| { | |
| "module": "keras_hub.src.models.clip.clip_backbone", | |
| "class_name": "CLIPBackbone", | |
| "config": { | |
| "name": "clip_backbone", | |
| "trainable": true, | |
| "vision_encoder": { | |
| "module": "keras_hub.src.models.clip.clip_vision_encoder", | |
| "class_name": "CLIPVisionEncoder", | |
| "config": { | |
| "name": "clip_vision_encoder", | |
| "trainable": true, | |
| "patch_size": 14, | |
| "hidden_dim": 1664, | |
| "num_layers": 48, | |
| "num_heads": 16, | |
| "intermediate_dim": 8192, | |
| "intermediate_activation": "gelu", | |
| "intermediate_output_index": null, | |
| "image_shape": [ | |
| 224, | |
| 224, | |
| 3 | |
| ] | |
| }, | |
| "registered_name": "keras_hub>CLIPVisionEncoder" | |
| }, | |
| "text_encoder": { | |
| "module": "keras_hub.src.models.clip.clip_text_encoder", | |
| "class_name": "CLIPTextEncoder", | |
| "config": { | |
| "name": "clip_text_encoder", | |
| "trainable": true, | |
| "vocabulary_size": 49408, | |
| "embedding_dim": 1280, | |
| "hidden_dim": 1280, | |
| "num_layers": 32, | |
| "num_heads": 20, | |
| "intermediate_dim": 5120, | |
| "intermediate_activation": "gelu", | |
| "intermediate_output_index": null, | |
| "max_sequence_length": 77 | |
| }, | |
| "registered_name": "keras_hub>CLIPTextEncoder" | |
| }, | |
| "projection_dim": 1280 | |
| }, | |
| "registered_name": "keras_hub>CLIPBackbone" | |
| } |