tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 0,
    "pad_type_id": 0,
    "pad_token": "<pad>"
  },
  "added_tokens": [
    {
      "id": 0,
      "special": true,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 1,
      "special": true,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 24,
      "special": true,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "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": [
          24
        ],
        "tokens": [
          "</s>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<unk>": 1,
      "activate": 2,
      "bring": 3,
      "change_language": 4,
      "deactivate": 5,
      "decrease": 6,
      "increase": 7,
      "Chinese": 8,
      "English": 9,
      "German": 10,
      "Korean": 11,
      "heat": 12,
      "juice": 13,
      "lamp": 14,
      "lights": 15,
      "music": 16,
      "newspaper": 17,
      "shoes": 18,
      "socks": 19,
      "volume": 20,
      "bedroom": 21,
      "kitchen": 22,
      "washroom": 23,
      "</s>": 24
    },
    "unk_token": "<unk>"
  }
}