{
  "architectures": [
    "ViTForImageClassification"
  ],
  "model_type": "vit",
  "attention_probs_dropout_prob": 0.0,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 32,
  "image_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 64,
  "layer_norm_eps": 1e-12,
  "num_attention_heads": 4,
  "num_channels": 3,
  "num_hidden_layers": 1,
  "patch_size": 16,
  "qkv_bias": true,
  "num_labels": 3,
  "id2label": {
    "0": "cat",
    "1": "dog",
    "2": "bird"
  },
  "label2id": {
    "cat": 0,
    "dog": 1,
    "bird": 2
  }
}