{
  "_name_or_path": "google/vit-base-patch16-224",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Italian",
    "1": "Russian",
    "2": "Mexican",
    "3": "French",
    "4": "Belgian",
    "5": "Spanish",
    "6": "Dutch",
    "7": "Austrian",
    "8": "Flemish",
    "9": "Spanish,Greek",
    "10": "German",
    "11": "French,British",
    "12": "French,Jewish,Belarusian",
    "13": "British",
    "14": "Norwegian",
    "15": "German,Swiss",
    "16": "American"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "American": 16,
    "Austrian": 7,
    "Belgian": 4,
    "British": 13,
    "Dutch": 6,
    "Flemish": 8,
    "French": 3,
    "French,British": 11,
    "French,Jewish,Belarusian": 12,
    "German": 10,
    "German,Swiss": 15,
    "Italian": 0,
    "Mexican": 2,
    "Norwegian": 14,
    "Russian": 1,
    "Spanish": 5,
    "Spanish,Greek": 9
  },
  "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": "4.46.2"
}