Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.8-slim

# Set the working directory in the container
WORKDIR /usr/src/app

# Install system dependencies
RUN apt-get update && apt-get install -y \
  wget \
  git \
  build-essential

# Clone llama.cpp
RUN git clone https://github.com/ggerganov/llama.cpp.git

# Download the model
RUN cd llama.cpp/models && \
    wget -O stablelm-2-zephyr-1_6b-Q4_0.gguf https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b/resolve/main/stablelm-2-zephyr-1_6b-Q4_0.gguf?download=true

# Build llama.cpp
RUN cd llama.cpp && \
    make -j

# Set MPLCONFIGDIR to a writable directory
ENV MPLCONFIGDIR /usr/src/app/flagged

# Make sure the directory exists and has proper permissions
RUN mkdir -p $MPLCONFIGDIR && chmod -R 777 $MPLCONFIGDIR

# Copy the current directory contents into the container at /usr/src/app
COPY . .

# Install any needed packages specified in requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

# Make port 7860 available to the world outside this container
EXPOSE 7860

# Run app.py when the container launches
CMD ["python", "./app.py"]