{
  "_name_or_path": "google/vit-base-patch16-224-in21k",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Electronic",
    "1": "Experimental",
    "2": "Folk",
    "3": "Hip-Hop",
    "4": "Instrumental",
    "5": "International",
    "6": "Pop",
    "7": "Rock"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Electronic": "0",
    "Experimental": "1",
    "Folk": "2",
    "Hip-Hop": "3",
    "Instrumental": "4",
    "International": "5",
    "Pop": "6",
    "Rock": "7"
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "qkv_bias": true,
  "transformers_version": "4.34.1"
}