# psyc training container — unsloth + Qwen3.5 QLoRA fine-tuning.
#
# Build:
#   docker build -t psyc-trainer -f Dockerfile.train .
#
# Run (24 GB GPU; mounts host data/ + scripts/ so script edits need no rebuild):
#   docker run --gpus all --rm --entrypoint python \
#       -v $(pwd)/data:/data -v $(pwd)/scripts:/scripts \
#       psyc-trainer /scripts/train_qlora.py \
#       --dataset /data/datasets/ioc_extraction-v2.jsonl \
#       --dataset /data/datasets/severity_classification-v2.jsonl \
#       --dataset /data/datasets/routing_decision-v2.jsonl \
#       --dataset /data/datasets/tlp_assignment-v2.jsonl \
#       --output /data/adapters/psyc-v2
#
# Base image already ships Python 3.11 + torch 2.6 + CUDA 12.4 + cuDNN9, so
# there is no apt step and no torch download. Qwen3.5 needs transformers v5 —
# unsloth pulls it automatically. The training/eval scripts are MOUNTED at run
# time (not baked in) so editing scripts/*.py never needs an image rebuild.

FROM pytorch/pytorch:2.6.0-cuda12.4-cudnn9-devel

ENV PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    HF_HOME=/data/.hf-cache

RUN pip install --upgrade pip && \
    pip install unsloth unsloth_zoo trl datasets

# fastapi + uvicorn power scripts/serve_model.py (the inference server).
RUN pip install fastapi uvicorn

WORKDIR /workspace

# Scripts are mounted at run time (-v $(pwd)/scripts:/scripts), never baked in.
ENTRYPOINT ["python"]