Dockerfile

FROM ubuntu:24.04

WORKDIR /app

RUN apt-get update && apt-get install -y curl libgomp1 && rm -rf /var/lib/apt/lists/*

RUN curl -L -o llama.tar.gz https://github.com/ggml-org/llama.cpp/releases/download/b8469/llama-b8469-bin-ubuntu-x64.tar.gz \
    && tar -xzf llama.tar.gz \
    && rm llama.tar.gz \
    && find . -name "*.so*" -exec cp {} /app/ \; \
    && find . -name "llama-server" -exec cp {} /app/ \; \
    && chmod +x /app/llama-server

# DeepSeek-Coder-1.3B (4-bit Q4_K_M version)
RUN curl -L -o deepseek-coder-1.3b-instruct-q4_k_m.gguf "https://huggingface.co/Vedika-AI/deepseek-coder-1.3b-instruct-Q4_K_M-GGUF/resolve/main/deepseek-coder-1.3b-instruct-q4_k_m.gguf"

ENV LD_LIBRARY_PATH=/app

EXPOSE 7860

CMD ["./llama-server", "-m", "deepseek-coder-1.3b-instruct-q4_k_m.gguf", "--host", "0.0.0.0", "--port", "7860", "-c", "4096", "--threads", "8", "--temp", "0.2"]