tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 2,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<unk>": 0,
      "<bos>": 1,
      "<pad>": 2,
      ":": 3,
      "S0": 4,
      "S1": 5,
      "S2": 6,
      "S3": 7,
      "S4": 8,
      "S5": 9,
      "S6": 10,
      "S7": 11,
      "S8": 12,
      "S9": 13,
      "S10": 14,
      "S11": 15,
      "S12": 16,
      "S13": 17,
      "S14": 18,
      "S15": 19,
      "S16": 20,
      "S17": 21,
      "S18": 22,
      "S19": 23,
      "a0": 24,
      "a1": 25,
      "a2": 26,
      "a3": 27,
      "a4": 28
    },
    "unk_token": "<unk>"
  }
}