tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<s>",
      "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
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "ⴳⵯ|ⴽⵯ|."
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "</s>": {
        "id": "</s>",
        "ids": [
          2
        ],
        "tokens": [
          "</s>"
        ]
      },
      "<s>": {
        "id": "<s>",
        "ids": [
          1
        ],
        "tokens": [
          "<s>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      "ⴳⵯ": 4,
      "ⴽⵯ": 5,
      "ⴰ": 6,
      "ⴱ": 7,
      "ⴳ": 8,
      "ⴷ": 9,
      "ⴹ": 10,
      "ⴻ": 11,
      "ⴼ": 12,
      "ⴽ": 13,
      "ⵀ": 14,
      "ⵃ": 15,
      "ⵄ": 16,
      "ⵅ": 17,
      "ⵇ": 18,
      "ⵉ": 19,
      "ⵊ": 20,
      "ⵍ": 21,
      "ⵎ": 22,
      "ⵏ": 23,
      "ⵓ": 24,
      "ⵔ": 25,
      "ⵕ": 26,
      "ⵖ": 27,
      "ⵙ": 28,
      "ⵚ": 29,
      "ⵛ": 30,
      "ⵜ": 31,
      "ⵟ": 32,
      "ⵡ": 33,
      "ⵢ": 34,
      "ⵣ": 35,
      "ⵥ": 36,
      "0": 37,
      "1": 38,
      "2": 39,
      "3": 40,
      "4": 41,
      "5": 42,
      "6": 43,
      "7": 44,
      "8": 45,
      "9": 46,
      " ": 47,
      ".": 48,
      ",": 49,
      ";": 50,
      ":": 51,
      "!": 52,
      "?": 53,
      "-": 54,
      "'": 55,
      "\"": 56,
      "(": 57,
      ")": 58,
      "[": 59,
      "]": 60,
      "{": 61,
      "}": 62,
      "@": 63,
      "#": 64,
      "%": 65,
      "&": 66,
      "*": 67,
      "+": 68,
      "=": 69,
      "/": 70,
      "<": 71,
      ">": 72,
      "\\": 73,
      "|": 74,
      "~": 75,
      "`": 76,
      "^": 77,
      "_": 78,
      "\n": 79,
      "\t": 80
    },
    "unk_token": "<unk>"
  }
}