tokenizer_config.json

{
  "add_prefix_space": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "errors": "replace",
  "mask_token": {
    "__type": "AddedToken",
    "content": "<mask>",
    "lstrip": true,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "max_len": 512,
  "model_max_length": 512,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<pad>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "processor_class": "TrOCRProcessor",
  "sep_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "tokenizer_class": "RobertaTokenizer",
  "trim_offsets": true,
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}