unicosys-hypergraph / tokenizer.json
drzo's picture
chore: update unicosys hypergraph model from CI pipeline
0b0319b verified
Raw
History Blame Contribute Delete
3.08 kB
{
"vocab_size": 32000,
"max_length": 128,
"char_to_id": {
"p": 4,
"e": 5,
"t": 6,
"r": 7,
" ": 8,
"a": 9,
"n": 10,
"d": 11,
"w": 12,
"f": 13,
"u": 14,
"c": 15,
"i": 16,
"j": 17,
"q": 18,
"l": 19,
"y": 20,
"o": 21,
"b": 22,
"s": 23,
"k": 24,
"v": 25,
"m": 26,
"h": 27,
"g": 28,
"(": 29,
")": 30,
"\u00e9": 31,
"z": 32,
":": 33,
"x": 34,
"-": 35,
"\ud83d\udc4b": 36,
"|": 37,
"4": 38,
"6": 39,
"7": 40,
"9": 41,
"3": 42,
"8": 43,
"\u00a0": 44,
".": 45,
"?": 46,
"\u00a3": 47,
"1": 48,
"+": 49,
"!": 50,
",": 51,
"\ud83d\udfe2": 52,
"2": 53,
"0": 54,
"\ud83c\udfe0": 55,
"5": 56,
"&": 57,
"\u2019": 58,
"'": 59,
"@": 60,
"#": 61,
"/": 62,
"[": 63,
"]": 64,
"\ud83d\udd52": 65,
"\ud83d\udd17": 66,
"\ud83d\udc8c": 67,
"\u2014": 68,
"\"": 69,
"$": 70,
"\u2013": 71,
"\ud83d\udcf8": 72,
"%": 73,
"\u2600": 74,
"\ufe0f": 75,
"_": 76,
"\u203c": 77,
"*": 78,
"=": 79,
"\ud83d\ude80": 80,
"\ud83c\udfba": 81,
"\ud83c\udfac": 82,
"\ud83d\udc64": 83,
"<": 84,
">": 85,
"\u26a1": 86,
"\u26bd": 87,
"\ud83d\ude26": 88,
"\ud83c\udf82": 89,
"\ud83d\udce3": 90,
"\u23f0": 91,
"~": 92,
"\ud83d\udc40": 93,
"\ud83d\udd06": 94,
"\ud835\udce1": 95,
"\ud835\udcee": 96,
"\ud835\udcf0": 97,
"\ud835\udcf2": 98,
"\ud835\udcf6": 99,
"\ud835\udcd0": 100,
"\ud835\udce4": 101,
"\ud835\udcda": 102,
"\ud83d\udcfa": 103,
"\ud83c\udf31": 104,
"\u201c": 105,
"\u201d": 106,
"\u2606": 107,
"\ud83d\uddd3": 108,
"\u23f3": 109,
"\ud83d\ude2d": 110,
"`": 111,
";": 112,
"\u2744": 113,
"\ud83e\udd16": 114,
"\ud83d\udcc4": 115,
"\ud83d\udca1": 116,
"\ud83c\udf89": 117,
"\ud83d\ude0a": 118,
"\ud83c\udfc6": 119,
"\u231b": 120,
"\ud83e\udd2f": 121,
"\u2728": 122,
"\u2022": 123,
"\ud83d\udcac": 124,
"\u2026": 125,
"\u200b": 126,
"\ud83c\udfc3": 127,
"\ud83c\udffd": 128,
"\u200d": 129,
"\u2642": 130,
"\ud83d\udecd": 131,
"\ud83d\udd25": 132,
"\u2764": 133,
"\ud83d\udd13": 134,
"\ud83d\udecb": 135,
"\u00ae": 136,
"\u2122": 137,
"\ud83c\udf3f": 138,
"\ud83d\udc1b": 139,
"\u2601": 140,
"\ud83d\udcf7": 141,
"\ud83c\udf88": 142,
"\ud83d\udc99": 143,
"\ud83d\ude0d": 144,
"\ud83c\udf81": 145,
"\u2708": 146,
"\ud83d\udc68": 147,
"\ud83c\udfa8": 148,
"\ud83d\ude0e": 149,
"\ud83d\udea8": 150,
"\ud83d\udcb8": 151,
"\ud83d\udee3": 152,
"\u25b6": 153,
"\ud83d\udcf9": 154,
"\ud83d\udccd": 155,
"\ud83c\udf6b": 156,
"\ud83d\udcb0": 157,
"\u20e3": 158,
"\ud83d\udcc2": 159,
"\u2705": 160,
"\ud83c\udf1e": 161,
"\ud83d\udd0d": 162,
"\ud83e\uddfb": 163
},
"next_id": 164
}