tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<mask>",
      "lstrip": true,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65536": {
      "content": "ar_AR",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65537": {
      "content": "cs_CZ",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65538": {
      "content": "de_DE",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65539": {
      "content": "en_XX",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65540": {
      "content": "es_XX",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65541": {
      "content": "et_EE",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65542": {
      "content": "fi_FI",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65543": {
      "content": "fr_XX",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65544": {
      "content": "gu_IN",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65545": {
      "content": "hi_IN",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65546": {
      "content": "it_IT",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65547": {
      "content": "ja_XX",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65548": {
      "content": "kk_KZ",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65549": {
      "content": "ko_KR",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65550": {
      "content": "lt_LT",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65551": {
      "content": "lv_LV",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65552": {
      "content": "my_MM",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65553": {
      "content": "ne_NP",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65554": {
      "content": "nl_XX",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65555": {
      "content": "ro_RO",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65556": {
      "content": "ru_RU",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65557": {
      "content": "si_LK",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65558": {
      "content": "tr_TR",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65559": {
      "content": "vi_VN",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "65560": {
      "content": "zh_CN",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "ar_AR",
    "cs_CZ",
    "de_DE",
    "en_XX",
    "es_XX",
    "et_EE",
    "fi_FI",
    "fr_XX",
    "gu_IN",
    "hi_IN",
    "it_IT",
    "ja_XX",
    "kk_KZ",
    "ko_KR",
    "lt_LT",
    "lv_LV",
    "my_MM",
    "ne_NP",
    "nl_XX",
    "ro_RO",
    "ru_RU",
    "si_LK",
    "tr_TR",
    "vi_VN",
    "zh_CN"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "cls_token": "<s>",
  "eos_token": "</s>",
  "errors": "replace",
  "mask_token": "<mask>",
  "max_len": 512,
  "model_max_length": 1024,
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "src_lang": "en_XX",
  "tgt_lang": "en_XX",
  "tokenizer_class": "MBartTokenizer",
  "trim_offsets": true,
  "unk_token": "<unk>"
}