Dockerfile

FROM python:3.11-slim

# Install build tools for torch.compile
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Create a non-root user with home directory for cache
RUN useradd -m -u 1000 user
USER user

WORKDIR /home/user/app

# Set cache directory to user's home
ENV HOME=/home/user
ENV HF_HOME=/home/user/.cache/huggingface
ENV TRANSFORMERS_CACHE=/home/user/.cache/huggingface/transformers
ENV HF_DATASETS_CACHE=/home/user/.cache/huggingface/datasets

# Install dependencies as user (use --user flag)
RUN pip install --user --no-cache-dir \
    torch \
    transformers>=4.48.0 \
    datasets \
    evaluate \
    seqeval \
    accelerate>=1.0.0 \
    huggingface_hub \
    gradio

# Add user's pip bin to PATH
ENV PATH="/home/user/.local/bin:${PATH}"

# Copy training script and app
COPY --chown=user:user train.py .
COPY --chown=user:user app.py .

# Expose Gradio port
EXPOSE 7860

# Run Gradio app which starts training in background
CMD ["python", "app.py"]