DeepSeek-R1-Distill-Qwen-7B-GGUF / scores /deepseek-r1-distill-qwen-7b-q3_k_l.tqa
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
94d6d71 verified
raw
history blame
12.6 kB
common_init_from_params: setting dry_penalty_last_n to ctx_size = 768
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
system_info: n_threads = 6 (n_threads_batch = 6) / 12 | Metal : EMBED_LIBRARY = 1 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | DOTPROD = 1 | LLAMAFILE = 1 | ACCELERATE = 1 | AARCH64_REPACK = 1 |
multiple_choice_score: there are 817 tasks in prompt
multiple_choice_score: selecting 750 random tasks from 817 tasks available
multiple_choice_score: preparing task data...done
multiple_choice_score : calculating TruthfulQA score over 750 tasks.
task acc_norm
1 100.00000000
2 50.00000000
3 33.33333333
4 25.00000000
5 20.00000000
6 16.66666667
7 14.28571429
8 12.50000000
9 11.11111111
10 10.00000000
11 9.09090909
12 16.66666667
13 15.38461538
14 14.28571429
15 13.33333333
16 18.75000000
17 17.64705882
18 16.66666667
19 21.05263158
20 20.00000000
21 19.04761905
22 18.18181818
23 17.39130435
24 20.83333333
25 20.00000000
26 23.07692308
27 22.22222222
28 21.42857143
29 24.13793103
30 23.33333333
31 25.80645161
32 25.00000000
33 27.27272727
34 26.47058824
35 25.71428571
36 25.00000000
37 27.02702703
38 26.31578947
39 25.64102564
40 25.00000000
41 24.39024390
42 23.80952381
43 25.58139535
44 27.27272727
45 26.66666667
46 28.26086957
47 27.65957447
48 29.16666667
49 28.57142857
50 28.00000000
51 27.45098039
52 26.92307692
53 28.30188679
54 29.62962963
55 30.90909091
56 30.35714286
57 29.82456140
58 29.31034483
59 28.81355932
60 30.00000000
61 29.50819672
62 30.64516129
63 30.15873016
64 29.68750000
65 29.23076923
66 28.78787879
67 28.35820896
68 27.94117647
69 27.53623188
70 28.57142857
71 29.57746479
72 30.55555556
73 31.50684932
74 31.08108108
75 30.66666667
76 31.57894737
77 31.16883117
78 30.76923077
79 30.37974684
80 30.00000000
81 29.62962963
82 30.48780488
83 30.12048193
84 29.76190476
85 29.41176471
86 29.06976744
87 28.73563218
88 28.40909091
89 28.08988764
90 27.77777778
91 28.57142857
92 28.26086957
93 27.95698925
94 27.65957447
95 28.42105263
96 29.16666667
97 28.86597938
98 28.57142857
99 29.29292929
100 30.00000000
101 30.69306931
102 30.39215686
103 31.06796117
104 30.76923077
105 30.47619048
106 31.13207547
107 31.77570093
108 32.40740741
109 32.11009174
110 32.72727273
111 32.43243243
112 32.14285714
113 31.85840708
114 32.45614035
115 32.17391304
116 31.89655172
117 31.62393162
118 31.35593220
119 31.09243697
120 31.66666667
121 32.23140496
122 31.96721311
123 32.52032520
124 33.06451613
125 33.60000000
126 34.12698413
127 33.85826772
128 33.59375000
129 33.33333333
130 33.07692308
131 32.82442748
132 32.57575758
133 32.33082707
134 32.83582090
135 33.33333333
136 33.08823529
137 33.57664234
138 34.05797101
139 33.81294964
140 34.28571429
141 34.04255319
142 33.80281690
143 33.56643357
144 34.02777778
145 33.79310345
146 33.56164384
147 34.01360544
148 33.78378378
149 33.55704698
150 33.33333333
151 33.77483444
152 33.55263158
153 33.33333333
154 33.11688312
155 32.90322581
156 33.33333333
157 33.12101911
158 33.54430380
159 33.33333333
160 33.12500000
161 32.91925466
162 32.71604938
163 33.12883436
164 32.92682927
165 33.33333333
166 33.73493976
167 33.53293413
168 33.33333333
169 33.13609467
170 32.94117647
171 32.74853801
172 32.55813953
173 32.36994220
174 32.18390805
175 32.00000000
176 32.38636364
177 32.20338983
178 32.02247191
179 31.84357542
180 31.66666667
181 31.49171271
182 31.31868132
183 31.14754098
184 30.97826087
185 30.81081081
186 31.18279570
187 31.01604278
188 30.85106383
189 31.21693122
190 31.05263158
191 30.89005236
192 30.72916667
193 30.56994819
194 30.92783505
195 30.76923077
196 30.61224490
197 30.96446701
198 31.31313131
199 31.15577889
200 31.50000000
201 31.34328358
202 31.68316832
203 31.52709360
204 31.37254902
205 31.21951220
206 31.06796117
207 31.40096618
208 31.25000000
209 31.10047847
210 30.95238095
211 30.80568720
212 30.66037736
213 30.51643192
214 30.37383178
215 30.23255814
216 30.09259259
217 29.95391705
218 30.27522936
219 30.13698630
220 30.00000000
221 29.86425339
222 29.72972973
223 29.59641256
224 29.91071429
225 29.77777778
226 29.64601770
227 29.51541850
228 29.38596491
229 29.25764192
230 29.13043478
231 29.00432900
232 29.31034483
233 29.61373391
234 29.91452991
235 30.21276596
236 30.50847458
237 30.80168776
238 31.09243697
239 30.96234310
240 30.83333333
241 30.70539419
242 30.57851240
243 30.45267490
244 30.32786885
245 30.20408163
246 30.08130081
247 29.95951417
248 30.24193548
249 30.12048193
250 30.00000000
251 30.27888446
252 30.15873016
253 30.03952569
254 29.92125984
255 29.80392157
256 29.68750000
257 29.57198444
258 29.45736434
259 29.34362934
260 29.23076923
261 29.11877395
262 29.00763359
263 28.89733840
264 29.16666667
265 29.43396226
266 29.32330827
267 29.58801498
268 29.47761194
269 29.36802974
270 29.62962963
271 29.52029520
272 29.41176471
273 29.30402930
274 29.19708029
275 29.09090909
276 28.98550725
277 28.88086643
278 28.77697842
279 28.67383513
280 28.57142857
281 28.82562278
282 28.72340426
283 28.62190813
284 28.52112676
285 28.42105263
286 28.67132867
287 28.57142857
288 28.47222222
289 28.37370242
290 28.27586207
291 28.52233677
292 28.76712329
293 29.01023891
294 28.91156463
295 29.15254237
296 29.39189189
297 29.62962963
298 29.53020134
299 29.43143813
300 29.33333333
301 29.23588040
302 29.47019868
303 29.37293729
304 29.27631579
305 29.18032787
306 29.08496732
307 28.99022801
308 29.22077922
309 29.12621359
310 29.03225806
311 28.93890675
312 29.16666667
313 29.07348243
314 28.98089172
315 28.88888889
316 28.79746835
317 28.70662461
318 28.61635220
319 28.52664577
320 28.43750000
321 28.34890966
322 28.57142857
323 28.48297214
324 28.39506173
325 28.30769231
326 28.22085890
327 28.13455657
328 28.35365854
329 28.26747720
330 28.48484848
331 28.39879154
332 28.61445783
333 28.82882883
334 28.74251497
335 28.95522388
336 29.16666667
337 29.08011869
338 28.99408284
339 29.20353982
340 29.11764706
341 29.32551320
342 29.53216374
343 29.44606414
344 29.65116279
345 29.85507246
346 30.05780347
347 30.25936599
348 30.17241379
349 30.08595989
350 30.00000000
351 29.91452991
352 30.11363636
353 30.31161473
354 30.22598870
355 30.42253521
356 30.33707865
357 30.25210084
358 30.44692737
359 30.36211699
360 30.27777778
361 30.19390582
362 30.11049724
363 30.02754821
364 29.94505495
365 30.13698630
366 30.05464481
367 30.24523161
368 30.16304348
369 30.08130081
370 30.00000000
371 29.91913747
372 30.10752688
373 30.02680965
374 30.21390374
375 30.13333333
376 30.05319149
377 29.97347480
378 29.89417989
379 29.81530343
380 29.73684211
381 29.65879265
382 29.58115183
383 29.50391645
384 29.42708333
385 29.35064935
386 29.27461140
387 29.19896641
388 29.38144330
389 29.30591260
390 29.23076923
391 29.41176471
392 29.33673469
393 29.51653944
394 29.69543147
395 29.62025316
396 29.54545455
397 29.72292191
398 29.64824121
399 29.57393484
400 29.50000000
401 29.42643392
402 29.60199005
403 29.52853598
404 29.45544554
405 29.38271605
406 29.31034483
407 29.23832924
408 29.16666667
409 29.09535452
410 29.02439024
411 28.95377129
412 29.12621359
413 29.05569007
414 29.22705314
415 29.15662651
416 29.08653846
417 29.01678657
418 28.94736842
419 28.87828162
420 29.04761905
421 29.21615202
422 29.14691943
423 29.07801418
424 29.00943396
425 28.94117647
426 28.87323944
427 28.80562061
428 28.73831776
429 28.67132867
430 28.60465116
431 28.53828306
432 28.70370370
433 28.86836028
434 29.03225806
435 28.96551724
436 28.89908257
437 28.83295195
438 28.76712329
439 28.70159453
440 28.86363636
441 28.79818594
442 28.73303167
443 28.66817156
444 28.82882883
445 28.76404494
446 28.69955157
447 28.63534676
448 28.57142857
449 28.73051225
450 28.66666667
451 28.60310421
452 28.53982301
453 28.47682119
454 28.41409692
455 28.35164835
456 28.28947368
457 28.22757112
458 28.16593886
459 28.10457516
460 28.04347826
461 27.98264642
462 27.92207792
463 27.86177106
464 27.80172414
465 27.95698925
466 27.89699571
467 28.05139186
468 27.99145299
469 27.93176972
470 27.87234043
471 27.81316348
472 27.75423729
473 27.90697674
474 28.05907173
475 28.21052632
476 28.15126050
477 28.30188679
478 28.24267782
479 28.18371608
480 28.12500000
481 28.06652807
482 28.00829876
483 27.95031056
484 28.09917355
485 28.24742268
486 28.18930041
487 28.33675565
488 28.27868852
489 28.42535787
490 28.57142857
491 28.51323829
492 28.65853659
493 28.60040568
494 28.54251012
495 28.68686869
496 28.62903226
497 28.57142857
498 28.51405622
499 28.45691383
500 28.40000000
501 28.34331337
502 28.28685259
503 28.23061630
504 28.37301587
505 28.51485149
506 28.45849802
507 28.40236686
508 28.34645669
509 28.48722986
510 28.62745098
511 28.57142857
512 28.51562500
513 28.46003899
514 28.40466926
515 28.54368932
516 28.48837209
517 28.62669246
518 28.57142857
519 28.51637765
520 28.46153846
521 28.59884837
522 28.54406130
523 28.68068834
524 28.62595420
525 28.57142857
526 28.51711027
527 28.65275142
528 28.59848485
529 28.54442344
530 28.49056604
531 28.62523540
532 28.57142857
533 28.70544090
534 28.65168539
535 28.59813084
536 28.54477612
537 28.67783985
538 28.62453532
539 28.57142857
540 28.70370370
541 28.65064695
542 28.59778598
543 28.54511971
544 28.49264706
545 28.44036697
546 28.57142857
547 28.51919561
548 28.64963504
549 28.59744991
550 28.54545455
551 28.49364791
552 28.62318841
553 28.75226040
554 28.70036101
555 28.64864865
556 28.77697842
557 28.72531418
558 28.67383513
559 28.62254025
560 28.57142857
561 28.52049911
562 28.46975089
563 28.41918295
564 28.54609929
565 28.67256637
566 28.62190813
567 28.57142857
568 28.52112676
569 28.47100176
570 28.42105263
571 28.37127846
572 28.32167832
573 28.27225131
574 28.39721254
575 28.52173913
576 28.47222222
577 28.42287695
578 28.54671280
579 28.49740933
580 28.62068966
581 28.74354561
582 28.86597938
583 28.81646655
584 28.93835616
585 28.88888889
586 29.01023891
587 29.13117547
588 29.08163265
589 29.03225806
590 29.15254237
591 29.10321489
592 29.05405405
593 29.00505902
594 29.12457912
595 29.07563025
596 29.02684564
597 29.14572864
598 29.09698997
599 29.04841402
600 29.00000000
601 29.11813644
602 29.06976744
603 29.02155887
604 28.97350993
605 28.92561983
606 29.04290429
607 28.99505766
608 28.94736842
609 28.89983580
610 28.85245902
611 28.80523732
612 28.92156863
613 28.87438825
614 28.82736156
615 28.78048780
616 28.89610390
617 29.01134522
618 28.96440129
619 29.07915994
620 29.03225806
621 28.98550725
622 29.09967846
623 29.05296950
624 29.00641026
625 28.96000000
626 28.91373802
627 29.02711324
628 28.98089172
629 28.93481717
630 28.88888889
631 29.00158479
632 28.95569620
633 28.90995261
634 29.02208202
635 28.97637795
636 28.93081761
637 29.04238619
638 28.99686520
639 28.95148670
640 28.90625000
641 28.86115445
642 28.97196262
643 28.92690513
644 29.03726708
645 29.14728682
646 29.10216718
647 29.05718702
648 29.16666667
649 29.12172573
650 29.23076923
651 29.33947773
652 29.44785276
653 29.55589587
654 29.51070336
655 29.46564885
656 29.42073171
657 29.52815830
658 29.48328267
659 29.43854325
660 29.39393939
661 29.34947050
662 29.30513595
663 29.26093514
664 29.21686747
665 29.32330827
666 29.42942943
667 29.38530735
668 29.34131737
669 29.29745889
670 29.25373134
671 29.21013413
672 29.16666667
673 29.12332838
674 29.08011869
675 29.18518519
676 29.28994083
677 29.24667651
678 29.20353982
679 29.16053019
680 29.26470588
681 29.22173275
682 29.17888563
683 29.13616398
684 29.23976608
685 29.19708029
686 29.15451895
687 29.11208151
688 29.21511628
689 29.17271408
690 29.13043478
691 29.08827786
692 29.04624277
693 29.14862915
694 29.25072046
695 29.20863309
696 29.31034483
697 29.26829268
698 29.22636103
699 29.32761087
700 29.42857143
701 29.38659058
702 29.34472934
703 29.30298720
704 29.40340909
705 29.36170213
706 29.32011331
707 29.27864215
708 29.23728814
709 29.19605078
710 29.15492958
711 29.11392405
712 29.21348315
713 29.17251052
714 29.13165266
715 29.09090909
716 29.05027933
717 29.00976290
718 28.96935933
719 29.06815021
720 29.02777778
721 28.98751734
722 28.94736842
723 28.90733057
724 28.86740331
725 28.82758621
726 28.92561983
727 28.88583219
728 28.84615385
729 28.80658436
730 28.90410959
731 28.86456908
732 28.96174863
733 28.92223738
734 28.88283379
735 28.84353741
736 28.80434783
737 28.76526459
738 28.72628726
739 28.68741543
740 28.64864865
741 28.60998650
742 28.57142857
743 28.53297443
744 28.62903226
745 28.59060403
746 28.68632708
747 28.64792503
748 28.60962567
749 28.70493992
750 28.66666667
Final result: 28.6667 ±1.6523
Random chance: 19.8992 ±1.4588