Llama-Guard-3-8B-GGUF / scores /Llama-Guard-3-8B-F16.mmlu
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
6de6927 verified
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 50.00000000
11 45.45454545
12 41.66666667
13 38.46153846
14 35.71428571
15 40.00000000
16 43.75000000
17 47.05882353
18 44.44444444
19 47.36842105
20 50.00000000
21 52.38095238
22 50.00000000
23 47.82608696
24 50.00000000
25 52.00000000
26 50.00000000
27 51.85185185
28 50.00000000
29 51.72413793
30 53.33333333
31 54.83870968
32 56.25000000
33 54.54545455
34 55.88235294
35 57.14285714
36 55.55555556
37 54.05405405
38 55.26315789
39 53.84615385
40 52.50000000
41 51.21951220
42 50.00000000
43 51.16279070
44 50.00000000
45 51.11111111
46 50.00000000
47 48.93617021
48 50.00000000
49 51.02040816
50 50.00000000
51 49.01960784
52 48.07692308
53 47.16981132
54 46.29629630
55 47.27272727
56 48.21428571
57 47.36842105
58 46.55172414
59 47.45762712
60 46.66666667
61 47.54098361
62 46.77419355
63 46.03174603
64 45.31250000
65 44.61538462
66 45.45454545
67 44.77611940
68 44.11764706
69 43.47826087
70 44.28571429
71 45.07042254
72 44.44444444
73 43.83561644
74 44.59459459
75 45.33333333
76 46.05263158
77 46.75324675
78 47.43589744
79 46.83544304
80 47.50000000
81 48.14814815
82 47.56097561
83 48.19277108
84 48.80952381
85 48.23529412
86 47.67441860
87 48.27586207
88 48.86363636
89 48.31460674
90 47.77777778
91 47.25274725
92 46.73913043
93 46.23655914
94 46.80851064
95 46.31578947
96 46.87500000
97 46.39175258
98 45.91836735
99 46.46464646
100 46.00000000
101 46.53465347
102 46.07843137
103 45.63106796
104 46.15384615
105 46.66666667
106 47.16981132
107 46.72897196
108 47.22222222
109 47.70642202
110 48.18181818
111 48.64864865
112 48.21428571
113 47.78761062
114 48.24561404
115 48.69565217
116 48.27586207
117 47.86324786
118 48.30508475
119 47.89915966
120 47.50000000
121 47.93388430
122 47.54098361
123 47.15447154
124 47.58064516
125 48.00000000
126 47.61904762
127 47.24409449
128 46.87500000
129 46.51162791
130 46.15384615
131 45.80152672
132 46.21212121
133 45.86466165
134 45.52238806
135 45.18518519
136 44.85294118
137 45.25547445
138 44.92753623
139 45.32374101
140 45.00000000
141 45.39007092
142 45.77464789
143 46.15384615
144 46.52777778
145 46.89655172
146 47.26027397
147 46.93877551
148 47.29729730
149 46.97986577
150 46.66666667
151 46.35761589
152 46.71052632
153 46.40522876
154 46.10389610
155 45.80645161
156 45.51282051
157 45.85987261
158 46.20253165
159 45.91194969
160 46.25000000
161 45.96273292
162 45.67901235
163 45.39877301
164 45.12195122
165 45.45454545
166 45.18072289
167 45.50898204
168 45.23809524
169 45.56213018
170 45.29411765
171 45.61403509
172 45.34883721
173 45.08670520
174 44.82758621
175 44.57142857
176 44.31818182
177 44.06779661
178 43.82022472
179 44.13407821
180 44.44444444
181 44.75138122
182 44.50549451
183 44.80874317
184 44.56521739
185 44.86486486
186 45.16129032
187 44.91978610
188 45.21276596
189 45.50264550
190 45.26315789
191 45.54973822
192 45.31250000
193 45.07772021
194 45.36082474
195 45.64102564
196 45.91836735
197 45.68527919
198 45.45454545
199 45.22613065
200 45.00000000
201 44.77611940
202 44.55445545
203 44.33497537
204 44.11764706
205 44.39024390
206 44.17475728
207 44.44444444
208 44.23076923
209 44.01913876
210 43.80952381
211 44.07582938
212 43.86792453
213 43.66197183
214 43.45794393
215 43.72093023
216 43.98148148
217 43.77880184
218 44.03669725
219 44.29223744
220 44.54545455
221 44.34389140
222 44.59459459
223 44.84304933
224 44.64285714
225 44.88888889
226 44.69026549
227 44.49339207
228 44.73684211
229 44.54148472
230 44.34782609
231 44.15584416
232 44.39655172
233 44.20600858
234 44.44444444
235 44.25531915
236 44.06779661
237 43.88185654
238 43.69747899
239 43.51464435
240 43.75000000
241 43.56846473
242 43.80165289
243 44.03292181
244 43.85245902
245 44.08163265
246 43.90243902
247 43.72469636
248 43.95161290
249 43.77510040
250 43.60000000
251 43.42629482
252 43.25396825
253 43.08300395
254 42.91338583
255 42.74509804
256 42.96875000
257 43.19066148
258 43.02325581
259 42.85714286
260 43.07692308
261 42.91187739
262 42.74809160
263 42.58555133
264 42.42424242
265 42.64150943
266 42.85714286
267 42.69662921
268 42.53731343
269 42.75092937
270 42.59259259
271 42.43542435
272 42.64705882
273 42.49084249
274 42.33576642
275 42.18181818
276 42.39130435
277 42.59927798
278 42.44604317
279 42.29390681
280 42.50000000
281 42.34875445
282 42.55319149
283 42.40282686
284 42.25352113
285 42.10526316
286 41.95804196
287 42.16027875
288 42.01388889
289 41.86851211
290 42.06896552
291 42.26804124
292 42.46575342
293 42.32081911
294 42.17687075
295 42.03389831
296 41.89189189
297 41.75084175
298 41.94630872
299 41.80602007
300 42.00000000
301 41.86046512
302 41.72185430
303 41.58415842
304 41.44736842
305 41.63934426
306 41.50326797
307 41.69381107
308 41.55844156
309 41.42394822
310 41.29032258
311 41.15755627
312 41.34615385
313 41.21405751
314 41.08280255
315 40.95238095
316 40.82278481
317 41.00946372
318 41.19496855
319 41.37931034
320 41.25000000
321 41.12149533
322 40.99378882
323 40.86687307
324 40.74074074
325 40.92307692
326 40.79754601
327 40.97859327
328 40.85365854
329 40.72948328
330 40.60606061
331 40.48338369
332 40.66265060
333 40.84084084
334 40.71856287
335 40.89552239
336 41.07142857
337 40.94955490
338 40.82840237
339 40.70796460
340 40.88235294
341 41.05571848
342 41.22807018
343 41.10787172
344 40.98837209
345 40.86956522
346 41.04046243
347 41.21037464
348 41.09195402
349 40.97421203
350 41.14285714
351 41.02564103
352 40.90909091
353 41.07648725
354 40.96045198
355 40.84507042
356 41.01123596
357 41.17647059
358 41.06145251
359 40.94707521
360 41.11111111
361 41.27423823
362 41.43646409
363 41.59779614
364 41.48351648
365 41.36986301
366 41.53005464
367 41.41689373
368 41.30434783
369 41.19241192
370 41.35135135
371 41.23989218
372 41.12903226
373 41.01876676
374 41.17647059
375 41.33333333
376 41.22340426
377 41.11405836
378 41.26984127
379 41.16094987
380 41.05263158
381 41.20734908
382 41.09947644
383 41.25326371
384 41.14583333
385 41.29870130
386 41.19170984
387 41.08527132
388 40.97938144
389 41.13110540
390 41.28205128
391 41.43222506
392 41.58163265
393 41.47582697
394 41.37055838
395 41.51898734
396 41.66666667
397 41.56171285
398 41.45728643
399 41.60401003
400 41.50000000
401 41.64588529
402 41.54228856
403 41.43920596
404 41.33663366
405 41.23456790
406 41.13300493
407 41.03194103
408 40.93137255
409 41.07579462
410 40.97560976
411 40.87591241
412 40.77669903
413 40.67796610
414 40.57971014
415 40.48192771
416 40.62500000
417 40.52757794
418 40.43062201
419 40.57279236
420 40.47619048
421 40.61757720
422 40.52132701
423 40.42553191
424 40.56603774
425 40.47058824
426 40.37558685
427 40.51522248
428 40.42056075
429 40.55944056
430 40.46511628
431 40.60324826
432 40.50925926
433 40.41570439
434 40.32258065
435 40.22988506
436 40.13761468
437 40.04576659
438 40.18264840
439 40.31890661
440 40.22727273
441 40.36281179
442 40.27149321
443 40.18058691
444 40.09009009
445 40.00000000
446 39.91031390
447 39.82102908
448 39.73214286
449 39.64365256
450 39.77777778
451 39.91130820
452 39.82300885
453 39.95584989
454 39.86784141
455 39.78021978
456 39.91228070
457 39.82494530
458 39.73799127
459 39.86928105
460 40.00000000
461 39.91323210
462 40.04329004
463 39.95680346
464 40.08620690
465 40.00000000
466 39.91416309
467 40.04282655
468 40.17094017
469 40.08528785
470 40.00000000
471 39.91507431
472 39.83050847
473 39.95771670
474 39.87341772
475 39.78947368
476 39.91596639
477 39.83228512
478 39.95815900
479 40.08350731
480 40.20833333
481 40.12474012
482 40.04149378
483 39.95859213
484 39.87603306
485 39.79381443
486 39.71193416
487 39.83572895
488 39.75409836
489 39.67280164
490 39.79591837
491 39.71486762
492 39.63414634
493 39.55375254
494 39.67611336
495 39.79797980
496 39.91935484
497 39.83903421
498 39.75903614
499 39.67935872
500 39.80000000
501 39.72055888
502 39.64143426
503 39.76143141
504 39.68253968
505 39.60396040
506 39.72332016
507 39.64497041
508 39.56692913
509 39.48919450
510 39.60784314
511 39.53033268
512 39.45312500
513 39.37621832
514 39.29961089
515 39.41747573
516 39.53488372
517 39.65183752
518 39.76833977
519 39.69171484
520 39.61538462
521 39.53934741
522 39.65517241
523 39.57934990
524 39.69465649
525 39.61904762
526 39.54372624
527 39.65844402
528 39.77272727
529 39.69754253
530 39.81132075
531 39.73634652
532 39.66165414
533 39.58724203
534 39.51310861
535 39.62616822
536 39.55223881
537 39.66480447
538 39.77695167
539 39.70315399
540 39.62962963
541 39.55637708
542 39.66789668
543 39.59484346
544 39.70588235
545 39.63302752
546 39.56043956
547 39.67093236
548 39.78102190
549 39.70856102
550 39.63636364
551 39.74591652
552 39.67391304
553 39.60216998
554 39.53068592
555 39.45945946
556 39.56834532
557 39.49730700
558 39.60573477
559 39.53488372
560 39.64285714
561 39.57219251
562 39.67971530
563 39.78685613
564 39.71631206
565 39.82300885
566 39.75265018
567 39.68253968
568 39.78873239
569 39.71880492
570 39.64912281
571 39.57968476
572 39.68531469
573 39.61605585
574 39.54703833
575 39.47826087
576 39.58333333
577 39.68804159
578 39.79238754
579 39.72366149
580 39.65517241
581 39.58691910
582 39.51890034
583 39.62264151
584 39.72602740
585 39.82905983
586 39.76109215
587 39.69335605
588 39.62585034
589 39.55857385
590 39.49152542
591 39.42470389
592 39.35810811
593 39.46037099
594 39.56228956
595 39.49579832
596 39.59731544
597 39.53098827
598 39.46488294
599 39.56594324
600 39.50000000
601 39.60066556
602 39.53488372
603 39.63515755
604 39.56953642
605 39.50413223
606 39.43894389
607 39.53871499
608 39.47368421
609 39.40886700
610 39.34426230
611 39.44353519
612 39.37908497
613 39.47797716
614 39.41368078
615 39.34959350
616 39.44805195
617 39.38411669
618 39.32038835
619 39.25686591
620 39.19354839
621 39.13043478
622 39.22829582
623 39.16532905
624 39.10256410
625 39.04000000
626 39.13738019
627 39.07496013
628 39.01273885
629 39.10969793
630 39.20634921
631 39.14421553
632 39.24050633
633 39.17851501
634 39.11671924
635 39.05511811
636 38.99371069
637 38.93249608
638 38.87147335
639 38.81064163
640 38.90625000
641 38.84555382
642 38.78504673
643 38.72472784
644 38.66459627
645 38.60465116
646 38.54489164
647 38.48531685
648 38.42592593
649 38.36671803
650 38.30769231
651 38.24884793
652 38.19018405
653 38.13169985
654 38.22629969
655 38.16793893
656 38.26219512
657 38.35616438
658 38.44984802
659 38.39150228
660 38.33333333
661 38.27534039
662 38.21752266
663 38.15987934
664 38.25301205
665 38.34586466
666 38.28828829
667 38.38080960
668 38.47305389
669 38.56502242
670 38.50746269
671 38.45007452
672 38.39285714
673 38.33580981
674 38.27893175
675 38.22222222
676 38.16568047
677 38.10930576
678 38.20058997
679 38.14432990
680 38.23529412
681 38.32599119
682 38.26979472
683 38.21376281
684 38.30409357
685 38.39416058
686 38.33819242
687 38.28238719
688 38.22674419
689 38.31640058
690 38.26086957
691 38.20549928
692 38.15028902
693 38.09523810
694 38.04034582
695 37.98561151
696 38.07471264
697 38.02008608
698 38.10888252
699 38.19742489
700 38.14285714
701 38.08844508
702 38.17663818
703 38.26458037
704 38.35227273
705 38.29787234
706 38.24362606
707 38.18953324
708 38.13559322
709 38.22284908
710 38.16901408
711 38.25597750
712 38.20224719
713 38.28892006
714 38.37535014
715 38.32167832
716 38.26815642
717 38.21478382
718 38.16155989
719 38.10848401
720 38.05555556
721 38.00277393
722 37.95013850
723 38.03596127
724 38.12154696
725 38.20689655
726 38.15426997
727 38.23933975
728 38.18681319
729 38.13443073
730 38.08219178
731 38.03009576
732 37.97814208
733 38.06275580
734 38.01089918
735 37.95918367
736 37.90760870
737 37.99185889
738 38.07588076
739 38.15967524
740 38.10810811
741 38.05668016
742 38.14016173
743 38.22341857
744 38.30645161
745 38.25503356
746 38.20375335
747 38.15261044
748 38.10160428
749 38.05073431
750 38.13333333
Final result: 38.1333 +/- 1.7748
Random chance: 25.0000 +/- 1.5822