{
  "architecture": "vit_small_patch16_224",
  "num_classes": 0,
  "num_features": 384,
  "global_pool": "token",
  "pretrained_cfg": {
    "tag": "dino",
    "custom_load": false,
    "input_size": [
      3,
      224,
      224
    ],
    "fixed_input_size": true,
    "interpolation": "bicubic",
    "crop_pct": 0.9,
    "crop_mode": "center",
    "mean": [
      0.485,
      0.456,
      0.406
    ],
    "std": [
      0.229,
      0.224,
      0.225
    ],
    "num_classes": 0,
    "pool_size": null,
    "first_conv": "patch_embed.proj",
    "classifier": "head"
  },
  "architectures": [
    "ViTModel"
  ],
  "attention_probs_dropout_prob": 0.0,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 384,
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 6,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "torch_dtype": "float32",
  "transformers_version": "4.10.0.dev0"
}