ggml-mllm / Dockerfile
matthoffner's picture
Update Dockerfile
f3eab1a
raw
history blame
453 Bytes
FROM ghcr.io/abetlen/llama-cpp-python:latest
ENV PYTHONUNBUFFERED 1
EXPOSE 8000
WORKDIR /app
RUN apt-get install curl
RUN curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | bash
RUN apt-get install git-lfs
RUN git clone https://huggingface.co/TheBloke/wizardLM-7B-GGML/blob/main/wizardLM-7B.ggml.q5_1.bin
RUN ls
COPY . .
RUN ls -al
CMD ["python3", "-m", "llama_cpp.server", "--model", "wizardLM-7B.ggml.q5_1.bin"]