Card corrections: adapter parameter accounting (24,576*r file + 367,616 embedding/output = trainable set, % of the 25,665,536 full-FT set); classical split provenance; released-checkpoint epoch note; fix a section reference

Fix genre-token counts (8 beyond base vocab, not 9) and state-dict vs unique-param phrasing

Rewrite model card: clean standard form (usage / eval / training data / license)

docs: standardize link-block (GitHub/@StudioPearlLee), Phase-0, real-song-eval format

docs: R9 cosmetic polish (formatting/wording/citation; no number changes)

docs: data-faithfulness fix (rock splits revert to actual 4,891 eval set; country/classical source; ±0.4 noise)

docs: data-faithfulness corrections (F2 best-epoch row; pop deltas vs held-out 84.21 baseline; Chordonomicon CC BY-NC; paper attribution/links)

Update card: multi-seed n=3 (jazz 75.76±0.03, seeds 42/123/7) + seed/data-dependent selection caveat + 6-src(167)/9-src(501) test-set qualifiers

Update model card: per-genre LoRA eval table

Card erratum: released F1 weights coincide with Phase-0 baseline (selection artifact)

Update model card: per-genre LoRA eval table

Add pipeline tag and links to paper, code, and project page (#1)

docs: fill arXiv2 ID (2606.07334) in citation (companion LoRA paper now on arXiv)

Add generated audio samples (chord-only + adapter/base output)

Add demo video link (youtu.be/iSDj4VK9nKc)

Card fix: deduplicate real-song-eval block + add begin marker (license + GPU naming preserved)

Update card: per-genre real-song eval (F1)

Update model card: per-genre LoRA eval table

Update model card: per-genre LoRA eval table

Update card: per-genre real-song eval (F1)

Update card: per-genre real-song eval (F1)

Update model card: add per-genre LoRA evaluation table (workshop paper)

Fill in arXiv ID 2605.04998

Initial release: TheArtist chord-generation paper companion

initial commit