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": 1,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[BOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "[EOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFD"
      },
      {
        "type": "StripAccents"
      },
      {
        "type": "Lowercase"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "_": 0,
      "[PAD]": 1,
      "[UNK]": 2,
      "[BOS]": 3,
      "[EOS]": 4,
      "a": 5,
      "b": 6,
      "c": 7,
      "d": 8,
      "e": 9,
      "f": 10,
      "g": 11,
      "h": 12,
      "i": 13,
      "j": 14,
      "k": 15,
      "l": 16,
      "m": 17,
      "n": 18,
      "o": 19,
      "p": 20,
      "q": 21,
      "r": 22,
      "s": 23,
      "t": 24,
      "u": 25,
      "v": 26,
      "w": 27,
      "x": 28,
      "y": 29,
      "z": 30,
      "0": 31,
      "1": 32,
      "2": 33,
      "3": 34,
      "4": 35,
      "5": 36,
      "6": 37,
      "7": 38,
      "8": 39,
      "9": 40,
      "10": 41,
      "11": 42,
      "12": 43,
      "13": 44,
      "14": 45,
      "15": 46,
      "16": 47,
      "17": 48,
      "18": 49,
      "19": 50,
      "20": 51,
      "21": 52,
      "22": 53,
      "23": 54,
      "24": 55,
      "25": 56,
      "26": 57,
      "27": 58,
      "28": 59,
      "29": 60,
      "30": 61,
      "31": 62,
      "32": 63,
      "33": 64,
      "34": 65,
      "35": 66,
      "36": 67,
      "37": 68,
      "38": 69,
      "39": 70,
      "40": 71,
      "41": 72,
      "42": 73,
      "43": 74,
      "44": 75,
      "45": 76,
      "46": 77,
      "47": 78,
      "48": 79,
      "49": 80,
      "50": 81,
      "51": 82,
      "52": 83,
      "53": 84,
      "54": 85,
      "55": 86,
      "56": 87,
      "57": 88,
      "58": 89,
      "59": 90,
      "60": 91,
      "61": 92,
      "62": 93,
      "63": 94,
      "64": 95,
      "65": 96,
      "66": 97,
      "67": 98,
      "68": 99,
      "69": 100,
      "70": 101,
      "71": 102,
      "72": 103,
      "73": 104,
      "74": 105,
      "75": 106,
      "|": 107,
      "?": 108
    },
    "unk_token": "[UNK]"
  }
}