{
    "module": "keras_hub.src.models.siglip.siglip_backbone",
    "class_name": "SigLIPBackbone",
    "config": {
        "name": "sig_lip_backbone",
        "trainable": true,
        "vision_encoder": {
            "module": "keras_hub.src.models.siglip.siglip_vision_encoder",
            "class_name": "SigLIPVisionEncoder",
            "config": {
                "name": "sig_lip_vision_encoder",
                "trainable": true,
                "patch_size": 16,
                "hidden_dim": 1536,
                "num_layers": 40,
                "num_heads": 16,
                "intermediate_dim": 6144,
                "intermediate_activation": "gelu_approximate",
                "layer_norm_epsilon": 1e-06,
                "image_shape": [
                    256,
                    256,
                    3
                ]
            },
            "registered_name": "keras_hub>SigLIPVisionEncoder"
        },
        "text_encoder": {
            "module": "keras_hub.src.models.siglip.siglip_text_encoder",
            "class_name": "SigLIPTextEncoder",
            "config": {
                "name": "sig_lip_text_encoder",
                "trainable": true,
                "vocabulary_size": 256000,
                "embedding_dim": 1152,
                "hidden_dim": 1152,
                "num_layers": 27,
                "num_heads": 16,
                "intermediate_dim": 4304,
                "intermediate_activation": "gelu_approximate",
                "layer_norm_epsilon": 1e-06,
                "max_sequence_length": 64
            },
            "registered_name": "keras_hub>SigLIPTextEncoder"
        }
    },
    "registered_name": "keras_hub>SigLIPBackbone"
}