# Based on llama-gpt-api:
# Pin the image to llama-cpp-python 0.1.78 to avoid ggml => gguf breaking changes
FROM ghcr.io/abetlen/llama-cpp-python:latest@sha256:b6d21ff8c4d9baad65e1fa741a0f8c898d68735fff3f3cd777e3f0c6a1839dd4

VOLUME ["/models"]

EXPOSE 8000

ENV PYTHONUNBUFFERED 1
ENV MODEL './models/llama-2-13b-chat.bin'
# ENV MODEL_DOWNLOAD_URL 'https://huggingface.co/TheBloke/Nous-Hermes-Llama-2-7B-GGML/resolve/main/nous-hermes-llama-2-7b.ggmlv3.q4_0.bin'

RUN apt install -y curl
RUN mkdir models
RUN curl -L https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/resolve/main/llama-2-13b-chat.ggmlv3.q4_K_M.bin -o ./models/llama-2-13b-chat.bin

# Build the project
RUN make build

# Run the server
CMD ["python3", "-m", "llama_cpp.server"]