jirvine commited on
Commit
271ff69
·
verified ·
1 Parent(s): 9e826e0

Upload OriGen tokenizer configuration

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +37 -0
  2. tokenizer.json +1144 -0
  3. tokenizer_config.json +981 -0
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[START]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[END]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,1144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[START]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[END]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[PAD]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[UNK]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[SEP]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 29,
53
+ "content": "[Acetobacter pasteurianus]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": true,
58
+ "special": false
59
+ },
60
+ {
61
+ "id": 30,
62
+ "content": "[Acinetobacter]",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": true,
67
+ "special": false
68
+ },
69
+ {
70
+ "id": 31,
71
+ "content": "[Acinetobacter baumannii]",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": true,
76
+ "special": false
77
+ },
78
+ {
79
+ "id": 32,
80
+ "content": "[Acinetobacter haemolyticus]",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 33,
89
+ "content": "[Acinetobacter indicus]",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 34,
98
+ "content": "[Acinetobacter johnsonii]",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 35,
107
+ "content": "[Acinetobacter lwoffii]",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 36,
116
+ "content": "[Acinetobacter nosocomialis]",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ {
124
+ "id": 37,
125
+ "content": "[Acinetobacter pittii]",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": true,
130
+ "special": false
131
+ },
132
+ {
133
+ "id": 38,
134
+ "content": "[Acinetobacter schindleri]",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": true,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 39,
143
+ "content": "[Acinetobacter seifertii]",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": true,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 40,
152
+ "content": "[Aeromonas]",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": true,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 41,
161
+ "content": "[Aeromonas caviae]",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": true,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 42,
170
+ "content": "[Aeromonas hydrophila]",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": true,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 43,
179
+ "content": "[Aeromonas salmonicida]",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": true,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 44,
188
+ "content": "[Aeromonas veronii]",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": true,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 45,
197
+ "content": "[Bacillus]",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": true,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 46,
206
+ "content": "[Bacillus anthracis]",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": true,
211
+ "special": false
212
+ },
213
+ {
214
+ "id": 47,
215
+ "content": "[Bacillus cereus]",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": true,
220
+ "special": false
221
+ },
222
+ {
223
+ "id": 48,
224
+ "content": "[Bacillus cytotoxicus]",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": true,
229
+ "special": false
230
+ },
231
+ {
232
+ "id": 49,
233
+ "content": "[Bacillus mycoides]",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": true,
238
+ "special": false
239
+ },
240
+ {
241
+ "id": 50,
242
+ "content": "[Bacillus subtilis]",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": true,
247
+ "special": false
248
+ },
249
+ {
250
+ "id": 51,
251
+ "content": "[Bacillus thuringiensis]",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": true,
256
+ "special": false
257
+ },
258
+ {
259
+ "id": 52,
260
+ "content": "[Bacillus velezensis]",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": true,
265
+ "special": false
266
+ },
267
+ {
268
+ "id": 53,
269
+ "content": "[Bacteroides fragilis]",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": true,
274
+ "special": false
275
+ },
276
+ {
277
+ "id": 54,
278
+ "content": "[Buchnera aphidicola]",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": true,
283
+ "special": false
284
+ },
285
+ {
286
+ "id": 55,
287
+ "content": "[Campylobacter coli]",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": true,
292
+ "special": false
293
+ },
294
+ {
295
+ "id": 56,
296
+ "content": "[Campylobacter fetus]",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": true,
301
+ "special": false
302
+ },
303
+ {
304
+ "id": 57,
305
+ "content": "[Campylobacter jejuni]",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": true,
310
+ "special": false
311
+ },
312
+ {
313
+ "id": 58,
314
+ "content": "[Citrobacter]",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": true,
319
+ "special": false
320
+ },
321
+ {
322
+ "id": 59,
323
+ "content": "[Citrobacter freundii]",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": true,
328
+ "special": false
329
+ },
330
+ {
331
+ "id": 60,
332
+ "content": "[Citrobacter portucalensis]",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": true,
337
+ "special": false
338
+ },
339
+ {
340
+ "id": 61,
341
+ "content": "[Clostridioides difficile]",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": true,
346
+ "special": false
347
+ },
348
+ {
349
+ "id": 62,
350
+ "content": "[Clostridium perfringens]",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": true,
355
+ "special": false
356
+ },
357
+ {
358
+ "id": 63,
359
+ "content": "[Clostridium taeniosporum]",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": true,
364
+ "special": false
365
+ },
366
+ {
367
+ "id": 64,
368
+ "content": "[Edwardsiella ictaluri]",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": true,
373
+ "special": false
374
+ },
375
+ {
376
+ "id": 65,
377
+ "content": "[Enterobacter]",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": true,
382
+ "special": false
383
+ },
384
+ {
385
+ "id": 66,
386
+ "content": "[Enterobacter asburiae]",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": true,
391
+ "special": false
392
+ },
393
+ {
394
+ "id": 67,
395
+ "content": "[Enterobacter cloacae]",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": true,
400
+ "special": false
401
+ },
402
+ {
403
+ "id": 68,
404
+ "content": "[Enterobacter hormaechei]",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": true,
409
+ "special": false
410
+ },
411
+ {
412
+ "id": 69,
413
+ "content": "[Enterobacter kobei]",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": true,
418
+ "special": false
419
+ },
420
+ {
421
+ "id": 70,
422
+ "content": "[Enterobacter roggenkampii]",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": true,
427
+ "special": false
428
+ },
429
+ {
430
+ "id": 71,
431
+ "content": "[Enterococcus casseliflavus]",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": true,
436
+ "special": false
437
+ },
438
+ {
439
+ "id": 72,
440
+ "content": "[Enterococcus faecalis]",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": true,
445
+ "special": false
446
+ },
447
+ {
448
+ "id": 73,
449
+ "content": "[Enterococcus faecium]",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": true,
454
+ "special": false
455
+ },
456
+ {
457
+ "id": 74,
458
+ "content": "[Enterococcus hirae]",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": true,
463
+ "special": false
464
+ },
465
+ {
466
+ "id": 75,
467
+ "content": "[Escherichia]",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": true,
472
+ "special": false
473
+ },
474
+ {
475
+ "id": 76,
476
+ "content": "[Escherichia albertii]",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": true,
481
+ "special": false
482
+ },
483
+ {
484
+ "id": 77,
485
+ "content": "[Escherichia coli]",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": true,
490
+ "special": false
491
+ },
492
+ {
493
+ "id": 78,
494
+ "content": "[Escherichia fergusonii]",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": true,
499
+ "special": false
500
+ },
501
+ {
502
+ "id": 79,
503
+ "content": "[Escherichia marmotae]",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": true,
508
+ "special": false
509
+ },
510
+ {
511
+ "id": 80,
512
+ "content": "[Helicobacter pylori]",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": true,
517
+ "special": false
518
+ },
519
+ {
520
+ "id": 81,
521
+ "content": "[Klebsiella]",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": true,
526
+ "special": false
527
+ },
528
+ {
529
+ "id": 82,
530
+ "content": "[Klebsiella aerogenes]",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": true,
535
+ "special": false
536
+ },
537
+ {
538
+ "id": 83,
539
+ "content": "[Klebsiella grimontii]",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": true,
544
+ "special": false
545
+ },
546
+ {
547
+ "id": 84,
548
+ "content": "[Klebsiella michiganensis]",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": true,
553
+ "special": false
554
+ },
555
+ {
556
+ "id": 85,
557
+ "content": "[Klebsiella oxytoca]",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": true,
562
+ "special": false
563
+ },
564
+ {
565
+ "id": 86,
566
+ "content": "[Klebsiella pneumoniae]",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": true,
571
+ "special": false
572
+ },
573
+ {
574
+ "id": 87,
575
+ "content": "[Klebsiella quasipneumoniae]",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": true,
580
+ "special": false
581
+ },
582
+ {
583
+ "id": 88,
584
+ "content": "[Klebsiella variicola]",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": true,
589
+ "special": false
590
+ },
591
+ {
592
+ "id": 89,
593
+ "content": "[Lacticaseibacillus paracasei]",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": true,
598
+ "special": false
599
+ },
600
+ {
601
+ "id": 90,
602
+ "content": "[Lactiplantibacillus pentosus]",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": true,
607
+ "special": false
608
+ },
609
+ {
610
+ "id": 91,
611
+ "content": "[Lactiplantibacillus plantarum]",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": true,
616
+ "special": false
617
+ },
618
+ {
619
+ "id": 92,
620
+ "content": "[Lactobacillus plantarum]",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": true,
625
+ "special": false
626
+ },
627
+ {
628
+ "id": 93,
629
+ "content": "[Lactococcus cremoris]",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": true,
634
+ "special": false
635
+ },
636
+ {
637
+ "id": 94,
638
+ "content": "[Lactococcus garvieae]",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": true,
643
+ "special": false
644
+ },
645
+ {
646
+ "id": 95,
647
+ "content": "[Lactococcus lactis]",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": true,
652
+ "special": false
653
+ },
654
+ {
655
+ "id": 96,
656
+ "content": "[Latilactobacillus sakei]",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": true,
661
+ "special": false
662
+ },
663
+ {
664
+ "id": 97,
665
+ "content": "[Leuconostoc citreum]",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": true,
670
+ "special": false
671
+ },
672
+ {
673
+ "id": 98,
674
+ "content": "[Leuconostoc mesenteroides]",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": true,
679
+ "special": false
680
+ },
681
+ {
682
+ "id": 99,
683
+ "content": "[Levilactobacillus brevis]",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": true,
688
+ "special": false
689
+ },
690
+ {
691
+ "id": 100,
692
+ "content": "[Ligilactobacillus salivarius]",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": true,
697
+ "special": false
698
+ },
699
+ {
700
+ "id": 101,
701
+ "content": "[Listeria innocua]",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": true,
706
+ "special": false
707
+ },
708
+ {
709
+ "id": 102,
710
+ "content": "[Listeria monocytogenes]",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": true,
715
+ "special": false
716
+ },
717
+ {
718
+ "id": 103,
719
+ "content": "[Loigolactobacillus backii]",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": true,
724
+ "special": false
725
+ },
726
+ {
727
+ "id": 104,
728
+ "content": "[Mammaliicoccus sciuri]",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": true,
733
+ "special": false
734
+ },
735
+ {
736
+ "id": 105,
737
+ "content": "[Moraxella osloensis]",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": true,
742
+ "special": false
743
+ },
744
+ {
745
+ "id": 106,
746
+ "content": "[Pediococcus acidilactici]",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": true,
751
+ "special": false
752
+ },
753
+ {
754
+ "id": 107,
755
+ "content": "[Proteus mirabilis]",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": true,
760
+ "special": false
761
+ },
762
+ {
763
+ "id": 108,
764
+ "content": "[Providencia rettgeri]",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": true,
769
+ "special": false
770
+ },
771
+ {
772
+ "id": 109,
773
+ "content": "[Providencia stuartii]",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": true,
778
+ "special": false
779
+ },
780
+ {
781
+ "id": 110,
782
+ "content": "[Pseudomonas]",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": true,
787
+ "special": false
788
+ },
789
+ {
790
+ "id": 111,
791
+ "content": "[Pseudomonas aeruginosa]",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": true,
796
+ "special": false
797
+ },
798
+ {
799
+ "id": 112,
800
+ "content": "[Pseudomonas putida]",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": true,
805
+ "special": false
806
+ },
807
+ {
808
+ "id": 113,
809
+ "content": "[Psychrobacter]",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": true,
814
+ "special": false
815
+ },
816
+ {
817
+ "id": 114,
818
+ "content": "[Raoultella ornithinolytica]",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": true,
823
+ "special": false
824
+ },
825
+ {
826
+ "id": 115,
827
+ "content": "[Raoultella planticola]",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": true,
832
+ "special": false
833
+ },
834
+ {
835
+ "id": 116,
836
+ "content": "[Salmonella]",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": true,
841
+ "special": false
842
+ },
843
+ {
844
+ "id": 117,
845
+ "content": "[Salmonella enterica]",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": true,
850
+ "special": false
851
+ },
852
+ {
853
+ "id": 118,
854
+ "content": "[Serratia marcescens]",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": true,
859
+ "special": false
860
+ },
861
+ {
862
+ "id": 119,
863
+ "content": "[Shigella boydii]",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": true,
868
+ "special": false
869
+ },
870
+ {
871
+ "id": 120,
872
+ "content": "[Shigella dysenteriae]",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": true,
877
+ "special": false
878
+ },
879
+ {
880
+ "id": 121,
881
+ "content": "[Shigella flexneri]",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": true,
886
+ "special": false
887
+ },
888
+ {
889
+ "id": 122,
890
+ "content": "[Shigella sonnei]",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": true,
895
+ "special": false
896
+ },
897
+ {
898
+ "id": 123,
899
+ "content": "[Staphylococcus arlettae]",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": true,
904
+ "special": false
905
+ },
906
+ {
907
+ "id": 124,
908
+ "content": "[Staphylococcus aureus]",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": true,
913
+ "special": false
914
+ },
915
+ {
916
+ "id": 125,
917
+ "content": "[Staphylococcus epidermidis]",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": true,
922
+ "special": false
923
+ },
924
+ {
925
+ "id": 126,
926
+ "content": "[Staphylococcus equorum]",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": true,
931
+ "special": false
932
+ },
933
+ {
934
+ "id": 127,
935
+ "content": "[Staphylococcus haemolyticus]",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": true,
940
+ "special": false
941
+ },
942
+ {
943
+ "id": 128,
944
+ "content": "[Staphylococcus hominis]",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": true,
949
+ "special": false
950
+ },
951
+ {
952
+ "id": 129,
953
+ "content": "[Staphylococcus lugdunensis]",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": true,
958
+ "special": false
959
+ },
960
+ {
961
+ "id": 130,
962
+ "content": "[Staphylococcus pasteuri]",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": true,
967
+ "special": false
968
+ },
969
+ {
970
+ "id": 131,
971
+ "content": "[Staphylococcus saprophyticus]",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": true,
976
+ "special": false
977
+ },
978
+ {
979
+ "id": 132,
980
+ "content": "[Staphylococcus simulans]",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": true,
985
+ "special": false
986
+ },
987
+ {
988
+ "id": 133,
989
+ "content": "[Staphylococcus warneri]",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": true,
994
+ "special": false
995
+ },
996
+ {
997
+ "id": 134,
998
+ "content": "[Streptococcus pneumoniae]",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": true,
1003
+ "special": false
1004
+ },
1005
+ {
1006
+ "id": 135,
1007
+ "content": "[Streptococcus pyogenes]",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": true,
1012
+ "special": false
1013
+ },
1014
+ {
1015
+ "id": 136,
1016
+ "content": "[Streptococcus thermophilus]",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": true,
1021
+ "special": false
1022
+ },
1023
+ {
1024
+ "id": 137,
1025
+ "content": "[Tetragenococcus halophilus]",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": true,
1030
+ "special": false
1031
+ },
1032
+ {
1033
+ "id": 138,
1034
+ "content": "[Vibrio cholerae]",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": true,
1039
+ "special": false
1040
+ },
1041
+ {
1042
+ "id": 139,
1043
+ "content": "[Yersinia enterocolitica]",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": true,
1048
+ "special": false
1049
+ },
1050
+ {
1051
+ "id": 140,
1052
+ "content": "[Yersinia pestis]",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": true,
1057
+ "special": false
1058
+ },
1059
+ {
1060
+ "id": 141,
1061
+ "content": "[Yersinia pseudotuberculosis]",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": true,
1066
+ "special": false
1067
+ },
1068
+ {
1069
+ "id": 142,
1070
+ "content": "[uncultured bacterium]",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": true,
1075
+ "special": false
1076
+ },
1077
+ {
1078
+ "id": 143,
1079
+ "content": "[UNKNOWN_SPECIES]",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": true,
1084
+ "special": false
1085
+ },
1086
+ {
1087
+ "id": 144,
1088
+ "content": "[UNANNOTATED_SPECIES]",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": true,
1093
+ "special": false
1094
+ }
1095
+ ],
1096
+ "normalizer": null,
1097
+ "pre_tokenizer": {
1098
+ "type": "Whitespace"
1099
+ },
1100
+ "post_processor": null,
1101
+ "decoder": null,
1102
+ "model": {
1103
+ "type": "BPE",
1104
+ "dropout": null,
1105
+ "unk_token": "[UNK]",
1106
+ "continuing_subword_prefix": null,
1107
+ "end_of_word_suffix": null,
1108
+ "fuse_unk": false,
1109
+ "byte_fallback": false,
1110
+ "ignore_merges": false,
1111
+ "vocab": {
1112
+ "[START]": 0,
1113
+ "[END]": 1,
1114
+ "[PAD]": 2,
1115
+ "[UNK]": 3,
1116
+ "[SEP]": 4,
1117
+ "A": 5,
1118
+ "C": 6,
1119
+ "D": 7,
1120
+ "E": 8,
1121
+ "F": 9,
1122
+ "G": 10,
1123
+ "H": 11,
1124
+ "I": 12,
1125
+ "K": 13,
1126
+ "L": 14,
1127
+ "M": 15,
1128
+ "N": 16,
1129
+ "P": 17,
1130
+ "Q": 18,
1131
+ "R": 19,
1132
+ "S": 20,
1133
+ "T": 21,
1134
+ "V": 22,
1135
+ "W": 23,
1136
+ "Y": 24,
1137
+ "a": 25,
1138
+ "c": 26,
1139
+ "g": 27,
1140
+ "t": 28
1141
+ },
1142
+ "merges": []
1143
+ }
1144
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,981 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[START]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[END]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[PAD]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "29": {
44
+ "content": "[Acetobacter pasteurianus]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "30": {
52
+ "content": "[Acinetobacter]",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "31": {
60
+ "content": "[Acinetobacter baumannii]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "32": {
68
+ "content": "[Acinetobacter haemolyticus]",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "33": {
76
+ "content": "[Acinetobacter indicus]",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "34": {
84
+ "content": "[Acinetobacter johnsonii]",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "35": {
92
+ "content": "[Acinetobacter lwoffii]",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "36": {
100
+ "content": "[Acinetobacter nosocomialis]",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "37": {
108
+ "content": "[Acinetobacter pittii]",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "38": {
116
+ "content": "[Acinetobacter schindleri]",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "39": {
124
+ "content": "[Acinetobacter seifertii]",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "40": {
132
+ "content": "[Aeromonas]",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "41": {
140
+ "content": "[Aeromonas caviae]",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "42": {
148
+ "content": "[Aeromonas hydrophila]",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "43": {
156
+ "content": "[Aeromonas salmonicida]",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "44": {
164
+ "content": "[Aeromonas veronii]",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "45": {
172
+ "content": "[Bacillus]",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "46": {
180
+ "content": "[Bacillus anthracis]",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "47": {
188
+ "content": "[Bacillus cereus]",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "48": {
196
+ "content": "[Bacillus cytotoxicus]",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "49": {
204
+ "content": "[Bacillus mycoides]",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50": {
212
+ "content": "[Bacillus subtilis]",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "51": {
220
+ "content": "[Bacillus thuringiensis]",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "52": {
228
+ "content": "[Bacillus velezensis]",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "53": {
236
+ "content": "[Bacteroides fragilis]",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "54": {
244
+ "content": "[Buchnera aphidicola]",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "55": {
252
+ "content": "[Campylobacter coli]",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "56": {
260
+ "content": "[Campylobacter fetus]",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "57": {
268
+ "content": "[Campylobacter jejuni]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "58": {
276
+ "content": "[Citrobacter]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "59": {
284
+ "content": "[Citrobacter freundii]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "60": {
292
+ "content": "[Citrobacter portucalensis]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "61": {
300
+ "content": "[Clostridioides difficile]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "62": {
308
+ "content": "[Clostridium perfringens]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "63": {
316
+ "content": "[Clostridium taeniosporum]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "64": {
324
+ "content": "[Edwardsiella ictaluri]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "65": {
332
+ "content": "[Enterobacter]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "66": {
340
+ "content": "[Enterobacter asburiae]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "67": {
348
+ "content": "[Enterobacter cloacae]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "68": {
356
+ "content": "[Enterobacter hormaechei]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "69": {
364
+ "content": "[Enterobacter kobei]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "70": {
372
+ "content": "[Enterobacter roggenkampii]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "71": {
380
+ "content": "[Enterococcus casseliflavus]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "72": {
388
+ "content": "[Enterococcus faecalis]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "73": {
396
+ "content": "[Enterococcus faecium]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "74": {
404
+ "content": "[Enterococcus hirae]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "75": {
412
+ "content": "[Escherichia]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "76": {
420
+ "content": "[Escherichia albertii]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "77": {
428
+ "content": "[Escherichia coli]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "78": {
436
+ "content": "[Escherichia fergusonii]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "79": {
444
+ "content": "[Escherichia marmotae]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "80": {
452
+ "content": "[Helicobacter pylori]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "81": {
460
+ "content": "[Klebsiella]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "82": {
468
+ "content": "[Klebsiella aerogenes]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "83": {
476
+ "content": "[Klebsiella grimontii]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "84": {
484
+ "content": "[Klebsiella michiganensis]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "85": {
492
+ "content": "[Klebsiella oxytoca]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "86": {
500
+ "content": "[Klebsiella pneumoniae]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "87": {
508
+ "content": "[Klebsiella quasipneumoniae]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "88": {
516
+ "content": "[Klebsiella variicola]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "89": {
524
+ "content": "[Lacticaseibacillus paracasei]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "90": {
532
+ "content": "[Lactiplantibacillus pentosus]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "91": {
540
+ "content": "[Lactiplantibacillus plantarum]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "92": {
548
+ "content": "[Lactobacillus plantarum]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "93": {
556
+ "content": "[Lactococcus cremoris]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "94": {
564
+ "content": "[Lactococcus garvieae]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "95": {
572
+ "content": "[Lactococcus lactis]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "96": {
580
+ "content": "[Latilactobacillus sakei]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "97": {
588
+ "content": "[Leuconostoc citreum]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "98": {
596
+ "content": "[Leuconostoc mesenteroides]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "99": {
604
+ "content": "[Levilactobacillus brevis]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "100": {
612
+ "content": "[Ligilactobacillus salivarius]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "101": {
620
+ "content": "[Listeria innocua]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "102": {
628
+ "content": "[Listeria monocytogenes]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "103": {
636
+ "content": "[Loigolactobacillus backii]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "104": {
644
+ "content": "[Mammaliicoccus sciuri]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "105": {
652
+ "content": "[Moraxella osloensis]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "106": {
660
+ "content": "[Pediococcus acidilactici]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "107": {
668
+ "content": "[Proteus mirabilis]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "108": {
676
+ "content": "[Providencia rettgeri]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "109": {
684
+ "content": "[Providencia stuartii]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "110": {
692
+ "content": "[Pseudomonas]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "111": {
700
+ "content": "[Pseudomonas aeruginosa]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "112": {
708
+ "content": "[Pseudomonas putida]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "113": {
716
+ "content": "[Psychrobacter]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "114": {
724
+ "content": "[Raoultella ornithinolytica]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "115": {
732
+ "content": "[Raoultella planticola]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "116": {
740
+ "content": "[Salmonella]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "117": {
748
+ "content": "[Salmonella enterica]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "118": {
756
+ "content": "[Serratia marcescens]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "119": {
764
+ "content": "[Shigella boydii]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "120": {
772
+ "content": "[Shigella dysenteriae]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "121": {
780
+ "content": "[Shigella flexneri]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "122": {
788
+ "content": "[Shigella sonnei]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "123": {
796
+ "content": "[Staphylococcus arlettae]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "124": {
804
+ "content": "[Staphylococcus aureus]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "125": {
812
+ "content": "[Staphylococcus epidermidis]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "126": {
820
+ "content": "[Staphylococcus equorum]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "127": {
828
+ "content": "[Staphylococcus haemolyticus]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "128": {
836
+ "content": "[Staphylococcus hominis]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "129": {
844
+ "content": "[Staphylococcus lugdunensis]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "130": {
852
+ "content": "[Staphylococcus pasteuri]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "131": {
860
+ "content": "[Staphylococcus saprophyticus]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "132": {
868
+ "content": "[Staphylococcus simulans]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "133": {
876
+ "content": "[Staphylococcus warneri]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "134": {
884
+ "content": "[Streptococcus pneumoniae]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "135": {
892
+ "content": "[Streptococcus pyogenes]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "136": {
900
+ "content": "[Streptococcus thermophilus]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "137": {
908
+ "content": "[Tetragenococcus halophilus]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "138": {
916
+ "content": "[Vibrio cholerae]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "139": {
924
+ "content": "[Yersinia enterocolitica]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ },
931
+ "140": {
932
+ "content": "[Yersinia pestis]",
933
+ "lstrip": false,
934
+ "normalized": true,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": false
938
+ },
939
+ "141": {
940
+ "content": "[Yersinia pseudotuberculosis]",
941
+ "lstrip": false,
942
+ "normalized": true,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": false
946
+ },
947
+ "142": {
948
+ "content": "[uncultured bacterium]",
949
+ "lstrip": false,
950
+ "normalized": true,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": false
954
+ },
955
+ "143": {
956
+ "content": "[UNKNOWN_SPECIES]",
957
+ "lstrip": false,
958
+ "normalized": true,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": false
962
+ },
963
+ "144": {
964
+ "content": "[UNANNOTATED_SPECIES]",
965
+ "lstrip": false,
966
+ "normalized": true,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": false
970
+ }
971
+ },
972
+ "bos_token": "[START]",
973
+ "clean_up_tokenization_spaces": true,
974
+ "eos_token": "[END]",
975
+ "extra_special_tokens": {},
976
+ "model_max_length": 1000000000000000019884624838656,
977
+ "pad_token": "[PAD]",
978
+ "sep_token": "[SEP]",
979
+ "tokenizer_class": "PreTrainedTokenizerFast",
980
+ "unk_token": "[UNK]"
981
+ }