{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "dtype": "float32",
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "abyssinian",
    "1": "bengal",
    "2": "birman",
    "3": "bombay",
    "4": "british_shorthair",
    "5": "egyptian_mau",
    "6": "maine_coon",
    "7": "persian",
    "8": "ragdoll",
    "9": "russian_blue",
    "10": "siamese",
    "11": "sphynx"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "abyssinian": 0,
    "bengal": 1,
    "birman": 2,
    "bombay": 3,
    "british_shorthair": 4,
    "egyptian_mau": 5,
    "maine_coon": 6,
    "persian": 7,
    "ragdoll": 8,
    "russian_blue": 9,
    "siamese": 10,
    "sphynx": 11
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "pooler_act": "tanh",
  "pooler_output_size": 768,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "transformers_version": "5.0.0"
}