MTP-2 / mtp_tokenizer.vocab
teszenofficial's picture
Upload 4 files
e52e8b9 verified
<pad> 0
<unk> 0
<s> 0
</s> 0
es -0
en -1
de -2
on -3
▁p -4
os -5
▁c -6
ar -7
te -8
as -9
an -10
▁es -11
ci -12
in -13
▁de -14
er -15
▁u -16
or -17
▁y -18
▁con -19
al -20
▁m -21
la -22
ti -23
ue -24
▁S -25
▁g -26
▁s -27
▁un -28
do -29
re -30
tr -31
▁B -32
▁en -33
ta -34
to -35
▁M -36
▁¿ -37
ca -38
om -39
op -40
ui -41
▁f -42
▁l -43
der -44
orm -45
▁pr -46
is -47
lo -48
▁a -49
▁d -50
▁gr -51
▁in -52
▁te -53
fi -54
gu -55
ig -56
pa -57
po -58
ra -59
si -60
ño -61
▁P -62
▁n -63
ado -64
ant -65
enci -66
form -67
AC -68
DU -69
IN -70
KP -71
ón -72
▁L -73
▁T -74
▁e -75
▁h -76
▁r -77
INK -78
LAC -79
ara -80
ino -81
mos -82
que -83
rav -84
upo -85
▁ar -86
▁mu -87
ales -88
ente -89
fici -90
▁son -91
KPINK -92
antos -93
ravos -94
▁BLAC -95
▁inte -96
▁para -97
▁grupo -98
▁Bravos -99
▁Santos -100
▁BLACKPINK -101
TP -102
aj -103
bl -104
bu -105
ch -106
di -107
ec -108
go -109
mo -110
oy -111
rb -112
tu -113
▁D -114
▁F -115
▁K -116
▁v -117
aje -118
ano -119
ans -120
bre -121
des -122
ero -123
ers -124
esp -125
lat -126
lig -127
ñol -128
▁Mi -129
▁mo -130
▁su -131
engu -132
sica -133
tren -134
vers -135
▁MTP -136
▁com -137
▁del -138
▁des -139
▁lat -140
▁pop -141
▁urb -142
encia -143
espon -144
pañol -145
▁arti -146
ficial -147
former -148
versar -149
▁lengu -150
trenado -151
▁latino -152
▁respon -153
ligencia -154
▁español -155
ansformer -156
▁lenguaje -157
▁conversar -158
▁entrenado -159
▁responder -160
▁artificial -161
▁inteligencia -162
Ho -163
Qu -164
ez -165
il -166
im -167
it -168
ni -169
nt -170
qu -171
ud -172
us -173
én -174
ós -175
▁A -176
▁J -177
▁Y -178
▁j -179
Qui -180
Qué -181
abl -182
cer -183
cto -184
dos -185
mas -186
men -187
oci -188
pop -189
sic -190
tar -191
ven -192
xto -193
yud -194
ómo -195
▁Ho -196
▁Me -197
▁Th -198
▁bu -199
▁el -200
▁im -201
▁mú -202
▁po -203
▁tr -204
arte -205
asta -206
ción -207
delo -208
diós -209
enas -210
ener -211
eque -212
esta -213
gunt -214
ones -215
onto -216
tigo -217
tilo -218
uedo -219
▁DDU -220
▁Fui -221
▁Soy -222
▁cre -223
▁est -224
▁lla -225
▁nom -226
▁pla -227
▁pre -228
▁que -229
Quién -230
pacto -231
▁ayud -232
▁cero -233
▁como -234
▁gran -235
enerar -236
equeño -237
guntas -238
▁Adiós -239
▁Puedo -240
▁desde -241
▁hasta -242
▁music -243
▁poder -244
▁texto -245
▁buenas -246
▁estilo -247
▁modelo -248
▁música -249
▁nombre -250
▁pronto -251
▁urbano -252
▁contigo -253
▁generar -254
▁impacto -255
▁ayudarte -256
▁preguntas -257
▁transformer -258
01 -259
Cu -260
En -261
GP -262
On -263
ap -264
at -265
-266
cn -267
da -268
du -269
ej -270
-271
gr -272
-273
ic -274
ik -275
ol -276
oo -277
ou -278
ov -279
pr -280
rc -281
sa -282
yT -283
ál -284
ás -285
▁2 -286
▁C -287
▁R -288
▁V -289
016 -290
GPT -291
One -292
alm -293
are -294
arr -295
atr -296
atu -297
bal -298
bez -299
bin -300
ble -301
cip -302
cla -303
cno -304
cre -305
ctu -306
dor -307
duc -308
ebu -309
ect -310
erg -311
ete -312
etr -313
gía -314
ide -315
ien -316
ike -317
ill -318
ink -319
isa -320
ist -321
isu -322
lti -323
mor -324
nie -325
nos -326
och -327
opu -328
ore -329
oso -330
osé -331
ove -332
qui -333
ral -334
res -335
rta -336
udi -337
uen -338
éti -339
ías -340
▁En -341
▁La -342
▁Su -343
▁Sí -344
▁Tr -345
▁YG -346
▁al -347
▁as -348
▁at -349
▁bá -350
▁em -351
▁fa -352
▁fe -353
▁fi -354
▁ha -355
▁ju -356
▁jó -357
▁op -358
▁re -359
▁so -360
▁ti -361
▁to -362
▁tu -363
▁ve -364
Cuál -365
Cómo -366
Habl -367
anci -368
anos -369
apas -370
beza -371
bina -372
chos -373
creí -374
cómo -375
ecto -376
ectr -377
ejor -378
enom -379
fica -380
icos -381
idos -382
igit -383
igni -384
inas -385
iseñ -386
isoo -387
lado -388
ment -389
oduc -390
orch -391
orma -392
orme -393
pren -394
ques -395
trar -396
uego -397
uida -398
usta -399
▁Fue -400
▁GPT -401
▁How -402
▁Jen -403
▁One -404
▁PyT -405
▁Squ -406
▁Sus -407
▁You -408
▁fue -409
▁fui -410
▁glo -411
▁mez -412
▁nos -413
▁por -414
▁pue -415
▁rit -416
▁tar -417
▁una -418
▁usa -419
ablar -420
ación -421
antes -422
arrol -423
cnolo -424
ctura -425
ectan -426
etras -427
ideos -428
ienen -429
incip -430
mosas -431
oches -432
ocido -433
omete -434
quite -435
rcore -436
resca -437
rtain -438
taron -439
uenos -440
venes -441
venil -442
ética -443
▁2016 -444
▁Debu -445
▁Ente -446
▁Hola -447
▁Kill -448
▁Like -449
▁Lisa -450
▁Love -451
▁Pink -452
▁Rosé -453
▁That -454
▁This -455
▁alta -456
▁amor -457
▁audi -458
▁creó -459
▁días -460
▁natu -461
▁patr -462
▁pero -463
▁proy -464
▁soci -465
▁tipo -466
▁visu -467
Hablas -468
cabeza -469
dernos -470
ectrón -471
encias -472
ención -473
formas -474
menino -475
▁Canci -476
▁Jisoo -477
▁Venom -478
▁apren -479
▁asist -480
▁capas -481
▁cuida -482
▁demos -483
▁digit -484
▁diseñ -485
▁efici -486
▁emerg -487
▁estás -488
▁forma -489
▁gusta -490
▁hacer -491
▁llamo -492
▁luego -493
▁mejor -494
▁multi -495
▁plata -496
▁propu -497
▁redes -498
▁signi -499
▁sobre -500
▁temas -501
▁vemos -502
Quiénes -503
almente -504
creíble -505
grantes -506
▁Buenos -507
▁Jennie -508
▁Square -509
▁Tienen -510
▁básica -511
▁creado -512
▁enorme -513
▁fiesta -514
▁fresca -515
▁global -516
▁hablar -517
▁inform -518
▁letras -519
▁llamas -520
▁mezcla -521
▁muchos -522
▁noches -523
▁opinas -524
▁placer -525
▁produc -526
▁puedes -527
▁ritmos -528
▁tardes -529
▁toques -530
▁videos -531
cnología -532
ometedor -533
rcoreano -534
▁Pequeño -535
▁PyTorch -536
▁arquite -537
▁combina -538
▁famosas -539
▁juvenil -540
▁jóvenes -541
▁musical -542
▁natural -543
▁pequeño -544
▁princip -545
▁sonidos -546
▁urbanos -547
arrollado -548
rtainment -549
▁aprender -550
▁atención -551
▁conectan -552
▁conocido -553
▁cuidados -554
▁diseñado -555
▁electrón -556
▁estética -557
▁femenino -558
▁modernos -559
▁patrones -560
▁poderoso -561
▁proyecto -562
▁sociales -563
▁visuales -564
▁Canciones -565
▁Debutaron -566
▁asistente -567
▁demostrar -568
▁digitales -569
▁eficiente -570
▁emergente -571
▁increíble -572
▁musicales -573
▁propuesta -574
▁significa -575
▁audiencias -576
▁producción -577
▁prometedor -578
▁surcoreano -579
▁tecnología -580
▁Transformer -581
▁información -582
▁integrantes -583
▁plataformas -584
▁arquitectura -585
▁desarrollado -586
▁electrónicos -587
▁Entertainment -588
▁principalmente -589
16 -590
20 -591
Ad -592
BL -593
Br -594
Bu -595
CK -596
Ca -597
-598
DD -599
De -600
Fu -601
Ha -602
Je -603
Ji -604
Ki -605
LA -606
La -607
Li -608
Lo -609
MT -610
Me -611
Mi -612
NK -613
PI -614
PT -615
Pe -616
Pi -617
Pu -618
Py -619
Ro -620
Sa -621
So -622
Sq -623
Su -624
-625
Th -626
Ti -627
To -628
Tr -629
Ve -630
YG -631
Yo -632
ab -633
ac -634
ad -635
af -636
ai -637
am -638
au -639
av -640
ay -641
-642
ba -643
be -644
bi -645
br -646
cc -647
ce -648
cl -649
co -650
cr -651
ct -652
cu -653
-654
-655
ea -656
eb -657
ed -658
ef -659
eg -660
el -661
em -662
eo -663
eq -664
et -665
ex -666
-667
-668
fa -669
fe -670
fo -671
fr -672
fu -673
ge -674
gi -675
gl -676
gn -677
ha -678
he -679
hi -680
ho -681
ia -682
id -683
ie -684
if -685
io -686
ip -687
-688
-689
je -690
jo -691
ju -692
-693
ke -694
le -695
li -696
ll -697
lm -698
lt -699
lu -700
ma -701
mb -702
me -703
mp -704
mu -705
-706
na -707
nc -708
nd -709
ne -710
nf -711
ng -712
nk -713
nm -714
nn -715
no -716
ns -717
nv -718
ob -719
oc -720
od -721
og -722
oq -723
ow -724
pe -725
pi -726
pl -727
pu -728
rd -729
rg -730
ri -731
rm -732
rn -733
ro -734
rq -735
rr -736
rs -737
rt -738
ru -739
-740
sc -741
sd -742
se -743
sf -744
so -745
sp -746
st -747
su -748
-749
tm -750
-751
-752
ua -753
uc -754
ul -755
un -756
up -757
ur -758
ut -759
uv -760
-761
-762
ve -763
vi -764
vo -765
xt -766
ye -767
yu -768
za -769
zc -770
ét -771
ía -772
íb -773
ña -774
óm -775
óv -776
ús -777
▁E -778
▁G -779
▁H -780
▁O -781
▁b -782
▁i -783
▁o -784
▁q -785
▁t -786
201 -787
ACK -788
Adi -789
Can -790
Cuá -791
DDU -792
Fue -793
Fui -794
How -795
Jen -796
Jis -797
Lis -798
PIN -799
Pin -800
Pue -801
Ros -802
San -803
Tor -804
Ven -805
aci -806
ain -807
alt -808
anc -809
ard -810
arq -811
art -812
asi -813
ast -814
ban -815
but -816
cab -817
cal -818
cci -819
cia -820
cid -821
ció -822
con -823
cor -824
cos -825
ctr -826
dar -827
del -828
dem -829
deo -830
dis -831
dió -832
ean -833
efi -834
ena -835
enc -836
end -837
ene -838
eng -839
eni -840
enn -841
eno -842
ent -843
esa -844
esc -845
esd -846
est -847
eza -848
ezc -849
for -850
fue -851
fui -852
gen -853
gua -854
gun -855
has -856
hes -857
his -858
hos -859
ias -860
ica -861
ici -862
ies -863
ifi -864
igi -865
ign -866
ina -867
inc -868
inf -869
inm -870
ion -871
ise -872
iso -873
ite -874
jor -875
lac -876
lad -877
lam -878
lar -879
las -880
lec -881
len -882
les -883
lla -884
lob -885
log -886
lue -887
mer -888
mpa -889
nas -890
nci -891
nde -892
nes -893
nom -894
nte -895
ode -896
odu -897
ola -898
olo -899
omb -900
ome -901
omo -902
one -903
oni -904
ono -905
ont -906
onv -907
orc -908
osa -909
ost -910
pac -911
pal -912
pas -913
pañ -914
pin -915
pon -916
ran -917
rar -918
ras -919
rea -920
red -921
reg -922
ren -923
reí -924
reó -925
rin -926
rol -927
rom -928
ron -929
rop -930
ros -931
-932
e -933
o -934
a -935
n -936
s -937
r -938
i -939
t -940
u -941
c -942
d -943
l -944
p -945
m -946
. -947
g -948
y -949
f -950
b -951
P -952
v -953
K -954
S -955
ó -956
B -957
T -958
h -959
? -960
L -961
M -962
¿ -963
C -964
D -965
q -966
A -967
j -968
é -969
ñ -970
- -971
I -972
N -973
Q -974
U -975
í -976
F -977
H -978
á -979
G -980
J -981
Y -982
k -983
x -984
z -985
ú -986
0 -987
1 -988
2 -989
6 -990
E -991
O -992
R -993
V -994
w -995