DeepSeek-R1-Distill-Llama-8B-GGUF / scores /DeepSeek-R1-Distill-Llama-8B-Q4_K_M-unsloth.mmlu
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
afa61ba 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 1548 tasks in prompt
multiple_choice_score: selecting 750 random tasks from 1548 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 50.00000000
5 40.00000000
6 33.33333333
7 42.85714286
8 50.00000000
9 44.44444444
10 40.00000000
11 36.36363636
12 33.33333333
13 38.46153846
14 35.71428571
15 33.33333333
16 37.50000000
17 41.17647059
18 38.88888889
19 42.10526316
20 45.00000000
21 47.61904762
22 45.45454545
23 43.47826087
24 41.66666667
25 44.00000000
26 42.30769231
27 40.74074074
28 39.28571429
29 41.37931034
30 43.33333333
31 45.16129032
32 46.87500000
33 45.45454545
34 44.11764706
35 45.71428571
36 44.44444444
37 43.24324324
38 42.10526316
39 41.02564103
40 40.00000000
41 41.46341463
42 40.47619048
43 41.86046512
44 40.90909091
45 42.22222222
46 41.30434783
47 40.42553191
48 41.66666667
49 42.85714286
50 42.00000000
51 41.17647059
52 42.30769231
53 41.50943396
54 40.74074074
55 41.81818182
56 42.85714286
57 43.85964912
58 43.10344828
59 42.37288136
60 41.66666667
61 42.62295082
62 41.93548387
63 41.26984127
64 40.62500000
65 40.00000000
66 40.90909091
67 40.29850746
68 39.70588235
69 39.13043478
70 40.00000000
71 40.84507042
72 40.27777778
73 39.72602740
74 40.54054054
75 41.33333333
76 42.10526316
77 42.85714286
78 43.58974359
79 43.03797468
80 42.50000000
81 43.20987654
82 42.68292683
83 43.37349398
84 42.85714286
85 42.35294118
86 41.86046512
87 42.52873563
88 43.18181818
89 42.69662921
90 42.22222222
91 41.75824176
92 41.30434783
93 40.86021505
94 40.42553191
95 41.05263158
96 41.66666667
97 41.23711340
98 40.81632653
99 40.40404040
100 40.00000000
101 40.59405941
102 40.19607843
103 39.80582524
104 40.38461538
105 40.95238095
106 40.56603774
107 40.18691589
108 40.74074074
109 40.36697248
110 40.90909091
111 40.54054054
112 40.17857143
113 40.70796460
114 41.22807018
115 41.73913043
116 42.24137931
117 41.88034188
118 41.52542373
119 42.01680672
120 42.50000000
121 42.97520661
122 42.62295082
123 42.27642276
124 41.93548387
125 42.40000000
126 42.06349206
127 41.73228346
128 41.40625000
129 41.08527132
130 40.76923077
131 41.22137405
132 41.66666667
133 41.35338346
134 41.04477612
135 40.74074074
136 40.44117647
137 40.14598540
138 40.57971014
139 40.28776978
140 40.71428571
141 41.13475177
142 41.54929577
143 41.95804196
144 41.66666667
145 42.06896552
146 41.78082192
147 41.49659864
148 41.89189189
149 41.61073826
150 42.00000000
151 41.72185430
152 41.44736842
153 41.83006536
154 41.55844156
155 41.29032258
156 41.02564103
157 41.40127389
158 41.13924051
159 40.88050314
160 41.25000000
161 40.99378882
162 40.74074074
163 41.10429448
164 41.46341463
165 41.81818182
166 41.56626506
167 41.91616766
168 41.66666667
169 42.01183432
170 41.76470588
171 42.10526316
172 41.86046512
173 41.61849711
174 41.37931034
175 41.14285714
176 40.90909091
177 40.67796610
178 40.44943820
179 40.22346369
180 40.00000000
181 39.77900552
182 39.56043956
183 39.89071038
184 39.67391304
185 40.00000000
186 40.32258065
187 40.10695187
188 40.42553191
189 40.74074074
190 40.52631579
191 40.83769634
192 40.62500000
193 40.41450777
194 40.72164948
195 41.02564103
196 41.32653061
197 41.11675127
198 41.41414141
199 41.20603015
200 41.00000000
201 40.79601990
202 40.59405941
203 40.39408867
204 40.19607843
205 40.48780488
206 40.29126214
207 40.57971014
208 40.38461538
209 40.19138756
210 40.00000000
211 40.28436019
212 40.09433962
213 39.90610329
214 39.71962617
215 40.00000000
216 39.81481481
217 40.09216590
218 39.90825688
219 40.18264840
220 40.45454545
221 40.27149321
222 40.54054054
223 40.80717489
224 40.62500000
225 40.88888889
226 40.70796460
227 40.52863436
228 40.78947368
229 40.61135371
230 40.43478261
231 40.25974026
232 40.51724138
233 40.77253219
234 41.02564103
235 40.85106383
236 40.67796610
237 40.50632911
238 40.33613445
239 40.16736402
240 40.00000000
241 39.83402490
242 40.08264463
243 40.32921811
244 40.16393443
245 40.40816327
246 40.24390244
247 40.48582996
248 40.72580645
249 40.56224900
250 40.40000000
251 40.63745020
252 40.47619048
253 40.31620553
254 40.15748031
255 40.00000000
256 40.23437500
257 40.46692607
258 40.31007752
259 40.15444015
260 40.00000000
261 39.84674330
262 39.69465649
263 39.54372624
264 39.39393939
265 39.24528302
266 39.09774436
267 38.95131086
268 38.80597015
269 39.03345725
270 38.88888889
271 38.74538745
272 38.97058824
273 38.82783883
274 38.68613139
275 38.54545455
276 38.76811594
277 38.98916968
278 38.84892086
279 39.06810036
280 39.28571429
281 39.14590747
282 39.36170213
283 39.22261484
284 39.08450704
285 38.94736842
286 38.81118881
287 39.02439024
288 38.88888889
289 38.75432526
290 38.96551724
291 39.17525773
292 39.38356164
293 39.24914676
294 39.11564626
295 38.98305085
296 38.85135135
297 38.72053872
298 38.92617450
299 38.79598662
300 39.00000000
301 38.87043189
302 39.07284768
303 38.94389439
304 39.14473684
305 39.34426230
306 39.21568627
307 39.41368078
308 39.28571429
309 39.15857605
310 39.03225806
311 38.90675241
312 39.10256410
313 39.29712460
314 39.17197452
315 39.04761905
316 38.92405063
317 39.11671924
318 39.30817610
319 39.49843260
320 39.37500000
321 39.25233645
322 39.13043478
323 39.00928793
324 38.88888889
325 39.07692308
326 38.95705521
327 39.14373089
328 39.02439024
329 39.20972644
330 39.09090909
331 38.97280967
332 38.85542169
333 39.03903904
334 38.92215569
335 39.10447761
336 38.98809524
337 38.87240356
338 38.75739645
339 38.64306785
340 38.82352941
341 39.00293255
342 39.18128655
343 39.06705539
344 38.95348837
345 38.84057971
346 39.01734104
347 39.19308357
348 39.08045977
349 38.96848138
350 38.85714286
351 38.74643875
352 38.63636364
353 38.81019830
354 38.70056497
355 38.59154930
356 38.76404494
357 38.93557423
358 38.82681564
359 38.71866295
360 38.88888889
361 38.78116343
362 38.95027624
363 39.11845730
364 39.01098901
365 38.90410959
366 39.07103825
367 38.96457766
368 38.85869565
369 38.75338753
370 38.91891892
371 38.81401617
372 38.70967742
373 38.60589812
374 38.77005348
375 38.93333333
376 38.82978723
377 38.99204244
378 39.15343915
379 39.05013193
380 38.94736842
381 38.84514436
382 38.74345550
383 38.90339426
384 38.80208333
385 38.70129870
386 38.60103627
387 38.50129199
388 38.40206186
389 38.56041131
390 38.71794872
391 38.87468031
392 39.03061224
393 38.93129771
394 38.83248731
395 38.98734177
396 39.14141414
397 39.29471033
398 39.19597990
399 39.34837093
400 39.25000000
401 39.40149626
402 39.55223881
403 39.45409429
404 39.35643564
405 39.50617284
406 39.40886700
407 39.31203931
408 39.21568627
409 39.36430318
410 39.26829268
411 39.17274939
412 39.07766990
413 38.98305085
414 38.88888889
415 39.03614458
416 39.18269231
417 39.08872902
418 39.23444976
419 39.37947494
420 39.28571429
421 39.19239905
422 39.09952607
423 39.00709220
424 38.91509434
425 38.82352941
426 38.73239437
427 38.64168618
428 38.55140187
429 38.69463869
430 38.60465116
431 38.51508121
432 38.65740741
433 38.56812933
434 38.47926267
435 38.39080460
436 38.30275229
437 38.44393593
438 38.58447489
439 38.72437358
440 38.63636364
441 38.77551020
442 38.68778281
443 38.60045147
444 38.51351351
445 38.42696629
446 38.34080717
447 38.25503356
448 38.16964286
449 38.08463252
450 38.00000000
451 37.91574279
452 37.83185841
453 37.96909492
454 37.88546256
455 37.80219780
456 37.93859649
457 37.85557987
458 37.77292576
459 37.69063181
460 37.82608696
461 37.74403471
462 37.66233766
463 37.79697624
464 37.93103448
465 37.84946237
466 37.76824034
467 37.90149893
468 37.82051282
469 37.95309168
470 37.87234043
471 37.79193206
472 37.71186441
473 37.84355180
474 37.76371308
475 37.68421053
476 37.81512605
477 37.73584906
478 37.86610879
479 37.78705637
480 37.70833333
481 37.62993763
482 37.55186722
483 37.68115942
484 37.80991736
485 37.73195876
486 37.65432099
487 37.78234086
488 37.70491803
489 37.62781186
490 37.75510204
491 37.67820774
492 37.60162602
493 37.52535497
494 37.65182186
495 37.77777778
496 37.90322581
497 37.82696177
498 37.75100402
499 37.67535070
500 37.60000000
501 37.52495010
502 37.45019920
503 37.37574553
504 37.50000000
505 37.42574257
506 37.54940711
507 37.47534517
508 37.59842520
509 37.52455796
510 37.45098039
511 37.37769080
512 37.30468750
513 37.23196881
514 37.15953307
515 37.28155340
516 37.40310078
517 37.52417795
518 37.64478764
519 37.57225434
520 37.50000000
521 37.42802303
522 37.54789272
523 37.47609943
524 37.59541985
525 37.52380952
526 37.45247148
527 37.38140417
528 37.31060606
529 37.42911153
530 37.54716981
531 37.47645951
532 37.40601504
533 37.52345216
534 37.64044944
535 37.75700935
536 37.68656716
537 37.80260708
538 37.91821561
539 37.84786642
540 37.77777778
541 37.70794824
542 37.82287823
543 37.75322284
544 37.68382353
545 37.61467890
546 37.72893773
547 37.65996344
548 37.77372263
549 37.70491803
550 37.63636364
551 37.74954628
552 37.68115942
553 37.61301989
554 37.54512635
555 37.47747748
556 37.58992806
557 37.70197487
558 37.81362007
559 37.92486583
560 37.85714286
561 37.78966132
562 37.90035587
563 38.01065719
564 37.94326241
565 38.05309735
566 38.16254417
567 38.09523810
568 38.02816901
569 37.96133568
570 37.89473684
571 37.82837128
572 37.76223776
573 37.69633508
574 37.63066202
575 37.56521739
576 37.67361111
577 37.78162912
578 37.71626298
579 37.65112263
580 37.75862069
581 37.86574871
582 37.80068729
583 37.90737564
584 38.01369863
585 38.11965812
586 38.22525597
587 38.16013629
588 38.09523810
589 38.03056027
590 37.96610169
591 37.90186125
592 37.83783784
593 37.94266442
594 38.04713805
595 37.98319328
596 38.08724832
597 38.02345059
598 37.95986622
599 38.06343907
600 38.00000000
601 38.10316140
602 38.03986711
603 38.14262023
604 38.07947020
605 38.01652893
606 37.95379538
607 38.05601318
608 37.99342105
609 37.93103448
610 37.86885246
611 37.97054010
612 37.90849673
613 37.84665579
614 37.78501629
615 37.72357724
616 37.66233766
617 37.76337115
618 37.70226537
619 37.64135703
620 37.58064516
621 37.68115942
622 37.62057878
623 37.56019262
624 37.66025641
625 37.60000000
626 37.69968051
627 37.63955343
628 37.57961783
629 37.67885533
630 37.77777778
631 37.71790808
632 37.81645570
633 37.75671406
634 37.69716088
635 37.63779528
636 37.57861635
637 37.51962323
638 37.46081505
639 37.55868545
640 37.65625000
641 37.59750390
642 37.53894081
643 37.48055988
644 37.57763975
645 37.51937984
646 37.46130031
647 37.40340031
648 37.34567901
649 37.28813559
650 37.23076923
651 37.17357911
652 37.11656442
653 37.05972435
654 37.15596330
655 37.09923664
656 37.19512195
657 37.13850837
658 37.23404255
659 37.32928680
660 37.27272727
661 37.21633888
662 37.16012085
663 37.10407240
664 37.04819277
665 36.99248120
666 36.93693694
667 36.88155922
668 36.97604790
669 37.07025411
670 37.01492537
671 36.95976155
672 36.90476190
673 36.84992571
674 36.79525223
675 36.74074074
676 36.68639053
677 36.63220089
678 36.57817109
679 36.52430044
680 36.61764706
681 36.71071953
682 36.65689150
683 36.60322108
684 36.69590643
685 36.64233577
686 36.58892128
687 36.53566230
688 36.48255814
689 36.57474601
690 36.52173913
691 36.46888567
692 36.41618497
693 36.36363636
694 36.31123919
695 36.25899281
696 36.35057471
697 36.29842181
698 36.24641834
699 36.33762518
700 36.28571429
701 36.37660485
702 36.46723647
703 36.41536273
704 36.36363636
705 36.31205674
706 36.26062323
707 36.20933522
708 36.15819209
709 36.10719323
710 36.05633803
711 36.14627286
712 36.09550562
713 36.18513324
714 36.27450980
715 36.22377622
716 36.17318436
717 36.26220363
718 36.21169916
719 36.30041725
720 36.25000000
721 36.19972261
722 36.14958449
723 36.23789765
724 36.32596685
725 36.41379310
726 36.36363636
727 36.31361761
728 36.40109890
729 36.35116598
730 36.30136986
731 36.25170999
732 36.20218579
733 36.28922237
734 36.37602180
735 36.32653061
736 36.27717391
737 36.36363636
738 36.31436314
739 36.40054127
740 36.35135135
741 36.30229420
742 36.38814016
743 36.47375505
744 36.55913978
745 36.51006711
746 36.46112601
747 36.41231593
748 36.36363636
749 36.31508678
750 36.40000000
Final result: 36.4000 +/- 1.7581
Random chance: 25.0000 +/- 1.5822