Fetching metadata from the HF Docker repository...
-
feat: gentler fine-tune + diversified synth data + interpretation engine + before/after eval
Codex
- modal_finetune: lower LR (2e-5) + warmup, 1 epoch, tunable hyperparams; re-runnable merge.
- synth_reports: section-grouped/varied layouts + ref-range/theme/demographic diversity to fix overfitting that regressed real-report extraction.
- modal_eval: Modal before/after eval (base vs fine-tuned) on the labeled reports.
- kb/knowledge_base + interpretation: grounded per-marker insight + cross-marker patterns (Phase 3).
