SiHC research checkpoints
Selected Group 1 epoch-200 model weights (manifest.json), plus historical flagship and scaling-law weights (manifest_flagship_scaling.json). For the large-model batch, epoch = step / 1251. Historical 40x1024 is epoch440; 28x1152 is epoch80. L-wide/deep are epoch200; H no-dropout includes epoch200 and epoch280; H projdrop0.2 is epoch80. Latest is not a claim of best FID. The H drop0.1 attempt has no checkpoint and is not included.
Public derivatives retain raw model, EMA(s), and allowlisted architecture configuration only. No optimizer, RNG, credentials, W&B identity or local paths are included. These are inference weights, not full training-resume backups. Original checkpoints remain unchanged in the owner's local archive.
No ImageNet images/caches, teacher weights, private logs or security evidence are included. CPU restricted loading and remote file sizes are checked; this release does not claim a fresh GPU/evaluation validation. Use weights_only=True to load. Architectures differ between runs; inspect metadata rather than guessing from names.