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": {
    "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": "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,
      ",": 1,
      "-": 2,
      ".": 3,
      "A": 4,
      "B": 5,
      "C": 6,
      "D": 7,
      "H": 8,
      "L": 9,
      "M": 10,
      "N": 11,
      "O": 12,
      "R": 13,
      "T": 14,
      "U": 15,
      "a": 16,
      "b": 17,
      "c": 18,
      "d": 19,
      "e": 20,
      "f": 21,
      "g": 22,
      "h": 23,
      "i": 24,
      "j": 25,
      "k": 26,
      "l": 27,
      "m": 28,
      "n": 29,
      "o": 30,
      "p": 31,
      "q": 32,
      "r": 33,
      "s": 34,
      "t": 35,
      "u": 36,
      "v": 37,
      "w": 38,
      "x": 39,
      "y": 40,
      "z": 41,
      "in": 42,
      "ti": 43,
      "on": 44,
      "al": 45,
      "er": 46,
      "ing": 47,
      "an": 48,
      "es": 49,
      "ar": 50,
      "en": 51,
      "he": 52,
      "or": 53,
      "tion": 54,
      "at": 55,
      "ne": 56,
      "ur": 57,
      "it": 58,
      "le": 59,
      "de": 60,
      "ro": 61,
      "and": 62,
      "ch": 63
    },
    "merges": [
      [
        "i",
        "n"
      ],
      [
        "t",
        "i"
      ],
      [
        "o",
        "n"
      ],
      [
        "a",
        "l"
      ],
      [
        "e",
        "r"
      ],
      [
        "in",
        "g"
      ],
      [
        "a",
        "n"
      ],
      [
        "e",
        "s"
      ],
      [
        "a",
        "r"
      ],
      [
        "e",
        "n"
      ],
      [
        "h",
        "e"
      ],
      [
        "o",
        "r"
      ],
      [
        "ti",
        "on"
      ],
      [
        "a",
        "t"
      ],
      [
        "n",
        "e"
      ],
      [
        "u",
        "r"
      ],
      [
        "i",
        "t"
      ],
      [
        "l",
        "e"
      ],
      [
        "d",
        "e"
      ],
      [
        "r",
        "o"
      ],
      [
        "an",
        "d"
      ],
      [
        "c",
        "h"
      ]
    ]
  }
}