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": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "</s>",
      "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,
      "<unk>": 1,
      "<s>": 2,
      "</s>": 3,
      "'": 4,
      ".": 5,
      "H": 6,
      "T": 7,
      "a": 8,
      "c": 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,
      "en": 23,
      "ce": 24,
      "er": 25,
      "in": 26,
      "is": 27,
      "sen": 28,
      "ten": 29,
      "senten": 30,
      "sentence": 31,
      "Her": 32,
      "Th": 33,
      "am": 34,
      "an": 35,
      "ain": 36,
      "fo": 37,
      "her": 38,
      "le": 39,
      "ot": 40,
      "ple": 41,
      "rain": 42,
      "sam": 43,
      "train": 44,
      "ing": 45,
      "Here": 46,
      "This": 47,
      "anot": 48,
      "for": 49,
      "sample": 50,
      "training": 51,
      "another": 52
    },
    "merges": [
      [
        "e",
        "n"
      ],
      [
        "c",
        "e"
      ],
      [
        "e",
        "r"
      ],
      [
        "i",
        "n"
      ],
      [
        "i",
        "s"
      ],
      [
        "s",
        "en"
      ],
      [
        "t",
        "en"
      ],
      [
        "sen",
        "ten"
      ],
      [
        "senten",
        "ce"
      ],
      [
        "H",
        "er"
      ],
      [
        "T",
        "h"
      ],
      [
        "a",
        "m"
      ],
      [
        "a",
        "n"
      ],
      [
        "a",
        "in"
      ],
      [
        "f",
        "o"
      ],
      [
        "h",
        "er"
      ],
      [
        "l",
        "e"
      ],
      [
        "o",
        "t"
      ],
      [
        "p",
        "le"
      ],
      [
        "r",
        "ain"
      ],
      [
        "s",
        "am"
      ],
      [
        "t",
        "rain"
      ],
      [
        "in",
        "g"
      ],
      [
        "Her",
        "e"
      ],
      [
        "Th",
        "is"
      ],
      [
        "an",
        "ot"
      ],
      [
        "fo",
        "r"
      ],
      [
        "sam",
        "ple"
      ],
      [
        "train",
        "ing"
      ],
      [
        "anot",
        "her"
      ]
    ]
  }
}