{
  "corpus": {
    "characters": 45223,
    "stories": 400
  },
  "alphabet": [
    "\n",
    " ",
    ",",
    ".",
    "a",
    "b",
    "c",
    "d",
    "e",
    "g",
    "h",
    "i",
    "k",
    "l",
    "m",
    "n",
    "o",
    "p",
    "r",
    "s",
    "t",
    "u",
    "v",
    "w",
    "x",
    "y",
    "z"
  ],
  "base_vocab_size": 28,
  "vocab_size": 96,
  "merge_count": 68,
  "first_merges": [
    {
      "pair": [
        " ",
        "t"
      ],
      "token": " t",
      "count": 2400
    },
    {
      "pair": [
        "h",
        "e"
      ],
      "token": "he",
      "count": 1798
    },
    {
      "pair": [
        " t",
        "he"
      ],
      "token": " the",
      "count": 1600
    },
    {
      "pair": [
        " ",
        "g"
      ],
      "token": " g",
      "count": 1186
    },
    {
      "pair": [
        " ",
        "b"
      ],
      "token": " b",
      "count": 1101
    },
    {
      "pair": [
        " ",
        "a"
      ],
      "token": " a",
      "count": 1072
    },
    {
      "pair": [
        " ",
        "h"
      ],
      "token": " h",
      "count": 1010
    },
    {
      "pair": [
        " h",
        "a"
      ],
      "token": " ha",
      "count": 1010
    },
    {
      "pair": [
        " ha",
        "s"
      ],
      "token": " has",
      "count": 800
    },
    {
      "pair": [
        " t",
        "o"
      ],
      "token": " to",
      "count": 800
    },
    {
      "pair": [
        "e",
        "s"
      ],
      "token": "es",
      "count": 800
    },
    {
      "pair": [
        "e",
        "n"
      ],
      "token": "en",
      "count": 716
    }
  ],
  "last_merges": [
    {
      "pair": [
        " kit",
        "c"
      ],
      "token": " kitc",
      "count": 198
    },
    {
      "pair": [
        " kitc",
        "he"
      ],
      "token": " kitche",
      "count": 198
    },
    {
      "pair": [
        " kitche",
        "n"
      ],
      "token": " kitchen",
      "count": 198
    },
    {
      "pair": [
        " p",
        "ar"
      ],
      "token": " par",
      "count": 198
    },
    {
      "pair": [
        " par",
        "k"
      ],
      "token": " park",
      "count": 198
    }
  ],
  "corpus_tokens": 14381,
  "characters_per_token": 3.145,
  "round_trip": true,
  "sweep": [
    {
      "requested": 40,
      "vocab_size": 40,
      "tokens": 30930,
      "characters_per_token": 1.462
    },
    {
      "requested": 64,
      "vocab_size": 64,
      "tokens": 21494,
      "characters_per_token": 2.104
    },
    {
      "requested": 96,
      "vocab_size": 96,
      "tokens": 14381,
      "characters_per_token": 3.145
    },
    {
      "requested": 128,
      "vocab_size": 109,
      "tokens": 12400,
      "characters_per_token": 3.647
    }
  ],
  "samples": [
    {
      "text": "mia has a red ball.",
      "tokens": [
        "mia",
        " has",
        " a",
        " red",
        " ball",
        "."
      ],
      "ids": [
        58,
        36,
        33,
        89,
        85,
        4
      ],
      "decoded": "mia has a red ball."
    },
    {
      "text": "maya has a purple umbrella.",
      "tokens": [
        "m",
        "a",
        "y",
        "a",
        " has",
        " a",
        " p",
        "u",
        "r",
        "p",
        "l",
        "e",
        " ",
        "u",
        "m",
        "b",
        "re",
        "ll",
        "a",
        "."
      ],
      "ids": [
        15,
        5,
        26,
        5,
        36,
        33,
        90,
        22,
        19,
        18,
        14,
        9,
        2,
        22,
        15,
        6,
        44,
        43,
        5,
        4
      ],
      "decoded": "maya has a purple umbrella."
    },
    {
      "text": "café",
      "tokens": [
        "c",
        "a",
        "<unk>",
        "<unk>"
      ],
      "ids": [
        7,
        5,
        0,
        0
      ],
      "decoded": "ca��"
    }
  ]
}