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
    },
    {
      "id": 1,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<mask>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<bos>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<bos>": {
        "id": "<bos>",
        "ids": [
          3
        ],
        "tokens": [
          "<bos>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<unk>": 0,
      "<pad>": 1,
      "<mask>": 2,
      "<bos>": 3,
      ".": 4,
      "the": 5,
      "and": 6,
      ",": 7,
      "was": 8,
      "it": 9,
      "had": 10,
      "he": 11,
      "in": 12,
      "Bible": 13,
      "a": 14,
      "n<apostrophe>t": 15,
      "here": 16,
      "He": 17,
      "to": 18,
      "by": 19,
      "ditch": 20,
      "<apostrophe>s": 21,
      "boy": 22,
      "did": 23,
      "knew": 24,
      "Oh": 25,
      ":": 26,
      "they": 27,
      "them": 28,
      "there": 29,
      "But": 30,
      "meant": 31,
      "that": 32,
      "The": 33,
      "Today": 34,
      "Tuesday": 35,
      "now": 36,
      "find": 37,
      "should": 38,
      "leave": 39,
      "help": 40,
      "care": 41,
      "not": 42,
      "intended": 43,
      "really": 44,
      "quite": 45,
      "They": 46,
      "mattered": 47,
      "finally": 48,
      "told": 49,
      "moved": 50,
      "blackened": 51,
      "happened": 52,
      "justice": 53,
      "world": 54,
      "fingers": 55,
      "none": 56,
      "his": 57,
      "of": 58,
      "cows": 59,
      "Because": 60,
      "class": 61,
      "virtue": 62,
      "finger": 63,
      "sure": 64,
      "what": 65,
      "narrowed": 66,
      "saw": 67,
      "were": 68,
      "And": 69,
      "even": 70,
      "then": 71,
      "dirt": 72,
      "lip": 73,
      "baby": 74,
      "grass": 75,
      "hazel": 76,
      "quivered": 77,
      "darker": 78,
      "child": 79,
      "eyes": 80,
      "like": 81,
      "than": 82,
      "rising": 83,
      "from": 84,
      "lower": 85,
      "silky": 86,
      "own": 87
    },
    "unk_token": "<unk>"
  }
}