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": "<s>",
      "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
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "Split",
        "pattern": {
          "Regex": "[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]*[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]+|[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]+[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]*|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
        },
        "behavior": "Isolated",
        "invert": false
      },
      {
        "type": "ByteLevel",
        "add_prefix_space": false,
        "trim_offsets": true,
        "use_regex": false
      }
    ]
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 1
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "</s>": {
        "id": "</s>",
        "ids": [
          2
        ],
        "tokens": [
          "</s>"
        ]
      },
      "<s>": {
        "id": "<s>",
        "ids": [
          1
        ],
        "tokens": [
          "<s>"
        ]
      }
    }
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "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": true,
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "Ċ": 3,
      "!": 4,
      "*": 5,
      "+": 6,
      ",": 7,
      "-": 8,
      ".": 9,
      "/": 10,
      "0": 11,
      "1": 12,
      "2": 13,
      "3": 14,
      "4": 15,
      "5": 16,
      "6": 17,
      "7": 18,
      "8": 19,
      "9": 20,
      ":": 21,
      ";": 22,
      "=": 23,
      "?": 24,
      "A": 25,
      "B": 26,
      "C": 27,
      "D": 28,
      "E": 29,
      "F": 30,
      "G": 31,
      "H": 32,
      "I": 33,
      "J": 34,
      "K": 35,
      "L": 36,
      "M": 37,
      "N": 38,
      "O": 39,
      "P": 40,
      "Q": 41,
      "R": 42,
      "S": 43,
      "T": 44,
      "U": 45,
      "V": 46,
      "W": 47,
      "X": 48,
      "Y": 49,
      "Z": 50,
      "a": 51,
      "b": 52,
      "c": 53,
      "d": 54,
      "e": 55,
      "f": 56,
      "g": 57,
      "h": 58,
      "i": 59,
      "j": 60,
      "k": 61,
      "l": 62,
      "m": 63,
      "n": 64,
      "o": 65,
      "p": 66,
      "q": 67,
      "r": 68,
      "s": 69,
      "t": 70,
      "u": 71,
      "v": 72,
      "w": 73,
      "x": 74,
      "y": 75,
      "z": 76
    },
    "merges": []
  }
}