Dockerfile

# Zelin-4B Training Pipeline
# Runs on HF Spaces (CPU free tier or GPU paid)
FROM python:3.10-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    git cmake build-essential \
    && rm -rf /var/lib/apt/lists/*

# Install Python dependencies
RUN pip install --no-cache-dir \
    gradio \
    huggingface-hub \
    datasets \
    torch --index-url https://download.pytorch.org/whl/cpu

# Copy application
COPY training/app.py /app/app.py
COPY data/ /app/data/

# Expose Gradio port
EXPOSE 7860

# Set environment
ENV GRADIO_SERVER_NAME=0.0.0.0
ENV GRADIO_SERVER_PORT=7860

CMD ["python", "app.py"]