viena-tiny-demo / tokenizer.vocab
lehungquangminh's picture
Upload Viena model
3ce00f4 verified
<pad> 0
<unk> 0
<s> 0
</s> 0
<|user|> 0
<|assistant|> 0
<|system|> 0
<|tool|> 0
▁t -0
▁l -1
▁h -2
▁th -3
ar -4
es -5
ic -6
▁n -7
ch -8
▁b -9
ọc -10
▁học -11
ra -12
ực -13
▁thực -14
▁v -15
th -16
am -17
▁a -18
▁p -19
ma -20
▁s -21
as -22
ll -23
wi -24
▁k -25
▁wi -26
▁with -27
Ho -28
St -29
ct -30
ee -31
ex -32
nd -33
ot -34
pl -35
How -36
arn -37
art -38
eep -39
ice -40
ics -41
▁St -42
▁ex -43
▁le -44
▁to -45
ampl -46
mall -47
otes -48
ract -49
▁How -50
▁and -51
▁bas -52
▁keep -53
amples -54
▁Start -55
▁learn -56
▁notes -57
▁pract -58
▁small -59
▁basics -60
▁examples -61
▁practice -62
nh -63
▁đ -64
Bắ -65
-66
gh -67
hỏ -68
uy -69
ép -70
ầu -71
ết -72
Bắt -73
ghi -74
ành -75
▁Cá -76
▁ch -77
▁lý -78
▁từ -79
▁và -80
uyết -81
▁Bắt -82
▁ghi -83
▁nhỏ -84
▁đầu -85
▁Cách -86
▁chép -87
▁hành -88
▁thuyết -89
ản -90
▁bản -91
▁d -92
iệ -93
iệu -94
▁dữ -95
▁liệu -96
iể -97
▁c -98
-99
Máy -100
▁cơ -101
▁Máy -102
-103
Xác -104
▁Xác -105
ăn -106
▁K -107
▁Đ -108
iểm -109
iểu -110
▁tra -111
▁văn -112
▁Đọc -113
▁Kiểm -114
▁hiểu -115
on -116
Py -117
▁Py -118
thon -119
▁Python -120
ie -121
na -122
iena -123
▁m -124
ix -125
tr -126
ietr -127
ietrix -128
te -129
ame -130
ter -131
▁do -132
▁là -133
▁tr -134
arame -135
arameter -136
do -137
ea -138
el -139
in -140
lt -141
lti -142
rea -143
ted -144
▁by -145
▁mu -146
▁ra -147
▁đa -148
doma -149
▁vực -150
▁crea -151
▁tham -152
domain -153
▁multi -154
▁triệu -155
▁created -156
arameters -157
▁parameters -158
bo -159
ed -160
ev -161
ho -162
-163
is -164
od -165
op -166
ut -167
hát -168
ill -169
ion -170
iển -171
ảng -172
▁am -173
▁is -174
bout -175
elop -176
odel -177
▁dev -178
▁has -179
▁kho -180
▁mill -181
▁phát -182
eloped -183
▁about -184
▁model -185
▁triển -186
▁khoảng -187
▁million -188
parameter -189
▁developed -190
Ki -191
ab -192
ac -193
ai -194
al -195
an -196
at -197
ba -198
by -199
bả -200
ce -201
cr -202
cs -203
-204
de -205
dữ -206
en -207
ep -208
er -209
et -210
ha -211
hi -212
hu -213
-214
-215
họ -216
hự -217
il -218
io -219
it -220
ke -221
kh -222
le -223
li -224
lo -225
-226
-227
me -228
mi -229
mo -230
mp -231
mu -232
ng -233
no -234
om -235
ou -236
ow -237
oả -238
pa -239
pe -240
ph -241
pr -242
re -243
ri -244
rn -245
rs -246
rt -247
si -248
sm -249
ta -250
ti -251
to -252
từ -253
ul -254
ve -255
-256
-257
vự -258
xa -259
yt -260
yế -261
àn -262
ác -263
át -264
áy -265
Đọ -266
đa -267
đầ -268
ắt -269
ểm -270
ển -271
ểu -272
ệu -273
▁B -274
▁C -275
▁H -276
▁M -277
▁P -278
▁S -279
▁X -280
▁e -281
▁g -282
▁i -283
▁r -284
▁w -285
Kiể -286
amp -287
ara -288
ate -289
bou -290
ché -291
del -292
ear -293
elo -294
ete -295
ien -296
iet -297
ith -298
les -299
lli -300
mai -301
mal -302
oma -303
oản -304
par -305
ped -306
pra -307
rac -308
rix -309
riể -310
riệ -311
sic -312
sma -313
tar -314
tes -315
tho -316
tic -317
ult -318
uyế -319
vel -320
vực -321
xam -322
yth -323
ách -324
Đọc -325
▁Bắ -326
▁Ho -327
▁Má -328
▁Xá -329
▁ab -330
▁an -331
▁ba -332
▁bả -333
▁cr -334
▁de -335
▁gh -336
▁ha -337
▁hi -338
▁hà -339
▁họ -340
▁ke -341
▁kh -342
▁li -343
▁mi -344
▁mo -345
▁nh -346
▁no -347
▁ph -348
▁vă -349
▁đầ -350
Cách -351
Pyth -352
Star -353
aram -354
asic -355
chép -356
ctic -357
earn -358
eate -359
evel -360
exam -361
hoản -362
illi -363
main -364
oped -365
ples -366
riệu -367
ters -368
trix -369
ulti -370
with -371
▁Kiể -372
▁abo -373
▁hiể -374
▁kee -375
▁liệ -376
▁mod -377
▁not -378
▁par -379
▁phá -380
▁pra -381
▁sma -382
▁tha -383
▁thu -384
▁thự -385
Start -386
amete -387
asics -388
ctice -389
hoảng -390
reate -391
▁Pyth -392
▁exam -393
▁thuy -394
▁triể -395
ameter -396
evelop -397
illion -398
parame -399
reated -400
ractice -401
▁exampl -402
▁parame -403
▁develop -404
▁parameter -405
-406
t -407
h -408
c -409
a -410
e -411
n -412
l -413
i -414
s -415
p -416
, -417
r -418
o -419
u -420
m -421
w -422
. -423
: -424
à -425
d -426
b -427
á -428
-429
y -430
-431
v -432
x -433
k -434
H -435
S -436
đ -437
g -438
B -439
C -440
é -441
ý -442
-443
-444
ế -445
-446
-447
-448
-449
-450
-451
M -452
ơ -453
X -454
K -455
ă -456
Đ -457
P -458