Dockerfile

# Use NVIDIA CUDA base image with Python and Ubuntu
FROM nvidia/cuda:12.6.0-devel-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV TRANSFORMERS_CACHE=/app/cache

# Install Python, pip, and other dependencies
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    git \
    git-lfs \
    curl \
    && git lfs install \
    && curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y \
    && . "$HOME/.cargo/env" \
    && rm -rf /var/lib/apt/lists/*

# Ensure the `python` command points to `python3`
RUN ln -s /usr/bin/python3 /usr/bin/python

# Install Python packages from requirements.txt
COPY requirements.txt /tmp/
RUN . "$HOME/.cargo/env" && pip install --no-cache-dir -r /tmp/requirements.txt

# Add the /app directory as a safe Git directory
RUN git config --global --add safe.directory /app

# Create a non-root user for better security
RUN useradd -m appuser

# Set up a writable working directory
WORKDIR /app

# Create the cache directory
RUN mkdir -p /app/cache

# Copy project files into the container
COPY --chown=appuser:appuser . /app

# Ensure the /app directory and its subdirectories are writable by appuser
RUN chown -R appuser:appuser /app

# Switch to the non-root user for running the application
USER appuser

# Define the command to run the app
CMD ["python", "train.py"]