{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "dtype": "float32",
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Cardboard",
    "1": "Food Organics",
    "2": "Glass",
    "3": "Metal",
    "4": "Miscellaneous Trash",
    "5": "Paper",
    "6": "Plastic",
    "7": "Textile Trash",
    "8": "Vegetation"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Cardboard": 0,
    "Food Organics": 1,
    "Glass": 2,
    "Metal": 3,
    "Miscellaneous Trash": 4,
    "Paper": 5,
    "Plastic": 6,
    "Textile Trash": 7,
    "Vegetation": 8
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "pooler_act": "tanh",
  "pooler_output_size": 768,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "transformers_version": "5.9.0",
  "use_cache": false
}