ChengsenWang commited on
Commit
8e5caf0
·
verified ·
1 Parent(s): 6d904dc

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +26 -0
  2. merges.txt +1007 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer_config.json +57 -0
  6. vocab.json +1026 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 512,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.53.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 1024
26
+ }
merges.txt ADDED
@@ -0,0 +1,1007 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #version: 0.2
2
+ T T
3
+ A A
4
+ T G
5
+ A G
6
+ C C
7
+ T C
8
+ A C
9
+ G G
10
+ A TT
11
+ A T
12
+ A TG
13
+ G C
14
+ T AA
15
+ T CC
16
+ A CC
17
+ AA AA
18
+ AG G
19
+ AG C
20
+ TT C
21
+ A TC
22
+ AA G
23
+ TT TT
24
+ TG C
25
+ TG G
26
+ AA C
27
+ TT G
28
+ T AG
29
+ T AC
30
+ CC C
31
+ T ATT
32
+ TG GG
33
+ AG AA
34
+ T AT
35
+ AG GG
36
+ TT TC
37
+ AG GC
38
+ AG CC
39
+ TG TG
40
+ AT AA
41
+ ATT C
42
+ TT GG
43
+ AC AC
44
+ AA GG
45
+ TC TC
46
+ TCC C
47
+ T ATG
48
+ TT TG
49
+ TT CC
50
+ AG AG
51
+ ATG G
52
+ AA AC
53
+ AG TG
54
+ ACC C
55
+ AG AC
56
+ TG CC
57
+ ATT G
58
+ AT CC
59
+ ATG C
60
+ AT AC
61
+ TC AC
62
+ TC TG
63
+ TT AA
64
+ TG AA
65
+ TG GC
66
+ TT GC
67
+ TAA G
68
+ T ATC
69
+ TAA C
70
+ AA AG
71
+ GG G
72
+ AA GC
73
+ GG C
74
+ TT AC
75
+ T AGC
76
+ AT AT
77
+ T ACC
78
+ AA CC
79
+ AA TG
80
+ T AGG
81
+ G CC
82
+ AT ATT
83
+ AG TC
84
+ TT TTC
85
+ TG AC
86
+ AAAA C
87
+ AA TC
88
+ TT TAA
89
+ AAAA G
90
+ AT AG
91
+ TG TC
92
+ TT ATT
93
+ TTTT G
94
+ TG AG
95
+ AA TT
96
+ AA ATT
97
+ AC AG
98
+ TT TCC
99
+ AA TAA
100
+ TC AG
101
+ AGG CC
102
+ AA ATG
103
+ TGGG C
104
+ AC TC
105
+ AC G
106
+ ATT TC
107
+ AC TG
108
+ TT AG
109
+ TGG CC
110
+ AA AT
111
+ ATC TC
112
+ AC AA
113
+ AT ATG
114
+ TATT C
115
+ TG TAA
116
+ ATT CC
117
+ AC TT
118
+ ATG CC
119
+ TT CCC
120
+ AAAA AAAA
121
+ TT TGC
122
+ TCC CC
123
+ TT TAG
124
+ TGGG G
125
+ TTC TC
126
+ TAA AA
127
+ ACC CC
128
+ AG AAG
129
+ AGGG C
130
+ ACC TC
131
+ TTTT TTTT
132
+ AC ATT
133
+ AG ATG
134
+ GG CC
135
+ G TG
136
+ AAG CC
137
+ AT AAAA
138
+ AGG AG
139
+ TT TAC
140
+ ATG GC
141
+ ATT AC
142
+ ATT GC
143
+ TT TGG
144
+ TC AA
145
+ AC TGC
146
+ TATT G
147
+ AAGG C
148
+ TGG AG
149
+ TTG CC
150
+ AA ATC
151
+ TTGG C
152
+ GG GC
153
+ AG AAC
154
+ AT ATC
155
+ AC TCC
156
+ AA TTC
157
+ AGGG G
158
+ AT CCC
159
+ AT AAC
160
+ AA AGC
161
+ AG AGC
162
+ TC G
163
+ ATG GG
164
+ ATT TT
165
+ TG AGG
166
+ AA AGG
167
+ TTGG G
168
+ AG AAAA
169
+ TC TCC
170
+ AT AAG
171
+ ATT TG
172
+ TAT CC
173
+ ACC AC
174
+ TC TTC
175
+ ATC AC
176
+ AG AGG
177
+ TT TATT
178
+ AG TAA
179
+ TG TAG
180
+ AT AGC
181
+ AG CCC
182
+ AG ATT
183
+ AG TT
184
+ TG TGC
185
+ TG TGG
186
+ GG GG
187
+ TATG C
188
+ TG AAG
189
+ TG CCC
190
+ TG TT
191
+ AG ACC
192
+ TC ATT
193
+ TC TT
194
+ AAGG G
195
+ TC TGC
196
+ AG TTC
197
+ AA ACC
198
+ AC ATG
199
+ AC AGC
200
+ AC TTC
201
+ AA TAG
202
+ TG ATG
203
+ AA TAC
204
+ AA TGC
205
+ AA TGG
206
+ TC AGC
207
+ TG ATT
208
+ TG AGC
209
+ TC AGG
210
+ TC TTG
211
+ TG TTC
212
+ TTTT CC
213
+ AG TGG
214
+ TT AAAA
215
+ TATG G
216
+ TCCC AGC
217
+ AT ACC
218
+ AG ATC
219
+ AA CCC
220
+ T ACCC
221
+ TG AAC
222
+ AA TCC
223
+ TG TTG
224
+ TAG CC
225
+ TT AAG
226
+ TT AAC
227
+ TT ATG
228
+ AT AGG
229
+ TT TAT
230
+ AA TTG
231
+ AG TGC
232
+ TG TCC
233
+ TAG GC
234
+ TC TAA
235
+ TC ATC
236
+ TC AAG
237
+ TC TTTT
238
+ AA TTTT
239
+ TC ACC
240
+ TT ATC
241
+ ATT TTC
242
+ AGTG GC
243
+ AGAA GC
244
+ CC CC
245
+ AC TAA
246
+ AG TAG
247
+ AC TAC
248
+ ATT GG
249
+ AA ATAA
250
+ TC ATG
251
+ TG AGGC
252
+ TC AGCC
253
+ AG TTG
254
+ AC AAC
255
+ AC ATC
256
+ ATT TAA
257
+ AC AGG
258
+ AG TCC
259
+ TC TGG
260
+ AC AAG
261
+ TC AAC
262
+ AC ACC
263
+ TG ACC
264
+ AT ATAA
265
+ TT AGC
266
+ TG AAAA
267
+ TG TTTT
268
+ AA AGAA
269
+ TTGG CC
270
+ AA TAT
271
+ AC TTG
272
+ TG ATC
273
+ AC AAAA
274
+ TAA GG
275
+ TAA GC
276
+ TG TAC
277
+ AA TATT
278
+ TAG GG
279
+ AA ACAC
280
+ TT TGTG
281
+ ATT TTG
282
+ TT ACC
283
+ TC TAC
284
+ TG TATT
285
+ TTC G
286
+ TAA TTTT
287
+ TT AGG
288
+ TAA CC
289
+ AGAA GG
290
+ AC TGG
291
+ ATT ATT
292
+ AG TAC
293
+ AG TTTT
294
+ AGC G
295
+ TC TAG
296
+ AC GG
297
+ ACC ATG
298
+ TAA TAA
299
+ AT ATTC
300
+ G CCC
301
+ TCC TG
302
+ AAAA GC
303
+ AAAA CC
304
+ TTC AC
305
+ AAAA GG
306
+ TC AGAA
307
+ AGG AAG
308
+ AC TAG
309
+ ACAC ACAC
310
+ AG AGAA
311
+ TCAC TGC
312
+ AAC G
313
+ ATT TCC
314
+ TG TCTC
315
+ TTCC CC
316
+ TGGG ATTAC
317
+ TGC G
318
+ AC GC
319
+ TG TAT
320
+ AGG AGG
321
+ TGTG TGTG
322
+ TC TTTC
323
+ AGGC TGG
324
+ AAG AC
325
+ TC TGCC
326
+ ATC G
327
+ AGC AG
328
+ TC GC
329
+ ATT TTTT
330
+ AT ATAC
331
+ AA ATTC
332
+ TTC AAG
333
+ TCC G
334
+ AAAA ATT
335
+ AAAG TGC
336
+ AC TTTT
337
+ AA TTTC
338
+ TCC TGCC
339
+ AGG TC
340
+ AGCC CC
341
+ TTG CCC
342
+ TTTG CC
343
+ AG TTTC
344
+ AGC AGC
345
+ AAAA TAA
346
+ TGGG GC
347
+ AT AGAA
348
+ ACC G
349
+ AAC AC
350
+ AGG AGAA
351
+ TG AGAC
352
+ TT TCCC
353
+ TGTG GC
354
+ TAT ATT
355
+ AA ATAC
356
+ AGGG GC
357
+ TGGG GG
358
+ TTTT GC
359
+ TGTAA TCCCAGC
360
+ AT ATTG
361
+ TGGG CC
362
+ AAG AAG
363
+ TT TATG
364
+ AA ATGG
365
+ AT ACAC
366
+ TTC TCC
367
+ AA ATGC
368
+ TAA AAC
369
+ A A</w>
370
+ AGC AC
371
+ AGGG CC
372
+ AAG TGG
373
+ TG AGAA
374
+ TAA ATG
375
+ TTTT GG
376
+ ACTT TGGG
377
+ TG TTTC
378
+ TTC TTC
379
+ AC AGAA
380
+ AA AGAC
381
+ TGTG CC
382
+ G AG
383
+ TCC TC
384
+ ATT TGC
385
+ AA TGAA
386
+ G TGG
387
+ ATT TAC
388
+ AAC TC
389
+ AGGC TGAGGC
390
+ AG TCTC
391
+ TGGAG TGC
392
+ AG ATGG
393
+ TTTG GC
394
+ TATT CC
395
+ TG ATCC
396
+ AGC TC
397
+ TT TAAG
398
+ AGG AC
399
+ TCC TCC
400
+ AGG TGG
401
+ TAT AC
402
+ TAT ATG
403
+ TAA AC
404
+ TAA AAG
405
+ TT TGGG
406
+ TT ATAA
407
+ AG ATAA
408
+ TTC TGC
409
+ TT TATC
410
+ AT ATGC
411
+ ATT CCC
412
+ AA AGAG
413
+ AA ATTG
414
+ TAC TC
415
+ TGC TGC
416
+ TG ATTC
417
+ TTG AAC
418
+ AGTG CC
419
+ TT ATTC
420
+ AT ATCC
421
+ AA TTAA
422
+ A T</w>
423
+ TC AAAA
424
+ AAG AAAA
425
+ AAC AAC
426
+ ATC TTC
427
+ AT ATGG
428
+ AG TATT
429
+ ATAT ATAT
430
+ ATT TATT
431
+ TCTG GC
432
+ ATG ATG
433
+ ACTCC AGCC
434
+ AG ACAC
435
+ ATC ACC
436
+ TG AAAC
437
+ AG AGGC
438
+ TCC AC
439
+ AA ATCC
440
+ AAG TC
441
+ A G</w>
442
+ AA AGCC
443
+ AA TATG
444
+ TGC AC
445
+ ATG TC
446
+ ATGG CC
447
+ GC G
448
+ AA TATC
449
+ AA TCTC
450
+ AA AGGG
451
+ AG AGGG
452
+ TG AAGG
453
+ TTGC AGTG
454
+ AG TAT
455
+ TTG TTG
456
+ AGG AGC
457
+ TGC TC
458
+ ATG AC
459
+ TAC G
460
+ AG ATTC
461
+ AAC TCC
462
+ ATTG CC
463
+ ATG TAA
464
+ ATC TCC
465
+ TTTT TAA
466
+ AA AGGC
467
+ TT TAAC
468
+ AA AGTG
469
+ AA TTTG
470
+ ACC TCC
471
+ TGG AAG
472
+ AA ATATT
473
+ TCCC AAAGTGC
474
+ AA TTCC
475
+ TTGG GG
476
+ TTC TG
477
+ ATT TAG
478
+ AAGG CC
479
+ TT AAAC
480
+ TC TTCC
481
+ AT AGAG
482
+ TT AGAA
483
+ CCC AGC
484
+ AA TGGC
485
+ TGGGATTAC AGGC
486
+ AAG AAC
487
+ TTGG GC
488
+ TC TCCC
489
+ T T</w>
490
+ TGCC CC
491
+ AAAA AC
492
+ AGG AAC
493
+ AA TAAC
494
+ TT AGCC
495
+ TGG AGC
496
+ ATCC CC
497
+ TC ACCC
498
+ TAAAA ATAC
499
+ TAA ATT
500
+ ATG AAG
501
+ ATG TG
502
+ TTTAG TAG
503
+ ACC ACC
504
+ AA ACCC
505
+ AGG CCC
506
+ AGC TCC
507
+ AGC TGC
508
+ AGGC TGGAGTGC
509
+ TGAA GC
510
+ TTC AAC
511
+ ATG GGG
512
+ AGG TGC
513
+ TC ATTC
514
+ TC GG
515
+ ATG TGG
516
+ AAGG GG
517
+ TTG AC
518
+ AG AGCC
519
+ ATC ATC
520
+ AGAA CC
521
+ ATG TGC
522
+ TCTC G
523
+ AGC AAG
524
+ TAT AAAA
525
+ AT AGTG
526
+ TAG AC
527
+ TC TGTG
528
+ ATT TGG
529
+ AA TGTG
530
+ AGC AGG
531
+ AA TTAC
532
+ AG TTTG
533
+ TG TTTG
534
+ AA TAAG
535
+ TT ATTG
536
+ TTTT TTG
537
+ TG ATAA
538
+ ATG TTC
539
+ TG AGCC
540
+ AT ACCC
541
+ AAGG GC
542
+ AT AGGC
543
+ AT AGAC
544
+ TGG AC
545
+ TAC AC
546
+ T G</w>
547
+ TGG CCC
548
+ ATC TGC
549
+ ATG TTG
550
+ TG TTCC
551
+ AC TCTG
552
+ TTC TTG
553
+ AAC ATGG
554
+ AG TTCC
555
+ TC TATT
556
+ TG TGGG
557
+ AGGG GG
558
+ TTC TTTT
559
+ AC AGAG
560
+ TAGC TGGG
561
+ TTC TAG
562
+ ATC TTG
563
+ TG TATG
564
+ ACC GC
565
+ TC TTGC
566
+ TT TACC
567
+ TC TTTG
568
+ TTC TAA
569
+ TCC TGC
570
+ AG ATGC
571
+ ATG AAC
572
+ ATC ATT
573
+ TAAG CC
574
+ ATG GGC
575
+ AACC CC
576
+ AAG TAA
577
+ TTC ATT
578
+ ATAA GC
579
+ GGG CC
580
+ TATT TATT
581
+ AG TTAA
582
+ AGC TAC
583
+ TGG TGG
584
+ AG TGGG
585
+ AAGC G
586
+ ACC CCC
587
+ TCCTGCC TCAGCC
588
+ ATC ATG
589
+ AAAAAAAA AAAAAAAA
590
+ AA TCAC
591
+ TTG AACC
592
+ TCC CCC
593
+ ATAA GG
594
+ TGC AGC
595
+ TGG AGG
596
+ AG TGTG
597
+ ATT TTTC
598
+ AAAA AAG
599
+ AAAA AAC
600
+ TG AGAG
601
+ A C</w>
602
+ TG ATGG
603
+ TTG AAG
604
+ TTTTTTTT TTTTTTTT
605
+ TAG AAG
606
+ TG AGGG
607
+ ACC TGC
608
+ TTC ATC
609
+ TTG TAA
610
+ AG ATAC
611
+ TG TCTG
612
+ AA TGCC
613
+ TTC TGG
614
+ ATG CCC
615
+ AC TTTC
616
+ AA TTGC
617
+ ATT TAT
618
+ TTC AGC
619
+ TAG AAC
620
+ ATG TCC
621
+ TT TAGC
622
+ AG TATG
623
+ ATT AAAA
624
+ ATC TAA
625
+ TAC TAAAAATAC
626
+ G TCTC
627
+ AT AAAAC
628
+ ATC AAC
629
+ TTAA CC
630
+ AGCC G
631
+ TGG AAC
632
+ AA TCTG
633
+ ATT AAC
634
+ AGG AAAA
635
+ TC TAT
636
+ AA TCCC
637
+ AAAT ATC
638
+ AG ACCC
639
+ AGGC GG
640
+ AGG TAA
641
+ TTAA GC
642
+ TATT GC
643
+ AGG TTC
644
+ AA ATAG
645
+ AC TGTG
646
+ TAC AAAA
647
+ ATAA CC
648
+ AA ATAT
649
+ TCCTG ACCTC
650
+ AGGCC G
651
+ TC TGGG
652
+ AG TCTG
653
+ TCC ACC
654
+ TT TAGG
655
+ TCC AGC
656
+ AG TAAC
657
+ AGG ATG
658
+ GCC CC
659
+ AA TAGC
660
+ TGG TGC
661
+ TCACTGC AACC
662
+ AAG AGC
663
+ TT ATAC
664
+ AT AGCC
665
+ TGAA CC
666
+ AG TCAC
667
+ G TGC
668
+ TCC TTC
669
+ TAT AAC
670
+ AAG ATG
671
+ ACTGC ACTCCAGCC
672
+ ATAA ATAA
673
+ TTG TAG
674
+ ATT ATG
675
+ AGC AAC
676
+ T A</w>
677
+ TTTT TC
678
+ AA TGGG
679
+ AC TTCC
680
+ TG AGTG
681
+ TGGGC AAC
682
+ T C</w>
683
+ TTG TC
684
+ TTC ATG
685
+ AT AGGG
686
+ AA TACC
687
+ TAC TAA
688
+ TGC AAG
689
+ TAT ATC
690
+ TG TTGG
691
+ TG ACAC
692
+ TATG CC
693
+ AG TAAG
694
+ AAG CCC
695
+ AG AAAAG
696
+ TTTC TTTC
697
+ TC AGGG
698
+ ACC TTG
699
+ TT AAGG
700
+ TAGG CC
701
+ AGC TGG
702
+ TG TCCC
703
+ AGACC AGCC
704
+ AG TCCC
705
+ TTG TTTT
706
+ TTC TAC
707
+ AT AAAAG
708
+ AGC ATC
709
+ ATT AAG
710
+ TT ATCC
711
+ AC ATTC
712
+ TCC TGG
713
+ TCAC AGAG
714
+ TC ACAC
715
+ AGGCTGAGGC AGGAGAA
716
+ ATG AGCC
717
+ AC ATGG
718
+ ACC AAC
719
+ TG ATGC
720
+ TAT CCC
721
+ AG AAAAC
722
+ AGG TAG
723
+ AG TTAC
724
+ ATT TTAA
725
+ ACC TAA
726
+ TC AGGC
727
+ AAG ATC
728
+ AGC TTC
729
+ AC AGCC
730
+ TT ACAC
731
+ TATG GC
732
+ AGG TTG
733
+ TGC TTC
734
+ TCCC AAG
735
+ TG TATC
736
+ TG TTAA
737
+ AGC ATT
738
+ TGC TCC
739
+ AA TTATT
740
+ AC AAAC
741
+ AGC TAA
742
+ TC ATGCC
743
+ AG ATTG
744
+ ACC AGCC
745
+ TT AGAG
746
+ TG TCAC
747
+ TG TAAG
748
+ TGGC TCAC
749
+ AA TTTAA
750
+ AC AGGG
751
+ TGTAATCCCAGC ACTTTGGG
752
+ CCC G
753
+ ATT ATC
754
+ AG ATCC
755
+ ATG AAAA
756
+ TC AGAG
757
+ AG TAGC
758
+ TAA TAC
759
+ TG TTGC
760
+ TC AAAC
761
+ TC AAGC
762
+ TACC CC
763
+ TTC TTTC
764
+ ACC AGC
765
+ ATG TAC
766
+ ATC AAG
767
+ AG TATC
768
+ TCC TTG
769
+ AGG TGTG
770
+ TCTC TCTC
771
+ ACC TGG
772
+ AAAT AAAA
773
+ TCC TGAG
774
+ AC AGTG
775
+ AG TTGC
776
+ AC TTTG
777
+ AA TAGG
778
+ TC ATTG
779
+ TAG AAAA
780
+ AG TTGG
781
+ AAC ATC
782
+ AC AGGC
783
+ ATT TCTC
784
+ AAAC GGG
785
+ TG TAAC
786
+ AA TTGG
787
+ TTG AACCC
788
+ TT ATGC
789
+ TCC ATG
790
+ GG GGC
791
+ AAC TTC
792
+ AAC AAAA
793
+ AGG ATC
794
+ GTG AGCC
795
+ TTTCC CC
796
+ TC ATCC
797
+ TC TTGG
798
+ AAG TGC
799
+ TT ACCC
800
+ ATG ATC
801
+ AAAC G
802
+ ACC ATC
803
+ TCC ATC
804
+ AT AGTC
805
+ ATAA TAA
806
+ AC TAT
807
+ TTG TATT
808
+ AGG TAC
809
+ AC AGAC
810
+ TC AGGAG
811
+ ATG TAG
812
+ TC AAGG
813
+ AC ATGC
814
+ TCC GCC
815
+ TC AGTG
816
+ ACC AAG
817
+ ACC TTC
818
+ ATT TTTG
819
+ TATT GG
820
+ TCCC G
821
+ TT ATATT
822
+ TGC TGG
823
+ ATT TTCC
824
+ ACAC G
825
+ TTTT AAAA
826
+ TG ACCC
827
+ ATT GGC
828
+ AA TTTTC
829
+ AGGC TGC
830
+ AAAAAAAA AAAA
831
+ TT AGGG
832
+ TTTTTTTT TTTT
833
+ TTC AGG
834
+ TG TTAC
835
+ AAG AGG
836
+ AGGC G
837
+ AC ATAA
838
+ TAG TAA
839
+ TCC TGGG
840
+ TGG TAA
841
+ ATG AGC
842
+ TGAA ACCCC
843
+ TGGC G
844
+ AGAG AGAG
845
+ TCC TAA
846
+ ATC TAC
847
+ AGAA AGAA
848
+ TTTC ACCATG
849
+ AGG ATGG
850
+ AGAC G
851
+ AC TATT
852
+ AGAC AGGG
853
+ TG TTTTC
854
+ AAAA TAC
855
+ TATG GG
856
+ TT AGTG
857
+ AGC ACC
858
+ TAT AAG
859
+ AG TAGG
860
+ TT ATGG
861
+ AAC TAA
862
+ AAC ATT
863
+ TTTGTG ATG
864
+ AC TGCC
865
+ TC ATAA
866
+ AC TGGG
867
+ TG ATTG
868
+ TTG TTC
869
+ AAC TGC
870
+ TC AAAG
871
+ TCC AAG
872
+ TCC AGG
873
+ ATG AGG
874
+ TT TATTC
875
+ TC ATGG
876
+ ATG ATT
877
+ ATTC TCAGAA
878
+ ACC TAC
879
+ TCCCAGC TAC
880
+ TTG TGC
881
+ AAC AGC
882
+ AC ATCC
883
+ TG AGTC
884
+ AC ATAC
885
+ AC TCTC
886
+ TGGG TGAC
887
+ TAATTTT TGTATT
888
+ ATTC G
889
+ GC GG
890
+ TT AGAC
891
+ TC GGCC
892
+ ATT TTAC
893
+ TAA AAAA
894
+ AGG AGGC
895
+ AAC AAG
896
+ ATC TGG
897
+ AC TGAA
898
+ AC TATG
899
+ TG ATAC
900
+ TC TATC
901
+ AAAG AAG
902
+ TGC AGG
903
+ AG TTTTC
904
+ AAC ATG
905
+ AC AATG
906
+ AAAG AAAA
907
+ AG TACC
908
+ TGGGC G
909
+ AGATG GGG
910
+ TTTG TAA
911
+ AC TCCC
912
+ ATT GGG
913
+ TG TAGG
914
+ AGC ATG
915
+ AC ATTG
916
+ TTG TAC
917
+ TC ATGC
918
+ AAG TTC
919
+ ATTTC G
920
+ TTTT TTC
921
+ TTG AAAA
922
+ TAA TTC
923
+ TC TTAA
924
+ ATT TTTAA
925
+ TGC ATG
926
+ AG ATATT
927
+ AAC TAC
928
+ TGGG AGG
929
+ TC TATG
930
+ ACC TGCC
931
+ TC TTAC
932
+ AATC TGC
933
+ AA TTTTG
934
+ TAGCTGGG ACTAC
935
+ TTG TGG
936
+ TG TAGC
937
+ TATT TTC
938
+ TT AAAAC
939
+ ATAT ATG
940
+ AC AAGG
941
+ TTG AGG
942
+ TAG TAG
943
+ AAAC AAAC
944
+ AC ACCC
945
+ ATC AGC
946
+ TT AGGC
947
+ TCTG TCTC
948
+ ATAT ATT
949
+ ATAT AAAA
950
+ AGGCC CC
951
+ AGC TGAG
952
+ TAC ATG
953
+ TGG ATC
954
+ ATAA ATG
955
+ TAA GGC
956
+ TGG TAG
957
+ AAAC TCC
958
+ TTTT TTTC
959
+ AAG TAG
960
+ AGGTC AGGAG
961
+ TAA ATC
962
+ TCAC G
963
+ ATGG TGGC
964
+ TTG TCC
965
+ TAA TGC
966
+ TTTC G
967
+ TG TACC
968
+ ACC ACG
969
+ TGG AAAA
970
+ AGG AAGG
971
+ ATTC AAC
972
+ TC AGAC
973
+ AC TTGG
974
+ AC TTGC
975
+ TTTT TCC
976
+ TATT TTG
977
+ TTGG AAACGGG
978
+ TC AACC
979
+ TAA TAG
980
+ TGG ATG
981
+ AGC TGGG
982
+ AC TGGC
983
+ TCC AGCC
984
+ AC AAAG
985
+ GC GC
986
+ TAC TTC
987
+ TT TATTG
988
+ TC AGTC
989
+ TGG TTC
990
+ TAT AGC
991
+ AGG AAAC
992
+ TAC TGC
993
+ TT ATAG
994
+ TTTT GCC
995
+ AAAA ATG
996
+ TAT ATAA
997
+ ATC GC
998
+ TC TTTTC
999
+ AGAA ATG
1000
+ AAG TTG
1001
+ TC AATG
1002
+ ACC AGG
1003
+ ATT TTATT
1004
+ AC TCAC
1005
+ TTTT TATT
1006
+ AG ATAG
1007
+ TC TACC
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05149405ae6ecfb32e6ec1214449bf14a49a6e3e4e687892459de0e099e2ee72
3
+ size 79886416
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": false,
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
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "unk_token": "<unk>"
57
+ }
vocab.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 1,
3
+ "<mask>": 4,
4
+ "<pad>": 3,
5
+ "<s>": 0,
6
+ "<unk>": 2,
7
+ "A": 5,
8
+ "A</w>": 16,
9
+ "AA": 19,
10
+ "AA</w>": 385,
11
+ "AAAA": 33,
12
+ "AAAAAAAA": 136,
13
+ "AAAAAAAAAAAA": 846,
14
+ "AAAAAAAAAAAAAAAA": 605,
15
+ "AAAAAAC": 615,
16
+ "AAAAAAG": 614,
17
+ "AAAAAC": 507,
18
+ "AAAAATG": 1011,
19
+ "AAAAATT": 350,
20
+ "AAAAC": 102,
21
+ "AAAACC": 319,
22
+ "AAAAG": 105,
23
+ "AAAAGC": 318,
24
+ "AAAAGG": 321,
25
+ "AAAATAA": 361,
26
+ "AAAATAC": 870,
27
+ "AAAC": 68,
28
+ "AAACAAAC": 959,
29
+ "AAACAC": 295,
30
+ "AAACC": 213,
31
+ "AAACCC": 520,
32
+ "AAACG": 817,
33
+ "AAACGGG": 800,
34
+ "AAACTCC": 973,
35
+ "AAAG": 86,
36
+ "AAAGAA": 284,
37
+ "AAAGAAAA": 922,
38
+ "AAAGAAG": 917,
39
+ "AAAGAC": 396,
40
+ "AAAGAG": 428,
41
+ "AAAGC": 176,
42
+ "AAAGCC": 458,
43
+ "AAAGG": 182,
44
+ "AAAGGC": 482,
45
+ "AAAGGG": 466,
46
+ "AAAGTG": 484,
47
+ "AAAGTGC": 351,
48
+ "AAAT": 126,
49
+ "AAATAA": 265,
50
+ "AAATAAAA": 788,
51
+ "AAATAC": 371,
52
+ "AAATAG": 660,
53
+ "AAATAT": 664,
54
+ "AAATATC": 653,
55
+ "AAATATT": 488,
56
+ "AAATC": 166,
57
+ "AAATCC": 455,
58
+ "AAATG": 118,
59
+ "AAATGC": 383,
60
+ "AAATGG": 380,
61
+ "AAATT": 112,
62
+ "AAATTC": 347,
63
+ "AAATTG": 429,
64
+ "AAC": 42,
65
+ "AACAAAA": 808,
66
+ "AACAAC": 441,
67
+ "AACAAG": 911,
68
+ "AACAC": 365,
69
+ "AACAGC": 897,
70
+ "AACATC": 797,
71
+ "AACATG": 920,
72
+ "AACATGG": 569,
73
+ "AACATT": 878,
74
+ "AACC": 94,
75
+ "AACCC": 235,
76
+ "AACCCC": 591,
77
+ "AACG": 328,
78
+ "AACTAA": 877,
79
+ "AACTAC": 943,
80
+ "AACTC": 404,
81
+ "AACTCC": 477,
82
+ "AACTGC": 885,
83
+ "AACTTC": 807,
84
+ "AAG": 38,
85
+ "AAGAAAA": 440,
86
+ "AAGAAC": 502,
87
+ "AAGAAG": 378,
88
+ "AAGAC": 340,
89
+ "AAGAGC": 678,
90
+ "AAGAGG": 851,
91
+ "AAGATC": 743,
92
+ "AAGATG": 686,
93
+ "AAGC": 88,
94
+ "AAGCC": 152,
95
+ "AAGCCC": 710,
96
+ "AAGCG": 601,
97
+ "AAGG": 60,
98
+ "AAGGC": 163,
99
+ "AAGGCC": 494,
100
+ "AAGGG": 210,
101
+ "AAGGGC": 557,
102
+ "AAGGGG": 532,
103
+ "AAGTAA": 592,
104
+ "AAGTAG": 975,
105
+ "AAGTC": 456,
106
+ "AAGTGC": 814,
107
+ "AAGTGG": 388,
108
+ "AAGTTC": 934,
109
+ "AAGTTG": 1016,
110
+ "AATAA": 115,
111
+ "AATAAC": 509,
112
+ "AATAAG": 550,
113
+ "AATAC": 219,
114
+ "AATACC": 702,
115
+ "AATAG": 217,
116
+ "AATAGC": 675,
117
+ "AATAGG": 793,
118
+ "AATAT": 286,
119
+ "AATATC": 464,
120
+ "AATATG": 459,
121
+ "AATATT": 293,
122
+ "AATC": 103,
123
+ "AATCAC": 606,
124
+ "AATCC": 238,
125
+ "AATCCC": 652,
126
+ "AATCTC": 465,
127
+ "AATCTG": 648,
128
+ "AATCTGC": 948,
129
+ "AATG": 95,
130
+ "AATGAA": 401,
131
+ "AATGC": 220,
132
+ "AATGCC": 628,
133
+ "AATGG": 221,
134
+ "AATGGC": 500,
135
+ "AATGGG": 694,
136
+ "AATGTG": 545,
137
+ "AATT": 111,
138
+ "AATTAA": 437,
139
+ "AATTAC": 547,
140
+ "AATTATT": 755,
141
+ "AATTC": 172,
142
+ "AATTCC": 490,
143
+ "AATTG": 246,
144
+ "AATTGC": 632,
145
+ "AATTGG": 802,
146
+ "AATTTAA": 765,
147
+ "AATTTC": 353,
148
+ "AATTTG": 485,
149
+ "AATTTT": 254,
150
+ "AATTTTC": 844,
151
+ "AATTTTG": 949,
152
+ "AC": 24,
153
+ "AC</w>": 617,
154
+ "ACAA": 128,
155
+ "ACAAAA": 289,
156
+ "ACAAAC": 756,
157
+ "ACAAAG": 1000,
158
+ "ACAAC": 270,
159
+ "ACAAG": 276,
160
+ "ACAAGG": 956,
161
+ "ACAATG": 921,
162
+ "ACAC": 59,
163
+ "ACACACAC": 325,
164
+ "ACACC": 278,
165
+ "ACACCC": 960,
166
+ "ACACG": 840,
167
+ "ACAG": 113,
168
+ "ACAGAA": 395,
169
+ "ACAGAC": 825,
170
+ "ACAGAG": 575,
171
+ "ACAGC": 215,
172
+ "ACAGCC": 745,
173
+ "ACAGG": 273,
174
+ "ACAGGC": 798,
175
+ "ACAGGG": 766,
176
+ "ACAGTG": 790,
177
+ "ACATAA": 853,
178
+ "ACATAC": 900,
179
+ "ACATC": 271,
180
+ "ACATCC": 898,
181
+ "ACATG": 214,
182
+ "ACATGC": 829,
183
+ "ACATGG": 733,
184
+ "ACATT": 148,
185
+ "ACATTC": 727,
186
+ "ACATTG": 931,
187
+ "ACC": 32,
188
+ "ACCAAC": 734,
189
+ "ACCAAG": 832,
190
+ "ACCAC": 189,
191
+ "ACCACC": 519,
192
+ "ACCACG": 984,
193
+ "ACCAGC": 780,
194
+ "ACCAGCC": 760,
195
+ "ACCAGG": 1018,
196
+ "ACCATC": 818,
197
+ "ACCATG": 313,
198
+ "ACCC": 70,
199
+ "ACCCC": 143,
200
+ "ACCCCC": 602,
201
+ "ACCG": 364,
202
+ "ACCGC": 580,
203
+ "ACCTAA": 741,
204
+ "ACCTAC": 894,
205
+ "ACCTC": 146,
206
+ "ACCTCC": 486,
207
+ "ACCTGC": 623,
208
+ "ACCTGCC": 946,
209
+ "ACCTGG": 787,
210
+ "ACCTTC": 833,
211
+ "ACCTTG": 714,
212
+ "ACG": 121,
213
+ "ACGC": 334,
214
+ "ACGG": 312,
215
+ "ACTAA": 261,
216
+ "ACTAC": 263,
217
+ "ACTAG": 324,
218
+ "ACTAT": 822,
219
+ "ACTATG": 914,
220
+ "ACTATT": 867,
221
+ "ACTC": 120,
222
+ "ACTCAC": 1020,
223
+ "ACTCC": 171,
224
+ "ACTCCAGCC": 449,
225
+ "ACTCCC": 927,
226
+ "ACTCTC": 901,
227
+ "ACTCTG": 567,
228
+ "ACTG": 123,
229
+ "ACTGAA": 913,
230
+ "ACTGC": 161,
231
+ "ACTGCACTCCAGCC": 687,
232
+ "ACTGCC": 880,
233
+ "ACTGG": 306,
234
+ "ACTGGC": 998,
235
+ "ACTGGG": 882,
236
+ "ACTGTG": 661,
237
+ "ACTT": 133,
238
+ "ACTTC": 216,
239
+ "ACTTCC": 695,
240
+ "ACTTG": 287,
241
+ "ACTTGC": 990,
242
+ "ACTTGG": 989,
243
+ "ACTTTC": 631,
244
+ "ACTTTG": 792,
245
+ "ACTTTGGG": 392,
246
+ "ACTTTT": 352,
247
+ "AG": 21,
248
+ "AG</w>": 457,
249
+ "AGAA": 49,
250
+ "AGAAAA": 184,
251
+ "AGAAAAC": 737,
252
+ "AGAAAAG": 711,
253
+ "AGAAAGAA": 863,
254
+ "AGAAATG": 1015,
255
+ "AGAAC": 169,
256
+ "AGAACC": 536,
257
+ "AGAAG": 144,
258
+ "AGAAGC": 259,
259
+ "AGAAGG": 305,
260
+ "AGAC": 71,
261
+ "AGACAC": 450,
262
+ "AGACAGGG": 868,
263
+ "AGACC": 207,
264
+ "AGACCAGCC": 719,
265
+ "AGACCC": 654,
266
+ "AGACG": 866,
267
+ "AGAG": 66,
268
+ "AGAGAA": 326,
269
+ "AGAGAGAG": 860,
270
+ "AGAGC": 177,
271
+ "AGAGCC": 534,
272
+ "AGAGG": 192,
273
+ "AGAGGC": 453,
274
+ "AGAGGG": 467,
275
+ "AGATAA": 423,
276
+ "AGATAC": 626,
277
+ "AGATAG": 1022,
278
+ "AGATATT": 942,
279
+ "AGATC": 234,
280
+ "AGATCC": 770,
281
+ "AGATG": 149,
282
+ "AGATGC": 586,
283
+ "AGATGG": 408,
284
+ "AGATGGGG": 925,
285
+ "AGATT": 198,
286
+ "AGATTC": 476,
287
+ "AGATTG": 759,
288
+ "AGC": 35,
289
+ "AGCAAC": 691,
290
+ "AGCAAG": 539,
291
+ "AGCAC": 386,
292
+ "AGCACC": 873,
293
+ "AGCAG": 343,
294
+ "AGCAGC": 360,
295
+ "AGCAGG": 546,
296
+ "AGCATC": 724,
297
+ "AGCATG": 930,
298
+ "AGCATT": 753,
299
+ "AGCC": 54,
300
+ "AGCCC": 197,
301
+ "AGCCCC": 356,
302
+ "AGCCG": 646,
303
+ "AGCG": 310,
304
+ "AGCTAA": 757,
305
+ "AGCTAC": 598,
306
+ "AGCTC": 412,
307
+ "AGCTCC": 522,
308
+ "AGCTGAG": 967,
309
+ "AGCTGC": 523,
310
+ "AGCTGG": 717,
311
+ "AGCTGGG": 997,
312
+ "AGCTTC": 744,
313
+ "AGG": 34,
314
+ "AGGAAAA": 650,
315
+ "AGGAAAC": 1007,
316
+ "AGGAAC": 508,
317
+ "AGGAAG": 323,
318
+ "AGGAAGG": 986,
319
+ "AGGAC": 414,
320
+ "AGGAG": 154,
321
+ "AGGAGAA": 366,
322
+ "AGGAGC": 472,
323
+ "AGGAGG": 336,
324
+ "AGGAGGC": 910,
325
+ "AGGATC": 809,
326
+ "AGGATG": 673,
327
+ "AGGATGG": 865,
328
+ "AGGC": 53,
329
+ "AGGCC": 117,
330
+ "AGGCCC": 521,
331
+ "AGGCCCC": 966,
332
+ "AGGCCG": 666,
333
+ "AGGCG": 852,
334
+ "AGGCGG": 655,
335
+ "AGGCTGAGGC": 405,
336
+ "AGGCTGAGGCAGGAGAA": 731,
337
+ "AGGCTGC": 845,
338
+ "AGGCTGG": 339,
339
+ "AGGCTGGAGTGC": 524,
340
+ "AGGG": 51,
341
+ "AGGGC": 145,
342
+ "AGGGCC": 387,
343
+ "AGGGG": 173,
344
+ "AGGGGC": 372,
345
+ "AGGGGG": 573,
346
+ "AGGTAA": 656,
347
+ "AGGTAC": 824,
348
+ "AGGTAG": 738,
349
+ "AGGTC": 355,
350
+ "AGGTCAGGAG": 976,
351
+ "AGGTGC": 528,
352
+ "AGGTGG": 416,
353
+ "AGGTGTG": 785,
354
+ "AGGTTC": 659,
355
+ "AGGTTG": 748,
356
+ "AGTAA": 194,
357
+ "AGTAAC": 672,
358
+ "AGTAAG": 709,
359
+ "AGTAC": 308,
360
+ "AGTACC": 923,
361
+ "AGTAG": 262,
362
+ "AGTAGC": 773,
363
+ "AGTAGG": 875,
364
+ "AGTAT": 470,
365
+ "AGTATC": 783,
366
+ "AGTATG": 638,
367
+ "AGTATT": 444,
368
+ "AGTC": 99,
369
+ "AGTCAC": 682,
370
+ "AGTCC": 274,
371
+ "AGTCCC": 720,
372
+ "AGTCTC": 406,
373
+ "AGTCTG": 668,
374
+ "AGTG": 69,
375
+ "AGTGC": 247,
376
+ "AGTGCC": 434,
377
+ "AGTGG": 229,
378
+ "AGTGGC": 258,
379
+ "AGTGGG": 600,
380
+ "AGTGTG": 612,
381
+ "AGTT": 199,
382
+ "AGTTAA": 597,
383
+ "AGTTAC": 739,
384
+ "AGTTC": 212,
385
+ "AGTTCC": 570,
386
+ "AGTTG": 269,
387
+ "AGTTGC": 791,
388
+ "AGTTGG": 796,
389
+ "AGTTTC": 359,
390
+ "AGTTTG": 548,
391
+ "AGTTTT": 309,
392
+ "AGTTTTC": 919,
393
+ "AT": 27,
394
+ "AT</w>": 438,
395
+ "ATAA": 56,
396
+ "ATAAAA": 153,
397
+ "ATAAAAC": 643,
398
+ "ATAAAAG": 723,
399
+ "ATAAATAA": 688,
400
+ "ATAAATG": 970,
401
+ "ATAAC": 175,
402
+ "ATAACC": 663,
403
+ "ATAAG": 186,
404
+ "ATAAGC": 594,
405
+ "ATAAGG": 609,
406
+ "ATAATAA": 821,
407
+ "ATAC": 76,
408
+ "ATACAC": 381,
409
+ "ATACC": 233,
410
+ "ATACCC": 556,
411
+ "ATAG": 106,
412
+ "ATAGAA": 363,
413
+ "ATAGAC": 559,
414
+ "ATAGAG": 497,
415
+ "ATAGC": 196,
416
+ "ATAGCC": 680,
417
+ "ATAGG": 244,
418
+ "ATAGGC": 558,
419
+ "ATAGGG": 701,
420
+ "ATAGTC": 820,
421
+ "ATAGTG": 541,
422
+ "ATAT": 92,
423
+ "ATATAA": 280,
424
+ "ATATAAAA": 965,
425
+ "ATATAC": 346,
426
+ "ATATATAT": 445,
427
+ "ATATATG": 955,
428
+ "ATATATT": 964,
429
+ "ATATC": 170,
430
+ "ATATCC": 436,
431
+ "ATATG": 129,
432
+ "ATATGC": 426,
433
+ "ATATGG": 443,
434
+ "ATATT": 98,
435
+ "ATATTC": 315,
436
+ "ATATTG": 376,
437
+ "ATC": 37,
438
+ "ATCAAC": 644,
439
+ "ATCAAG": 782,
440
+ "ATCAC": 191,
441
+ "ATCACC": 451,
442
+ "ATCAGC": 961,
443
+ "ATCATC": 535,
444
+ "ATCATG": 604,
445
+ "ATCATT": 588,
446
+ "ATCC": 74,
447
+ "ATCCC": 174,
448
+ "ATCCCC": 512,
449
+ "ATCG": 342,
450
+ "ATCGC": 1013,
451
+ "ATCTAA": 640,
452
+ "ATCTAC": 862,
453
+ "ATCTC": 127,
454
+ "ATCTCC": 480,
455
+ "ATCTGC": 564,
456
+ "ATCTGG": 912,
457
+ "ATCTTC": 442,
458
+ "ATCTTG": 578,
459
+ "ATG": 28,
460
+ "ATGAAAA": 771,
461
+ "ATGAAC": 587,
462
+ "ATGAAG": 516,
463
+ "ATGAC": 474,
464
+ "ATGAGC": 857,
465
+ "ATGAGCC": 732,
466
+ "ATGAGG": 889,
467
+ "ATGATC": 816,
468
+ "ATGATG": 448,
469
+ "ATGATT": 892,
470
+ "ATGC": 75,
471
+ "ATGCC": 134,
472
+ "ATGCCC": 630,
473
+ "ATGG": 67,
474
+ "ATGGC": 156,
475
+ "ATGGCC": 462,
476
+ "ATGGG": 179,
477
+ "ATGGGC": 590,
478
+ "ATGGGG": 527,
479
+ "ATGGTGGC": 979,
480
+ "ATGTAA": 479,
481
+ "ATGTAC": 781,
482
+ "ATGTAG": 827,
483
+ "ATGTC": 461,
484
+ "ATGTCC": 636,
485
+ "ATGTG": 517,
486
+ "ATGTGC": 537,
487
+ "ATGTGG": 531,
488
+ "ATGTTC": 554,
489
+ "ATGTTG": 565,
490
+ "ATT": 26,
491
+ "ATTAAAA": 639,
492
+ "ATTAAC": 649,
493
+ "ATTAAG": 725,
494
+ "ATTAC": 157,
495
+ "ATTATC": 769,
496
+ "ATTATG": 690,
497
+ "ATTATT": 307,
498
+ "ATTC": 57,
499
+ "ATTCAAC": 987,
500
+ "ATTCC": 132,
501
+ "ATTCCC": 427,
502
+ "ATTCG": 904,
503
+ "ATTCTCAGAA": 893,
504
+ "ATTG": 73,
505
+ "ATTGC": 158,
506
+ "ATTGCC": 478,
507
+ "ATTGG": 264,
508
+ "ATTGGC": 843,
509
+ "ATTGGG": 928,
510
+ "ATTTAA": 272,
511
+ "ATTTAC": 403,
512
+ "ATTTAG": 493,
513
+ "ATTTAT": 633,
514
+ "ATTTATT": 446,
515
+ "ATTTC": 122,
516
+ "ATTTCC": 329,
517
+ "ATTTCG": 935,
518
+ "ATTTCTC": 799,
519
+ "ATTTG": 187,
520
+ "ATTTGC": 400,
521
+ "ATTTGG": 544,
522
+ "ATTTT": 180,
523
+ "ATTTTAA": 740,
524
+ "ATTTTAC": 908,
525
+ "ATTTTATT": 1019,
526
+ "ATTTTC": 257,
527
+ "ATTTTCC": 839,
528
+ "ATTTTG": 297,
529
+ "ATTTTTAA": 940,
530
+ "ATTTTTC": 613,
531
+ "ATTTTTG": 834,
532
+ "ATTTTTT": 345,
533
+ "C": 6,
534
+ "C</w>": 17,
535
+ "CC": 22,
536
+ "CCC": 46,
537
+ "CCCAGC": 499,
538
+ "CCCC": 260,
539
+ "CCCG": 768,
540
+ "G": 7,
541
+ "G</w>": 15,
542
+ "GAG": 398,
543
+ "GC": 29,
544
+ "GCC": 97,
545
+ "GCCC": 316,
546
+ "GCCCC": 674,
547
+ "GCG": 463,
548
+ "GCGC": 1001,
549
+ "GCGG": 905,
550
+ "GG": 25,
551
+ "GGC": 89,
552
+ "GGCC": 150,
553
+ "GGG": 87,
554
+ "GGGC": 168,
555
+ "GGGCC": 595,
556
+ "GGGG": 202,
557
+ "GGGGC": 806,
558
+ "GTCTC": 642,
559
+ "GTG": 151,
560
+ "GTGAGCC": 810,
561
+ "GTGC": 683,
562
+ "GTGG": 402,
563
+ "K": 8,
564
+ "M": 9,
565
+ "R": 10,
566
+ "S": 11,
567
+ "T": 12,
568
+ "T</w>": 14,
569
+ "TA</w>": 692,
570
+ "TAA": 30,
571
+ "TAAAA": 142,
572
+ "TAAAAAA": 909,
573
+ "TAAAAATAC": 514,
574
+ "TAAAAC": 384,
575
+ "TAAAAG": 420,
576
+ "TAAAC": 419,
577
+ "TAAATC": 977,
578
+ "TAAATG": 390,
579
+ "TAAATT": 515,
580
+ "TAAC": 85,
581
+ "TAACC": 304,
582
+ "TAAG": 83,
583
+ "TAAGC": 291,
584
+ "TAAGCC": 589,
585
+ "TAAGG": 290,
586
+ "TAAGGC": 971,
587
+ "TAATAA": 314,
588
+ "TAATAC": 774,
589
+ "TAATAG": 995,
590
+ "TAATGC": 981,
591
+ "TAATTC": 938,
592
+ "TAATTTT": 302,
593
+ "TAATTTTTGTATT": 903,
594
+ "TAC": 45,
595
+ "TACAAAA": 662,
596
+ "TACAC": 561,
597
+ "TACATG": 968,
598
+ "TACC": 93,
599
+ "TACCC": 236,
600
+ "TACCCC": 778,
601
+ "TACG": 475,
602
+ "TACTAA": 703,
603
+ "TACTAAAAATAC": 641,
604
+ "TACTC": 430,
605
+ "TACTGC": 1008,
606
+ "TACTTC": 1002,
607
+ "TAG": 44,
608
+ "TAGAAAA": 795,
609
+ "TAGAAC": 635,
610
+ "TAGAAG": 621,
611
+ "TAGAC": 542,
612
+ "TAGC": 91,
613
+ "TAGCC": 240,
614
+ "TAGCTGGG": 576,
615
+ "TAGCTGGGACTAC": 950,
616
+ "TAGG": 96,
617
+ "TAGGC": 249,
618
+ "TAGGCC": 716,
619
+ "TAGGG": 294,
620
+ "TAGTAA": 854,
621
+ "TAGTAG": 958,
622
+ "TAT": 50,
623
+ "TATAAAA": 540,
624
+ "TATAAC": 685,
625
+ "TATAAG": 874,
626
+ "TATAC": 417,
627
+ "TATAGC": 1006,
628
+ "TATATAA": 1012,
629
+ "TATATC": 705,
630
+ "TATATG": 418,
631
+ "TATATT": 370,
632
+ "TATC": 84,
633
+ "TATCC": 188,
634
+ "TATCCC": 736,
635
+ "TATG": 63,
636
+ "TATGC": 203,
637
+ "TATGCC": 708,
638
+ "TATGG": 231,
639
+ "TATGGC": 747,
640
+ "TATGGG": 871,
641
+ "TATT": 47,
642
+ "TATTC": 130,
643
+ "TATTCC": 410,
644
+ "TATTG": 162,
645
+ "TATTGC": 658,
646
+ "TATTGG": 835,
647
+ "TATTTATT": 596,
648
+ "TATTTTC": 953,
649
+ "TATTTTG": 992,
650
+ "TC": 23,
651
+ "TC</w>": 698,
652
+ "TCAA": 160,
653
+ "TCAAAA": 439,
654
+ "TCAAAC": 776,
655
+ "TCAAAG": 886,
656
+ "TCAAC": 277,
657
+ "TCAACC": 994,
658
+ "TCAAG": 252,
659
+ "TCAAGC": 777,
660
+ "TCAAGG": 828,
661
+ "TCAATG": 1017,
662
+ "TCAC": 77,
663
+ "TCACAC": 730,
664
+ "TCACAGAG": 729,
665
+ "TCACC": 255,
666
+ "TCACCC": 513,
667
+ "TCACG": 978,
668
+ "TCACTGC": 327,
669
+ "TCACTGCAACC": 677,
670
+ "TCAG": 116,
671
+ "TCAGAA": 322,
672
+ "TCAGAC": 988,
673
+ "TCAGAG": 772,
674
+ "TCAGC": 222,
675
+ "TCAGCC": 268,
676
+ "TCAGG": 225,
677
+ "TCAGGAG": 826,
678
+ "TCAGGC": 742,
679
+ "TCAGGG": 713,
680
+ "TCAGTC": 1004,
681
+ "TCAGTG": 831,
682
+ "TCATAA": 881,
683
+ "TCATC": 251,
684
+ "TCATCC": 812,
685
+ "TCATG": 266,
686
+ "TCATGC": 933,
687
+ "TCATGCC": 758,
688
+ "TCATGG": 891,
689
+ "TCATT": 208,
690
+ "TCATTC": 529,
691
+ "TCATTG": 794,
692
+ "TCC": 31,
693
+ "TCCAAG": 887,
694
+ "TCCAC": 454,
695
+ "TCCACC": 669,
696
+ "TCCAGC": 671,
697
+ "TCCAGCC": 999,
698
+ "TCCAGG": 888,
699
+ "TCCATC": 819,
700
+ "TCCATG": 805,
701
+ "TCCC": 62,
702
+ "TCCCAAAGTGC": 489,
703
+ "TCCCAAG": 750,
704
+ "TCCCAGC": 232,
705
+ "TCCCAGCTAC": 895,
706
+ "TCCCC": 138,
707
+ "TCCCCC": 608,
708
+ "TCCCG": 836,
709
+ "TCCG": 349,
710
+ "TCCGCC": 830,
711
+ "TCCTAA": 861,
712
+ "TCCTC": 399,
713
+ "TCCTCC": 415,
714
+ "TCCTG": 317,
715
+ "TCCTGACCTC": 665,
716
+ "TCCTGAG": 789,
717
+ "TCCTGC": 585,
718
+ "TCCTGCC": 354,
719
+ "TCCTGCCTCAGCC": 603,
720
+ "TCCTGG": 728,
721
+ "TCCTGGG": 855,
722
+ "TCCTTC": 684,
723
+ "TCCTTG": 784,
724
+ "TCG": 178,
725
+ "TCGC": 344,
726
+ "TCGG": 530,
727
+ "TCGGCC": 907,
728
+ "TCTAA": 250,
729
+ "TCTAC": 299,
730
+ "TCTACC": 1023,
731
+ "TCTAG": 311,
732
+ "TCTAT": 651,
733
+ "TCTATC": 916,
734
+ "TCTATG": 945,
735
+ "TCTATT": 571,
736
+ "TCTC": 61,
737
+ "TCTCC": 185,
738
+ "TCTCCC": 504,
739
+ "TCTCG": 538,
740
+ "TCTCTCTC": 786,
741
+ "TCTG": 78,
742
+ "TCTGC": 211,
743
+ "TCTGCC": 341,
744
+ "TCTGG": 275,
745
+ "TCTGGC": 447,
746
+ "TCTGGG": 667,
747
+ "TCTGTCTC": 963,
748
+ "TCTGTG": 543,
749
+ "TCTT": 209,
750
+ "TCTTAA": 939,
751
+ "TCTTAC": 947,
752
+ "TCTTC": 190,
753
+ "TCTTCC": 496,
754
+ "TCTTG": 226,
755
+ "TCTTGC": 581,
756
+ "TCTTGG": 813,
757
+ "TCTTTC": 338,
758
+ "TCTTTG": 583,
759
+ "TCTTTT": 253,
760
+ "TCTTTTC": 1014,
761
+ "TG": 20,
762
+ "TG</w>": 562,
763
+ "TGAA": 80,
764
+ "TGAAAA": 282,
765
+ "TGAAAC": 452,
766
+ "TGAAACCCC": 858,
767
+ "TGAAC": 237,
768
+ "TGAACC": 681,
769
+ "TGAAG": 204,
770
+ "TGAAGC": 525,
771
+ "TGAAGG": 468,
772
+ "TGAC": 101,
773
+ "TGACAC": 707,
774
+ "TGACC": 279,
775
+ "TGACCC": 842,
776
+ "TGAG": 110,
777
+ "TGAGAA": 389,
778
+ "TGAGAC": 367,
779
+ "TGAGAG": 616,
780
+ "TGAGC": 224,
781
+ "TGAGCC": 555,
782
+ "TGAGG": 181,
783
+ "TGAGGC": 267,
784
+ "TGAGGG": 622,
785
+ "TGAGTC": 899,
786
+ "TGAGTG": 696,
787
+ "TGATAA": 553,
788
+ "TGATAC": 915,
789
+ "TGATC": 288,
790
+ "TGATCC": 411,
791
+ "TGATG": 218,
792
+ "TGATGC": 735,
793
+ "TGATGG": 618,
794
+ "TGATT": 223,
795
+ "TGATTC": 432,
796
+ "TGATTG": 883,
797
+ "TGC": 40,
798
+ "TGCAAG": 704,
799
+ "TGCAC": 460,
800
+ "TGCAGC": 610,
801
+ "TGCAGG": 918,
802
+ "TGCATG": 941,
803
+ "TGCC": 72,
804
+ "TGCCC": 205,
805
+ "TGCCCC": 506,
806
+ "TGCG": 333,
807
+ "TGCTC": 473,
808
+ "TGCTCC": 754,
809
+ "TGCTGC": 431,
810
+ "TGCTGG": 838,
811
+ "TGCTTC": 749,
812
+ "TGG": 41,
813
+ "TGGAAAA": 985,
814
+ "TGGAAC": 647,
815
+ "TGGAAG": 487,
816
+ "TGGAC": 560,
817
+ "TGGAG": 164,
818
+ "TGGAGC": 511,
819
+ "TGGAGG": 611,
820
+ "TGGAGTGC": 407,
821
+ "TGGATC": 969,
822
+ "TGGATG": 996,
823
+ "TGGC": 81,
824
+ "TGGCC": 125,
825
+ "TGGCCC": 563,
826
+ "TGGCG": 859,
827
+ "TGGCTCAC": 764,
828
+ "TGGG": 48,
829
+ "TGGGAGG": 944,
830
+ "TGGGATTAC": 332,
831
+ "TGGGATTACAGGC": 501,
832
+ "TGGGC": 119,
833
+ "TGGGCAAC": 697,
834
+ "TGGGCC": 377,
835
+ "TGGGCG": 924,
836
+ "TGGGG": 140,
837
+ "TGGGGC": 362,
838
+ "TGGGGG": 373,
839
+ "TGGGTGAC": 902,
840
+ "TGGTAA": 856,
841
+ "TGGTAG": 972,
842
+ "TGGTGC": 676,
843
+ "TGGTGG": 599,
844
+ "TGGTTC": 1005,
845
+ "TGTAA": 131,
846
+ "TGTAAC": 801,
847
+ "TGTAAG": 763,
848
+ "TGTAATCCCAGC": 375,
849
+ "TGTAATCCCAGCACTTTGGG": 767,
850
+ "TGTAC": 292,
851
+ "TGTACC": 983,
852
+ "TGTAG": 195,
853
+ "TGTAGC": 952,
854
+ "TGTAGG": 929,
855
+ "TGTAT": 335,
856
+ "TGTATC": 751,
857
+ "TGTATG": 579,
858
+ "TGTATT": 300,
859
+ "TGTC": 107,
860
+ "TGTCAC": 762,
861
+ "TGTCC": 248,
862
+ "TGTCCC": 718,
863
+ "TGTCTC": 330,
864
+ "TGTCTG": 627,
865
+ "TGTG": 55,
866
+ "TGTGC": 200,
867
+ "TGTGCC": 397,
868
+ "TGTGG": 201,
869
+ "TGTGGC": 369,
870
+ "TGTGGG": 572,
871
+ "TGTGTGTG": 337,
872
+ "TGTT": 206,
873
+ "TGTTAA": 752,
874
+ "TGTTAC": 850,
875
+ "TGTTC": 227,
876
+ "TGTTCC": 566,
877
+ "TGTTG": 239,
878
+ "TGTTGC": 775,
879
+ "TGTTGG": 706,
880
+ "TGTTTC": 393,
881
+ "TGTTTG": 549,
882
+ "TGTTTT": 283,
883
+ "TGTTTTC": 869,
884
+ "TT": 18,
885
+ "TT</w>": 505,
886
+ "TTAA": 79,
887
+ "TTAAAA": 230,
888
+ "TTAAAAC": 954,
889
+ "TTAAAC": 495,
890
+ "TTAAC": 242,
891
+ "TTAACC": 645,
892
+ "TTAAG": 241,
893
+ "TTAAGC": 657,
894
+ "TTAAGG": 715,
895
+ "TTAC": 90,
896
+ "TTACAC": 746,
897
+ "TTACC": 298,
898
+ "TTACCC": 815,
899
+ "TTAG": 124,
900
+ "TTAGAA": 498,
901
+ "TTAGAC": 906,
902
+ "TTAGAG": 761,
903
+ "TTAGC": 281,
904
+ "TTAGCC": 510,
905
+ "TTAGG": 303,
906
+ "TTAGGC": 962,
907
+ "TTAGGG": 847,
908
+ "TTAGTG": 872,
909
+ "TTATAA": 422,
910
+ "TTATAC": 679,
911
+ "TTATAG": 1009,
912
+ "TTATATT": 837,
913
+ "TTATC": 256,
914
+ "TTATCC": 726,
915
+ "TTATG": 243,
916
+ "TTATGC": 804,
917
+ "TTATGG": 876,
918
+ "TTATT": 108,
919
+ "TTATTC": 435,
920
+ "TTATTG": 551,
921
+ "TTC": 36,
922
+ "TTCAAC": 526,
923
+ "TTCAAG": 348,
924
+ "TTCAC": 320,
925
+ "TTCAGC": 634,
926
+ "TTCAGG": 849,
927
+ "TTCATC": 624,
928
+ "TTCATG": 700,
929
+ "TTCATT": 593,
930
+ "TTCC": 65,
931
+ "TTCCC": 135,
932
+ "TTCCCC": 331,
933
+ "TTCG": 301,
934
+ "TTCTAA": 584,
935
+ "TTCTAC": 722,
936
+ "TTCTAG": 577,
937
+ "TTCTC": 141,
938
+ "TTCTCC": 382,
939
+ "TTCTG": 492,
940
+ "TTCTGC": 424,
941
+ "TTCTGG": 629,
942
+ "TTCTTC": 394,
943
+ "TTCTTG": 568,
944
+ "TTCTTTC": 779,
945
+ "TTCTTTT": 574,
946
+ "TTG": 43,
947
+ "TTGAAAA": 937,
948
+ "TTGAAC": 433,
949
+ "TTGAACC": 607,
950
+ "TTGAACCC": 803,
951
+ "TTGAAG": 619,
952
+ "TTGAC": 533,
953
+ "TTGAGG": 957,
954
+ "TTGC": 82,
955
+ "TTGCAGTG": 469,
956
+ "TTGCC": 165,
957
+ "TTGCCC": 357,
958
+ "TTGG": 58,
959
+ "TTGGAAACGGG": 993,
960
+ "TTGGC": 167,
961
+ "TTGGCC": 285,
962
+ "TTGGG": 183,
963
+ "TTGGGC": 503,
964
+ "TTGGGG": 491,
965
+ "TTGTAA": 625,
966
+ "TTGTAC": 932,
967
+ "TTGTAG": 689,
968
+ "TTGTATT": 823,
969
+ "TTGTC": 699,
970
+ "TTGTCC": 980,
971
+ "TTGTGC": 896,
972
+ "TTGTGG": 951,
973
+ "TTGTTC": 884,
974
+ "TTGTTG": 471,
975
+ "TTGTTTT": 721,
976
+ "TTTAA": 104,
977
+ "TTTAAC": 483,
978
+ "TTTAAG": 413,
979
+ "TTTAC": 155,
980
+ "TTTACC": 582,
981
+ "TTTAG": 139,
982
+ "TTTAGC": 637,
983
+ "TTTAGG": 670,
984
+ "TTTAGTAG": 518,
985
+ "TTTAT": 245,
986
+ "TTTATC": 425,
987
+ "TTTATG": 379,
988
+ "TTTATT": 193,
989
+ "TTTATTC": 890,
990
+ "TTTATTG": 1003,
991
+ "TTTC": 52,
992
+ "TTTCACCATG": 864,
993
+ "TTTCC": 114,
994
+ "TTTCCC": 368,
995
+ "TTTCCCC": 811,
996
+ "TTTCG": 982,
997
+ "TTTCTTTC": 712,
998
+ "TTTG": 64,
999
+ "TTTGC": 137,
1000
+ "TTTGCC": 358,
1001
+ "TTTGG": 159,
1002
+ "TTTGGC": 409,
1003
+ "TTTGGG": 421,
1004
+ "TTTGTAA": 926,
1005
+ "TTTGTG": 296,
1006
+ "TTTGTGATG": 879,
1007
+ "TTTT": 39,
1008
+ "TTTTAAAA": 841,
1009
+ "TTTTC": 100,
1010
+ "TTTTCC": 228,
1011
+ "TTTTG": 109,
1012
+ "TTTTGC": 374,
1013
+ "TTTTGCC": 1010,
1014
+ "TTTTGG": 391,
1015
+ "TTTTTAA": 481,
1016
+ "TTTTTATT": 1021,
1017
+ "TTTTTC": 693,
1018
+ "TTTTTCC": 991,
1019
+ "TTTTTTC": 936,
1020
+ "TTTTTTG": 552,
1021
+ "TTTTTTTC": 974,
1022
+ "TTTTTTTT": 147,
1023
+ "TTTTTTTTTTTT": 848,
1024
+ "TTTTTTTTTTTTTTTT": 620,
1025
+ "Y": 13
1026
+ }