tokenizer/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true,
    "use_regex": true
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<|endoftext|>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<|endoftext|>": 0,
      "H": 1,
      "a": 2,
      "d": 3,
      "e": 4,
      "h": 5,
      "i": 6,
      "l": 7,
      "o": 8,
      "r": 9,
      "s": 10,
      "t": 11,
      "w": 12,
      "Ġ": 13,
      "is": 14,
      "Ġt": 15,
      "He": 16,
      "es": 17,
      "his": 18,
      "ld": 19,
      "ll": 20,
      "or": 21,
      "wor": 22,
      "Ġa": 23,
      "Ġis": 24,
      "Ġwor": 25,
      "Ġtes": 26,
      "Ġthis": 27,
      "Hell": 28,
      "Ġworld": 29,
      "Ġtest": 30,
      "Hello": 31
    },
    "merges": [
      [
        "i",
        "s"
      ],
      [
        "Ġ",
        "t"
      ],
      [
        "H",
        "e"
      ],
      [
        "e",
        "s"
      ],
      [
        "h",
        "is"
      ],
      [
        "l",
        "d"
      ],
      [
        "l",
        "l"
      ],
      [
        "o",
        "r"
      ],
      [
        "w",
        "or"
      ],
      [
        "Ġ",
        "a"
      ],
      [
        "Ġ",
        "is"
      ],
      [
        "Ġ",
        "wor"
      ],
      [
        "Ġt",
        "es"
      ],
      [
        "Ġt",
        "his"
      ],
      [
        "He",
        "ll"
      ],
      [
        "Ġwor",
        "ld"
      ],
      [
        "Ġtes",
        "t"
      ],
      [
        "Hell",
        "o"
      ]
    ]
  }
}