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": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52000": {
      "content": "[DOMAIN_ADM]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52001": {
      "content": "[DOMAIN_ATT]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52002": {
      "content": "[DOMAIN_BER]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52003": {
      "content": "[DOMAIN_ENR]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52004": {
      "content": "[DOMAIN_ETN]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52005": {
      "content": "[DOMAIN_FAC]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52006": {
      "content": "[DOMAIN_INS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52007": {
      "content": "[DOMAIN_MBW]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52008": {
      "content": "[DOMAIN_STM]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52009": {
      "content": "[DOMAIN_SLP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52010": {
      "content": "[DOMAIN_HLC]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52011": {
      "content": "[DOMAIN_HRN]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52012": {
      "content": "[DOMAIN_SOP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52013": {
      "content": "[DOMAIN_HSP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52014": {
      "content": "[DOMAIN_CBP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52015": {
      "content": "[DOMAIN_MAE]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "52016": {
      "content": "[DOMAIN_FML]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "[DOMAIN_ADM]",
    "[DOMAIN_ATT]",
    "[DOMAIN_BER]",
    "[DOMAIN_ENR]",
    "[DOMAIN_ETN]",
    "[DOMAIN_FAC]",
    "[DOMAIN_INS]",
    "[DOMAIN_MBW]",
    "[DOMAIN_STM]",
    "[DOMAIN_SLP]",
    "[DOMAIN_HLC]",
    "[DOMAIN_HRN]",
    "[DOMAIN_SOP]",
    "[DOMAIN_HSP]",
    "[DOMAIN_CBP]",
    "[DOMAIN_MAE]",
    "[DOMAIN_FML]"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<s>",
  "eos_token": "</s>",
  "errors": "replace",
  "extra_special_tokens": {},
  "mask_token": "<mask>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "tokenizer_class": "RobertaTokenizer",
  "trim_offsets": true,
  "unk_token": "<unk>"
}