clip_vision_siglip_512.json

{
  "num_channels": 3,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_size": 1152,
  "image_size": 512,
  "intermediate_size": 4304,
  "model_type": "siglip_vision_model",
  "num_attention_heads": 16,
  "num_hidden_layers": 27,
  "patch_size": 16,
  "image_mean": [0.5, 0.5, 0.5],
  "image_std": [0.5, 0.5, 0.5]
}