{
  "_name_or_path": "google/vit-large-patch16-224-in21k",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "finetuning_task": "image-classification",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 1024,
  "id2label": {
    "0": "model-back-close",
    "1": "model-back-full",
    "10": "pack-detail",
    "11": "pack-front",
    "12": "pack-side",
    "13": "pack-top",
    "2": "model-detail",
    "3": "model-front-close",
    "4": "model-front-full",
    "5": "model-side-close",
    "6": "model-side-full",
    "7": "pack-angled",
    "8": "pack-back",
    "9": "pack-bottom"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "model-back-close": "0",
    "model-back-full": "1",
    "model-detail": "2",
    "model-front-close": "3",
    "model-front-full": "4",
    "model-side-close": "5",
    "model-side-full": "6",
    "pack-angled": "7",
    "pack-back": "8",
    "pack-bottom": "9",
    "pack-detail": "10",
    "pack-front": "11",
    "pack-side": "12",
    "pack-top": "13"
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 24,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.33.0.dev0"
}