{
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "image_size": 512,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "image_mean": [0.5, 0.5, 0.5],
    "image_std": [0.5, 0.5, 0.5],
    "use_head": true
  }