checkpoint-110000/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 1,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<pad>",
      "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
    },
    {
      "id": 67,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 68,
      "content": "<sep>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 69,
      "content": "<cls>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 70,
      "content": "<mask>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true,
    "use_regex": true
  },
  "post_processor": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": false,
    "use_regex": true
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": "",
    "end_of_word_suffix": "",
    "fuse_unk": false,
    "vocab": {
      "[UNK]": 0,
      "<s>": 1,
      "<pad>": 2,
      "</s>": 3,
      "\r": 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,
      "A": 22,
      "B": 23,
      "C": 24,
      "D": 25,
      "E": 26,
      "F": 27,
      "G": 28,
      "H": 29,
      "I": 30,
      "K": 31,
      "L": 32,
      "M": 33,
      "N": 34,
      "O": 35,
      "P": 36,
      "R": 37,
      "S": 38,
      "T": 39,
      "U": 40,
      "V": 41,
      "W": 42,
      "X": 43,
      "Y": 44,
      "Z": 45,
      "[": 46,
      "]": 47,
      "a": 48,
      "b": 49,
      "c": 50,
      "d": 51,
      "e": 52,
      "f": 53,
      "g": 54,
      "h": 55,
      "i": 56,
      "l": 57,
      "m": 58,
      "n": 59,
      "o": 60,
      "p": 61,
      "r": 62,
      "s": 63,
      "t": 64,
      "u": 65,
      "y": 66
    },
    "merges": []
  }
}