{
  "_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": "banana",
    "1": "bread",
    "2": "eggs",
    "3": "milk",
    "4": "potato",
    "5": "spinach",
    "6": "tomato",
    "7": "train",
    "8": "val"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "banana": "0",
    "bread": "1",
    "eggs": "2",
    "milk": "3",
    "potato": "4",
    "spinach": "5",
    "tomato": "6",
    "train": "7",
    "val": "8"
  },
  "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": "4.28.1"
}