ./docker/docker-npu
-```
-
-Then run the following command to build docker image and start the container:
-
-```bash
-docker-compose up -d
-docker-compose exec llamafactory bash
-```
-
 <details><summary>Details about volume</summary>
 
 - hf_cache: Utilize Hugging Face cache on the host machine. Reassignable if a cache already exists in a different directory.

From ec95f942d1f36dee9facb687ae4168e7c3c4d3f5 Mon Sep 17 00:00:00 2001
From: hoshi-hiyouga <hiyouga@buaa.edu.cn>
Date: Tue, 25 Jun 2024 01:06:59 +0800
Subject: [PATCH 8/8] Update README_zh.md

---
 README_zh.md | 83 ++++++++++++++++++++++++----------------------------
 1 file changed, 38 insertions(+), 45 deletions(-)

diff --git a/README_zh.md b/README_zh.md
index 6326c0b5..3bed0846 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -360,7 +360,7 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl
 
 <details><summary>昇腾 NPU 用户指南</summary>
 
-在昇腾 NPU 设备上安装 LLaMA Factory 时，需要指定额外依赖项，使用 `pip install -e '.[torch-npu,metrics]'` 命令安装。此外，还需要安装 **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**，安装方法请参考[安装教程](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/80RC2alpha002/quickstart/quickstart/quickstart_18_0004.html)或使用以下命令：
+在昇腾 NPU 设备上安装 LLaMA Factory 时，需要指定额外依赖项，使用 `pip install -e ".[torch-npu,metrics]"` 命令安装。此外，还需要安装 **[Ascend CANN Toolkit and Kernels](https://www.hiascend.com/developer/download/community/result?module=cann)**，安装方法请参考[安装教程](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/80RC2alpha002/quickstart/quickstart/quickstart_18_0004.html)或使用以下命令：
 
 ```bash
 # 请替换 URL 为 CANN 版本和设备型号对应的 URL
@@ -383,12 +383,6 @@ source /usr/local/Ascend/ascend-toolkit/set_env.sh
 | torch-npu    | 2.1.0   | 2.1.0.post3 |
 | deepspeed    | 0.13.2  | 0.13.2      |
 
-Docker用户请参考 [构建 Docker](#构建-Docker).
-
-**NOTE**
-
-默认镜像为 [cosdt/cann:8.0.rc1-910b-ubuntu22.04](https://hub.docker.com/layers/cosdt/cann/8.0.rc1-910b-ubuntu22.04/images/sha256-29ef8aacf6b2babd292f06f00b9190c212e7c79a947411e213135e4d41a178a9?context=explore). 更多选择见 [cosdt/cann](https://hub.docker.com/r/cosdt/cann/tags).
-
 请使用 `ASCEND_RT_VISIBLE_DEVICES` 而非 `CUDA_VISIBLE_DEVICES` 来指定运算设备。
 
 如果遇到无法正常推理的情况，请尝试设置 `do_sample: false`。
@@ -425,49 +419,62 @@ llamafactory-cli webui
 
 ### 构建 Docker
 
-#### 使用 Docker
-
-<details><summary>NVIDIA GPU 用户：</summary>
+CUDA 用户：
 
 ```bash
-cd ./docker/docker-cuda
-docker build -f ./Dockerfile \
+docker-compose -f ./docker/docker-cuda/docker-compose.yml up -d
+docker-compose exec llamafactory bash
+```
+
+昇腾 NPU 用户：
+
+```bash
+docker-compose -f ./docker/docker-npu/docker-compose.yml up -d
+docker-compose exec llamafactory bash
+```
+
+<details><summary>不使用 Docker Compose 构建</summary>
+
+CUDA 用户：
+
+```bash
+docker build -f ./docker/docker-cuda/Dockerfile \
     --build-arg INSTALL_BNB=false \
     --build-arg INSTALL_VLLM=false \
     --build-arg INSTALL_DEEPSPEED=false \
     --build-arg PIP_INDEX=https://pypi.org/simple \
     -t llamafactory:latest .
 
-docker run -it --gpus=all \
-    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
-    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
-    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
+docker run -dit --gpus=all \
+    -v ./hf_cache:/root/.cache/huggingface/ \
+    -v ./data:/app/data \
+    -v ./output:/app/output \
     -p 7860:7860 \
     -p 8000:8000 \
     --shm-size 16G \
     --name llamafactory \
     llamafactory:latest
-```
-</details>
 
-<details><summary>Ascend NPU 用户：</summary>
+docker exec -it llamafactory bash
+```
+
+昇腾 NPU 用户：
 
 ```bash
-cd ./docker/docker-npu
-docker build -f ./Dockerfile \
+# 根据您的环境选择镜像
+docker build -f ./docker/docker-npu/Dockerfile \
     --build-arg INSTALL_DEEPSPEED=false \
     --build-arg PIP_INDEX=https://pypi.org/simple \
     -t llamafactory:latest .
 
-# 增加 --device 来使用多卡 NPU 或修改第一个 --device 来更改 NPU 卡
-docker run -it \
-    -v /$(dirname $(dirname "$PWD"))/hf_cache:/root/.cache/huggingface/ \
-    -v /$(dirname $(dirname "$PWD"))/data:/app/data \
-    -v /$(dirname $(dirname "$PWD"))/output:/app/output \
+# 根据您的资源更改 `device`
+docker run -dit \
+    -v ./hf_cache:/root/.cache/huggingface/ \
+    -v ./data:/app/data \
+    -v ./output:/app/output \
     -v /usr/local/dcmi:/usr/local/dcmi \
     -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-    -v /usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64 \
-    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
+    -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
     -v /etc/ascend_install.info:/etc/ascend_install.info \
     -p 7860:7860 \
     -p 8000:8000 \
@@ -478,26 +485,12 @@ docker run -it \
     --shm-size 16G \
     --name llamafactory \
     llamafactory:latest
+
+docker exec -it llamafactory bash
 ```
+
 </details>
 
-#### 使用 Docker Compose
-
-首先进入 docker 目录：
-```bash
-# NVIDIA GPU 用户
-cd ./docker/docker-cuda
-
-# Ascend NPU 用户
-cd ./docker/docker-npu
-```
-然后运行以下命令创建 docker 镜像并启动容器:
-
-```bash
-docker-compose up -d
-docker-compose exec llamafactory bash
-```
-
 <details><summary>数据卷详情</summary>
 
 - hf_cache：使用宿主机的 Hugging Face 缓存文件夹，允许更改为新的目录。