| { | |
| "sam": { | |
| "params": 95569152, | |
| "architecture": "SAM ViT-B", | |
| "image_size": 1024, | |
| "patch_size": 16, | |
| "embed_dim": 768, | |
| "depth": 12, | |
| "num_heads": 12 | |
| }, | |
| "clip": { | |
| "params": 303177728, | |
| "architecture": "CLIP-Large", | |
| "image_size": 224, | |
| "patch_size": 14, | |
| "width": 1024, | |
| "layers": 24, | |
| "heads": 16 | |
| }, | |
| "projector": { | |
| "params": 2622720, | |
| "type": "linear", | |
| "input_dim": 2048, | |
| "output_dim": 1280 | |
| }, | |
| "total_params": 401369600, | |
| "output_tokens": 256, | |
| "output_dim": 1280 | |
| } |