teszenofficial commited on
Commit
18cf520
·
verified ·
1 Parent(s): af31e91

Delete mtp_tokenizer.vocab

Browse files
Files changed (1) hide show
  1. mtp_tokenizer.vocab +0 -1000
mtp_tokenizer.vocab DELETED
@@ -1,1000 +0,0 @@
1
- <pad> 0
2
- <unk> 0
3
- <s> 0
4
- </s> 0
5
- es -0
6
- en -1
7
- de -2
8
- on -3
9
- ▁p -4
10
- os -5
11
- ▁c -6
12
- ar -7
13
- te -8
14
- as -9
15
- an -10
16
- ▁es -11
17
- ci -12
18
- in -13
19
- ▁de -14
20
- er -15
21
- ▁u -16
22
- or -17
23
- ▁y -18
24
- ▁con -19
25
- al -20
26
- ▁m -21
27
- la -22
28
- ti -23
29
- ue -24
30
- ▁S -25
31
- ▁g -26
32
- ▁s -27
33
- ▁un -28
34
- do -29
35
- re -30
36
- tr -31
37
- ▁B -32
38
- ▁en -33
39
- ta -34
40
- to -35
41
- ▁M -36
42
- ▁¿ -37
43
- ca -38
44
- om -39
45
- op -40
46
- ui -41
47
- ▁f -42
48
- ▁l -43
49
- der -44
50
- orm -45
51
- ▁pr -46
52
- is -47
53
- lo -48
54
- ▁a -49
55
- ▁d -50
56
- ▁gr -51
57
- ▁in -52
58
- ▁te -53
59
- fi -54
60
- gu -55
61
- ig -56
62
- pa -57
63
- po -58
64
- ra -59
65
- si -60
66
- ño -61
67
- ▁P -62
68
- ▁n -63
69
- ado -64
70
- ant -65
71
- enci -66
72
- form -67
73
- AC -68
74
- DU -69
75
- IN -70
76
- KP -71
77
- ón -72
78
- ▁L -73
79
- ▁T -74
80
- ▁e -75
81
- ▁h -76
82
- ▁r -77
83
- INK -78
84
- LAC -79
85
- ara -80
86
- ino -81
87
- mos -82
88
- que -83
89
- rav -84
90
- upo -85
91
- ▁ar -86
92
- ▁mu -87
93
- ales -88
94
- ente -89
95
- fici -90
96
- ▁son -91
97
- KPINK -92
98
- antos -93
99
- ravos -94
100
- ▁BLAC -95
101
- ▁inte -96
102
- ▁para -97
103
- ▁grupo -98
104
- ▁Bravos -99
105
- ▁Santos -100
106
- ▁BLACKPINK -101
107
- TP -102
108
- aj -103
109
- bl -104
110
- bu -105
111
- ch -106
112
- di -107
113
- ec -108
114
- go -109
115
- mo -110
116
- oy -111
117
- rb -112
118
- tu -113
119
- ▁D -114
120
- ▁F -115
121
- ▁K -116
122
- ▁v -117
123
- aje -118
124
- ano -119
125
- ans -120
126
- bre -121
127
- des -122
128
- ero -123
129
- ers -124
130
- esp -125
131
- lat -126
132
- lig -127
133
- ñol -128
134
- ▁Mi -129
135
- ▁mo -130
136
- ▁su -131
137
- engu -132
138
- sica -133
139
- tren -134
140
- vers -135
141
- ▁MTP -136
142
- ▁com -137
143
- ▁del -138
144
- ▁des -139
145
- ▁lat -140
146
- ▁pop -141
147
- ▁urb -142
148
- encia -143
149
- espon -144
150
- pañol -145
151
- ▁arti -146
152
- ficial -147
153
- former -148
154
- versar -149
155
- ▁lengu -150
156
- trenado -151
157
- ▁latino -152
158
- ▁respon -153
159
- ligencia -154
160
- ▁español -155
161
- ansformer -156
162
- ▁lenguaje -157
163
- ▁conversar -158
164
- ▁entrenado -159
165
- ▁responder -160
166
- ▁artificial -161
167
- ▁inteligencia -162
168
- Ho -163
169
- Qu -164
170
- ez -165
171
- il -166
172
- im -167
173
- it -168
174
- ni -169
175
- nt -170
176
- qu -171
177
- ud -172
178
- us -173
179
- én -174
180
- ós -175
181
- ▁A -176
182
- ▁J -177
183
- ▁Y -178
184
- ▁j -179
185
- Qui -180
186
- Qué -181
187
- abl -182
188
- cer -183
189
- cto -184
190
- dos -185
191
- mas -186
192
- men -187
193
- oci -188
194
- pop -189
195
- sic -190
196
- tar -191
197
- ven -192
198
- xto -193
199
- yud -194
200
- ómo -195
201
- ▁Ho -196
202
- ▁Me -197
203
- ▁Th -198
204
- ▁bu -199
205
- ▁el -200
206
- ▁im -201
207
- ▁mú -202
208
- ▁po -203
209
- ▁tr -204
210
- arte -205
211
- asta -206
212
- ción -207
213
- delo -208
214
- diós -209
215
- enas -210
216
- ener -211
217
- eque -212
218
- esta -213
219
- gunt -214
220
- ones -215
221
- onto -216
222
- tigo -217
223
- tilo -218
224
- uedo -219
225
- ▁DDU -220
226
- ▁Fui -221
227
- ▁Soy -222
228
- ▁cre -223
229
- ▁est -224
230
- ▁lla -225
231
- ▁nom -226
232
- ▁pla -227
233
- ▁pre -228
234
- ▁que -229
235
- Quién -230
236
- pacto -231
237
- ▁ayud -232
238
- ▁cero -233
239
- ▁como -234
240
- ▁gran -235
241
- enerar -236
242
- equeño -237
243
- guntas -238
244
- ▁Adiós -239
245
- ▁Puedo -240
246
- ▁desde -241
247
- ▁hasta -242
248
- ▁music -243
249
- ▁poder -244
250
- ▁texto -245
251
- ▁buenas -246
252
- ▁estilo -247
253
- ▁modelo -248
254
- ▁música -249
255
- ▁nombre -250
256
- ▁pronto -251
257
- ▁urbano -252
258
- ▁contigo -253
259
- ▁generar -254
260
- ▁impacto -255
261
- ▁ayudarte -256
262
- ▁preguntas -257
263
- ▁transformer -258
264
- 01 -259
265
- Cu -260
266
- En -261
267
- GP -262
268
- On -263
269
- ap -264
270
- at -265
271
- bá -266
272
- cn -267
273
- da -268
274
- du -269
275
- ej -270
276
- eñ -271
277
- gr -272
278
- gí -273
279
- ic -274
280
- ik -275
281
- ol -276
282
- oo -277
283
- ou -278
284
- ov -279
285
- pr -280
286
- rc -281
287
- sa -282
288
- yT -283
289
- ál -284
290
- ás -285
291
- ▁2 -286
292
- ▁C -287
293
- ▁R -288
294
- ▁V -289
295
- 016 -290
296
- GPT -291
297
- One -292
298
- alm -293
299
- are -294
300
- arr -295
301
- atr -296
302
- atu -297
303
- bal -298
304
- bez -299
305
- bin -300
306
- ble -301
307
- cip -302
308
- cla -303
309
- cno -304
310
- cre -305
311
- ctu -306
312
- dor -307
313
- duc -308
314
- ebu -309
315
- ect -310
316
- erg -311
317
- ete -312
318
- etr -313
319
- gía -314
320
- ide -315
321
- ien -316
322
- ike -317
323
- ill -318
324
- ink -319
325
- isa -320
326
- ist -321
327
- isu -322
328
- lti -323
329
- mor -324
330
- nie -325
331
- nos -326
332
- och -327
333
- opu -328
334
- ore -329
335
- oso -330
336
- osé -331
337
- ove -332
338
- qui -333
339
- ral -334
340
- res -335
341
- rta -336
342
- udi -337
343
- uen -338
344
- éti -339
345
- ías -340
346
- ▁En -341
347
- ▁La -342
348
- ▁Su -343
349
- ▁Sí -344
350
- ▁Tr -345
351
- ▁YG -346
352
- ▁al -347
353
- ▁as -348
354
- ▁at -349
355
- ▁bá -350
356
- ▁em -351
357
- ▁fa -352
358
- ▁fe -353
359
- ▁fi -354
360
- ▁ha -355
361
- ▁ju -356
362
- ▁jó -357
363
- ▁op -358
364
- ▁re -359
365
- ▁so -360
366
- ▁ti -361
367
- ▁to -362
368
- ▁tu -363
369
- ▁ve -364
370
- Cuál -365
371
- Cómo -366
372
- Habl -367
373
- anci -368
374
- anos -369
375
- apas -370
376
- beza -371
377
- bina -372
378
- chos -373
379
- creí -374
380
- cómo -375
381
- ecto -376
382
- ectr -377
383
- ejor -378
384
- enom -379
385
- fica -380
386
- icos -381
387
- idos -382
388
- igit -383
389
- igni -384
390
- inas -385
391
- iseñ -386
392
- isoo -387
393
- lado -388
394
- ment -389
395
- oduc -390
396
- orch -391
397
- orma -392
398
- orme -393
399
- pren -394
400
- ques -395
401
- trar -396
402
- uego -397
403
- uida -398
404
- usta -399
405
- ▁Fue -400
406
- ▁GPT -401
407
- ▁How -402
408
- ▁Jen -403
409
- ▁One -404
410
- ▁PyT -405
411
- ▁Squ -406
412
- ▁Sus -407
413
- ▁You -408
414
- ▁fue -409
415
- ▁fui -410
416
- ▁glo -411
417
- ▁mez -412
418
- ▁nos -413
419
- ▁por -414
420
- ▁pue -415
421
- ▁rit -416
422
- ▁tar -417
423
- ▁una -418
424
- ▁usa -419
425
- ablar -420
426
- ación -421
427
- antes -422
428
- arrol -423
429
- cnolo -424
430
- ctura -425
431
- ectan -426
432
- etras -427
433
- ideos -428
434
- ienen -429
435
- incip -430
436
- mosas -431
437
- oches -432
438
- ocido -433
439
- omete -434
440
- quite -435
441
- rcore -436
442
- resca -437
443
- rtain -438
444
- taron -439
445
- uenos -440
446
- venes -441
447
- venil -442
448
- ética -443
449
- ▁2016 -444
450
- ▁Debu -445
451
- ▁Ente -446
452
- ▁Hola -447
453
- ▁Kill -448
454
- ▁Like -449
455
- ▁Lisa -450
456
- ▁Love -451
457
- ▁Pink -452
458
- ▁Rosé -453
459
- ▁That -454
460
- ▁This -455
461
- ▁alta -456
462
- ▁amor -457
463
- ▁audi -458
464
- ▁creó -459
465
- ▁días -460
466
- ▁natu -461
467
- ▁patr -462
468
- ▁pero -463
469
- ▁proy -464
470
- ▁soci -465
471
- ▁tipo -466
472
- ▁visu -467
473
- Hablas -468
474
- cabeza -469
475
- dernos -470
476
- ectrón -471
477
- encias -472
478
- ención -473
479
- formas -474
480
- menino -475
481
- ▁Canci -476
482
- ▁Jisoo -477
483
- ▁Venom -478
484
- ▁apren -479
485
- ▁asist -480
486
- ▁capas -481
487
- ▁cuida -482
488
- ▁demos -483
489
- ▁digit -484
490
- ▁diseñ -485
491
- ▁efici -486
492
- ▁emerg -487
493
- ▁estás -488
494
- ▁forma -489
495
- ▁gusta -490
496
- ▁hacer -491
497
- ▁llamo -492
498
- ▁luego -493
499
- ▁mejor -494
500
- ▁multi -495
501
- ▁plata -496
502
- ▁propu -497
503
- ▁redes -498
504
- ▁signi -499
505
- ▁sobre -500
506
- ▁temas -501
507
- ▁vemos -502
508
- Quiénes -503
509
- almente -504
510
- creíble -505
511
- grantes -506
512
- ▁Buenos -507
513
- ▁Jennie -508
514
- ▁Square -509
515
- ▁Tienen -510
516
- ▁básica -511
517
- ▁creado -512
518
- ▁enorme -513
519
- ▁fiesta -514
520
- ▁fresca -515
521
- ▁global -516
522
- ▁hablar -517
523
- ▁inform -518
524
- ▁letras -519
525
- ▁llamas -520
526
- ▁mezcla -521
527
- ▁muchos -522
528
- ▁noches -523
529
- ▁opinas -524
530
- ▁placer -525
531
- ▁produc -526
532
- ▁puedes -527
533
- ▁ritmos -528
534
- ▁tardes -529
535
- ▁toques -530
536
- ▁videos -531
537
- cnología -532
538
- ometedor -533
539
- rcoreano -534
540
- ▁Pequeño -535
541
- ▁PyTorch -536
542
- ▁arquite -537
543
- ▁combina -538
544
- ▁famosas -539
545
- ▁juvenil -540
546
- ▁jóvenes -541
547
- ▁musical -542
548
- ▁natural -543
549
- ▁pequeño -544
550
- ▁princip -545
551
- ▁sonidos -546
552
- ▁urbanos -547
553
- arrollado -548
554
- rtainment -549
555
- ▁aprender -550
556
- ▁atención -551
557
- ▁conectan -552
558
- ▁conocido -553
559
- ▁cuidados -554
560
- ▁diseñado -555
561
- ▁electrón -556
562
- ▁estética -557
563
- ▁femenino -558
564
- ▁modernos -559
565
- ▁patrones -560
566
- ▁poderoso -561
567
- ▁proyecto -562
568
- ▁sociales -563
569
- ▁visuales -564
570
- ▁Canciones -565
571
- ▁Debutaron -566
572
- ▁asistente -567
573
- ▁demostrar -568
574
- ▁digitales -569
575
- ▁eficiente -570
576
- ▁emergente -571
577
- ▁increíble -572
578
- ▁musicales -573
579
- ▁propuesta -574
580
- ▁significa -575
581
- ▁audiencias -576
582
- ▁producción -577
583
- ▁prometedor -578
584
- ▁surcoreano -579
585
- ▁tecnología -580
586
- ▁Transformer -581
587
- ▁información -582
588
- ▁integrantes -583
589
- ▁plataformas -584
590
- ▁arquitectura -585
591
- ▁desarrollado -586
592
- ▁electrónicos -587
593
- ▁Entertainment -588
594
- ▁principalmente -589
595
- 16 -590
596
- 20 -591
597
- Ad -592
598
- BL -593
599
- Br -594
600
- Bu -595
601
- CK -596
602
- Ca -597
603
- Có -598
604
- DD -599
605
- De -600
606
- Fu -601
607
- Ha -602
608
- Je -603
609
- Ji -604
610
- Ki -605
611
- LA -606
612
- La -607
613
- Li -608
614
- Lo -609
615
- MT -610
616
- Me -611
617
- Mi -612
618
- NK -613
619
- PI -614
620
- PT -615
621
- Pe -616
622
- Pi -617
623
- Pu -618
624
- Py -619
625
- Ro -620
626
- Sa -621
627
- So -622
628
- Sq -623
629
- Su -624
630
- Sí -625
631
- Th -626
632
- Ti -627
633
- To -628
634
- Tr -629
635
- Ve -630
636
- YG -631
637
- Yo -632
638
- ab -633
639
- ac -634
640
- ad -635
641
- af -636
642
- ai -637
643
- am -638
644
- au -639
645
- av -640
646
- ay -641
647
- añ -642
648
- ba -643
649
- be -644
650
- bi -645
651
- br -646
652
- cc -647
653
- ce -648
654
- cl -649
655
- co -650
656
- cr -651
657
- ct -652
658
- cu -653
659
- có -654
660
- dí -655
661
- ea -656
662
- eb -657
663
- ed -658
664
- ef -659
665
- eg -660
666
- el -661
667
- em -662
668
- eo -663
669
- eq -664
670
- et -665
671
- ex -666
672
- eí -667
673
- eó -668
674
- fa -669
675
- fe -670
676
- fo -671
677
- fr -672
678
- fu -673
679
- ge -674
680
- gi -675
681
- gl -676
682
- gn -677
683
- ha -678
684
- he -679
685
- hi -680
686
- ho -681
687
- ia -682
688
- id -683
689
- ie -684
690
- if -685
691
- io -686
692
- ip -687
693
- ié -688
694
- ió -689
695
- je -690
696
- jo -691
697
- ju -692
698
- jó -693
699
- ke -694
700
- le -695
701
- li -696
702
- ll -697
703
- lm -698
704
- lt -699
705
- lu -700
706
- ma -701
707
- mb -702
708
- me -703
709
- mp -704
710
- mu -705
711
- mú -706
712
- na -707
713
- nc -708
714
- nd -709
715
- ne -710
716
- nf -711
717
- ng -712
718
- nk -713
719
- nm -714
720
- nn -715
721
- no -716
722
- ns -717
723
- nv -718
724
- ob -719
725
- oc -720
726
- od -721
727
- og -722
728
- oq -723
729
- ow -724
730
- pe -725
731
- pi -726
732
- pl -727
733
- pu -728
734
- rd -729
735
- rg -730
736
- ri -731
737
- rm -732
738
- rn -733
739
- ro -734
740
- rq -735
741
- rr -736
742
- rs -737
743
- rt -738
744
- ru -739
745
- ró -740
746
- sc -741
747
- sd -742
748
- se -743
749
- sf -744
750
- so -745
751
- sp -746
752
- st -747
753
- su -748
754
- sé -749
755
- tm -750
756
- tá -751
757
- té -752
758
- ua -753
759
- uc -754
760
- ul -755
761
- un -756
762
- up -757
763
- ur -758
764
- ut -759
765
- uv -760
766
- uá -761
767
- ué -762
768
- ve -763
769
- vi -764
770
- vo -765
771
- xt -766
772
- ye -767
773
- yu -768
774
- za -769
775
- zc -770
776
- ét -771
777
- ía -772
778
- íb -773
779
- ña -774
780
- óm -775
781
- óv -776
782
- ús -777
783
- ▁E -778
784
- ▁G -779
785
- ▁H -780
786
- ▁O -781
787
- ▁b -782
788
- ▁i -783
789
- ▁o -784
790
- ▁q -785
791
- ▁t -786
792
- 201 -787
793
- ACK -788
794
- Adi -789
795
- Can -790
796
- Cuá -791
797
- DDU -792
798
- Fue -793
799
- Fui -794
800
- How -795
801
- Jen -796
802
- Jis -797
803
- Lis -798
804
- PIN -799
805
- Pin -800
806
- Pue -801
807
- Ros -802
808
- San -803
809
- Tor -804
810
- Ven -805
811
- aci -806
812
- ain -807
813
- alt -808
814
- anc -809
815
- ard -810
816
- arq -811
817
- art -812
818
- asi -813
819
- ast -814
820
- ban -815
821
- but -816
822
- cab -817
823
- cal -818
824
- cci -819
825
- cia -820
826
- cid -821
827
- ció -822
828
- con -823
829
- cor -824
830
- cos -825
831
- ctr -826
832
- dar -827
833
- del -828
834
- dem -829
835
- deo -830
836
- dis -831
837
- dió -832
838
- ean -833
839
- efi -834
840
- ena -835
841
- enc -836
842
- end -837
843
- ene -838
844
- eng -839
845
- eni -840
846
- enn -841
847
- eno -842
848
- ent -843
849
- esa -844
850
- esc -845
851
- esd -846
852
- est -847
853
- eza -848
854
- ezc -849
855
- for -850
856
- fue -851
857
- fui -852
858
- gen -853
859
- gua -854
860
- gun -855
861
- has -856
862
- hes -857
863
- his -858
864
- hos -859
865
- ias -860
866
- ica -861
867
- ici -862
868
- ies -863
869
- ifi -864
870
- igi -865
871
- ign -866
872
- ina -867
873
- inc -868
874
- inf -869
875
- inm -870
876
- ion -871
877
- ise -872
878
- iso -873
879
- ite -874
880
- jor -875
881
- lac -876
882
- lad -877
883
- lam -878
884
- lar -879
885
- las -880
886
- lec -881
887
- len -882
888
- les -883
889
- lla -884
890
- lob -885
891
- log -886
892
- lue -887
893
- mer -888
894
- mpa -889
895
- nas -890
896
- nci -891
897
- nde -892
898
- nes -893
899
- nom -894
900
- nte -895
901
- ode -896
902
- odu -897
903
- ola -898
904
- olo -899
905
- omb -900
906
- ome -901
907
- omo -902
908
- one -903
909
- oni -904
910
- ono -905
911
- ont -906
912
- onv -907
913
- orc -908
914
- osa -909
915
- ost -910
916
- pac -911
917
- pal -912
918
- pas -913
919
- pañ -914
920
- pin -915
921
- pon -916
922
- ran -917
923
- rar -918
924
- ras -919
925
- rea -920
926
- red -921
927
- reg -922
928
- ren -923
929
- reí -924
930
- reó -925
931
- rin -926
932
- rol -927
933
- rom -928
934
- ron -929
935
- rop -930
936
- ros -931
937
- ▁ -932
938
- e -933
939
- o -934
940
- a -935
941
- n -936
942
- s -937
943
- r -938
944
- i -939
945
- t -940
946
- u -941
947
- c -942
948
- d -943
949
- l -944
950
- p -945
951
- m -946
952
- . -947
953
- g -948
954
- y -949
955
- f -950
956
- b -951
957
- P -952
958
- v -953
959
- K -954
960
- S -955
961
- ó -956
962
- B -957
963
- T -958
964
- h -959
965
- ? -960
966
- L -961
967
- M -962
968
- ¿ -963
969
- C -964
970
- D -965
971
- q -966
972
- A -967
973
- j -968
974
- é -969
975
- ñ -970
976
- - -971
977
- I -972
978
- N -973
979
- Q -974
980
- U -975
981
- í -976
982
- F -977
983
- H -978
984
- á -979
985
- G -980
986
- J -981
987
- Y -982
988
- k -983
989
- x -984
990
- z -985
991
- ú -986
992
- 0 -987
993
- 1 -988
994
- 2 -989
995
- 6 -990
996
- E -991
997
- O -992
998
- R -993
999
- V -994
1000
- w -995