tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 1,
    "pad_type_id": 0,
    "pad_token": "[PAD]"
  },
  "added_tokens": [
    {
      "id": 11,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "0": 0,
      "1": 1,
      "2": 2,
      "3": 3,
      "4": 4,
      "5": 5,
      "6": 6,
      "7": 7,
      "8": 8,
      "9": 9,
      "S": 10
    },
    "unk_token": "[UNK]"
  }
}