tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<mask>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50000": {
      "content": "<special0>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50001": {
      "content": "<special1>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50002": {
      "content": "<special2>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50003": {
      "content": "<special3>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50004": {
      "content": "<special4>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50005": {
      "content": "<special5>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50006": {
      "content": "<special6>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50007": {
      "content": "<special7>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50008": {
      "content": "<special8>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "50009": {
      "content": "<special9>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<special0>",
    "<special1>",
    "<special2>",
    "<special3>",
    "<special4>",
    "<special5>",
    "<special6>",
    "<special7>",
    "<special8>",
    "<special9>"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "cls_token": "<s>",
  "do_lowercase_and_remove_accent": false,
  "id2lang": null,
  "lang2id": null,
  "mask_token": "<mask>",
  "model_max_length": 512,
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "tokenizer_class": "HerbertTokenizer",
  "unk_token": "<unk>"
}