tokenizer_config.json

{
  "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
  },
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "mask_token": {
    "__type": "AddedToken",
    "content": "<mask>",
    "lstrip": true,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "max_length": 512,
  "model_max_length": 512,
  "never_split": null,
  "pad_to_multiple_of": null,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<pad>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "pad_token_type_id": 0,
  "padding_side": "right",
  "sep_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "stride": 0,
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "MPNetTokenizer",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": {
    "__type": "AddedToken",
    "content": "[UNK]",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}