| { | |
| "model_cfg": { | |
| "embed_dim": 768, | |
| "vision_cfg": { | |
| "image_size": 224, | |
| "layers": 24, | |
| "width": 1024, | |
| "patch_size": 14 | |
| }, | |
| "text_cfg": { | |
| "context_length": 77, | |
| "vocab_size": 49408, | |
| "width": 768, | |
| "heads": 12, | |
| "layers": 12 | |
| } | |
| }, | |
| "preprocess_cfg": { | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| } | |
| } |