{
  "architectures": [
    "LayoutLMForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "finetuning_task": "token_classification",
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "paragraph",
    "1": "title",
    "2": "equation",
    "3": "reference",
    "4": "section",
    "5": "list",
    "6": "table",
    "7": "caption",
    "8": "author",
    "9": "abstract",
    "10": "footer",
    "11": "date",
    "12": "figure"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "abstract": "9",
    "author": "8",
    "caption": "7",
    "date": "11",
    "equation": "2",
    "figure": "12",
    "footer": "10",
    "list": "5",
    "paragraph": "0",
    "reference": "3",
    "section": "4",
    "table": "6",
    "title": "1"
  },
  "layer_norm_eps": 1e-12,
  "max_2d_position_embeddings": 1024,
  "max_position_embeddings": 512,
  "model_type": "layoutlm",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "transformers_version": "4.7.0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vila_preprocessor_config": {
    "added_special_sepration_token": "[BLK]",
    "agg_level": "block",
    "group_bbox_agg": "first"
  },
  "vocab_size": 30522
}