tokenizer_config.json

{
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "cls_token": "<s>",
  "cls_token_box": [
    0,
    0,
    0,
    0
  ],
  "eos_token": "</s>",
  "mask_token": {
    "__type": "AddedToken",
    "content": "<mask>",
    "lstrip": true,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "max_length": 512,
  "model_max_length": 1000000000000000019884624838656,
  "only_label_first_subword": true,
  "pad_token": "<pad>",
  "pad_token_box": [
    0,
    0,
    0,
    0
  ],
  "pad_token_label": -100,
  "sep_token": "</s>",
  "sep_token_box": [
    1000,
    1000,
    1000,
    1000
  ],
  "stride": 0,
  "tokenizer_class": "LayoutXLMTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>"
}