The released -ema.ckpt files carried three copies of the weights' worth of data: the EMA state_dict, a duplicate SimpleEMA shadow copy, and optimizer state. Since generate.py treats -ema.ckpt as already-EMA, the shadow copy is redundant for every published use. Dropping callbacks, optimizer_states, lr_schedulers and loops takes the flow checkpoint from 4.21 to 1.74 GB and the autoencoder from 3.10 to 1.03 GB. All 1257 and 699 weight tensors are bit-identical to the originals, and generation at seed 42 reproduces the full-checkpoint output exactly. Full-checkpoint digests stay recorded in release-checkpoints.json and provenance.json; resuming a training run needs those, which are not distributed.
Release the 2026-10-15 hero flow model and unified autoencoder
Replaces the bundle and the stable checkpoint aliases with the hero/unified-AE pair (latent dim 16 -> 32, residue vocabulary 33 -> 147 classes). Removes the previous release's dated filenames, which duplicated the aliases byte for byte; they remain available through the repository history.
13 days ago
Add stable release checkpoint names and pair checksums
