hf-transformers-bot commited on
Commit
11aaa04
1 Parent(s): 8b03951

Upload tiny models for GPTJForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiny_models/gptj/GPTJForCausalLM",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "attn_pdrop": 0.0,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 0,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.0,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 37,
16
+ "is_decoder": true,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "model_type": "gptj",
19
+ "n_embd": 32,
20
+ "n_head": 4,
21
+ "n_inner": null,
22
+ "n_layer": 5,
23
+ "n_positions": 512,
24
+ "pad_token_id": 1023,
25
+ "resid_pdrop": 0.0,
26
+ "rotary_dim": 4,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.28.0.dev0",
30
+ "type_vocab_size": 16,
31
+ "use_cache": true,
32
+ "vocab_size": 1024
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 1023,
6
+ "transformers_version": "4.28.0.dev0"
7
+ }
merges.txt ADDED
@@ -0,0 +1,768 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
765
+ u ally
766
+ o ot
767
+ Ġbe gan
768
+ Ġ19 6
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12c012e4fb280b919d4d159adf9b39c7b429800b5e3461f6b47ebe9a47de289
3
+ size 1847348
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e85b50ab8432b36337ed5a3a7c92e2c440a73f94bc1924ab0c84e73bb10f291
3
+ size 603176
tokenizer.json ADDED
@@ -0,0 +1,1838 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ }
15
+ ],
16
+ "normalizer": null,
17
+ "pre_tokenizer": {
18
+ "type": "ByteLevel",
19
+ "add_prefix_space": false,
20
+ "trim_offsets": true,
21
+ "use_regex": true
22
+ },
23
+ "post_processor": {
24
+ "type": "ByteLevel",
25
+ "add_prefix_space": true,
26
+ "trim_offsets": false,
27
+ "use_regex": true
28
+ },
29
+ "decoder": {
30
+ "type": "ByteLevel",
31
+ "add_prefix_space": true,
32
+ "trim_offsets": true,
33
+ "use_regex": true
34
+ },
35
+ "model": {
36
+ "type": "BPE",
37
+ "dropout": null,
38
+ "unk_token": null,
39
+ "continuing_subword_prefix": "",
40
+ "end_of_word_suffix": "",
41
+ "fuse_unk": false,
42
+ "vocab": {
43
+ "<|endoftext|>": 0,
44
+ "!": 1,
45
+ "\"": 2,
46
+ "#": 3,
47
+ "$": 4,
48
+ "%": 5,
49
+ "&": 6,
50
+ "'": 7,
51
+ "(": 8,
52
+ ")": 9,
53
+ "*": 10,
54
+ "+": 11,
55
+ ",": 12,
56
+ "-": 13,
57
+ ".": 14,
58
+ "/": 15,
59
+ "0": 16,
60
+ "1": 17,
61
+ "2": 18,
62
+ "3": 19,
63
+ "4": 20,
64
+ "5": 21,
65
+ "6": 22,
66
+ "7": 23,
67
+ "8": 24,
68
+ "9": 25,
69
+ ":": 26,
70
+ ";": 27,
71
+ "<": 28,
72
+ "=": 29,
73
+ ">": 30,
74
+ "?": 31,
75
+ "@": 32,
76
+ "A": 33,
77
+ "B": 34,
78
+ "C": 35,
79
+ "D": 36,
80
+ "E": 37,
81
+ "F": 38,
82
+ "G": 39,
83
+ "H": 40,
84
+ "I": 41,
85
+ "J": 42,
86
+ "K": 43,
87
+ "L": 44,
88
+ "M": 45,
89
+ "N": 46,
90
+ "O": 47,
91
+ "P": 48,
92
+ "Q": 49,
93
+ "R": 50,
94
+ "S": 51,
95
+ "T": 52,
96
+ "U": 53,
97
+ "V": 54,
98
+ "W": 55,
99
+ "X": 56,
100
+ "Y": 57,
101
+ "Z": 58,
102
+ "[": 59,
103
+ "\\": 60,
104
+ "]": 61,
105
+ "^": 62,
106
+ "_": 63,
107
+ "`": 64,
108
+ "a": 65,
109
+ "b": 66,
110
+ "c": 67,
111
+ "d": 68,
112
+ "e": 69,
113
+ "f": 70,
114
+ "g": 71,
115
+ "h": 72,
116
+ "i": 73,
117
+ "j": 74,
118
+ "k": 75,
119
+ "l": 76,
120
+ "m": 77,
121
+ "n": 78,
122
+ "o": 79,
123
+ "p": 80,
124
+ "q": 81,
125
+ "r": 82,
126
+ "s": 83,
127
+ "t": 84,
128
+ "u": 85,
129
+ "v": 86,
130
+ "w": 87,
131
+ "x": 88,
132
+ "y": 89,
133
+ "z": 90,
134
+ "{": 91,
135
+ "|": 92,
136
+ "}": 93,
137
+ "~": 94,
138
+ "¡": 95,
139
+ "¢": 96,
140
+ "£": 97,
141
+ "¤": 98,
142
+ "¥": 99,
143
+ "¦": 100,
144
+ "§": 101,
145
+ "¨": 102,
146
+ "©": 103,
147
+ "ª": 104,
148
+ "«": 105,
149
+ "¬": 106,
150
+ "®": 107,
151
+ "¯": 108,
152
+ "°": 109,
153
+ "±": 110,
154
+ "²": 111,
155
+ "³": 112,
156
+ "´": 113,
157
+ "µ": 114,
158
+ "¶": 115,
159
+ "·": 116,
160
+ "¸": 117,
161
+ "¹": 118,
162
+ "º": 119,
163
+ "»": 120,
164
+ "¼": 121,
165
+ "½": 122,
166
+ "¾": 123,
167
+ "¿": 124,
168
+ "À": 125,
169
+ "Á": 126,
170
+ "Â": 127,
171
+ "Ã": 128,
172
+ "Ä": 129,
173
+ "Å": 130,
174
+ "Æ": 131,
175
+ "Ç": 132,
176
+ "È": 133,
177
+ "É": 134,
178
+ "Ê": 135,
179
+ "Ë": 136,
180
+ "Ì": 137,
181
+ "Í": 138,
182
+ "Î": 139,
183
+ "Ï": 140,
184
+ "Ð": 141,
185
+ "Ñ": 142,
186
+ "Ò": 143,
187
+ "Ó": 144,
188
+ "Ô": 145,
189
+ "Õ": 146,
190
+ "Ö": 147,
191
+ "×": 148,
192
+ "Ø": 149,
193
+ "Ù": 150,
194
+ "Ú": 151,
195
+ "Û": 152,
196
+ "Ü": 153,
197
+ "Ý": 154,
198
+ "Þ": 155,
199
+ "ß": 156,
200
+ "à": 157,
201
+ "á": 158,
202
+ "â": 159,
203
+ "ã": 160,
204
+ "ä": 161,
205
+ "å": 162,
206
+ "æ": 163,
207
+ "ç": 164,
208
+ "è": 165,
209
+ "é": 166,
210
+ "ê": 167,
211
+ "ë": 168,
212
+ "ì": 169,
213
+ "í": 170,
214
+ "î": 171,
215
+ "ï": 172,
216
+ "ð": 173,
217
+ "ñ": 174,
218
+ "ò": 175,
219
+ "ó": 176,
220
+ "ô": 177,
221
+ "õ": 178,
222
+ "ö": 179,
223
+ "÷": 180,
224
+ "ø": 181,
225
+ "ù": 182,
226
+ "ú": 183,
227
+ "û": 184,
228
+ "ü": 185,
229
+ "ý": 186,
230
+ "þ": 187,
231
+ "ÿ": 188,
232
+ "Ā": 189,
233
+ "ā": 190,
234
+ "Ă": 191,
235
+ "ă": 192,
236
+ "Ą": 193,
237
+ "ą": 194,
238
+ "Ć": 195,
239
+ "ć": 196,
240
+ "Ĉ": 197,
241
+ "ĉ": 198,
242
+ "Ċ": 199,
243
+ "ċ": 200,
244
+ "Č": 201,
245
+ "č": 202,
246
+ "Ď": 203,
247
+ "ď": 204,
248
+ "Đ": 205,
249
+ "đ": 206,
250
+ "Ē": 207,
251
+ "ē": 208,
252
+ "Ĕ": 209,
253
+ "ĕ": 210,
254
+ "Ė": 211,
255
+ "ė": 212,
256
+ "Ę": 213,
257
+ "ę": 214,
258
+ "Ě": 215,
259
+ "ě": 216,
260
+ "Ĝ": 217,
261
+ "ĝ": 218,
262
+ "Ğ": 219,
263
+ "ğ": 220,
264
+ "Ġ": 221,
265
+ "ġ": 222,
266
+ "Ģ": 223,
267
+ "ģ": 224,
268
+ "Ĥ": 225,
269
+ "ĥ": 226,
270
+ "Ħ": 227,
271
+ "ħ": 228,
272
+ "Ĩ": 229,
273
+ "ĩ": 230,
274
+ "Ī": 231,
275
+ "ī": 232,
276
+ "Ĭ": 233,
277
+ "ĭ": 234,
278
+ "Į": 235,
279
+ "į": 236,
280
+ "İ": 237,
281
+ "ı": 238,
282
+ "IJ": 239,
283
+ "ij": 240,
284
+ "Ĵ": 241,
285
+ "ĵ": 242,
286
+ "Ķ": 243,
287
+ "ķ": 244,
288
+ "ĸ": 245,
289
+ "Ĺ": 246,
290
+ "ĺ": 247,
291
+ "Ļ": 248,
292
+ "ļ": 249,
293
+ "Ľ": 250,
294
+ "ľ": 251,
295
+ "Ŀ": 252,
296
+ "ŀ": 253,
297
+ "Ł": 254,
298
+ "ł": 255,
299
+ "Ń": 256,
300
+ "Ġt": 257,
301
+ "he": 258,
302
+ "Ġa": 259,
303
+ "in": 260,
304
+ "Ġthe": 261,
305
+ "er": 262,
306
+ "on": 263,
307
+ "Ġ,": 264,
308
+ "re": 265,
309
+ "Ġs": 266,
310
+ "ed": 267,
311
+ "Ġo": 268,
312
+ "Ġw": 269,
313
+ "nd": 270,
314
+ "at": 271,
315
+ "Ġ.": 272,
316
+ "or": 273,
317
+ "it": 274,
318
+ "Ġc": 275,
319
+ "en": 276,
320
+ "Ġf": 277,
321
+ "is": 278,
322
+ "es": 279,
323
+ "ar": 280,
324
+ "Ġof": 281,
325
+ "Ġb": 282,
326
+ "an": 283,
327
+ "Ġin": 284,
328
+ "al": 285,
329
+ "ing": 286,
330
+ "Ġp": 287,
331
+ "Ġand": 288,
332
+ "as": 289,
333
+ "Ġto": 290,
334
+ "ro": 291,
335
+ "ic": 292,
336
+ "Ġm": 293,
337
+ "Ġd": 294,
338
+ "Ġh": 295,
339
+ "ion": 296,
340
+ "le": 297,
341
+ "ou": 298,
342
+ "ĠT": 299,
343
+ "Ġre": 300,
344
+ "Ġ=": 301,
345
+ "Ġ\"": 302,
346
+ "ĠA": 303,
347
+ "ĠS": 304,
348
+ "ent": 305,
349
+ "il": 306,
350
+ "Ġth": 307,
351
+ "Ġ1": 308,
352
+ "st": 309,
353
+ "ĠC": 310,
354
+ "el": 311,
355
+ "om": 312,
356
+ "Ġl": 313,
357
+ "am": 314,
358
+ "ĠĊ": 315,
359
+ "Ġe": 316,
360
+ "Ġn": 317,
361
+ "Ġ@": 318,
362
+ "ad": 319,
363
+ "ac": 320,
364
+ "Ġwas": 321,
365
+ "ĠM": 322,
366
+ "ur": 323,
367
+ "ĠThe": 324,
368
+ "ec": 325,
369
+ "Ġon": 326,
370
+ "ly": 327,
371
+ "ĠB": 328,
372
+ "ĠI": 329,
373
+ "Ġg": 330,
374
+ "Ġ'": 331,
375
+ "et": 332,
376
+ "ol": 333,
377
+ "id": 334,
378
+ "iv": 335,
379
+ "im": 336,
380
+ "Ġfor": 337,
381
+ "ir": 338,
382
+ "-@": 339,
383
+ "Ġ@-@": 340,
384
+ "ig": 341,
385
+ "ot": 342,
386
+ "ter": 343,
387
+ "Ġas": 344,
388
+ "ĠH": 345,
389
+ "us": 346,
390
+ "ow": 347,
391
+ "Ġst": 348,
392
+ "ut": 349,
393
+ "ith": 350,
394
+ "ay": 351,
395
+ "Ġ2": 352,
396
+ "ĠP": 353,
397
+ "ation": 354,
398
+ "ver": 355,
399
+ "Ġbe": 356,
400
+ "her": 357,
401
+ "Ġthat": 358,
402
+ "Ġwith": 359,
403
+ "ĠR": 360,
404
+ "ce": 361,
405
+ "th": 362,
406
+ "ĠD": 363,
407
+ "Ġis": 364,
408
+ "un": 365,
409
+ "em": 366,
410
+ "ĠF": 367,
411
+ "Ġwh": 368,
412
+ "ul": 369,
413
+ "Ġby": 370,
414
+ "Ġal": 371,
415
+ "ch": 372,
416
+ "Ġ)": 373,
417
+ "Ġ(": 374,
418
+ "ĠW": 375,
419
+ "Ġcon": 376,
420
+ "ra": 377,
421
+ "ĠG": 378,
422
+ "os": 379,
423
+ "ĠL": 380,
424
+ "ĠN": 381,
425
+ "Ġat": 382,
426
+ "ers": 383,
427
+ "ct": 384,
428
+ "Ġit": 385,
429
+ "Ġ19": 386,
430
+ "rom": 387,
431
+ "and": 388,
432
+ "Ġan": 389,
433
+ "um": 390,
434
+ "est": 391,
435
+ "ĠJ": 392,
436
+ "ag": 393,
437
+ "Ġhe": 394,
438
+ "00": 395,
439
+ "ist": 396,
440
+ "ain": 397,
441
+ "od": 398,
442
+ "av": 399,
443
+ "ri": 400,
444
+ "ĠE": 401,
445
+ "ĠO": 402,
446
+ "Ġfrom": 403,
447
+ "Ġcom": 404,
448
+ "Ġhis": 405,
449
+ "op": 406,
450
+ "Ġpro": 407,
451
+ "res": 408,
452
+ "ies": 409,
453
+ "if": 410,
454
+ "Ġv": 411,
455
+ "ort": 412,
456
+ "ere": 413,
457
+ "ill": 414,
458
+ "ld": 415,
459
+ "Ġde": 416,
460
+ "pp": 417,
461
+ "Ġsu": 418,
462
+ "ore": 419,
463
+ "ĠIn": 420,
464
+ "Ġr": 421,
465
+ "Ġse": 422,
466
+ "Ġwere": 423,
467
+ "ew": 424,
468
+ "ong": 425,
469
+ "igh": 426,
470
+ "ard": 427,
471
+ "ate": 428,
472
+ "all": 429,
473
+ "art": 430,
474
+ "ak": 431,
475
+ "ich": 432,
476
+ "Ġch": 433,
477
+ "Ġor": 434,
478
+ "ab": 435,
479
+ "ant": 436,
480
+ "ud": 437,
481
+ "oc": 438,
482
+ "ber": 439,
483
+ "Ġex": 440,
484
+ "gh": 441,
485
+ "ity": 442,
486
+ "ated": 443,
487
+ "pt": 444,
488
+ "ess": 445,
489
+ "ear": 446,
490
+ "ĠK": 447,
491
+ "Ġpl": 448,
492
+ "ame": 449,
493
+ "qu": 450,
494
+ "ive": 451,
495
+ "rou": 452,
496
+ "Ġare": 453,
497
+ "Ġâ": 454,
498
+ "Ġsh": 455,
499
+ "Ġk": 456,
500
+ "ack": 457,
501
+ "ect": 458,
502
+ "ĠâĢ": 459,
503
+ "ĠU": 460,
504
+ "Ġhad": 461,
505
+ "se": 462,
506
+ "Ġwhich": 463,
507
+ "red": 464,
508
+ "ov": 465,
509
+ "ĠSt": 466,
510
+ "ast": 467,
511
+ "Ġsp": 468,
512
+ "ian": 469,
513
+ "Ġy": 470,
514
+ "ment": 471,
515
+ "Ġle": 472,
516
+ "Ġnot": 473,
517
+ "ge": 474,
518
+ "ord": 475,
519
+ "rit": 476,
520
+ "ip": 477,
521
+ "ine": 478,
522
+ "ell": 479,
523
+ "ally": 480,
524
+ "our": 481,
525
+ "ost": 482,
526
+ "ight": 483,
527
+ "ther": 484,
528
+ "ap": 485,
529
+ "Ġu": 486,
530
+ "ish": 487,
531
+ "ĠCh": 488,
532
+ "oun": 489,
533
+ "ia": 490,
534
+ "Ġ3": 491,
535
+ "ave": 492,
536
+ "ary": 493,
537
+ "ust": 494,
538
+ "og": 495,
539
+ "Ġ200": 496,
540
+ "Ġun": 497,
541
+ "ous": 498,
542
+ "irst": 499,
543
+ "ĠV": 500,
544
+ "cc": 501,
545
+ "Ġinc": 502,
546
+ "Ġ;": 503,
547
+ "Ġcomp": 504,
548
+ "ru": 505,
549
+ "ions": 506,
550
+ "Ġtheir": 507,
551
+ "Ġbut": 508,
552
+ "ide": 509,
553
+ "ure": 510,
554
+ "so": 511,
555
+ "Ġcont": 512,
556
+ "Ġint": 513,
557
+ "fter": 514,
558
+ "ical": 515,
559
+ "ial": 516,
560
+ "Ġar": 517,
561
+ "Ġfirst": 518,
562
+ "ould": 519,
563
+ "Ġits": 520,
564
+ "hed": 521,
565
+ "ĠâĢĵ": 522,
566
+ "Ġwhe": 523,
567
+ "wo": 524,
568
+ "out": 525,
569
+ "ub": 526,
570
+ "Ġ20": 527,
571
+ "ff": 528,
572
+ "Ġ:": 529,
573
+ "ue": 530,
574
+ "Ġher": 531,
575
+ "own": 532,
576
+ "ok": 533,
577
+ "Ġalso": 534,
578
+ "Ġcl": 535,
579
+ "per": 536,
580
+ "ign": 537,
581
+ "ater": 538,
582
+ "ran": 539,
583
+ "orm": 540,
584
+ "ie": 541,
585
+ "ome": 542,
586
+ "ork": 543,
587
+ "ass": 544,
588
+ "ire": 545,
589
+ "end": 546,
590
+ "Ġres": 547,
591
+ "Ġab": 548,
592
+ "Ġad": 549,
593
+ "Ġus": 550,
594
+ "ry": 551,
595
+ "Ġrec": 552,
596
+ "Ġhave": 553,
597
+ "age": 554,
598
+ "ĠHe": 555,
599
+ "Ġ4": 556,
600
+ "Ġro": 557,
601
+ "mer": 558,
602
+ "Ġone": 559,
603
+ "ond": 560,
604
+ "low": 561,
605
+ "Ġhas": 562,
606
+ "ĠTh": 563,
607
+ "du": 564,
608
+ "Ġ5": 565,
609
+ "Ġper": 566,
610
+ "Ġbeen": 567,
611
+ "ime": 568,
612
+ "Ġtwo": 569,
613
+ "ence": 570,
614
+ "land": 571,
615
+ "Ġ18": 572,
616
+ ".@": 573,
617
+ "Ġ@.@": 574,
618
+ "ult": 575,
619
+ "ree": 576,
620
+ "ough": 577,
621
+ "ile": 578,
622
+ "Ġwho": 579,
623
+ "ĠAl": 580,
624
+ "Ġsc": 581,
625
+ "uring": 582,
626
+ "pl": 583,
627
+ "ory": 584,
628
+ "ition": 585,
629
+ "ric": 586,
630
+ "ations": 587,
631
+ "Ġdis": 588,
632
+ "Ġthis": 589,
633
+ "Ġbec": 590,
634
+ "Ġapp": 591,
635
+ "iz": 592,
636
+ "ĠIt": 593,
637
+ "are": 594,
638
+ "ach": 595,
639
+ "lud": 596,
640
+ "ade": 597,
641
+ "Ġplay": 598,
642
+ "Ġj": 599,
643
+ "Ġman": 600,
644
+ "act": 601,
645
+ "ely": 602,
646
+ "Ġpart": 603,
647
+ "Ġdes": 604,
648
+ "Ġag": 605,
649
+ "Ġthey": 606,
650
+ "Ġyear": 607,
651
+ "ount": 608,
652
+ "Ġ201": 609,
653
+ "Ġover": 610,
654
+ "Ġother": 611,
655
+ "ound": 612,
656
+ "Ġafter": 613,
657
+ "ib": 614,
658
+ "over": 615,
659
+ "Ġser": 616,
660
+ "Ġen": 617,
661
+ "Ġoff": 618,
662
+ "Ġim": 619,
663
+ "ction": 620,
664
+ "ĠY": 621,
665
+ "ke": 622,
666
+ "ite": 623,
667
+ ",@": 624,
668
+ "Ġ@,@": 625,
669
+ "te": 626,
670
+ "urn": 627,
671
+ "Ġinclud": 628,
672
+ "ress": 629,
673
+ "ance": 630,
674
+ "ang": 631,
675
+ "Ġatt": 632,
676
+ "ice": 633,
677
+ "ace": 634,
678
+ "ark": 635,
679
+ "Ġout": 636,
680
+ "wn": 637,
681
+ "ph": 638,
682
+ "ember": 639,
683
+ "Ġpre": 640,
684
+ "Ġup": 641,
685
+ "ens": 642,
686
+ "man": 643,
687
+ "Ġev": 644,
688
+ "Ġtime": 645,
689
+ "nder": 646,
690
+ "rough": 647,
691
+ "ced": 648,
692
+ "Ġfin": 649,
693
+ "Ġinto": 650,
694
+ "one": 651,
695
+ "port": 652,
696
+ "round": 653,
697
+ "we": 654,
698
+ "ren": 655,
699
+ "les": 656,
700
+ "int": 657,
701
+ "ĠOn": 658,
702
+ "vel": 659,
703
+ "Ġcomm": 660,
704
+ "Ġshe": 661,
705
+ "ason": 662,
706
+ "amp": 663,
707
+ "Ġte": 664,
708
+ "Ġwould": 665,
709
+ "ward": 666,
710
+ "Ġmore": 667,
711
+ "Ġ6": 668,
712
+ "ied": 669,
713
+ "ose": 670,
714
+ "rib": 671,
715
+ "ĠUn": 672,
716
+ "Ġall": 673,
717
+ "ings": 674,
718
+ "tern": 675,
719
+ "ces": 676,
720
+ "able": 677,
721
+ "Ġwe": 678,
722
+ "ited": 679,
723
+ "ever": 680,
724
+ "ents": 681,
725
+ "Ġhim": 682,
726
+ "ased": 683,
727
+ "ors": 684,
728
+ "oy": 685,
729
+ "ood": 686,
730
+ "Ġcent": 687,
731
+ "ix": 688,
732
+ "ase": 689,
733
+ "ild": 690,
734
+ "ĠAn": 691,
735
+ "Ġ7": 692,
736
+ "Ġwork": 693,
737
+ "ates": 694,
738
+ "ious": 695,
739
+ "ath": 696,
740
+ "Ġpo": 697,
741
+ "rop": 698,
742
+ "old": 699,
743
+ "als": 700,
744
+ "iss": 701,
745
+ "ey": 702,
746
+ "ict": 703,
747
+ "Ġfe": 704,
748
+ "Ġthem": 705,
749
+ "gan": 706,
750
+ "Ġsec": 707,
751
+ "Ġbet": 708,
752
+ "Ġwhen": 709,
753
+ "Ġsong": 710,
754
+ "Ġrem": 711,
755
+ "ep": 712,
756
+ "form": 713,
757
+ "ail": 714,
758
+ "fer": 715,
759
+ "Ġear": 716,
760
+ "ubl": 717,
761
+ "aw": 718,
762
+ "Ġkn": 719,
763
+ "ake": 720,
764
+ "aus": 721,
765
+ "Ġmost": 722,
766
+ "Ġcons": 723,
767
+ "Ġduring": 724,
768
+ "ĠAs": 725,
769
+ "orth": 726,
770
+ "Ġnew": 727,
771
+ "ered": 728,
772
+ "ilm": 729,
773
+ "ved": 730,
774
+ "att": 731,
775
+ "Ġonly": 732,
776
+ "Ġ9": 733,
777
+ "Ġdec": 734,
778
+ "Ġ8": 735,
779
+ "ick": 736,
780
+ "Ġgame": 737,
781
+ "ons": 738,
782
+ "ug": 739,
783
+ "Ġtr": 740,
784
+ "ft": 741,
785
+ "oth": 742,
786
+ "ook": 743,
787
+ "ĠMar": 744,
788
+ "reat": 745,
789
+ "way": 746,
790
+ "Ġcan": 747,
791
+ "ollow": 748,
792
+ "outh": 749,
793
+ "ween": 750,
794
+ "ĠEn": 751,
795
+ "Ġ199": 752,
796
+ "ters": 753,
797
+ "Ġrel": 754,
798
+ "ind": 755,
799
+ "Ġabout": 756,
800
+ "Ġseason": 757,
801
+ "Ġagain": 758,
802
+ "ral": 759,
803
+ "Ġthree": 760,
804
+ "ational": 761,
805
+ "Ġunder": 762,
806
+ "ular": 763,
807
+ "Ġme": 764,
808
+ "Ġthan": 765,
809
+ "ĠCom": 766,
810
+ "ĠAr": 767,
811
+ "hip": 768,
812
+ "ob": 769,
813
+ "Ġne": 770,
814
+ "Ġbetween": 771,
815
+ "Ġfl": 772,
816
+ "hn": 773,
817
+ "ve": 774,
818
+ "Ġchar": 775,
819
+ "Ġcol": 776,
820
+ "Ġrecord": 777,
821
+ "iew": 778,
822
+ "ron": 779,
823
+ "fore": 780,
824
+ "Ġthrough": 781,
825
+ "ision": 782,
826
+ "orn": 783,
827
+ "Ġ00": 784,
828
+ "ock": 785,
829
+ "Ġver": 786,
830
+ "Ġlater": 787,
831
+ "Ġnum": 788,
832
+ "Ġend": 789,
833
+ "olog": 790,
834
+ "ames": 791,
835
+ "Ġpos": 792,
836
+ "Ġwrit": 793,
837
+ "Ġprodu": 794,
838
+ "Ġwhile": 795,
839
+ "Ġact": 796,
840
+ "Ġrele": 797,
841
+ "Ġfilm": 798,
842
+ "ished": 799,
843
+ "Ġpr": 800,
844
+ "ans": 801,
845
+ "Ġreg": 802,
846
+ "Ġform": 803,
847
+ "Ġass": 804,
848
+ "ĠSe": 805,
849
+ "ury": 806,
850
+ "ted": 807,
851
+ "ts": 808,
852
+ "Ġmade": 809,
853
+ "Ġsub": 810,
854
+ "Ġpe": 811,
855
+ "Ġso": 812,
856
+ "orld": 813,
857
+ "Ġret": 814,
858
+ "ĠNew": 815,
859
+ "Ġspec": 816,
860
+ "Ġacc": 817,
861
+ "Ġqu": 818,
862
+ "Ġwhere": 819,
863
+ "ener": 820,
864
+ "Ġmov": 821,
865
+ "hes": 822,
866
+ "meric": 823,
867
+ "ating": 824,
868
+ "Ġinter": 825,
869
+ "ĠLe": 826,
870
+ "ĠAmeric": 827,
871
+ "Ġra": 828,
872
+ "Ġsome": 829,
873
+ "Ġco": 830,
874
+ "Ġlar": 831,
875
+ "Ġbu": 832,
876
+ "Ġdef": 833,
877
+ "bum": 834,
878
+ "Ġac": 835,
879
+ "Ġmus": 836,
880
+ "Ġfollow": 837,
881
+ "ĠAt": 838,
882
+ "ins": 839,
883
+ "ived": 840,
884
+ "ific": 841,
885
+ "ual": 842,
886
+ "Ġam": 843,
887
+ "Ġsuch": 844,
888
+ "Ġsecond": 845,
889
+ "ike": 846,
890
+ "Ġfour": 847,
891
+ "Ġind": 848,
892
+ "ann": 849,
893
+ "hen": 850,
894
+ "Ġused": 851,
895
+ "ĠRe": 852,
896
+ "ics": 853,
897
+ "lect": 854,
898
+ "Ġday": 855,
899
+ "iel": 856,
900
+ "ily": 857,
901
+ "ĠThis": 858,
902
+ "Ġ0": 859,
903
+ "Ġpubl": 860,
904
+ "Ġcall": 861,
905
+ "ĠJo": 862,
906
+ "ll": 863,
907
+ "Ġalbum": 864,
908
+ "Ġ000": 865,
909
+ "rans": 866,
910
+ "Ġdo": 867,
911
+ "any": 868,
912
+ "Ġbefore": 869,
913
+ "ros": 870,
914
+ "ĠSh": 871,
915
+ "Ġsy": 872,
916
+ "aid": 873,
917
+ "ĠEng": 874,
918
+ "Ġbeing": 875,
919
+ "Ġ10": 876,
920
+ "uc": 877,
921
+ "Ġep": 878,
922
+ "Ġsupp": 879,
923
+ "Ġthere": 880,
924
+ "Ġyears": 881,
925
+ "ars": 882,
926
+ "owever": 883,
927
+ "Ġent": 884,
928
+ "ife": 885,
929
+ "Ġhigh": 886,
930
+ "Ġfound": 887,
931
+ "ird": 888,
932
+ "Ġno": 889,
933
+ "Ġset": 890,
934
+ "ines": 891,
935
+ "iver": 892,
936
+ "io": 893,
937
+ "other": 894,
938
+ "ject": 895,
939
+ "Ġsur": 896,
940
+ "aj": 897,
941
+ "ten": 898,
942
+ "Ġtra": 899,
943
+ "Ġ12": 900,
944
+ "ised": 901,
945
+ "ities": 902,
946
+ "velop": 903,
947
+ "Ġbl": 904,
948
+ "ale": 905,
949
+ "Ġseries": 906,
950
+ "Ġloc": 907,
951
+ "Ġnumber": 908,
952
+ "Ġpres": 909,
953
+ "ane": 910,
954
+ "ause": 911,
955
+ "ode": 912,
956
+ "ek": 913,
957
+ "ton": 914,
958
+ "ĠSc": 915,
959
+ "ier": 916,
960
+ "ise": 917,
961
+ "Ġsever": 918,
962
+ "ince": 919,
963
+ "Ġboth": 920,
964
+ "ank": 921,
965
+ "row": 922,
966
+ "irect": 923,
967
+ "son": 924,
968
+ "Ġthen": 925,
969
+ "ĠBrit": 926,
970
+ "iet": 927,
971
+ "Ġ16": 928,
972
+ "Ġepis": 929,
973
+ "Ġincluding": 930,
974
+ "its": 931,
975
+ "igin": 932,
976
+ "pr": 933,
977
+ "Ġ/": 934,
978
+ "Ġagainst": 935,
979
+ "Ġwell": 936,
980
+ "Ġbecame": 937,
981
+ "Ġexp": 938,
982
+ "Ġknown": 939,
983
+ "Ġtrans": 940,
984
+ "Ġcharac": 941,
985
+ "ĠâĢĶ": 942,
986
+ "ram": 943,
987
+ "Ġback": 944,
988
+ "Ġadd": 945,
989
+ "Ġpop": 946,
990
+ "Ġgo": 947,
991
+ "urch": 948,
992
+ "Ġdesc": 949,
993
+ "Ġsing": 950,
994
+ "ield": 951,
995
+ "Ġperform": 952,
996
+ "ained": 953,
997
+ "Ġrece": 954,
998
+ "ident": 955,
999
+ "Ġem": 956,
1000
+ "ert": 957,
1001
+ "ures": 958,
1002
+ "Ġinv": 959,
1003
+ "Ġdep": 960,
1004
+ "Ġ198": 961,
1005
+ "air": 962,
1006
+ "ern": 963,
1007
+ "ather": 964,
1008
+ "ful": 965,
1009
+ "ĠZ": 966,
1010
+ "Ġmon": 967,
1011
+ "Ġmany": 968,
1012
+ "Ġmain": 969,
1013
+ "Ġstud": 970,
1014
+ "Ġlong": 971,
1015
+ "inn": 972,
1016
+ "though": 973,
1017
+ "up": 974,
1018
+ "ool": 975,
1019
+ "ĠUnited": 976,
1020
+ "led": 977,
1021
+ "ement": 978,
1022
+ "Ġ15": 979,
1023
+ "ower": 980,
1024
+ "ĠJohn": 981,
1025
+ "Ġop": 982,
1026
+ "Ġ11": 983,
1027
+ "ined": 984,
1028
+ "Ġmet": 985,
1029
+ "ober": 986,
1030
+ "ley": 987,
1031
+ "Ġ17": 988,
1032
+ "Ġcentury": 989,
1033
+ "Ġteam": 990,
1034
+ "Ġest": 991,
1035
+ "ĠAfter": 992,
1036
+ "yl": 993,
1037
+ "Ġmin": 994,
1038
+ "uch": 995,
1039
+ "ute": 996,
1040
+ "Ġdevelop": 997,
1041
+ "ĠShe": 998,
1042
+ "iam": 999,
1043
+ "Ġshow": 1000,
1044
+ "elf": 1001,
1045
+ "Ġrep": 1002,
1046
+ "Ġconc": 1003,
1047
+ "ative": 1004,
1048
+ "Ġcre": 1005,
1049
+ "overn": 1006,
1050
+ "ared": 1007,
1051
+ "Ġ194": 1008,
1052
+ "Ġorigin": 1009,
1053
+ "Ġsm": 1010,
1054
+ "ivers": 1011,
1055
+ "az": 1012,
1056
+ "Ġlead": 1013,
1057
+ "Ġseveral": 1014,
1058
+ "ah": 1015,
1059
+ "Ġob": 1016,
1060
+ "Ġrev": 1017,
1061
+ "Ġmill": 1018,
1062
+ "erm": 1019,
1063
+ "ually": 1020,
1064
+ "oot": 1021,
1065
+ "Ġbegan": 1022,
1066
+ "Ġ196": 1023
1067
+ },
1068
+ "merges": [
1069
+ "Ġ t",
1070
+ "h e",
1071
+ "Ġ a",
1072
+ "i n",
1073
+ "Ġt he",
1074
+ "e r",
1075
+ "o n",
1076
+ "Ġ ,",
1077
+ "r e",
1078
+ "Ġ s",
1079
+ "e d",
1080
+ "Ġ o",
1081
+ "Ġ w",
1082
+ "n d",
1083
+ "a t",
1084
+ "Ġ .",
1085
+ "o r",
1086
+ "i t",
1087
+ "Ġ c",
1088
+ "e n",
1089
+ "Ġ f",
1090
+ "i s",
1091
+ "e s",
1092
+ "a r",
1093
+ "Ġo f",
1094
+ "Ġ b",
1095
+ "a n",
1096
+ "Ġ in",
1097
+ "a l",
1098
+ "in g",
1099
+ "Ġ p",
1100
+ "Ġa nd",
1101
+ "a s",
1102
+ "Ġt o",
1103
+ "r o",
1104
+ "i c",
1105
+ "Ġ m",
1106
+ "Ġ d",
1107
+ "Ġ h",
1108
+ "i on",
1109
+ "l e",
1110
+ "o u",
1111
+ "Ġ T",
1112
+ "Ġ re",
1113
+ "Ġ =",
1114
+ "Ġ \"",
1115
+ "Ġ A",
1116
+ "Ġ S",
1117
+ "en t",
1118
+ "i l",
1119
+ "Ġt h",
1120
+ "Ġ 1",
1121
+ "s t",
1122
+ "Ġ C",
1123
+ "e l",
1124
+ "o m",
1125
+ "Ġ l",
1126
+ "a m",
1127
+ "Ġ Ċ",
1128
+ "Ġ e",
1129
+ "Ġ n",
1130
+ "Ġ @",
1131
+ "a d",
1132
+ "a c",
1133
+ "Ġw as",
1134
+ "Ġ M",
1135
+ "u r",
1136
+ "ĠT he",
1137
+ "e c",
1138
+ "Ġ on",
1139
+ "l y",
1140
+ "Ġ B",
1141
+ "Ġ I",
1142
+ "Ġ g",
1143
+ "Ġ '",
1144
+ "e t",
1145
+ "o l",
1146
+ "i d",
1147
+ "i v",
1148
+ "i m",
1149
+ "Ġf or",
1150
+ "i r",
1151
+ "- @",
1152
+ "Ġ@ -@",
1153
+ "i g",
1154
+ "o t",
1155
+ "t er",
1156
+ "Ġa s",
1157
+ "Ġ H",
1158
+ "u s",
1159
+ "o w",
1160
+ "Ġs t",
1161
+ "u t",
1162
+ "it h",
1163
+ "a y",
1164
+ "Ġ 2",
1165
+ "Ġ P",
1166
+ "at ion",
1167
+ "v er",
1168
+ "Ġb e",
1169
+ "he r",
1170
+ "Ġth at",
1171
+ "Ġw ith",
1172
+ "Ġ R",
1173
+ "c e",
1174
+ "t h",
1175
+ "Ġ D",
1176
+ "Ġ is",
1177
+ "u n",
1178
+ "e m",
1179
+ "Ġ F",
1180
+ "Ġw h",
1181
+ "u l",
1182
+ "Ġb y",
1183
+ "Ġa l",
1184
+ "c h",
1185
+ "Ġ )",
1186
+ "Ġ (",
1187
+ "Ġ W",
1188
+ "Ġc on",
1189
+ "r a",
1190
+ "Ġ G",
1191
+ "o s",
1192
+ "Ġ L",
1193
+ "Ġ N",
1194
+ "Ġa t",
1195
+ "er s",
1196
+ "c t",
1197
+ "Ġ it",
1198
+ "Ġ1 9",
1199
+ "ro m",
1200
+ "a nd",
1201
+ "Ġa n",
1202
+ "u m",
1203
+ "es t",
1204
+ "Ġ J",
1205
+ "a g",
1206
+ "Ġ he",
1207
+ "0 0",
1208
+ "is t",
1209
+ "a in",
1210
+ "o d",
1211
+ "a v",
1212
+ "r i",
1213
+ "Ġ E",
1214
+ "Ġ O",
1215
+ "Ġf rom",
1216
+ "Ġc om",
1217
+ "Ġh is",
1218
+ "o p",
1219
+ "Ġp ro",
1220
+ "re s",
1221
+ "i es",
1222
+ "i f",
1223
+ "Ġ v",
1224
+ "or t",
1225
+ "er e",
1226
+ "il l",
1227
+ "l d",
1228
+ "Ġd e",
1229
+ "p p",
1230
+ "Ġs u",
1231
+ "o re",
1232
+ "ĠI n",
1233
+ "Ġ r",
1234
+ "Ġs e",
1235
+ "Ġw ere",
1236
+ "e w",
1237
+ "on g",
1238
+ "ig h",
1239
+ "ar d",
1240
+ "at e",
1241
+ "al l",
1242
+ "ar t",
1243
+ "a k",
1244
+ "ic h",
1245
+ "Ġc h",
1246
+ "Ġo r",
1247
+ "a b",
1248
+ "an t",
1249
+ "u d",
1250
+ "o c",
1251
+ "b er",
1252
+ "Ġe x",
1253
+ "g h",
1254
+ "it y",
1255
+ "at ed",
1256
+ "p t",
1257
+ "es s",
1258
+ "e ar",
1259
+ "Ġ K",
1260
+ "Ġp l",
1261
+ "am e",
1262
+ "q u",
1263
+ "iv e",
1264
+ "ro u",
1265
+ "Ġa re",
1266
+ "Ġ â",
1267
+ "Ġs h",
1268
+ "Ġ k",
1269
+ "ac k",
1270
+ "ec t",
1271
+ "Ġâ Ģ",
1272
+ "Ġ U",
1273
+ "Ġh ad",
1274
+ "s e",
1275
+ "Ġwh ich",
1276
+ "re d",
1277
+ "o v",
1278
+ "ĠS t",
1279
+ "as t",
1280
+ "Ġs p",
1281
+ "i an",
1282
+ "Ġ y",
1283
+ "m ent",
1284
+ "Ġ le",
1285
+ "Ġn ot",
1286
+ "g e",
1287
+ "or d",
1288
+ "r it",
1289
+ "i p",
1290
+ "in e",
1291
+ "el l",
1292
+ "al ly",
1293
+ "ou r",
1294
+ "o st",
1295
+ "igh t",
1296
+ "t her",
1297
+ "a p",
1298
+ "Ġ u",
1299
+ "is h",
1300
+ "ĠC h",
1301
+ "ou n",
1302
+ "i a",
1303
+ "Ġ 3",
1304
+ "av e",
1305
+ "ar y",
1306
+ "u st",
1307
+ "o g",
1308
+ "Ġ2 00",
1309
+ "Ġ un",
1310
+ "ou s",
1311
+ "ir st",
1312
+ "Ġ V",
1313
+ "c c",
1314
+ "Ġin c",
1315
+ "Ġ ;",
1316
+ "Ġcom p",
1317
+ "r u",
1318
+ "ion s",
1319
+ "Ġthe ir",
1320
+ "Ġb ut",
1321
+ "id e",
1322
+ "u re",
1323
+ "s o",
1324
+ "Ġcon t",
1325
+ "Ġin t",
1326
+ "f ter",
1327
+ "ic al",
1328
+ "i al",
1329
+ "Ġa r",
1330
+ "Ġf irst",
1331
+ "ou ld",
1332
+ "Ġit s",
1333
+ "he d",
1334
+ "ĠâĢ ĵ",
1335
+ "Ġw he",
1336
+ "w o",
1337
+ "ou t",
1338
+ "u b",
1339
+ "Ġ2 0",
1340
+ "f f",
1341
+ "Ġ :",
1342
+ "u e",
1343
+ "Ġ her",
1344
+ "ow n",
1345
+ "o k",
1346
+ "Ġal so",
1347
+ "Ġc l",
1348
+ "p er",
1349
+ "ig n",
1350
+ "at er",
1351
+ "r an",
1352
+ "or m",
1353
+ "i e",
1354
+ "om e",
1355
+ "or k",
1356
+ "as s",
1357
+ "i re",
1358
+ "e nd",
1359
+ "Ġre s",
1360
+ "Ġa b",
1361
+ "Ġa d",
1362
+ "Ġ us",
1363
+ "r y",
1364
+ "Ġre c",
1365
+ "Ġh ave",
1366
+ "ag e",
1367
+ "ĠH e",
1368
+ "Ġ 4",
1369
+ "Ġ ro",
1370
+ "m er",
1371
+ "Ġon e",
1372
+ "on d",
1373
+ "l ow",
1374
+ "Ġh as",
1375
+ "ĠT h",
1376
+ "d u",
1377
+ "Ġ 5",
1378
+ "Ġp er",
1379
+ "Ġbe en",
1380
+ "im e",
1381
+ "Ġt wo",
1382
+ "en ce",
1383
+ "l and",
1384
+ "Ġ1 8",
1385
+ ". @",
1386
+ "Ġ@ .@",
1387
+ "ul t",
1388
+ "re e",
1389
+ "ou gh",
1390
+ "i le",
1391
+ "Ġwh o",
1392
+ "ĠA l",
1393
+ "Ġs c",
1394
+ "ur ing",
1395
+ "p l",
1396
+ "or y",
1397
+ "it ion",
1398
+ "r ic",
1399
+ "ation s",
1400
+ "Ġd is",
1401
+ "Ġth is",
1402
+ "Ġb ec",
1403
+ "Ġa pp",
1404
+ "i z",
1405
+ "ĠI t",
1406
+ "a re",
1407
+ "ac h",
1408
+ "l ud",
1409
+ "ad e",
1410
+ "Ġpl ay",
1411
+ "Ġ j",
1412
+ "Ġm an",
1413
+ "ac t",
1414
+ "el y",
1415
+ "Ġp art",
1416
+ "Ġd es",
1417
+ "Ġa g",
1418
+ "Ġthe y",
1419
+ "Ġy ear",
1420
+ "oun t",
1421
+ "Ġ20 1",
1422
+ "Ġo ver",
1423
+ "Ġo ther",
1424
+ "ou nd",
1425
+ "Ġa fter",
1426
+ "i b",
1427
+ "o ver",
1428
+ "Ġs er",
1429
+ "Ġ en",
1430
+ "Ġof f",
1431
+ "Ġ im",
1432
+ "ct ion",
1433
+ "Ġ Y",
1434
+ "k e",
1435
+ "it e",
1436
+ ", @",
1437
+ "Ġ@ ,@",
1438
+ "t e",
1439
+ "ur n",
1440
+ "Ġinc lud",
1441
+ "res s",
1442
+ "an ce",
1443
+ "an g",
1444
+ "Ġat t",
1445
+ "ic e",
1446
+ "ac e",
1447
+ "ar k",
1448
+ "Ġo ut",
1449
+ "w n",
1450
+ "p h",
1451
+ "em ber",
1452
+ "Ġp re",
1453
+ "Ġu p",
1454
+ "en s",
1455
+ "m an",
1456
+ "Ġe v",
1457
+ "Ġt ime",
1458
+ "nd er",
1459
+ "rou gh",
1460
+ "c ed",
1461
+ "Ġf in",
1462
+ "Ġint o",
1463
+ "on e",
1464
+ "p ort",
1465
+ "rou nd",
1466
+ "w e",
1467
+ "re n",
1468
+ "l es",
1469
+ "in t",
1470
+ "ĠO n",
1471
+ "v el",
1472
+ "Ġcom m",
1473
+ "Ġs he",
1474
+ "as on",
1475
+ "am p",
1476
+ "Ġt e",
1477
+ "Ġw ould",
1478
+ "w ard",
1479
+ "Ġm ore",
1480
+ "Ġ 6",
1481
+ "i ed",
1482
+ "os e",
1483
+ "ri b",
1484
+ "ĠU n",
1485
+ "Ġal l",
1486
+ "ing s",
1487
+ "ter n",
1488
+ "c es",
1489
+ "ab le",
1490
+ "Ġw e",
1491
+ "it ed",
1492
+ "e ver",
1493
+ "ent s",
1494
+ "Ġh im",
1495
+ "as ed",
1496
+ "or s",
1497
+ "o y",
1498
+ "o od",
1499
+ "Ġc ent",
1500
+ "i x",
1501
+ "as e",
1502
+ "il d",
1503
+ "ĠA n",
1504
+ "Ġ 7",
1505
+ "Ġw ork",
1506
+ "at es",
1507
+ "i ous",
1508
+ "at h",
1509
+ "Ġp o",
1510
+ "ro p",
1511
+ "ol d",
1512
+ "al s",
1513
+ "is s",
1514
+ "e y",
1515
+ "ic t",
1516
+ "Ġf e",
1517
+ "Ġthe m",
1518
+ "g an",
1519
+ "Ġs ec",
1520
+ "Ġb et",
1521
+ "Ġwhe n",
1522
+ "Ġs ong",
1523
+ "Ġre m",
1524
+ "e p",
1525
+ "f orm",
1526
+ "a il",
1527
+ "f er",
1528
+ "Ġe ar",
1529
+ "ub l",
1530
+ "a w",
1531
+ "Ġk n",
1532
+ "ak e",
1533
+ "a us",
1534
+ "Ġm ost",
1535
+ "Ġcon s",
1536
+ "Ġd uring",
1537
+ "ĠA s",
1538
+ "or th",
1539
+ "Ġn ew",
1540
+ "er ed",
1541
+ "il m",
1542
+ "v ed",
1543
+ "at t",
1544
+ "Ġon ly",
1545
+ "Ġ 9",
1546
+ "Ġd ec",
1547
+ "Ġ 8",
1548
+ "ic k",
1549
+ "Ġg ame",
1550
+ "on s",
1551
+ "u g",
1552
+ "Ġt r",
1553
+ "f t",
1554
+ "ot h",
1555
+ "o ok",
1556
+ "ĠM ar",
1557
+ "re at",
1558
+ "w ay",
1559
+ "Ġc an",
1560
+ "ol low",
1561
+ "ou th",
1562
+ "we en",
1563
+ "ĠE n",
1564
+ "Ġ19 9",
1565
+ "ter s",
1566
+ "Ġre l",
1567
+ "in d",
1568
+ "Ġab out",
1569
+ "Ġse ason",
1570
+ "Ġag ain",
1571
+ "r al",
1572
+ "Ġth ree",
1573
+ "ation al",
1574
+ "Ġu nder",
1575
+ "ul ar",
1576
+ "Ġm e",
1577
+ "Ġth an",
1578
+ "ĠC om",
1579
+ "ĠA r",
1580
+ "h ip",
1581
+ "o b",
1582
+ "Ġn e",
1583
+ "Ġbet ween",
1584
+ "Ġf l",
1585
+ "h n",
1586
+ "v e",
1587
+ "Ġch ar",
1588
+ "Ġc ol",
1589
+ "Ġrec ord",
1590
+ "i ew",
1591
+ "r on",
1592
+ "f ore",
1593
+ "Ġth rough",
1594
+ "is ion",
1595
+ "or n",
1596
+ "Ġ 00",
1597
+ "oc k",
1598
+ "Ġ ver",
1599
+ "Ġl ater",
1600
+ "Ġn um",
1601
+ "Ġe nd",
1602
+ "ol og",
1603
+ "am es",
1604
+ "Ġp os",
1605
+ "Ġw rit",
1606
+ "Ġpro du",
1607
+ "Ġwh ile",
1608
+ "Ġa ct",
1609
+ "Ġre le",
1610
+ "Ġf ilm",
1611
+ "is hed",
1612
+ "Ġp r",
1613
+ "an s",
1614
+ "Ġre g",
1615
+ "Ġfor m",
1616
+ "Ġas s",
1617
+ "ĠS e",
1618
+ "ur y",
1619
+ "t ed",
1620
+ "t s",
1621
+ "Ġm ade",
1622
+ "Ġsu b",
1623
+ "Ġp e",
1624
+ "Ġs o",
1625
+ "or ld",
1626
+ "Ġre t",
1627
+ "ĠN ew",
1628
+ "Ġsp ec",
1629
+ "Ġa cc",
1630
+ "Ġ qu",
1631
+ "Ġwhe re",
1632
+ "en er",
1633
+ "Ġm ov",
1634
+ "he s",
1635
+ "mer ic",
1636
+ "at ing",
1637
+ "Ġin ter",
1638
+ "ĠL e",
1639
+ "ĠA meric",
1640
+ "Ġ ra",
1641
+ "Ġs ome",
1642
+ "Ġc o",
1643
+ "Ġl ar",
1644
+ "Ġb u",
1645
+ "Ġde f",
1646
+ "b um",
1647
+ "Ġa c",
1648
+ "Ġm us",
1649
+ "Ġf ollow",
1650
+ "ĠA t",
1651
+ "in s",
1652
+ "iv ed",
1653
+ "if ic",
1654
+ "u al",
1655
+ "Ġa m",
1656
+ "Ġsu ch",
1657
+ "Ġsec ond",
1658
+ "i ke",
1659
+ "Ġf our",
1660
+ "Ġin d",
1661
+ "an n",
1662
+ "he n",
1663
+ "Ġus ed",
1664
+ "ĠR e",
1665
+ "ic s",
1666
+ "le ct",
1667
+ "Ġd ay",
1668
+ "i el",
1669
+ "il y",
1670
+ "ĠTh is",
1671
+ "Ġ 0",
1672
+ "Ġp ubl",
1673
+ "Ġc all",
1674
+ "ĠJ o",
1675
+ "l l",
1676
+ "Ġal bum",
1677
+ "Ġ00 0",
1678
+ "ran s",
1679
+ "Ġd o",
1680
+ "an y",
1681
+ "Ġbe fore",
1682
+ "ro s",
1683
+ "ĠS h",
1684
+ "Ġs y",
1685
+ "a id",
1686
+ "ĠEn g",
1687
+ "Ġbe ing",
1688
+ "Ġ1 0",
1689
+ "u c",
1690
+ "Ġe p",
1691
+ "Ġsu pp",
1692
+ "Ġthe re",
1693
+ "Ġyear s",
1694
+ "ar s",
1695
+ "ow ever",
1696
+ "Ġ ent",
1697
+ "if e",
1698
+ "Ġh igh",
1699
+ "Ġf ound",
1700
+ "ir d",
1701
+ "Ġn o",
1702
+ "Ġs et",
1703
+ "in es",
1704
+ "iv er",
1705
+ "i o",
1706
+ "ot her",
1707
+ "j ect",
1708
+ "Ġs ur",
1709
+ "a j",
1710
+ "t en",
1711
+ "Ġt ra",
1712
+ "Ġ1 2",
1713
+ "is ed",
1714
+ "it ies",
1715
+ "vel op",
1716
+ "Ġb l",
1717
+ "al e",
1718
+ "Ġser ies",
1719
+ "Ġl oc",
1720
+ "Ġnum ber",
1721
+ "Ġp res",
1722
+ "an e",
1723
+ "aus e",
1724
+ "od e",
1725
+ "e k",
1726
+ "t on",
1727
+ "ĠS c",
1728
+ "i er",
1729
+ "is e",
1730
+ "Ġse ver",
1731
+ "in ce",
1732
+ "Ġb oth",
1733
+ "an k",
1734
+ "ro w",
1735
+ "ire ct",
1736
+ "s on",
1737
+ "Ġthe n",
1738
+ "ĠB rit",
1739
+ "i et",
1740
+ "Ġ1 6",
1741
+ "Ġep is",
1742
+ "Ġinclud ing",
1743
+ "it s",
1744
+ "ig in",
1745
+ "p r",
1746
+ "Ġ /",
1747
+ "Ġagain st",
1748
+ "Ġw ell",
1749
+ "Ġbec ame",
1750
+ "Ġex p",
1751
+ "Ġkn own",
1752
+ "Ġt rans",
1753
+ "Ġchar ac",
1754
+ "ĠâĢ Ķ",
1755
+ "r am",
1756
+ "Ġb ack",
1757
+ "Ġad d",
1758
+ "Ġp op",
1759
+ "Ġg o",
1760
+ "ur ch",
1761
+ "Ġdes c",
1762
+ "Ġs ing",
1763
+ "iel d",
1764
+ "Ġper form",
1765
+ "ain ed",
1766
+ "Ġre ce",
1767
+ "id ent",
1768
+ "Ġe m",
1769
+ "er t",
1770
+ "u res",
1771
+ "Ġin v",
1772
+ "Ġde p",
1773
+ "Ġ19 8",
1774
+ "a ir",
1775
+ "er n",
1776
+ "at her",
1777
+ "f ul",
1778
+ "Ġ Z",
1779
+ "Ġm on",
1780
+ "Ġman y",
1781
+ "Ġm ain",
1782
+ "Ġst ud",
1783
+ "Ġl ong",
1784
+ "in n",
1785
+ "th ough",
1786
+ "u p",
1787
+ "o ol",
1788
+ "ĠUn ited",
1789
+ "l ed",
1790
+ "em ent",
1791
+ "Ġ1 5",
1792
+ "ow er",
1793
+ "ĠJo hn",
1794
+ "Ġo p",
1795
+ "Ġ1 1",
1796
+ "in ed",
1797
+ "Ġm et",
1798
+ "o ber",
1799
+ "le y",
1800
+ "Ġ1 7",
1801
+ "Ġcent ury",
1802
+ "Ġte am",
1803
+ "Ġ est",
1804
+ "ĠA fter",
1805
+ "y l",
1806
+ "Ġm in",
1807
+ "u ch",
1808
+ "ut e",
1809
+ "Ġde velop",
1810
+ "ĠS he",
1811
+ "i am",
1812
+ "Ġsh ow",
1813
+ "el f",
1814
+ "Ġre p",
1815
+ "Ġcon c",
1816
+ "at ive",
1817
+ "Ġc re",
1818
+ "over n",
1819
+ "a red",
1820
+ "Ġ19 4",
1821
+ "Ġor igin",
1822
+ "Ġs m",
1823
+ "iv ers",
1824
+ "a z",
1825
+ "Ġle ad",
1826
+ "Ġsever al",
1827
+ "a h",
1828
+ "Ġo b",
1829
+ "Ġre v",
1830
+ "Ġm ill",
1831
+ "er m",
1832
+ "u ally",
1833
+ "o ot",
1834
+ "Ġbe gan",
1835
+ "Ġ19 6"
1836
+ ]
1837
+ }
1838
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 512,
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
vocab.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 1,
3
+ "\"": 2,
4
+ "#": 3,
5
+ "$": 4,
6
+ "%": 5,
7
+ "&": 6,
8
+ "'": 7,
9
+ "(": 8,
10
+ ")": 9,
11
+ "*": 10,
12
+ "+": 11,
13
+ ",": 12,
14
+ ",@": 624,
15
+ "-": 13,
16
+ "-@": 339,
17
+ ".": 14,
18
+ ".@": 573,
19
+ "/": 15,
20
+ "0": 16,
21
+ "00": 395,
22
+ "1": 17,
23
+ "2": 18,
24
+ "3": 19,
25
+ "4": 20,
26
+ "5": 21,
27
+ "6": 22,
28
+ "7": 23,
29
+ "8": 24,
30
+ "9": 25,
31
+ ":": 26,
32
+ ";": 27,
33
+ "<": 28,
34
+ "<|endoftext|>": 0,
35
+ "=": 29,
36
+ ">": 30,
37
+ "?": 31,
38
+ "@": 32,
39
+ "A": 33,
40
+ "B": 34,
41
+ "C": 35,
42
+ "D": 36,
43
+ "E": 37,
44
+ "F": 38,
45
+ "G": 39,
46
+ "H": 40,
47
+ "I": 41,
48
+ "J": 42,
49
+ "K": 43,
50
+ "L": 44,
51
+ "M": 45,
52
+ "N": 46,
53
+ "O": 47,
54
+ "P": 48,
55
+ "Q": 49,
56
+ "R": 50,
57
+ "S": 51,
58
+ "T": 52,
59
+ "U": 53,
60
+ "V": 54,
61
+ "W": 55,
62
+ "X": 56,
63
+ "Y": 57,
64
+ "Z": 58,
65
+ "[": 59,
66
+ "\\": 60,
67
+ "]": 61,
68
+ "^": 62,
69
+ "_": 63,
70
+ "`": 64,
71
+ "a": 65,
72
+ "ab": 435,
73
+ "able": 677,
74
+ "ac": 320,
75
+ "ace": 634,
76
+ "ach": 595,
77
+ "ack": 457,
78
+ "act": 601,
79
+ "ad": 319,
80
+ "ade": 597,
81
+ "ag": 393,
82
+ "age": 554,
83
+ "ah": 1015,
84
+ "aid": 873,
85
+ "ail": 714,
86
+ "ain": 397,
87
+ "ained": 953,
88
+ "air": 962,
89
+ "aj": 897,
90
+ "ak": 431,
91
+ "ake": 720,
92
+ "al": 285,
93
+ "ale": 905,
94
+ "all": 429,
95
+ "ally": 480,
96
+ "als": 700,
97
+ "am": 314,
98
+ "ame": 449,
99
+ "ames": 791,
100
+ "amp": 663,
101
+ "an": 283,
102
+ "ance": 630,
103
+ "and": 388,
104
+ "ane": 910,
105
+ "ang": 631,
106
+ "ank": 921,
107
+ "ann": 849,
108
+ "ans": 801,
109
+ "ant": 436,
110
+ "any": 868,
111
+ "ap": 485,
112
+ "ar": 280,
113
+ "ard": 427,
114
+ "are": 594,
115
+ "ared": 1007,
116
+ "ark": 635,
117
+ "ars": 882,
118
+ "art": 430,
119
+ "ary": 493,
120
+ "as": 289,
121
+ "ase": 689,
122
+ "ased": 683,
123
+ "ason": 662,
124
+ "ass": 544,
125
+ "ast": 467,
126
+ "at": 271,
127
+ "ate": 428,
128
+ "ated": 443,
129
+ "ater": 538,
130
+ "ates": 694,
131
+ "ath": 696,
132
+ "ather": 964,
133
+ "ating": 824,
134
+ "ation": 354,
135
+ "ational": 761,
136
+ "ations": 587,
137
+ "ative": 1004,
138
+ "att": 731,
139
+ "aus": 721,
140
+ "ause": 911,
141
+ "av": 399,
142
+ "ave": 492,
143
+ "aw": 718,
144
+ "ay": 351,
145
+ "az": 1012,
146
+ "b": 66,
147
+ "ber": 439,
148
+ "bum": 834,
149
+ "c": 67,
150
+ "cc": 501,
151
+ "ce": 361,
152
+ "ced": 648,
153
+ "ces": 676,
154
+ "ch": 372,
155
+ "ct": 384,
156
+ "ction": 620,
157
+ "d": 68,
158
+ "du": 564,
159
+ "e": 69,
160
+ "ear": 446,
161
+ "ec": 325,
162
+ "ect": 458,
163
+ "ed": 267,
164
+ "ek": 913,
165
+ "el": 311,
166
+ "elf": 1001,
167
+ "ell": 479,
168
+ "ely": 602,
169
+ "em": 366,
170
+ "ember": 639,
171
+ "ement": 978,
172
+ "en": 276,
173
+ "ence": 570,
174
+ "end": 546,
175
+ "ener": 820,
176
+ "ens": 642,
177
+ "ent": 305,
178
+ "ents": 681,
179
+ "ep": 712,
180
+ "er": 262,
181
+ "ere": 413,
182
+ "ered": 728,
183
+ "erm": 1019,
184
+ "ern": 963,
185
+ "ers": 383,
186
+ "ert": 957,
187
+ "es": 279,
188
+ "ess": 445,
189
+ "est": 391,
190
+ "et": 332,
191
+ "ever": 680,
192
+ "ew": 424,
193
+ "ey": 702,
194
+ "f": 70,
195
+ "fer": 715,
196
+ "ff": 528,
197
+ "fore": 780,
198
+ "form": 713,
199
+ "ft": 741,
200
+ "fter": 514,
201
+ "ful": 965,
202
+ "g": 71,
203
+ "gan": 706,
204
+ "ge": 474,
205
+ "gh": 441,
206
+ "h": 72,
207
+ "he": 258,
208
+ "hed": 521,
209
+ "hen": 850,
210
+ "her": 357,
211
+ "hes": 822,
212
+ "hip": 768,
213
+ "hn": 773,
214
+ "i": 73,
215
+ "ia": 490,
216
+ "ial": 516,
217
+ "iam": 999,
218
+ "ian": 469,
219
+ "ib": 614,
220
+ "ic": 292,
221
+ "ical": 515,
222
+ "ice": 633,
223
+ "ich": 432,
224
+ "ick": 736,
225
+ "ics": 853,
226
+ "ict": 703,
227
+ "id": 334,
228
+ "ide": 509,
229
+ "ident": 955,
230
+ "ie": 541,
231
+ "ied": 669,
232
+ "iel": 856,
233
+ "ield": 951,
234
+ "ier": 916,
235
+ "ies": 409,
236
+ "iet": 927,
237
+ "iew": 778,
238
+ "if": 410,
239
+ "ife": 885,
240
+ "ific": 841,
241
+ "ig": 341,
242
+ "igh": 426,
243
+ "ight": 483,
244
+ "igin": 932,
245
+ "ign": 537,
246
+ "ike": 846,
247
+ "il": 306,
248
+ "ild": 690,
249
+ "ile": 578,
250
+ "ill": 414,
251
+ "ilm": 729,
252
+ "ily": 857,
253
+ "im": 336,
254
+ "ime": 568,
255
+ "in": 260,
256
+ "ince": 919,
257
+ "ind": 755,
258
+ "ine": 478,
259
+ "ined": 984,
260
+ "ines": 891,
261
+ "ing": 286,
262
+ "ings": 674,
263
+ "inn": 972,
264
+ "ins": 839,
265
+ "int": 657,
266
+ "io": 893,
267
+ "ion": 296,
268
+ "ions": 506,
269
+ "ious": 695,
270
+ "ip": 477,
271
+ "ir": 338,
272
+ "ird": 888,
273
+ "ire": 545,
274
+ "irect": 923,
275
+ "irst": 499,
276
+ "is": 278,
277
+ "ise": 917,
278
+ "ised": 901,
279
+ "ish": 487,
280
+ "ished": 799,
281
+ "ision": 782,
282
+ "iss": 701,
283
+ "ist": 396,
284
+ "it": 274,
285
+ "ite": 623,
286
+ "ited": 679,
287
+ "ith": 350,
288
+ "ities": 902,
289
+ "ition": 585,
290
+ "its": 931,
291
+ "ity": 442,
292
+ "iv": 335,
293
+ "ive": 451,
294
+ "ived": 840,
295
+ "iver": 892,
296
+ "ivers": 1011,
297
+ "ix": 688,
298
+ "iz": 592,
299
+ "j": 74,
300
+ "ject": 895,
301
+ "k": 75,
302
+ "ke": 622,
303
+ "l": 76,
304
+ "land": 571,
305
+ "ld": 415,
306
+ "le": 297,
307
+ "lect": 854,
308
+ "led": 977,
309
+ "les": 656,
310
+ "ley": 987,
311
+ "ll": 863,
312
+ "low": 561,
313
+ "lud": 596,
314
+ "ly": 327,
315
+ "m": 77,
316
+ "man": 643,
317
+ "ment": 471,
318
+ "mer": 558,
319
+ "meric": 823,
320
+ "n": 78,
321
+ "nd": 270,
322
+ "nder": 646,
323
+ "o": 79,
324
+ "ob": 769,
325
+ "ober": 986,
326
+ "oc": 438,
327
+ "ock": 785,
328
+ "od": 398,
329
+ "ode": 912,
330
+ "og": 495,
331
+ "ok": 533,
332
+ "ol": 333,
333
+ "old": 699,
334
+ "ollow": 748,
335
+ "olog": 790,
336
+ "om": 312,
337
+ "ome": 542,
338
+ "on": 263,
339
+ "ond": 560,
340
+ "one": 651,
341
+ "ong": 425,
342
+ "ons": 738,
343
+ "ood": 686,
344
+ "ook": 743,
345
+ "ool": 975,
346
+ "oot": 1021,
347
+ "op": 406,
348
+ "or": 273,
349
+ "ord": 475,
350
+ "ore": 419,
351
+ "ork": 543,
352
+ "orld": 813,
353
+ "orm": 540,
354
+ "orn": 783,
355
+ "ors": 684,
356
+ "ort": 412,
357
+ "orth": 726,
358
+ "ory": 584,
359
+ "os": 379,
360
+ "ose": 670,
361
+ "ost": 482,
362
+ "ot": 342,
363
+ "oth": 742,
364
+ "other": 894,
365
+ "ou": 298,
366
+ "ough": 577,
367
+ "ould": 519,
368
+ "oun": 489,
369
+ "ound": 612,
370
+ "ount": 608,
371
+ "our": 481,
372
+ "ous": 498,
373
+ "out": 525,
374
+ "outh": 749,
375
+ "ov": 465,
376
+ "over": 615,
377
+ "overn": 1006,
378
+ "ow": 347,
379
+ "ower": 980,
380
+ "owever": 883,
381
+ "own": 532,
382
+ "oy": 685,
383
+ "p": 80,
384
+ "per": 536,
385
+ "ph": 638,
386
+ "pl": 583,
387
+ "port": 652,
388
+ "pp": 417,
389
+ "pr": 933,
390
+ "pt": 444,
391
+ "q": 81,
392
+ "qu": 450,
393
+ "r": 82,
394
+ "ra": 377,
395
+ "ral": 759,
396
+ "ram": 943,
397
+ "ran": 539,
398
+ "rans": 866,
399
+ "re": 265,
400
+ "reat": 745,
401
+ "red": 464,
402
+ "ree": 576,
403
+ "ren": 655,
404
+ "res": 408,
405
+ "ress": 629,
406
+ "ri": 400,
407
+ "rib": 671,
408
+ "ric": 586,
409
+ "rit": 476,
410
+ "ro": 291,
411
+ "rom": 387,
412
+ "ron": 779,
413
+ "rop": 698,
414
+ "ros": 870,
415
+ "rou": 452,
416
+ "rough": 647,
417
+ "round": 653,
418
+ "row": 922,
419
+ "ru": 505,
420
+ "ry": 551,
421
+ "s": 83,
422
+ "se": 462,
423
+ "so": 511,
424
+ "son": 924,
425
+ "st": 309,
426
+ "t": 84,
427
+ "te": 626,
428
+ "ted": 807,
429
+ "ten": 898,
430
+ "ter": 343,
431
+ "tern": 675,
432
+ "ters": 753,
433
+ "th": 362,
434
+ "ther": 484,
435
+ "though": 973,
436
+ "ton": 914,
437
+ "ts": 808,
438
+ "u": 85,
439
+ "ual": 842,
440
+ "ually": 1020,
441
+ "ub": 526,
442
+ "ubl": 717,
443
+ "uc": 877,
444
+ "uch": 995,
445
+ "ud": 437,
446
+ "ue": 530,
447
+ "ug": 739,
448
+ "ul": 369,
449
+ "ular": 763,
450
+ "ult": 575,
451
+ "um": 390,
452
+ "un": 365,
453
+ "up": 974,
454
+ "ur": 323,
455
+ "urch": 948,
456
+ "ure": 510,
457
+ "ures": 958,
458
+ "uring": 582,
459
+ "urn": 627,
460
+ "ury": 806,
461
+ "us": 346,
462
+ "ust": 494,
463
+ "ut": 349,
464
+ "ute": 996,
465
+ "v": 86,
466
+ "ve": 774,
467
+ "ved": 730,
468
+ "vel": 659,
469
+ "velop": 903,
470
+ "ver": 355,
471
+ "w": 87,
472
+ "ward": 666,
473
+ "way": 746,
474
+ "we": 654,
475
+ "ween": 750,
476
+ "wn": 637,
477
+ "wo": 524,
478
+ "x": 88,
479
+ "y": 89,
480
+ "yl": 993,
481
+ "z": 90,
482
+ "{": 91,
483
+ "|": 92,
484
+ "}": 93,
485
+ "~": 94,
486
+ "¡": 95,
487
+ "¢": 96,
488
+ "£": 97,
489
+ "¤": 98,
490
+ "¥": 99,
491
+ "¦": 100,
492
+ "§": 101,
493
+ "¨": 102,
494
+ "©": 103,
495
+ "ª": 104,
496
+ "«": 105,
497
+ "¬": 106,
498
+ "®": 107,
499
+ "¯": 108,
500
+ "°": 109,
501
+ "±": 110,
502
+ "²": 111,
503
+ "³": 112,
504
+ "´": 113,
505
+ "µ": 114,
506
+ "¶": 115,
507
+ "·": 116,
508
+ "¸": 117,
509
+ "¹": 118,
510
+ "º": 119,
511
+ "»": 120,
512
+ "¼": 121,
513
+ "½": 122,
514
+ "¾": 123,
515
+ "¿": 124,
516
+ "À": 125,
517
+ "Á": 126,
518
+ "Â": 127,
519
+ "Ã": 128,
520
+ "Ä": 129,
521
+ "Å": 130,
522
+ "Æ": 131,
523
+ "Ç": 132,
524
+ "È": 133,
525
+ "É": 134,
526
+ "Ê": 135,
527
+ "Ë": 136,
528
+ "Ì": 137,
529
+ "Í": 138,
530
+ "Î": 139,
531
+ "Ï": 140,
532
+ "Ð": 141,
533
+ "Ñ": 142,
534
+ "Ò": 143,
535
+ "Ó": 144,
536
+ "Ô": 145,
537
+ "Õ": 146,
538
+ "Ö": 147,
539
+ "×": 148,
540
+ "Ø": 149,
541
+ "Ù": 150,
542
+ "Ú": 151,
543
+ "Û": 152,
544
+ "Ü": 153,
545
+ "Ý": 154,
546
+ "Þ": 155,
547
+ "ß": 156,
548
+ "à": 157,
549
+ "á": 158,
550
+ "â": 159,
551
+ "ã": 160,
552
+ "ä": 161,
553
+ "å": 162,
554
+ "æ": 163,
555
+ "ç": 164,
556
+ "è": 165,
557
+ "é": 166,
558
+ "ê": 167,
559
+ "ë": 168,
560
+ "ì": 169,
561
+ "í": 170,
562
+ "î": 171,
563
+ "ï": 172,
564
+ "ð": 173,
565
+ "ñ": 174,
566
+ "ò": 175,
567
+ "ó": 176,
568
+ "ô": 177,
569
+ "õ": 178,
570
+ "ö": 179,
571
+ "÷": 180,
572
+ "ø": 181,
573
+ "ù": 182,
574
+ "ú": 183,
575
+ "û": 184,
576
+ "ü": 185,
577
+ "ý": 186,
578
+ "þ": 187,
579
+ "ÿ": 188,
580
+ "Ā": 189,
581
+ "ā": 190,
582
+ "Ă": 191,
583
+ "ă": 192,
584
+ "Ą": 193,
585
+ "ą": 194,
586
+ "Ć": 195,
587
+ "ć": 196,
588
+ "Ĉ": 197,
589
+ "ĉ": 198,
590
+ "Ċ": 199,
591
+ "ċ": 200,
592
+ "Č": 201,
593
+ "č": 202,
594
+ "Ď": 203,
595
+ "ď": 204,
596
+ "Đ": 205,
597
+ "đ": 206,
598
+ "Ē": 207,
599
+ "ē": 208,
600
+ "Ĕ": 209,
601
+ "ĕ": 210,
602
+ "Ė": 211,
603
+ "ė": 212,
604
+ "Ę": 213,
605
+ "ę": 214,
606
+ "Ě": 215,
607
+ "ě": 216,
608
+ "Ĝ": 217,
609
+ "ĝ": 218,
610
+ "Ğ": 219,
611
+ "ğ": 220,
612
+ "Ġ": 221,
613
+ "Ġ\"": 302,
614
+ "Ġ'": 331,
615
+ "Ġ(": 374,
616
+ "Ġ)": 373,
617
+ "Ġ,": 264,
618
+ "Ġ.": 272,
619
+ "Ġ/": 934,
620
+ "Ġ0": 859,
621
+ "Ġ00": 784,
622
+ "Ġ000": 865,
623
+ "Ġ1": 308,
624
+ "Ġ10": 876,
625
+ "Ġ11": 983,
626
+ "Ġ12": 900,
627
+ "Ġ15": 979,
628
+ "Ġ16": 928,
629
+ "Ġ17": 988,
630
+ "Ġ18": 572,
631
+ "Ġ19": 386,
632
+ "Ġ194": 1008,
633
+ "Ġ196": 1023,
634
+ "Ġ198": 961,
635
+ "Ġ199": 752,
636
+ "Ġ2": 352,
637
+ "Ġ20": 527,
638
+ "Ġ200": 496,
639
+ "Ġ201": 609,
640
+ "Ġ3": 491,
641
+ "Ġ4": 556,
642
+ "Ġ5": 565,
643
+ "Ġ6": 668,
644
+ "Ġ7": 692,
645
+ "Ġ8": 735,
646
+ "Ġ9": 733,
647
+ "Ġ:": 529,
648
+ "Ġ;": 503,
649
+ "Ġ=": 301,
650
+ "Ġ@": 318,
651
+ "Ġ@,@": 625,
652
+ "Ġ@-@": 340,
653
+ "Ġ@.@": 574,
654
+ "ĠA": 303,
655
+ "ĠAfter": 992,
656
+ "ĠAl": 580,
657
+ "ĠAmeric": 827,
658
+ "ĠAn": 691,
659
+ "ĠAr": 767,
660
+ "ĠAs": 725,
661
+ "ĠAt": 838,
662
+ "ĠB": 328,
663
+ "ĠBrit": 926,
664
+ "ĠC": 310,
665
+ "ĠCh": 488,
666
+ "ĠCom": 766,
667
+ "ĠD": 363,
668
+ "ĠE": 401,
669
+ "ĠEn": 751,
670
+ "ĠEng": 874,
671
+ "ĠF": 367,
672
+ "ĠG": 378,
673
+ "ĠH": 345,
674
+ "ĠHe": 555,
675
+ "ĠI": 329,
676
+ "ĠIn": 420,
677
+ "ĠIt": 593,
678
+ "ĠJ": 392,
679
+ "ĠJo": 862,
680
+ "ĠJohn": 981,
681
+ "ĠK": 447,
682
+ "ĠL": 380,
683
+ "ĠLe": 826,
684
+ "ĠM": 322,
685
+ "ĠMar": 744,
686
+ "ĠN": 381,
687
+ "ĠNew": 815,
688
+ "ĠO": 402,
689
+ "ĠOn": 658,
690
+ "ĠP": 353,
691
+ "ĠR": 360,
692
+ "ĠRe": 852,
693
+ "ĠS": 304,
694
+ "ĠSc": 915,
695
+ "ĠSe": 805,
696
+ "ĠSh": 871,
697
+ "ĠShe": 998,
698
+ "ĠSt": 466,
699
+ "ĠT": 299,
700
+ "ĠTh": 563,
701
+ "ĠThe": 324,
702
+ "ĠThis": 858,
703
+ "ĠU": 460,
704
+ "��Un": 672,
705
+ "ĠUnited": 976,
706
+ "ĠV": 500,
707
+ "ĠW": 375,
708
+ "ĠY": 621,
709
+ "ĠZ": 966,
710
+ "Ġa": 259,
711
+ "Ġab": 548,
712
+ "Ġabout": 756,
713
+ "Ġac": 835,
714
+ "Ġacc": 817,
715
+ "Ġact": 796,
716
+ "Ġad": 549,
717
+ "Ġadd": 945,
718
+ "Ġafter": 613,
719
+ "Ġag": 605,
720
+ "Ġagain": 758,
721
+ "Ġagainst": 935,
722
+ "Ġal": 371,
723
+ "Ġalbum": 864,
724
+ "Ġall": 673,
725
+ "Ġalso": 534,
726
+ "Ġam": 843,
727
+ "Ġan": 389,
728
+ "Ġand": 288,
729
+ "Ġapp": 591,
730
+ "Ġar": 517,
731
+ "Ġare": 453,
732
+ "Ġas": 344,
733
+ "Ġass": 804,
734
+ "Ġat": 382,
735
+ "Ġatt": 632,
736
+ "Ġb": 282,
737
+ "Ġback": 944,
738
+ "Ġbe": 356,
739
+ "Ġbec": 590,
740
+ "Ġbecame": 937,
741
+ "Ġbeen": 567,
742
+ "Ġbefore": 869,
743
+ "Ġbegan": 1022,
744
+ "Ġbeing": 875,
745
+ "Ġbet": 708,
746
+ "Ġbetween": 771,
747
+ "Ġbl": 904,
748
+ "Ġboth": 920,
749
+ "Ġbu": 832,
750
+ "Ġbut": 508,
751
+ "Ġby": 370,
752
+ "Ġc": 275,
753
+ "Ġcall": 861,
754
+ "Ġcan": 747,
755
+ "Ġcent": 687,
756
+ "Ġcentury": 989,
757
+ "Ġch": 433,
758
+ "Ġchar": 775,
759
+ "Ġcharac": 941,
760
+ "Ġcl": 535,
761
+ "Ġco": 830,
762
+ "Ġcol": 776,
763
+ "Ġcom": 404,
764
+ "Ġcomm": 660,
765
+ "Ġcomp": 504,
766
+ "Ġcon": 376,
767
+ "Ġconc": 1003,
768
+ "Ġcons": 723,
769
+ "Ġcont": 512,
770
+ "Ġcre": 1005,
771
+ "Ġd": 294,
772
+ "Ġday": 855,
773
+ "Ġde": 416,
774
+ "Ġdec": 734,
775
+ "Ġdef": 833,
776
+ "Ġdep": 960,
777
+ "Ġdes": 604,
778
+ "Ġdesc": 949,
779
+ "Ġdevelop": 997,
780
+ "Ġdis": 588,
781
+ "Ġdo": 867,
782
+ "Ġduring": 724,
783
+ "Ġe": 316,
784
+ "Ġear": 716,
785
+ "Ġem": 956,
786
+ "Ġen": 617,
787
+ "Ġend": 789,
788
+ "Ġent": 884,
789
+ "Ġep": 878,
790
+ "Ġepis": 929,
791
+ "Ġest": 991,
792
+ "Ġev": 644,
793
+ "Ġex": 440,
794
+ "Ġexp": 938,
795
+ "Ġf": 277,
796
+ "Ġfe": 704,
797
+ "Ġfilm": 798,
798
+ "Ġfin": 649,
799
+ "Ġfirst": 518,
800
+ "Ġfl": 772,
801
+ "Ġfollow": 837,
802
+ "Ġfor": 337,
803
+ "Ġform": 803,
804
+ "Ġfound": 887,
805
+ "Ġfour": 847,
806
+ "Ġfrom": 403,
807
+ "Ġg": 330,
808
+ "Ġgame": 737,
809
+ "Ġgo": 947,
810
+ "Ġh": 295,
811
+ "Ġhad": 461,
812
+ "Ġhas": 562,
813
+ "Ġhave": 553,
814
+ "Ġhe": 394,
815
+ "Ġher": 531,
816
+ "Ġhigh": 886,
817
+ "Ġhim": 682,
818
+ "Ġhis": 405,
819
+ "Ġim": 619,
820
+ "Ġin": 284,
821
+ "Ġinc": 502,
822
+ "Ġinclud": 628,
823
+ "Ġincluding": 930,
824
+ "Ġind": 848,
825
+ "Ġint": 513,
826
+ "Ġinter": 825,
827
+ "Ġinto": 650,
828
+ "Ġinv": 959,
829
+ "Ġis": 364,
830
+ "Ġit": 385,
831
+ "Ġits": 520,
832
+ "Ġj": 599,
833
+ "Ġk": 456,
834
+ "Ġkn": 719,
835
+ "Ġknown": 939,
836
+ "Ġl": 313,
837
+ "Ġlar": 831,
838
+ "Ġlater": 787,
839
+ "Ġle": 472,
840
+ "Ġlead": 1013,
841
+ "Ġloc": 907,
842
+ "Ġlong": 971,
843
+ "Ġm": 293,
844
+ "Ġmade": 809,
845
+ "Ġmain": 969,
846
+ "Ġman": 600,
847
+ "Ġmany": 968,
848
+ "Ġme": 764,
849
+ "Ġmet": 985,
850
+ "Ġmill": 1018,
851
+ "Ġmin": 994,
852
+ "Ġmon": 967,
853
+ "Ġmore": 667,
854
+ "Ġmost": 722,
855
+ "Ġmov": 821,
856
+ "Ġmus": 836,
857
+ "Ġn": 317,
858
+ "Ġne": 770,
859
+ "Ġnew": 727,
860
+ "Ġno": 889,
861
+ "Ġnot": 473,
862
+ "Ġnum": 788,
863
+ "Ġnumber": 908,
864
+ "Ġo": 268,
865
+ "Ġob": 1016,
866
+ "Ġof": 281,
867
+ "Ġoff": 618,
868
+ "Ġon": 326,
869
+ "Ġone": 559,
870
+ "Ġonly": 732,
871
+ "Ġop": 982,
872
+ "Ġor": 434,
873
+ "Ġorigin": 1009,
874
+ "Ġother": 611,
875
+ "Ġout": 636,
876
+ "Ġover": 610,
877
+ "Ġp": 287,
878
+ "Ġpart": 603,
879
+ "Ġpe": 811,
880
+ "Ġper": 566,
881
+ "Ġperform": 952,
882
+ "Ġpl": 448,
883
+ "Ġplay": 598,
884
+ "Ġpo": 697,
885
+ "Ġpop": 946,
886
+ "Ġpos": 792,
887
+ "Ġpr": 800,
888
+ "Ġpre": 640,
889
+ "Ġpres": 909,
890
+ "Ġpro": 407,
891
+ "Ġprodu": 794,
892
+ "Ġpubl": 860,
893
+ "Ġqu": 818,
894
+ "Ġr": 421,
895
+ "Ġra": 828,
896
+ "Ġre": 300,
897
+ "Ġrec": 552,
898
+ "Ġrece": 954,
899
+ "Ġrecord": 777,
900
+ "Ġreg": 802,
901
+ "Ġrel": 754,
902
+ "Ġrele": 797,
903
+ "Ġrem": 711,
904
+ "Ġrep": 1002,
905
+ "Ġres": 547,
906
+ "Ġret": 814,
907
+ "Ġrev": 1017,
908
+ "Ġro": 557,
909
+ "Ġs": 266,
910
+ "Ġsc": 581,
911
+ "Ġse": 422,
912
+ "Ġseason": 757,
913
+ "Ġsec": 707,
914
+ "Ġsecond": 845,
915
+ "Ġser": 616,
916
+ "Ġseries": 906,
917
+ "Ġset": 890,
918
+ "Ġsever": 918,
919
+ "Ġseveral": 1014,
920
+ "Ġsh": 455,
921
+ "Ġshe": 661,
922
+ "Ġshow": 1000,
923
+ "Ġsing": 950,
924
+ "Ġsm": 1010,
925
+ "Ġso": 812,
926
+ "Ġsome": 829,
927
+ "Ġsong": 710,
928
+ "Ġsp": 468,
929
+ "Ġspec": 816,
930
+ "Ġst": 348,
931
+ "Ġstud": 970,
932
+ "Ġsu": 418,
933
+ "Ġsub": 810,
934
+ "Ġsuch": 844,
935
+ "Ġsupp": 879,
936
+ "Ġsur": 896,
937
+ "Ġsy": 872,
938
+ "Ġt": 257,
939
+ "Ġte": 664,
940
+ "Ġteam": 990,
941
+ "Ġth": 307,
942
+ "Ġthan": 765,
943
+ "Ġthat": 358,
944
+ "Ġthe": 261,
945
+ "Ġtheir": 507,
946
+ "Ġthem": 705,
947
+ "Ġthen": 925,
948
+ "Ġthere": 880,
949
+ "Ġthey": 606,
950
+ "Ġthis": 589,
951
+ "Ġthree": 760,
952
+ "Ġthrough": 781,
953
+ "Ġtime": 645,
954
+ "Ġto": 290,
955
+ "Ġtr": 740,
956
+ "Ġtra": 899,
957
+ "Ġtrans": 940,
958
+ "Ġtwo": 569,
959
+ "Ġu": 486,
960
+ "Ġun": 497,
961
+ "Ġunder": 762,
962
+ "Ġup": 641,
963
+ "Ġus": 550,
964
+ "Ġused": 851,
965
+ "Ġv": 411,
966
+ "Ġver": 786,
967
+ "Ġw": 269,
968
+ "Ġwas": 321,
969
+ "Ġwe": 678,
970
+ "Ġwell": 936,
971
+ "Ġwere": 423,
972
+ "Ġwh": 368,
973
+ "Ġwhe": 523,
974
+ "Ġwhen": 709,
975
+ "Ġwhere": 819,
976
+ "Ġwhich": 463,
977
+ "Ġwhile": 795,
978
+ "Ġwho": 579,
979
+ "Ġwith": 359,
980
+ "Ġwork": 693,
981
+ "Ġwould": 665,
982
+ "Ġwrit": 793,
983
+ "Ġy": 470,
984
+ "Ġyear": 607,
985
+ "Ġyears": 881,
986
+ "Ġâ": 454,
987
+ "ĠâĢ": 459,
988
+ "ĠâĢĵ": 522,
989
+ "ĠâĢĶ": 942,
990
+ "ĠĊ": 315,
991
+ "ġ": 222,
992
+ "Ģ": 223,
993
+ "ģ": 224,
994
+ "Ĥ": 225,
995
+ "ĥ": 226,
996
+ "Ħ": 227,
997
+ "ħ": 228,
998
+ "Ĩ": 229,
999
+ "ĩ": 230,
1000
+ "Ī": 231,
1001
+ "ī": 232,
1002
+ "Ĭ": 233,
1003
+ "ĭ": 234,
1004
+ "Į": 235,
1005
+ "į": 236,
1006
+ "İ": 237,
1007
+ "ı": 238,
1008
+ "IJ": 239,
1009
+ "ij": 240,
1010
+ "Ĵ": 241,
1011
+ "ĵ": 242,
1012
+ "Ķ": 243,
1013
+ "ķ": 244,
1014
+ "ĸ": 245,
1015
+ "Ĺ": 246,
1016
+ "ĺ": 247,
1017
+ "Ļ": 248,
1018
+ "ļ": 249,
1019
+ "Ľ": 250,
1020
+ "ľ": 251,
1021
+ "Ŀ": 252,
1022
+ "ŀ": 253,
1023
+ "Ł": 254,
1024
+ "ł": 255,
1025
+ "Ń": 256
1026
+ }