Pikachu / tokenizer.json

Ajout du tokenizer associé au modèle final

ac0227c verified about 1 month ago

9.34 kB

	{
	"version": "1.0",
	"truncation": null,
	"padding": null,
	"added_tokens": [
	{
	"id": 0,
	"content": "<s>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 1,
	"content": "<pad>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 2,
	"content": "</s>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 3,
	"content": "<unk>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	{
	"id": 4,
	"content": "<mask>",
	"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": "ByteLevel",
	"add_prefix_space": true,
	"trim_offsets": false,
	"use_regex": true
	},
	"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": {
	"<s>": 0,
	"<pad>": 1,
	"</s>": 2,
	"<unk>": 3,
	"<mask>": 4,
	"!": 5,
	"\"": 6,
	"#": 7,
	"$": 8,
	"%": 9,
	"&": 10,
	"'": 11,
	"(": 12,
	")": 13,
	"*": 14,
	"+": 15,
	",": 16,
	"-": 17,
	".": 18,
	"/": 19,
	"0": 20,
	"1": 21,
	"2": 22,
	"3": 23,
	"4": 24,
	"5": 25,
	"6": 26,
	"7": 27,
	"8": 28,
	"9": 29,
	":": 30,
	";": 31,
	"<": 32,
	"=": 33,
	">": 34,
	"?": 35,
	"@": 36,
	"A": 37,
	"B": 38,
	"C": 39,
	"D": 40,
	"E": 41,
	"F": 42,
	"G": 43,
	"H": 44,
	"I": 45,
	"J": 46,
	"K": 47,
	"L": 48,
	"M": 49,
	"N": 50,
	"O": 51,
	"P": 52,
	"Q": 53,
	"R": 54,
	"S": 55,
	"T": 56,
	"U": 57,
	"V": 58,
	"W": 59,
	"X": 60,
	"Y": 61,
	"Z": 62,
	"[": 63,
	"\\": 64,
	"]": 65,
	"^": 66,
	"_": 67,
	"`": 68,
	"a": 69,
	"b": 70,
	"c": 71,
	"d": 72,
	"e": 73,
	"f": 74,
	"g": 75,
	"h": 76,
	"i": 77,
	"j": 78,
	"k": 79,
	"l": 80,
	"m": 81,
	"n": 82,
	"o": 83,
	"p": 84,
	"q": 85,
	"r": 86,
	"s": 87,
	"t": 88,
	"u": 89,
	"v": 90,
	"w": 91,
	"x": 92,
	"y": 93,
	"z": 94,
	"{": 95,
	"\|": 96,
	"}": 97,
	"~": 98,
	"¡": 99,
	"¢": 100,
	"£": 101,
	"¤": 102,
	"¥": 103,
	"¦": 104,
	"§": 105,
	"¨": 106,
	"©": 107,
	"ª": 108,
	"«": 109,
	"¬": 110,
	"®": 111,
	"¯": 112,
	"°": 113,
	"±": 114,
	"²": 115,
	"³": 116,
	"´": 117,
	"µ": 118,
	"¶": 119,
	"·": 120,
	"¸": 121,
	"¹": 122,
	"º": 123,
	"»": 124,
	"¼": 125,
	"½": 126,
	"¾": 127,
	"¿": 128,
	"À": 129,
	"Á": 130,
	"Â": 131,
	"Ã": 132,
	"Ä": 133,
	"Å": 134,
	"Æ": 135,
	"Ç": 136,
	"È": 137,
	"É": 138,
	"Ê": 139,
	"Ë": 140,
	"Ì": 141,
	"Í": 142,
	"Î": 143,
	"Ï": 144,
	"Ð": 145,
	"Ñ": 146,
	"Ò": 147,
	"Ó": 148,
	"Ô": 149,
	"Õ": 150,
	"Ö": 151,
	"×": 152,
	"Ø": 153,
	"Ù": 154,
	"Ú": 155,
	"Û": 156,
	"Ü": 157,
	"Ý": 158,
	"Þ": 159,
	"ß": 160,
	"à": 161,
	"á": 162,
	"â": 163,
	"ã": 164,
	"ä": 165,
	"å": 166,
	"æ": 167,
	"ç": 168,
	"è": 169,
	"é": 170,
	"ê": 171,
	"ë": 172,
	"ì": 173,
	"í": 174,
	"î": 175,
	"ï": 176,
	"ð": 177,
	"ñ": 178,
	"ò": 179,
	"ó": 180,
	"ô": 181,
	"õ": 182,
	"ö": 183,
	"÷": 184,
	"ø": 185,
	"ù": 186,
	"ú": 187,
	"û": 188,
	"ü": 189,
	"ý": 190,
	"þ": 191,
	"ÿ": 192,
	"Ā": 193,
	"ā": 194,
	"Ă": 195,
	"ă": 196,
	"Ą": 197,
	"ą": 198,
	"Ć": 199,
	"ć": 200,
	"Ĉ": 201,
	"ĉ": 202,
	"Ċ": 203,
	"ċ": 204,
	"Č": 205,
	"č": 206,
	"Ď": 207,
	"ď": 208,
	"Đ": 209,
	"đ": 210,
	"Ē": 211,
	"ē": 212,
	"Ĕ": 213,
	"ĕ": 214,
	"Ė": 215,
	"ė": 216,
	"Ę": 217,
	"ę": 218,
	"Ě": 219,
	"ě": 220,
	"Ĝ": 221,
	"ĝ": 222,
	"Ğ": 223,
	"ğ": 224,
	"Ġ": 225,
	"ġ": 226,
	"Ģ": 227,
	"ģ": 228,
	"Ĥ": 229,
	"ĥ": 230,
	"Ħ": 231,
	"ħ": 232,
	"Ĩ": 233,
	"ĩ": 234,
	"Ī": 235,
	"ī": 236,
	"Ĭ": 237,
	"ĭ": 238,
	"Į": 239,
	"į": 240,
	"İ": 241,
	"ı": 242,
	"Ĳ": 243,
	"ĳ": 244,
	"Ĵ": 245,
	"ĵ": 246,
	"Ķ": 247,
	"ķ": 248,
	"ĸ": 249,
	"Ĺ": 250,
	"ĺ": 251,
	"Ļ": 252,
	"ļ": 253,
	"Ľ": 254,
	"ľ": 255,
	"Ŀ": 256,
	"ŀ": 257,
	"Ł": 258,
	"ł": 259,
	"Ń": 260,
	"ik": 261,
	"ika": 262,
	"Pika": 263,
	"Ġ?": 264,
	"..": 265,
	"hu": 266,
	"Ġp": 267,
	"chu": 268,
	"Ġ!": 269,
	"Ġpika": 270,
	"es": 271,
	"Tu": 272,
	"ou": 273,
	"...": 274,
	"Qu": 275,
	"eu": 276,
	"Ġv": 277,
	"Ġchu": 278,
	"Ġes": 279,
	"Pikachu": 280,
	"as": 281,
	"en": 282,
	"oi": 283,
	"pika": 284,
	"tu": 285,
	"Ã©": 286,
	"Ġf": 287,
	"Ġt": 288,
	"ai": 289,
	"el": 290,
	"er": 291,
	"jou": 292,
	"on": 293,
	"re": 294,
	"Quel": 295,
	"eux": 296,
	"Ġest": 297,
	"Chu": 298,
	"Sa": 299,
	"cou": 300,
	"la": 301,
	"lu": 302,
	"qu": 303,
	"rÃ©": 304,
	"Ã§": 305,
	"Ġb": 306,
	"ĠPika": 307,
	"Ġas": 308,
	"Ġqu": 309,
	"Ġ!!": 310,
	"Ġvas": 311,
	"Ġfai": 312,
	"Ġton": 313,
	"jour": 314,
	"lut": 315,
	"Ġquoi": 316
	},
	"merges": [
	[
	"i",
	"k"
	],
	[
	"ik",
	"a"
	],
	[
	"P",
	"ika"
	],
	[
	"Ġ",
	"?"
	],
	[
	".",
	"."
	],
	[
	"h",
	"u"
	],
	[
	"Ġ",
	"p"
	],
	[
	"c",
	"hu"
	],
	[
	"Ġ",
	"!"
	],
	[
	"Ġp",
	"ika"
	],
	[
	"e",
	"s"
	],
	[
	"T",
	"u"
	],
	[
	"o",
	"u"
	],
	[
	"..",
	"."
	],
	[
	"Q",
	"u"
	],
	[
	"e",
	"u"
	],
	[
	"Ġ",
	"v"
	],
	[
	"Ġ",
	"chu"
	],
	[
	"Ġ",
	"es"
	],
	[
	"Pika",
	"chu"
	],
	[
	"a",
	"s"
	],
	[
	"e",
	"n"
	],
	[
	"o",
	"i"
	],
	[
	"p",
	"ika"
	],
	[
	"t",
	"u"
	],
	[
	"Ã",
	"©"
	],
	[
	"Ġ",
	"f"
	],
	[
	"Ġ",
	"t"
	],
	[
	"a",
	"i"
	],
	[
	"e",
	"l"
	],
	[
	"e",
	"r"
	],
	[
	"j",
	"ou"
	],
	[
	"o",
	"n"
	],
	[
	"r",
	"e"
	],
	[
	"Qu",
	"el"
	],
	[
	"eu",
	"x"
	],
	[
	"Ġes",
	"t"
	],
	[
	"C",
	"hu"
	],
	[
	"S",
	"a"
	],
	[
	"c",
	"ou"
	],
	[
	"l",
	"a"
	],
	[
	"l",
	"u"
	],
	[
	"q",
	"u"
	],
	[
	"r",
	"Ã©"
	],
	[
	"Ã",
	"§"
	],
	[
	"Ġ",
	"b"
	],
	[
	"Ġ",
	"Pika"
	],
	[
	"Ġ",
	"as"
	],
	[
	"Ġ",
	"qu"
	],
	[
	"Ġ!",
	"!"
	],
	[
	"Ġv",
	"as"
	],
	[
	"Ġf",
	"ai"
	],
	[
	"Ġt",
	"on"
	],
	[
	"jou",
	"r"
	],
	[
	"lu",
	"t"
	],
	[
	"Ġqu",
	"oi"
	]
	]
	}
	}