DeepSeek-R1-Distill-Qwen-7B-GGUF / scores /deepseek-r1-distill-qwen-7b-q4_k_m-unsloth.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 23.52941176
18 22.22222222
19 26.31578947
20 25.00000000
21 23.80952381
22 22.72727273
23 21.73913043
24 25.00000000
25 24.00000000
26 26.92307692
27 25.92592593
28 25.00000000
29 27.58620690
30 26.66666667
31 29.03225806
32 28.12500000
33 30.30303030
34 29.41176471
35 28.57142857
36 27.77777778
37 29.72972973
38 28.94736842
39 28.20512821
40 27.50000000
41 26.82926829
42 26.19047619
43 27.90697674
44 29.54545455
45 28.88888889
46 30.43478261
47 29.78723404
48 31.25000000
49 30.61224490
50 32.00000000
51 31.37254902
52 30.76923077
53 32.07547170
54 33.33333333
55 34.54545455
56 33.92857143
57 33.33333333
58 32.75862069
59 32.20338983
60 33.33333333
61 32.78688525
62 33.87096774
63 33.33333333
64 32.81250000
65 32.30769231
66 31.81818182
67 31.34328358
68 30.88235294
69 31.88405797
70 31.42857143
71 32.39436620
72 33.33333333
73 34.24657534
74 33.78378378
75 33.33333333
76 32.89473684
77 32.46753247
78 32.05128205
79 31.64556962
80 31.25000000
81 30.86419753
82 31.70731707
83 31.32530120
84 30.95238095
85 30.58823529
86 30.23255814
87 29.88505747
88 29.54545455
89 30.33707865
90 30.00000000
91 30.76923077
92 30.43478261
93 30.10752688
94 29.78723404
95 30.52631579
96 31.25000000
97 30.92783505
98 30.61224490
99 31.31313131
100 31.00000000
101 31.68316832
102 31.37254902
103 32.03883495
104 31.73076923
105 31.42857143
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 31.57894737
115 31.30434783
116 31.03448276
117 30.76923077
118 30.50847458
119 30.25210084
120 30.00000000
121 30.57851240
122 30.32786885
123 30.08130081
124 30.64516129
125 31.20000000
126 31.74603175
127 31.49606299
128 31.25000000
129 31.00775194
130 30.76923077
131 30.53435115
132 30.30303030
133 30.07518797
134 30.59701493
135 31.11111111
136 30.88235294
137 31.38686131
138 31.15942029
139 31.65467626
140 31.42857143
141 31.20567376
142 30.98591549
143 30.76923077
144 30.55555556
145 30.34482759
146 30.13698630
147 29.93197279
148 29.72972973
149 29.53020134
150 30.00000000
151 30.46357616
152 30.26315789
153 30.06535948
154 29.87012987
155 29.67741935
156 30.12820513
157 29.93630573
158 30.37974684
159 30.18867925
160 30.00000000
161 29.81366460
162 29.62962963
163 29.44785276
164 29.26829268
165 29.69696970
166 30.12048193
167 29.94011976
168 29.76190476
169 29.58579882
170 29.41176471
171 29.23976608
172 29.06976744
173 28.90173410
174 28.73563218
175 28.57142857
176 28.97727273
177 28.81355932
178 28.65168539
179 28.49162011
180 28.33333333
181 28.17679558
182 28.02197802
183 27.86885246
184 27.71739130
185 27.56756757
186 27.95698925
187 27.80748663
188 27.65957447
189 28.04232804
190 27.89473684
191 27.74869110
192 27.60416667
193 27.46113990
194 27.83505155
195 27.69230769
196 27.55102041
197 27.91878173
198 28.28282828
199 28.14070352
200 28.00000000
201 27.86069652
202 28.21782178
203 28.07881773
204 27.94117647
205 28.29268293
206 28.15533981
207 28.50241546
208 28.36538462
209 28.22966507
210 28.09523810
211 27.96208531
212 27.83018868
213 27.69953052
214 27.57009346
215 27.44186047
216 27.77777778
217 27.64976959
218 27.98165138
219 27.85388128
220 27.72727273
221 27.60180995
222 27.47747748
223 27.35426009
224 27.67857143
225 27.55555556
226 27.43362832
227 27.31277533
228 27.19298246
229 27.07423581
230 26.95652174
231 26.83982684
232 27.15517241
233 27.46781116
234 27.77777778
235 27.65957447
236 27.96610169
237 28.27004219
238 28.57142857
239 28.45188285
240 28.33333333
241 28.21576763
242 28.09917355
243 27.98353909
244 27.86885246
245 27.75510204
246 27.64227642
247 27.53036437
248 27.41935484
249 27.71084337
250 27.60000000
251 27.88844622
252 27.77777778
253 27.66798419
254 27.55905512
255 27.45098039
256 27.34375000
257 27.23735409
258 27.13178295
259 27.02702703
260 26.92307692
261 27.20306513
262 27.09923664
263 26.99619772
264 27.27272727
265 27.54716981
266 27.44360902
267 27.71535581
268 27.61194030
269 27.50929368
270 27.40740741
271 27.30627306
272 27.20588235
273 27.10622711
274 27.00729927
275 26.90909091
276 26.81159420
277 26.71480144
278 26.61870504
279 26.52329749
280 26.78571429
281 27.04626335
282 26.95035461
283 26.85512367
284 26.76056338
285 26.66666667
286 26.92307692
287 27.17770035
288 27.08333333
289 26.98961938
290 26.89655172
291 27.14776632
292 27.39726027
293 27.64505119
294 27.55102041
295 27.79661017
296 28.04054054
297 27.94612795
298 27.85234899
299 27.75919732
300 27.66666667
301 27.57475083
302 27.48344371
303 27.39273927
304 27.30263158
305 27.21311475
306 27.12418301
307 27.03583062
308 27.27272727
309 27.18446602
310 27.09677419
311 27.00964630
312 27.24358974
313 27.15654952
314 27.07006369
315 26.98412698
316 26.89873418
317 26.81388013
318 26.72955975
319 26.64576803
320 26.56250000
321 26.47975078
322 26.70807453
323 26.62538700
324 26.54320988
325 26.46153846
326 26.38036810
327 26.29969419
328 26.52439024
329 26.44376900
330 26.66666667
331 26.58610272
332 26.80722892
333 26.72672673
334 26.64670659
335 26.86567164
336 26.78571429
337 26.70623145
338 26.62721893
339 26.84365782
340 26.76470588
341 26.68621701
342 26.60818713
343 26.53061224
344 26.74418605
345 26.95652174
346 27.16763006
347 27.37752161
348 27.29885057
349 27.22063037
350 27.14285714
351 27.06552707
352 27.27272727
353 27.47875354
354 27.40112994
355 27.60563380
356 27.52808989
357 27.45098039
358 27.65363128
359 27.57660167
360 27.50000000
361 27.42382271
362 27.34806630
363 27.54820937
364 27.47252747
365 27.67123288
366 27.59562842
367 27.79291553
368 27.71739130
369 27.64227642
370 27.56756757
371 27.49326146
372 27.68817204
373 27.61394102
374 27.80748663
375 27.73333333
376 27.65957447
377 27.58620690
378 27.51322751
379 27.44063325
380 27.36842105
381 27.29658793
382 27.22513089
383 27.15404700
384 27.08333333
385 27.01298701
386 26.94300518
387 26.87338501
388 27.06185567
389 26.99228792
390 26.92307692
391 27.10997442
392 27.04081633
393 26.97201018
394 27.15736041
395 27.08860759
396 27.02020202
397 27.20403023
398 27.13567839
399 27.06766917
400 27.00000000
401 26.93266833
402 27.11442786
403 27.29528536
404 27.22772277
405 27.16049383
406 27.09359606
407 27.02702703
408 26.96078431
409 26.89486553
410 26.82926829
411 26.76399027
412 26.94174757
413 26.87651332
414 27.05314010
415 26.98795181
416 26.92307692
417 26.85851319
418 26.79425837
419 26.73031026
420 26.90476190
421 27.07838480
422 27.01421801
423 26.95035461
424 26.88679245
425 26.82352941
426 26.76056338
427 26.69789227
428 26.63551402
429 26.57342657
430 26.51162791
431 26.45011601
432 26.62037037
433 26.78983834
434 26.95852535
435 26.89655172
436 27.06422018
437 27.00228833
438 26.94063927
439 26.87927107
440 26.81818182
441 26.75736961
442 26.92307692
443 26.86230248
444 26.80180180
445 26.74157303
446 26.68161435
447 26.62192394
448 26.56250000
449 26.50334076
450 26.44444444
451 26.38580931
452 26.32743363
453 26.49006623
454 26.43171806
455 26.37362637
456 26.31578947
457 26.25820569
458 26.20087336
459 26.14379085
460 26.08695652
461 26.03036876
462 25.97402597
463 25.91792657
464 25.86206897
465 26.02150538
466 25.96566524
467 25.91006424
468 25.85470085
469 25.79957356
470 25.74468085
471 25.69002123
472 25.63559322
473 25.58139535
474 25.52742616
475 25.68421053
476 25.63025210
477 25.78616352
478 25.73221757
479 25.67849687
480 25.62500000
481 25.57172557
482 25.72614108
483 25.67287785
484 25.82644628
485 25.97938144
486 25.92592593
487 26.07802875
488 26.02459016
489 26.17586912
490 26.32653061
491 26.27291242
492 26.42276423
493 26.36916836
494 26.31578947
495 26.46464646
496 26.41129032
497 26.35814889
498 26.30522088
499 26.25250501
500 26.20000000
501 26.34730539
502 26.29482072
503 26.24254473
504 26.38888889
505 26.53465347
506 26.48221344
507 26.42998028
508 26.37795276
509 26.52259332
510 26.66666667
511 26.61448141
512 26.56250000
513 26.51072125
514 26.45914397
515 26.60194175
516 26.55038760
517 26.69245648
518 26.64092664
519 26.58959538
520 26.53846154
521 26.67946257
522 26.62835249
523 26.76864245
524 26.71755725
525 26.85714286
526 26.80608365
527 26.94497154
528 26.89393939
529 26.84310019
530 26.79245283
531 26.93032015
532 26.87969925
533 27.01688555
534 26.96629213
535 26.91588785
536 26.86567164
537 27.00186220
538 26.95167286
539 26.90166976
540 27.03703704
541 26.98706100
542 26.93726937
543 26.88766114
544 26.83823529
545 26.78899083
546 26.92307692
547 26.87385740
548 27.00729927
549 26.95810565
550 26.90909091
551 26.86025408
552 26.99275362
553 26.94394213
554 26.89530686
555 26.84684685
556 26.97841727
557 26.92998205
558 26.88172043
559 26.83363148
560 26.78571429
561 26.73796791
562 26.69039146
563 26.64298401
564 26.77304965
565 26.90265487
566 26.85512367
567 26.80776014
568 26.93661972
569 27.06502636
570 27.01754386
571 26.97022767
572 26.92307692
573 26.87609075
574 27.00348432
575 27.13043478
576 27.08333333
577 27.03639515
578 27.16262976
579 27.28842832
580 27.41379310
581 27.36660929
582 27.49140893
583 27.44425386
584 27.56849315
585 27.52136752
586 27.64505119
587 27.59795571
588 27.55102041
589 27.50424448
590 27.62711864
591 27.58037225
592 27.53378378
593 27.48735245
594 27.44107744
595 27.39495798
596 27.34899329
597 27.30318258
598 27.25752508
599 27.21202003
600 27.16666667
601 27.28785358
602 27.40863787
603 27.36318408
604 27.31788079
605 27.27272727
606 27.39273927
607 27.34761120
608 27.30263158
609 27.25779967
610 27.21311475
611 27.16857610
612 27.28758170
613 27.24306688
614 27.19869707
615 27.15447154
616 27.27272727
617 27.39059968
618 27.34627832
619 27.30210016
620 27.25806452
621 27.21417069
622 27.33118971
623 27.28731942
624 27.24358974
625 27.20000000
626 27.15654952
627 27.11323764
628 27.07006369
629 27.02702703
630 26.98412698
631 27.09984152
632 27.21518987
633 27.17219589
634 27.28706625
635 27.24409449
636 27.20125786
637 27.31554160
638 27.27272727
639 27.23004695
640 27.18750000
641 27.14508580
642 27.25856698
643 27.21617418
644 27.32919255
645 27.44186047
646 27.39938080
647 27.35703246
648 27.46913580
649 27.42681048
650 27.53846154
651 27.64976959
652 27.76073620
653 27.87136294
654 27.82874618
655 27.78625954
656 27.74390244
657 27.85388128
658 27.81155015
659 27.76934750
660 27.72727273
661 27.68532526
662 27.64350453
663 27.60180995
664 27.56024096
665 27.66917293
666 27.77777778
667 27.73613193
668 27.69461078
669 27.65321375
670 27.61194030
671 27.57078987
672 27.52976190
673 27.48885587
674 27.44807122
675 27.55555556
676 27.66272189
677 27.62186115
678 27.58112094
679 27.54050074
680 27.64705882
681 27.60646109
682 27.56598240
683 27.52562225
684 27.63157895
685 27.59124088
686 27.55102041
687 27.51091703
688 27.61627907
689 27.72133527
690 27.68115942
691 27.78581766
692 27.74566474
693 27.70562771
694 27.80979827
695 27.76978417
696 27.87356322
697 27.83357245
698 27.79369628
699 27.89699571
700 28.00000000
701 27.96005706
702 27.92022792
703 27.88051209
704 27.84090909
705 27.80141844
706 27.76203966
707 27.86421499
708 27.82485876
709 27.78561354
710 27.74647887
711 27.70745429
712 27.80898876
713 27.76998597
714 27.73109244
715 27.69230769
716 27.65363128
717 27.61506276
718 27.57660167
719 27.53824757
720 27.50000000
721 27.46185853
722 27.42382271
723 27.38589212
724 27.34806630
725 27.31034483
726 27.41046832
727 27.37276479
728 27.33516484
729 27.29766804
730 27.39726027
731 27.35978112
732 27.45901639
733 27.42155525
734 27.38419619
735 27.34693878
736 27.30978261
737 27.27272727
738 27.23577236
739 27.33423545
740 27.29729730
741 27.26045884
742 27.22371968
743 27.18707941
744 27.28494624
745 27.24832215
746 27.34584450
747 27.44310576
748 27.40641711
749 27.50333778
750 27.60000000
Final result: 27.6000 ±1.6334
Random chance: 19.8992 ±1.4588