{
  "_name_or_path": "jordyvl/vit-base_rvl-cdip",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "letter",
    "1": "form",
    "2": "email",
    "3": "handwritten",
    "4": "advertisement",
    "5": "scientific_report",
    "6": "scientific_publication",
    "7": "specification",
    "8": "file_folder",
    "9": "news_article",
    "10": "budget",
    "11": "invoice",
    "12": "presentation",
    "13": "questionnaire",
    "14": "resume",
    "15": "memo"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "advertisement": 4,
    "budget": 10,
    "email": 2,
    "file_folder": 8,
    "form": 1,
    "handwritten": 3,
    "invoice": 11,
    "letter": 0,
    "memo": 15,
    "news_article": 9,
    "presentation": 12,
    "questionnaire": 13,
    "resume": 14,
    "scientific_publication": 6,
    "scientific_report": 5,
    "specification": 7
  },
  "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": "4.33.3"
}