checkpoints/v2_semantic_ground_implicit_t2i/vit_config.json

{
    "hidden_size": 1152,
    "image_size": 980,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14
}