DaniilAlpha commited on
Commit
02b77d0
·
1 Parent(s): 6a34faa

Create data_config.json

Browse files
models/multi-qa-distilbert-cos-v1/data_config.json ADDED
@@ -0,0 +1,942 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "name": "stackexchange_title_body/skeptics.stackexchange.com.jsonl.gz",
4
+ "lines": 10009,
5
+ "weight": 3
6
+ },
7
+ {
8
+ "name": "stackexchange_Title_Answer/islam.stackexchange.com.jsonl.gz",
9
+ "lines": 10052,
10
+ "weight": 3
11
+ },
12
+ {
13
+ "name": "stackexchange_Title_Answer/anime.stackexchange.com.jsonl.gz",
14
+ "lines": 10131,
15
+ "weight": 3
16
+ },
17
+ {
18
+ "name": "stackexchange_title_body/writers.stackexchange.com.jsonl.gz",
19
+ "lines": 10157,
20
+ "weight": 3
21
+ },
22
+ {
23
+ "name": "stackexchange_title_body/astronomy.stackexchange.com.jsonl.gz",
24
+ "lines": 10462,
25
+ "weight": 3
26
+ },
27
+ {
28
+ "name": "stackexchange_title_body/vi.stackexchange.com.jsonl.gz",
29
+ "lines": 10551,
30
+ "weight": 3
31
+ },
32
+ {
33
+ "name": "stackexchange_Title_Answer/french.stackexchange.com.jsonl.gz",
34
+ "lines": 10578,
35
+ "weight": 3
36
+ },
37
+ {
38
+ "name": "stackexchange_title_body/cstheory.stackexchange.com.jsonl.gz",
39
+ "lines": 10642,
40
+ "weight": 3
41
+ },
42
+ {
43
+ "name": "stackexchange_Title_Answer/civicrm.stackexchange.com.jsonl.gz",
44
+ "lines": 10648,
45
+ "weight": 3
46
+ },
47
+ {
48
+ "name": "stackexchange_Title_Answer/expressionengine.stackexchange.com.jsonl.gz",
49
+ "lines": 10742,
50
+ "weight": 3
51
+ },
52
+ {
53
+ "name": "stackexchange_title_body/engineering.stackexchange.com.jsonl.gz",
54
+ "lines": 10753,
55
+ "weight": 3
56
+ },
57
+ {
58
+ "name": "stackexchange_Title_Answer/history.stackexchange.com.jsonl.gz",
59
+ "lines": 10766,
60
+ "weight": 3
61
+ },
62
+ {
63
+ "name": "stackexchange_title_body/french.stackexchange.com.jsonl.gz",
64
+ "lines": 10794,
65
+ "weight": 3
66
+ },
67
+ {
68
+ "name": "stackexchange_Title_Answer/politics.stackexchange.com.jsonl.gz",
69
+ "lines": 11047,
70
+ "weight": 3
71
+ },
72
+ {
73
+ "name": "stackexchange_title_body/economics.stackexchange.com.jsonl.gz",
74
+ "lines": 11115,
75
+ "weight": 3
76
+ },
77
+ {
78
+ "name": "stackexchange_Title_Answer/craftcms.stackexchange.com.jsonl.gz",
79
+ "lines": 11236,
80
+ "weight": 3
81
+ },
82
+ {
83
+ "name": "stackexchange_title_body/anime.stackexchange.com.jsonl.gz",
84
+ "lines": 11444,
85
+ "weight": 3
86
+ },
87
+ {
88
+ "name": "stackexchange_Title_Answer/christianity.stackexchange.com.jsonl.gz",
89
+ "lines": 11498,
90
+ "weight": 3
91
+ },
92
+ {
93
+ "name": "stackexchange_Title_Answer/softwarerecs.stackexchange.com.jsonl.gz",
94
+ "lines": 11761,
95
+ "weight": 3
96
+ },
97
+ {
98
+ "name": "stackexchange_Title_Answer/boardgames.stackexchange.com.jsonl.gz",
99
+ "lines": 11805,
100
+ "weight": 3
101
+ },
102
+ {
103
+ "name": "stackexchange_title_body/islam.stackexchange.com.jsonl.gz",
104
+ "lines": 11853,
105
+ "weight": 3
106
+ },
107
+ {
108
+ "name": "stackexchange_title_body/expressionengine.stackexchange.com.jsonl.gz",
109
+ "lines": 11866,
110
+ "weight": 3
111
+ },
112
+ {
113
+ "name": "stackexchange_title_body/politics.stackexchange.com.jsonl.gz",
114
+ "lines": 11894,
115
+ "weight": 3
116
+ },
117
+ {
118
+ "name": "stackexchange_title_body/history.stackexchange.com.jsonl.gz",
119
+ "lines": 12021,
120
+ "weight": 3
121
+ },
122
+ {
123
+ "name": "stackexchange_title_body/christianity.stackexchange.com.jsonl.gz",
124
+ "lines": 12108,
125
+ "weight": 3
126
+ },
127
+ {
128
+ "name": "stackexchange_title_body/boardgames.stackexchange.com.jsonl.gz",
129
+ "lines": 12149,
130
+ "weight": 3
131
+ },
132
+ {
133
+ "name": "stackexchange_title_body/civicrm.stackexchange.com.jsonl.gz",
134
+ "lines": 12543,
135
+ "weight": 3
136
+ },
137
+ {
138
+ "name": "stackexchange_title_body/craftcms.stackexchange.com.jsonl.gz",
139
+ "lines": 12574,
140
+ "weight": 3
141
+ },
142
+ {
143
+ "name": "stackexchange_Title_Answer/networkengineering.stackexchange.com.jsonl.gz",
144
+ "lines": 12590,
145
+ "weight": 3
146
+ },
147
+ {
148
+ "name": "stackexchange_Title_Answer/space.stackexchange.com.jsonl.gz",
149
+ "lines": 12893,
150
+ "weight": 3
151
+ },
152
+ {
153
+ "name": "stackexchange_Title_Answer/quant.stackexchange.com.jsonl.gz",
154
+ "lines": 12933,
155
+ "weight": 3
156
+ },
157
+ {
158
+ "name": "stackexchange_Title_Answer/philosophy.stackexchange.com.jsonl.gz",
159
+ "lines": 13114,
160
+ "weight": 3
161
+ },
162
+ {
163
+ "name": "stackexchange_Title_Answer/gardening.stackexchange.com.jsonl.gz",
164
+ "lines": 13246,
165
+ "weight": 3
166
+ },
167
+ {
168
+ "name": "stackexchange_title_body/hinduism.stackexchange.com.jsonl.gz",
169
+ "lines": 13450,
170
+ "weight": 4
171
+ },
172
+ {
173
+ "name": "stackexchange_title_body/networkengineering.stackexchange.com.jsonl.gz",
174
+ "lines": 13454,
175
+ "weight": 4
176
+ },
177
+ {
178
+ "name": "stackexchange_Title_Answer/german.stackexchange.com.jsonl.gz",
179
+ "lines": 13733,
180
+ "weight": 4
181
+ },
182
+ {
183
+ "name": "stackexchange_title_body/german.stackexchange.com.jsonl.gz",
184
+ "lines": 13950,
185
+ "weight": 4
186
+ },
187
+ {
188
+ "name": "stackexchange_title_body/philosophy.stackexchange.com.jsonl.gz",
189
+ "lines": 14829,
190
+ "weight": 4
191
+ },
192
+ {
193
+ "name": "stackexchange_title_body/gardening.stackexchange.com.jsonl.gz",
194
+ "lines": 15136,
195
+ "weight": 4
196
+ },
197
+ {
198
+ "name": "stackexchange_title_body/space.stackexchange.com.jsonl.gz",
199
+ "lines": 15142,
200
+ "weight": 4
201
+ },
202
+ {
203
+ "name": "stackexchange_Title_Answer/bicycles.stackexchange.com.jsonl.gz",
204
+ "lines": 15708,
205
+ "weight": 4
206
+ },
207
+ {
208
+ "name": "stackexchange_Title_Answer/law.stackexchange.com.jsonl.gz",
209
+ "lines": 16133,
210
+ "weight": 4
211
+ },
212
+ {
213
+ "name": "stackexchange_Title_Answer/arduino.stackexchange.com.jsonl.gz",
214
+ "lines": 16281,
215
+ "weight": 4
216
+ },
217
+ {
218
+ "name": "stackexchange_title_body/bicycles.stackexchange.com.jsonl.gz",
219
+ "lines": 16353,
220
+ "weight": 4
221
+ },
222
+ {
223
+ "name": "stackexchange_Title_Answer/emacs.stackexchange.com.jsonl.gz",
224
+ "lines": 16830,
225
+ "weight": 4
226
+ },
227
+ {
228
+ "name": "stackexchange_title_body/quant.stackexchange.com.jsonl.gz",
229
+ "lines": 17261,
230
+ "weight": 4
231
+ },
232
+ {
233
+ "name": "stackexchange_Title_Answer/dsp.stackexchange.com.jsonl.gz",
234
+ "lines": 17430,
235
+ "weight": 4
236
+ },
237
+ {
238
+ "name": "stackexchange_Title_Answer/puzzling.stackexchange.com.jsonl.gz",
239
+ "lines": 17448,
240
+ "weight": 4
241
+ },
242
+ {
243
+ "name": "stackexchange_title_body/puzzling.stackexchange.com.jsonl.gz",
244
+ "lines": 17851,
245
+ "weight": 5
246
+ },
247
+ {
248
+ "name": "stackexchange_title_body/law.stackexchange.com.jsonl.gz",
249
+ "lines": 17941,
250
+ "weight": 5
251
+ },
252
+ {
253
+ "name": "stackexchange_Title_Answer/movies.stackexchange.com.jsonl.gz",
254
+ "lines": 18243,
255
+ "weight": 5
256
+ },
257
+ {
258
+ "name": "stackexchange_Title_Answer/mechanics.stackexchange.com.jsonl.gz",
259
+ "lines": 18613,
260
+ "weight": 5
261
+ },
262
+ {
263
+ "name": "stackexchange_Title_Answer/aviation.stackexchange.com.jsonl.gz",
264
+ "lines": 18755,
265
+ "weight": 5
266
+ },
267
+ {
268
+ "name": "stackexchange_Title_Answer/biology.stackexchange.com.jsonl.gz",
269
+ "lines": 19277,
270
+ "weight": 5
271
+ },
272
+ {
273
+ "name": "stackexchange_Title_Answer/crypto.stackexchange.com.jsonl.gz",
274
+ "lines": 19404,
275
+ "weight": 5
276
+ },
277
+ {
278
+ "name": "stackexchange_title_body/arduino.stackexchange.com.jsonl.gz",
279
+ "lines": 19553,
280
+ "weight": 5
281
+ },
282
+ {
283
+ "name": "stackexchange_Title_Answer/music.stackexchange.com.jsonl.gz",
284
+ "lines": 19936,
285
+ "weight": 5
286
+ },
287
+ {
288
+ "name": "stackexchange_title_body/aviation.stackexchange.com.jsonl.gz",
289
+ "lines": 20139,
290
+ "weight": 5
291
+ },
292
+ {
293
+ "name": "stackexchange_title_body/softwarerecs.stackexchange.com.jsonl.gz",
294
+ "lines": 20142,
295
+ "weight": 5
296
+ },
297
+ {
298
+ "name": "stackexchange_title_body/movies.stackexchange.com.jsonl.gz",
299
+ "lines": 20181,
300
+ "weight": 5
301
+ },
302
+ {
303
+ "name": "stackexchange_Title_Answer/datascience.stackexchange.com.jsonl.gz",
304
+ "lines": 20503,
305
+ "weight": 5
306
+ },
307
+ {
308
+ "name": "stackexchange_title_body/music.stackexchange.com.jsonl.gz",
309
+ "lines": 20636,
310
+ "weight": 5
311
+ },
312
+ {
313
+ "name": "stackexchange_Title_Answer/japanese.stackexchange.com.jsonl.gz",
314
+ "lines": 20948,
315
+ "weight": 5
316
+ },
317
+ {
318
+ "name": "stackexchange_title_body/emacs.stackexchange.com.jsonl.gz",
319
+ "lines": 21055,
320
+ "weight": 5
321
+ },
322
+ {
323
+ "name": "stackexchange_title_body/dsp.stackexchange.com.jsonl.gz",
324
+ "lines": 21252,
325
+ "weight": 5
326
+ },
327
+ {
328
+ "name": "stackexchange_title_body/japanese.stackexchange.com.jsonl.gz",
329
+ "lines": 22056,
330
+ "weight": 5
331
+ },
332
+ {
333
+ "name": "stackexchange_Title_Answer/bitcoin.stackexchange.com.jsonl.gz",
334
+ "lines": 22474,
335
+ "weight": 6
336
+ },
337
+ {
338
+ "name": "stackexchange_Title_Answer/cooking.stackexchange.com.jsonl.gz",
339
+ "lines": 22641,
340
+ "weight": 6
341
+ },
342
+ {
343
+ "name": "stackexchange_title_body/mechanics.stackexchange.com.jsonl.gz",
344
+ "lines": 22868,
345
+ "weight": 6
346
+ },
347
+ {
348
+ "name": "stackexchange_Title_Answer/photo.stackexchange.com.jsonl.gz",
349
+ "lines": 23204,
350
+ "weight": 6
351
+ },
352
+ {
353
+ "name": "stackexchange_title_body/crypto.stackexchange.com.jsonl.gz",
354
+ "lines": 23231,
355
+ "weight": 6
356
+ },
357
+ {
358
+ "name": "stackexchange_title_body/cooking.stackexchange.com.jsonl.gz",
359
+ "lines": 23705,
360
+ "weight": 6
361
+ },
362
+ {
363
+ "name": "stackexchange_title_body/photo.stackexchange.com.jsonl.gz",
364
+ "lines": 23753,
365
+ "weight": 6
366
+ },
367
+ {
368
+ "name": "stackexchange_Title_Answer/workplace.stackexchange.com.jsonl.gz",
369
+ "lines": 24012,
370
+ "weight": 6
371
+ },
372
+ {
373
+ "name": "stackexchange_Title_Answer/meta.stackoverflow.com.jsonl.gz",
374
+ "lines": 24044,
375
+ "weight": 6
376
+ },
377
+ {
378
+ "name": "stackexchange_Title_Answer/raspberrypi.stackexchange.com.jsonl.gz",
379
+ "lines": 24143,
380
+ "weight": 6
381
+ },
382
+ {
383
+ "name": "stackexchange_title_body/workplace.stackexchange.com.jsonl.gz",
384
+ "lines": 24189,
385
+ "weight": 6
386
+ },
387
+ {
388
+ "name": "stackexchange_title_body/biology.stackexchange.com.jsonl.gz",
389
+ "lines": 24447,
390
+ "weight": 6
391
+ },
392
+ {
393
+ "name": "stackexchange_Title_Answer/webapps.stackexchange.com.jsonl.gz",
394
+ "lines": 24867,
395
+ "weight": 6
396
+ },
397
+ {
398
+ "name": "stackexchange_title_body/bitcoin.stackexchange.com.jsonl.gz",
399
+ "lines": 25374,
400
+ "weight": 6
401
+ },
402
+ {
403
+ "name": "stackexchange_Title_Answer/judaism.stackexchange.com.jsonl.gz",
404
+ "lines": 26085,
405
+ "weight": 6
406
+ },
407
+ {
408
+ "name": "stackexchange_Title_Answer/ethereum.stackexchange.com.jsonl.gz",
409
+ "lines": 26124,
410
+ "weight": 6
411
+ },
412
+ {
413
+ "name": "stackexchange_Title_Answer/worldbuilding.stackexchange.com.jsonl.gz",
414
+ "lines": 26210,
415
+ "weight": 6
416
+ },
417
+ {
418
+ "name": "stackexchange_title_body/worldbuilding.stackexchange.com.jsonl.gz",
419
+ "lines": 26763,
420
+ "weight": 7
421
+ },
422
+ {
423
+ "name": "stackexchange_Title_Answer/chemistry.stackexchange.com.jsonl.gz",
424
+ "lines": 27061,
425
+ "weight": 7
426
+ },
427
+ {
428
+ "name": "stackexchange_title_body/datascience.stackexchange.com.jsonl.gz",
429
+ "lines": 27397,
430
+ "weight": 7
431
+ },
432
+ {
433
+ "name": "stackexchange_Title_Answer/graphicdesign.stackexchange.com.jsonl.gz",
434
+ "lines": 28083,
435
+ "weight": 7
436
+ },
437
+ {
438
+ "name": "stackexchange_Title_Answer/ux.stackexchange.com.jsonl.gz",
439
+ "lines": 28901,
440
+ "weight": 7
441
+ },
442
+ {
443
+ "name": "stackexchange_title_body/ux.stackexchange.com.jsonl.gz",
444
+ "lines": 29403,
445
+ "weight": 7
446
+ },
447
+ {
448
+ "name": "stackexchange_Title_Answer/money.stackexchange.com.jsonl.gz",
449
+ "lines": 29404,
450
+ "weight": 7
451
+ },
452
+ {
453
+ "name": "stackexchange_title_body/webapps.stackexchange.com.jsonl.gz",
454
+ "lines": 29697,
455
+ "weight": 7
456
+ },
457
+ {
458
+ "name": "stackexchange_Title_Answer/cs.stackexchange.com.jsonl.gz",
459
+ "lines": 30010,
460
+ "weight": 7
461
+ },
462
+ {
463
+ "name": "stackexchange_title_body/graphicdesign.stackexchange.com.jsonl.gz",
464
+ "lines": 30233,
465
+ "weight": 7
466
+ },
467
+ {
468
+ "name": "stackexchange_Title_Answer/webmasters.stackexchange.com.jsonl.gz",
469
+ "lines": 30370,
470
+ "weight": 7
471
+ },
472
+ {
473
+ "name": "stackexchange_title_body/raspberrypi.stackexchange.com.jsonl.gz",
474
+ "lines": 30625,
475
+ "weight": 7
476
+ },
477
+ {
478
+ "name": "stackexchange_title_body/money.stackexchange.com.jsonl.gz",
479
+ "lines": 32021,
480
+ "weight": 8
481
+ },
482
+ {
483
+ "name": "stackexchange_title_body/judaism.stackexchange.com.jsonl.gz",
484
+ "lines": 32028,
485
+ "weight": 8
486
+ },
487
+ {
488
+ "name": "stackexchange_Title_Answer/academia.stackexchange.com.jsonl.gz",
489
+ "lines": 32137,
490
+ "weight": 8
491
+ },
492
+ {
493
+ "name": "stackexchange_title_body/ethereum.stackexchange.com.jsonl.gz",
494
+ "lines": 32760,
495
+ "weight": 8
496
+ },
497
+ {
498
+ "name": "stackexchange_title_body/academia.stackexchange.com.jsonl.gz",
499
+ "lines": 34331,
500
+ "weight": 8
501
+ },
502
+ {
503
+ "name": "stackexchange_title_body/chemistry.stackexchange.com.jsonl.gz",
504
+ "lines": 34506,
505
+ "weight": 8
506
+ },
507
+ {
508
+ "name": "stackexchange_title_body/webmasters.stackexchange.com.jsonl.gz",
509
+ "lines": 34559,
510
+ "weight": 8
511
+ },
512
+ {
513
+ "name": "stackexchange_title_body/meta.stackoverflow.com.jsonl.gz",
514
+ "lines": 36456,
515
+ "weight": 9
516
+ },
517
+ {
518
+ "name": "stackexchange_Title_Answer/travel.stackexchange.com.jsonl.gz",
519
+ "lines": 36533,
520
+ "weight": 9
521
+ },
522
+ {
523
+ "name": "stackexchange_Title_Answer/android.stackexchange.com.jsonl.gz",
524
+ "lines": 38077,
525
+ "weight": 9
526
+ },
527
+ {
528
+ "name": "stackexchange_title_body/cs.stackexchange.com.jsonl.gz",
529
+ "lines": 38314,
530
+ "weight": 9
531
+ },
532
+ {
533
+ "name": "stackexchange_Title_Answer/gamedev.stackexchange.com.jsonl.gz",
534
+ "lines": 40154,
535
+ "weight": 10
536
+ },
537
+ {
538
+ "name": "stackexchange_Title_Answer/rpg.stackexchange.com.jsonl.gz",
539
+ "lines": 40435,
540
+ "weight": 10
541
+ },
542
+ {
543
+ "name": "stackexchange_title_body/travel.stackexchange.com.jsonl.gz",
544
+ "lines": 41227,
545
+ "weight": 10
546
+ },
547
+ {
548
+ "name": "stackexchange_Title_Answer/codereview.stackexchange.com.jsonl.gz",
549
+ "lines": 41748,
550
+ "weight": 10
551
+ },
552
+ {
553
+ "name": "stackexchange_title_body/rpg.stackexchange.com.jsonl.gz",
554
+ "lines": 42303,
555
+ "weight": 10
556
+ },
557
+ {
558
+ "name": "stackexchange_title_body/codereview.stackexchange.com.jsonl.gz",
559
+ "lines": 45765,
560
+ "weight": 11
561
+ },
562
+ {
563
+ "name": "stackexchange_title_body/gamedev.stackexchange.com.jsonl.gz",
564
+ "lines": 46485,
565
+ "weight": 11
566
+ },
567
+ {
568
+ "name": "stackexchange_Title_Answer/softwareengineering.stackexchange.com.jsonl.gz",
569
+ "lines": 51326,
570
+ "weight": 12
571
+ },
572
+ {
573
+ "name": "stackexchange_Title_Answer/security.stackexchange.com.jsonl.gz",
574
+ "lines": 51355,
575
+ "weight": 12
576
+ },
577
+ {
578
+ "name": "stackexchange_title_body/android.stackexchange.com.jsonl.gz",
579
+ "lines": 51608,
580
+ "weight": 12
581
+ },
582
+ {
583
+ "name": "stackexchange_Title_Answer/diy.stackexchange.com.jsonl.gz",
584
+ "lines": 52896,
585
+ "weight": 12
586
+ },
587
+ {
588
+ "name": "stackexchange_title_body/softwareengineering.stackexchange.com.jsonl.gz",
589
+ "lines": 53942,
590
+ "weight": 13
591
+ },
592
+ {
593
+ "name": "stackexchange_Title_Answer/blender.stackexchange.com.jsonl.gz",
594
+ "lines": 54153,
595
+ "weight": 13
596
+ },
597
+ {
598
+ "name": "stackexchange_Title_Answer/scifi.stackexchange.com.jsonl.gz",
599
+ "lines": 54805,
600
+ "weight": 13
601
+ },
602
+ {
603
+ "name": "stackexchange_title_body/security.stackexchange.com.jsonl.gz",
604
+ "lines": 58000,
605
+ "weight": 14
606
+ },
607
+ {
608
+ "name": "stackexchange_Title_Answer/mathematica.stackexchange.com.jsonl.gz",
609
+ "lines": 59895,
610
+ "weight": 14
611
+ },
612
+ {
613
+ "name": "stackexchange_title_body/diy.stackexchange.com.jsonl.gz",
614
+ "lines": 60083,
615
+ "weight": 14
616
+ },
617
+ {
618
+ "name": "stackexchange_Title_Answer/meta.stackexchange.com.jsonl.gz",
619
+ "lines": 60744,
620
+ "weight": 14
621
+ },
622
+ {
623
+ "name": "stackexchange_title_body/scifi.stackexchange.com.jsonl.gz",
624
+ "lines": 61528,
625
+ "weight": 14
626
+ },
627
+ {
628
+ "name": "stackexchange_Title_Answer/drupal.stackexchange.com.jsonl.gz",
629
+ "lines": 67817,
630
+ "weight": 16
631
+ },
632
+ {
633
+ "name": "stackexchange_Title_Answer/dba.stackexchange.com.jsonl.gz",
634
+ "lines": 71449,
635
+ "weight": 17
636
+ },
637
+ {
638
+ "name": "stackexchange_title_body/mathematica.stackexchange.com.jsonl.gz",
639
+ "lines": 73131,
640
+ "weight": 17
641
+ },
642
+ {
643
+ "name": "stackexchange_Title_Answer/ell.stackexchange.com.jsonl.gz",
644
+ "lines": 77892,
645
+ "weight": 18
646
+ },
647
+ {
648
+ "name": "stackexchange_Title_Answer/magento.stackexchange.com.jsonl.gz",
649
+ "lines": 79241,
650
+ "weight": 18
651
+ },
652
+ {
653
+ "name": "stackexchange_title_body/drupal.stackexchange.com.jsonl.gz",
654
+ "lines": 79717,
655
+ "weight": 18
656
+ },
657
+ {
658
+ "name": "stackexchange_Title_Answer/sharepoint.stackexchange.com.jsonl.gz",
659
+ "lines": 80420,
660
+ "weight": 19
661
+ },
662
+ {
663
+ "name": "stackexchange_title_body/blender.stackexchange.com.jsonl.gz",
664
+ "lines": 80766,
665
+ "weight": 19
666
+ },
667
+ {
668
+ "name": "stackexchange_title_body/dba.stackexchange.com.jsonl.gz",
669
+ "lines": 81871,
670
+ "weight": 19
671
+ },
672
+ {
673
+ "name": "stackexchange_Title_Answer/gaming.stackexchange.com.jsonl.gz",
674
+ "lines": 82887,
675
+ "weight": 19
676
+ },
677
+ {
678
+ "name": "stackexchange_title_body/ell.stackexchange.com.jsonl.gz",
679
+ "lines": 83271,
680
+ "weight": 19
681
+ },
682
+ {
683
+ "name": "stackexchange_title_body/meta.stackexchange.com.jsonl.gz",
684
+ "lines": 83510,
685
+ "weight": 19
686
+ },
687
+ {
688
+ "name": "stackexchange_Title_Answer/wordpress.stackexchange.com.jsonl.gz",
689
+ "lines": 83621,
690
+ "weight": 19
691
+ },
692
+ {
693
+ "name": "stackexchange_Title_Answer/mathoverflow.net.jsonl.gz",
694
+ "lines": 85289,
695
+ "weight": 20
696
+ },
697
+ {
698
+ "name": "stackexchange_Title_Answer/salesforce.stackexchange.com.jsonl.gz",
699
+ "lines": 87272,
700
+ "weight": 20
701
+ },
702
+ {
703
+ "name": "stackexchange_title_body/gaming.stackexchange.com.jsonl.gz",
704
+ "lines": 88912,
705
+ "weight": 21
706
+ },
707
+ {
708
+ "name": "stackexchange_Title_Answer/apple.stackexchange.com.jsonl.gz",
709
+ "lines": 92487,
710
+ "weight": 21
711
+ },
712
+ {
713
+ "name": "stackexchange_title_body/sharepoint.stackexchange.com.jsonl.gz",
714
+ "lines": 94011,
715
+ "weight": 22
716
+ },
717
+ {
718
+ "name": "stackexchange_title_body/magento.stackexchange.com.jsonl.gz",
719
+ "lines": 99991,
720
+ "weight": 23
721
+ },
722
+ {
723
+ "name": "stackexchange_Title_Answer/gis.stackexchange.com.jsonl.gz",
724
+ "lines": 100254,
725
+ "weight": 23
726
+ },
727
+ {
728
+ "name": "stackexchange_title_body/wordpress.stackexchange.com.jsonl.gz",
729
+ "lines": 100474,
730
+ "weight": 23
731
+ },
732
+ {
733
+ "name": "stackexchange_Title_Answer/english.stackexchange.com.jsonl.gz",
734
+ "lines": 100640,
735
+ "weight": 23
736
+ },
737
+ {
738
+ "name": "stackexchange_title_body/salesforce.stackexchange.com.jsonl.gz",
739
+ "lines": 105260,
740
+ "weight": 24
741
+ },
742
+ {
743
+ "name": "stackexchange_title_body/english.stackexchange.com.jsonl.gz",
744
+ "lines": 109522,
745
+ "weight": 25
746
+ },
747
+ {
748
+ "name": "stackexchange_title_body/apple.stackexchange.com.jsonl.gz",
749
+ "lines": 110622,
750
+ "weight": 25
751
+ },
752
+ {
753
+ "name": "stackexchange_Title_Answer/stats.stackexchange.com.jsonl.gz",
754
+ "lines": 115679,
755
+ "weight": 27
756
+ },
757
+ {
758
+ "name": "stackexchange_title_body/mathoverflow.net.jsonl.gz",
759
+ "lines": 120851,
760
+ "weight": 28
761
+ },
762
+ {
763
+ "name": "stackexchange_Title_Answer/electronics.stackexchange.com.jsonl.gz",
764
+ "lines": 129494,
765
+ "weight": 30
766
+ },
767
+ {
768
+ "name": "stackexchange_title_body/gis.stackexchange.com.jsonl.gz",
769
+ "lines": 131000,
770
+ "weight": 30
771
+ },
772
+ {
773
+ "name": "stackexchange_Title_Answer/physics.stackexchange.com.jsonl.gz",
774
+ "lines": 141230,
775
+ "weight": 32
776
+ },
777
+ {
778
+ "name": "stackexchange_title_body/electronics.stackexchange.com.jsonl.gz",
779
+ "lines": 143582,
780
+ "weight": 33
781
+ },
782
+ {
783
+ "name": "TriviaQA_pairs.jsonl.gz",
784
+ "lines": 73346,
785
+ "weight": 34
786
+ },
787
+ {
788
+ "name": "stackexchange_Title_Answer/unix.stackexchange.com.jsonl.gz",
789
+ "lines": 155414,
790
+ "weight": 36
791
+ },
792
+ {
793
+ "name": "stackexchange_Title_Answer/tex.stackexchange.com.jsonl.gz",
794
+ "lines": 171628,
795
+ "weight": 39
796
+ },
797
+ {
798
+ "name": "squad_pairs.jsonl.gz",
799
+ "lines": 87599,
800
+ "weight": 40
801
+ },
802
+ {
803
+ "name": "stackexchange_title_body/physics.stackexchange.com.jsonl.gz",
804
+ "lines": 173307,
805
+ "weight": 40
806
+ },
807
+ {
808
+ "name": "stackexchange_title_body/stats.stackexchange.com.jsonl.gz",
809
+ "lines": 173466,
810
+ "weight": 40
811
+ },
812
+ {
813
+ "name": "stackexchange_title_body/unix.stackexchange.com.jsonl.gz",
814
+ "lines": 185997,
815
+ "weight": 42
816
+ },
817
+ {
818
+ "name": "NQ-train_pairs.jsonl.gz",
819
+ "lines": 100231,
820
+ "weight": 46
821
+ },
822
+ {
823
+ "name": "stackexchange_title_body/tex.stackexchange.com.jsonl.gz",
824
+ "lines": 202954,
825
+ "weight": 46
826
+ },
827
+ {
828
+ "name": "quora_duplicates_triplets.jsonl.gz",
829
+ "lines": 103663,
830
+ "weight": 47
831
+ },
832
+ {
833
+ "name": "stackexchange_Title_Answer/serverfault.com.jsonl.gz",
834
+ "lines": 238507,
835
+ "weight": 54
836
+ },
837
+ {
838
+ "name": "stackexchange_Title_Answer/askubuntu.com.jsonl.gz",
839
+ "lines": 267135,
840
+ "weight": 61
841
+ },
842
+ {
843
+ "name": "stackexchange_title_body/serverfault.com.jsonl.gz",
844
+ "lines": 270904,
845
+ "weight": 62
846
+ },
847
+ {
848
+ "name": "stackexchange_duplicate_questions_title_title.jsonl.gz",
849
+ "lines": 304525,
850
+ "weight": 69
851
+ },
852
+ {
853
+ "name": "stackexchange_title_body/askubuntu.com.jsonl.gz",
854
+ "lines": 347925,
855
+ "weight": 79
856
+ },
857
+ {
858
+ "name": "stackexchange_Title_Answer/superuser.com.jsonl.gz",
859
+ "lines": 352610,
860
+ "weight": 80
861
+ },
862
+ {
863
+ "name": "stackexchange_title_body/superuser.com.jsonl.gz",
864
+ "lines": 435463,
865
+ "weight": 99
866
+ },
867
+ {
868
+ "name": "stackexchange_title_body/small_stackexchanges.jsonl.gz",
869
+ "lines": 448146,
870
+ "weight": 102
871
+ },
872
+ {
873
+ "name": "stackexchange_Title_Answer/small_stackexchanges.jsonl.gz",
874
+ "lines": 460256,
875
+ "weight": 104
876
+ },
877
+ {
878
+ "name": "eli5_question_answer.jsonl.gz",
879
+ "lines": 325475,
880
+ "weight": 147
881
+ },
882
+ {
883
+ "name": "yahoo_answers_title_question.jsonl.gz",
884
+ "lines": 659896,
885
+ "weight": 149
886
+ },
887
+ {
888
+ "name": "PAQ_pairs.jsonl.gz",
889
+ "lines": 64371441,
890
+ "weight": 150
891
+ },
892
+ {
893
+ "name": "WikiAnswers_pairs.jsonl.gz",
894
+ "lines": 77427422,
895
+ "weight": 150
896
+ },
897
+ {
898
+ "name": "stackexchange_Title_Answer/math.stackexchange.com.jsonl.gz",
899
+ "lines": 1100953,
900
+ "weight": 226
901
+ },
902
+ {
903
+ "name": "yahoo_answers_title_answer.jsonl.gz",
904
+ "lines": 1198260,
905
+ "weight": 226
906
+ },
907
+ {
908
+ "name": "stackexchange_title_body/math.stackexchange.com.jsonl.gz",
909
+ "lines": 1338443,
910
+ "weight": 226
911
+ },
912
+ {
913
+ "name": "stackexchange_Title_Answer/stackoverflow.com-Posts.jsonl.gz",
914
+ "lines": 15768211,
915
+ "weight": 226
916
+ },
917
+ {
918
+ "name": "stackexchange_title_body/stackoverflow.com-Posts.jsonl.gz",
919
+ "lines": 18562443,
920
+ "weight": 226
921
+ },
922
+ {
923
+ "name": "searchQA_question_top5_snippets_merged.jsonl.gz",
924
+ "lines": 582261,
925
+ "weight": 263
926
+ },
927
+ {
928
+ "name": "amazon-qa-train-pairs.jsonl.gz",
929
+ "lines": 2448839,
930
+ "weight": 451
931
+ },
932
+ {
933
+ "name": "gooaq_pairs.jsonl.gz",
934
+ "lines": 3012496,
935
+ "weight": 451
936
+ },
937
+ {
938
+ "name": "msmarco-query_passage_negative_v2.jsonl.gz",
939
+ "lines": 17579773,
940
+ "weight": 1000
941
+ }
942
+ ]