tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "NFC"
  },
  "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": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      "[BOS]": 5,
      "[EOS]": 6,
      "\n": 7,
      " ": 8,
      "!": 9,
      "\"": 10,
      "'": 11,
      "-": 12,
      ".": 13,
      "«": 14,
      "»": 15,
      "؁": 16,
      "،": 17,
      "؎": 18,
      "ؐ": 19,
      "ؑ": 20,
      "ؒ": 21,
      "ؓ": 22,
      "ؔ": 23,
      "؛": 24,
      "؟": 25,
      "ؠ": 26,
      "ء": 27,
      "آ": 28,
      "أ": 29,
      "ؤ": 30,
      "إ": 31,
      "ئ": 32,
      "ا": 33,
      "ب": 34,
      "ت": 35,
      "ث": 36,
      "ج": 37,
      "ح": 38,
      "خ": 39,
      "د": 40,
      "ذ": 41,
      "ر": 42,
      "ز": 43,
      "س": 44,
      "ش": 45,
      "ص": 46,
      "ض": 47,
      "ط": 48,
      "ظ": 49,
      "ع": 50,
      "غ": 51,
      "ف": 52,
      "ق": 53,
      "ك": 54,
      "ل": 55,
      "م": 56,
      "ن": 57,
      "ه": 58,
      "و": 59,
      "ً": 60,
      "ٍ": 61,
      "َ": 62,
      "ُ": 63,
      "ِ": 64,
      "ّ": 65,
      "ْ": 66,
      "ٓ": 67,
      "ٔ": 68,
      "ٕ": 69,
      "ٖ": 70,
      "ٗ": 71,
      "٘": 72,
      "ٚ": 73,
      "ٛ": 74,
      "ٟ": 75,
      "٠": 76,
      "١": 77,
      "٢": 78,
      "٣": 79,
      "٤": 80,
      "٥": 81,
      "٦": 82,
      "٧": 83,
      "٨": 84,
      "٩": 85,
      "٪": 86,
      "٭": 87,
      "ٮ": 88,
      "ٮ۪": 89,
      "ٰ": 90,
      "ٲ": 91,
      "ٳ": 92,
      "ٹ": 93,
      "پ": 94,
      "ٿ": 95,
      "ڀ": 96,
      "چ": 97,
      "ڈ": 98,
      "ڑ": 99,
      "ژ": 100,
      "ڙ": 101,
      "ک": 102,
      "ڪ": 103,
      "ڮ": 104,
      "گ": 105,
      "ں": 106,
      "ھ": 107,
      "ہ": 108,
      "ۂ": 109,
      "ۃ": 110,
      "ۄ": 111,
      "ۅ": 112,
      "ۆ": 113,
      "ی": 114,
      "ۍ": 115,
      "ے": 116,
      "ۓ": 117,
      "۔": 118,
      "۪": 119,
      "ۭ": 120,
      "۰": 121,
      "۱": 122,
      "۲": 123,
      "۳": 124,
      "۴": 125,
      "۵": 126,
      "۶": 127,
      "۷": 128,
      "۸": 129,
      "۹": 130,
      "﴾": 131,
      "﴿": 132
    },
    "unk_token": "[UNK]"
  }
}