config.json

{
  "_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": "battery",
    "1": "biological",
    "10": "trash",
    "11": "white-glass",
    "2": "brown-glass",
    "3": "cardboard",
    "4": "clothes",
    "5": "green-glass",
    "6": "metal",
    "7": "paper",
    "8": "plastic",
    "9": "shoes"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "battery": "0",
    "biological": "1",
    "brown-glass": "2",
    "cardboard": "3",
    "clothes": "4",
    "green-glass": "5",
    "metal": "6",
    "paper": "7",
    "plastic": "8",
    "shoes": "9",
    "trash": "10",
    "white-glass": "11"
  },
  "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": "4.46.1"
}