vojtam commited on
Commit
643f42d
·
verified ·
1 Parent(s): 23a7ada

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +1310 -0
tokenizer.json ADDED
@@ -0,0 +1,1310 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[PAD]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": null,
26
+ "pre_tokenizer": {
27
+ "type": "ByteLevel",
28
+ "add_prefix_space": false,
29
+ "trim_offsets": true,
30
+ "use_regex": false
31
+ },
32
+ "post_processor": {
33
+ "type": "ByteLevel",
34
+ "add_prefix_space": true,
35
+ "trim_offsets": false,
36
+ "use_regex": true
37
+ },
38
+ "decoder": {
39
+ "type": "ByteLevel",
40
+ "add_prefix_space": true,
41
+ "trim_offsets": true,
42
+ "use_regex": true
43
+ },
44
+ "model": {
45
+ "type": "BPE",
46
+ "dropout": null,
47
+ "unk_token": null,
48
+ "continuing_subword_prefix": null,
49
+ "end_of_word_suffix": null,
50
+ "fuse_unk": false,
51
+ "byte_fallback": false,
52
+ "ignore_merges": false,
53
+ "vocab": {
54
+ "<|endoftext|>": 0,
55
+ "[PAD]": 1,
56
+ "A": 2,
57
+ "C": 3,
58
+ "G": 4,
59
+ "T": 5,
60
+ "Ċ": 6,
61
+ "TT": 7,
62
+ "AA": 8,
63
+ "TG": 9,
64
+ "AG": 10,
65
+ "CC": 11,
66
+ "TC": 12,
67
+ "AC": 13,
68
+ "GG": 14,
69
+ "ATT": 15,
70
+ "AT": 16,
71
+ "ATG": 17,
72
+ "GC": 18,
73
+ "TAA": 19,
74
+ "TCC": 20,
75
+ "ACC": 21,
76
+ "AAAA": 22,
77
+ "AGG": 23,
78
+ "AGC": 24,
79
+ "ATC": 25,
80
+ "TTC": 26,
81
+ "AAG": 27,
82
+ "TTTT": 28,
83
+ "TGC": 29,
84
+ "TGG": 30,
85
+ "AAC": 31,
86
+ "TTG": 32,
87
+ "TAG": 33,
88
+ "TAC": 34,
89
+ "CCC": 35,
90
+ "TATT": 36,
91
+ "TGGG": 37,
92
+ "AGAA": 38,
93
+ "TAT": 39,
94
+ "AGGG": 40,
95
+ "TTTC": 41,
96
+ "AGGC": 42,
97
+ "AGCC": 43,
98
+ "TGTG": 44,
99
+ "ATAA": 45,
100
+ "ATTC": 46,
101
+ "TTGG": 47,
102
+ "ACAC": 48,
103
+ "AAGG": 49,
104
+ "TCTC": 50,
105
+ "TCCC": 51,
106
+ "TATG": 52,
107
+ "TTTG": 53,
108
+ "TTCC": 54,
109
+ "AGAG": 55,
110
+ "AAAC": 56,
111
+ "ATGG": 57,
112
+ "AGTG": 58,
113
+ "ACCC": 59,
114
+ "AGAC": 60,
115
+ "TGCC": 61,
116
+ "ATTG": 62,
117
+ "ATCC": 63,
118
+ "ATGC": 64,
119
+ "ATAC": 65,
120
+ "TCAC": 66,
121
+ "TCTG": 67,
122
+ "TTAA": 68,
123
+ "TGAA": 69,
124
+ "TGGC": 70,
125
+ "TTGC": 71,
126
+ "TATC": 72,
127
+ "TAAG": 73,
128
+ "TAAC": 74,
129
+ "AAAG": 75,
130
+ "GGG": 76,
131
+ "AAGC": 77,
132
+ "GGC": 78,
133
+ "TTAC": 79,
134
+ "ATAT": 80,
135
+ "TAGC": 81,
136
+ "TACC": 82,
137
+ "AACC": 83,
138
+ "AATG": 84,
139
+ "TAGG": 85,
140
+ "ATATT": 86,
141
+ "GCC": 87,
142
+ "AGTC": 88,
143
+ "TTTTC": 89,
144
+ "TGAC": 90,
145
+ "AAAAC": 91,
146
+ "AATC": 92,
147
+ "TTTAA": 93,
148
+ "AAAAG": 94,
149
+ "ATAG": 95,
150
+ "TGTC": 96,
151
+ "TTATT": 97,
152
+ "TTTTG": 98,
153
+ "TGAG": 99,
154
+ "AATT": 100,
155
+ "AAATT": 101,
156
+ "ACAG": 102,
157
+ "TTTCC": 103,
158
+ "AATAA": 104,
159
+ "TCAG": 105,
160
+ "AGGCC": 106,
161
+ "AAATG": 107,
162
+ "TGGGC": 108,
163
+ "ACTC": 109,
164
+ "ACG": 110,
165
+ "ATTTC": 111,
166
+ "ACTG": 112,
167
+ "TTAG": 113,
168
+ "TGGCC": 114,
169
+ "ATATG": 115,
170
+ "ACAA": 116,
171
+ "ATCTC": 117,
172
+ "TATTC": 118,
173
+ "TGTAA": 119,
174
+ "ACTT": 120,
175
+ "ATTCC": 121,
176
+ "AAAT": 122,
177
+ "ATGCC": 123,
178
+ "AAAAAAAA": 124,
179
+ "TTCCC": 125,
180
+ "TTTGC": 126,
181
+ "TTTAG": 127,
182
+ "TCCCC": 128,
183
+ "TGGGG": 129,
184
+ "TTCTC": 130,
185
+ "TAAAA": 131,
186
+ "ACCCC": 132,
187
+ "AGAAG": 133,
188
+ "ACCTC": 134,
189
+ "AGGGC": 135,
190
+ "TTTTTTTT": 136,
191
+ "ACATT": 137,
192
+ "AGATG": 138,
193
+ "GGCC": 139,
194
+ "GTG": 140,
195
+ "AAGCC": 141,
196
+ "ATAAAA": 142,
197
+ "AGGAG": 143,
198
+ "ATGGC": 144,
199
+ "ATTAC": 145,
200
+ "TTTAC": 146,
201
+ "ATTGC": 147,
202
+ "TGGAG": 148,
203
+ "TCAA": 149,
204
+ "ACTGC": 150,
205
+ "TATTG": 151,
206
+ "AAGGC": 152,
207
+ "TTTGG": 153,
208
+ "TTGCC": 154,
209
+ "AAATC": 155,
210
+ "TTGGC": 156,
211
+ "GGGC": 157,
212
+ "ATATC": 158,
213
+ "AGAAC": 159,
214
+ "ACTCC": 160,
215
+ "ATCCC": 161,
216
+ "ATAAC": 162,
217
+ "AATTC": 163,
218
+ "AGGGG": 164,
219
+ "AAAGC": 165,
220
+ "AGAGC": 166,
221
+ "TCG": 167,
222
+ "ATTTT": 168,
223
+ "TGAGG": 169,
224
+ "ATGGG": 170,
225
+ "AAAGG": 171,
226
+ "TTGGG": 172,
227
+ "AGAAAA": 173,
228
+ "TCTCC": 174,
229
+ "ATAAG": 175,
230
+ "ATTTG": 176,
231
+ "TATCC": 177,
232
+ "ACCAC": 178,
233
+ "TCTTC": 179,
234
+ "ATCAC": 180,
235
+ "AGAGG": 181,
236
+ "TTTATT": 182,
237
+ "TGTAG": 183,
238
+ "AGTAA": 184,
239
+ "ATAGC": 185,
240
+ "AGCCC": 186,
241
+ "AGATT": 187,
242
+ "AGTT": 188,
243
+ "GGGG": 189,
244
+ "TGTGC": 190,
245
+ "TGTGG": 191,
246
+ "TATGC": 192,
247
+ "TGCCC": 193,
248
+ "TGAAG": 194,
249
+ "TGTT": 195,
250
+ "TCTT": 196,
251
+ "AGACC": 197,
252
+ "TCATT": 198,
253
+ "TCTGC": 199,
254
+ "AAGGG": 200,
255
+ "AGTTC": 201,
256
+ "AAACC": 202,
257
+ "ACATG": 203,
258
+ "ACTTC": 204,
259
+ "ACAGC": 205,
260
+ "AATAG": 206,
261
+ "AATAC": 207,
262
+ "TGATG": 208,
263
+ "AATGC": 209,
264
+ "AATGG": 210,
265
+ "TGATT": 211,
266
+ "TCAGC": 212,
267
+ "TGTTC": 213,
268
+ "TGAGC": 214,
269
+ "TCTTG": 215,
270
+ "TCAGG": 216,
271
+ "TTTTCC": 217,
272
+ "TTAAAA": 218,
273
+ "TATGG": 219,
274
+ "ATACC": 220,
275
+ "AGTGG": 221,
276
+ "TCCCAGC": 222,
277
+ "AGATC": 223,
278
+ "AACCC": 224,
279
+ "TACCC": 225,
280
+ "TGAAC": 226,
281
+ "AATCC": 227,
282
+ "TGTTG": 228,
283
+ "TTAAG": 229,
284
+ "TAGCC": 230,
285
+ "TTAAC": 231,
286
+ "TTATG": 232,
287
+ "ATAGG": 233,
288
+ "AATTG": 234,
289
+ "TTTAT": 235,
290
+ "AGTGC": 236,
291
+ "TGTCC": 237,
292
+ "TAGGC": 238,
293
+ "TCTAA": 239,
294
+ "AĊ": 240,
295
+ "TCATC": 241,
296
+ "TCAAG": 242,
297
+ "TCACC": 243,
298
+ "AATTTT": 244,
299
+ "TCTTTT": 245,
300
+ "TTATC": 246,
301
+ "AGAAGC": 247,
302
+ "AGTGGC": 248,
303
+ "ATTTTC": 249,
304
+ "CCCC": 250,
305
+ "AAGAC": 251,
306
+ "AGTAG": 252,
307
+ "ATTGG": 253,
308
+ "TCATG": 254,
309
+ "AAATAA": 255
310
+ },
311
+ "merges": [
312
+ [
313
+ "T",
314
+ "T"
315
+ ],
316
+ [
317
+ "A",
318
+ "A"
319
+ ],
320
+ [
321
+ "T",
322
+ "G"
323
+ ],
324
+ [
325
+ "A",
326
+ "G"
327
+ ],
328
+ [
329
+ "C",
330
+ "C"
331
+ ],
332
+ [
333
+ "T",
334
+ "C"
335
+ ],
336
+ [
337
+ "A",
338
+ "C"
339
+ ],
340
+ [
341
+ "G",
342
+ "G"
343
+ ],
344
+ [
345
+ "A",
346
+ "TT"
347
+ ],
348
+ [
349
+ "A",
350
+ "T"
351
+ ],
352
+ [
353
+ "A",
354
+ "TG"
355
+ ],
356
+ [
357
+ "G",
358
+ "C"
359
+ ],
360
+ [
361
+ "T",
362
+ "AA"
363
+ ],
364
+ [
365
+ "T",
366
+ "CC"
367
+ ],
368
+ [
369
+ "A",
370
+ "CC"
371
+ ],
372
+ [
373
+ "AA",
374
+ "AA"
375
+ ],
376
+ [
377
+ "AG",
378
+ "G"
379
+ ],
380
+ [
381
+ "AG",
382
+ "C"
383
+ ],
384
+ [
385
+ "A",
386
+ "TC"
387
+ ],
388
+ [
389
+ "TT",
390
+ "C"
391
+ ],
392
+ [
393
+ "AA",
394
+ "G"
395
+ ],
396
+ [
397
+ "TT",
398
+ "TT"
399
+ ],
400
+ [
401
+ "TG",
402
+ "C"
403
+ ],
404
+ [
405
+ "TG",
406
+ "G"
407
+ ],
408
+ [
409
+ "AA",
410
+ "C"
411
+ ],
412
+ [
413
+ "TT",
414
+ "G"
415
+ ],
416
+ [
417
+ "T",
418
+ "AG"
419
+ ],
420
+ [
421
+ "T",
422
+ "AC"
423
+ ],
424
+ [
425
+ "CC",
426
+ "C"
427
+ ],
428
+ [
429
+ "T",
430
+ "ATT"
431
+ ],
432
+ [
433
+ "TG",
434
+ "GG"
435
+ ],
436
+ [
437
+ "AG",
438
+ "AA"
439
+ ],
440
+ [
441
+ "T",
442
+ "AT"
443
+ ],
444
+ [
445
+ "AG",
446
+ "GG"
447
+ ],
448
+ [
449
+ "TT",
450
+ "TC"
451
+ ],
452
+ [
453
+ "AG",
454
+ "GC"
455
+ ],
456
+ [
457
+ "AG",
458
+ "CC"
459
+ ],
460
+ [
461
+ "TG",
462
+ "TG"
463
+ ],
464
+ [
465
+ "AT",
466
+ "AA"
467
+ ],
468
+ [
469
+ "ATT",
470
+ "C"
471
+ ],
472
+ [
473
+ "TT",
474
+ "GG"
475
+ ],
476
+ [
477
+ "AC",
478
+ "AC"
479
+ ],
480
+ [
481
+ "AA",
482
+ "GG"
483
+ ],
484
+ [
485
+ "TC",
486
+ "TC"
487
+ ],
488
+ [
489
+ "TCC",
490
+ "C"
491
+ ],
492
+ [
493
+ "T",
494
+ "ATG"
495
+ ],
496
+ [
497
+ "TT",
498
+ "TG"
499
+ ],
500
+ [
501
+ "TT",
502
+ "CC"
503
+ ],
504
+ [
505
+ "AG",
506
+ "AG"
507
+ ],
508
+ [
509
+ "AA",
510
+ "AC"
511
+ ],
512
+ [
513
+ "ATG",
514
+ "G"
515
+ ],
516
+ [
517
+ "AG",
518
+ "TG"
519
+ ],
520
+ [
521
+ "ACC",
522
+ "C"
523
+ ],
524
+ [
525
+ "AG",
526
+ "AC"
527
+ ],
528
+ [
529
+ "TG",
530
+ "CC"
531
+ ],
532
+ [
533
+ "ATT",
534
+ "G"
535
+ ],
536
+ [
537
+ "AT",
538
+ "CC"
539
+ ],
540
+ [
541
+ "ATG",
542
+ "C"
543
+ ],
544
+ [
545
+ "AT",
546
+ "AC"
547
+ ],
548
+ [
549
+ "TC",
550
+ "AC"
551
+ ],
552
+ [
553
+ "TC",
554
+ "TG"
555
+ ],
556
+ [
557
+ "TT",
558
+ "AA"
559
+ ],
560
+ [
561
+ "TG",
562
+ "AA"
563
+ ],
564
+ [
565
+ "TG",
566
+ "GC"
567
+ ],
568
+ [
569
+ "TT",
570
+ "GC"
571
+ ],
572
+ [
573
+ "T",
574
+ "ATC"
575
+ ],
576
+ [
577
+ "TAA",
578
+ "G"
579
+ ],
580
+ [
581
+ "TAA",
582
+ "C"
583
+ ],
584
+ [
585
+ "AA",
586
+ "AG"
587
+ ],
588
+ [
589
+ "GG",
590
+ "G"
591
+ ],
592
+ [
593
+ "AA",
594
+ "GC"
595
+ ],
596
+ [
597
+ "GG",
598
+ "C"
599
+ ],
600
+ [
601
+ "TT",
602
+ "AC"
603
+ ],
604
+ [
605
+ "AT",
606
+ "AT"
607
+ ],
608
+ [
609
+ "T",
610
+ "AGC"
611
+ ],
612
+ [
613
+ "T",
614
+ "ACC"
615
+ ],
616
+ [
617
+ "AA",
618
+ "CC"
619
+ ],
620
+ [
621
+ "AA",
622
+ "TG"
623
+ ],
624
+ [
625
+ "T",
626
+ "AGG"
627
+ ],
628
+ [
629
+ "AT",
630
+ "ATT"
631
+ ],
632
+ [
633
+ "G",
634
+ "CC"
635
+ ],
636
+ [
637
+ "AG",
638
+ "TC"
639
+ ],
640
+ [
641
+ "TT",
642
+ "TTC"
643
+ ],
644
+ [
645
+ "TG",
646
+ "AC"
647
+ ],
648
+ [
649
+ "AAAA",
650
+ "C"
651
+ ],
652
+ [
653
+ "AA",
654
+ "TC"
655
+ ],
656
+ [
657
+ "TT",
658
+ "TAA"
659
+ ],
660
+ [
661
+ "AAAA",
662
+ "G"
663
+ ],
664
+ [
665
+ "AT",
666
+ "AG"
667
+ ],
668
+ [
669
+ "TG",
670
+ "TC"
671
+ ],
672
+ [
673
+ "TT",
674
+ "ATT"
675
+ ],
676
+ [
677
+ "TTTT",
678
+ "G"
679
+ ],
680
+ [
681
+ "TG",
682
+ "AG"
683
+ ],
684
+ [
685
+ "AA",
686
+ "TT"
687
+ ],
688
+ [
689
+ "AA",
690
+ "ATT"
691
+ ],
692
+ [
693
+ "AC",
694
+ "AG"
695
+ ],
696
+ [
697
+ "TT",
698
+ "TCC"
699
+ ],
700
+ [
701
+ "AA",
702
+ "TAA"
703
+ ],
704
+ [
705
+ "TC",
706
+ "AG"
707
+ ],
708
+ [
709
+ "AGG",
710
+ "CC"
711
+ ],
712
+ [
713
+ "AA",
714
+ "ATG"
715
+ ],
716
+ [
717
+ "TGGG",
718
+ "C"
719
+ ],
720
+ [
721
+ "AC",
722
+ "TC"
723
+ ],
724
+ [
725
+ "AC",
726
+ "G"
727
+ ],
728
+ [
729
+ "ATT",
730
+ "TC"
731
+ ],
732
+ [
733
+ "AC",
734
+ "TG"
735
+ ],
736
+ [
737
+ "TT",
738
+ "AG"
739
+ ],
740
+ [
741
+ "TGG",
742
+ "CC"
743
+ ],
744
+ [
745
+ "AT",
746
+ "ATG"
747
+ ],
748
+ [
749
+ "AC",
750
+ "AA"
751
+ ],
752
+ [
753
+ "ATC",
754
+ "TC"
755
+ ],
756
+ [
757
+ "TATT",
758
+ "C"
759
+ ],
760
+ [
761
+ "TG",
762
+ "TAA"
763
+ ],
764
+ [
765
+ "AC",
766
+ "TT"
767
+ ],
768
+ [
769
+ "ATT",
770
+ "CC"
771
+ ],
772
+ [
773
+ "AA",
774
+ "AT"
775
+ ],
776
+ [
777
+ "ATG",
778
+ "CC"
779
+ ],
780
+ [
781
+ "AAAA",
782
+ "AAAA"
783
+ ],
784
+ [
785
+ "TT",
786
+ "CCC"
787
+ ],
788
+ [
789
+ "TT",
790
+ "TGC"
791
+ ],
792
+ [
793
+ "TT",
794
+ "TAG"
795
+ ],
796
+ [
797
+ "TCC",
798
+ "CC"
799
+ ],
800
+ [
801
+ "TGGG",
802
+ "G"
803
+ ],
804
+ [
805
+ "TTC",
806
+ "TC"
807
+ ],
808
+ [
809
+ "TAA",
810
+ "AA"
811
+ ],
812
+ [
813
+ "ACC",
814
+ "CC"
815
+ ],
816
+ [
817
+ "AG",
818
+ "AAG"
819
+ ],
820
+ [
821
+ "ACC",
822
+ "TC"
823
+ ],
824
+ [
825
+ "AGGG",
826
+ "C"
827
+ ],
828
+ [
829
+ "TTTT",
830
+ "TTTT"
831
+ ],
832
+ [
833
+ "AC",
834
+ "ATT"
835
+ ],
836
+ [
837
+ "AG",
838
+ "ATG"
839
+ ],
840
+ [
841
+ "GG",
842
+ "CC"
843
+ ],
844
+ [
845
+ "G",
846
+ "TG"
847
+ ],
848
+ [
849
+ "AAG",
850
+ "CC"
851
+ ],
852
+ [
853
+ "AT",
854
+ "AAAA"
855
+ ],
856
+ [
857
+ "AGG",
858
+ "AG"
859
+ ],
860
+ [
861
+ "ATG",
862
+ "GC"
863
+ ],
864
+ [
865
+ "ATT",
866
+ "AC"
867
+ ],
868
+ [
869
+ "TT",
870
+ "TAC"
871
+ ],
872
+ [
873
+ "ATT",
874
+ "GC"
875
+ ],
876
+ [
877
+ "TGG",
878
+ "AG"
879
+ ],
880
+ [
881
+ "TC",
882
+ "AA"
883
+ ],
884
+ [
885
+ "AC",
886
+ "TGC"
887
+ ],
888
+ [
889
+ "TATT",
890
+ "G"
891
+ ],
892
+ [
893
+ "AAGG",
894
+ "C"
895
+ ],
896
+ [
897
+ "TT",
898
+ "TGG"
899
+ ],
900
+ [
901
+ "TTG",
902
+ "CC"
903
+ ],
904
+ [
905
+ "AA",
906
+ "ATC"
907
+ ],
908
+ [
909
+ "TTGG",
910
+ "C"
911
+ ],
912
+ [
913
+ "GG",
914
+ "GC"
915
+ ],
916
+ [
917
+ "AT",
918
+ "ATC"
919
+ ],
920
+ [
921
+ "AG",
922
+ "AAC"
923
+ ],
924
+ [
925
+ "AC",
926
+ "TCC"
927
+ ],
928
+ [
929
+ "AT",
930
+ "CCC"
931
+ ],
932
+ [
933
+ "AT",
934
+ "AAC"
935
+ ],
936
+ [
937
+ "AA",
938
+ "TTC"
939
+ ],
940
+ [
941
+ "AGGG",
942
+ "G"
943
+ ],
944
+ [
945
+ "AA",
946
+ "AGC"
947
+ ],
948
+ [
949
+ "AG",
950
+ "AGC"
951
+ ],
952
+ [
953
+ "TC",
954
+ "G"
955
+ ],
956
+ [
957
+ "ATT",
958
+ "TT"
959
+ ],
960
+ [
961
+ "TG",
962
+ "AGG"
963
+ ],
964
+ [
965
+ "ATG",
966
+ "GG"
967
+ ],
968
+ [
969
+ "AA",
970
+ "AGG"
971
+ ],
972
+ [
973
+ "TTGG",
974
+ "G"
975
+ ],
976
+ [
977
+ "AG",
978
+ "AAAA"
979
+ ],
980
+ [
981
+ "TC",
982
+ "TCC"
983
+ ],
984
+ [
985
+ "AT",
986
+ "AAG"
987
+ ],
988
+ [
989
+ "ATT",
990
+ "TG"
991
+ ],
992
+ [
993
+ "TAT",
994
+ "CC"
995
+ ],
996
+ [
997
+ "ACC",
998
+ "AC"
999
+ ],
1000
+ [
1001
+ "TC",
1002
+ "TTC"
1003
+ ],
1004
+ [
1005
+ "ATC",
1006
+ "AC"
1007
+ ],
1008
+ [
1009
+ "AG",
1010
+ "AGG"
1011
+ ],
1012
+ [
1013
+ "TT",
1014
+ "TATT"
1015
+ ],
1016
+ [
1017
+ "TG",
1018
+ "TAG"
1019
+ ],
1020
+ [
1021
+ "AG",
1022
+ "TAA"
1023
+ ],
1024
+ [
1025
+ "AT",
1026
+ "AGC"
1027
+ ],
1028
+ [
1029
+ "AG",
1030
+ "CCC"
1031
+ ],
1032
+ [
1033
+ "AG",
1034
+ "ATT"
1035
+ ],
1036
+ [
1037
+ "AG",
1038
+ "TT"
1039
+ ],
1040
+ [
1041
+ "GG",
1042
+ "GG"
1043
+ ],
1044
+ [
1045
+ "TG",
1046
+ "TGC"
1047
+ ],
1048
+ [
1049
+ "TG",
1050
+ "TGG"
1051
+ ],
1052
+ [
1053
+ "TATG",
1054
+ "C"
1055
+ ],
1056
+ [
1057
+ "TG",
1058
+ "CCC"
1059
+ ],
1060
+ [
1061
+ "TG",
1062
+ "AAG"
1063
+ ],
1064
+ [
1065
+ "TG",
1066
+ "TT"
1067
+ ],
1068
+ [
1069
+ "TC",
1070
+ "TT"
1071
+ ],
1072
+ [
1073
+ "AG",
1074
+ "ACC"
1075
+ ],
1076
+ [
1077
+ "TC",
1078
+ "ATT"
1079
+ ],
1080
+ [
1081
+ "TC",
1082
+ "TGC"
1083
+ ],
1084
+ [
1085
+ "AAGG",
1086
+ "G"
1087
+ ],
1088
+ [
1089
+ "AG",
1090
+ "TTC"
1091
+ ],
1092
+ [
1093
+ "AA",
1094
+ "ACC"
1095
+ ],
1096
+ [
1097
+ "AC",
1098
+ "ATG"
1099
+ ],
1100
+ [
1101
+ "AC",
1102
+ "TTC"
1103
+ ],
1104
+ [
1105
+ "AC",
1106
+ "AGC"
1107
+ ],
1108
+ [
1109
+ "AA",
1110
+ "TAG"
1111
+ ],
1112
+ [
1113
+ "AA",
1114
+ "TAC"
1115
+ ],
1116
+ [
1117
+ "TG",
1118
+ "ATG"
1119
+ ],
1120
+ [
1121
+ "AA",
1122
+ "TGC"
1123
+ ],
1124
+ [
1125
+ "AA",
1126
+ "TGG"
1127
+ ],
1128
+ [
1129
+ "TG",
1130
+ "ATT"
1131
+ ],
1132
+ [
1133
+ "TC",
1134
+ "AGC"
1135
+ ],
1136
+ [
1137
+ "TG",
1138
+ "TTC"
1139
+ ],
1140
+ [
1141
+ "TG",
1142
+ "AGC"
1143
+ ],
1144
+ [
1145
+ "TC",
1146
+ "TTG"
1147
+ ],
1148
+ [
1149
+ "TC",
1150
+ "AGG"
1151
+ ],
1152
+ [
1153
+ "TTTT",
1154
+ "CC"
1155
+ ],
1156
+ [
1157
+ "TT",
1158
+ "AAAA"
1159
+ ],
1160
+ [
1161
+ "TATG",
1162
+ "G"
1163
+ ],
1164
+ [
1165
+ "AT",
1166
+ "ACC"
1167
+ ],
1168
+ [
1169
+ "AG",
1170
+ "TGG"
1171
+ ],
1172
+ [
1173
+ "TCCC",
1174
+ "AGC"
1175
+ ],
1176
+ [
1177
+ "AG",
1178
+ "ATC"
1179
+ ],
1180
+ [
1181
+ "AA",
1182
+ "CCC"
1183
+ ],
1184
+ [
1185
+ "T",
1186
+ "ACCC"
1187
+ ],
1188
+ [
1189
+ "TG",
1190
+ "AAC"
1191
+ ],
1192
+ [
1193
+ "AA",
1194
+ "TCC"
1195
+ ],
1196
+ [
1197
+ "TG",
1198
+ "TTG"
1199
+ ],
1200
+ [
1201
+ "TT",
1202
+ "AAG"
1203
+ ],
1204
+ [
1205
+ "TAG",
1206
+ "CC"
1207
+ ],
1208
+ [
1209
+ "TT",
1210
+ "AAC"
1211
+ ],
1212
+ [
1213
+ "TT",
1214
+ "ATG"
1215
+ ],
1216
+ [
1217
+ "AT",
1218
+ "AGG"
1219
+ ],
1220
+ [
1221
+ "AA",
1222
+ "TTG"
1223
+ ],
1224
+ [
1225
+ "TT",
1226
+ "TAT"
1227
+ ],
1228
+ [
1229
+ "AG",
1230
+ "TGC"
1231
+ ],
1232
+ [
1233
+ "TG",
1234
+ "TCC"
1235
+ ],
1236
+ [
1237
+ "TAG",
1238
+ "GC"
1239
+ ],
1240
+ [
1241
+ "TC",
1242
+ "TAA"
1243
+ ],
1244
+ [
1245
+ "A",
1246
+ "Ċ"
1247
+ ],
1248
+ [
1249
+ "TC",
1250
+ "ATC"
1251
+ ],
1252
+ [
1253
+ "TC",
1254
+ "AAG"
1255
+ ],
1256
+ [
1257
+ "TC",
1258
+ "ACC"
1259
+ ],
1260
+ [
1261
+ "AA",
1262
+ "TTTT"
1263
+ ],
1264
+ [
1265
+ "TC",
1266
+ "TTTT"
1267
+ ],
1268
+ [
1269
+ "TT",
1270
+ "ATC"
1271
+ ],
1272
+ [
1273
+ "AGAA",
1274
+ "GC"
1275
+ ],
1276
+ [
1277
+ "AGTG",
1278
+ "GC"
1279
+ ],
1280
+ [
1281
+ "ATT",
1282
+ "TTC"
1283
+ ],
1284
+ [
1285
+ "CC",
1286
+ "CC"
1287
+ ],
1288
+ [
1289
+ "AAG",
1290
+ "AC"
1291
+ ],
1292
+ [
1293
+ "AG",
1294
+ "TAG"
1295
+ ],
1296
+ [
1297
+ "ATT",
1298
+ "GG"
1299
+ ],
1300
+ [
1301
+ "TC",
1302
+ "ATG"
1303
+ ],
1304
+ [
1305
+ "AA",
1306
+ "ATAA"
1307
+ ]
1308
+ ]
1309
+ }
1310
+ }