bert-large-cased / vocab.txt
system
Update vocab.txt 1da98eb
1 [PAD]
2 [unused1]
3 [unused2]
4 [unused3]
5 [unused4]
6 [unused5]
7 [unused6]
8 [unused7]
9 [unused8]
10 [unused9]
11 [unused10]
12 [unused11]
13 [unused12]
14 [unused13]
15 [unused14]
16 [unused15]
17 [unused16]
18 [unused17]
19 [unused18]
20 [unused19]
21 [unused20]
22 [unused21]
23 [unused22]
24 [unused23]
25 [unused24]
26 [unused25]
27 [unused26]
28 [unused27]
29 [unused28]
30 [unused29]
31 [unused30]
32 [unused31]
33 [unused32]
34 [unused33]
35 [unused34]
36 [unused35]
37 [unused36]
38 [unused37]
39 [unused38]
40 [unused39]
41 [unused40]
42 [unused41]
43 [unused42]
44 [unused43]
45 [unused44]
46 [unused45]
47 [unused46]
48 [unused47]
49 [unused48]
50 [unused49]
51 [unused50]
52 [unused51]
53 [unused52]
54 [unused53]
55 [unused54]
56 [unused55]
57 [unused56]
58 [unused57]
59 [unused58]
60 [unused59]
61 [unused60]
62 [unused61]
63 [unused62]
64 [unused63]
65 [unused64]
66 [unused65]
67 [unused66]
68 [unused67]
69 [unused68]
70 [unused69]
71 [unused70]
72 [unused71]
73 [unused72]
74 [unused73]
75 [unused74]
76 [unused75]
77 [unused76]
78 [unused77]
79 [unused78]
80 [unused79]
81 [unused80]
82 [unused81]
83 [unused82]
84 [unused83]
85 [unused84]
86 [unused85]
87 [unused86]
88 [unused87]
89 [unused88]
90 [unused89]
91 [unused90]
92 [unused91]
93 [unused92]
94 [unused93]
95 [unused94]
96 [unused95]
97 [unused96]
98 [unused97]
99 [unused98]
100 [unused99]
101 [UNK]
102 [CLS]
103 [SEP]
104 [MASK]
105 [unused100]
106 [unused101]
107 !
108 "
109 #
110 $
111 %
112 &
113 '
114 (
115 )
116 *
117 +
118 ,
119 -
120 .
121 /
122 0
123 1
124 2
125 3
126 4
127 5
128 6
129 7
130 8
131 9
132 :
133 ;
134 <
135 =
136 >
137 ?
138 @
139 A
140 B
141 C
142 D
143 E
144 F
145 G
146 H
147 I
148 J
149 K
150 L
151 M
152 N
153 O
154 P
155 Q
156 R
157 S
158 T
159 U
160 V
161 W
162 X
163 Y
164 Z
165 [
166 \
167 ]
168 ^
169 _
170 `
171 a
172 b
173 c
174 d
175 e
176 f
177 g
178 h
179 i
180 j
181 k
182 l
183 m
184 n
185 o
186 p
187 q
188 r
189 s
190 t
191 u
192 v
193 w
194 x
195 y
196 z
197 {
198 |
199 }
200 ~
201 ¡
202 ¢
203 £
204 ¥
205 §
206 ¨
207 ©
208 ª
209 «
210 ¬
211 ®
212 °
213 ±
214 ²
215 ³
216 ´
217 µ
218
219 ·
220 ¹
221 º
222 »
223 ¼
224 ½
225 ¾
226 ¿
227 À
228 Á
229 Â
230 Ä
231 Å
232 Æ
233 Ç
234 È
235 É
236 Í
237 Î
238 Ñ
239 Ó
240 Ö
241 ×
242 Ø
243 Ú
244 Ü
245 Þ
246 ß
247 à
248 á
249 â
250 ã
251 ä
252 å
253 æ
254 ç
255 è
256 é
257 ê
258 ë
259 ì
260 í
261 î
262 ï
263 ð
264 ñ
265 ò
266 ó
267 ô
268 õ
269 ö
270 ÷
271 ø
272 ù
273 ú
274 û
275 ü
276 ý
277 þ
278 ÿ
279 Ā
280 ā
281 ă
282 ą
283 Ć
284 ć
285 Č
286 č
287 ď
288 Đ
289 đ
290 ē
291 ė
292 ę
293 ě
294 ğ
295 ġ
296 Ħ
297 ħ
298 ĩ
299 Ī
300 ī
301 İ
302 ı
303 ļ
304 Ľ
305 ľ
306 Ł
307 ł
308 ń
309 ņ
310 ň
311 ŋ
312 Ō
313 ō
314 ŏ
315 ő
316 Œ
317 œ
318 ř
319 Ś
320 ś
321 Ş
322 ş
323 Š
324 š
325 Ţ
326 ţ
327 ť
328 ũ
329 ū
330 ŭ
331 ů
332 ű
333 ų
334 ŵ
335 ŷ
336 ź
337 Ż
338 ż
339 Ž
340 ž
341 Ə
342 ƒ
343 ơ
344 ư
345 ǎ
346 ǐ
347 ǒ
348 ǔ
349 ǫ
350 Ș
351 ș
352 Ț
353 ț
354 ɐ
355 ɑ
356 ɔ
357 ɕ
358 ə
359 ɛ
360 ɡ
361 ɣ
362 ɨ
363 ɪ
364 ɲ
365 ɾ
366 ʀ
367 ʁ
368 ʂ
369 ʃ
370 ʊ
371 ʋ
372 ʌ
373 ʐ
374 ʑ
375 ʒ
376 ʔ
377 ʰ
378 ʲ
379 ʳ
380 ʷ
381 ʻ
382 ʼ
383 ʾ
384 ʿ
385 ˈ
386 ː
387 ˡ
388 ˢ
389 ˣ
390 ́
391 ̃
392 ̍
393 ̯
394 ͡
395 Α
396 Β
397 Γ
398 Δ
399 Ε
400 Η
401 Θ
402 Ι
403 Κ
404 Λ
405 Μ
406 Ν
407 Ο
408 Π
409 Σ
410 Τ
411 Φ
412 Χ
413 Ψ
414 Ω
415 ά
416 έ
417 ή
418 ί
419 α
420 β
421 γ
422 δ
423 ε
424 ζ
425 η
426 θ
427 ι
428 κ
429 λ
430 μ
431 ν
432 ξ
433 ο
434 π
435 ρ
436 ς
437 σ
438 τ
439 υ
440 φ
441 χ
442 ψ
443 ω
444 ό
445 ύ
446 ώ
447 І
448 Ј
449 А
450 Б
451 В
452 Г
453 Д
454 Е
455 Ж
456 З
457 И
458 К
459 Л
460 М
461 Н
462 О
463 П
464 Р
465 С
466 Т
467 У
468 Ф
469 Х
470 Ц
471 Ч
472 Ш
473 Э
474 Ю
475 Я
476 а
477 б
478 в
479 г
480 д
481 е
482 ж
483 з
484 и
485 й
486 к
487 л
488 м
489 н
490 о
491 п
492 р
493 с
494 т
495 у
496 ф
497 х
498 ц
499 ч
500 ш
501 щ
502 ъ
503 ы
504 ь
505 э
506 ю
507 я
508 ё
509 і
510 ї
511 ј
512 њ
513 ћ
514 Ա
515 Հ
516 ա
517 ե
518 ի
519 կ
520 մ
521 յ
522 ն
523 ո
524 ս
525 տ
526 ր
527 ւ
528 ְ
529 ִ
530 ֵ
531 ֶ
532 ַ
533 ָ
534 ֹ
535 ּ
536 א
537 ב
538 ג
539 ד
540 ה
541 ו
542 ז
543 ח
544 ט
545 י
546 כ
547 ל
548 ם
549 מ
550 ן
551 נ
552 ס
553 ע
554 פ
555 צ
556 ק
557 ר
558 ש
559 ת
560 ،
561 ء
562 آ
563 أ
564 إ
565 ئ
566 ا
567 ب
568 ة
569 ت
570 ث
571 ج
572 ح
573 خ
574 د
575 ذ
576 ر
577 ز
578 س
579 ش
580 ص
581 ض
582 ط
583 ظ
584 ع
585 غ
586 ف
587 ق
588 ك
589 ل
590 م
591 ن
592 ه
593 و
594 ى
595 ي
596 َ
597 ِ
598 ٹ
599 پ
600 چ
601 ک
602 گ
603 ہ
604 ی
605 ے
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630 ि
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665 ি
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681 ி
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746 ế
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019 宿
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071 西
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104 the
1105 of
1106 and
1107 to
1108 in
1109 was
1110 The
1111 is
1112 for
1113 as
1114 on
1115 with
1116 that
1117 ##s
1118 his
1119 by
1120 he
1121 at
1122 from
1123 it
1124 her
1125 He
1126 had
1127 an
1128 were
1129 you
1130 be
1131 In
1132 she
1133 are
1134 but
1135 which
1136 It
1137 not
1138 or
1139 have
1140 my
1141 him
1142 one
1143 this
1144 me
1145 has
1146 also
1147 up
1148 their
1149 first
1150 out
1151 who
1152 been
1153 they
1154 She
1155 into
1156 all
1157 would
1158 its
1159 ##ing
1160 time
1161 two
1162 ##a
1163 ##e
1164 said
1165 about
1166 when
1167 over
1168 more
1169 other
1170 can
1171 after
1172 back
1173 them
1174 then
1175 ##ed
1176 there
1177 like
1178 so
1179 only
1180 ##n
1181 could
1182 ##d
1183 ##i
1184 ##y
1185 what
1186 no
1187 ##o
1188 where
1189 This
1190 made
1191 than
1192 if
1193 You
1194 ##ly
1195 through
1196 we
1197 before
1198 ##r
1199 just
1200 some
1201 ##er
1202 years
1203 do
1204 New
1205 ##t
1206 down
1207 between
1208 new
1209 now
1210 will
1211 three
1212 most
1213 On
1214 around
1215 year
1216 used
1217 such
1218 being
1219 well
1220 during
1221 They
1222 know
1223 against
1224 under
1225 later
1226 did
1227 part
1228 known
1229 off
1230 while
1231 His
1232 re
1233 ...
1234 ##l
1235 people
1236 until
1237 way
1238 American
1239 didn
1240 University
1241 your
1242 both
1243 many
1244 get
1245 United
1246 became
1247 head
1248 There
1249 second
1250 As
1251 work
1252 any
1253 But
1254 still
1255 again
1256 born
1257 even
1258 eyes
1259 After
1260 including
1261 de
1262 took
1263 And
1264 long
1265 team
1266 season
1267 family
1268 see
1269 right
1270 same
1271 called
1272 name
1273 because
1274 film
1275 don
1276 10
1277 found
1278 much
1279 school
1280 ##es
1281 going
1282 won
1283 place
1284 away
1285 We
1286 day
1287 left
1288 John
1289 000
1290 hand
1291 since
1292 World
1293 these
1294 how
1295 make
1296 number
1297 each
1298 life
1299 area
1300 man
1301 four
1302 go
1303 No
1304 here
1305 very
1306 National
1307 ##m
1308 played
1309 released
1310 never
1311 began
1312 States
1313 album
1314 home
1315 last
1316 too
1317 held
1318 several
1319 May
1320 own
1321 ##on
1322 take
1323 end
1324 School
1325 ##h
1326 ll
1327 series
1328 What
1329 want
1330 use
1331 another
1332 city
1333 When
1334 2010
1335 side
1336 At
1337 may
1338 That
1339 came
1340 face
1341 June
1342 think
1343 game
1344 those
1345 high
1346 March
1347 early
1348 September
1349 ##al
1350 2011
1351 looked
1352 July
1353 state
1354 small
1355 thought
1356 went
1357 January
1358 October
1359 ##u
1360 based
1361 August
1362 ##us
1363 world
1364 good
1365 April
1366 York
1367 us
1368 12
1369 2012
1370 2008
1371 For
1372 2009
1373 group
1374 along
1375 few
1376 South
1377 little
1378 ##k
1379 following
1380 November
1381 something
1382 2013
1383 December
1384 set
1385 2007
1386 old
1387 2006
1388 2014
1389 located
1390 ##an
1391 music
1392 County
1393 City
1394 former
1395 ##in
1396 room
1397 ve
1398 next
1399 All
1400 ##man
1401 got
1402 father
1403 house
1404 ##g
1405 body
1406 15
1407 20
1408 18
1409 started
1410 If
1411 2015
1412 town
1413 our
1414 line
1415 War
1416 large
1417 population
1418 named
1419 British
1420 company
1421 member
1422 five
1423 My
1424 single
1425 ##en
1426 age
1427 State
1428 moved
1429 February
1430 11
1431 Her
1432 should
1433 century
1434 government
1435 built
1436 come
1437 best
1438 show
1439 However
1440 within
1441 look
1442 men
1443 door
1444 without
1445 need
1446 wasn
1447 2016
1448 water
1449 One
1450 system
1451 knew
1452 every
1453 died
1454 League
1455 turned
1456 asked
1457 North
1458 St
1459 wanted
1460 building
1461 received
1462 song
1463 served
1464 though
1465 felt
1466 ##ia
1467 station
1468 band
1469 ##ers
1470 local
1471 public
1472 himself
1473 different
1474 death
1475 say
1476 ##1
1477 30
1478 ##2
1479 2005
1480 16
1481 night
1482 behind
1483 children
1484 English
1485 members
1486 near
1487 saw
1488 together
1489 son
1490 14
1491 voice
1492 village
1493 13
1494 hands
1495 help
1496 ##3
1497 due
1498 French
1499 London
1500 top
1501 told
1502 open
1503 published
1504 third
1505 2017
1506 play
1507 across
1508 During
1509 put
1510 final
1511 often
1512 include
1513 25
1514 ##le
1515 main
1516 having
1517 2004
1518 once
1519 ever
1520 let
1521 book
1522 led
1523 gave
1524 late
1525 front
1526 find
1527 club
1528 ##4
1529 German
1530 included
1531 species
1532 College
1533 form
1534 opened
1535 mother
1536 women
1537 enough
1538 West
1539 must
1540 2000
1541 power
1542 really
1543 17
1544 making
1545 half
1546 ##6
1547 order
1548 might
1549 ##is
1550 given
1551 million
1552 times
1553 days
1554 point
1555 full
1556 service
1557 With
1558 km
1559 major
1560 ##7
1561 original
1562 become
1563 seen
1564 II
1565 north
1566 six
1567 ##te
1568 love
1569 ##0
1570 national
1571 International
1572 ##5
1573 24
1574 So
1575 District
1576 lost
1577 run
1578 couldn
1579 career
1580 always
1581 ##9
1582 2003
1583 ##th
1584 country
1585 ##z
1586 House
1587 air
1588 tell
1589 south
1590 worked
1591 woman
1592 player
1593 ##A
1594 almost
1595 war
1596 River
1597 ##ic
1598 married
1599 continued
1600 Then
1601 James
1602 close
1603 black
1604 short
1605 ##8
1606 ##na
1607 using
1608 history
1609 returned
1610 light
1611 car
1612 ##ra
1613 sure
1614 William
1615 things
1616 General
1617 ##ry
1618 2002
1619 better
1620 support
1621 100
1622 among
1623 From
1624 feet
1625 King
1626 anything
1627 21
1628 19
1629 established
1630 district
1631 2001
1632 feel
1633 great
1634 ##ton
1635 level
1636 Cup
1637 These
1638 written
1639 games
1640 others
1641 already
1642 title
1643 story
1644 ##p
1645 law
1646 thing
1647 US
1648 record
1649 role
1650 however
1651 By
1652 students
1653 England
1654 white
1655 control
1656 least
1657 inside
1658 land
1659 ##C
1660 22
1661 give
1662 community
1663 hard
1664 ##ie
1665 non
1666 ##c
1667 produced
1668 George
1669 round
1670 period
1671 Park
1672 business
1673 various
1674 ##ne
1675 does
1676 present
1677 wife
1678 far
1679 taken
1680 per
1681 reached
1682 David
1683 able
1684 version
1685 working
1686 young
1687 live
1688 created
1689 joined
1690 East
1691 living
1692 appeared
1693 case
1694 High
1695 done
1696 23
1697 important
1698 President
1699 Award
1700 France
1701 position
1702 office
1703 looking
1704 total
1705 general
1706 class
1707 To
1708 production
1709 ##S
1710 football
1711 party
1712 brother
1713 keep
1714 mind
1715 free
1716 Street
1717 hair
1718 announced
1719 development
1720 either
1721 nothing
1722 moment
1723 Church
1724 followed
1725 wrote
1726 why
1727 India
1728 San
1729 election
1730 1999
1731 lead
1732 How
1733 ##ch
1734 ##rs
1735 words
1736 European
1737 course
1738 considered
1739 America
1740 arms
1741 Army
1742 political
1743 ##la
1744 28
1745 26
1746 west
1747 east
1748 ground
1749 further
1750 church
1751 less
1752 site
1753 First
1754 Not
1755 Australia
1756 toward
1757 California
1758 ##ness
1759 described
1760 works
1761 An
1762 Council
1763 heart
1764 past
1765 military
1766 27
1767 ##or
1768 heard
1769 field
1770 human
1771 soon
1772 founded
1773 1998
1774 playing
1775 trying
1776 ##x
1777 ##ist
1778 ##ta
1779 television
1780 mouth
1781 although
1782 taking
1783 win
1784 fire
1785 Division
1786 ##ity
1787 Party
1788 Royal
1789 program
1790 Some
1791 Don
1792 Association
1793 According
1794 tried
1795 TV
1796 Paul
1797 outside
1798 daughter
1799 Best
1800 While
1801 someone
1802 match
1803 recorded
1804 Canada
1805 closed
1806 region
1807 Air
1808 above
1809 months
1810 elected
1811 ##da
1812 ##ian
1813 road
1814 ##ar
1815 brought
1816 move
1817 1997
1818 leave
1819 ##um
1820 Thomas
1821 1996
1822 am
1823 low
1824 Robert
1825 formed
1826 person
1827 services
1828 points
1829 Mr
1830 miles
1831 ##b
1832 stop
1833 rest
1834 doing
1835 needed
1836 international
1837 release
1838 floor
1839 start
1840 sound
1841 call
1842 killed
1843 real
1844 dark
1845 research
1846 finished
1847 language
1848 Michael
1849 professional
1850 change
1851 sent
1852 50
1853 upon
1854 29
1855 track
1856 hit
1857 event
1858 2018
1859 term
1860 example
1861 Germany
1862 similar
1863 return
1864 ##ism
1865 fact
1866 pulled
1867 stood
1868 says
1869 ran
1870 information
1871 yet
1872 result
1873 developed
1874 girl
1875 ##re
1876 God
1877 1995
1878 areas
1879 signed
1880 decided
1881 ##ment
1882 Company
1883 seemed
1884 ##el
1885 co
1886 turn
1887 race
1888 common
1889 video
1890 Charles
1891 Indian
1892 ##ation
1893 blood
1894 art
1895 red
1896 ##able
1897 added
1898 rather
1899 1994
1900 met
1901 director
1902 addition
1903 design
1904 average
1905 minutes
1906 ##ies
1907 ##ted
1908 available
1909 bed
1910 coming
1911 friend
1912 idea
1913 kind
1914 Union
1915 Road
1916 remained
1917 ##ting
1918 everything
1919 ##ma
1920 running
1921 care
1922 finally
1923 Chinese
1924 appointed
1925 1992
1926 Australian
1927 ##ley
1928 popular
1929 mean
1930 teams
1931 probably
1932 ##land
1933 usually
1934 project
1935 social
1936 Championship
1937 possible
1938 word
1939 Russian
1940 instead
1941 mi
1942 herself
1943 ##T
1944 Peter
1945 Hall
1946 Center
1947 seat
1948 style
1949 money
1950 1993
1951 else
1952 Department
1953 table
1954 Music
1955 current
1956 31
1957 features
1958 special
1959 events
1960 character
1961 Two
1962 square
1963 sold
1964 debut
1965 ##v
1966 process
1967 Although
1968 Since
1969 ##ka
1970 40
1971 Central
1972 currently
1973 education
1974 placed
1975 lot
1976 China
1977 quickly
1978 forward
1979 seven
1980 ##ling
1981 Europe
1982 arm
1983 performed
1984 Japanese
1985 1991
1986 Henry
1987 Now
1988 Dr
1989 ##ion
1990 week
1991 Group
1992 myself
1993 big
1994 UK
1995 Washington
1996 ten
1997 deep
1998 1990
1999 Club
2000 Japan
2001 space
2002 La
2003 directed
2004 smile
2005 episode
2006 hours
2007 whole
2008 ##de
2009 ##less
2010 Why
2011 wouldn
2012 designed
2013 strong
2014 training
2015 changed
2016 Society
2017 stage
2018 involved
2019 hadn
2020 towards
2021 leading
2022 police
2023 eight
2024 kept
2025 Institute
2026 study
2027 largest
2028 child
2029 eventually
2030 private
2031 modern
2032 Court
2033 throughout
2034 getting
2035 originally
2036 attack
2037 ##E
2038 talk
2039 Great
2040 longer
2041 songs
2042 alone
2043 ##ine
2044 wide
2045 dead
2046 walked
2047 shot
2048 ##ri
2049 Oh
2050 force
2051 ##st
2052 Art
2053 today
2054 friends
2055 Island
2056 Richard
2057 1989
2058 center
2059 construction
2060 believe
2061 size
2062 White