config.json

{
    "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": 32,
                "hidden_dim": 768,
                "num_layers": 12,
                "num_heads": 12,
                "intermediate_dim": 3072,
                "intermediate_activation": "quick_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": 512,
                "hidden_dim": 512,
                "num_layers": 12,
                "num_heads": 8,
                "intermediate_dim": 2048,
                "intermediate_activation": "quick_gelu",
                "intermediate_output_index": null,
                "max_sequence_length": 77
            },
            "registered_name": "keras_hub>CLIPTextEncoder"
        },
        "projection_dim": 512
    },
    "registered_name": "keras_hub>CLIPBackbone"
}