{
  "_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": 15,
    "1": 0,
    "2": 1,
    "3": 2,
    "4": 3,
    "5": 4,
    "6": 5,
    "7": 6,
    "8": 7,
    "9": 8,
    "10": 9,
    "11": 10,
    "12": 11,
    "13": 12,
    "14": 13,
    "15": 14,
    "16": 16,
    "17": 17
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "0": 1,
    "1": 2,
    "2": 3,
    "3": 4,
    "4": 5,
    "5": 6,
    "6": 7,
    "7": 8,
    "8": 9,
    "9": 10,
    "10": 11,
    "11": 12,
    "12": 13,
    "13": 14,
    "14": 15,
    "15": 0,
    "16": 16,
    "17": 17
  },
  "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": "4.47.1"
}