Dockerfile

FROM pytorch/pytorch:2.0.1-cuda11.7-cudnn8-runtime

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV HF_HOME=/app/.cache/huggingface
ENV TRANSFORMERS_CACHE=/app/.cache/huggingface/transformers
ENV PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:128

# Create necessary directories with proper permissions
RUN mkdir -p /app/.cache/huggingface/transformers && \
    chmod -R 777 /app

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    git \
    curl \
    ca-certificates \
    python3-pip \
    && rm -rf /var/lib/apt/lists/*

# Create a working directory
WORKDIR /app

# Copy requirements file
COPY requirements.txt ./requirements.txt

# Install dependencies
RUN pip3 install --no-cache-dir --upgrade pip && \
    pip3 install --no-cache-dir -r requirements.txt

# Copy the diagnostic script
COPY debug_model_loading.py ./app.py

# Make port 7860 available 
EXPOSE 7860

# Run the diagnostic
CMD ["python3", "app.py"]