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

RUN apt update && apt install wget -y

# Download the coding-specialized model
RUN wget "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_k_m.gguf" -O /Qwen2.5-Coder-7B-Q4_K_M.gguf

CMD ["--server", \
     "-m", "/Qwen2.5-Coder-7B-Q4_K_M.gguf", \
     "--port", "7860", \
     "--host", "0.0.0.0", \
     "--ctx-size", "32768", \
     "--n-predict", "-1", \
     "--threads", "2", \
     "--jinja"]