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,
      ",": 1,
      ".": 2,
      "a": 3,
      "b": 4,
      "c": 5,
      "d": 6,
      "e": 7,
      "f": 8,
      "g": 9,
      "h": 10,
      "i": 11,
      "k": 12,
      "l": 13,
      "m": 14,
      "n": 15,
      "o": 16,
      "p": 17,
      "q": 18,
      "r": 19,
      "s": 20,
      "t": 21,
      "u": 22,
      "w": 23,
      "y": 24,
      "it": 25,
      "is": 26,
      "th": 27,
      "the": 28,
      "an": 29,
      "al": 30,
      "in": 31,
      "ital": 32,
      "ap": 33,
      "cap": 34,
      "capital": 35,
      "of": 36,
      "or": 37,
      "on": 38,
      "and": 39,
      "ar": 40,
      "un": 41,
      "ur": 42,
      "ac": 43,
      "ed": 44,
      "en": 45,
      "no": 46,
      "es": 47,
      "ma": 48,
      "as": 49,
      "eac": 50,
      "ri": 51,
      "ited": 52,
      "united": 53,
      "each": 54,
      "eur": 55,
      "op": 56,
      "europ": 57,
      "europe": 58,
      "se": 59,
      "wn": 60,
      "these": 61,
      "not": 62,
      "mad": 63
    },
    "merges": [
      [
        "i",
        "t"
      ],
      [
        "i",
        "s"
      ],
      [
        "t",
        "h"
      ],
      [
        "th",
        "e"
      ],
      [
        "a",
        "n"
      ],
      [
        "a",
        "l"
      ],
      [
        "i",
        "n"
      ],
      [
        "it",
        "al"
      ],
      [
        "a",
        "p"
      ],
      [
        "c",
        "ap"
      ],
      [
        "cap",
        "ital"
      ],
      [
        "o",
        "f"
      ],
      [
        "o",
        "r"
      ],
      [
        "o",
        "n"
      ],
      [
        "an",
        "d"
      ],
      [
        "a",
        "r"
      ],
      [
        "u",
        "n"
      ],
      [
        "u",
        "r"
      ],
      [
        "a",
        "c"
      ],
      [
        "e",
        "d"
      ],
      [
        "e",
        "n"
      ],
      [
        "n",
        "o"
      ],
      [
        "e",
        "s"
      ],
      [
        "m",
        "a"
      ],
      [
        "a",
        "s"
      ],
      [
        "e",
        "ac"
      ],
      [
        "r",
        "i"
      ],
      [
        "it",
        "ed"
      ],
      [
        "un",
        "ited"
      ],
      [
        "eac",
        "h"
      ],
      [
        "e",
        "ur"
      ],
      [
        "o",
        "p"
      ],
      [
        "eur",
        "op"
      ],
      [
        "europ",
        "e"
      ],
      [
        "s",
        "e"
      ],
      [
        "w",
        "n"
      ],
      [
        "the",
        "se"
      ],
      [
        "no",
        "t"
      ],
      [
        "ma",
        "d"
      ]
    ]
  }
}