{
  "architectures": [
    "Siglip2VisionModel"
  ],
  "attention_dropout": 0.0,
  "dtype": "float32",
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_size": 768,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-06,
  "model_type": "siglip2_vision_model",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "num_patches": 256,
  "patch_size": 16,
  "transformers_version": "5.8.1"
}