tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "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": {
      "<unk>": 0,
      "A": 1,
      "F": 2,
      "M": 3,
      "N": 4,
      "P": 5,
      "T": 6,
      "a": 7,
      "c": 8,
      "d": 9,
      "e": 10,
      "f": 11,
      "g": 12,
      "h": 13,
      "i": 14,
      "l": 15,
      "m": 16,
      "n": 17,
      "o": 18,
      "p": 19,
      "r": 20,
      "s": 21,
      "t": 22,
      "u": 23,
      "v": 24,
      "y": 25,
      "in": 26,
      "an": 27,
      "he": 28,
      "is": 29,
      "at": 30,
      "ch": 31,
      "ed": 32,
      "ing": 33,
      "The": 34,
      "al": 35,
      "as": 36,
      "ar": 37,
      "ce": 38,
      "cat": 39,
      "do": 40,
      "er": 41,
      "or": 42,
      "ran": 43,
      "the": 44,
      "ang": 45,
      "chas": 46,
      "dog": 47,
      "chased": 48,
      "At": 49,
      "Fran": 50,
      "Ma": 51,
      "Nat": 52,
      "Par": 53,
      "Tran": 54,
      "ag": 55,
      "ap": 56,
      "cin": 57,
      "cap": 58,
      "en": 59,
      "ev": 60,
      "eed": 61,
      "ear": 62,
      "fas": 63
    },
    "merges": [
      [
        "i",
        "n"
      ],
      [
        "a",
        "n"
      ],
      [
        "h",
        "e"
      ],
      [
        "i",
        "s"
      ],
      [
        "a",
        "t"
      ],
      [
        "c",
        "h"
      ],
      [
        "e",
        "d"
      ],
      [
        "in",
        "g"
      ],
      [
        "T",
        "he"
      ],
      [
        "a",
        "l"
      ],
      [
        "a",
        "s"
      ],
      [
        "a",
        "r"
      ],
      [
        "c",
        "e"
      ],
      [
        "c",
        "at"
      ],
      [
        "d",
        "o"
      ],
      [
        "e",
        "r"
      ],
      [
        "o",
        "r"
      ],
      [
        "r",
        "an"
      ],
      [
        "t",
        "he"
      ],
      [
        "an",
        "g"
      ],
      [
        "ch",
        "as"
      ],
      [
        "do",
        "g"
      ],
      [
        "chas",
        "ed"
      ],
      [
        "A",
        "t"
      ],
      [
        "F",
        "ran"
      ],
      [
        "M",
        "a"
      ],
      [
        "N",
        "at"
      ],
      [
        "P",
        "ar"
      ],
      [
        "T",
        "ran"
      ],
      [
        "a",
        "g"
      ],
      [
        "a",
        "p"
      ],
      [
        "c",
        "in"
      ],
      [
        "c",
        "ap"
      ],
      [
        "e",
        "n"
      ],
      [
        "e",
        "v"
      ],
      [
        "e",
        "ed"
      ],
      [
        "e",
        "ar"
      ],
      [
        "f",
        "as"
      ]
    ]
  }
}