hf-transformers-bot commited on
Commit
f662eed
1 Parent(s): 3251f26

Upload tiny models for LayoutLMv3ForQuestionAnswering

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiny_models/layoutlmv3/LayoutLMv3ForQuestionAnswering",
3
+ "architectures": [
4
+ "LayoutLMv3ForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coordinate_size": 6,
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 36,
16
+ "initializer_range": 0.02,
17
+ "input_size": 4,
18
+ "intermediate_size": 37,
19
+ "layer_norm_eps": 1e-05,
20
+ "max_2d_position_embeddings": 1024,
21
+ "max_position_embeddings": 512,
22
+ "max_rel_2d_pos": 256,
23
+ "max_rel_pos": 128,
24
+ "model_type": "layoutlmv3",
25
+ "num_attention_heads": 4,
26
+ "num_channels": 3,
27
+ "num_hidden_layers": 3,
28
+ "pad_token_id": 1,
29
+ "patch_size": 2,
30
+ "rel_2d_pos_bins": 64,
31
+ "rel_pos_bins": 32,
32
+ "shape_size": 6,
33
+ "text_embed": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.28.0.dev0",
36
+ "type_vocab_size": 16,
37
+ "visual_embed": true,
38
+ "vocab_size": 1024
39
+ }
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
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "LayoutLMv3FeatureExtractor",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "ocr_lang": null,
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdabc8a5324a0b9f957bf9d9c25fab238c6b9c34537dbb1a40e10896f47b233
3
+ size 458892
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
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": "</s>",
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 sha256:70450d3a809079457455dcd0e7328adc0520781f25cc45d2d08a39c5d6f6c3e4
3
+ size 534648
tokenizer.json ADDED
@@ -0,0 +1,1877 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<s>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
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": true,
56
+ "trim_offsets": true,
57
+ "use_regex": true
58
+ },
59
+ "post_processor": {
60
+ "type": "RobertaProcessing",
61
+ "sep": [
62
+ "</s>",
63
+ 2
64
+ ],
65
+ "cls": [
66
+ "<s>",
67
+ 0
68
+ ],
69
+ "trim_offsets": true,
70
+ "add_prefix_space": true
71
+ },
72
+ "decoder": {
73
+ "type": "ByteLevel",
74
+ "add_prefix_space": true,
75
+ "trim_offsets": true,
76
+ "use_regex": true
77
+ },
78
+ "model": {
79
+ "type": "BPE",
80
+ "dropout": null,
81
+ "unk_token": null,
82
+ "continuing_subword_prefix": "",
83
+ "end_of_word_suffix": "",
84
+ "fuse_unk": false,
85
+ "vocab": {
86
+ "<s>": 0,
87
+ "<pad>": 1,
88
+ "</s>": 2,
89
+ "<unk>": 3,
90
+ "<mask>": 4,
91
+ "!": 5,
92
+ "\"": 6,
93
+ "#": 7,
94
+ "$": 8,
95
+ "%": 9,
96
+ "&": 10,
97
+ "'": 11,
98
+ "(": 12,
99
+ ")": 13,
100
+ "*": 14,
101
+ "+": 15,
102
+ ",": 16,
103
+ "-": 17,
104
+ ".": 18,
105
+ "/": 19,
106
+ "0": 20,
107
+ "1": 21,
108
+ "2": 22,
109
+ "3": 23,
110
+ "4": 24,
111
+ "5": 25,
112
+ "6": 26,
113
+ "7": 27,
114
+ "8": 28,
115
+ "9": 29,
116
+ ":": 30,
117
+ ";": 31,
118
+ "<": 32,
119
+ "=": 33,
120
+ ">": 34,
121
+ "?": 35,
122
+ "@": 36,
123
+ "A": 37,
124
+ "B": 38,
125
+ "C": 39,
126
+ "D": 40,
127
+ "E": 41,
128
+ "F": 42,
129
+ "G": 43,
130
+ "H": 44,
131
+ "I": 45,
132
+ "J": 46,
133
+ "K": 47,
134
+ "L": 48,
135
+ "M": 49,
136
+ "N": 50,
137
+ "O": 51,
138
+ "P": 52,
139
+ "Q": 53,
140
+ "R": 54,
141
+ "S": 55,
142
+ "T": 56,
143
+ "U": 57,
144
+ "V": 58,
145
+ "W": 59,
146
+ "X": 60,
147
+ "Y": 61,
148
+ "Z": 62,
149
+ "[": 63,
150
+ "\\": 64,
151
+ "]": 65,
152
+ "^": 66,
153
+ "_": 67,
154
+ "`": 68,
155
+ "a": 69,
156
+ "b": 70,
157
+ "c": 71,
158
+ "d": 72,
159
+ "e": 73,
160
+ "f": 74,
161
+ "g": 75,
162
+ "h": 76,
163
+ "i": 77,
164
+ "j": 78,
165
+ "k": 79,
166
+ "l": 80,
167
+ "m": 81,
168
+ "n": 82,
169
+ "o": 83,
170
+ "p": 84,
171
+ "q": 85,
172
+ "r": 86,
173
+ "s": 87,
174
+ "t": 88,
175
+ "u": 89,
176
+ "v": 90,
177
+ "w": 91,
178
+ "x": 92,
179
+ "y": 93,
180
+ "z": 94,
181
+ "{": 95,
182
+ "|": 96,
183
+ "}": 97,
184
+ "~": 98,
185
+ "¡": 99,
186
+ "¢": 100,
187
+ "£": 101,
188
+ "¤": 102,
189
+ "¥": 103,
190
+ "¦": 104,
191
+ "§": 105,
192
+ "¨": 106,
193
+ "©": 107,
194
+ "ª": 108,
195
+ "«": 109,
196
+ "¬": 110,
197
+ "®": 111,
198
+ "¯": 112,
199
+ "°": 113,
200
+ "±": 114,
201
+ "²": 115,
202
+ "³": 116,
203
+ "´": 117,
204
+ "µ": 118,
205
+ "¶": 119,
206
+ "·": 120,
207
+ "¸": 121,
208
+ "¹": 122,
209
+ "º": 123,
210
+ "»": 124,
211
+ "¼": 125,
212
+ "½": 126,
213
+ "¾": 127,
214
+ "¿": 128,
215
+ "À": 129,
216
+ "Á": 130,
217
+ "Â": 131,
218
+ "Ã": 132,
219
+ "Ä": 133,
220
+ "Å": 134,
221
+ "Æ": 135,
222
+ "Ç": 136,
223
+ "È": 137,
224
+ "É": 138,
225
+ "Ê": 139,
226
+ "Ë": 140,
227
+ "Ì": 141,
228
+ "Í": 142,
229
+ "Î": 143,
230
+ "Ï": 144,
231
+ "Ð": 145,
232
+ "Ñ": 146,
233
+ "Ò": 147,
234
+ "Ó": 148,
235
+ "Ô": 149,
236
+ "Õ": 150,
237
+ "Ö": 151,
238
+ "×": 152,
239
+ "Ø": 153,
240
+ "Ù": 154,
241
+ "Ú": 155,
242
+ "Û": 156,
243
+ "Ü": 157,
244
+ "Ý": 158,
245
+ "Þ": 159,
246
+ "ß": 160,
247
+ "à": 161,
248
+ "á": 162,
249
+ "â": 163,
250
+ "ã": 164,
251
+ "ä": 165,
252
+ "å": 166,
253
+ "æ": 167,
254
+ "ç": 168,
255
+ "è": 169,
256
+ "é": 170,
257
+ "ê": 171,
258
+ "ë": 172,
259
+ "ì": 173,
260
+ "í": 174,
261
+ "î": 175,
262
+ "ï": 176,
263
+ "ð": 177,
264
+ "ñ": 178,
265
+ "ò": 179,
266
+ "ó": 180,
267
+ "ô": 181,
268
+ "õ": 182,
269
+ "ö": 183,
270
+ "÷": 184,
271
+ "ø": 185,
272
+ "ù": 186,
273
+ "ú": 187,
274
+ "û": 188,
275
+ "ü": 189,
276
+ "ý": 190,
277
+ "þ": 191,
278
+ "ÿ": 192,
279
+ "Ā": 193,
280
+ "ā": 194,
281
+ "Ă": 195,
282
+ "ă": 196,
283
+ "Ą": 197,
284
+ "ą": 198,
285
+ "Ć": 199,
286
+ "ć": 200,
287
+ "Ĉ": 201,
288
+ "ĉ": 202,
289
+ "Ċ": 203,
290
+ "ċ": 204,
291
+ "Č": 205,
292
+ "č": 206,
293
+ "Ď": 207,
294
+ "ď": 208,
295
+ "Đ": 209,
296
+ "đ": 210,
297
+ "Ē": 211,
298
+ "ē": 212,
299
+ "Ĕ": 213,
300
+ "ĕ": 214,
301
+ "Ė": 215,
302
+ "ė": 216,
303
+ "Ę": 217,
304
+ "ę": 218,
305
+ "Ě": 219,
306
+ "ě": 220,
307
+ "Ĝ": 221,
308
+ "ĝ": 222,
309
+ "Ğ": 223,
310
+ "ğ": 224,
311
+ "Ġ": 225,
312
+ "ġ": 226,
313
+ "Ģ": 227,
314
+ "ģ": 228,
315
+ "Ĥ": 229,
316
+ "ĥ": 230,
317
+ "Ħ": 231,
318
+ "ħ": 232,
319
+ "Ĩ": 233,
320
+ "ĩ": 234,
321
+ "Ī": 235,
322
+ "ī": 236,
323
+ "Ĭ": 237,
324
+ "ĭ": 238,
325
+ "Į": 239,
326
+ "į": 240,
327
+ "İ": 241,
328
+ "ı": 242,
329
+ "IJ": 243,
330
+ "ij": 244,
331
+ "Ĵ": 245,
332
+ "ĵ": 246,
333
+ "Ķ": 247,
334
+ "ķ": 248,
335
+ "ĸ": 249,
336
+ "Ĺ": 250,
337
+ "ĺ": 251,
338
+ "Ļ": 252,
339
+ "ļ": 253,
340
+ "Ľ": 254,
341
+ "ľ": 255,
342
+ "Ŀ": 256,
343
+ "ŀ": 257,
344
+ "Ł": 258,
345
+ "ł": 259,
346
+ "Ń": 260,
347
+ "Ġt": 261,
348
+ "he": 262,
349
+ "Ġa": 263,
350
+ "in": 264,
351
+ "Ġthe": 265,
352
+ "er": 266,
353
+ "on": 267,
354
+ "Ġ,": 268,
355
+ "re": 269,
356
+ "Ġs": 270,
357
+ "ed": 271,
358
+ "Ġo": 272,
359
+ "Ġw": 273,
360
+ "nd": 274,
361
+ "at": 275,
362
+ "Ġ.": 276,
363
+ "or": 277,
364
+ "it": 278,
365
+ "Ġc": 279,
366
+ "en": 280,
367
+ "Ġf": 281,
368
+ "is": 282,
369
+ "es": 283,
370
+ "ar": 284,
371
+ "Ġof": 285,
372
+ "Ġb": 286,
373
+ "an": 287,
374
+ "Ġin": 288,
375
+ "al": 289,
376
+ "ing": 290,
377
+ "Ġp": 291,
378
+ "Ġand": 292,
379
+ "as": 293,
380
+ "Ġto": 294,
381
+ "ro": 295,
382
+ "ic": 296,
383
+ "Ġm": 297,
384
+ "Ġd": 298,
385
+ "Ġh": 299,
386
+ "ion": 300,
387
+ "le": 301,
388
+ "ou": 302,
389
+ "ĠT": 303,
390
+ "Ġre": 304,
391
+ "Ġ=": 305,
392
+ "Ġ\"": 306,
393
+ "ĠA": 307,
394
+ "ĠS": 308,
395
+ "ent": 309,
396
+ "il": 310,
397
+ "Ġth": 311,
398
+ "Ġ1": 312,
399
+ "st": 313,
400
+ "ĠC": 314,
401
+ "el": 315,
402
+ "om": 316,
403
+ "Ġl": 317,
404
+ "am": 318,
405
+ "ĠĊ": 319,
406
+ "Ġe": 320,
407
+ "Ġn": 321,
408
+ "Ġ@": 322,
409
+ "ad": 323,
410
+ "ac": 324,
411
+ "Ġwas": 325,
412
+ "ĠM": 326,
413
+ "ur": 327,
414
+ "ĠThe": 328,
415
+ "ec": 329,
416
+ "Ġon": 330,
417
+ "ly": 331,
418
+ "ĠB": 332,
419
+ "ĠI": 333,
420
+ "Ġg": 334,
421
+ "Ġ'": 335,
422
+ "et": 336,
423
+ "ol": 337,
424
+ "id": 338,
425
+ "iv": 339,
426
+ "im": 340,
427
+ "Ġfor": 341,
428
+ "ir": 342,
429
+ "-@": 343,
430
+ "Ġ@-@": 344,
431
+ "ig": 345,
432
+ "ot": 346,
433
+ "ter": 347,
434
+ "Ġas": 348,
435
+ "ĠH": 349,
436
+ "us": 350,
437
+ "ow": 351,
438
+ "Ġst": 352,
439
+ "ut": 353,
440
+ "ith": 354,
441
+ "ay": 355,
442
+ "Ġ2": 356,
443
+ "ĠP": 357,
444
+ "ation": 358,
445
+ "ver": 359,
446
+ "Ġbe": 360,
447
+ "her": 361,
448
+ "Ġthat": 362,
449
+ "Ġwith": 363,
450
+ "ĠR": 364,
451
+ "ce": 365,
452
+ "th": 366,
453
+ "ĠD": 367,
454
+ "Ġis": 368,
455
+ "un": 369,
456
+ "em": 370,
457
+ "ĠF": 371,
458
+ "Ġwh": 372,
459
+ "ul": 373,
460
+ "Ġby": 374,
461
+ "Ġal": 375,
462
+ "ch": 376,
463
+ "Ġ)": 377,
464
+ "Ġ(": 378,
465
+ "ĠW": 379,
466
+ "Ġcon": 380,
467
+ "ra": 381,
468
+ "ĠG": 382,
469
+ "os": 383,
470
+ "ĠL": 384,
471
+ "ĠN": 385,
472
+ "Ġat": 386,
473
+ "ers": 387,
474
+ "ct": 388,
475
+ "Ġit": 389,
476
+ "Ġ19": 390,
477
+ "rom": 391,
478
+ "and": 392,
479
+ "Ġan": 393,
480
+ "um": 394,
481
+ "est": 395,
482
+ "ĠJ": 396,
483
+ "ag": 397,
484
+ "Ġhe": 398,
485
+ "00": 399,
486
+ "ist": 400,
487
+ "ain": 401,
488
+ "od": 402,
489
+ "av": 403,
490
+ "ri": 404,
491
+ "ĠE": 405,
492
+ "ĠO": 406,
493
+ "Ġfrom": 407,
494
+ "Ġcom": 408,
495
+ "Ġhis": 409,
496
+ "op": 410,
497
+ "Ġpro": 411,
498
+ "res": 412,
499
+ "ies": 413,
500
+ "if": 414,
501
+ "Ġv": 415,
502
+ "ort": 416,
503
+ "ere": 417,
504
+ "ill": 418,
505
+ "ld": 419,
506
+ "Ġde": 420,
507
+ "pp": 421,
508
+ "Ġsu": 422,
509
+ "ore": 423,
510
+ "ĠIn": 424,
511
+ "Ġr": 425,
512
+ "Ġse": 426,
513
+ "Ġwere": 427,
514
+ "ew": 428,
515
+ "ong": 429,
516
+ "igh": 430,
517
+ "ard": 431,
518
+ "ate": 432,
519
+ "all": 433,
520
+ "art": 434,
521
+ "ak": 435,
522
+ "ich": 436,
523
+ "Ġch": 437,
524
+ "Ġor": 438,
525
+ "ab": 439,
526
+ "ant": 440,
527
+ "ud": 441,
528
+ "oc": 442,
529
+ "ber": 443,
530
+ "Ġex": 444,
531
+ "gh": 445,
532
+ "ity": 446,
533
+ "ated": 447,
534
+ "pt": 448,
535
+ "ess": 449,
536
+ "ear": 450,
537
+ "ĠK": 451,
538
+ "Ġpl": 452,
539
+ "ame": 453,
540
+ "qu": 454,
541
+ "ive": 455,
542
+ "rou": 456,
543
+ "Ġare": 457,
544
+ "Ġâ": 458,
545
+ "Ġsh": 459,
546
+ "Ġk": 460,
547
+ "ack": 461,
548
+ "ect": 462,
549
+ "ĠâĢ": 463,
550
+ "ĠU": 464,
551
+ "Ġhad": 465,
552
+ "se": 466,
553
+ "Ġwhich": 467,
554
+ "red": 468,
555
+ "ov": 469,
556
+ "ĠSt": 470,
557
+ "ast": 471,
558
+ "Ġsp": 472,
559
+ "ian": 473,
560
+ "Ġy": 474,
561
+ "ment": 475,
562
+ "Ġle": 476,
563
+ "Ġnot": 477,
564
+ "ge": 478,
565
+ "ord": 479,
566
+ "rit": 480,
567
+ "ip": 481,
568
+ "ine": 482,
569
+ "ell": 483,
570
+ "ally": 484,
571
+ "our": 485,
572
+ "ost": 486,
573
+ "ight": 487,
574
+ "ther": 488,
575
+ "ap": 489,
576
+ "Ġu": 490,
577
+ "ish": 491,
578
+ "ĠCh": 492,
579
+ "oun": 493,
580
+ "ia": 494,
581
+ "Ġ3": 495,
582
+ "ave": 496,
583
+ "ary": 497,
584
+ "ust": 498,
585
+ "og": 499,
586
+ "Ġ200": 500,
587
+ "Ġun": 501,
588
+ "ous": 502,
589
+ "irst": 503,
590
+ "ĠV": 504,
591
+ "cc": 505,
592
+ "Ġinc": 506,
593
+ "Ġ;": 507,
594
+ "Ġcomp": 508,
595
+ "ru": 509,
596
+ "ions": 510,
597
+ "Ġtheir": 511,
598
+ "Ġbut": 512,
599
+ "ide": 513,
600
+ "ure": 514,
601
+ "so": 515,
602
+ "Ġcont": 516,
603
+ "Ġint": 517,
604
+ "fter": 518,
605
+ "ical": 519,
606
+ "ial": 520,
607
+ "Ġar": 521,
608
+ "Ġfirst": 522,
609
+ "ould": 523,
610
+ "Ġits": 524,
611
+ "hed": 525,
612
+ "ĠâĢĵ": 526,
613
+ "Ġwhe": 527,
614
+ "wo": 528,
615
+ "out": 529,
616
+ "ub": 530,
617
+ "Ġ20": 531,
618
+ "ff": 532,
619
+ "Ġ:": 533,
620
+ "ue": 534,
621
+ "Ġher": 535,
622
+ "own": 536,
623
+ "ok": 537,
624
+ "Ġalso": 538,
625
+ "Ġcl": 539,
626
+ "per": 540,
627
+ "ign": 541,
628
+ "ater": 542,
629
+ "ran": 543,
630
+ "orm": 544,
631
+ "ie": 545,
632
+ "ome": 546,
633
+ "ork": 547,
634
+ "ass": 548,
635
+ "ire": 549,
636
+ "end": 550,
637
+ "Ġres": 551,
638
+ "Ġab": 552,
639
+ "Ġad": 553,
640
+ "Ġus": 554,
641
+ "ry": 555,
642
+ "Ġrec": 556,
643
+ "Ġhave": 557,
644
+ "age": 558,
645
+ "ĠHe": 559,
646
+ "Ġ4": 560,
647
+ "Ġro": 561,
648
+ "mer": 562,
649
+ "Ġone": 563,
650
+ "ond": 564,
651
+ "low": 565,
652
+ "Ġhas": 566,
653
+ "ĠTh": 567,
654
+ "du": 568,
655
+ "Ġ5": 569,
656
+ "Ġper": 570,
657
+ "Ġbeen": 571,
658
+ "ime": 572,
659
+ "Ġtwo": 573,
660
+ "ence": 574,
661
+ "land": 575,
662
+ "Ġ18": 576,
663
+ ".@": 577,
664
+ "Ġ@.@": 578,
665
+ "ult": 579,
666
+ "ree": 580,
667
+ "ough": 581,
668
+ "ile": 582,
669
+ "Ġwho": 583,
670
+ "ĠAl": 584,
671
+ "Ġsc": 585,
672
+ "uring": 586,
673
+ "pl": 587,
674
+ "ory": 588,
675
+ "ition": 589,
676
+ "ric": 590,
677
+ "ations": 591,
678
+ "Ġdis": 592,
679
+ "Ġthis": 593,
680
+ "Ġbec": 594,
681
+ "Ġapp": 595,
682
+ "iz": 596,
683
+ "ĠIt": 597,
684
+ "are": 598,
685
+ "ach": 599,
686
+ "lud": 600,
687
+ "ade": 601,
688
+ "Ġplay": 602,
689
+ "Ġj": 603,
690
+ "Ġman": 604,
691
+ "act": 605,
692
+ "ely": 606,
693
+ "Ġpart": 607,
694
+ "Ġdes": 608,
695
+ "Ġag": 609,
696
+ "Ġthey": 610,
697
+ "Ġyear": 611,
698
+ "ount": 612,
699
+ "Ġ201": 613,
700
+ "Ġover": 614,
701
+ "Ġother": 615,
702
+ "ound": 616,
703
+ "Ġafter": 617,
704
+ "ib": 618,
705
+ "over": 619,
706
+ "Ġser": 620,
707
+ "Ġen": 621,
708
+ "Ġoff": 622,
709
+ "Ġim": 623,
710
+ "ction": 624,
711
+ "ĠY": 625,
712
+ "ke": 626,
713
+ "ite": 627,
714
+ ",@": 628,
715
+ "Ġ@,@": 629,
716
+ "te": 630,
717
+ "urn": 631,
718
+ "Ġinclud": 632,
719
+ "ress": 633,
720
+ "ance": 634,
721
+ "ang": 635,
722
+ "Ġatt": 636,
723
+ "ice": 637,
724
+ "ace": 638,
725
+ "ark": 639,
726
+ "Ġout": 640,
727
+ "wn": 641,
728
+ "ph": 642,
729
+ "ember": 643,
730
+ "Ġpre": 644,
731
+ "Ġup": 645,
732
+ "ens": 646,
733
+ "man": 647,
734
+ "Ġev": 648,
735
+ "Ġtime": 649,
736
+ "nder": 650,
737
+ "rough": 651,
738
+ "ced": 652,
739
+ "Ġfin": 653,
740
+ "Ġinto": 654,
741
+ "one": 655,
742
+ "port": 656,
743
+ "round": 657,
744
+ "we": 658,
745
+ "ren": 659,
746
+ "les": 660,
747
+ "int": 661,
748
+ "ĠOn": 662,
749
+ "vel": 663,
750
+ "Ġcomm": 664,
751
+ "Ġshe": 665,
752
+ "ason": 666,
753
+ "amp": 667,
754
+ "Ġte": 668,
755
+ "Ġwould": 669,
756
+ "ward": 670,
757
+ "Ġmore": 671,
758
+ "Ġ6": 672,
759
+ "ied": 673,
760
+ "ose": 674,
761
+ "rib": 675,
762
+ "ĠUn": 676,
763
+ "Ġall": 677,
764
+ "ings": 678,
765
+ "tern": 679,
766
+ "ces": 680,
767
+ "able": 681,
768
+ "Ġwe": 682,
769
+ "ited": 683,
770
+ "ever": 684,
771
+ "ents": 685,
772
+ "Ġhim": 686,
773
+ "ased": 687,
774
+ "ors": 688,
775
+ "oy": 689,
776
+ "ood": 690,
777
+ "Ġcent": 691,
778
+ "ix": 692,
779
+ "ase": 693,
780
+ "ild": 694,
781
+ "ĠAn": 695,
782
+ "Ġ7": 696,
783
+ "Ġwork": 697,
784
+ "ates": 698,
785
+ "ious": 699,
786
+ "ath": 700,
787
+ "Ġpo": 701,
788
+ "rop": 702,
789
+ "old": 703,
790
+ "als": 704,
791
+ "iss": 705,
792
+ "ey": 706,
793
+ "ict": 707,
794
+ "Ġfe": 708,
795
+ "Ġthem": 709,
796
+ "gan": 710,
797
+ "Ġsec": 711,
798
+ "Ġbet": 712,
799
+ "Ġwhen": 713,
800
+ "Ġsong": 714,
801
+ "Ġrem": 715,
802
+ "ep": 716,
803
+ "form": 717,
804
+ "ail": 718,
805
+ "fer": 719,
806
+ "Ġear": 720,
807
+ "ubl": 721,
808
+ "aw": 722,
809
+ "Ġkn": 723,
810
+ "ake": 724,
811
+ "aus": 725,
812
+ "Ġmost": 726,
813
+ "Ġcons": 727,
814
+ "Ġduring": 728,
815
+ "ĠAs": 729,
816
+ "orth": 730,
817
+ "Ġnew": 731,
818
+ "ered": 732,
819
+ "ilm": 733,
820
+ "ved": 734,
821
+ "att": 735,
822
+ "Ġonly": 736,
823
+ "Ġ9": 737,
824
+ "Ġdec": 738,
825
+ "Ġ8": 739,
826
+ "ick": 740,
827
+ "Ġgame": 741,
828
+ "ons": 742,
829
+ "ug": 743,
830
+ "Ġtr": 744,
831
+ "ft": 745,
832
+ "oth": 746,
833
+ "ook": 747,
834
+ "ĠMar": 748,
835
+ "reat": 749,
836
+ "way": 750,
837
+ "Ġcan": 751,
838
+ "ollow": 752,
839
+ "outh": 753,
840
+ "ween": 754,
841
+ "ĠEn": 755,
842
+ "Ġ199": 756,
843
+ "ters": 757,
844
+ "Ġrel": 758,
845
+ "ind": 759,
846
+ "Ġabout": 760,
847
+ "Ġseason": 761,
848
+ "Ġagain": 762,
849
+ "ral": 763,
850
+ "Ġthree": 764,
851
+ "ational": 765,
852
+ "Ġunder": 766,
853
+ "ular": 767,
854
+ "Ġme": 768,
855
+ "Ġthan": 769,
856
+ "ĠCom": 770,
857
+ "ĠAr": 771,
858
+ "hip": 772,
859
+ "ob": 773,
860
+ "Ġne": 774,
861
+ "Ġbetween": 775,
862
+ "Ġfl": 776,
863
+ "hn": 777,
864
+ "ve": 778,
865
+ "Ġchar": 779,
866
+ "Ġcol": 780,
867
+ "Ġrecord": 781,
868
+ "iew": 782,
869
+ "ron": 783,
870
+ "fore": 784,
871
+ "Ġthrough": 785,
872
+ "ision": 786,
873
+ "orn": 787,
874
+ "Ġ00": 788,
875
+ "ock": 789,
876
+ "Ġver": 790,
877
+ "Ġlater": 791,
878
+ "Ġnum": 792,
879
+ "Ġend": 793,
880
+ "olog": 794,
881
+ "ames": 795,
882
+ "Ġpos": 796,
883
+ "Ġwrit": 797,
884
+ "Ġprodu": 798,
885
+ "Ġwhile": 799,
886
+ "Ġact": 800,
887
+ "Ġrele": 801,
888
+ "Ġfilm": 802,
889
+ "ished": 803,
890
+ "Ġpr": 804,
891
+ "ans": 805,
892
+ "Ġreg": 806,
893
+ "Ġform": 807,
894
+ "Ġass": 808,
895
+ "ĠSe": 809,
896
+ "ury": 810,
897
+ "ted": 811,
898
+ "ts": 812,
899
+ "Ġmade": 813,
900
+ "Ġsub": 814,
901
+ "Ġpe": 815,
902
+ "Ġso": 816,
903
+ "orld": 817,
904
+ "Ġret": 818,
905
+ "ĠNew": 819,
906
+ "Ġspec": 820,
907
+ "Ġacc": 821,
908
+ "Ġqu": 822,
909
+ "Ġwhere": 823,
910
+ "ener": 824,
911
+ "Ġmov": 825,
912
+ "hes": 826,
913
+ "meric": 827,
914
+ "ating": 828,
915
+ "Ġinter": 829,
916
+ "ĠLe": 830,
917
+ "ĠAmeric": 831,
918
+ "Ġra": 832,
919
+ "Ġsome": 833,
920
+ "Ġco": 834,
921
+ "Ġlar": 835,
922
+ "Ġbu": 836,
923
+ "Ġdef": 837,
924
+ "bum": 838,
925
+ "Ġac": 839,
926
+ "Ġmus": 840,
927
+ "Ġfollow": 841,
928
+ "ĠAt": 842,
929
+ "ins": 843,
930
+ "ived": 844,
931
+ "ific": 845,
932
+ "ual": 846,
933
+ "Ġam": 847,
934
+ "Ġsuch": 848,
935
+ "Ġsecond": 849,
936
+ "ike": 850,
937
+ "Ġfour": 851,
938
+ "Ġind": 852,
939
+ "ann": 853,
940
+ "hen": 854,
941
+ "Ġused": 855,
942
+ "ĠRe": 856,
943
+ "ics": 857,
944
+ "lect": 858,
945
+ "Ġday": 859,
946
+ "iel": 860,
947
+ "ily": 861,
948
+ "ĠThis": 862,
949
+ "Ġ0": 863,
950
+ "Ġpubl": 864,
951
+ "Ġcall": 865,
952
+ "ĠJo": 866,
953
+ "ll": 867,
954
+ "Ġalbum": 868,
955
+ "Ġ000": 869,
956
+ "rans": 870,
957
+ "Ġdo": 871,
958
+ "any": 872,
959
+ "Ġbefore": 873,
960
+ "ros": 874,
961
+ "ĠSh": 875,
962
+ "Ġsy": 876,
963
+ "aid": 877,
964
+ "ĠEng": 878,
965
+ "Ġbeing": 879,
966
+ "Ġ10": 880,
967
+ "uc": 881,
968
+ "Ġep": 882,
969
+ "Ġsupp": 883,
970
+ "Ġthere": 884,
971
+ "Ġyears": 885,
972
+ "ars": 886,
973
+ "owever": 887,
974
+ "Ġent": 888,
975
+ "ife": 889,
976
+ "Ġhigh": 890,
977
+ "Ġfound": 891,
978
+ "ird": 892,
979
+ "Ġno": 893,
980
+ "Ġset": 894,
981
+ "ines": 895,
982
+ "iver": 896,
983
+ "io": 897,
984
+ "other": 898,
985
+ "ject": 899,
986
+ "Ġsur": 900,
987
+ "aj": 901,
988
+ "ten": 902,
989
+ "Ġtra": 903,
990
+ "Ġ12": 904,
991
+ "ised": 905,
992
+ "ities": 906,
993
+ "velop": 907,
994
+ "Ġbl": 908,
995
+ "ale": 909,
996
+ "Ġseries": 910,
997
+ "Ġloc": 911,
998
+ "Ġnumber": 912,
999
+ "Ġpres": 913,
1000
+ "ane": 914,
1001
+ "ause": 915,
1002
+ "ode": 916,
1003
+ "ek": 917,
1004
+ "ton": 918,
1005
+ "ĠSc": 919,
1006
+ "ier": 920,
1007
+ "ise": 921,
1008
+ "Ġsever": 922,
1009
+ "ince": 923,
1010
+ "Ġboth": 924,
1011
+ "ank": 925,
1012
+ "row": 926,
1013
+ "irect": 927,
1014
+ "son": 928,
1015
+ "Ġthen": 929,
1016
+ "ĠBrit": 930,
1017
+ "iet": 931,
1018
+ "Ġ16": 932,
1019
+ "Ġepis": 933,
1020
+ "Ġincluding": 934,
1021
+ "its": 935,
1022
+ "igin": 936,
1023
+ "pr": 937,
1024
+ "Ġ/": 938,
1025
+ "Ġagainst": 939,
1026
+ "Ġwell": 940,
1027
+ "Ġbecame": 941,
1028
+ "Ġexp": 942,
1029
+ "Ġknown": 943,
1030
+ "Ġtrans": 944,
1031
+ "Ġcharac": 945,
1032
+ "ĠâĢĶ": 946,
1033
+ "ram": 947,
1034
+ "Ġback": 948,
1035
+ "Ġadd": 949,
1036
+ "Ġpop": 950,
1037
+ "Ġgo": 951,
1038
+ "urch": 952,
1039
+ "Ġdesc": 953,
1040
+ "Ġsing": 954,
1041
+ "ield": 955,
1042
+ "Ġperform": 956,
1043
+ "ained": 957,
1044
+ "Ġrece": 958,
1045
+ "ident": 959,
1046
+ "Ġem": 960,
1047
+ "ert": 961,
1048
+ "ures": 962,
1049
+ "Ġinv": 963,
1050
+ "Ġdep": 964,
1051
+ "Ġ198": 965,
1052
+ "air": 966,
1053
+ "ern": 967,
1054
+ "ather": 968,
1055
+ "ful": 969,
1056
+ "ĠZ": 970,
1057
+ "Ġmon": 971,
1058
+ "Ġmany": 972,
1059
+ "Ġmain": 973,
1060
+ "Ġstud": 974,
1061
+ "Ġlong": 975,
1062
+ "inn": 976,
1063
+ "though": 977,
1064
+ "up": 978,
1065
+ "ool": 979,
1066
+ "ĠUnited": 980,
1067
+ "led": 981,
1068
+ "ement": 982,
1069
+ "Ġ15": 983,
1070
+ "ower": 984,
1071
+ "ĠJohn": 985,
1072
+ "Ġop": 986,
1073
+ "Ġ11": 987,
1074
+ "ined": 988,
1075
+ "Ġmet": 989,
1076
+ "ober": 990,
1077
+ "ley": 991,
1078
+ "Ġ17": 992,
1079
+ "Ġcentury": 993,
1080
+ "Ġteam": 994,
1081
+ "Ġest": 995,
1082
+ "ĠAfter": 996,
1083
+ "yl": 997,
1084
+ "Ġmin": 998,
1085
+ "uch": 999,
1086
+ "ute": 1000,
1087
+ "Ġdevelop": 1001,
1088
+ "ĠShe": 1002,
1089
+ "iam": 1003,
1090
+ "Ġshow": 1004,
1091
+ "elf": 1005,
1092
+ "Ġrep": 1006,
1093
+ "Ġconc": 1007,
1094
+ "ative": 1008,
1095
+ "Ġcre": 1009,
1096
+ "overn": 1010,
1097
+ "ared": 1011,
1098
+ "Ġ194": 1012,
1099
+ "Ġorigin": 1013,
1100
+ "Ġsm": 1014,
1101
+ "ivers": 1015,
1102
+ "az": 1016,
1103
+ "Ġlead": 1017,
1104
+ "Ġseveral": 1018,
1105
+ "ah": 1019,
1106
+ "Ġob": 1020,
1107
+ "Ġrev": 1021,
1108
+ "Ġmill": 1022,
1109
+ "erm": 1023
1110
+ },
1111
+ "merges": [
1112
+ "Ġ t",
1113
+ "h e",
1114
+ "Ġ a",
1115
+ "i n",
1116
+ "Ġt he",
1117
+ "e r",
1118
+ "o n",
1119
+ "Ġ ,",
1120
+ "r e",
1121
+ "Ġ s",
1122
+ "e d",
1123
+ "Ġ o",
1124
+ "Ġ w",
1125
+ "n d",
1126
+ "a t",
1127
+ "Ġ .",
1128
+ "o r",
1129
+ "i t",
1130
+ "Ġ c",
1131
+ "e n",
1132
+ "Ġ f",
1133
+ "i s",
1134
+ "e s",
1135
+ "a r",
1136
+ "Ġo f",
1137
+ "Ġ b",
1138
+ "a n",
1139
+ "Ġ in",
1140
+ "a l",
1141
+ "in g",
1142
+ "Ġ p",
1143
+ "Ġa nd",
1144
+ "a s",
1145
+ "Ġt o",
1146
+ "r o",
1147
+ "i c",
1148
+ "Ġ m",
1149
+ "Ġ d",
1150
+ "Ġ h",
1151
+ "i on",
1152
+ "l e",
1153
+ "o u",
1154
+ "Ġ T",
1155
+ "Ġ re",
1156
+ "Ġ =",
1157
+ "Ġ \"",
1158
+ "Ġ A",
1159
+ "Ġ S",
1160
+ "en t",
1161
+ "i l",
1162
+ "Ġt h",
1163
+ "Ġ 1",
1164
+ "s t",
1165
+ "Ġ C",
1166
+ "e l",
1167
+ "o m",
1168
+ "Ġ l",
1169
+ "a m",
1170
+ "Ġ Ċ",
1171
+ "Ġ e",
1172
+ "Ġ n",
1173
+ "Ġ @",
1174
+ "a d",
1175
+ "a c",
1176
+ "Ġw as",
1177
+ "Ġ M",
1178
+ "u r",
1179
+ "ĠT he",
1180
+ "e c",
1181
+ "Ġ on",
1182
+ "l y",
1183
+ "Ġ B",
1184
+ "Ġ I",
1185
+ "Ġ g",
1186
+ "Ġ '",
1187
+ "e t",
1188
+ "o l",
1189
+ "i d",
1190
+ "i v",
1191
+ "i m",
1192
+ "Ġf or",
1193
+ "i r",
1194
+ "- @",
1195
+ "Ġ@ -@",
1196
+ "i g",
1197
+ "o t",
1198
+ "t er",
1199
+ "Ġa s",
1200
+ "Ġ H",
1201
+ "u s",
1202
+ "o w",
1203
+ "Ġs t",
1204
+ "u t",
1205
+ "it h",
1206
+ "a y",
1207
+ "Ġ 2",
1208
+ "Ġ P",
1209
+ "at ion",
1210
+ "v er",
1211
+ "Ġb e",
1212
+ "he r",
1213
+ "Ġth at",
1214
+ "Ġw ith",
1215
+ "Ġ R",
1216
+ "c e",
1217
+ "t h",
1218
+ "Ġ D",
1219
+ "Ġ is",
1220
+ "u n",
1221
+ "e m",
1222
+ "Ġ F",
1223
+ "Ġw h",
1224
+ "u l",
1225
+ "Ġb y",
1226
+ "Ġa l",
1227
+ "c h",
1228
+ "Ġ )",
1229
+ "Ġ (",
1230
+ "Ġ W",
1231
+ "Ġc on",
1232
+ "r a",
1233
+ "Ġ G",
1234
+ "o s",
1235
+ "Ġ L",
1236
+ "Ġ N",
1237
+ "Ġa t",
1238
+ "er s",
1239
+ "c t",
1240
+ "Ġ it",
1241
+ "Ġ1 9",
1242
+ "ro m",
1243
+ "a nd",
1244
+ "Ġa n",
1245
+ "u m",
1246
+ "es t",
1247
+ "Ġ J",
1248
+ "a g",
1249
+ "Ġ he",
1250
+ "0 0",
1251
+ "is t",
1252
+ "a in",
1253
+ "o d",
1254
+ "a v",
1255
+ "r i",
1256
+ "Ġ E",
1257
+ "Ġ O",
1258
+ "Ġf rom",
1259
+ "Ġc om",
1260
+ "Ġh is",
1261
+ "o p",
1262
+ "Ġp ro",
1263
+ "re s",
1264
+ "i es",
1265
+ "i f",
1266
+ "Ġ v",
1267
+ "or t",
1268
+ "er e",
1269
+ "il l",
1270
+ "l d",
1271
+ "Ġd e",
1272
+ "p p",
1273
+ "Ġs u",
1274
+ "o re",
1275
+ "ĠI n",
1276
+ "Ġ r",
1277
+ "Ġs e",
1278
+ "Ġw ere",
1279
+ "e w",
1280
+ "on g",
1281
+ "ig h",
1282
+ "ar d",
1283
+ "at e",
1284
+ "al l",
1285
+ "ar t",
1286
+ "a k",
1287
+ "ic h",
1288
+ "Ġc h",
1289
+ "Ġo r",
1290
+ "a b",
1291
+ "an t",
1292
+ "u d",
1293
+ "o c",
1294
+ "b er",
1295
+ "Ġe x",
1296
+ "g h",
1297
+ "it y",
1298
+ "at ed",
1299
+ "p t",
1300
+ "es s",
1301
+ "e ar",
1302
+ "Ġ K",
1303
+ "Ġp l",
1304
+ "am e",
1305
+ "q u",
1306
+ "iv e",
1307
+ "ro u",
1308
+ "Ġa re",
1309
+ "Ġ â",
1310
+ "Ġs h",
1311
+ "Ġ k",
1312
+ "ac k",
1313
+ "ec t",
1314
+ "Ġâ Ģ",
1315
+ "Ġ U",
1316
+ "Ġh ad",
1317
+ "s e",
1318
+ "Ġwh ich",
1319
+ "re d",
1320
+ "o v",
1321
+ "ĠS t",
1322
+ "as t",
1323
+ "Ġs p",
1324
+ "i an",
1325
+ "Ġ y",
1326
+ "m ent",
1327
+ "Ġ le",
1328
+ "Ġn ot",
1329
+ "g e",
1330
+ "or d",
1331
+ "r it",
1332
+ "i p",
1333
+ "in e",
1334
+ "el l",
1335
+ "al ly",
1336
+ "ou r",
1337
+ "o st",
1338
+ "igh t",
1339
+ "t her",
1340
+ "a p",
1341
+ "Ġ u",
1342
+ "is h",
1343
+ "ĠC h",
1344
+ "ou n",
1345
+ "i a",
1346
+ "Ġ 3",
1347
+ "av e",
1348
+ "ar y",
1349
+ "u st",
1350
+ "o g",
1351
+ "Ġ2 00",
1352
+ "Ġ un",
1353
+ "ou s",
1354
+ "ir st",
1355
+ "Ġ V",
1356
+ "c c",
1357
+ "Ġin c",
1358
+ "Ġ ;",
1359
+ "Ġcom p",
1360
+ "r u",
1361
+ "ion s",
1362
+ "Ġthe ir",
1363
+ "Ġb ut",
1364
+ "id e",
1365
+ "u re",
1366
+ "s o",
1367
+ "Ġcon t",
1368
+ "Ġin t",
1369
+ "f ter",
1370
+ "ic al",
1371
+ "i al",
1372
+ "Ġa r",
1373
+ "Ġf irst",
1374
+ "ou ld",
1375
+ "Ġit s",
1376
+ "he d",
1377
+ "ĠâĢ ĵ",
1378
+ "Ġw he",
1379
+ "w o",
1380
+ "ou t",
1381
+ "u b",
1382
+ "Ġ2 0",
1383
+ "f f",
1384
+ "Ġ :",
1385
+ "u e",
1386
+ "Ġ her",
1387
+ "ow n",
1388
+ "o k",
1389
+ "Ġal so",
1390
+ "Ġc l",
1391
+ "p er",
1392
+ "ig n",
1393
+ "at er",
1394
+ "r an",
1395
+ "or m",
1396
+ "i e",
1397
+ "om e",
1398
+ "or k",
1399
+ "as s",
1400
+ "i re",
1401
+ "e nd",
1402
+ "Ġre s",
1403
+ "Ġa b",
1404
+ "Ġa d",
1405
+ "Ġ us",
1406
+ "r y",
1407
+ "Ġre c",
1408
+ "Ġh ave",
1409
+ "ag e",
1410
+ "ĠH e",
1411
+ "Ġ 4",
1412
+ "Ġ ro",
1413
+ "m er",
1414
+ "Ġon e",
1415
+ "on d",
1416
+ "l ow",
1417
+ "Ġh as",
1418
+ "ĠT h",
1419
+ "d u",
1420
+ "Ġ 5",
1421
+ "Ġp er",
1422
+ "Ġbe en",
1423
+ "im e",
1424
+ "Ġt wo",
1425
+ "en ce",
1426
+ "l and",
1427
+ "Ġ1 8",
1428
+ ". @",
1429
+ "Ġ@ .@",
1430
+ "ul t",
1431
+ "re e",
1432
+ "ou gh",
1433
+ "i le",
1434
+ "Ġwh o",
1435
+ "ĠA l",
1436
+ "Ġs c",
1437
+ "ur ing",
1438
+ "p l",
1439
+ "or y",
1440
+ "it ion",
1441
+ "r ic",
1442
+ "ation s",
1443
+ "Ġd is",
1444
+ "Ġth is",
1445
+ "Ġb ec",
1446
+ "Ġa pp",
1447
+ "i z",
1448
+ "ĠI t",
1449
+ "a re",
1450
+ "ac h",
1451
+ "l ud",
1452
+ "ad e",
1453
+ "Ġpl ay",
1454
+ "Ġ j",
1455
+ "Ġm an",
1456
+ "ac t",
1457
+ "el y",
1458
+ "Ġp art",
1459
+ "Ġd es",
1460
+ "Ġa g",
1461
+ "Ġthe y",
1462
+ "Ġy ear",
1463
+ "oun t",
1464
+ "Ġ20 1",
1465
+ "Ġo ver",
1466
+ "Ġo ther",
1467
+ "ou nd",
1468
+ "Ġa fter",
1469
+ "i b",
1470
+ "o ver",
1471
+ "Ġs er",
1472
+ "Ġ en",
1473
+ "Ġof f",
1474
+ "Ġ im",
1475
+ "ct ion",
1476
+ "Ġ Y",
1477
+ "k e",
1478
+ "it e",
1479
+ ", @",
1480
+ "Ġ@ ,@",
1481
+ "t e",
1482
+ "ur n",
1483
+ "Ġinc lud",
1484
+ "res s",
1485
+ "an ce",
1486
+ "an g",
1487
+ "Ġat t",
1488
+ "ic e",
1489
+ "ac e",
1490
+ "ar k",
1491
+ "Ġo ut",
1492
+ "w n",
1493
+ "p h",
1494
+ "em ber",
1495
+ "Ġp re",
1496
+ "Ġu p",
1497
+ "en s",
1498
+ "m an",
1499
+ "Ġe v",
1500
+ "Ġt ime",
1501
+ "nd er",
1502
+ "rou gh",
1503
+ "c ed",
1504
+ "Ġf in",
1505
+ "Ġint o",
1506
+ "on e",
1507
+ "p ort",
1508
+ "rou nd",
1509
+ "w e",
1510
+ "re n",
1511
+ "l es",
1512
+ "in t",
1513
+ "ĠO n",
1514
+ "v el",
1515
+ "Ġcom m",
1516
+ "Ġs he",
1517
+ "as on",
1518
+ "am p",
1519
+ "Ġt e",
1520
+ "Ġw ould",
1521
+ "w ard",
1522
+ "Ġm ore",
1523
+ "Ġ 6",
1524
+ "i ed",
1525
+ "os e",
1526
+ "ri b",
1527
+ "ĠU n",
1528
+ "Ġal l",
1529
+ "ing s",
1530
+ "ter n",
1531
+ "c es",
1532
+ "ab le",
1533
+ "Ġw e",
1534
+ "it ed",
1535
+ "e ver",
1536
+ "ent s",
1537
+ "Ġh im",
1538
+ "as ed",
1539
+ "or s",
1540
+ "o y",
1541
+ "o od",
1542
+ "Ġc ent",
1543
+ "i x",
1544
+ "as e",
1545
+ "il d",
1546
+ "ĠA n",
1547
+ "Ġ 7",
1548
+ "Ġw ork",
1549
+ "at es",
1550
+ "i ous",
1551
+ "at h",
1552
+ "Ġp o",
1553
+ "ro p",
1554
+ "ol d",
1555
+ "al s",
1556
+ "is s",
1557
+ "e y",
1558
+ "ic t",
1559
+ "Ġf e",
1560
+ "Ġthe m",
1561
+ "g an",
1562
+ "Ġs ec",
1563
+ "Ġb et",
1564
+ "Ġwhe n",
1565
+ "Ġs ong",
1566
+ "Ġre m",
1567
+ "e p",
1568
+ "f orm",
1569
+ "a il",
1570
+ "f er",
1571
+ "Ġe ar",
1572
+ "ub l",
1573
+ "a w",
1574
+ "Ġk n",
1575
+ "ak e",
1576
+ "a us",
1577
+ "Ġm ost",
1578
+ "Ġcon s",
1579
+ "Ġd uring",
1580
+ "ĠA s",
1581
+ "or th",
1582
+ "Ġn ew",
1583
+ "er ed",
1584
+ "il m",
1585
+ "v ed",
1586
+ "at t",
1587
+ "Ġon ly",
1588
+ "Ġ 9",
1589
+ "Ġd ec",
1590
+ "Ġ 8",
1591
+ "ic k",
1592
+ "Ġg ame",
1593
+ "on s",
1594
+ "u g",
1595
+ "Ġt r",
1596
+ "f t",
1597
+ "ot h",
1598
+ "o ok",
1599
+ "ĠM ar",
1600
+ "re at",
1601
+ "w ay",
1602
+ "Ġc an",
1603
+ "ol low",
1604
+ "ou th",
1605
+ "we en",
1606
+ "ĠE n",
1607
+ "Ġ19 9",
1608
+ "ter s",
1609
+ "Ġre l",
1610
+ "in d",
1611
+ "Ġab out",
1612
+ "Ġse ason",
1613
+ "Ġag ain",
1614
+ "r al",
1615
+ "Ġth ree",
1616
+ "ation al",
1617
+ "Ġu nder",
1618
+ "ul ar",
1619
+ "Ġm e",
1620
+ "Ġth an",
1621
+ "ĠC om",
1622
+ "ĠA r",
1623
+ "h ip",
1624
+ "o b",
1625
+ "Ġn e",
1626
+ "Ġbet ween",
1627
+ "Ġf l",
1628
+ "h n",
1629
+ "v e",
1630
+ "Ġch ar",
1631
+ "Ġc ol",
1632
+ "Ġrec ord",
1633
+ "i ew",
1634
+ "r on",
1635
+ "f ore",
1636
+ "Ġth rough",
1637
+ "is ion",
1638
+ "or n",
1639
+ "Ġ 00",
1640
+ "oc k",
1641
+ "Ġ ver",
1642
+ "Ġl ater",
1643
+ "Ġn um",
1644
+ "Ġe nd",
1645
+ "ol og",
1646
+ "am es",
1647
+ "Ġp os",
1648
+ "Ġw rit",
1649
+ "Ġpro du",
1650
+ "Ġwh ile",
1651
+ "Ġa ct",
1652
+ "Ġre le",
1653
+ "Ġf ilm",
1654
+ "is hed",
1655
+ "Ġp r",
1656
+ "an s",
1657
+ "Ġre g",
1658
+ "Ġfor m",
1659
+ "Ġas s",
1660
+ "ĠS e",
1661
+ "ur y",
1662
+ "t ed",
1663
+ "t s",
1664
+ "Ġm ade",
1665
+ "Ġsu b",
1666
+ "Ġp e",
1667
+ "Ġs o",
1668
+ "or ld",
1669
+ "Ġre t",
1670
+ "ĠN ew",
1671
+ "Ġsp ec",
1672
+ "Ġa cc",
1673
+ "Ġ qu",
1674
+ "Ġwhe re",
1675
+ "en er",
1676
+ "Ġm ov",
1677
+ "he s",
1678
+ "mer ic",
1679
+ "at ing",
1680
+ "Ġin ter",
1681
+ "ĠL e",
1682
+ "ĠA meric",
1683
+ "Ġ ra",
1684
+ "Ġs ome",
1685
+ "Ġc o",
1686
+ "Ġl ar",
1687
+ "Ġb u",
1688
+ "Ġde f",
1689
+ "b um",
1690
+ "Ġa c",
1691
+ "Ġm us",
1692
+ "Ġf ollow",
1693
+ "ĠA t",
1694
+ "in s",
1695
+ "iv ed",
1696
+ "if ic",
1697
+ "u al",
1698
+ "Ġa m",
1699
+ "Ġsu ch",
1700
+ "Ġsec ond",
1701
+ "i ke",
1702
+ "Ġf our",
1703
+ "Ġin d",
1704
+ "an n",
1705
+ "he n",
1706
+ "Ġus ed",
1707
+ "ĠR e",
1708
+ "ic s",
1709
+ "le ct",
1710
+ "Ġd ay",
1711
+ "i el",
1712
+ "il y",
1713
+ "ĠTh is",
1714
+ "Ġ 0",
1715
+ "Ġp ubl",
1716
+ "Ġc all",
1717
+ "ĠJ o",
1718
+ "l l",
1719
+ "Ġal bum",
1720
+ "Ġ00 0",
1721
+ "ran s",
1722
+ "Ġd o",
1723
+ "an y",
1724
+ "Ġbe fore",
1725
+ "ro s",
1726
+ "ĠS h",
1727
+ "Ġs y",
1728
+ "a id",
1729
+ "ĠEn g",
1730
+ "Ġbe ing",
1731
+ "Ġ1 0",
1732
+ "u c",
1733
+ "Ġe p",
1734
+ "Ġsu pp",
1735
+ "Ġthe re",
1736
+ "Ġyear s",
1737
+ "ar s",
1738
+ "ow ever",
1739
+ "Ġ ent",
1740
+ "if e",
1741
+ "Ġh igh",
1742
+ "Ġf ound",
1743
+ "ir d",
1744
+ "Ġn o",
1745
+ "Ġs et",
1746
+ "in es",
1747
+ "iv er",
1748
+ "i o",
1749
+ "ot her",
1750
+ "j ect",
1751
+ "Ġs ur",
1752
+ "a j",
1753
+ "t en",
1754
+ "Ġt ra",
1755
+ "Ġ1 2",
1756
+ "is ed",
1757
+ "it ies",
1758
+ "vel op",
1759
+ "Ġb l",
1760
+ "al e",
1761
+ "Ġser ies",
1762
+ "Ġl oc",
1763
+ "Ġnum ber",
1764
+ "Ġp res",
1765
+ "an e",
1766
+ "aus e",
1767
+ "od e",
1768
+ "e k",
1769
+ "t on",
1770
+ "ĠS c",
1771
+ "i er",
1772
+ "is e",
1773
+ "Ġse ver",
1774
+ "in ce",
1775
+ "Ġb oth",
1776
+ "an k",
1777
+ "ro w",
1778
+ "ire ct",
1779
+ "s on",
1780
+ "Ġthe n",
1781
+ "ĠB rit",
1782
+ "i et",
1783
+ "Ġ1 6",
1784
+ "Ġep is",
1785
+ "Ġinclud ing",
1786
+ "it s",
1787
+ "ig in",
1788
+ "p r",
1789
+ "Ġ /",
1790
+ "Ġagain st",
1791
+ "Ġw ell",
1792
+ "Ġbec ame",
1793
+ "Ġex p",
1794
+ "Ġkn own",
1795
+ "Ġt rans",
1796
+ "Ġchar ac",
1797
+ "ĠâĢ Ķ",
1798
+ "r am",
1799
+ "Ġb ack",
1800
+ "Ġad d",
1801
+ "Ġp op",
1802
+ "Ġg o",
1803
+ "ur ch",
1804
+ "Ġdes c",
1805
+ "Ġs ing",
1806
+ "iel d",
1807
+ "Ġper form",
1808
+ "ain ed",
1809
+ "Ġre ce",
1810
+ "id ent",
1811
+ "Ġe m",
1812
+ "er t",
1813
+ "u res",
1814
+ "Ġin v",
1815
+ "Ġde p",
1816
+ "Ġ19 8",
1817
+ "a ir",
1818
+ "er n",
1819
+ "at her",
1820
+ "f ul",
1821
+ "Ġ Z",
1822
+ "Ġm on",
1823
+ "Ġman y",
1824
+ "Ġm ain",
1825
+ "Ġst ud",
1826
+ "Ġl ong",
1827
+ "in n",
1828
+ "th ough",
1829
+ "u p",
1830
+ "o ol",
1831
+ "ĠUn ited",
1832
+ "l ed",
1833
+ "em ent",
1834
+ "Ġ1 5",
1835
+ "ow er",
1836
+ "ĠJo hn",
1837
+ "Ġo p",
1838
+ "Ġ1 1",
1839
+ "in ed",
1840
+ "Ġm et",
1841
+ "o ber",
1842
+ "le y",
1843
+ "Ġ1 7",
1844
+ "Ġcent ury",
1845
+ "Ġte am",
1846
+ "Ġ est",
1847
+ "ĠA fter",
1848
+ "y l",
1849
+ "Ġm in",
1850
+ "u ch",
1851
+ "ut e",
1852
+ "Ġde velop",
1853
+ "ĠS he",
1854
+ "i am",
1855
+ "Ġsh ow",
1856
+ "el f",
1857
+ "Ġre p",
1858
+ "Ġcon c",
1859
+ "at ive",
1860
+ "Ġc re",
1861
+ "over n",
1862
+ "a red",
1863
+ "Ġ19 4",
1864
+ "Ġor igin",
1865
+ "Ġs m",
1866
+ "iv ers",
1867
+ "a z",
1868
+ "Ġle ad",
1869
+ "Ġsever al",
1870
+ "a h",
1871
+ "Ġo b",
1872
+ "Ġre v",
1873
+ "Ġm ill",
1874
+ "er m"
1875
+ ]
1876
+ }
1877
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "cls_token_box": [
21
+ 0,
22
+ 0,
23
+ 0,
24
+ 0
25
+ ],
26
+ "eos_token": {
27
+ "__type": "AddedToken",
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "errors": "replace",
35
+ "mask_token": {
36
+ "__type": "AddedToken",
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "model_max_length": 512,
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "sep_token": {
61
+ "__type": "AddedToken",
62
+ "content": "</s>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "sep_token_box": [
69
+ 0,
70
+ 0,
71
+ 0,
72
+ 0
73
+ ],
74
+ "special_tokens_map_file": null,
75
+ "tokenizer_class": "LayoutLMv3Tokenizer",
76
+ "trim_offsets": true,
77
+ "unk_token": {
78
+ "__type": "AddedToken",
79
+ "content": "<unk>",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false
84
+ }
85
+ }
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
+ "</s>": 2,
35
+ "<mask>": 4,
36
+ "<pad>": 1,
37
+ "<s>": 0,
38
+ "<unk>": 3,
39
+ "=": 33,
40
+ ">": 34,
41
+ "?": 35,
42
+ "@": 36,
43
+ "A": 37,
44
+ "B": 38,
45
+ "C": 39,
46
+ "D": 40,
47
+ "E": 41,
48
+ "F": 42,
49
+ "G": 43,
50
+ "H": 44,
51
+ "I": 45,
52
+ "J": 46,
53
+ "K": 47,
54
+ "L": 48,
55
+ "M": 49,
56
+ "N": 50,
57
+ "O": 51,
58
+ "P": 52,
59
+ "Q": 53,
60
+ "R": 54,
61
+ "S": 55,
62
+ "T": 56,
63
+ "U": 57,
64
+ "V": 58,
65
+ "W": 59,
66
+ "X": 60,
67
+ "Y": 61,
68
+ "Z": 62,
69
+ "[": 63,
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
+ }