tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 74,
      "content": "<|begin_of_text|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 75,
      "content": "<|finetune_right_pad_id|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 76,
      "content": "<|eot_id|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "Split",
        "pattern": {
          "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\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": "Sequence",
    "processors": [
      {
        "type": "ByteLevel",
        "add_prefix_space": true,
        "trim_offsets": false,
        "use_regex": true
      },
      {
        "type": "TemplateProcessing",
        "single": [
          {
            "SpecialToken": {
              "id": "<|begin_of_text|>",
              "type_id": 0
            }
          },
          {
            "Sequence": {
              "id": "A",
              "type_id": 0
            }
          }
        ],
        "pair": [
          {
            "SpecialToken": {
              "id": "<|begin_of_text|>",
              "type_id": 0
            }
          },
          {
            "Sequence": {
              "id": "A",
              "type_id": 0
            }
          },
          {
            "SpecialToken": {
              "id": "<|begin_of_text|>",
              "type_id": 1
            }
          },
          {
            "Sequence": {
              "id": "B",
              "type_id": 1
            }
          }
        ],
        "special_tokens": {
          "<|begin_of_text|>": {
            "id": "<|begin_of_text|>",
            "ids": [
              74
            ],
            "tokens": [
              "<|begin_of_text|>"
            ]
          }
        }
      }
    ]
  },
  "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": {
      "!": 0,
      "*": 1,
      "+": 2,
      ",": 3,
      "-": 4,
      ".": 5,
      "/": 6,
      "0": 7,
      "1": 8,
      "2": 9,
      "3": 10,
      "4": 11,
      "5": 12,
      "6": 13,
      "7": 14,
      "8": 15,
      "9": 16,
      ":": 17,
      ";": 18,
      "=": 19,
      "?": 20,
      "A": 21,
      "B": 22,
      "C": 23,
      "D": 24,
      "E": 25,
      "F": 26,
      "G": 27,
      "H": 28,
      "I": 29,
      "J": 30,
      "K": 31,
      "L": 32,
      "M": 33,
      "N": 34,
      "O": 35,
      "P": 36,
      "Q": 37,
      "R": 38,
      "S": 39,
      "T": 40,
      "U": 41,
      "V": 42,
      "W": 43,
      "X": 44,
      "Y": 45,
      "Z": 46,
      "a": 47,
      "b": 48,
      "c": 49,
      "d": 50,
      "e": 51,
      "f": 52,
      "g": 53,
      "h": 54,
      "i": 55,
      "j": 56,
      "k": 57,
      "l": 58,
      "m": 59,
      "n": 60,
      "o": 61,
      "p": 62,
      "q": 63,
      "r": 64,
      "s": 65,
      "t": 66,
      "u": 67,
      "v": 68,
      "w": 69,
      "x": 70,
      "y": 71,
      "z": 72,
      "Ċ": 73,
      "<|begin_of_text|>": 74,
      "<|finetune_right_pad_id|>": 75,
      "<|eot_id|>": 76
    },
    "merges": []
  }
}