Dockerfile

FROM python:3.10.9

# Set the working directory to /
WORKDIR /

# Copy the current directory contents into the container at .
COPY . .

RUN pip install transformers

# Install pytorch starts

RUN pip install torch

#Install pytorch ends

RUN pip install accelerate

# Install hugging face hub to download llama2 model
RUN pip install --upgrade huggingface_hub
RUN CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install 'llama-cpp-python[server]' --upgrade --force-reinstall --no-cache-dir 
# Install requirements.txt 
RUN pip install --no-cache-dir --upgrade -r /requirements.txt

# write access
RUN useradd -m -u 1000 user

USER user

ENV HOME=/home/user \
	PATH=/home/user/.local/bin:$PATH

WORKDIR $HOME/app

RUN huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False


COPY --chown=user . $HOME/app

# Start the FastAPI app on port 7860, the default port expected by Spaces
CMD ["uvicorn", "question_paper:app", "--host", "0.0.0.0", "--port", "7860"]