{
    "_name_or_path": "siglip-model",
    "architectures": [
      "SiglipVisionModel"
    ],
    "image_grid_pinpoints": [
        [384,768],
        [384,1152],
        [384,1536],
        [384,1920],
        [384,2304],
        [384,2688],
        [384,3072],
        [384,3456],
        [384,3840],
        [768,384],
        [768,768],
        [768,1152],
        [768,1536],
        [768,1920],
        [1152,384],
        [1152,768],
        [1152,1152],
        [1536,384],
        [1536,768],
        [1920,384],
        [1920,768],
        [2304,384],
        [2688,384],
        [3072,384],
        [3456,384],
        [3840,384]
    ],
    "mm_patch_merge_type": "spatial_unpad",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "transformers_version": "4.45.0.dev0",
    "layer_norm_eps": 1e-6,
    "hidden_act": "gelu_pytorch_tanh",
    "projection_dim": 0,
    "vision_feature_layer": [-24, -20, -12, -1]
}