ggml-mllm / Dockerfile
matthoffner's picture
Update Dockerfile
d99bd36
raw
history blame
636 Bytes
FROM python:latest
ENV PYTHONUNBUFFERED 1
EXPOSE 8080
WORKDIR /app
RUN wget -qO- "https://cmake.org/files/v3.17/cmake-3.17.0-Linux-x86_64.tar.gz" | tar --strip-components=1 -xz -C /usr/local
RUN git clone https://github.com/abetlen/llama-cpp-python
RUN CMAKE_ARGS="-DLLAMA_OPENBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
RUN pip install uvicorn fastapi toml
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
COPY . .
RUN ls -al
CMD uvicorn main:app --host 0.0.0.0 --port 8080 --workers 2