Model | Layers | Hidden size D | MLP size | Heads | Parasm |
ViT-Base | 12 | 768 | 3072 | 12 | 86M |
ViT-Large | 24 | 1024 | 4096 | 16 | 307M |
ViT-Huge | 32 | 1280 | 5120 | 16 | 632M |