tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<cls>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<sep>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<mask>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "<eow>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<seg>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<eow>",
    "<seg>"
  ],
  "clean_up_tokenization_spaces": false,
  "cls_token": "<cls>",
  "extra_special_tokens": {},
  "mask_token": "<mask>",
  "max_seg_len": 5,
  "model_max_length": 1024,
  "pad_token": "<pad>",
  "sep_token": "<sep>",
  "tokenizer_class": "SubSegDeBERTaTokenizer",
  "unk_token": "<unk>"
}