tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "$",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 97,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 98,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 99,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "$": 0,
      "ア": 1,
      "イ": 2,
      "ウ": 3,
      "エ": 4,
      "オ": 5,
      "カ": 6,
      "キ": 7,
      "ク": 8,
      "ケ": 9,
      "コ": 10,
      "サ": 11,
      "シ": 12,
      "ス": 13,
      "セ": 14,
      "ソ": 15,
      "タ": 16,
      "チ": 17,
      "ツ": 18,
      "テ": 19,
      "ト": 20,
      "ナ": 21,
      "ニ": 22,
      "ヌ": 23,
      "ネ": 24,
      "ノ": 25,
      "ハ": 26,
      "ヒ": 27,
      "フ": 28,
      "ヘ": 29,
      "ホ": 30,
      "マ": 31,
      "ミ": 32,
      "ム": 33,
      "メ": 34,
      "モ": 35,
      "ヤ": 36,
      "ユ": 37,
      "ヨ": 38,
      "ワ": 39,
      "ヲ": 40,
      "ン": 41,
      "ガ": 42,
      "ギ": 43,
      "グ": 44,
      "ゲ": 45,
      "ゴ": 46,
      "ザ": 47,
      "ジ": 48,
      "ズ": 49,
      "ゼ": 50,
      "ゾ": 51,
      "ダ": 52,
      "ヂ": 53,
      "ヅ": 54,
      "デ": 55,
      "ド": 56,
      "パ": 57,
      "ピ": 58,
      "プ": 59,
      "ペ": 60,
      "ポ": 61,
      "ァ": 62,
      "ィ": 63,
      "ゥ": 64,
      "ェ": 65,
      "ォ": 66,
      "ャ": 67,
      "ュ": 68,
      "ョ": 69,
      "ヴ": 70,
      "ー": 71,
      "_": 72,
      "/": 73,
      "'": 74,
      "ッ": 75,
      "<unused_token_2>": 76,
      "<unused_token_3>": 77,
      "<unused_token_4>": 78,
      "<unused_token_5>": 79,
      "<unused_token_6>": 80,
      "<unused_token_7>": 81,
      "<unused_token_8>": 82,
      "<unused_token_9>": 83,
      "<unused_token_10>": 84,
      "<unused_token_11>": 85,
      "<unused_token_12>": 86,
      "<unused_token_13>": 87,
      "<unused_token_14>": 88,
      "<unused_token_15>": 89,
      "<unused_token_16>": 90,
      "<unused_token_17>": 91,
      "<unused_token_18>": 92,
      "<unused_token_19>": 93,
      "<unused_token_20>": 94,
      "<unused_token_21>": 95,
      "<unused_token_22>": 96,
      "[UNK]": 97,
      "<s>": 98,
      "</s>": 99
    },
    "unk_token": "[UNK]"
  }
}