File size: 1,019 Bytes
4f0cbe4 a8c97c6 4f0cbe4 adfa3e0 4d5a1a5 88556e1 adfa3e0 4f0cbe4 88556e1 4f0cbe4 02746d7 4d5a1a5 ea091e9 b62bba0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 |
# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
# you will also find guides on how best to write your Dockerfile
FROM ghcr.io/ggml-org/llama.cpp:server
ARG MODEL_DOWNLOAD_LINK
ENV MODEL_DOWNLOAD_LINK=${MODEL_DOWNLOAD_LINK:-https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf?download=true}
ENV DEBIAN_FRONTEND=noninteractive
USER root
RUN apt-get update && apt-get install -y wget
RUN mkdir /models && chmod 777 /models
RUN useradd -m -u 1000 user
USER user
ENV PATH="/home/user/.local/bin:$PATH"
WORKDIR /app
COPY --chown=user . /app
RUN wget -nv -O /models/local_model.gguf ${MODEL_DOWNLOAD_LINK}
# CMD ["/app/llama-server", "--host", "0.0.0.0","--port","8080", "-c", "2048","-m","/models/local_model.gguf", "--cache-type-k", "q8_0", "--api-key", "1234", "--parallel", "2" ]
CMD ["--host", "0.0.0.0","--port","8080","-m","/models/local_model.gguf", "--cache-type-k", "q8_0", "--api-key", "1234", "--parallel", "2" ]
|