{
  "_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": "apple",
    "1": "banana",
    "2": "cake",
    "3": "candy",
    "4": "carrot",
    "5": "cookie",
    "6": "doughnut",
    "7": "grape",
    "8": "hot dog",
    "9": "ice cream",
    "10": "juice",
    "11": "muffin",
    "12": "orange",
    "13": "pineapple",
    "14": "popcorn",
    "15": "pretzel",
    "16": "salad",
    "17": "strawberry",
    "18": "waffle",
    "19": "watermelon"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "apple": 0,
    "banana": 1,
    "cake": 2,
    "candy": 3,
    "carrot": 4,
    "cookie": 5,
    "doughnut": 6,
    "grape": 7,
    "hot dog": 8,
    "ice cream": 9,
    "juice": 10,
    "muffin": 11,
    "orange": 12,
    "pineapple": 13,
    "popcorn": 14,
    "pretzel": 15,
    "salad": 16,
    "strawberry": 17,
    "waffle": 18,
    "watermelon": 19
  },
  "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": "4.19.1"
}