config.json

{
  "architectures": [
    "LayoutLMForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "finetuning_task": "token_classification",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "1",
    "1": "2",
    "2": "3"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "1": "0",
    "2": "1",
    "3": "2"
  },
  "layer_norm_eps": 1e-12,
  "max_2d_position_embeddings": 1024,
  "max_length": 512,
  "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",
  "torch_dtype": "float32",
  "transformers_version": "4.31.0",
  "type_vocab_size": 2,
  "use_cache": true,
  "vila_preprocessor_config": {
    "agg_level": "row",
    "group_bbox_agg": "first"
  },
  "vocab_size": 30523
}