Dockerfile.llamacpp

FROM intel/oneapi-runtime:latest

RUN apt-get update && apt-get install -y --no-install-recommends \
    aria2 \
    unzip \
    && rm -rf /var/lib/apt/lists/*

RUN useradd -m -u 1000 user

USER user

ENV HOME=/home/user

WORKDIR $HOME/app

ARG LLAMA_CPP_VERSION

RUN aria2c -c -x16 https://github.com/MZWNET/actions/releases/download/llama_cpp-$LLAMA_CPP_VERSION/llama-$LLAMA_CPP_VERSION-bin-linux-avx2-intel-mkl-x64.zip \
    && unzip llama-$LLAMA_CPP_VERSION-bin-linux-avx2-intel-mkl-x64.zip -d llama.cpp \
    && mv llama.cpp/server . \
    && chmod +x ./server \
    && rm -rf llama-$LLAMA_CPP_VERSION-bin-linux-avx2-intel-mkl-x64.zip llama.cpp

RUN aria2c -c -x16 https://huggingface.co/mzwing/AquilaChat2-7B-16K-GGUF/resolve/main/AquilaChat2-7B-16K.Q3_K_L.gguf?download=true -o AquilaChat2-7B-16K.Q3_K_L.gguf

COPY --chown=user start.sh .

RUN chmod +x start.sh

EXPOSE 8080

CMD ["bash", "start.sh"]