architectures · meta-research
Self-supervised ViT features for universal vision tasks without fine-tuning.
| Weight file SHA-256 | 0cd4de96229fa32588e45239658140f3bf868694ea461d0e30bacbce2ee2be70 |
|---|
| Publisher | meta-research |
|---|---|
| Origin | United States |
| Licence | Apache-2.0 |
| Modality | Image |
| Pulls recorded here | 57,001 |
Registry record as of 2026-06-06. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.