tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": {
    "strategy": {
      "Fixed": 12
    },
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 1,
    "pad_type_id": 0,
    "pad_token": "<pad>"
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<pad>",
      "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
    },
    {
      "id": 3,
      "content": "<unk>",
      "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": {
    "type": "Replace",
    "pattern": {
      "String": "X"
    },
    "content": "S"
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": "-"
    },
    "behavior": "Removed",
    "invert": false
  },
  "post_processor": {
    "type": "RobertaProcessing",
    "sep": [
      "</s>",
      2
    ],
    "cls": [
      "<s>",
      0
    ],
    "trim_offsets": true,
    "add_prefix_space": false
  },
  "decoder": {
    "type": "Fuse"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<s>": 0,
      "<pad>": 1,
      "</s>": 2,
      "<unk>": 3,
      "<mask>": 4,
      "E": 5,
      "S": 6,
      "R": 7,
      "A": 8,
      "K": 9,
      "L": 10,
      "N": 11,
      "T": 12,
      "O": 13,
      "P": 14,
      "M": 15,
      "^": 16,
      "U": 17,
      "B": 18,
      "D": 19,
      "SH": 20,
      "F": 21,
      "V": 22,
      "I": 23,
      "G": 24,
      "J": 25,
      "NT": 26,
      "'": 27,
      "TN": 28,
      "MN": 29,
      "TH": 30,
      "CH": 31,
      "EU": 32,
      "TM": 33,
      "DF": 34,
      "A&'": 35,
      "OE": 36,
      "SS": 37,
      "NG": 38,
      "NK": 39,
      "AU": 40,
      "TD": 41,
      "PNT": 42,
      "A&E": 43,
      "LD": 44,
      "MT": 45,
      "\\": 46
    },
    "unk_token": "<unk>"
  }
}