tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 8,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 9,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "WhitespaceSplit"
      }
    ]
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "-4": 0,
      "-3": 1,
      "-2": 2,
      "-1": 3,
      "1": 4,
      "2": 5,
      "3": 6,
      "4": 7
    },
    "unk_token": "<unk>"
  }
}