Dockerfile

# D1337 CIPHER - Custom Training Environment
# Optimized for 4x L40S (192GB VRAM) with QLoRA

FROM nvidia/cuda:12.1.0-cudnn8-devel-ubuntu22.04

# Set environment
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512
ENV TOKENIZERS_PARALLELISM=false
ENV HF_HOME=/app/.cache/huggingface

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3-pip \
    python3.10-venv \
    git \
    git-lfs \
    curl \
    wget \
    && rm -rf /var/lib/apt/lists/* \
    && git lfs install

# Create user for HuggingFace Spaces
RUN useradd -m -u 1000 user
USER user
ENV PATH="/home/user/.local/bin:$PATH"

WORKDIR /app

# Copy requirements first (for caching)
COPY --chown=user requirements.txt .

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

# Copy application files
COPY --chown=user . .

# Expose port for Gradio
EXPOSE 7860

# Set HuggingFace cache directory
RUN mkdir -p /app/.cache/huggingface

# Run training script
CMD ["python3", "train.py"]