{
  "_name_or_path": "google/vit-base-patch16-224-in21k",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "documents",
    "1": "castle",
    "2": "looking downstream from the footbridge",
    "3": "stadium",
    "4": "dynamikum",
    "5": "fireworks",
    "6": "park",
    "7": "memorial tablet",
    "8": "views from the lookout tower",
    "9": "trams",
    "10": "museum"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "documents": "0",
    "castle": "1",
    "dynamikum": "4",
    "stadium": "3",
    "Looking downstream from the footbridge": "2",
    "fireworks": "5",
    "park": "6",
    "memorial tablet": "7",
    "views from the lookout tower": "8",
    "trams": "9",
    "museum": "10"
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.25.1"
}