set shell := ["bash", "-uc"]

validate:
    uv run dataset/validate_schema.py
    uv run dataset/score_data.py
    for f in data/*.jsonl; do \
      uv run dataset/analyze_data.py --input "$f" --show-examples 0; \
    done

score:
    uv run dataset/score_data.py

schema:
    uv run dataset/validate_schema.py

analyze:
    for f in data/*.jsonl; do \
      uv run dataset/analyze_data.py --input "$f" --show-examples 0; \
    done

prepare:
    QMD_BASE_MODEL=Qwen/Qwen3-1.7B uv run dataset/prepare_data.py --seed 42

convert-onnx size="1.7B":
    uv run convert_onnx.py --size {{size}}

convert-gguf size="1.7B":
    uv run convert_gguf.py --size {{size}}

train-local:
    just prepare
    HF_TOKEN=${HF_TOKEN} uv run torchrun --standalone --nproc_per_node auto \
      train.py sft --config configs/sft_local.yaml |& tee /tmp/qmd-sft-train.log

# Experimental GRPO training is in finetune/experiments/grpo and not part of
# the default pipeline.
#
# grpo-local:
#   HF_TOKEN=${HF_TOKEN} uv run train.py grpo --config experiments/grpo/grpo.yaml |& tee /tmp/qmd-grpo-train.log