the-net / tokenizer.json
JacobLinCool's picture
The Net
93ebaf2
Raw History Blame Contribute Delete
6.02 kB
{
"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": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<eos>",
"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": [
{
"SpecialToken": {
"id": "<bos>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"<bos>": {
"id": "<bos>",
"ids": [
1
],
"tokens": [
"<bos>"
]
}
}
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<pad>": 0,
"<bos>": 1,
"<eos>": 2,
"Ā": 3,
"ā": 4,
"Ă": 5,
"ă": 6,
"Ą": 7,
"ą": 8,
"Ć": 9,
"ć": 10,
"Ĉ": 11,
"ĉ": 12,
"Ċ": 13,
"ċ": 14,
"Č": 15,
"č": 16,
"Ď": 17,
"ď": 18,
"Đ": 19,
"đ": 20,
"Ē": 21,
"ē": 22,
"Ĕ": 23,
"ĕ": 24,
"Ė": 25,
"ė": 26,
"Ę": 27,
"ę": 28,
"Ě": 29,
"ě": 30,
"Ĝ": 31,
"ĝ": 32,
"Ğ": 33,
"ğ": 34,
"Ġ": 35,
"!": 36,
"\"": 37,
"#": 38,
"$": 39,
"%": 40,
"&": 41,
"'": 42,
"(": 43,
")": 44,
"*": 45,
"+": 46,
",": 47,
"-": 48,
".": 49,
"/": 50,
"0": 51,
"1": 52,
"2": 53,
"3": 54,
"4": 55,
"5": 56,
"6": 57,
"7": 58,
"8": 59,
"9": 60,
":": 61,
";": 62,
"<": 63,
"=": 64,
">": 65,
"?": 66,
"@": 67,
"A": 68,
"B": 69,
"C": 70,
"D": 71,
"E": 72,
"F": 73,
"G": 74,
"H": 75,
"I": 76,
"J": 77,
"K": 78,
"L": 79,
"M": 80,
"N": 81,
"O": 82,
"P": 83,
"Q": 84,
"R": 85,
"S": 86,
"T": 87,
"U": 88,
"V": 89,
"W": 90,
"X": 91,
"Y": 92,
"Z": 93,
"[": 94,
"\\": 95,
"]": 96,
"^": 97,
"_": 98,
"`": 99,
"a": 100,
"b": 101,
"c": 102,
"d": 103,
"e": 104,
"f": 105,
"g": 106,
"h": 107,
"i": 108,
"j": 109,
"k": 110,
"l": 111,
"m": 112,
"n": 113,
"o": 114,
"p": 115,
"q": 116,
"r": 117,
"s": 118,
"t": 119,
"u": 120,
"v": 121,
"w": 122,
"x": 123,
"y": 124,
"z": 125,
"{": 126,
"|": 127,
"}": 128,
"~": 129,
"ġ": 130,
"Ģ": 131,
"ģ": 132,
"Ĥ": 133,
"ĥ": 134,
"Ħ": 135,
"ħ": 136,
"Ĩ": 137,
"ĩ": 138,
"Ī": 139,
"ī": 140,
"Ĭ": 141,
"ĭ": 142,
"Į": 143,
"į": 144,
"İ": 145,
"ı": 146,
"IJ": 147,
"ij": 148,
"Ĵ": 149,
"ĵ": 150,
"Ķ": 151,
"ķ": 152,
"ĸ": 153,
"Ĺ": 154,
"ĺ": 155,
"Ļ": 156,
"ļ": 157,
"Ľ": 158,
"ľ": 159,
"Ŀ": 160,
"ŀ": 161,
"Ł": 162,
"ł": 163,
"¡": 164,
"¢": 165,
"£": 166,
"¤": 167,
"¥": 168,
"¦": 169,
"§": 170,
"¨": 171,
"©": 172,
"ª": 173,
"«": 174,
"¬": 175,
"Ń": 176,
"®": 177,
"¯": 178,
"°": 179,
"±": 180,
"²": 181,
"³": 182,
"´": 183,
"µ": 184,
"¶": 185,
"·": 186,
"¸": 187,
"¹": 188,
"º": 189,
"»": 190,
"¼": 191,
"½": 192,
"¾": 193,
"¿": 194,
"À": 195,
"Á": 196,
"Â": 197,
"Ã": 198,
"Ä": 199,
"Å": 200,
"Æ": 201,
"Ç": 202,
"È": 203,
"É": 204,
"Ê": 205,
"Ë": 206,
"Ì": 207,
"Í": 208,
"Î": 209,
"Ï": 210,
"Ð": 211,
"Ñ": 212,
"Ò": 213,
"Ó": 214,
"Ô": 215,
"Õ": 216,
"Ö": 217,
"×": 218,
"Ø": 219,
"Ù": 220,
"Ú": 221,
"Û": 222,
"Ü": 223,
"Ý": 224,
"Þ": 225,
"ß": 226,
"à": 227,
"á": 228,
"â": 229,
"ã": 230,
"ä": 231,
"å": 232,
"æ": 233,
"ç": 234,
"è": 235,
"é": 236,
"ê": 237,
"ë": 238,
"ì": 239,
"í": 240,
"î": 241,
"ï": 242,
"ð": 243,
"ñ": 244,
"ò": 245,
"ó": 246,
"ô": 247,
"õ": 248,
"ö": 249,
"÷": 250,
"ø": 251,
"ù": 252,
"ú": 253,
"û": 254,
"ü": 255,
"ý": 256,
"þ": 257,
"ÿ": 258
},
"merges": []
}
}