Version | Commit message | Commit author | Last scanned | ||
|---|---|---|---|---|---|
| eval: publish governed contract base comparison (#2) | betterwithage | Oct 3, 2026 | |||
| card: publish the reviewed curated card (szl-forge willay/card/README.md, metadata/prose only) (#4) | betterwithage | Oct 1, 2026 | |||
| docs(card): estate audit 2026-09-25 — honest labels, dead links, metadata (#3) | betterwithage | Oct 1, 2026 | |||
| Merged full-precision checkpoint (receipted) + config fixes | betterwithage | Sep 13, 2026 | |||
| Add per-repo CycloneDX BOM (canonical registry: datasets/SZLHOLDINGS/model-bom) | betterwithage | Sep 2, 2026 | |||
| Add per-repo CycloneDX BOM (canonical registry: datasets/SZLHOLDINGS/model-bom) | betterwithage | Sep 1, 2026 | |||
| Materialize declared Apache-2.0 license | betterwithage | Sep 1, 2026 | |||
| fix: correct metadata and quickstart — PEFT adapter, not a transformers checkpoint | betterwithage | Never scanned | |||
| security(model): replace pickle training arguments with JSON | betterwithage | Never scanned | |||
| chore(receipt): MEASURED unique Unsloth willay (eval none-this-run) | betterwithage | Aug 30, 2026 | |||
| feat(adapter): unique Unsloth willay Doctrine mouth. rsLoRA rank-8 attn+mlp packing=false. Short ctx. | betterwithage | Aug 30, 2026 | |||
| feat(train): unique Unsloth GPU trainer (adapter-unsloth/, does not clobber R1 signed khipu) | betterwithage | Never scanned | |||
| weights(atelier): CPU NumPy silhouette seed=20260721 — not a GPU retrain | betterwithage | Aug 29, 2026 | |||
| atelier: one-of-one card — cut, silhouette, GitHub Python. YAML preserved. | betterwithage | Aug 29, 2026 | |||
| End of training | betterwithage | Aug 29, 2026 | |||
| docs(card): INTI copy contract — ROADMAP. first sentence + roadmap tag | betterwithage | Never scanned | |||
| docs(card): Series A WILLAY signed-refusal card — cutting, no weights yet | betterwithage | Never scanned | |||
| initial commit | betterwithage | Jan 27, 2026 | |||
27
18