config.json

{
  "_name_or_path": "google/vit-base-patch16-224",
  "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": "bell_pepper",
    "10": "cereal_box",
    "11": "comb",
    "12": "dry_battery",
    "2": "ball",
    "3": "binder",
    "4": "bowl",
    "5": "cell_phone",
    "6": "calculator",
    "7": "cap",
    "8": "camera",
    "9": "coffee_mug"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "ball": "2",
    "banana": "0",
    "bell_pepper": "1",
    "binder": "3",
    "bowl": "4",
    "calculator": "6",
    "camera": "8",
    "cap": "7",
    "cell_phone": "5",
    "cereal_box": "10",
    "coffee_mug": "9",
    "comb": "11",
    "dry_battery": "12"
  },
  "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": "4.31.0"
}