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": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[BOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[EOS]",
      "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": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[BOS]": 2,
      "[EOS]": 3,
      "hello": 4,
      "world": 5,
      "this": 6,
      "is": 7,
      "a": 8,
      "tiny": 9,
      "test": 10,
      "model": 11,
      "the": 12,
      "cat": 13,
      "sat": 14,
      "on": 15,
      "mat": 16,
      ".": 17,
      "I": 18,
      "you": 19,
      "we": 20,
      "like": 21,
      "code": 22,
      "and": 23,
      "data": 24,
      "good": 25,
      "morning": 26,
      "one": 27,
      "two": 28,
      "three": 29,
      "yes": 30,
      "no": 31
    },
    "unk_token": "[UNK]"
  }
}