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": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<eos>",
      "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": "[\\s\\S]"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": {
    "type": "Fuse"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<bos>": 1,
      "<eos>": 2,
      "<unk>": 3,
      "\n": 4,
      "+": 5,
      "0": 6,
      "1": 7,
      "2": 8,
      "3": 9,
      "4": 10,
      "5": 11,
      "6": 12,
      "7": 13,
      "8": 14,
      "9": 15,
      "=": 16,
      "०": 17,
      "१": 18,
      "२": 19,
      "३": 20,
      "४": 21,
      "५": 22,
      "६": 23,
      "७": 24,
      "८": 25,
      "९": 26,
      "一": 27,
      "七": 28,
      "三": 29,
      "九": 30,
      "二": 31,
      "五": 32,
      "八": 33,
      "六": 34,
      "十": 35,
      "千": 36,
      "四": 37,
      "百": 38,
      "零": 39
    },
    "unk_token": "<unk>"
  }
}