tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 53,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 54,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 55,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 56,
      "content": "<mask>",
      "single_word": false,
      "lstrip": true,
      "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": "RobertaProcessing",
    "sep": [
      "</s>",
      54
    ],
    "cls": [
      "<s>",
      53
    ],
    "trim_offsets": true,
    "add_prefix_space": false
  },
  "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,
    "byte_fallback": false,
    "vocab": {
      "<unk>": 0,
      "a": 1,
      "b": 2,
      "c": 3,
      "d": 4,
      "e": 5,
      "f": 6,
      "g": 7,
      "h": 8,
      "i": 9,
      "j": 10,
      "k": 11,
      "l": 12,
      "m": 13,
      "n": 14,
      "o": 15,
      "p": 16,
      "q": 17,
      "r": 18,
      "s": 19,
      "t": 20,
      "u": 21,
      "v": 22,
      "w": 23,
      "x": 24,
      "y": 25,
      "z": 26,
      "x</w>": 27,
      "v</w>": 28,
      "d</w>": 29,
      "r</w>": 30,
      "s</w>": 31,
      "w</w>": 32,
      "c</w>": 33,
      "k</w>": 34,
      "n</w>": 35,
      "y</w>": 36,
      "p</w>": 37,
      "j</w>": 38,
      "g</w>": 39,
      "f</w>": 40,
      "t</w>": 41,
      "z</w>": 42,
      "a</w>": 43,
      "e</w>": 44,
      "o</w>": 45,
      "q</w>": 46,
      "i</w>": 47,
      "u</w>": 48,
      "m</w>": 49,
      "h</w>": 50,
      "l</w>": 51,
      "b</w>": 52
    },
    "merges": []
  }
}