Dockerfile

# Hayat Elixir AI V5 - Meditron3-70B QLoRA Training
# ERROR-PROOF Dockerfile - addresses all 16 known HF Space errors
# Last updated: Feb 2026

# ERR-07 FIX: CUDA 12.1 base image (PyTorch 2.5.1 requires CUDA 12.1+)
FROM nvidia/cuda:12.1.0-devel-ubuntu22.04

# ERR-08 FIX: Set cache paths BEFORE any model downloads
# HF containers run as non-root (UID 1000) — cannot write to /.cache
ENV DEBIAN_FRONTEND=noninteractive
ENV HF_HOME=/app/hf_cache
ENV TRANSFORMERS_CACHE=/app/hf_cache
ENV TORCH_HOME=/app/torch_cache
ENV PYTHONUNBUFFERED=1

# System dependencies
RUN apt-get update && apt-get install -y \
    python3 python3-pip git wget curl \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# ERR-08 FIX: chmod BEFORE pip install to avoid permission issues
RUN chmod -R 777 /app

# ERR-07 FIX: PyTorch >= 2.4 (we use 2.5.1 with CUDA 12.1)
RUN pip3 install --no-cache-dir \
    torch==2.5.1 --index-url https://download.pytorch.org/whl/cu121

# ERR-09 FIX: Pin ALL dependency versions exactly
# ERR-10 FIX: Include 'rich' explicitly (trl requires it but doesn't declare it)
RUN pip3 install --no-cache-dir \
    transformers==4.46.0 \
    peft==0.13.0 \
    trl==0.9.6 \
    bitsandbytes==0.44.1 \
    accelerate==1.0.0 \
    datasets==3.0.0 \
    huggingface_hub==0.26.0 \
    rich \
    flask \
    scipy \
    sentencepiece \
    protobuf

# Copy training script and data
COPY train.py /app/
COPY hayat_writer_v5_MASTER.jsonl /app/

# ERR-08 FIX: Ensure all directories writable after copy
RUN chmod -R 777 /app

# ERR-16 NOTE: Port 7860 for HF health check (may return HTML from proxy — use logs instead)
EXPOSE 7860

CMD ["python3", "train.py"]