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": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "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": null,
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "[UNK]",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "[UNK]": 0,
      "[CLS]": 1,
      "[SEP]": 2,
      "[PAD]": 3,
      "[MASK]": 4,
      "(": 5,
      ")": 6,
      "*": 7,
      "+": 8,
      "-": 9,
      "0": 10,
      "1": 11,
      "2": 12,
      "3": 13,
      "4": 14,
      "5": 15,
      "6": 16,
      "7": 17,
      "8": 18,
      "9": 19,
      ":": 20,
      "<": 21,
      "=": 22,
      ">": 23,
      "F": 24,
      "I": 25,
      "R": 26,
      "S": 27,
      "a": 28,
      "d": 29,
      "e": 30,
      "i": 31,
      "l": 32,
      "n": 33,
      "p": 34,
      "s": 35,
      "t": 36,
      "u": 37,
      "Ċ": 38,
      "Ġ": 39
    },
    "merges": []
  }
}