patronus-protect commited on
Commit
c09bcf4
·
verified ·
1 Parent(s): 2139759

Sync orca-sonar-document-classifier files

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ l2/l2_config.json filter=lfs diff=lfs merge=lfs -text
cascade/cascade_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "thresholds": {},
3
+ "global_k": 0.35
4
+ }
l1/l1_rules.json ADDED
@@ -0,0 +1,1052 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "ngram": "31 2025",
4
+ "class": "finance",
5
+ "count": 155
6
+ },
7
+ {
8
+ "ngram": "december 31 2025",
9
+ "class": "finance",
10
+ "count": 136
11
+ },
12
+ {
13
+ "ngram": "cash flows",
14
+ "class": "finance",
15
+ "count": 132
16
+ },
17
+ {
18
+ "ngram": "consolidated financial",
19
+ "class": "finance",
20
+ "count": 123
21
+ },
22
+ {
23
+ "ngram": "consolidated financial statements",
24
+ "class": "finance",
25
+ "count": 118
26
+ },
27
+ {
28
+ "ngram": "results of operations",
29
+ "class": "finance",
30
+ "count": 104
31
+ },
32
+ {
33
+ "ngram": "financial condition",
34
+ "class": "finance",
35
+ "count": 100
36
+ },
37
+ {
38
+ "ngram": "as of december",
39
+ "class": "finance",
40
+ "count": 97
41
+ },
42
+ {
43
+ "ngram": "of december 31",
44
+ "class": "finance",
45
+ "count": 91
46
+ },
47
+ {
48
+ "ngram": "ended december",
49
+ "class": "finance",
50
+ "count": 90
51
+ },
52
+ {
53
+ "ngram": "notes to",
54
+ "class": "finance",
55
+ "count": 88
56
+ },
57
+ {
58
+ "ngram": "ended december 31",
59
+ "class": "finance",
60
+ "count": 87
61
+ },
62
+ {
63
+ "ngram": "fair value",
64
+ "class": "finance",
65
+ "count": 80
66
+ },
67
+ {
68
+ "ngram": "vergabeunterlagen",
69
+ "class": "finance",
70
+ "count": 80
71
+ },
72
+ {
73
+ "ngram": "amortization",
74
+ "class": "finance",
75
+ "count": 79
76
+ },
77
+ {
78
+ "ngram": "bieter",
79
+ "class": "finance",
80
+ "count": 78
81
+ },
82
+ {
83
+ "ngram": "year ended",
84
+ "class": "finance",
85
+ "count": 76
86
+ },
87
+ {
88
+ "ngram": "abil",
89
+ "class": "finance",
90
+ "count": 75
91
+ },
92
+ {
93
+ "ngram": "tp abil",
94
+ "class": "finance",
95
+ "count": 75
96
+ },
97
+ {
98
+ "ngram": "form 10",
99
+ "class": "finance",
100
+ "count": 74
101
+ },
102
+ {
103
+ "ngram": "00 01",
104
+ "class": "finance",
105
+ "count": 71
106
+ },
107
+ {
108
+ "ngram": "consolidated balance",
109
+ "class": "finance",
110
+ "count": 70
111
+ },
112
+ {
113
+ "ngram": "and liabilities",
114
+ "class": "finance",
115
+ "count": 68
116
+ },
117
+ {
118
+ "ngram": "per share",
119
+ "class": "finance",
120
+ "count": 67
121
+ },
122
+ {
123
+ "ngram": "00 2024",
124
+ "class": "finance",
125
+ "count": 66
126
+ },
127
+ {
128
+ "ngram": "den vergabeunterlagen",
129
+ "class": "finance",
130
+ "count": 66
131
+ },
132
+ {
133
+ "ngram": "ef stand",
134
+ "class": "finance",
135
+ "count": 66
136
+ },
137
+ {
138
+ "ngram": "00 01 00",
139
+ "class": "finance",
140
+ "count": 65
141
+ },
142
+ {
143
+ "ngram": "fair value of",
144
+ "class": "finance",
145
+ "count": 65
146
+ },
147
+ {
148
+ "ngram": "restricted document",
149
+ "class": "finance",
150
+ "count": 65
151
+ },
152
+ {
153
+ "ngram": "biographical",
154
+ "class": "hr",
155
+ "count": 225
156
+ },
157
+ {
158
+ "ngram": "biology",
159
+ "class": "hr",
160
+ "count": 222
161
+ },
162
+ {
163
+ "ngram": "assistant professor",
164
+ "class": "hr",
165
+ "count": 218
166
+ },
167
+ {
168
+ "ngram": "biographical sketch",
169
+ "class": "hr",
170
+ "count": 212
171
+ },
172
+ {
173
+ "ngram": "professional experience",
174
+ "class": "hr",
175
+ "count": 205
176
+ },
177
+ {
178
+ "ngram": "postdoctoral",
179
+ "class": "hr",
180
+ "count": 190
181
+ },
182
+ {
183
+ "ngram": "vitae",
184
+ "class": "hr",
185
+ "count": 134
186
+ },
187
+ {
188
+ "ngram": "associate professor",
189
+ "class": "hr",
190
+ "count": 129
191
+ },
192
+ {
193
+ "ngram": "institution and",
194
+ "class": "hr",
195
+ "count": 127
196
+ },
197
+ {
198
+ "ngram": "fellowship",
199
+ "class": "hr",
200
+ "count": 126
201
+ },
202
+ {
203
+ "ngram": "photocopy",
204
+ "class": "hr",
205
+ "count": 126
206
+ },
207
+ {
208
+ "ngram": "two pages",
209
+ "class": "hr",
210
+ "count": 126
211
+ },
212
+ {
213
+ "ngram": "institution and location",
214
+ "class": "hr",
215
+ "count": 121
216
+ },
217
+ {
218
+ "ngram": "curriculum vitae",
219
+ "class": "hr",
220
+ "count": 120
221
+ },
222
+ {
223
+ "ngram": "and professional experience",
224
+ "class": "hr",
225
+ "count": 115
226
+ },
227
+ {
228
+ "ngram": "exceed two",
229
+ "class": "hr",
230
+ "count": 111
231
+ },
232
+ {
233
+ "ngram": "biographical sketch give",
234
+ "class": "hr",
235
+ "count": 110
236
+ },
237
+ {
238
+ "ngram": "sketch give",
239
+ "class": "hr",
240
+ "count": 110
241
+ },
242
+ {
243
+ "ngram": "exceed two pages",
244
+ "class": "hr",
245
+ "count": 105
246
+ },
247
+ {
248
+ "ngram": "research and professional",
249
+ "class": "hr",
250
+ "count": 102
251
+ },
252
+ {
253
+ "ngram": "sketch give the",
254
+ "class": "hr",
255
+ "count": 96
256
+ },
257
+ {
258
+ "ngram": "photocopy this",
259
+ "class": "hr",
260
+ "count": 92
261
+ },
262
+ {
263
+ "ngram": "each person",
264
+ "class": "hr",
265
+ "count": 90
266
+ },
267
+ {
268
+ "ngram": "instructor",
269
+ "class": "hr",
270
+ "count": 90
271
+ },
272
+ {
273
+ "ngram": "assistant professor of",
274
+ "class": "hr",
275
+ "count": 89
276
+ },
277
+ {
278
+ "ngram": "research associate",
279
+ "class": "hr",
280
+ "count": 88
281
+ },
282
+ {
283
+ "ngram": "not exceed two",
284
+ "class": "hr",
285
+ "count": 87
286
+ },
287
+ {
288
+ "ngram": "photocopy this page",
289
+ "class": "hr",
290
+ "count": 85
291
+ },
292
+ {
293
+ "ngram": "professor department",
294
+ "class": "hr",
295
+ "count": 85
296
+ },
297
+ {
298
+ "ngram": "membership on",
299
+ "class": "hr",
300
+ "count": 84
301
+ },
302
+ {
303
+ "ngram": "rfc",
304
+ "class": "internal_and_tech",
305
+ "count": 189
306
+ },
307
+ {
308
+ "ngram": "fiir",
309
+ "class": "internal_and_tech",
310
+ "count": 164
311
+ },
312
+ {
313
+ "ngram": "com rust",
314
+ "class": "internal_and_tech",
315
+ "count": 155
316
+ },
317
+ {
318
+ "ngram": "com rust lang",
319
+ "class": "internal_and_tech",
320
+ "count": 155
321
+ },
322
+ {
323
+ "ngram": "github com rust",
324
+ "class": "internal_and_tech",
325
+ "count": 155
326
+ },
327
+ {
328
+ "ngram": "rfcs",
329
+ "class": "internal_and_tech",
330
+ "count": 155
331
+ },
332
+ {
333
+ "ngram": "rust lang",
334
+ "class": "internal_and_tech",
335
+ "count": 155
336
+ },
337
+ {
338
+ "ngram": "lang rfcs",
339
+ "class": "internal_and_tech",
340
+ "count": 153
341
+ },
342
+ {
343
+ "ngram": "lang rfcs pull",
344
+ "class": "internal_and_tech",
345
+ "count": 153
346
+ },
347
+ {
348
+ "ngram": "rfc pr",
349
+ "class": "internal_and_tech",
350
+ "count": 153
351
+ },
352
+ {
353
+ "ngram": "rfcs pull",
354
+ "class": "internal_and_tech",
355
+ "count": 153
356
+ },
357
+ {
358
+ "ngram": "rust lang rfcs",
359
+ "class": "internal_and_tech",
360
+ "count": 153
361
+ },
362
+ {
363
+ "ngram": "drawbacks",
364
+ "class": "internal_and_tech",
365
+ "count": 147
366
+ },
367
+ {
368
+ "ngram": "unresolved",
369
+ "class": "internal_and_tech",
370
+ "count": 146
371
+ },
372
+ {
373
+ "ngram": "pr rust",
374
+ "class": "internal_and_tech",
375
+ "count": 145
376
+ },
377
+ {
378
+ "ngram": "pr rust lang",
379
+ "class": "internal_and_tech",
380
+ "count": 145
381
+ },
382
+ {
383
+ "ngram": "rfc pr rust",
384
+ "class": "internal_and_tech",
385
+ "count": 145
386
+ },
387
+ {
388
+ "ngram": "rust issue",
389
+ "class": "internal_and_tech",
390
+ "count": 140
391
+ },
392
+ {
393
+ "ngram": "unresolved questions",
394
+ "class": "internal_and_tech",
395
+ "count": 140
396
+ },
397
+ {
398
+ "ngram": "lang rust",
399
+ "class": "internal_and_tech",
400
+ "count": 139
401
+ },
402
+ {
403
+ "ngram": "rust lang rust",
404
+ "class": "internal_and_tech",
405
+ "count": 139
406
+ },
407
+ {
408
+ "ngram": "lang rust issues",
409
+ "class": "internal_and_tech",
410
+ "count": 137
411
+ },
412
+ {
413
+ "ngram": "rust issues",
414
+ "class": "internal_and_tech",
415
+ "count": 137
416
+ },
417
+ {
418
+ "ngram": "copyright this",
419
+ "class": "internal_and_tech",
420
+ "count": 134
421
+ },
422
+ {
423
+ "ngram": "copyright this document",
424
+ "class": "internal_and_tech",
425
+ "count": 133
426
+ },
427
+ {
428
+ "ngram": "placed in the",
429
+ "class": "internal_and_tech",
430
+ "count": 133
431
+ },
432
+ {
433
+ "ngram": "issue rust",
434
+ "class": "internal_and_tech",
435
+ "count": 131
436
+ },
437
+ {
438
+ "ngram": "issue rust lang",
439
+ "class": "internal_and_tech",
440
+ "count": 131
441
+ },
442
+ {
443
+ "ngram": "python org",
444
+ "class": "internal_and_tech",
445
+ "count": 125
446
+ },
447
+ {
448
+ "ngram": "iiber",
449
+ "class": "internal_and_tech",
450
+ "count": 124
451
+ },
452
+ {
453
+ "ngram": "regard to the",
454
+ "class": "legal",
455
+ "count": 270
456
+ },
457
+ {
458
+ "ngram": "done at",
459
+ "class": "legal",
460
+ "count": 266
461
+ },
462
+ {
463
+ "ngram": "having regard",
464
+ "class": "legal",
465
+ "count": 266
466
+ },
467
+ {
468
+ "ngram": "having regard to",
469
+ "class": "legal",
470
+ "count": 266
471
+ },
472
+ {
473
+ "ngram": "adopted this",
474
+ "class": "legal",
475
+ "count": 265
476
+ },
477
+ {
478
+ "ngram": "and in particular",
479
+ "class": "legal",
480
+ "count": 265
481
+ },
482
+ {
483
+ "ngram": "the treaty",
484
+ "class": "legal",
485
+ "count": 265
486
+ },
487
+ {
488
+ "ngram": "the treaty on",
489
+ "class": "legal",
490
+ "count": 265
491
+ },
492
+ {
493
+ "ngram": "treaty on",
494
+ "class": "legal",
495
+ "count": 265
496
+ },
497
+ {
498
+ "ngram": "to the treaty",
499
+ "class": "legal",
500
+ "count": 264
501
+ },
502
+ {
503
+ "ngram": "european union having",
504
+ "class": "legal",
505
+ "count": 258
506
+ },
507
+ {
508
+ "ngram": "union having",
509
+ "class": "legal",
510
+ "count": 258
511
+ },
512
+ {
513
+ "ngram": "union having regard",
514
+ "class": "legal",
515
+ "count": 258
516
+ },
517
+ {
518
+ "ngram": "has adopted",
519
+ "class": "legal",
520
+ "count": 254
521
+ },
522
+ {
523
+ "ngram": "gest\u00fctzt",
524
+ "class": "legal",
525
+ "count": 253
526
+ },
527
+ {
528
+ "ngram": "erlassen",
529
+ "class": "legal",
530
+ "count": 252
531
+ },
532
+ {
533
+ "ngram": "erw\u00e4gung",
534
+ "class": "legal",
535
+ "count": 252
536
+ },
537
+ {
538
+ "ngram": "has adopted this",
539
+ "class": "legal",
540
+ "count": 252
541
+ },
542
+ {
543
+ "ngram": "den vertrag",
544
+ "class": "legal",
545
+ "count": 251
546
+ },
547
+ {
548
+ "ngram": "gest\u00fctzt auf",
549
+ "class": "legal",
550
+ "count": 251
551
+ },
552
+ {
553
+ "ngram": "in erw\u00e4gung",
554
+ "class": "legal",
555
+ "count": 250
556
+ },
557
+ {
558
+ "ngram": "vertrag \u00fcber die",
559
+ "class": "legal",
560
+ "count": 249
561
+ },
562
+ {
563
+ "ngram": "erw\u00e4gung nachstehender",
564
+ "class": "legal",
565
+ "count": 248
566
+ },
567
+ {
568
+ "ngram": "erw\u00e4gung nachstehender gr\u00fcnde",
569
+ "class": "legal",
570
+ "count": 248
571
+ },
572
+ {
573
+ "ngram": "gest\u00fctzt auf den",
574
+ "class": "legal",
575
+ "count": 248
576
+ },
577
+ {
578
+ "ngram": "in erw\u00e4gung nachstehender",
579
+ "class": "legal",
580
+ "count": 248
581
+ },
582
+ {
583
+ "ngram": "nachstehender",
584
+ "class": "legal",
585
+ "count": 248
586
+ },
587
+ {
588
+ "ngram": "nachstehender gr\u00fcnde",
589
+ "class": "legal",
590
+ "count": 248
591
+ },
592
+ {
593
+ "ngram": "auf den vertrag",
594
+ "class": "legal",
595
+ "count": 247
596
+ },
597
+ {
598
+ "ngram": "den vertrag \u00fcber",
599
+ "class": "legal",
600
+ "count": 247
601
+ },
602
+ {
603
+ "ngram": "europ\u00e4ische kommission hat",
604
+ "class": "marketing",
605
+ "count": 83
606
+ },
607
+ {
608
+ "ngram": "management summary",
609
+ "class": "marketing",
610
+ "count": 70
611
+ },
612
+ {
613
+ "ngram": "preheader",
614
+ "class": "marketing",
615
+ "count": 68
616
+ },
617
+ {
618
+ "ngram": "kommission hat heute",
619
+ "class": "marketing",
620
+ "count": 65
621
+ },
622
+ {
623
+ "ngram": "pressekontakt",
624
+ "class": "marketing",
625
+ "count": 58
626
+ },
627
+ {
628
+ "ngram": "2026 die europ\u00e4ische",
629
+ "class": "marketing",
630
+ "count": 57
631
+ },
632
+ {
633
+ "ngram": "sald",
634
+ "class": "marketing",
635
+ "count": 52
636
+ },
637
+ {
638
+ "ngram": "2025 die europ\u00e4ische",
639
+ "class": "marketing",
640
+ "count": 50
641
+ },
642
+ {
643
+ "ngram": "mail presse",
644
+ "class": "marketing",
645
+ "count": 35
646
+ },
647
+ {
648
+ "ngram": "n\u00e4chster schritt",
649
+ "class": "marketing",
650
+ "count": 34
651
+ },
652
+ {
653
+ "ngram": "smoking is",
654
+ "class": "marketing",
655
+ "count": 34
656
+ },
657
+ {
658
+ "ngram": "problemraum",
659
+ "class": "marketing",
660
+ "count": 32
661
+ },
662
+ {
663
+ "ngram": "mitarbeitende pressekontakt",
664
+ "class": "marketing",
665
+ "count": 26
666
+ },
667
+ {
668
+ "ngram": "schluss mit",
669
+ "class": "marketing",
670
+ "count": 26
671
+ },
672
+ {
673
+ "ngram": "general warning",
674
+ "class": "marketing",
675
+ "count": 25
676
+ },
677
+ {
678
+ "ngram": "surgeon general warning",
679
+ "class": "marketing",
680
+ "count": 25
681
+ },
682
+ {
683
+ "ngram": "2025 die kommission",
684
+ "class": "marketing",
685
+ "count": 24
686
+ },
687
+ {
688
+ "ngram": "folie wie",
689
+ "class": "marketing",
690
+ "count": 24
691
+ },
692
+ {
693
+ "ngram": "the problem space",
694
+ "class": "marketing",
695
+ "count": 24
696
+ },
697
+ {
698
+ "ngram": "thelr",
699
+ "class": "marketing",
700
+ "count": 23
701
+ },
702
+ {
703
+ "ngram": "bacco",
704
+ "class": "marketing",
705
+ "count": 22
706
+ },
707
+ {
708
+ "ngram": "prozent weniger",
709
+ "class": "marketing",
710
+ "count": 22
711
+ },
712
+ {
713
+ "ngram": "sie erhalten diese",
714
+ "class": "marketing",
715
+ "count": 22
716
+ },
717
+ {
718
+ "ngram": "thet",
719
+ "class": "marketing",
720
+ "count": 22
721
+ },
722
+ {
723
+ "ngram": "today announced",
724
+ "class": "marketing",
725
+ "count": 22
726
+ },
727
+ {
728
+ "ngram": "ergebnisse nach",
729
+ "class": "marketing",
730
+ "count": 21
731
+ },
732
+ {
733
+ "ngram": "heute die",
734
+ "class": "marketing",
735
+ "count": 21
736
+ },
737
+ {
738
+ "ngram": "2026 management summary",
739
+ "class": "marketing",
740
+ "count": 19
741
+ },
742
+ {
743
+ "ngram": "for immediate release",
744
+ "class": "marketing",
745
+ "count": 19
746
+ },
747
+ {
748
+ "ngram": "immediate release",
749
+ "class": "marketing",
750
+ "count": 19
751
+ },
752
+ {
753
+ "ngram": "2006 cest",
754
+ "class": "other",
755
+ "count": 38
756
+ },
757
+ {
758
+ "ngram": "mai 2006 cest",
759
+ "class": "other",
760
+ "count": 19
761
+ },
762
+ {
763
+ "ngram": "fucking",
764
+ "class": "other",
765
+ "count": 17
766
+ },
767
+ {
768
+ "ngram": "w\u00fcrde gern",
769
+ "class": "other",
770
+ "count": 17
771
+ },
772
+ {
773
+ "ngram": "she doesn",
774
+ "class": "other",
775
+ "count": 14
776
+ },
777
+ {
778
+ "ngram": "2007 cest",
779
+ "class": "other",
780
+ "count": 13
781
+ },
782
+ {
783
+ "ngram": "amerikanischer",
784
+ "class": "other",
785
+ "count": 13
786
+ },
787
+ {
788
+ "ngram": "helfen eine",
789
+ "class": "other",
790
+ "count": 13
791
+ },
792
+ {
793
+ "ngram": "juden",
794
+ "class": "other",
795
+ "count": 13
796
+ },
797
+ {
798
+ "ngram": "mir helfen eine",
799
+ "class": "other",
800
+ "count": 13
801
+ },
802
+ {
803
+ "ngram": "m\u00e4r",
804
+ "class": "other",
805
+ "count": 13
806
+ },
807
+ {
808
+ "ngram": "rollenspiel",
809
+ "class": "other",
810
+ "count": 13
811
+ },
812
+ {
813
+ "ngram": "us amerikanischer",
814
+ "class": "other",
815
+ "count": 13
816
+ },
817
+ {
818
+ "ngram": "2006 cet",
819
+ "class": "other",
820
+ "count": 12
821
+ },
822
+ {
823
+ "ngram": "damit ich nicht",
824
+ "class": "other",
825
+ "count": 12
826
+ },
827
+ {
828
+ "ngram": "drau\u00dfen",
829
+ "class": "other",
830
+ "count": 12
831
+ },
832
+ {
833
+ "ngram": "endlich mal",
834
+ "class": "other",
835
+ "count": 12
836
+ },
837
+ {
838
+ "ngram": "ich w\u00fcrde gern",
839
+ "class": "other",
840
+ "count": 12
841
+ },
842
+ {
843
+ "ngram": "judenfeindlichkeit",
844
+ "class": "other",
845
+ "count": 12
846
+ },
847
+ {
848
+ "ngram": "mir ein paar",
849
+ "class": "other",
850
+ "count": 12
851
+ },
852
+ {
853
+ "ngram": "rezept",
854
+ "class": "other",
855
+ "count": 12
856
+ },
857
+ {
858
+ "ngram": "chemisches element",
859
+ "class": "other",
860
+ "count": 11
861
+ },
862
+ {
863
+ "ngram": "out of my",
864
+ "class": "other",
865
+ "count": 11
866
+ },
867
+ {
868
+ "ngram": "tourist",
869
+ "class": "other",
870
+ "count": 11
871
+ },
872
+ {
873
+ "ngram": "will einfach",
874
+ "class": "other",
875
+ "count": 11
876
+ },
877
+ {
878
+ "ngram": "2000 w\u00f6rter",
879
+ "class": "other",
880
+ "count": 10
881
+ },
882
+ {
883
+ "ngram": "chemisches element mit",
884
+ "class": "other",
885
+ "count": 10
886
+ },
887
+ {
888
+ "ngram": "der ordnungszahl",
889
+ "class": "other",
890
+ "count": 10
891
+ },
892
+ {
893
+ "ngram": "dr you",
894
+ "class": "other",
895
+ "count": 10
896
+ },
897
+ {
898
+ "ngram": "ein chemisches",
899
+ "class": "other",
900
+ "count": 10
901
+ },
902
+ {
903
+ "ngram": "checkreturnvalue",
904
+ "class": "source_code",
905
+ "count": 60
906
+ },
907
+ {
908
+ "ngram": "public final",
909
+ "class": "source_code",
910
+ "count": 60
911
+ },
912
+ {
913
+ "ngram": "schedulersupport",
914
+ "class": "source_code",
915
+ "count": 52
916
+ },
917
+ {
918
+ "ngram": "schedulersupport schedulersupport",
919
+ "class": "source_code",
920
+ "count": 52
921
+ },
922
+ {
923
+ "ngram": "checkreturnvalue schedulersupport",
924
+ "class": "source_code",
925
+ "count": 48
926
+ },
927
+ {
928
+ "ngram": "checkreturnvalue schedulersupport schedulersupport",
929
+ "class": "source_code",
930
+ "count": 48
931
+ },
932
+ {
933
+ "ngram": "apiversion",
934
+ "class": "source_code",
935
+ "count": 43
936
+ },
937
+ {
938
+ "ngram": "metadata name",
939
+ "class": "source_code",
940
+ "count": 42
941
+ },
942
+ {
943
+ "ngram": "schedulersupport none",
944
+ "class": "source_code",
945
+ "count": 42
946
+ },
947
+ {
948
+ "ngram": "schedulersupport schedulersupport none",
949
+ "class": "source_code",
950
+ "count": 42
951
+ },
952
+ {
953
+ "ngram": "schedulersupport none public",
954
+ "class": "source_code",
955
+ "count": 39
956
+ },
957
+ {
958
+ "ngram": "requirenonnull",
959
+ "class": "source_code",
960
+ "count": 38
961
+ },
962
+ {
963
+ "ngram": "objecthelper",
964
+ "class": "source_code",
965
+ "count": 36
966
+ },
967
+ {
968
+ "ngram": "objecthelper requirenonnull",
969
+ "class": "source_code",
970
+ "count": 36
971
+ },
972
+ {
973
+ "ngram": "sqlfluff",
974
+ "class": "source_code",
975
+ "count": 36
976
+ },
977
+ {
978
+ "ngram": "onassembly",
979
+ "class": "source_code",
980
+ "count": 35
981
+ },
982
+ {
983
+ "ngram": "return rxjavaplugins",
984
+ "class": "source_code",
985
+ "count": 35
986
+ },
987
+ {
988
+ "ngram": "return rxjavaplugins onassembly",
989
+ "class": "source_code",
990
+ "count": 35
991
+ },
992
+ {
993
+ "ngram": "rxjavaplugins",
994
+ "class": "source_code",
995
+ "count": 35
996
+ },
997
+ {
998
+ "ngram": "rxjavaplugins onassembly",
999
+ "class": "source_code",
1000
+ "count": 35
1001
+ },
1002
+ {
1003
+ "ngram": "license identifier",
1004
+ "class": "source_code",
1005
+ "count": 34
1006
+ },
1007
+ {
1008
+ "ngram": "onassembly new",
1009
+ "class": "source_code",
1010
+ "count": 34
1011
+ },
1012
+ {
1013
+ "ngram": "rxjavaplugins onassembly new",
1014
+ "class": "source_code",
1015
+ "count": 34
1016
+ },
1017
+ {
1018
+ "ngram": "spdx",
1019
+ "class": "source_code",
1020
+ "count": 34
1021
+ },
1022
+ {
1023
+ "ngram": "spdx license",
1024
+ "class": "source_code",
1025
+ "count": 34
1026
+ },
1027
+ {
1028
+ "ngram": "spdx license identifier",
1029
+ "class": "source_code",
1030
+ "count": 34
1031
+ },
1032
+ {
1033
+ "ngram": "v1 kind",
1034
+ "class": "source_code",
1035
+ "count": 33
1036
+ },
1037
+ {
1038
+ "ngram": "_hash",
1039
+ "class": "source_code",
1040
+ "count": 32
1041
+ },
1042
+ {
1043
+ "ngram": "adding or",
1044
+ "class": "source_code",
1045
+ "count": 32
1046
+ },
1047
+ {
1048
+ "ngram": "adding or altering",
1049
+ "class": "source_code",
1050
+ "count": 32
1051
+ }
1052
+ ]
l2/l2_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3197704a67e306fd33542e0e993273000876bff2c80b89eda1e9f8b35e2dc181
3
+ size 133907775