tokenizer_config.json

{
  "do_tokenize_postprocess": false,
  "sep_token": "[SEP]",
  "cls_token": "[CLS]",
  "unk_token": "[UNK]",
  "pad_token": "[PAD]",
  "mask_token": "[MASK]",
  "do_lower_case": true,
  "model_max_length": 512,
  "vocab_file": "/home/ysocr/data/pretrain/ernie-layoutx-base-uncased/torch_version/vocab.txt",
  "sentencepiece_model_file": "/home/ysocr/data/pretrain/ernie-layoutx-base-uncased/torch_version/sentencepiece.bpe.model"
}