urlbert-tiny-base-v2 / tokenizer.json
CrabInHoney's picture
Upload 8 files
af17464 verified
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 64,
"strategy": "LongestFirst",
"stride": 0
},
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[SEP]",
"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": {
"type": "BertNormalizer",
"clean_text": true,
"handle_chinese_chars": true,
"strip_accents": null,
"lowercase": true
},
"pre_tokenizer": {
"type": "BertPreTokenizer"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 1
}
}
],
"special_tokens": {
"[CLS]": {
"id": "[CLS]",
"ids": [
2
],
"tokens": [
"[CLS]"
]
},
"[SEP]": {
"id": "[SEP]",
"ids": [
3
],
"tokens": [
"[SEP]"
]
}
}
},
"decoder": {
"type": "WordPiece",
"prefix": "##",
"cleanup": true
},
"model": {
"type": "WordPiece",
"unk_token": "[UNK]",
"continuing_subword_prefix": "##",
"max_input_chars_per_word": 100,
"vocab": {
"[PAD]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[SEP]": 3,
"[MASK]": 4,
"&": 5,
"'": 6,
"*": 7,
",": 8,
"-": 9,
".": 10,
"/": 11,
"?": 12,
"0": 13,
"1": 14,
"2": 15,
"3": 16,
"4": 17,
"5": 18,
"6": 19,
"7": 20,
"8": 21,
"9": 22,
":": 23,
";": 24,
"\\": 25,
"_": 26,
"a": 27,
"b": 28,
"c": 29,
"d": 30,
"e": 31,
"f": 32,
"g": 33,
"h": 34,
"i": 35,
"j": 36,
"k": 37,
"l": 38,
"m": 39,
"n": 40,
"o": 41,
"p": 42,
"q": 43,
"r": 44,
"s": 45,
"t": 46,
"u": 47,
"v": 48,
"w": 49,
"x": 50,
"y": 51,
"z": 52,
"//": 53,
"//:": 54,
"http": 55,
"https": 56,
"ftp": 57,
"sftp": 58,
"mailto": 59,
"tel": 60,
"file": 61,
"ws": 62,
"wss": 63,
"rtmp": 64,
"ssh": 65,
"ldap": 66,
"ldaps": 67,
"nntp": 68,
"gopher": 69,
"telnet": 70,
"view": 71,
"source": 72,
"about": 73,
"chrome": 74,
"data": 75,
"irc": 76,
"ircs": 77,
"magnet": 78,
"mms": 79,
"redis": 80,
"rsync": 81,
"rtsp": 82,
"svn": 83,
"vnc": 84,
"webcal": 85,
"xmpp": 86,
"dns": 87,
"ntp": 88,
"ip": 89,
"com": 90,
"de": 91,
"net": 92,
"uk": 93,
"cn": 94,
"org": 95,
"info": 96,
"nl": 97,
"eu": 98,
"ru": 99,
"su": 100,
"href": 101,
"br": 102,
"htm": 103,
"php": 104,
"co": 105,
"ly": 106,
"bit": 107,
"log": 108,
"index": 109,
"bank": 110,
"za": 111,
"direct": 112,
"xml": 113,
"mail": 114,
"it": 115,
"www": 116,
"run": 117,
"security": 118,
"code": 119,
"promo": 120,
"jpg": 121,
"img": 122,
"pay": 123,
"form": 124,
"docs": 125,
"host": 126,
"ec": 127,
"cx": 128,
"free": 129,
"true": 130,
"false": 131,
"amp": 132,
"blog": 133,
"key": 134,
"pal": 135,
"contact": 136,
"online": 137,
"abc": 138,
"media": 139,
"admin": 140,
"etc": 141,
"login": 142,
"cmd": 143,
"bin": 144,
"web": 145,
"verif": 146,
"the": 147,
"in": 148,
"##s": 149,
"of": 150,
"la": 151,
"en": 152,
"and": 153,
"##e": 154,
"##a": 155,
"to": 156,
"##n": 157,
"##i": 158,
"der": 159,
"un": 160,
"di": 161,
"que": 162,
"##t": 163,
"is": 164,
"el": 165,
"se": 166,
"del": 167,
"die": 168,
"##r": 169,
"und": 170,
"et": 171,
"na": 172,
"##o": 173,
"was": 174,
"on": 175,
"##en": 176,
"##u": 177,
"des": 178,
"den": 179,
"le": 180,
"for": 181,
"da": 182,
"je": 183,
"van": 184,
"as": 185,
"##m": 186,
"sa": 187,
"do": 188,
"10": 189,
"an": 190,
"les": 191,
"una": 192,
"il": 193,
"by": 194,
"og": 195,
"##y": 196,
"at": 197,
"##l": 198,
"##d": 199,
"er": 200,
"al": 201,
"##er": 202,
"von": 203,
"du": 204,
"av": 205,
"##es": 206,
"med": 207,
"con": 208,
"##k": 209,
"est": 210,
"per": 211,
"som": 212,
"los": 213,
"por": 214,
"from": 215,
"that": 216,
"no": 217,
"11": 218,
"es": 219,
"ja": 220,
"km": 221,
"##е": 222,
"##an": 223,
"om": 224,
"im": 225,
"##ta": 226,
"dan": 227,
"##te": 228,
"##na": 229,
"para": 230,
"mit": 231,
"El": 232,
"his": 233,
"##у": 234,
"ha": 235,
"##da": 236,
"##ing": 237,
"une": 238,
"##h": 239,
"##ne": 240,
"##g": 241,
"das": 242,
"##in": 243,
"##re": 244,
"par": 245,
"##us": 246,
"##de": 247,
"au": 248,
"dans": 249,
"he": 250,
"che": 251,
"em": 252,
"dem": 253,
"19": 254,
"til": 255,
"се": 256,
"han": 257,
"##ia": 258,
"##le": 259,
"las": 260,
"della": 261,
"new": 262,
"##ra": 263,
"##is": 264,
"um": 265,
"si": 266,
"var": 267,
"are": 268,
"op": 269,
"zu": 270,
"##et": 271,
"were": 272,
"##os": 273,
"od": 274,
"son": 275,
"##о": 276,
"##do": 277,
"which": 278,
"##ja": 279,
"va": 280,
"pour": 281,
"ve": 282,
"##ti": 283,
"sur": 284,
"##la": 285,
"##ed": 286,
"war": 287,
"##to": 288,
"##se": 289,
"##ni": 290,
"##no": 291,
"be": 292,
"det": 293,
"##і": 294,
"##х": 295,
"gov": 296,
"##ar": 297,
"qui": 298,
"az": 299,
"te": 300,
"##va": 301,
"##nt": 302,
"##ma": 303,
"##ka": 304,
"had": 305,
"##ng": 306,
"also": 307,
"so": 308,
"##je": 309,
"##li": 310,
"am": 311,
"has": 312,
"dos": 313,
"ur": 314,
"##ie": 315,
"##ri": 316,
"entre": 317,
"##as": 318,
"lo": 319,
"era": 320,
"ni": 321,
"##al": 322,
"##j": 323,
"##ce": 324,
"first": 325,
"##ca": 326,
"##ment": 327,
"os": 328,
"met": 329,
"ou": 330,
"all": 331,
"##ko": 332,
"aus": 333,
"non": 334,
"##si": 335,
"##em": 336,
"##ly": 337,
"##b": 338,
"film": 339,
"##um": 340,
"##sa": 341,
"##v": 342,
"##ga": 343,
"##it": 344,
"##mi": 345,
"##ki": 346,
"po": 347,
"##ge": 348,
"##at": 349,
"##ba": 350,
"##ur": 351,
"##ke": 352,
"##st": 353,
"##ro": 354,
"##el": 355,
"##f": 356,
"##man": 357,
"##ci": 358,
"##ul": 359,
"##ndo": 360,
"##mente": 361,
"##ve": 362,
"##me": 363,
"##den": 364,
"##za": 365,
"##io": 366,
"##or": 367,
"##nya": 368,
"##ya": 369,
"##ten": 370,
"##x": 371,
"##om": 372,
"##di": 373,
"##kan": 374,
"##ek": 375,
"into": 376,
"##ak": 377,
"till": 378,
"##lo": 379,
"ble": 380,
"ka": 381,
"##S": 382,
"mai": 383,
"up": 384,
"ng": 385,
"##то": 386,
"aux": 387,
"##ny": 388,
"##ho": 389,
"##1": 390,
"##ju": 391,
"##lar": 392,
"##ji": 393,
"##go": 394,
"##ts": 395,
"##co": 396,
"##ler": 397,
"##tion": 398,
"##ir": 399,
"ad": 400,
"##ku": 401,
"##ze": 402,
"##w": 403,
"ki": 404,
"##ns": 405,
"##ik": 406,
"##ers": 407,
"##ry": 408,
"me": 409,
"##sen": 410,
"##des": 411,
"##ha": 412,
"##ban": 413,
"during": 414,
"where": 415,
"ze": 416,
"##rs": 417,
"can": 418,
"out": 419,
"wie": 420,
"со": 421,
"##ben": 422,
"##ren": 423,
"##sta": 424,
"##rt": 425,
"##tu": 426,
"fu": 427,
"##am": 428,
"##ou": 429,
"##ria": 430,
"##ov": 431,
"##il": 432,
"##mo": 433,
"vom": 434,
"##wa": 435,
"##jo": 436,
"##ica": 437,
"##be": 438,
"##ion": 439,
"##ken": 440,
"##ina": 441,
"##land": 442,
"##lla": 443,
"nu": 444,
"##ine": 445,
"##un": 446,
"club": 447,
"##che": 448,
"team": 449,
"##ner": 450,
"##ic": 451,
"ca": 452,
"##ok": 453,
"##ig": 454,
"##th": 455,
"##nu": 456,
"##ada": 457,
"##ste": 458,
"##ut": 459,
"pe": 460,
"ke": 461,
"area": 462,
"any": 463,
"##dos": 464,
"##ton": 465,
"##que": 466,
"vor": 467,
"##ty": 468,
"##tes": 469,
"##ble": 470,
"##das": 471
}
}
}