Model lineage — from MusicGen/Meta to Foundation One¶
The version specifics here are confirmed against the model board (version registry, snapshot 2026-06-08). Narrative context is from the transcript evaluation.
Compiled truth¶
The model line has two eras:
- MusicGen on Meta checkpoints (the
0.xline). Every released0.xversion is a MusicGen model on a Meta checkpoint — mostly musicgen-small, with a large variant at 0.8.1L. The lineage ran0.5.x → 0.6.0 → 0.7.1 → 0.8.x, improving by changing the data each version trained on (e.g. 0.7.1 added MiDasheng-enriched metadata; 0.6.0 added Omnisphere/REVO sounds; 0.5.4 fixed piano Serum sounds; pitch handling moved C4 → C3). 0.7.1 is the current production model. 0.8.1L (large) vs 0.8.2 (small, AI-assisted parameter tuning) are the two in testing. - Foundation One (the
F1.xline) — the own-model next generation.F1.0.0andF1.0.0Aare in training now: the move beyond MusicGen to Deep Noise's own foundation model (built on a fork of Stability AI'sstable-audio-tools), trained on the ~2.5M licensed/CC0 corpus.F1.0.0Ais on synthetic/Serum batches (5–11);F1.0.0adds VST/acoustic batches.
Full table: version registry. Quality is gated by Arseniy listening to the audio samples emitted every 10 epochs — see 0006 agent system layers and quality gates.
Compute: Foundation One is migrating Google Cloud → the NVIDIA/Brev 8×H100
cluster for a 2-month sprint; indicative split 1×80 GB for the foundation model,
the rest for MusicGen ([VERIFY] exact split). See training spine.
Relationships¶
- version registry
- training spine
- training
- corpus quality
- README
Timeline¶
- 2026-06-08 — Lineage compiled from the transcript evaluation; the speculative architecture list (ACE-step/DDSP/ASEP) was removed and the version facts reconciled to the model board — see version registry. Source: self.