{
  "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": "baseball",
    "1": "basketball",
    "2": "boxing",
    "3": "cricket",
    "4": "field hockey",
    "5": "american football",
    "6": "golf",
    "7": "rugby",
    "8": "swimming",
    "9": "table tennis",
    "10": "tennis",
    "11": "track bicycle",
    "12": "volleyball",
    "13": "badminton",
    "14": "football"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "american football": 5,
    "badminton": 13,
    "baseball": 0,
    "basketball": 1,
    "boxing": 2,
    "cricket": 3,
    "field hockey": 4,
    "football": 14,
    "golf": 6,
    "rugby": 7,
    "swimming": 8,
    "table tennis": 9,
    "tennis": 10,
    "track bicycle": 11,
    "volleyball": 12
  },
  "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": "4.57.5"
}