tokenizer (3).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": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      ",": 4,
      "a": 5,
      "b": 6,
      "d": 7,
      "e": 8,
      "f": 9,
      "g": 10,
      "h": 11,
      "i": 12,
      "k": 13,
      "l": 14,
      "m": 15,
      "n": 16,
      "o": 17,
      "p": 18,
      "r": 19,
      "s": 20,
      "t": 21,
      "u": 22,
      "w": 23,
      "y": 24,
      "br": 25,
      "ha": 26,
      "uh": 27,
      "bruh": 28,
      "su": 29,
      "lo": 30,
      "lol": 31,
      "bo": 32,
      "er": 33,
      "mer": 34,
      "ok": 35,
      "omer": 36,
      "boomer": 37,
      "am": 38,
      "an": 39,
      "dan": 40,
      "fam": 41,
      "yo": 42,
      "dang": 43,
      "bro": 44,
      "sup": 45,
      "ay": 46,
      "no": 47,
      "way": 48,
      "haha": 49,
      "bi": 50,
      "di": 51,
      "ibi": 52,
      "kibi": 53,
      "skibi": 54,
      "skibidi": 55,
      "tf": 56,
      "wtf": 57,
      "ee": 58,
      "og": 59,
      "pog": 60,
      "yee": 61,
      "yeet": 62,
      "de": 63,
      "du": 64,
      "dude": 65,
      "sus": 66,
      "ao": 67,
      "lm": 68,
      "lmao": 69,
      "ey": 70,
      "hey": 71
    },
    "merges": [
      [
        "b",
        "r"
      ],
      [
        "h",
        "a"
      ],
      [
        "u",
        "h"
      ],
      [
        "br",
        "uh"
      ],
      [
        "s",
        "u"
      ],
      [
        "l",
        "o"
      ],
      [
        "lo",
        "l"
      ],
      [
        "b",
        "o"
      ],
      [
        "e",
        "r"
      ],
      [
        "m",
        "er"
      ],
      [
        "o",
        "k"
      ],
      [
        "o",
        "mer"
      ],
      [
        "bo",
        "omer"
      ],
      [
        "a",
        "m"
      ],
      [
        "a",
        "n"
      ],
      [
        "d",
        "an"
      ],
      [
        "f",
        "am"
      ],
      [
        "y",
        "o"
      ],
      [
        "dan",
        "g"
      ],
      [
        "br",
        "o"
      ],
      [
        "su",
        "p"
      ],
      [
        "a",
        "y"
      ],
      [
        "n",
        "o"
      ],
      [
        "w",
        "ay"
      ],
      [
        "ha",
        "ha"
      ],
      [
        "b",
        "i"
      ],
      [
        "d",
        "i"
      ],
      [
        "i",
        "bi"
      ],
      [
        "k",
        "ibi"
      ],
      [
        "s",
        "kibi"
      ],
      [
        "skibi",
        "di"
      ],
      [
        "t",
        "f"
      ],
      [
        "w",
        "tf"
      ],
      [
        "e",
        "e"
      ],
      [
        "o",
        "g"
      ],
      [
        "p",
        "og"
      ],
      [
        "y",
        "ee"
      ],
      [
        "yee",
        "t"
      ],
      [
        "d",
        "e"
      ],
      [
        "d",
        "u"
      ],
      [
        "du",
        "de"
      ],
      [
        "su",
        "s"
      ],
      [
        "a",
        "o"
      ],
      [
        "l",
        "m"
      ],
      [
        "lm",
        "ao"
      ],
      [
        "e",
        "y"
      ],
      [
        "h",
        "ey"
      ]
    ]
  }
}