ydshieh HF staff commited on
Commit
89c90e7
1 Parent(s): 7154c92

Upload tiny models for DebertaForSequenceClassification

Browse files
Files changed (8) hide show
  1. config.json +31 -0
  2. merges.txt +764 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +51 -0
  5. tf_model.h5 +3 -0
  6. tokenizer.json +1939 -0
  7. tokenizer_config.json +67 -0
  8. vocab.json +1026 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "temp/dummy/deberta/DebertaForSequenceClassification",
3
+ "architectures": [
4
+ "DebertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 32,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 37,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta",
16
+ "num_attention_heads": 4,
17
+ "num_hidden_layers": 5,
18
+ "pad_token_id": 0,
19
+ "pooler_dropout": 0,
20
+ "pooler_hidden_act": "gelu",
21
+ "pooler_hidden_size": 32,
22
+ "pos_att_type": [
23
+ "none"
24
+ ],
25
+ "position_biased_input": true,
26
+ "relative_attention": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.24.0.dev0",
29
+ "type_vocab_size": 16,
30
+ "vocab_size": 1024
31
+ }
merges.txt ADDED
@@ -0,0 +1,764 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #version: 0.2
2
+ Ġ t
3
+ h e
4
+ Ġ a
5
+ i n
6
+ Ġt he
7
+ e r
8
+ o n
9
+ Ġ ,
10
+ r e
11
+ Ġ s
12
+ e d
13
+ Ġ o
14
+ Ġ w
15
+ n d
16
+ a t
17
+ Ġ .
18
+ o r
19
+ i t
20
+ Ġ c
21
+ e n
22
+ Ġ f
23
+ i s
24
+ e s
25
+ a r
26
+ Ġo f
27
+ Ġ b
28
+ a n
29
+ Ġ in
30
+ a l
31
+ in g
32
+ Ġ p
33
+ Ġa nd
34
+ a s
35
+ Ġt o
36
+ r o
37
+ i c
38
+ Ġ m
39
+ Ġ d
40
+ Ġ h
41
+ i on
42
+ l e
43
+ o u
44
+ Ġ T
45
+ Ġ re
46
+ Ġ =
47
+ Ġ "
48
+ Ġ A
49
+ Ġ S
50
+ en t
51
+ i l
52
+ Ġt h
53
+ Ġ 1
54
+ s t
55
+ Ġ C
56
+ e l
57
+ o m
58
+ Ġ l
59
+ a m
60
+ Ġ Ċ
61
+ Ġ e
62
+ Ġ n
63
+ Ġ @
64
+ a d
65
+ a c
66
+ Ġw as
67
+ Ġ M
68
+ u r
69
+ ĠT he
70
+ e c
71
+ Ġ on
72
+ l y
73
+ Ġ B
74
+ Ġ I
75
+ Ġ g
76
+ Ġ '
77
+ e t
78
+ o l
79
+ i d
80
+ i v
81
+ i m
82
+ Ġf or
83
+ i r
84
+ - @
85
+ Ġ@ -@
86
+ i g
87
+ o t
88
+ t er
89
+ Ġa s
90
+ Ġ H
91
+ u s
92
+ o w
93
+ Ġs t
94
+ u t
95
+ it h
96
+ a y
97
+ Ġ 2
98
+ Ġ P
99
+ at ion
100
+ v er
101
+ Ġb e
102
+ he r
103
+ Ġth at
104
+ Ġw ith
105
+ Ġ R
106
+ c e
107
+ t h
108
+ Ġ D
109
+ Ġ is
110
+ u n
111
+ e m
112
+ Ġ F
113
+ Ġw h
114
+ u l
115
+ Ġb y
116
+ Ġa l
117
+ c h
118
+ Ġ )
119
+ Ġ (
120
+ Ġ W
121
+ Ġc on
122
+ r a
123
+ Ġ G
124
+ o s
125
+ Ġ L
126
+ Ġ N
127
+ Ġa t
128
+ er s
129
+ c t
130
+ Ġ it
131
+ Ġ1 9
132
+ ro m
133
+ a nd
134
+ Ġa n
135
+ u m
136
+ es t
137
+ Ġ J
138
+ a g
139
+ Ġ he
140
+ 0 0
141
+ is t
142
+ a in
143
+ o d
144
+ a v
145
+ r i
146
+ Ġ E
147
+ Ġ O
148
+ Ġf rom
149
+ Ġc om
150
+ Ġh is
151
+ o p
152
+ Ġp ro
153
+ re s
154
+ i es
155
+ i f
156
+ Ġ v
157
+ or t
158
+ er e
159
+ il l
160
+ l d
161
+ Ġd e
162
+ p p
163
+ Ġs u
164
+ o re
165
+ ĠI n
166
+ Ġ r
167
+ Ġs e
168
+ Ġw ere
169
+ e w
170
+ on g
171
+ ig h
172
+ ar d
173
+ at e
174
+ al l
175
+ ar t
176
+ a k
177
+ ic h
178
+ Ġc h
179
+ Ġo r
180
+ a b
181
+ an t
182
+ u d
183
+ o c
184
+ b er
185
+ Ġe x
186
+ g h
187
+ it y
188
+ at ed
189
+ p t
190
+ es s
191
+ e ar
192
+ Ġ K
193
+ Ġp l
194
+ am e
195
+ q u
196
+ iv e
197
+ ro u
198
+ Ġa re
199
+ Ġ â
200
+ Ġs h
201
+ Ġ k
202
+ ac k
203
+ ec t
204
+ Ġâ Ģ
205
+ Ġ U
206
+ Ġh ad
207
+ s e
208
+ Ġwh ich
209
+ re d
210
+ o v
211
+ ĠS t
212
+ as t
213
+ Ġs p
214
+ i an
215
+ Ġ y
216
+ m ent
217
+ Ġ le
218
+ Ġn ot
219
+ g e
220
+ or d
221
+ r it
222
+ i p
223
+ in e
224
+ el l
225
+ al ly
226
+ ou r
227
+ o st
228
+ igh t
229
+ t her
230
+ a p
231
+ Ġ u
232
+ is h
233
+ ĠC h
234
+ ou n
235
+ i a
236
+ Ġ 3
237
+ av e
238
+ ar y
239
+ u st
240
+ o g
241
+ Ġ2 00
242
+ Ġ un
243
+ ou s
244
+ ir st
245
+ Ġ V
246
+ c c
247
+ Ġin c
248
+ Ġ ;
249
+ Ġcom p
250
+ r u
251
+ ion s
252
+ Ġthe ir
253
+ Ġb ut
254
+ id e
255
+ u re
256
+ s o
257
+ Ġcon t
258
+ Ġin t
259
+ f ter
260
+ ic al
261
+ i al
262
+ Ġa r
263
+ Ġf irst
264
+ ou ld
265
+ Ġit s
266
+ he d
267
+ ĠâĢ ĵ
268
+ Ġw he
269
+ w o
270
+ ou t
271
+ u b
272
+ Ġ2 0
273
+ f f
274
+ Ġ :
275
+ u e
276
+ Ġ her
277
+ ow n
278
+ o k
279
+ Ġal so
280
+ Ġc l
281
+ p er
282
+ ig n
283
+ at er
284
+ r an
285
+ or m
286
+ i e
287
+ om e
288
+ or k
289
+ as s
290
+ i re
291
+ e nd
292
+ Ġre s
293
+ Ġa b
294
+ Ġa d
295
+ Ġ us
296
+ r y
297
+ Ġre c
298
+ Ġh ave
299
+ ag e
300
+ ĠH e
301
+ Ġ 4
302
+ Ġ ro
303
+ m er
304
+ Ġon e
305
+ on d
306
+ l ow
307
+ Ġh as
308
+ ĠT h
309
+ d u
310
+ Ġ 5
311
+ Ġp er
312
+ Ġbe en
313
+ im e
314
+ Ġt wo
315
+ en ce
316
+ l and
317
+ Ġ1 8
318
+ . @
319
+ Ġ@ .@
320
+ ul t
321
+ re e
322
+ ou gh
323
+ i le
324
+ Ġwh o
325
+ ĠA l
326
+ Ġs c
327
+ ur ing
328
+ p l
329
+ or y
330
+ it ion
331
+ r ic
332
+ ation s
333
+ Ġd is
334
+ Ġth is
335
+ Ġb ec
336
+ Ġa pp
337
+ i z
338
+ ĠI t
339
+ a re
340
+ ac h
341
+ l ud
342
+ ad e
343
+ Ġpl ay
344
+ Ġ j
345
+ Ġm an
346
+ ac t
347
+ el y
348
+ Ġp art
349
+ Ġd es
350
+ Ġa g
351
+ Ġthe y
352
+ Ġy ear
353
+ oun t
354
+ Ġ20 1
355
+ Ġo ver
356
+ Ġo ther
357
+ ou nd
358
+ Ġa fter
359
+ i b
360
+ o ver
361
+ Ġs er
362
+ Ġ en
363
+ Ġof f
364
+ Ġ im
365
+ ct ion
366
+ Ġ Y
367
+ k e
368
+ it e
369
+ , @
370
+ Ġ@ ,@
371
+ t e
372
+ ur n
373
+ Ġinc lud
374
+ res s
375
+ an ce
376
+ an g
377
+ Ġat t
378
+ ic e
379
+ ac e
380
+ ar k
381
+ Ġo ut
382
+ w n
383
+ p h
384
+ em ber
385
+ Ġp re
386
+ Ġu p
387
+ en s
388
+ m an
389
+ Ġe v
390
+ Ġt ime
391
+ nd er
392
+ rou gh
393
+ c ed
394
+ Ġf in
395
+ Ġint o
396
+ on e
397
+ p ort
398
+ rou nd
399
+ w e
400
+ re n
401
+ l es
402
+ in t
403
+ ĠO n
404
+ v el
405
+ Ġcom m
406
+ Ġs he
407
+ as on
408
+ am p
409
+ Ġt e
410
+ Ġw ould
411
+ w ard
412
+ Ġm ore
413
+ Ġ 6
414
+ i ed
415
+ os e
416
+ ri b
417
+ ĠU n
418
+ Ġal l
419
+ ing s
420
+ ter n
421
+ c es
422
+ ab le
423
+ Ġw e
424
+ it ed
425
+ e ver
426
+ ent s
427
+ Ġh im
428
+ as ed
429
+ or s
430
+ o y
431
+ o od
432
+ Ġc ent
433
+ i x
434
+ as e
435
+ il d
436
+ ĠA n
437
+ Ġ 7
438
+ Ġw ork
439
+ at es
440
+ i ous
441
+ at h
442
+ Ġp o
443
+ ro p
444
+ ol d
445
+ al s
446
+ is s
447
+ e y
448
+ ic t
449
+ Ġf e
450
+ Ġthe m
451
+ g an
452
+ Ġs ec
453
+ Ġb et
454
+ Ġwhe n
455
+ Ġs ong
456
+ Ġre m
457
+ e p
458
+ f orm
459
+ a il
460
+ f er
461
+ Ġe ar
462
+ ub l
463
+ a w
464
+ Ġk n
465
+ ak e
466
+ a us
467
+ Ġm ost
468
+ Ġcon s
469
+ Ġd uring
470
+ ĠA s
471
+ or th
472
+ Ġn ew
473
+ er ed
474
+ il m
475
+ v ed
476
+ at t
477
+ Ġon ly
478
+ Ġ 9
479
+ Ġd ec
480
+ Ġ 8
481
+ ic k
482
+ Ġg ame
483
+ on s
484
+ u g
485
+ Ġt r
486
+ f t
487
+ ot h
488
+ o ok
489
+ ĠM ar
490
+ re at
491
+ w ay
492
+ Ġc an
493
+ ol low
494
+ ou th
495
+ we en
496
+ ĠE n
497
+ Ġ19 9
498
+ ter s
499
+ Ġre l
500
+ in d
501
+ Ġab out
502
+ Ġse ason
503
+ Ġag ain
504
+ r al
505
+ Ġth ree
506
+ ation al
507
+ Ġu nder
508
+ ul ar
509
+ Ġm e
510
+ Ġth an
511
+ ĠC om
512
+ ĠA r
513
+ h ip
514
+ o b
515
+ Ġn e
516
+ Ġbet ween
517
+ Ġf l
518
+ h n
519
+ v e
520
+ Ġch ar
521
+ Ġc ol
522
+ Ġrec ord
523
+ i ew
524
+ r on
525
+ f ore
526
+ Ġth rough
527
+ is ion
528
+ or n
529
+ Ġ 00
530
+ oc k
531
+ Ġ ver
532
+ Ġl ater
533
+ Ġn um
534
+ Ġe nd
535
+ ol og
536
+ am es
537
+ Ġp os
538
+ Ġw rit
539
+ Ġpro du
540
+ Ġwh ile
541
+ Ġa ct
542
+ Ġre le
543
+ Ġf ilm
544
+ is hed
545
+ Ġp r
546
+ an s
547
+ Ġre g
548
+ Ġfor m
549
+ Ġas s
550
+ ĠS e
551
+ ur y
552
+ t ed
553
+ t s
554
+ Ġm ade
555
+ Ġsu b
556
+ Ġp e
557
+ Ġs o
558
+ or ld
559
+ Ġre t
560
+ ĠN ew
561
+ Ġsp ec
562
+ Ġa cc
563
+ Ġ qu
564
+ Ġwhe re
565
+ en er
566
+ Ġm ov
567
+ he s
568
+ mer ic
569
+ at ing
570
+ Ġin ter
571
+ ĠL e
572
+ ĠA meric
573
+ Ġ ra
574
+ Ġs ome
575
+ Ġc o
576
+ Ġl ar
577
+ Ġb u
578
+ Ġde f
579
+ b um
580
+ Ġa c
581
+ Ġm us
582
+ Ġf ollow
583
+ ĠA t
584
+ in s
585
+ iv ed
586
+ if ic
587
+ u al
588
+ Ġa m
589
+ Ġsu ch
590
+ Ġsec ond
591
+ i ke
592
+ Ġf our
593
+ Ġin d
594
+ an n
595
+ he n
596
+ Ġus ed
597
+ ĠR e
598
+ ic s
599
+ le ct
600
+ Ġd ay
601
+ i el
602
+ il y
603
+ ĠTh is
604
+ Ġ 0
605
+ Ġp ubl
606
+ Ġc all
607
+ ĠJ o
608
+ l l
609
+ Ġal bum
610
+ Ġ00 0
611
+ ran s
612
+ Ġd o
613
+ an y
614
+ Ġbe fore
615
+ ro s
616
+ ĠS h
617
+ Ġs y
618
+ a id
619
+ ĠEn g
620
+ Ġbe ing
621
+ Ġ1 0
622
+ u c
623
+ Ġe p
624
+ Ġsu pp
625
+ Ġthe re
626
+ Ġyear s
627
+ ar s
628
+ ow ever
629
+ Ġ ent
630
+ if e
631
+ Ġh igh
632
+ Ġf ound
633
+ ir d
634
+ Ġn o
635
+ Ġs et
636
+ in es
637
+ iv er
638
+ i o
639
+ ot her
640
+ j ect
641
+ Ġs ur
642
+ a j
643
+ t en
644
+ Ġt ra
645
+ Ġ1 2
646
+ is ed
647
+ it ies
648
+ vel op
649
+ Ġb l
650
+ al e
651
+ Ġser ies
652
+ Ġl oc
653
+ Ġnum ber
654
+ Ġp res
655
+ an e
656
+ aus e
657
+ od e
658
+ e k
659
+ t on
660
+ ĠS c
661
+ i er
662
+ is e
663
+ Ġse ver
664
+ in ce
665
+ Ġb oth
666
+ an k
667
+ ro w
668
+ ire ct
669
+ s on
670
+ Ġthe n
671
+ ĠB rit
672
+ i et
673
+ Ġ1 6
674
+ Ġep is
675
+ Ġinclud ing
676
+ it s
677
+ ig in
678
+ p r
679
+ Ġ /
680
+ Ġagain st
681
+ Ġw ell
682
+ Ġbec ame
683
+ Ġex p
684
+ Ġkn own
685
+ Ġt rans
686
+ Ġchar ac
687
+ ĠâĢ Ķ
688
+ r am
689
+ Ġb ack
690
+ Ġad d
691
+ Ġp op
692
+ Ġg o
693
+ ur ch
694
+ Ġdes c
695
+ Ġs ing
696
+ iel d
697
+ Ġper form
698
+ ain ed
699
+ Ġre ce
700
+ id ent
701
+ Ġe m
702
+ er t
703
+ u res
704
+ Ġin v
705
+ Ġde p
706
+ Ġ19 8
707
+ a ir
708
+ er n
709
+ at her
710
+ f ul
711
+ Ġ Z
712
+ Ġm on
713
+ Ġman y
714
+ Ġm ain
715
+ Ġst ud
716
+ Ġl ong
717
+ in n
718
+ th ough
719
+ u p
720
+ o ol
721
+ ĠUn ited
722
+ l ed
723
+ em ent
724
+ Ġ1 5
725
+ ow er
726
+ ĠJo hn
727
+ Ġo p
728
+ Ġ1 1
729
+ in ed
730
+ Ġm et
731
+ o ber
732
+ le y
733
+ Ġ1 7
734
+ Ġcent ury
735
+ Ġte am
736
+ Ġ est
737
+ ĠA fter
738
+ y l
739
+ Ġm in
740
+ u ch
741
+ ut e
742
+ Ġde velop
743
+ ĠS he
744
+ i am
745
+ Ġsh ow
746
+ el f
747
+ Ġre p
748
+ Ġcon c
749
+ at ive
750
+ Ġc re
751
+ over n
752
+ a red
753
+ Ġ19 4
754
+ Ġor igin
755
+ Ġs m
756
+ iv ers
757
+ a z
758
+ Ġle ad
759
+ Ġsever al
760
+ a h
761
+ Ġo b
762
+ Ġre v
763
+ Ġm ill
764
+ er m
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd24b3eef290f63acca7a98b0e88280e479c1faf02211537c30b182c804c1fb
3
+ size 365636
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b857adb354600f4756f49af9c889f9992ebdd16b58a57eb0598f32eb4de443
3
+ size 451744
tokenizer.json ADDED
@@ -0,0 +1,1939 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[CLS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": true,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[UNK]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": true,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": true,
47
+ "rstrip": false,
48
+ "normalized": true,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "ByteLevel",
55
+ "add_prefix_space": false,
56
+ "trim_offsets": true,
57
+ "use_regex": true
58
+ },
59
+ "post_processor": {
60
+ "type": "TemplateProcessing",
61
+ "single": [
62
+ {
63
+ "SpecialToken": {
64
+ "id": "[CLS]",
65
+ "type_id": 0
66
+ }
67
+ },
68
+ {
69
+ "Sequence": {
70
+ "id": "A",
71
+ "type_id": 0
72
+ }
73
+ },
74
+ {
75
+ "SpecialToken": {
76
+ "id": "[SEP]",
77
+ "type_id": 0
78
+ }
79
+ }
80
+ ],
81
+ "pair": [
82
+ {
83
+ "SpecialToken": {
84
+ "id": "[CLS]",
85
+ "type_id": 0
86
+ }
87
+ },
88
+ {
89
+ "Sequence": {
90
+ "id": "A",
91
+ "type_id": 0
92
+ }
93
+ },
94
+ {
95
+ "SpecialToken": {
96
+ "id": "[SEP]",
97
+ "type_id": 0
98
+ }
99
+ },
100
+ {
101
+ "Sequence": {
102
+ "id": "B",
103
+ "type_id": 1
104
+ }
105
+ },
106
+ {
107
+ "SpecialToken": {
108
+ "id": "[SEP]",
109
+ "type_id": 1
110
+ }
111
+ }
112
+ ],
113
+ "special_tokens": {
114
+ "[CLS]": {
115
+ "id": "[CLS]",
116
+ "ids": [
117
+ 1
118
+ ],
119
+ "tokens": [
120
+ "[CLS]"
121
+ ]
122
+ },
123
+ "[SEP]": {
124
+ "id": "[SEP]",
125
+ "ids": [
126
+ 2
127
+ ],
128
+ "tokens": [
129
+ "[SEP]"
130
+ ]
131
+ }
132
+ }
133
+ },
134
+ "decoder": {
135
+ "type": "ByteLevel",
136
+ "add_prefix_space": true,
137
+ "trim_offsets": true,
138
+ "use_regex": true
139
+ },
140
+ "model": {
141
+ "type": "BPE",
142
+ "dropout": null,
143
+ "unk_token": null,
144
+ "continuing_subword_prefix": "",
145
+ "end_of_word_suffix": "",
146
+ "fuse_unk": false,
147
+ "vocab": {
148
+ "[PAD]": 0,
149
+ "[CLS]": 1,
150
+ "[SEP]": 2,
151
+ "[UNK]": 3,
152
+ "[MASK]": 4,
153
+ "!": 5,
154
+ "\"": 6,
155
+ "#": 7,
156
+ "$": 8,
157
+ "%": 9,
158
+ "&": 10,
159
+ "'": 11,
160
+ "(": 12,
161
+ ")": 13,
162
+ "*": 14,
163
+ "+": 15,
164
+ ",": 16,
165
+ "-": 17,
166
+ ".": 18,
167
+ "/": 19,
168
+ "0": 20,
169
+ "1": 21,
170
+ "2": 22,
171
+ "3": 23,
172
+ "4": 24,
173
+ "5": 25,
174
+ "6": 26,
175
+ "7": 27,
176
+ "8": 28,
177
+ "9": 29,
178
+ ":": 30,
179
+ ";": 31,
180
+ "<": 32,
181
+ "=": 33,
182
+ ">": 34,
183
+ "?": 35,
184
+ "@": 36,
185
+ "A": 37,
186
+ "B": 38,
187
+ "C": 39,
188
+ "D": 40,
189
+ "E": 41,
190
+ "F": 42,
191
+ "G": 43,
192
+ "H": 44,
193
+ "I": 45,
194
+ "J": 46,
195
+ "K": 47,
196
+ "L": 48,
197
+ "M": 49,
198
+ "N": 50,
199
+ "O": 51,
200
+ "P": 52,
201
+ "Q": 53,
202
+ "R": 54,
203
+ "S": 55,
204
+ "T": 56,
205
+ "U": 57,
206
+ "V": 58,
207
+ "W": 59,
208
+ "X": 60,
209
+ "Y": 61,
210
+ "Z": 62,
211
+ "[": 63,
212
+ "\\": 64,
213
+ "]": 65,
214
+ "^": 66,
215
+ "_": 67,
216
+ "`": 68,
217
+ "a": 69,
218
+ "b": 70,
219
+ "c": 71,
220
+ "d": 72,
221
+ "e": 73,
222
+ "f": 74,
223
+ "g": 75,
224
+ "h": 76,
225
+ "i": 77,
226
+ "j": 78,
227
+ "k": 79,
228
+ "l": 80,
229
+ "m": 81,
230
+ "n": 82,
231
+ "o": 83,
232
+ "p": 84,
233
+ "q": 85,
234
+ "r": 86,
235
+ "s": 87,
236
+ "t": 88,
237
+ "u": 89,
238
+ "v": 90,
239
+ "w": 91,
240
+ "x": 92,
241
+ "y": 93,
242
+ "z": 94,
243
+ "{": 95,
244
+ "|": 96,
245
+ "}": 97,
246
+ "~": 98,
247
+ "¡": 99,
248
+ "¢": 100,
249
+ "£": 101,
250
+ "¤": 102,
251
+ "¥": 103,
252
+ "¦": 104,
253
+ "§": 105,
254
+ "¨": 106,
255
+ "©": 107,
256
+ "ª": 108,
257
+ "«": 109,
258
+ "¬": 110,
259
+ "®": 111,
260
+ "¯": 112,
261
+ "°": 113,
262
+ "±": 114,
263
+ "²": 115,
264
+ "³": 116,
265
+ "´": 117,
266
+ "µ": 118,
267
+ "¶": 119,
268
+ "·": 120,
269
+ "¸": 121,
270
+ "¹": 122,
271
+ "º": 123,
272
+ "»": 124,
273
+ "¼": 125,
274
+ "½": 126,
275
+ "¾": 127,
276
+ "¿": 128,
277
+ "À": 129,
278
+ "Á": 130,
279
+ "Â": 131,
280
+ "Ã": 132,
281
+ "Ä": 133,
282
+ "Å": 134,
283
+ "Æ": 135,
284
+ "Ç": 136,
285
+ "È": 137,
286
+ "É": 138,
287
+ "Ê": 139,
288
+ "Ë": 140,
289
+ "Ì": 141,
290
+ "Í": 142,
291
+ "Î": 143,
292
+ "Ï": 144,
293
+ "Ð": 145,
294
+ "Ñ": 146,
295
+ "Ò": 147,
296
+ "Ó": 148,
297
+ "Ô": 149,
298
+ "Õ": 150,
299
+ "Ö": 151,
300
+ "×": 152,
301
+ "Ø": 153,
302
+ "Ù": 154,
303
+ "Ú": 155,
304
+ "Û": 156,
305
+ "Ü": 157,
306
+ "Ý": 158,
307
+ "Þ": 159,
308
+ "ß": 160,
309
+ "à": 161,
310
+ "á": 162,
311
+ "â": 163,
312
+ "ã": 164,
313
+ "ä": 165,
314
+ "å": 166,
315
+ "æ": 167,
316
+ "ç": 168,
317
+ "è": 169,
318
+ "é": 170,
319
+ "ê": 171,
320
+ "ë": 172,
321
+ "ì": 173,
322
+ "í": 174,
323
+ "î": 175,
324
+ "ï": 176,
325
+ "ð": 177,
326
+ "ñ": 178,
327
+ "ò": 179,
328
+ "ó": 180,
329
+ "ô": 181,
330
+ "õ": 182,
331
+ "ö": 183,
332
+ "÷": 184,
333
+ "ø": 185,
334
+ "ù": 186,
335
+ "ú": 187,
336
+ "û": 188,
337
+ "ü": 189,
338
+ "ý": 190,
339
+ "þ": 191,
340
+ "ÿ": 192,
341
+ "Ā": 193,
342
+ "ā": 194,
343
+ "Ă": 195,
344
+ "ă": 196,
345
+ "Ą": 197,
346
+ "ą": 198,
347
+ "Ć": 199,
348
+ "ć": 200,
349
+ "Ĉ": 201,
350
+ "ĉ": 202,
351
+ "Ċ": 203,
352
+ "ċ": 204,
353
+ "Č": 205,
354
+ "č": 206,
355
+ "Ď": 207,
356
+ "ď": 208,
357
+ "Đ": 209,
358
+ "đ": 210,
359
+ "Ē": 211,
360
+ "ē": 212,
361
+ "Ĕ": 213,
362
+ "ĕ": 214,
363
+ "Ė": 215,
364
+ "ė": 216,
365
+ "Ę": 217,
366
+ "ę": 218,
367
+ "Ě": 219,
368
+ "ě": 220,
369
+ "Ĝ": 221,
370
+ "ĝ": 222,
371
+ "Ğ": 223,
372
+ "ğ": 224,
373
+ "Ġ": 225,
374
+ "ġ": 226,
375
+ "Ģ": 227,
376
+ "ģ": 228,
377
+ "Ĥ": 229,
378
+ "ĥ": 230,
379
+ "Ħ": 231,
380
+ "ħ": 232,
381
+ "Ĩ": 233,
382
+ "ĩ": 234,
383
+ "Ī": 235,
384
+ "ī": 236,
385
+ "Ĭ": 237,
386
+ "ĭ": 238,
387
+ "Į": 239,
388
+ "į": 240,
389
+ "İ": 241,
390
+ "ı": 242,
391
+ "IJ": 243,
392
+ "ij": 244,
393
+ "Ĵ": 245,
394
+ "ĵ": 246,
395
+ "Ķ": 247,
396
+ "ķ": 248,
397
+ "ĸ": 249,
398
+ "Ĺ": 250,
399
+ "ĺ": 251,
400
+ "Ļ": 252,
401
+ "ļ": 253,
402
+ "Ľ": 254,
403
+ "ľ": 255,
404
+ "Ŀ": 256,
405
+ "ŀ": 257,
406
+ "Ł": 258,
407
+ "ł": 259,
408
+ "Ń": 260,
409
+ "Ġt": 261,
410
+ "he": 262,
411
+ "Ġa": 263,
412
+ "in": 264,
413
+ "Ġthe": 265,
414
+ "er": 266,
415
+ "on": 267,
416
+ "Ġ,": 268,
417
+ "re": 269,
418
+ "Ġs": 270,
419
+ "ed": 271,
420
+ "Ġo": 272,
421
+ "Ġw": 273,
422
+ "nd": 274,
423
+ "at": 275,
424
+ "Ġ.": 276,
425
+ "or": 277,
426
+ "it": 278,
427
+ "Ġc": 279,
428
+ "en": 280,
429
+ "Ġf": 281,
430
+ "is": 282,
431
+ "es": 283,
432
+ "ar": 284,
433
+ "Ġof": 285,
434
+ "Ġb": 286,
435
+ "an": 287,
436
+ "Ġin": 288,
437
+ "al": 289,
438
+ "ing": 290,
439
+ "Ġp": 291,
440
+ "Ġand": 292,
441
+ "as": 293,
442
+ "Ġto": 294,
443
+ "ro": 295,
444
+ "ic": 296,
445
+ "Ġm": 297,
446
+ "Ġd": 298,
447
+ "Ġh": 299,
448
+ "ion": 300,
449
+ "le": 301,
450
+ "ou": 302,
451
+ "ĠT": 303,
452
+ "Ġre": 304,
453
+ "Ġ=": 305,
454
+ "Ġ\"": 306,
455
+ "ĠA": 307,
456
+ "ĠS": 308,
457
+ "ent": 309,
458
+ "il": 310,
459
+ "Ġth": 311,
460
+ "Ġ1": 312,
461
+ "st": 313,
462
+ "ĠC": 314,
463
+ "el": 315,
464
+ "om": 316,
465
+ "Ġl": 317,
466
+ "am": 318,
467
+ "ĠĊ": 319,
468
+ "Ġe": 320,
469
+ "Ġn": 321,
470
+ "Ġ@": 322,
471
+ "ad": 323,
472
+ "ac": 324,
473
+ "Ġwas": 325,
474
+ "ĠM": 326,
475
+ "ur": 327,
476
+ "ĠThe": 328,
477
+ "ec": 329,
478
+ "Ġon": 330,
479
+ "ly": 331,
480
+ "ĠB": 332,
481
+ "ĠI": 333,
482
+ "Ġg": 334,
483
+ "Ġ'": 335,
484
+ "et": 336,
485
+ "ol": 337,
486
+ "id": 338,
487
+ "iv": 339,
488
+ "im": 340,
489
+ "Ġfor": 341,
490
+ "ir": 342,
491
+ "-@": 343,
492
+ "Ġ@-@": 344,
493
+ "ig": 345,
494
+ "ot": 346,
495
+ "ter": 347,
496
+ "Ġas": 348,
497
+ "ĠH": 349,
498
+ "us": 350,
499
+ "ow": 351,
500
+ "Ġst": 352,
501
+ "ut": 353,
502
+ "ith": 354,
503
+ "ay": 355,
504
+ "Ġ2": 356,
505
+ "ĠP": 357,
506
+ "ation": 358,
507
+ "ver": 359,
508
+ "Ġbe": 360,
509
+ "her": 361,
510
+ "Ġthat": 362,
511
+ "Ġwith": 363,
512
+ "ĠR": 364,
513
+ "ce": 365,
514
+ "th": 366,
515
+ "ĠD": 367,
516
+ "Ġis": 368,
517
+ "un": 369,
518
+ "em": 370,
519
+ "ĠF": 371,
520
+ "Ġwh": 372,
521
+ "ul": 373,
522
+ "Ġby": 374,
523
+ "Ġal": 375,
524
+ "ch": 376,
525
+ "Ġ)": 377,
526
+ "Ġ(": 378,
527
+ "ĠW": 379,
528
+ "Ġcon": 380,
529
+ "ra": 381,
530
+ "ĠG": 382,
531
+ "os": 383,
532
+ "ĠL": 384,
533
+ "ĠN": 385,
534
+ "Ġat": 386,
535
+ "ers": 387,
536
+ "ct": 388,
537
+ "Ġit": 389,
538
+ "Ġ19": 390,
539
+ "rom": 391,
540
+ "and": 392,
541
+ "Ġan": 393,
542
+ "um": 394,
543
+ "est": 395,
544
+ "ĠJ": 396,
545
+ "ag": 397,
546
+ "Ġhe": 398,
547
+ "00": 399,
548
+ "ist": 400,
549
+ "ain": 401,
550
+ "od": 402,
551
+ "av": 403,
552
+ "ri": 404,
553
+ "ĠE": 405,
554
+ "ĠO": 406,
555
+ "Ġfrom": 407,
556
+ "Ġcom": 408,
557
+ "Ġhis": 409,
558
+ "op": 410,
559
+ "Ġpro": 411,
560
+ "res": 412,
561
+ "ies": 413,
562
+ "if": 414,
563
+ "Ġv": 415,
564
+ "ort": 416,
565
+ "ere": 417,
566
+ "ill": 418,
567
+ "ld": 419,
568
+ "Ġde": 420,
569
+ "pp": 421,
570
+ "Ġsu": 422,
571
+ "ore": 423,
572
+ "ĠIn": 424,
573
+ "Ġr": 425,
574
+ "Ġse": 426,
575
+ "Ġwere": 427,
576
+ "ew": 428,
577
+ "ong": 429,
578
+ "igh": 430,
579
+ "ard": 431,
580
+ "ate": 432,
581
+ "all": 433,
582
+ "art": 434,
583
+ "ak": 435,
584
+ "ich": 436,
585
+ "Ġch": 437,
586
+ "Ġor": 438,
587
+ "ab": 439,
588
+ "ant": 440,
589
+ "ud": 441,
590
+ "oc": 442,
591
+ "ber": 443,
592
+ "Ġex": 444,
593
+ "gh": 445,
594
+ "ity": 446,
595
+ "ated": 447,
596
+ "pt": 448,
597
+ "ess": 449,
598
+ "ear": 450,
599
+ "ĠK": 451,
600
+ "Ġpl": 452,
601
+ "ame": 453,
602
+ "qu": 454,
603
+ "ive": 455,
604
+ "rou": 456,
605
+ "Ġare": 457,
606
+ "Ġâ": 458,
607
+ "Ġsh": 459,
608
+ "Ġk": 460,
609
+ "ack": 461,
610
+ "ect": 462,
611
+ "ĠâĢ": 463,
612
+ "ĠU": 464,
613
+ "Ġhad": 465,
614
+ "se": 466,
615
+ "Ġwhich": 467,
616
+ "red": 468,
617
+ "ov": 469,
618
+ "ĠSt": 470,
619
+ "ast": 471,
620
+ "Ġsp": 472,
621
+ "ian": 473,
622
+ "Ġy": 474,
623
+ "ment": 475,
624
+ "Ġle": 476,
625
+ "Ġnot": 477,
626
+ "ge": 478,
627
+ "ord": 479,
628
+ "rit": 480,
629
+ "ip": 481,
630
+ "ine": 482,
631
+ "ell": 483,
632
+ "ally": 484,
633
+ "our": 485,
634
+ "ost": 486,
635
+ "ight": 487,
636
+ "ther": 488,
637
+ "ap": 489,
638
+ "Ġu": 490,
639
+ "ish": 491,
640
+ "ĠCh": 492,
641
+ "oun": 493,
642
+ "ia": 494,
643
+ "Ġ3": 495,
644
+ "ave": 496,
645
+ "ary": 497,
646
+ "ust": 498,
647
+ "og": 499,
648
+ "Ġ200": 500,
649
+ "Ġun": 501,
650
+ "ous": 502,
651
+ "irst": 503,
652
+ "ĠV": 504,
653
+ "cc": 505,
654
+ "Ġinc": 506,
655
+ "Ġ;": 507,
656
+ "Ġcomp": 508,
657
+ "ru": 509,
658
+ "ions": 510,
659
+ "Ġtheir": 511,
660
+ "Ġbut": 512,
661
+ "ide": 513,
662
+ "ure": 514,
663
+ "so": 515,
664
+ "Ġcont": 516,
665
+ "Ġint": 517,
666
+ "fter": 518,
667
+ "ical": 519,
668
+ "ial": 520,
669
+ "Ġar": 521,
670
+ "Ġfirst": 522,
671
+ "ould": 523,
672
+ "Ġits": 524,
673
+ "hed": 525,
674
+ "ĠâĢĵ": 526,
675
+ "Ġwhe": 527,
676
+ "wo": 528,
677
+ "out": 529,
678
+ "ub": 530,
679
+ "Ġ20": 531,
680
+ "ff": 532,
681
+ "Ġ:": 533,
682
+ "ue": 534,
683
+ "Ġher": 535,
684
+ "own": 536,
685
+ "ok": 537,
686
+ "Ġalso": 538,
687
+ "Ġcl": 539,
688
+ "per": 540,
689
+ "ign": 541,
690
+ "ater": 542,
691
+ "ran": 543,
692
+ "orm": 544,
693
+ "ie": 545,
694
+ "ome": 546,
695
+ "ork": 547,
696
+ "ass": 548,
697
+ "ire": 549,
698
+ "end": 550,
699
+ "Ġres": 551,
700
+ "Ġab": 552,
701
+ "Ġad": 553,
702
+ "Ġus": 554,
703
+ "ry": 555,
704
+ "Ġrec": 556,
705
+ "Ġhave": 557,
706
+ "age": 558,
707
+ "ĠHe": 559,
708
+ "Ġ4": 560,
709
+ "Ġro": 561,
710
+ "mer": 562,
711
+ "Ġone": 563,
712
+ "ond": 564,
713
+ "low": 565,
714
+ "Ġhas": 566,
715
+ "ĠTh": 567,
716
+ "du": 568,
717
+ "Ġ5": 569,
718
+ "Ġper": 570,
719
+ "Ġbeen": 571,
720
+ "ime": 572,
721
+ "Ġtwo": 573,
722
+ "ence": 574,
723
+ "land": 575,
724
+ "Ġ18": 576,
725
+ ".@": 577,
726
+ "Ġ@.@": 578,
727
+ "ult": 579,
728
+ "ree": 580,
729
+ "ough": 581,
730
+ "ile": 582,
731
+ "Ġwho": 583,
732
+ "ĠAl": 584,
733
+ "Ġsc": 585,
734
+ "uring": 586,
735
+ "pl": 587,
736
+ "ory": 588,
737
+ "ition": 589,
738
+ "ric": 590,
739
+ "ations": 591,
740
+ "Ġdis": 592,
741
+ "Ġthis": 593,
742
+ "Ġbec": 594,
743
+ "Ġapp": 595,
744
+ "iz": 596,
745
+ "ĠIt": 597,
746
+ "are": 598,
747
+ "ach": 599,
748
+ "lud": 600,
749
+ "ade": 601,
750
+ "Ġplay": 602,
751
+ "Ġj": 603,
752
+ "Ġman": 604,
753
+ "act": 605,
754
+ "ely": 606,
755
+ "Ġpart": 607,
756
+ "Ġdes": 608,
757
+ "Ġag": 609,
758
+ "Ġthey": 610,
759
+ "Ġyear": 611,
760
+ "ount": 612,
761
+ "Ġ201": 613,
762
+ "Ġover": 614,
763
+ "Ġother": 615,
764
+ "ound": 616,
765
+ "Ġafter": 617,
766
+ "ib": 618,
767
+ "over": 619,
768
+ "Ġser": 620,
769
+ "Ġen": 621,
770
+ "Ġoff": 622,
771
+ "Ġim": 623,
772
+ "ction": 624,
773
+ "ĠY": 625,
774
+ "ke": 626,
775
+ "ite": 627,
776
+ ",@": 628,
777
+ "Ġ@,@": 629,
778
+ "te": 630,
779
+ "urn": 631,
780
+ "Ġinclud": 632,
781
+ "ress": 633,
782
+ "ance": 634,
783
+ "ang": 635,
784
+ "Ġatt": 636,
785
+ "ice": 637,
786
+ "ace": 638,
787
+ "ark": 639,
788
+ "Ġout": 640,
789
+ "wn": 641,
790
+ "ph": 642,
791
+ "ember": 643,
792
+ "Ġpre": 644,
793
+ "Ġup": 645,
794
+ "ens": 646,
795
+ "man": 647,
796
+ "Ġev": 648,
797
+ "Ġtime": 649,
798
+ "nder": 650,
799
+ "rough": 651,
800
+ "ced": 652,
801
+ "Ġfin": 653,
802
+ "Ġinto": 654,
803
+ "one": 655,
804
+ "port": 656,
805
+ "round": 657,
806
+ "we": 658,
807
+ "ren": 659,
808
+ "les": 660,
809
+ "int": 661,
810
+ "ĠOn": 662,
811
+ "vel": 663,
812
+ "Ġcomm": 664,
813
+ "Ġshe": 665,
814
+ "ason": 666,
815
+ "amp": 667,
816
+ "Ġte": 668,
817
+ "Ġwould": 669,
818
+ "ward": 670,
819
+ "Ġmore": 671,
820
+ "Ġ6": 672,
821
+ "ied": 673,
822
+ "ose": 674,
823
+ "rib": 675,
824
+ "ĠUn": 676,
825
+ "Ġall": 677,
826
+ "ings": 678,
827
+ "tern": 679,
828
+ "ces": 680,
829
+ "able": 681,
830
+ "Ġwe": 682,
831
+ "ited": 683,
832
+ "ever": 684,
833
+ "ents": 685,
834
+ "Ġhim": 686,
835
+ "ased": 687,
836
+ "ors": 688,
837
+ "oy": 689,
838
+ "ood": 690,
839
+ "Ġcent": 691,
840
+ "ix": 692,
841
+ "ase": 693,
842
+ "ild": 694,
843
+ "ĠAn": 695,
844
+ "Ġ7": 696,
845
+ "Ġwork": 697,
846
+ "ates": 698,
847
+ "ious": 699,
848
+ "ath": 700,
849
+ "Ġpo": 701,
850
+ "rop": 702,
851
+ "old": 703,
852
+ "als": 704,
853
+ "iss": 705,
854
+ "ey": 706,
855
+ "ict": 707,
856
+ "Ġfe": 708,
857
+ "Ġthem": 709,
858
+ "gan": 710,
859
+ "Ġsec": 711,
860
+ "Ġbet": 712,
861
+ "Ġwhen": 713,
862
+ "Ġsong": 714,
863
+ "Ġrem": 715,
864
+ "ep": 716,
865
+ "form": 717,
866
+ "ail": 718,
867
+ "fer": 719,
868
+ "Ġear": 720,
869
+ "ubl": 721,
870
+ "aw": 722,
871
+ "Ġkn": 723,
872
+ "ake": 724,
873
+ "aus": 725,
874
+ "Ġmost": 726,
875
+ "Ġcons": 727,
876
+ "Ġduring": 728,
877
+ "ĠAs": 729,
878
+ "orth": 730,
879
+ "Ġnew": 731,
880
+ "ered": 732,
881
+ "ilm": 733,
882
+ "ved": 734,
883
+ "att": 735,
884
+ "Ġonly": 736,
885
+ "Ġ9": 737,
886
+ "Ġdec": 738,
887
+ "Ġ8": 739,
888
+ "ick": 740,
889
+ "Ġgame": 741,
890
+ "ons": 742,
891
+ "ug": 743,
892
+ "Ġtr": 744,
893
+ "ft": 745,
894
+ "oth": 746,
895
+ "ook": 747,
896
+ "ĠMar": 748,
897
+ "reat": 749,
898
+ "way": 750,
899
+ "Ġcan": 751,
900
+ "ollow": 752,
901
+ "outh": 753,
902
+ "ween": 754,
903
+ "ĠEn": 755,
904
+ "Ġ199": 756,
905
+ "ters": 757,
906
+ "Ġrel": 758,
907
+ "ind": 759,
908
+ "Ġabout": 760,
909
+ "Ġseason": 761,
910
+ "Ġagain": 762,
911
+ "ral": 763,
912
+ "Ġthree": 764,
913
+ "ational": 765,
914
+ "Ġunder": 766,
915
+ "ular": 767,
916
+ "Ġme": 768,
917
+ "Ġthan": 769,
918
+ "ĠCom": 770,
919
+ "ĠAr": 771,
920
+ "hip": 772,
921
+ "ob": 773,
922
+ "Ġne": 774,
923
+ "Ġbetween": 775,
924
+ "Ġfl": 776,
925
+ "hn": 777,
926
+ "ve": 778,
927
+ "Ġchar": 779,
928
+ "Ġcol": 780,
929
+ "Ġrecord": 781,
930
+ "iew": 782,
931
+ "ron": 783,
932
+ "fore": 784,
933
+ "Ġthrough": 785,
934
+ "ision": 786,
935
+ "orn": 787,
936
+ "Ġ00": 788,
937
+ "ock": 789,
938
+ "Ġver": 790,
939
+ "Ġlater": 791,
940
+ "Ġnum": 792,
941
+ "Ġend": 793,
942
+ "olog": 794,
943
+ "ames": 795,
944
+ "Ġpos": 796,
945
+ "Ġwrit": 797,
946
+ "Ġprodu": 798,
947
+ "Ġwhile": 799,
948
+ "Ġact": 800,
949
+ "Ġrele": 801,
950
+ "Ġfilm": 802,
951
+ "ished": 803,
952
+ "Ġpr": 804,
953
+ "ans": 805,
954
+ "Ġreg": 806,
955
+ "Ġform": 807,
956
+ "Ġass": 808,
957
+ "ĠSe": 809,
958
+ "ury": 810,
959
+ "ted": 811,
960
+ "ts": 812,
961
+ "Ġmade": 813,
962
+ "Ġsub": 814,
963
+ "Ġpe": 815,
964
+ "Ġso": 816,
965
+ "orld": 817,
966
+ "Ġret": 818,
967
+ "ĠNew": 819,
968
+ "Ġspec": 820,
969
+ "Ġacc": 821,
970
+ "Ġqu": 822,
971
+ "Ġwhere": 823,
972
+ "ener": 824,
973
+ "Ġmov": 825,
974
+ "hes": 826,
975
+ "meric": 827,
976
+ "ating": 828,
977
+ "Ġinter": 829,
978
+ "ĠLe": 830,
979
+ "ĠAmeric": 831,
980
+ "Ġra": 832,
981
+ "Ġsome": 833,
982
+ "Ġco": 834,
983
+ "Ġlar": 835,
984
+ "Ġbu": 836,
985
+ "Ġdef": 837,
986
+ "bum": 838,
987
+ "Ġac": 839,
988
+ "Ġmus": 840,
989
+ "Ġfollow": 841,
990
+ "ĠAt": 842,
991
+ "ins": 843,
992
+ "ived": 844,
993
+ "ific": 845,
994
+ "ual": 846,
995
+ "Ġam": 847,
996
+ "Ġsuch": 848,
997
+ "Ġsecond": 849,
998
+ "ike": 850,
999
+ "Ġfour": 851,
1000
+ "Ġind": 852,
1001
+ "ann": 853,
1002
+ "hen": 854,
1003
+ "Ġused": 855,
1004
+ "ĠRe": 856,
1005
+ "ics": 857,
1006
+ "lect": 858,
1007
+ "Ġday": 859,
1008
+ "iel": 860,
1009
+ "ily": 861,
1010
+ "ĠThis": 862,
1011
+ "Ġ0": 863,
1012
+ "Ġpubl": 864,
1013
+ "Ġcall": 865,
1014
+ "ĠJo": 866,
1015
+ "ll": 867,
1016
+ "Ġalbum": 868,
1017
+ "Ġ000": 869,
1018
+ "rans": 870,
1019
+ "Ġdo": 871,
1020
+ "any": 872,
1021
+ "Ġbefore": 873,
1022
+ "ros": 874,
1023
+ "ĠSh": 875,
1024
+ "Ġsy": 876,
1025
+ "aid": 877,
1026
+ "ĠEng": 878,
1027
+ "Ġbeing": 879,
1028
+ "Ġ10": 880,
1029
+ "uc": 881,
1030
+ "Ġep": 882,
1031
+ "Ġsupp": 883,
1032
+ "Ġthere": 884,
1033
+ "Ġyears": 885,
1034
+ "ars": 886,
1035
+ "owever": 887,
1036
+ "Ġent": 888,
1037
+ "ife": 889,
1038
+ "Ġhigh": 890,
1039
+ "Ġfound": 891,
1040
+ "ird": 892,
1041
+ "Ġno": 893,
1042
+ "Ġset": 894,
1043
+ "ines": 895,
1044
+ "iver": 896,
1045
+ "io": 897,
1046
+ "other": 898,
1047
+ "ject": 899,
1048
+ "Ġsur": 900,
1049
+ "aj": 901,
1050
+ "ten": 902,
1051
+ "Ġtra": 903,
1052
+ "Ġ12": 904,
1053
+ "ised": 905,
1054
+ "ities": 906,
1055
+ "velop": 907,
1056
+ "Ġbl": 908,
1057
+ "ale": 909,
1058
+ "Ġseries": 910,
1059
+ "Ġloc": 911,
1060
+ "Ġnumber": 912,
1061
+ "Ġpres": 913,
1062
+ "ane": 914,
1063
+ "ause": 915,
1064
+ "ode": 916,
1065
+ "ek": 917,
1066
+ "ton": 918,
1067
+ "ĠSc": 919,
1068
+ "ier": 920,
1069
+ "ise": 921,
1070
+ "Ġsever": 922,
1071
+ "ince": 923,
1072
+ "Ġboth": 924,
1073
+ "ank": 925,
1074
+ "row": 926,
1075
+ "irect": 927,
1076
+ "son": 928,
1077
+ "Ġthen": 929,
1078
+ "ĠBrit": 930,
1079
+ "iet": 931,
1080
+ "Ġ16": 932,
1081
+ "Ġepis": 933,
1082
+ "Ġincluding": 934,
1083
+ "its": 935,
1084
+ "igin": 936,
1085
+ "pr": 937,
1086
+ "Ġ/": 938,
1087
+ "Ġagainst": 939,
1088
+ "Ġwell": 940,
1089
+ "Ġbecame": 941,
1090
+ "Ġexp": 942,
1091
+ "Ġknown": 943,
1092
+ "Ġtrans": 944,
1093
+ "Ġcharac": 945,
1094
+ "ĠâĢĶ": 946,
1095
+ "ram": 947,
1096
+ "Ġback": 948,
1097
+ "Ġadd": 949,
1098
+ "Ġpop": 950,
1099
+ "Ġgo": 951,
1100
+ "urch": 952,
1101
+ "Ġdesc": 953,
1102
+ "Ġsing": 954,
1103
+ "ield": 955,
1104
+ "Ġperform": 956,
1105
+ "ained": 957,
1106
+ "Ġrece": 958,
1107
+ "ident": 959,
1108
+ "Ġem": 960,
1109
+ "ert": 961,
1110
+ "ures": 962,
1111
+ "Ġinv": 963,
1112
+ "Ġdep": 964,
1113
+ "Ġ198": 965,
1114
+ "air": 966,
1115
+ "ern": 967,
1116
+ "ather": 968,
1117
+ "ful": 969,
1118
+ "ĠZ": 970,
1119
+ "Ġmon": 971,
1120
+ "Ġmany": 972,
1121
+ "Ġmain": 973,
1122
+ "Ġstud": 974,
1123
+ "Ġlong": 975,
1124
+ "inn": 976,
1125
+ "though": 977,
1126
+ "up": 978,
1127
+ "ool": 979,
1128
+ "ĠUnited": 980,
1129
+ "led": 981,
1130
+ "ement": 982,
1131
+ "Ġ15": 983,
1132
+ "ower": 984,
1133
+ "ĠJohn": 985,
1134
+ "Ġop": 986,
1135
+ "Ġ11": 987,
1136
+ "ined": 988,
1137
+ "Ġmet": 989,
1138
+ "ober": 990,
1139
+ "ley": 991,
1140
+ "Ġ17": 992,
1141
+ "Ġcentury": 993,
1142
+ "Ġteam": 994,
1143
+ "Ġest": 995,
1144
+ "ĠAfter": 996,
1145
+ "yl": 997,
1146
+ "Ġmin": 998,
1147
+ "uch": 999,
1148
+ "ute": 1000,
1149
+ "Ġdevelop": 1001,
1150
+ "ĠShe": 1002,
1151
+ "iam": 1003,
1152
+ "Ġshow": 1004,
1153
+ "elf": 1005,
1154
+ "Ġrep": 1006,
1155
+ "Ġconc": 1007,
1156
+ "ative": 1008,
1157
+ "Ġcre": 1009,
1158
+ "overn": 1010,
1159
+ "ared": 1011,
1160
+ "Ġ194": 1012,
1161
+ "Ġorigin": 1013,
1162
+ "Ġsm": 1014,
1163
+ "ivers": 1015,
1164
+ "az": 1016,
1165
+ "Ġlead": 1017,
1166
+ "Ġseveral": 1018,
1167
+ "ah": 1019,
1168
+ "Ġob": 1020,
1169
+ "Ġrev": 1021,
1170
+ "Ġmill": 1022,
1171
+ "erm": 1023
1172
+ },
1173
+ "merges": [
1174
+ "Ġ t",
1175
+ "h e",
1176
+ "Ġ a",
1177
+ "i n",
1178
+ "Ġt he",
1179
+ "e r",
1180
+ "o n",
1181
+ "Ġ ,",
1182
+ "r e",
1183
+ "Ġ s",
1184
+ "e d",
1185
+ "Ġ o",
1186
+ "Ġ w",
1187
+ "n d",
1188
+ "a t",
1189
+ "Ġ .",
1190
+ "o r",
1191
+ "i t",
1192
+ "Ġ c",
1193
+ "e n",
1194
+ "Ġ f",
1195
+ "i s",
1196
+ "e s",
1197
+ "a r",
1198
+ "Ġo f",
1199
+ "Ġ b",
1200
+ "a n",
1201
+ "Ġ in",
1202
+ "a l",
1203
+ "in g",
1204
+ "Ġ p",
1205
+ "Ġa nd",
1206
+ "a s",
1207
+ "Ġt o",
1208
+ "r o",
1209
+ "i c",
1210
+ "Ġ m",
1211
+ "Ġ d",
1212
+ "Ġ h",
1213
+ "i on",
1214
+ "l e",
1215
+ "o u",
1216
+ "Ġ T",
1217
+ "Ġ re",
1218
+ "Ġ =",
1219
+ "Ġ \"",
1220
+ "Ġ A",
1221
+ "Ġ S",
1222
+ "en t",
1223
+ "i l",
1224
+ "Ġt h",
1225
+ "Ġ 1",
1226
+ "s t",
1227
+ "Ġ C",
1228
+ "e l",
1229
+ "o m",
1230
+ "Ġ l",
1231
+ "a m",
1232
+ "Ġ Ċ",
1233
+ "Ġ e",
1234
+ "Ġ n",
1235
+ "Ġ @",
1236
+ "a d",
1237
+ "a c",
1238
+ "Ġw as",
1239
+ "Ġ M",
1240
+ "u r",
1241
+ "ĠT he",
1242
+ "e c",
1243
+ "Ġ on",
1244
+ "l y",
1245
+ "Ġ B",
1246
+ "Ġ I",
1247
+ "Ġ g",
1248
+ "Ġ '",
1249
+ "e t",
1250
+ "o l",
1251
+ "i d",
1252
+ "i v",
1253
+ "i m",
1254
+ "Ġf or",
1255
+ "i r",
1256
+ "- @",
1257
+ "Ġ@ -@",
1258
+ "i g",
1259
+ "o t",
1260
+ "t er",
1261
+ "Ġa s",
1262
+ "Ġ H",
1263
+ "u s",
1264
+ "o w",
1265
+ "Ġs t",
1266
+ "u t",
1267
+ "it h",
1268
+ "a y",
1269
+ "Ġ 2",
1270
+ "Ġ P",
1271
+ "at ion",
1272
+ "v er",
1273
+ "Ġb e",
1274
+ "he r",
1275
+ "Ġth at",
1276
+ "Ġw ith",
1277
+ "Ġ R",
1278
+ "c e",
1279
+ "t h",
1280
+ "Ġ D",
1281
+ "Ġ is",
1282
+ "u n",
1283
+ "e m",
1284
+ "Ġ F",
1285
+ "Ġw h",
1286
+ "u l",
1287
+ "Ġb y",
1288
+ "Ġa l",
1289
+ "c h",
1290
+ "Ġ )",
1291
+ "Ġ (",
1292
+ "Ġ W",
1293
+ "Ġc on",
1294
+ "r a",
1295
+ "Ġ G",
1296
+ "o s",
1297
+ "Ġ L",
1298
+ "Ġ N",
1299
+ "Ġa t",
1300
+ "er s",
1301
+ "c t",
1302
+ "Ġ it",
1303
+ "Ġ1 9",
1304
+ "ro m",
1305
+ "a nd",
1306
+ "Ġa n",
1307
+ "u m",
1308
+ "es t",
1309
+ "Ġ J",
1310
+ "a g",
1311
+ "Ġ he",
1312
+ "0 0",
1313
+ "is t",
1314
+ "a in",
1315
+ "o d",
1316
+ "a v",
1317
+ "r i",
1318
+ "Ġ E",
1319
+ "Ġ O",
1320
+ "Ġf rom",
1321
+ "Ġc om",
1322
+ "Ġh is",
1323
+ "o p",
1324
+ "Ġp ro",
1325
+ "re s",
1326
+ "i es",
1327
+ "i f",
1328
+ "Ġ v",
1329
+ "or t",
1330
+ "er e",
1331
+ "il l",
1332
+ "l d",
1333
+ "Ġd e",
1334
+ "p p",
1335
+ "Ġs u",
1336
+ "o re",
1337
+ "ĠI n",
1338
+ "Ġ r",
1339
+ "Ġs e",
1340
+ "Ġw ere",
1341
+ "e w",
1342
+ "on g",
1343
+ "ig h",
1344
+ "ar d",
1345
+ "at e",
1346
+ "al l",
1347
+ "ar t",
1348
+ "a k",
1349
+ "ic h",
1350
+ "Ġc h",
1351
+ "Ġo r",
1352
+ "a b",
1353
+ "an t",
1354
+ "u d",
1355
+ "o c",
1356
+ "b er",
1357
+ "Ġe x",
1358
+ "g h",
1359
+ "it y",
1360
+ "at ed",
1361
+ "p t",
1362
+ "es s",
1363
+ "e ar",
1364
+ "Ġ K",
1365
+ "Ġp l",
1366
+ "am e",
1367
+ "q u",
1368
+ "iv e",
1369
+ "ro u",
1370
+ "Ġa re",
1371
+ "Ġ â",
1372
+ "Ġs h",
1373
+ "Ġ k",
1374
+ "ac k",
1375
+ "ec t",
1376
+ "Ġâ Ģ",
1377
+ "Ġ U",
1378
+ "Ġh ad",
1379
+ "s e",
1380
+ "Ġwh ich",
1381
+ "re d",
1382
+ "o v",
1383
+ "ĠS t",
1384
+ "as t",
1385
+ "Ġs p",
1386
+ "i an",
1387
+ "Ġ y",
1388
+ "m ent",
1389
+ "Ġ le",
1390
+ "Ġn ot",
1391
+ "g e",
1392
+ "or d",
1393
+ "r it",
1394
+ "i p",
1395
+ "in e",
1396
+ "el l",
1397
+ "al ly",
1398
+ "ou r",
1399
+ "o st",
1400
+ "igh t",
1401
+ "t her",
1402
+ "a p",
1403
+ "Ġ u",
1404
+ "is h",
1405
+ "ĠC h",
1406
+ "ou n",
1407
+ "i a",
1408
+ "Ġ 3",
1409
+ "av e",
1410
+ "ar y",
1411
+ "u st",
1412
+ "o g",
1413
+ "Ġ2 00",
1414
+ "Ġ un",
1415
+ "ou s",
1416
+ "ir st",
1417
+ "Ġ V",
1418
+ "c c",
1419
+ "Ġin c",
1420
+ "Ġ ;",
1421
+ "Ġcom p",
1422
+ "r u",
1423
+ "ion s",
1424
+ "Ġthe ir",
1425
+ "Ġb ut",
1426
+ "id e",
1427
+ "u re",
1428
+ "s o",
1429
+ "Ġcon t",
1430
+ "Ġin t",
1431
+ "f ter",
1432
+ "ic al",
1433
+ "i al",
1434
+ "Ġa r",
1435
+ "Ġf irst",
1436
+ "ou ld",
1437
+ "Ġit s",
1438
+ "he d",
1439
+ "ĠâĢ ĵ",
1440
+ "Ġw he",
1441
+ "w o",
1442
+ "ou t",
1443
+ "u b",
1444
+ "Ġ2 0",
1445
+ "f f",
1446
+ "Ġ :",
1447
+ "u e",
1448
+ "Ġ her",
1449
+ "ow n",
1450
+ "o k",
1451
+ "Ġal so",
1452
+ "Ġc l",
1453
+ "p er",
1454
+ "ig n",
1455
+ "at er",
1456
+ "r an",
1457
+ "or m",
1458
+ "i e",
1459
+ "om e",
1460
+ "or k",
1461
+ "as s",
1462
+ "i re",
1463
+ "e nd",
1464
+ "Ġre s",
1465
+ "Ġa b",
1466
+ "Ġa d",
1467
+ "Ġ us",
1468
+ "r y",
1469
+ "Ġre c",
1470
+ "Ġh ave",
1471
+ "ag e",
1472
+ "ĠH e",
1473
+ "Ġ 4",
1474
+ "Ġ ro",
1475
+ "m er",
1476
+ "Ġon e",
1477
+ "on d",
1478
+ "l ow",
1479
+ "Ġh as",
1480
+ "ĠT h",
1481
+ "d u",
1482
+ "Ġ 5",
1483
+ "Ġp er",
1484
+ "Ġbe en",
1485
+ "im e",
1486
+ "Ġt wo",
1487
+ "en ce",
1488
+ "l and",
1489
+ "Ġ1 8",
1490
+ ". @",
1491
+ "Ġ@ .@",
1492
+ "ul t",
1493
+ "re e",
1494
+ "ou gh",
1495
+ "i le",
1496
+ "Ġwh o",
1497
+ "ĠA l",
1498
+ "Ġs c",
1499
+ "ur ing",
1500
+ "p l",
1501
+ "or y",
1502
+ "it ion",
1503
+ "r ic",
1504
+ "ation s",
1505
+ "Ġd is",
1506
+ "Ġth is",
1507
+ "Ġb ec",
1508
+ "Ġa pp",
1509
+ "i z",
1510
+ "ĠI t",
1511
+ "a re",
1512
+ "ac h",
1513
+ "l ud",
1514
+ "ad e",
1515
+ "Ġpl ay",
1516
+ "Ġ j",
1517
+ "Ġm an",
1518
+ "ac t",
1519
+ "el y",
1520
+ "Ġp art",
1521
+ "Ġd es",
1522
+ "Ġa g",
1523
+ "Ġthe y",
1524
+ "Ġy ear",
1525
+ "oun t",
1526
+ "Ġ20 1",
1527
+ "Ġo ver",
1528
+ "Ġo ther",
1529
+ "ou nd",
1530
+ "Ġa fter",
1531
+ "i b",
1532
+ "o ver",
1533
+ "Ġs er",
1534
+ "Ġ en",
1535
+ "Ġof f",
1536
+ "Ġ im",
1537
+ "ct ion",
1538
+ "Ġ Y",
1539
+ "k e",
1540
+ "it e",
1541
+ ", @",
1542
+ "Ġ@ ,@",
1543
+ "t e",
1544
+ "ur n",
1545
+ "Ġinc lud",
1546
+ "res s",
1547
+ "an ce",
1548
+ "an g",
1549
+ "Ġat t",
1550
+ "ic e",
1551
+ "ac e",
1552
+ "ar k",
1553
+ "Ġo ut",
1554
+ "w n",
1555
+ "p h",
1556
+ "em ber",
1557
+ "Ġp re",
1558
+ "Ġu p",
1559
+ "en s",
1560
+ "m an",
1561
+ "Ġe v",
1562
+ "Ġt ime",
1563
+ "nd er",
1564
+ "rou gh",
1565
+ "c ed",
1566
+ "Ġf in",
1567
+ "Ġint o",
1568
+ "on e",
1569
+ "p ort",
1570
+ "rou nd",
1571
+ "w e",
1572
+ "re n",
1573
+ "l es",
1574
+ "in t",
1575
+ "ĠO n",
1576
+ "v el",
1577
+ "Ġcom m",
1578
+ "Ġs he",
1579
+ "as on",
1580
+ "am p",
1581
+ "Ġt e",
1582
+ "Ġw ould",
1583
+ "w ard",
1584
+ "Ġm ore",
1585
+ "Ġ 6",
1586
+ "i ed",
1587
+ "os e",
1588
+ "ri b",
1589
+ "ĠU n",
1590
+ "Ġal l",
1591
+ "ing s",
1592
+ "ter n",
1593
+ "c es",
1594
+ "ab le",
1595
+ "Ġw e",
1596
+ "it ed",
1597
+ "e ver",
1598
+ "ent s",
1599
+ "Ġh im",
1600
+ "as ed",
1601
+ "or s",
1602
+ "o y",
1603
+ "o od",
1604
+ "Ġc ent",
1605
+ "i x",
1606
+ "as e",
1607
+ "il d",
1608
+ "ĠA n",
1609
+ "Ġ 7",
1610
+ "Ġw ork",
1611
+ "at es",
1612
+ "i ous",
1613
+ "at h",
1614
+ "Ġp o",
1615
+ "ro p",
1616
+ "ol d",
1617
+ "al s",
1618
+ "is s",
1619
+ "e y",
1620
+ "ic t",
1621
+ "Ġf e",
1622
+ "Ġthe m",
1623
+ "g an",
1624
+ "Ġs ec",
1625
+ "Ġb et",
1626
+ "Ġwhe n",
1627
+ "Ġs ong",
1628
+ "Ġre m",
1629
+ "e p",
1630
+ "f orm",
1631
+ "a il",
1632
+ "f er",
1633
+ "Ġe ar",
1634
+ "ub l",
1635
+ "a w",
1636
+ "Ġk n",
1637
+ "ak e",
1638
+ "a us",
1639
+ "Ġm ost",
1640
+ "Ġcon s",
1641
+ "Ġd uring",
1642
+ "ĠA s",
1643
+ "or th",
1644
+ "Ġn ew",
1645
+ "er ed",
1646
+ "il m",
1647
+ "v ed",
1648
+ "at t",
1649
+ "Ġon ly",
1650
+ "Ġ 9",
1651
+ "Ġd ec",
1652
+ "Ġ 8",
1653
+ "ic k",
1654
+ "Ġg ame",
1655
+ "on s",
1656
+ "u g",
1657
+ "Ġt r",
1658
+ "f t",
1659
+ "ot h",
1660
+ "o ok",
1661
+ "ĠM ar",
1662
+ "re at",
1663
+ "w ay",
1664
+ "Ġc an",
1665
+ "ol low",
1666
+ "ou th",
1667
+ "we en",
1668
+ "ĠE n",
1669
+ "Ġ19 9",
1670
+ "ter s",
1671
+ "Ġre l",
1672
+ "in d",
1673
+ "Ġab out",
1674
+ "Ġse ason",
1675
+ "Ġag ain",
1676
+ "r al",
1677
+ "Ġth ree",
1678
+ "ation al",
1679
+ "Ġu nder",
1680
+ "ul ar",
1681
+ "Ġm e",
1682
+ "Ġth an",
1683
+ "ĠC om",
1684
+ "ĠA r",
1685
+ "h ip",
1686
+ "o b",
1687
+ "Ġn e",
1688
+ "Ġbet ween",
1689
+ "Ġf l",
1690
+ "h n",
1691
+ "v e",
1692
+ "Ġch ar",
1693
+ "Ġc ol",
1694
+ "Ġrec ord",
1695
+ "i ew",
1696
+ "r on",
1697
+ "f ore",
1698
+ "Ġth rough",
1699
+ "is ion",
1700
+ "or n",
1701
+ "Ġ 00",
1702
+ "oc k",
1703
+ "Ġ ver",
1704
+ "Ġl ater",
1705
+ "Ġn um",
1706
+ "Ġe nd",
1707
+ "ol og",
1708
+ "am es",
1709
+ "Ġp os",
1710
+ "Ġw rit",
1711
+ "Ġpro du",
1712
+ "Ġwh ile",
1713
+ "Ġa ct",
1714
+ "Ġre le",
1715
+ "Ġf ilm",
1716
+ "is hed",
1717
+ "Ġp r",
1718
+ "an s",
1719
+ "Ġre g",
1720
+ "Ġfor m",
1721
+ "Ġas s",
1722
+ "ĠS e",
1723
+ "ur y",
1724
+ "t ed",
1725
+ "t s",
1726
+ "Ġm ade",
1727
+ "Ġsu b",
1728
+ "Ġp e",
1729
+ "Ġs o",
1730
+ "or ld",
1731
+ "Ġre t",
1732
+ "ĠN ew",
1733
+ "Ġsp ec",
1734
+ "Ġa cc",
1735
+ "Ġ qu",
1736
+ "Ġwhe re",
1737
+ "en er",
1738
+ "Ġm ov",
1739
+ "he s",
1740
+ "mer ic",
1741
+ "at ing",
1742
+ "Ġin ter",
1743
+ "ĠL e",
1744
+ "ĠA meric",
1745
+ "Ġ ra",
1746
+ "Ġs ome",
1747
+ "Ġc o",
1748
+ "Ġl ar",
1749
+ "Ġb u",
1750
+ "Ġde f",
1751
+ "b um",
1752
+ "Ġa c",
1753
+ "Ġm us",
1754
+ "Ġf ollow",
1755
+ "ĠA t",
1756
+ "in s",
1757
+ "iv ed",
1758
+ "if ic",
1759
+ "u al",
1760
+ "Ġa m",
1761
+ "Ġsu ch",
1762
+ "Ġsec ond",
1763
+ "i ke",
1764
+ "Ġf our",
1765
+ "Ġin d",
1766
+ "an n",
1767
+ "he n",
1768
+ "Ġus ed",
1769
+ "ĠR e",
1770
+ "ic s",
1771
+ "le ct",
1772
+ "Ġd ay",
1773
+ "i el",
1774
+ "il y",
1775
+ "ĠTh is",
1776
+ "Ġ 0",
1777
+ "Ġp ubl",
1778
+ "Ġc all",
1779
+ "ĠJ o",
1780
+ "l l",
1781
+ "Ġal bum",
1782
+ "Ġ00 0",
1783
+ "ran s",
1784
+ "Ġd o",
1785
+ "an y",
1786
+ "Ġbe fore",
1787
+ "ro s",
1788
+ "ĠS h",
1789
+ "Ġs y",
1790
+ "a id",
1791
+ "ĠEn g",
1792
+ "Ġbe ing",
1793
+ "Ġ1 0",
1794
+ "u c",
1795
+ "Ġe p",
1796
+ "Ġsu pp",
1797
+ "Ġthe re",
1798
+ "Ġyear s",
1799
+ "ar s",
1800
+ "ow ever",
1801
+ "Ġ ent",
1802
+ "if e",
1803
+ "Ġh igh",
1804
+ "Ġf ound",
1805
+ "ir d",
1806
+ "Ġn o",
1807
+ "Ġs et",
1808
+ "in es",
1809
+ "iv er",
1810
+ "i o",
1811
+ "ot her",
1812
+ "j ect",
1813
+ "Ġs ur",
1814
+ "a j",
1815
+ "t en",
1816
+ "Ġt ra",
1817
+ "Ġ1 2",
1818
+ "is ed",
1819
+ "it ies",
1820
+ "vel op",
1821
+ "Ġb l",
1822
+ "al e",
1823
+ "Ġser ies",
1824
+ "Ġl oc",
1825
+ "Ġnum ber",
1826
+ "Ġp res",
1827
+ "an e",
1828
+ "aus e",
1829
+ "od e",
1830
+ "e k",
1831
+ "t on",
1832
+ "ĠS c",
1833
+ "i er",
1834
+ "is e",
1835
+ "Ġse ver",
1836
+ "in ce",
1837
+ "Ġb oth",
1838
+ "an k",
1839
+ "ro w",
1840
+ "ire ct",
1841
+ "s on",
1842
+ "Ġthe n",
1843
+ "ĠB rit",
1844
+ "i et",
1845
+ "Ġ1 6",
1846
+ "Ġep is",
1847
+ "Ġinclud ing",
1848
+ "it s",
1849
+ "ig in",
1850
+ "p r",
1851
+ "Ġ /",
1852
+ "Ġagain st",
1853
+ "Ġw ell",
1854
+ "Ġbec ame",
1855
+ "Ġex p",
1856
+ "Ġkn own",
1857
+ "Ġt rans",
1858
+ "Ġchar ac",
1859
+ "ĠâĢ Ķ",
1860
+ "r am",
1861
+ "Ġb ack",
1862
+ "Ġad d",
1863
+ "Ġp op",
1864
+ "Ġg o",
1865
+ "ur ch",
1866
+ "Ġdes c",
1867
+ "Ġs ing",
1868
+ "iel d",
1869
+ "Ġper form",
1870
+ "ain ed",
1871
+ "Ġre ce",
1872
+ "id ent",
1873
+ "Ġe m",
1874
+ "er t",
1875
+ "u res",
1876
+ "Ġin v",
1877
+ "Ġde p",
1878
+ "Ġ19 8",
1879
+ "a ir",
1880
+ "er n",
1881
+ "at her",
1882
+ "f ul",
1883
+ "Ġ Z",
1884
+ "Ġm on",
1885
+ "Ġman y",
1886
+ "Ġm ain",
1887
+ "Ġst ud",
1888
+ "Ġl ong",
1889
+ "in n",
1890
+ "th ough",
1891
+ "u p",
1892
+ "o ol",
1893
+ "ĠUn ited",
1894
+ "l ed",
1895
+ "em ent",
1896
+ "Ġ1 5",
1897
+ "ow er",
1898
+ "ĠJo hn",
1899
+ "Ġo p",
1900
+ "Ġ1 1",
1901
+ "in ed",
1902
+ "Ġm et",
1903
+ "o ber",
1904
+ "le y",
1905
+ "Ġ1 7",
1906
+ "Ġcent ury",
1907
+ "Ġte am",
1908
+ "Ġ est",
1909
+ "ĠA fter",
1910
+ "y l",
1911
+ "Ġm in",
1912
+ "u ch",
1913
+ "ut e",
1914
+ "Ġde velop",
1915
+ "ĠS he",
1916
+ "i am",
1917
+ "Ġsh ow",
1918
+ "el f",
1919
+ "Ġre p",
1920
+ "Ġcon c",
1921
+ "at ive",
1922
+ "Ġc re",
1923
+ "over n",
1924
+ "a red",
1925
+ "Ġ19 4",
1926
+ "Ġor igin",
1927
+ "Ġs m",
1928
+ "iv ers",
1929
+ "a z",
1930
+ "Ġle ad",
1931
+ "Ġsever al",
1932
+ "a h",
1933
+ "Ġo b",
1934
+ "Ġre v",
1935
+ "Ġm ill",
1936
+ "er m"
1937
+ ]
1938
+ }
1939
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "[CLS]",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "do_lower_case": false,
21
+ "eos_token": {
22
+ "__type": "AddedToken",
23
+ "content": "[SEP]",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "errors": "replace",
30
+ "mask_token": {
31
+ "__type": "AddedToken",
32
+ "content": "[MASK]",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "model_max_length": 512,
39
+ "name_or_path": "temp/dummy/deberta/processors",
40
+ "pad_token": {
41
+ "__type": "AddedToken",
42
+ "content": "[PAD]",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sep_token": {
49
+ "__type": "AddedToken",
50
+ "content": "[SEP]",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "special_tokens_map_file": null,
57
+ "tokenizer_class": "DebertaTokenizer",
58
+ "unk_token": {
59
+ "__type": "AddedToken",
60
+ "content": "[UNK]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "vocab_type": "gpt2"
67
+ }
vocab.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 5,
3
+ "\"": 6,
4
+ "#": 7,
5
+ "$": 8,
6
+ "%": 9,
7
+ "&": 10,
8
+ "'": 11,
9
+ "(": 12,
10
+ ")": 13,
11
+ "*": 14,
12
+ "+": 15,
13
+ ",": 16,
14
+ ",@": 628,
15
+ "-": 17,
16
+ "-@": 343,
17
+ ".": 18,
18
+ ".@": 577,
19
+ "/": 19,
20
+ "0": 20,
21
+ "00": 399,
22
+ "1": 21,
23
+ "2": 22,
24
+ "3": 23,
25
+ "4": 24,
26
+ "5": 25,
27
+ "6": 26,
28
+ "7": 27,
29
+ "8": 28,
30
+ "9": 29,
31
+ ":": 30,
32
+ ";": 31,
33
+ "<": 32,
34
+ "=": 33,
35
+ ">": 34,
36
+ "?": 35,
37
+ "@": 36,
38
+ "A": 37,
39
+ "B": 38,
40
+ "C": 39,
41
+ "D": 40,
42
+ "E": 41,
43
+ "F": 42,
44
+ "G": 43,
45
+ "H": 44,
46
+ "I": 45,
47
+ "J": 46,
48
+ "K": 47,
49
+ "L": 48,
50
+ "M": 49,
51
+ "N": 50,
52
+ "O": 51,
53
+ "P": 52,
54
+ "Q": 53,
55
+ "R": 54,
56
+ "S": 55,
57
+ "T": 56,
58
+ "U": 57,
59
+ "V": 58,
60
+ "W": 59,
61
+ "X": 60,
62
+ "Y": 61,
63
+ "Z": 62,
64
+ "[": 63,
65
+ "[CLS]": 1,
66
+ "[MASK]": 4,
67
+ "[PAD]": 0,
68
+ "[SEP]": 2,
69
+ "[UNK]": 3,
70
+ "\\": 64,
71
+ "]": 65,
72
+ "^": 66,
73
+ "_": 67,
74
+ "`": 68,
75
+ "a": 69,
76
+ "ab": 439,
77
+ "able": 681,
78
+ "ac": 324,
79
+ "ace": 638,
80
+ "ach": 599,
81
+ "ack": 461,
82
+ "act": 605,
83
+ "ad": 323,
84
+ "ade": 601,
85
+ "ag": 397,
86
+ "age": 558,
87
+ "ah": 1019,
88
+ "aid": 877,
89
+ "ail": 718,
90
+ "ain": 401,
91
+ "ained": 957,
92
+ "air": 966,
93
+ "aj": 901,
94
+ "ak": 435,
95
+ "ake": 724,
96
+ "al": 289,
97
+ "ale": 909,
98
+ "all": 433,
99
+ "ally": 484,
100
+ "als": 704,
101
+ "am": 318,
102
+ "ame": 453,
103
+ "ames": 795,
104
+ "amp": 667,
105
+ "an": 287,
106
+ "ance": 634,
107
+ "and": 392,
108
+ "ane": 914,
109
+ "ang": 635,
110
+ "ank": 925,
111
+ "ann": 853,
112
+ "ans": 805,
113
+ "ant": 440,
114
+ "any": 872,
115
+ "ap": 489,
116
+ "ar": 284,
117
+ "ard": 431,
118
+ "are": 598,
119
+ "ared": 1011,
120
+ "ark": 639,
121
+ "ars": 886,
122
+ "art": 434,
123
+ "ary": 497,
124
+ "as": 293,
125
+ "ase": 693,
126
+ "ased": 687,
127
+ "ason": 666,
128
+ "ass": 548,
129
+ "ast": 471,
130
+ "at": 275,
131
+ "ate": 432,
132
+ "ated": 447,
133
+ "ater": 542,
134
+ "ates": 698,
135
+ "ath": 700,
136
+ "ather": 968,
137
+ "ating": 828,
138
+ "ation": 358,
139
+ "ational": 765,
140
+ "ations": 591,
141
+ "ative": 1008,
142
+ "att": 735,
143
+ "aus": 725,
144
+ "ause": 915,
145
+ "av": 403,
146
+ "ave": 496,
147
+ "aw": 722,
148
+ "ay": 355,
149
+ "az": 1016,
150
+ "b": 70,
151
+ "ber": 443,
152
+ "bum": 838,
153
+ "c": 71,
154
+ "cc": 505,
155
+ "ce": 365,
156
+ "ced": 652,
157
+ "ces": 680,
158
+ "ch": 376,
159
+ "ct": 388,
160
+ "ction": 624,
161
+ "d": 72,
162
+ "du": 568,
163
+ "e": 73,
164
+ "ear": 450,
165
+ "ec": 329,
166
+ "ect": 462,
167
+ "ed": 271,
168
+ "ek": 917,
169
+ "el": 315,
170
+ "elf": 1005,
171
+ "ell": 483,
172
+ "ely": 606,
173
+ "em": 370,
174
+ "ember": 643,
175
+ "ement": 982,
176
+ "en": 280,
177
+ "ence": 574,
178
+ "end": 550,
179
+ "ener": 824,
180
+ "ens": 646,
181
+ "ent": 309,
182
+ "ents": 685,
183
+ "ep": 716,
184
+ "er": 266,
185
+ "ere": 417,
186
+ "ered": 732,
187
+ "erm": 1023,
188
+ "ern": 967,
189
+ "ers": 387,
190
+ "ert": 961,
191
+ "es": 283,
192
+ "ess": 449,
193
+ "est": 395,
194
+ "et": 336,
195
+ "ever": 684,
196
+ "ew": 428,
197
+ "ey": 706,
198
+ "f": 74,
199
+ "fer": 719,
200
+ "ff": 532,
201
+ "fore": 784,
202
+ "form": 717,
203
+ "ft": 745,
204
+ "fter": 518,
205
+ "ful": 969,
206
+ "g": 75,
207
+ "gan": 710,
208
+ "ge": 478,
209
+ "gh": 445,
210
+ "h": 76,
211
+ "he": 262,
212
+ "hed": 525,
213
+ "hen": 854,
214
+ "her": 361,
215
+ "hes": 826,
216
+ "hip": 772,
217
+ "hn": 777,
218
+ "i": 77,
219
+ "ia": 494,
220
+ "ial": 520,
221
+ "iam": 1003,
222
+ "ian": 473,
223
+ "ib": 618,
224
+ "ic": 296,
225
+ "ical": 519,
226
+ "ice": 637,
227
+ "ich": 436,
228
+ "ick": 740,
229
+ "ics": 857,
230
+ "ict": 707,
231
+ "id": 338,
232
+ "ide": 513,
233
+ "ident": 959,
234
+ "ie": 545,
235
+ "ied": 673,
236
+ "iel": 860,
237
+ "ield": 955,
238
+ "ier": 920,
239
+ "ies": 413,
240
+ "iet": 931,
241
+ "iew": 782,
242
+ "if": 414,
243
+ "ife": 889,
244
+ "ific": 845,
245
+ "ig": 345,
246
+ "igh": 430,
247
+ "ight": 487,
248
+ "igin": 936,
249
+ "ign": 541,
250
+ "ike": 850,
251
+ "il": 310,
252
+ "ild": 694,
253
+ "ile": 582,
254
+ "ill": 418,
255
+ "ilm": 733,
256
+ "ily": 861,
257
+ "im": 340,
258
+ "ime": 572,
259
+ "in": 264,
260
+ "ince": 923,
261
+ "ind": 759,
262
+ "ine": 482,
263
+ "ined": 988,
264
+ "ines": 895,
265
+ "ing": 290,
266
+ "ings": 678,
267
+ "inn": 976,
268
+ "ins": 843,
269
+ "int": 661,
270
+ "io": 897,
271
+ "ion": 300,
272
+ "ions": 510,
273
+ "ious": 699,
274
+ "ip": 481,
275
+ "ir": 342,
276
+ "ird": 892,
277
+ "ire": 549,
278
+ "irect": 927,
279
+ "irst": 503,
280
+ "is": 282,
281
+ "ise": 921,
282
+ "ised": 905,
283
+ "ish": 491,
284
+ "ished": 803,
285
+ "ision": 786,
286
+ "iss": 705,
287
+ "ist": 400,
288
+ "it": 278,
289
+ "ite": 627,
290
+ "ited": 683,
291
+ "ith": 354,
292
+ "ities": 906,
293
+ "ition": 589,
294
+ "its": 935,
295
+ "ity": 446,
296
+ "iv": 339,
297
+ "ive": 455,
298
+ "ived": 844,
299
+ "iver": 896,
300
+ "ivers": 1015,
301
+ "ix": 692,
302
+ "iz": 596,
303
+ "j": 78,
304
+ "ject": 899,
305
+ "k": 79,
306
+ "ke": 626,
307
+ "l": 80,
308
+ "land": 575,
309
+ "ld": 419,
310
+ "le": 301,
311
+ "lect": 858,
312
+ "led": 981,
313
+ "les": 660,
314
+ "ley": 991,
315
+ "ll": 867,
316
+ "low": 565,
317
+ "lud": 600,
318
+ "ly": 331,
319
+ "m": 81,
320
+ "man": 647,
321
+ "ment": 475,
322
+ "mer": 562,
323
+ "meric": 827,
324
+ "n": 82,
325
+ "nd": 274,
326
+ "nder": 650,
327
+ "o": 83,
328
+ "ob": 773,
329
+ "ober": 990,
330
+ "oc": 442,
331
+ "ock": 789,
332
+ "od": 402,
333
+ "ode": 916,
334
+ "og": 499,
335
+ "ok": 537,
336
+ "ol": 337,
337
+ "old": 703,
338
+ "ollow": 752,
339
+ "olog": 794,
340
+ "om": 316,
341
+ "ome": 546,
342
+ "on": 267,
343
+ "ond": 564,
344
+ "one": 655,
345
+ "ong": 429,
346
+ "ons": 742,
347
+ "ood": 690,
348
+ "ook": 747,
349
+ "ool": 979,
350
+ "op": 410,
351
+ "or": 277,
352
+ "ord": 479,
353
+ "ore": 423,
354
+ "ork": 547,
355
+ "orld": 817,
356
+ "orm": 544,
357
+ "orn": 787,
358
+ "ors": 688,
359
+ "ort": 416,
360
+ "orth": 730,
361
+ "ory": 588,
362
+ "os": 383,
363
+ "ose": 674,
364
+ "ost": 486,
365
+ "ot": 346,
366
+ "oth": 746,
367
+ "other": 898,
368
+ "ou": 302,
369
+ "ough": 581,
370
+ "ould": 523,
371
+ "oun": 493,
372
+ "ound": 616,
373
+ "ount": 612,
374
+ "our": 485,
375
+ "ous": 502,
376
+ "out": 529,
377
+ "outh": 753,
378
+ "ov": 469,
379
+ "over": 619,
380
+ "overn": 1010,
381
+ "ow": 351,
382
+ "ower": 984,
383
+ "owever": 887,
384
+ "own": 536,
385
+ "oy": 689,
386
+ "p": 84,
387
+ "per": 540,
388
+ "ph": 642,
389
+ "pl": 587,
390
+ "port": 656,
391
+ "pp": 421,
392
+ "pr": 937,
393
+ "pt": 448,
394
+ "q": 85,
395
+ "qu": 454,
396
+ "r": 86,
397
+ "ra": 381,
398
+ "ral": 763,
399
+ "ram": 947,
400
+ "ran": 543,
401
+ "rans": 870,
402
+ "re": 269,
403
+ "reat": 749,
404
+ "red": 468,
405
+ "ree": 580,
406
+ "ren": 659,
407
+ "res": 412,
408
+ "ress": 633,
409
+ "ri": 404,
410
+ "rib": 675,
411
+ "ric": 590,
412
+ "rit": 480,
413
+ "ro": 295,
414
+ "rom": 391,
415
+ "ron": 783,
416
+ "rop": 702,
417
+ "ros": 874,
418
+ "rou": 456,
419
+ "rough": 651,
420
+ "round": 657,
421
+ "row": 926,
422
+ "ru": 509,
423
+ "ry": 555,
424
+ "s": 87,
425
+ "se": 466,
426
+ "so": 515,
427
+ "son": 928,
428
+ "st": 313,
429
+ "t": 88,
430
+ "te": 630,
431
+ "ted": 811,
432
+ "ten": 902,
433
+ "ter": 347,
434
+ "tern": 679,
435
+ "ters": 757,
436
+ "th": 366,
437
+ "ther": 488,
438
+ "though": 977,
439
+ "ton": 918,
440
+ "ts": 812,
441
+ "u": 89,
442
+ "ual": 846,
443
+ "ub": 530,
444
+ "ubl": 721,
445
+ "uc": 881,
446
+ "uch": 999,
447
+ "ud": 441,
448
+ "ue": 534,
449
+ "ug": 743,
450
+ "ul": 373,
451
+ "ular": 767,
452
+ "ult": 579,
453
+ "um": 394,
454
+ "un": 369,
455
+ "up": 978,
456
+ "ur": 327,
457
+ "urch": 952,
458
+ "ure": 514,
459
+ "ures": 962,
460
+ "uring": 586,
461
+ "urn": 631,
462
+ "ury": 810,
463
+ "us": 350,
464
+ "ust": 498,
465
+ "ut": 353,
466
+ "ute": 1000,
467
+ "v": 90,
468
+ "ve": 778,
469
+ "ved": 734,
470
+ "vel": 663,
471
+ "velop": 907,
472
+ "ver": 359,
473
+ "w": 91,
474
+ "ward": 670,
475
+ "way": 750,
476
+ "we": 658,
477
+ "ween": 754,
478
+ "wn": 641,
479
+ "wo": 528,
480
+ "x": 92,
481
+ "y": 93,
482
+ "yl": 997,
483
+ "z": 94,
484
+ "{": 95,
485
+ "|": 96,
486
+ "}": 97,
487
+ "~": 98,
488
+ "¡": 99,
489
+ "¢": 100,
490
+ "£": 101,
491
+ "¤": 102,
492
+ "¥": 103,
493
+ "¦": 104,
494
+ "§": 105,
495
+ "¨": 106,
496
+ "©": 107,
497
+ "ª": 108,
498
+ "«": 109,
499
+ "¬": 110,
500
+ "®": 111,
501
+ "¯": 112,
502
+ "°": 113,
503
+ "±": 114,
504
+ "²": 115,
505
+ "³": 116,
506
+ "´": 117,
507
+ "µ": 118,
508
+ "¶": 119,
509
+ "·": 120,
510
+ "¸": 121,
511
+ "¹": 122,
512
+ "º": 123,
513
+ "»": 124,
514
+ "¼": 125,
515
+ "½": 126,
516
+ "¾": 127,
517
+ "¿": 128,
518
+ "À": 129,
519
+ "Á": 130,
520
+ "Â": 131,
521
+ "Ã": 132,
522
+ "Ä": 133,
523
+ "Å": 134,
524
+ "Æ": 135,
525
+ "Ç": 136,
526
+ "È": 137,
527
+ "É": 138,
528
+ "Ê": 139,
529
+ "Ë": 140,
530
+ "Ì": 141,
531
+ "Í": 142,
532
+ "Î": 143,
533
+ "Ï": 144,
534
+ "Ð": 145,
535
+ "Ñ": 146,
536
+ "Ò": 147,
537
+ "Ó": 148,
538
+ "Ô": 149,
539
+ "Õ": 150,
540
+ "Ö": 151,
541
+ "×": 152,
542
+ "Ø": 153,
543
+ "Ù": 154,
544
+ "Ú": 155,
545
+ "Û": 156,
546
+ "Ü": 157,
547
+ "Ý": 158,
548
+ "Þ": 159,
549
+ "ß": 160,
550
+ "à": 161,
551
+ "á": 162,
552
+ "â": 163,
553
+ "ã": 164,
554
+ "ä": 165,
555
+ "å": 166,
556
+ "æ": 167,
557
+ "ç": 168,
558
+ "è": 169,
559
+ "é": 170,
560
+ "ê": 171,
561
+ "ë": 172,
562
+ "ì": 173,
563
+ "í": 174,
564
+ "î": 175,
565
+ "ï": 176,
566
+ "ð": 177,
567
+ "ñ": 178,
568
+ "ò": 179,
569
+ "ó": 180,
570
+ "ô": 181,
571
+ "õ": 182,
572
+ "ö": 183,
573
+ "÷": 184,
574
+ "ø": 185,
575
+ "ù": 186,
576
+ "ú": 187,
577
+ "û": 188,
578
+ "ü": 189,
579
+ "ý": 190,
580
+ "þ": 191,
581
+ "ÿ": 192,
582
+ "Ā": 193,
583
+ "ā": 194,
584
+ "Ă": 195,
585
+ "ă": 196,
586
+ "Ą": 197,
587
+ "ą": 198,
588
+ "Ć": 199,
589
+ "ć": 200,
590
+ "Ĉ": 201,
591
+ "ĉ": 202,
592
+ "Ċ": 203,
593
+ "ċ": 204,
594
+ "Č": 205,
595
+ "č": 206,
596
+ "Ď": 207,
597
+ "ď": 208,
598
+ "Đ": 209,
599
+ "đ": 210,
600
+ "Ē": 211,
601
+ "ē": 212,
602
+ "Ĕ": 213,
603
+ "ĕ": 214,
604
+ "Ė": 215,
605
+ "ė": 216,
606
+ "Ę": 217,
607
+ "ę": 218,
608
+ "Ě": 219,
609
+ "ě": 220,
610
+ "Ĝ": 221,
611
+ "ĝ": 222,
612
+ "Ğ": 223,
613
+ "ğ": 224,
614
+ "Ġ": 225,
615
+ "Ġ\"": 306,
616
+ "Ġ'": 335,
617
+ "Ġ(": 378,
618
+ "Ġ)": 377,
619
+ "Ġ,": 268,
620
+ "Ġ.": 276,
621
+ "Ġ/": 938,
622
+ "Ġ0": 863,
623
+ "Ġ00": 788,
624
+ "Ġ000": 869,
625
+ "Ġ1": 312,
626
+ "Ġ10": 880,
627
+ "Ġ11": 987,
628
+ "Ġ12": 904,
629
+ "Ġ15": 983,
630
+ "Ġ16": 932,
631
+ "Ġ17": 992,
632
+ "Ġ18": 576,
633
+ "Ġ19": 390,
634
+ "Ġ194": 1012,
635
+ "Ġ198": 965,
636
+ "Ġ199": 756,
637
+ "Ġ2": 356,
638
+ "Ġ20": 531,
639
+ "Ġ200": 500,
640
+ "Ġ201": 613,
641
+ "Ġ3": 495,
642
+ "Ġ4": 560,
643
+ "Ġ5": 569,
644
+ "Ġ6": 672,
645
+ "Ġ7": 696,
646
+ "Ġ8": 739,
647
+ "Ġ9": 737,
648
+ "Ġ:": 533,
649
+ "Ġ;": 507,
650
+ "Ġ=": 305,
651
+ "Ġ@": 322,
652
+ "Ġ@,@": 629,
653
+ "Ġ@-@": 344,
654
+ "Ġ@.@": 578,
655
+ "ĠA": 307,
656
+ "ĠAfter": 996,
657
+ "ĠAl": 584,
658
+ "ĠAmeric": 831,
659
+ "ĠAn": 695,
660
+ "ĠAr": 771,
661
+ "ĠAs": 729,
662
+ "ĠAt": 842,
663
+ "ĠB": 332,
664
+ "ĠBrit": 930,
665
+ "ĠC": 314,
666
+ "ĠCh": 492,
667
+ "ĠCom": 770,
668
+ "ĠD": 367,
669
+ "ĠE": 405,
670
+ "ĠEn": 755,
671
+ "ĠEng": 878,
672
+ "ĠF": 371,
673
+ "ĠG": 382,
674
+ "ĠH": 349,
675
+ "ĠHe": 559,
676
+ "ĠI": 333,
677
+ "ĠIn": 424,
678
+ "ĠIt": 597,
679
+ "ĠJ": 396,
680
+ "ĠJo": 866,
681
+ "ĠJohn": 985,
682
+ "ĠK": 451,
683
+ "ĠL": 384,
684
+ "ĠLe": 830,
685
+ "ĠM": 326,
686
+ "ĠMar": 748,
687
+ "ĠN": 385,
688
+ "ĠNew": 819,
689
+ "ĠO": 406,
690
+ "ĠOn": 662,
691
+ "ĠP": 357,
692
+ "ĠR": 364,
693
+ "ĠRe": 856,
694
+ "ĠS": 308,
695
+ "ĠSc": 919,
696
+ "ĠSe": 809,
697
+ "ĠSh": 875,
698
+ "ĠShe": 1002,
699
+ "ĠSt": 470,
700
+ "ĠT": 303,
701
+ "ĠTh": 567,
702
+ "ĠThe": 328,
703
+ "ĠThis": 862,
704
+ "ĠU": 464,
705
+ "ĠUn": 676,
706
+ "ĠUnited": 980,
707
+ "ĠV": 504,
708
+ "ĠW": 379,
709
+ "ĠY": 625,
710
+ "ĠZ": 970,
711
+ "Ġa": 263,
712
+ "Ġab": 552,
713
+ "Ġabout": 760,
714
+ "Ġac": 839,
715
+ "Ġacc": 821,
716
+ "Ġact": 800,
717
+ "Ġad": 553,
718
+ "Ġadd": 949,
719
+ "Ġafter": 617,
720
+ "Ġag": 609,
721
+ "Ġagain": 762,
722
+ "Ġagainst": 939,
723
+ "Ġal": 375,
724
+ "Ġalbum": 868,
725
+ "Ġall": 677,
726
+ "Ġalso": 538,
727
+ "Ġam": 847,
728
+ "Ġan": 393,
729
+ "Ġand": 292,
730
+ "Ġapp": 595,
731
+ "Ġar": 521,
732
+ "Ġare": 457,
733
+ "Ġas": 348,
734
+ "Ġass": 808,
735
+ "Ġat": 386,
736
+ "Ġatt": 636,
737
+ "Ġb": 286,
738
+ "Ġback": 948,
739
+ "Ġbe": 360,
740
+ "Ġbec": 594,
741
+ "Ġbecame": 941,
742
+ "Ġbeen": 571,
743
+ "Ġbefore": 873,
744
+ "Ġbeing": 879,
745
+ "Ġbet": 712,
746
+ "Ġbetween": 775,
747
+ "Ġbl": 908,
748
+ "Ġboth": 924,
749
+ "Ġbu": 836,
750
+ "Ġbut": 512,
751
+ "Ġby": 374,
752
+ "Ġc": 279,
753
+ "Ġcall": 865,
754
+ "Ġcan": 751,
755
+ "Ġcent": 691,
756
+ "Ġcentury": 993,
757
+ "Ġch": 437,
758
+ "Ġchar": 779,
759
+ "Ġcharac": 945,
760
+ "Ġcl": 539,
761
+ "Ġco": 834,
762
+ "Ġcol": 780,
763
+ "Ġcom": 408,
764
+ "Ġcomm": 664,
765
+ "Ġcomp": 508,
766
+ "Ġcon": 380,
767
+ "Ġconc": 1007,
768
+ "Ġcons": 727,
769
+ "Ġcont": 516,
770
+ "Ġcre": 1009,
771
+ "Ġd": 298,
772
+ "Ġday": 859,
773
+ "Ġde": 420,
774
+ "Ġdec": 738,
775
+ "Ġdef": 837,
776
+ "Ġdep": 964,
777
+ "Ġdes": 608,
778
+ "Ġdesc": 953,
779
+ "Ġdevelop": 1001,
780
+ "Ġdis": 592,
781
+ "Ġdo": 871,
782
+ "Ġduring": 728,
783
+ "Ġe": 320,
784
+ "Ġear": 720,
785
+ "Ġem": 960,
786
+ "Ġen": 621,
787
+ "Ġend": 793,
788
+ "Ġent": 888,
789
+ "Ġep": 882,
790
+ "Ġepis": 933,
791
+ "Ġest": 995,
792
+ "Ġev": 648,
793
+ "Ġex": 444,
794
+ "Ġexp": 942,
795
+ "Ġf": 281,
796
+ "Ġfe": 708,
797
+ "Ġfilm": 802,
798
+ "Ġfin": 653,
799
+ "Ġfirst": 522,
800
+ "Ġfl": 776,
801
+ "Ġfollow": 841,
802
+ "Ġfor": 341,
803
+ "Ġform": 807,
804
+ "Ġfound": 891,
805
+ "Ġfour": 851,
806
+ "Ġfrom": 407,
807
+ "Ġg": 334,
808
+ "Ġgame": 741,
809
+ "Ġgo": 951,
810
+ "Ġh": 299,
811
+ "Ġhad": 465,
812
+ "Ġhas": 566,
813
+ "Ġhave": 557,
814
+ "Ġhe": 398,
815
+ "Ġher": 535,
816
+ "Ġhigh": 890,
817
+ "Ġhim": 686,
818
+ "Ġhis": 409,
819
+ "Ġim": 623,
820
+ "Ġin": 288,
821
+ "Ġinc": 506,
822
+ "Ġinclud": 632,
823
+ "Ġincluding": 934,
824
+ "Ġind": 852,
825
+ "Ġint": 517,
826
+ "Ġinter": 829,
827
+ "Ġinto": 654,
828
+ "Ġinv": 963,
829
+ "Ġis": 368,
830
+ "Ġit": 389,
831
+ "Ġits": 524,
832
+ "Ġj": 603,
833
+ "Ġk": 460,
834
+ "Ġkn": 723,
835
+ "Ġknown": 943,
836
+ "Ġl": 317,
837
+ "Ġlar": 835,
838
+ "Ġlater": 791,
839
+ "Ġle": 476,
840
+ "Ġlead": 1017,
841
+ "Ġloc": 911,
842
+ "Ġlong": 975,
843
+ "Ġm": 297,
844
+ "Ġmade": 813,
845
+ "Ġmain": 973,
846
+ "Ġman": 604,
847
+ "Ġmany": 972,
848
+ "Ġme": 768,
849
+ "Ġmet": 989,
850
+ "Ġmill": 1022,
851
+ "Ġmin": 998,
852
+ "Ġmon": 971,
853
+ "Ġmore": 671,
854
+ "Ġmost": 726,
855
+ "Ġmov": 825,
856
+ "Ġmus": 840,
857
+ "Ġn": 321,
858
+ "Ġne": 774,
859
+ "Ġnew": 731,
860
+ "Ġno": 893,
861
+ "Ġnot": 477,
862
+ "Ġnum": 792,
863
+ "Ġnumber": 912,
864
+ "Ġo": 272,
865
+ "Ġob": 1020,
866
+ "Ġof": 285,
867
+ "Ġoff": 622,
868
+ "Ġon": 330,
869
+ "Ġone": 563,
870
+ "Ġonly": 736,
871
+ "Ġop": 986,
872
+ "Ġor": 438,
873
+ "Ġorigin": 1013,
874
+ "Ġother": 615,
875
+ "Ġout": 640,
876
+ "Ġover": 614,
877
+ "Ġp": 291,
878
+ "Ġpart": 607,
879
+ "Ġpe": 815,
880
+ "Ġper": 570,
881
+ "Ġperform": 956,
882
+ "Ġpl": 452,
883
+ "Ġplay": 602,
884
+ "Ġpo": 701,
885
+ "Ġpop": 950,
886
+ "Ġpos": 796,
887
+ "Ġpr": 804,
888
+ "Ġpre": 644,
889
+ "Ġpres": 913,
890
+ "Ġpro": 411,
891
+ "Ġprodu": 798,
892
+ "Ġpubl": 864,
893
+ "Ġqu": 822,
894
+ "Ġr": 425,
895
+ "Ġra": 832,
896
+ "Ġre": 304,
897
+ "Ġrec": 556,
898
+ "Ġrece": 958,
899
+ "Ġrecord": 781,
900
+ "Ġreg": 806,
901
+ "Ġrel": 758,
902
+ "Ġrele": 801,
903
+ "Ġrem": 715,
904
+ "Ġrep": 1006,
905
+ "Ġres": 551,
906
+ "Ġret": 818,
907
+ "Ġrev": 1021,
908
+ "Ġro": 561,
909
+ "Ġs": 270,
910
+ "Ġsc": 585,
911
+ "Ġse": 426,
912
+ "Ġseason": 761,
913
+ "Ġsec": 711,
914
+ "Ġsecond": 849,
915
+ "Ġser": 620,
916
+ "Ġseries": 910,
917
+ "Ġset": 894,
918
+ "Ġsever": 922,
919
+ "Ġseveral": 1018,
920
+ "Ġsh": 459,
921
+ "Ġshe": 665,
922
+ "Ġshow": 1004,
923
+ "Ġsing": 954,
924
+ "Ġsm": 1014,
925
+ "Ġso": 816,
926
+ "Ġsome": 833,
927
+ "Ġsong": 714,
928
+ "Ġsp": 472,
929
+ "Ġspec": 820,
930
+ "Ġst": 352,
931
+ "Ġstud": 974,
932
+ "Ġsu": 422,
933
+ "Ġsub": 814,
934
+ "Ġsuch": 848,
935
+ "Ġsupp": 883,
936
+ "Ġsur": 900,
937
+ "Ġsy": 876,
938
+ "Ġt": 261,
939
+ "Ġte": 668,
940
+ "Ġteam": 994,
941
+ "Ġth": 311,
942
+ "Ġthan": 769,
943
+ "Ġthat": 362,
944
+ "Ġthe": 265,
945
+ "Ġtheir": 511,
946
+ "Ġthem": 709,
947
+ "Ġthen": 929,
948
+ "Ġthere": 884,
949
+ "Ġthey": 610,
950
+ "Ġthis": 593,
951
+ "Ġthree": 764,
952
+ "Ġthrough": 785,
953
+ "Ġtime": 649,
954
+ "Ġto": 294,
955
+ "Ġtr": 744,
956
+ "Ġtra": 903,
957
+ "Ġtrans": 944,
958
+ "Ġtwo": 573,
959
+ "Ġu": 490,
960
+ "Ġun": 501,
961
+ "Ġunder": 766,
962
+ "Ġup": 645,
963
+ "Ġus": 554,
964
+ "Ġused": 855,
965
+ "Ġv": 415,
966
+ "Ġver": 790,
967
+ "Ġw": 273,
968
+ "Ġwas": 325,
969
+ "Ġwe": 682,
970
+ "Ġwell": 940,
971
+ "Ġwere": 427,
972
+ "Ġwh": 372,
973
+ "Ġwhe": 527,
974
+ "Ġwhen": 713,
975
+ "Ġwhere": 823,
976
+ "Ġwhich": 467,
977
+ "Ġwhile": 799,
978
+ "Ġwho": 583,
979
+ "Ġwith": 363,
980
+ "Ġwork": 697,
981
+ "Ġwould": 669,
982
+ "Ġwrit": 797,
983
+ "Ġy": 474,
984
+ "Ġyear": 611,
985
+ "Ġyears": 885,
986
+ "Ġâ": 458,
987
+ "ĠâĢ": 463,
988
+ "ĠâĢĵ": 526,
989
+ "ĠâĢĶ": 946,
990
+ "ĠĊ": 319,
991
+ "ġ": 226,
992
+ "Ģ": 227,
993
+ "ģ": 228,
994
+ "Ĥ": 229,
995
+ "ĥ": 230,
996
+ "Ħ": 231,
997
+ "ħ": 232,
998
+ "Ĩ": 233,
999
+ "ĩ": 234,
1000
+ "Ī": 235,
1001
+ "ī": 236,
1002
+ "Ĭ": 237,
1003
+ "ĭ": 238,
1004
+ "Į": 239,
1005
+ "į": 240,
1006
+ "İ": 241,
1007
+ "ı": 242,
1008
+ "IJ": 243,
1009
+ "ij": 244,
1010
+ "Ĵ": 245,
1011
+ "ĵ": 246,
1012
+ "Ķ": 247,
1013
+ "ķ": 248,
1014
+ "ĸ": 249,
1015
+ "Ĺ": 250,
1016
+ "ĺ": 251,
1017
+ "Ļ": 252,
1018
+ "ļ": 253,
1019
+ "Ľ": 254,
1020
+ "ľ": 255,
1021
+ "Ŀ": 256,
1022
+ "ŀ": 257,
1023
+ "Ł": 258,
1024
+ "ł": 259,
1025
+ "Ń": 260
1026
+ }