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": null,
  "pre_tokenizer": null,
  "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,
      "[UNK]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      "\n": 5,
      "\r": 6,
      " ": 7,
      ",": 8,
      ".": 9,
      "a": 10,
      "b": 11,
      "c": 12,
      "d": 13,
      "e": 14,
      "f": 15,
      "g": 16,
      "h": 17,
      "i": 18,
      "k": 19,
      "l": 20,
      "m": 21,
      "n": 22,
      "o": 23,
      "p": 24,
      "q": 25,
      "r": 26,
      "s": 27,
      "t": 28,
      "u": 29,
      "w": 30,
      "y": 31,
      " i": 32,
      "e ": 33,
      "th": 34,
      "s ": 35,
      "it": 36,
      "an": 37,
      ", ": 38,
      "al": 39,
      "d ": 40,
      " is ": 41,
      "ap": 42,
      "cap": 43,
      "the ": 44,
      "ital": 45,
      "capital": 46,
      "n ": 47,
      "of": 48,
      "or": 49,
      "on": 50,
      "and ": 51,
      "h ": 52,
      "ar": 53,
      "es": 54,
      "of ": 55,
      "un": 56,
      ". ": 57,
      "ur": 58,
      "ac": 59,
      "is": 60,
      "capital ": 61,
      "in": 62,
      "\r\n": 63
    },
    "merges": [
      [
        " ",
        "i"
      ],
      [
        "e",
        " "
      ],
      [
        "t",
        "h"
      ],
      [
        "s",
        " "
      ],
      [
        "i",
        "t"
      ],
      [
        "a",
        "n"
      ],
      [
        ",",
        " "
      ],
      [
        "a",
        "l"
      ],
      [
        "d",
        " "
      ],
      [
        " i",
        "s "
      ],
      [
        "a",
        "p"
      ],
      [
        "c",
        "ap"
      ],
      [
        "th",
        "e "
      ],
      [
        "it",
        "al"
      ],
      [
        "cap",
        "ital"
      ],
      [
        "n",
        " "
      ],
      [
        "o",
        "f"
      ],
      [
        "o",
        "r"
      ],
      [
        "o",
        "n"
      ],
      [
        "an",
        "d "
      ],
      [
        "h",
        " "
      ],
      [
        "a",
        "r"
      ],
      [
        "e",
        "s"
      ],
      [
        "of",
        " "
      ],
      [
        "u",
        "n"
      ],
      [
        ".",
        " "
      ],
      [
        "u",
        "r"
      ],
      [
        "a",
        "c"
      ],
      [
        "i",
        "s"
      ],
      [
        "capital",
        " "
      ],
      [
        "i",
        "n"
      ],
      [
        "\r",
        "\n"
      ]
    ]
  }
}