test / giga-tokens.txt
csukuangfj's picture
small fixes
ee0d936
<blk> 0
<sos/eos> 1
<unk> 2
S 3
T 4
▁THE 5
▁A 6
E 7
▁AND 8
▁TO 9
N 10
D 11
▁OF 12
' 13
ING 14
▁I 15
Y 16
▁IN 17
ED 18
▁THAT 19
▁ 20
P 21
R 22
▁YOU 23
M 24
RE 25
ER 26
C 27
O 28
▁IT 29
L 30
A 31
U 32
G 33
▁WE 34
▁IS 35
▁SO 36
AL 37
I 38
▁S 39
▁RE 40
AR 41
B 42
▁FOR 43
▁C 44
▁BE 45
LE 46
F 47
W 48
▁E 49
▁HE 50
LL 51
▁WAS 52
LY 53
OR 54
IN 55
▁F 56
VE 57
▁THIS 58
TH 59
K 60
▁ON 61
IT 62
▁B 63
▁WITH 64
▁BUT 65
EN 66
CE 67
RI 68
▁DO 69
UR 70
▁HAVE 71
▁DE 72
▁ME 73
▁T 74
ENT 75
CH 76
▁THEY 77
▁NOT 78
ES 79
V 80
▁AS 81
RA 82
▁P 83
ON 84
TER 85
▁ARE 86
▁WHAT 87
IC 88
▁ST 89
▁LIKE 90
ATION 91
▁OR 92
▁CA 93
▁AT 94
H 95
▁KNOW 96
▁G 97
AN 98
▁CON 99
IL 100
ND 101
RO 102
▁HIS 103
▁CAN 104
▁ALL 105
TE 106
▁THERE 107
▁SU 108
▁MO 109
▁MA 110
LI 111
▁ONE 112
▁ABOUT 113
LA 114
▁CO 115
- 116
▁MY 117
▁HAD 118
CK 119
NG 120
▁NO 121
MENT 122
AD 123
LO 124
ME 125
▁AN 126
▁FROM 127
NE 128
▁IF 129
VER 130
▁JUST 131
▁PRO 132
ION 133
▁PA 134
▁WHO 135
▁SE 136
EL 137
IR 138
▁US 139
▁UP 140
▁YOUR 141
CI 142
RY 143
▁GO 144
▁SHE 145
▁LE 146
▁OUT 147
▁PO 148
▁HO 149
ATE 150
▁BO 151
▁BY 152
▁FA 153
▁MI 154
AS 155
MP 156
▁HER 157
VI 158
▁THINK 159
▁SOME 160
▁WHEN 161
▁AH 162
▁PEOPLE 163
IG 164
▁WA 165
▁TE 166
▁LA 167
▁WERE 168
▁LI 169
▁WOULD 170
▁SEE 171
▁WHICH 172
DE 173
GE 174
▁K 175
IGHT 176
▁HA 177
▁OUR 178
UN 179
▁HOW 180
▁GET 181
IS 182
UT 183
Z 184
CO 185
ET 186
UL 187
IES 188
IVE 189
AT 190
▁O 191
▁DON 192
LU 193
▁TIME 194
▁WILL 195
▁MORE 196
▁SP 197
▁NOW 198
RU 199
▁THEIR 200
▁UN 201
ITY 202
OL 203
X 204
TI 205
US 206
▁VERY 207
TION 208
▁FI 209
▁SAY 210
▁BECAUSE 211
▁EX 212
▁RO 213
ERS 214
IST 215
▁DA 216
TING 217
▁EN 218
OM 219
▁BA 220
▁BEEN 221
▁LO 222
▁UM 223
AGE 224
ABLE 225
▁WO 226
▁RA 227
▁OTHER 228
▁REALLY 229
ENCE 230
▁GOING 231
▁HIM 232
▁HAS 233
▁THEM 234
▁DIS 235
▁WANT 236
ID 237
TA 238
▁LOOK 239
KE 240
▁DID 241
▁SA 242
▁VI 243
▁SAID 244
▁RIGHT 245
▁THESE 246
▁WORK 247
▁COM 248
ALLY 249
FF 250
QU 251
AC 252
▁DR 253
▁WAY 254
▁INTO 255
MO 256
TED 257
EST 258
▁HERE 259
OK 260
▁COULD 261
▁WELL 262
MA 263
▁PRE 264
▁DI 265
MAN 266
▁COMP 267
▁THEN 268
IM 269
▁PER 270
▁NA 271
▁WHERE 272
▁TWO 273
▁WI 274
▁FE 275
INE 276
▁ANY 277
TURE 278
▁OVER 279
BO 280
ACH 281
OW 282
▁MAKE 283
▁TRA 284
HE 285
UND 286
▁EVEN 287
ANCE 288
▁YEAR 289
HO 290
AM 291
▁CHA 292
▁BACK 293
VO 294
ANT 295
DI 296
▁ALSO 297
▁THOSE 298
▁MAN 299
CTION 300
ICAL 301
▁JO 302
▁OP 303
▁NEW 304
▁MU 305
▁HU 306
▁KIND 307
▁NE 308
CA 309
END 310
TIC 311
FUL 312
▁YEAH 313
SH 314
▁APP 315
▁THINGS 316
SIDE 317
▁GOOD 318
ONE 319
▁TAKE 320
CU 321
▁EVERY 322
▁MEAN 323
▁FIRST 324
OP 325
▁TH 326
▁MUCH 327
▁PART 328
UGH 329
▁COME 330
J 331
▁THAN 332
▁EXP 333
▁AGAIN 334
▁LITTLE 335
MB 336
▁NEED 337
▁TALK 338
IF 339
FOR 340
▁SH 341
ISH 342
▁STA 343
ATED 344
▁GU 345
▁LET 346
IA 347
▁MAR 348
▁DOWN 349
▁DAY 350
▁GA 351
▁SOMETHING 352
▁BU 353
DUC 354
HA 355
▁LOT 356
▁RU 357
▁THOUGH 358
▁GREAT 359
AIN 360
▁THROUGH 361
▁THING 362
OUS 363
▁PRI 364
▁GOT 365
▁SHOULD 366
▁AFTER 367
▁HEAR 368
▁TA 369
▁ONLY 370
▁CHI 371
IOUS 372
▁SHA 373
▁MOST 374
▁ACTUALLY 375
▁START 376
LIC 377
▁VA 378
▁RI 379
DAY 380
IAN 381
▁DOES 382
ROW 383
▁GRA 384
ITION 385
▁MANY 386
▁BEFORE 387
▁GIVE 388
PORT 389
QUI 390
▁LIFE 391
▁WORLD 392
▁PI 393
▁LONG 394
▁THREE 395
IZE 396
NESS 397
▁SHOW 398
PH 399
▁WHY 400
▁QUESTION 401
WARD 402
▁THANK 403
▁PH 404
▁DIFFERENT 405
▁OWN 406
▁FEEL 407
▁MIGHT 408
▁HAPPEN 409
▁MADE 410
▁BRO 411
IBLE 412
▁HI 413
▁STATE 414
▁HAND 415
▁NEVER 416
▁PLACE 417
▁LOVE 418
▁DU 419
▁POINT 420
▁HELP 421
▁COUNT 422
▁STILL 423
▁MR 424
▁FIND 425
▁PERSON 426
▁CAME 427
▁SAME 428
▁LAST 429
▁HIGH 430
▁OLD 431
▁UNDER 432
▁FOUR 433
▁AROUND 434
▁SORT 435
▁CHANGE 436
▁YES 437
SHIP 438
▁ANOTHER 439
ATIVE 440
▁FOUND 441
▁JA 442
▁ALWAYS 443
▁NEXT 444
▁TURN 445
▁JU 446
▁SIX 447
▁FACT 448
▁INTEREST 449
▁WORD 450
▁THOUSAND 451
▁HUNDRED 452
▁NUMBER 453
▁IDEA 454
▁PLAN 455
▁COURSE 456
▁SCHOOL 457
▁HOUSE 458
▁TWENTY 459
▁JE 460
▁PLAY 461
▁AWAY 462
▁LEARN 463
▁HARD 464
▁WEEK 465
▁BETTER 466
▁WHILE 467
▁FRIEND 468
▁OKAY 469
▁NINE 470
▁UNDERSTAND 471
▁KEEP 472
▁GONNA 473
▁SYSTEM 474
▁AMERICA 475
▁POWER 476
▁IMPORTANT 477
▁WITHOUT 478
▁MAYBE 479
▁SEVEN 480
▁BETWEEN 481
▁BUILD 482
▁CERTAIN 483
▁PROBLEM 484
▁MONEY 485
▁BELIEVE 486
▁SECOND 487
▁REASON 488
▁TOGETHER 489
▁PUBLIC 490
▁ANYTHING 491
▁SPEAK 492
▁BUSINESS 493
▁EVERYTHING 494
▁CLOSE 495
▁QUITE 496
▁ANSWER 497
▁ENOUGH 498
Q 499