{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 1024,
  "id2label": {
    "0": "CHECK - V",
    "1": "GESSATI - V",
    "2": "MICRO EFFETTI - V",
    "3": "PIED DE POULE - V",
    "4": "PRINCIPE DI GALLES - V",
    "5": "QUADRETTO - V",
    "6": "SPIGA - V",
    "7": "UNITI"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "CHECK - V": 0,
    "GESSATI - V": 1,
    "MICRO EFFETTI - V": 2,
    "PIED DE POULE - V": 3,
    "PRINCIPE DI GALLES - V": 4,
    "QUADRETTO - V": 5,
    "SPIGA - V": 6,
    "UNITI": 7
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 24,
  "patch_size": 16,
  "pooler_act": "tanh",
  "pooler_output_size": 1024,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.55.4"
}