Dockerfile

FROM ghcr.io/ggml-org/llama.cpp:full

RUN apt update && apt install wget -y

# Install necessary dependencies
RUN pip install -U "huggingface_hub[cli]"

# Log in to Hugging Face using the CLI
RUN --mount=type=secret,id=HF_TOKEN \
    huggingface-cli login --token $(cat /run/secrets/HF_TOKEN)

# Download the gated model
RUN huggingface-cli download google/gemma-3-4b-it-qat-q4_0-gguf gemma-3-4b-it-q4_0.gguf --local-dir /
RUN huggingface-cli download google/gemma-3-4b-it-qat-q4_0-gguf mmproj-model-f16-4B.gguf --local-dir /

CMD ["--server", "-m", "/gemma-3-4b-it-q4_0.gguf", "--mmproj", "/mmproj-model-f16-4B.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "512"]