Merge pull request #2743 from S3Studio/DockerizeSupport

Add dockerize support

.dockerignore

@@ -0,0 +1,11 @@
+.vscode
+.git
+.github
+.venv
+cache
+data
+examples
+.dockerignore
+.gitattributes
+.gitignore
+Dockerfile

Dockerfile

@@ -0,0 +1,15 @@
+FROM cnstark/pytorch:2.0.1-py3.9.17-cuda11.8.0-ubuntu20.04
+
+WORKDIR /app
+
+COPY requirements.txt /app/
+RUN pip install -r requirements.txt && \
+    pip install tiktoken && \
+    pip install transformers_stream_generator
+
+COPY . /app/
+
+VOLUME [ "/root/.cache/huggingface/", "/app/data", "/app/output" ]
+EXPOSE 7860
+
+CMD [ "python", "src/train_web.py" ]

README.md

@@ -651,6 +651,32 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
 > [!TIP]
 > We recommend using `--per_device_eval_batch_size=1` and `--max_target_length 128` at 4/8-bit predict.
 
+### Dockerize Training
+
+#### Get ready
+
+Necessary dockerized environment is needed, such as Docker or Docker Compose.
+
+#### Docker support
+
+```bash
+docker build -f ./Dockerfile -t llama-factory:latest .
+
+docker run --gpus=all -v ./hf_cache:/root/.cache/huggingface/ -v ./data:/app/data -v ./output:/app/output -p 7860:7860 --shm-size 16G --name llama_factory -d llama-factory:latest
+```
+
+#### Docker Compose support
+
+```bash
+docker compose -f ./docker-compose.yml up -d
+```
+
+> [!TIP]
+> Details about volume:
+> * hf_cache: Utilize Huggingface cache on the host machine. Reassignable if a cache already exists in a different directory.
+> * data: Place datasets on this dir of the host machine so that they can be selected on LLaMA Board GUI.
+> * output: Set export dir to this location so that the merged result can be accessed directly on the host machine.
+
 ## Projects using LLaMA Factory
 
 1. Wang et al. ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation. 2023. [[arxiv]](https://arxiv.org/abs/2308.02223)

docker-compose.yml

@@ -0,0 +1,23 @@
+version: '3.8'
+
+services:
+  llama-factory:
+    build:
+      dockerfile: Dockerfile
+      context: .
+    container_name: llama_factory
+    volumes:
+      - ./hf_cache:/root/.cache/huggingface/
+      - ./data:/app/data
+      - ./output:/app/output
+    ports:
+      - "7860:7860"
+    shm_size: 16G
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: "all"
+            capabilities: [gpu]
+    restart: unless-stopped