File size: 675 Bytes
536ac2d 77ee54e 536ac2d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 |
# 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
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"] |