FROM nvidia/cuda:11.6.0-base-ubuntu20.04 RUN export PATH="/usr/local/cuda/bin:$PATH" RUN apt update && \ apt install --no-install-recommends -y build-essential python3 python3-pip wget curl git && \ apt clean && rm -rf /var/lib/apt/lists/* # Set the working directory in the container to /app WORKDIR /app # Install cmake RUN apt-get install -y wget && \ wget -qO- "https://cmake.org/files/v3.18/cmake-3.18.0-Linux-x86_64.tar.gz" | tar --strip-components=1 -xz -C /usr/local # Copy the requirements.txt file into the container COPY requirements.txt ./ # Install any needed packages specified in requirements.txt RUN pip3 install --upgrade pip && \ pip3 install -r requirements.txt RUN export PATH="/usr/local/cuda/bin:$PATH" RUN pip install ctransformers --no-binary ctransformers # Assume the specific file is hosted somewhere and is publicly accessible, replace the URL with the actual URL #RUN wget -O falcon40b-instruct.ggmlv3.q2_K.bin https://huggingface.co/TheBloke/falcon-40b-instruct-GGML/raw/main/falcon40b-instruct.ggmlv3.q2_K.bin # Change the ownership of the downloaded file to myuser #RUN chown myuser:myuser falcon40b-instruct.ggmlv3.q2_K.bin # Install git and clone the ggllm.cpp repository and build #RUN apt-get install -y git && \ # git clone https://github.com/cmp-nct/ggllm.cpp && \ # cd ggllm.cpp && \ # rm -rf build && mkdir build && cd build && cmake -DGGML_CUBLAS=1 .. && cmake --build . --config Release RUN useradd -m -u 1000 user USER user ENV HOME=/home/user \ PATH=/home/user/.local/bin:$PATH WORKDIR $HOME/app COPY --chown=user . $HOME/app RUN ls -al # Make port available to the world outside this container EXPOSE 7860 # Run uvicorn when the container launches CMD ["python3", "demo.py", "--host", "0.0.0.0", "--port", "7860"]