{
  "cases": [
    {
      "text": "The quick brown fox jumps over the lazy dog.",
      "words": [
        "The",
        "quick",
        "brown",
        "fox",
        "jumps",
        "over",
        "the",
        "lazy",
        "dog."
      ],
      "input_ids": [
        50281,
        510,
        32600,
        33167,
        15736,
        75,
        10628,
        1189,
        783,
        77,
        26537,
        21428,
        15,
        50282
      ],
      "word_ids": [
        -1,
        0,
        1,
        2,
        3,
        4,
        4,
        5,
        6,
        7,
        7,
        8,
        8,
        -1
      ],
      "attention_mask": [
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
      ],
      "tokens": [
        "[CLS]",
        "The",
        "quick",
        "brown",
        "fox",
        "j",
        "umps",
        "over",
        "the",
        "l",
        "azy",
        "dog",
        ".",
        "[SEP]"
      ]
    },
    {
      "text": "Compression keeps high-entropy identifiers like 7f3a9c2b intact.",
      "words": [
        "Compression",
        "keeps",
        "high-entropy",
        "identifiers",
        "like",
        "7f3a9c2b",
        "intact."
      ],
      "input_ids": [
        50281,
        5065,
        1256,
        413,
        2265,
        8656,
        14,
        290,
        10144,
        888,
        13783,
        3022,
        24,
        71,
        20,
        66,
        26,
        68,
        19,
        67,
        565,
        514,
        15,
        50282
      ],
      "word_ids": [
        -1,
        0,
        0,
        1,
        1,
        2,
        2,
        2,
        2,
        3,
        3,
        4,
        5,
        5,
        5,
        5,
        5,
        5,
        5,
        5,
        6,
        6,
        6,
        -1
      ],
      "attention_mask": [
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
      ],
      "tokens": [
        "[CLS]",
        "Comp",
        "ression",
        "ke",
        "eps",
        "high",
        "-",
        "ent",
        "ropy",
        "ident",
        "ifiers",
        "like",
        "7",
        "f",
        "3",
        "a",
        "9",
        "c",
        "2",
        "b",
        "int",
        "act",
        ".",
        "[SEP]"
      ]
    },
    {
      "text": "ModernBERT byte-level BPE handles subwords: tokenization, retokenizing.",
      "words": [
        "ModernBERT",
        "byte-level",
        "BPE",
        "handles",
        "subwords:",
        "tokenization,",
        "retokenizing."
      ],
      "input_ids": [
        50281,
        33824,
        35,
        6366,
        8833,
        14,
        5251,
        35,
        3246,
        4608,
        868,
        2377,
        12113,
        27,
        13763,
        1320,
        13,
        1221,
        5097,
        3006,
        15,
        50282
      ],
      "word_ids": [
        -1,
        0,
        0,
        0,
        1,
        1,
        1,
        2,
        2,
        3,
        3,
        4,
        4,
        4,
        5,
        5,
        5,
        6,
        6,
        6,
        6,
        -1
      ],
      "attention_mask": [
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
      ],
      "tokens": [
        "[CLS]",
        "Modern",
        "B",
        "ERT",
        "byte",
        "-",
        "level",
        "B",
        "PE",
        "hand",
        "les",
        "sub",
        "words",
        ":",
        "token",
        "ization",
        ",",
        "ret",
        "oken",
        "izing",
        ".",
        "[SEP]"
      ]
    },
    {
      "text": "ERROR: connection refused at 10.0.0.42:8080 (retry in 3s)",
      "words": [
        "ERROR:",
        "connection",
        "refused",
        "at",
        "10.0.0.42:8080",
        "(retry",
        "in",
        "3s)"
      ],
      "input_ids": [
        50281,
        12641,
        27,
        14477,
        709,
        3197,
        255,
        740,
        15,
        17,
        15,
        17,
        15,
        2945,
        27,
        40058,
        9,
        1221,
        610,
        249,
        20,
        84,
        10,
        50282
      ],
      "word_ids": [
        -1,
        0,
        0,
        1,
        2,
        2,
        3,
        4,
        4,
        4,
        4,
        4,
        4,
        4,
        4,
        4,
        5,
        5,
        5,
        6,
        7,
        7,
        7,
        -1
      ],
      "attention_mask": [
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
      ],
      "tokens": [
        "[CLS]",
        "ERROR",
        ":",
        "connection",
        "ref",
        "used",
        "at",
        "10",
        ".",
        "0",
        ".",
        "0",
        ".",
        "42",
        ":",
        "8080",
        "(",
        "ret",
        "ry",
        "in",
        "3",
        "s",
        ")",
        "[SEP]"
      ]
    },
    {
      "text": "a",
      "words": [
        "a"
      ],
      "input_ids": [
        50281,
        66,
        50282
      ],
      "word_ids": [
        -1,
        0,
        -1
      ],
      "attention_mask": [
        1,
        1,
        1
      ],
      "tokens": [
        "[CLS]",
        "a",
        "[SEP]"
      ]
    }
  ]
}