Llama-Guard-3-8B-GGUF / scores /Llama-Guard-3-8B-q3_k_s.tqa
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 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 40.00000000
6 33.33333333
7 28.57142857
8 37.50000000
9 33.33333333
10 30.00000000
11 27.27272727
12 33.33333333
13 38.46153846
14 35.71428571
15 40.00000000
16 37.50000000
17 35.29411765
18 33.33333333
19 31.57894737
20 30.00000000
21 28.57142857
22 27.27272727
23 26.08695652
24 29.16666667
25 28.00000000
26 26.92307692
27 25.92592593
28 25.00000000
29 27.58620690
30 26.66666667
31 25.80645161
32 28.12500000
33 30.30303030
34 29.41176471
35 28.57142857
36 27.77777778
37 29.72972973
38 28.94736842
39 30.76923077
40 30.00000000
41 29.26829268
42 28.57142857
43 27.90697674
44 29.54545455
45 31.11111111
46 30.43478261
47 31.91489362
48 33.33333333
49 32.65306122
50 34.00000000
51 33.33333333
52 32.69230769
53 32.07547170
54 31.48148148
55 32.72727273
56 32.14285714
57 31.57894737
58 32.75862069
59 33.89830508
60 35.00000000
61 34.42622951
62 35.48387097
63 34.92063492
64 34.37500000
65 33.84615385
66 33.33333333
67 32.83582090
68 32.35294118
69 33.33333333
70 32.85714286
71 33.80281690
72 34.72222222
73 34.24657534
74 33.78378378
75 33.33333333
76 32.89473684
77 32.46753247
78 32.05128205
79 31.64556962
80 32.50000000
81 32.09876543
82 32.92682927
83 32.53012048
84 32.14285714
85 31.76470588
86 31.39534884
87 31.03448276
88 30.68181818
89 31.46067416
90 31.11111111
91 31.86813187
92 31.52173913
93 31.18279570
94 30.85106383
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 31.06796117
104 30.76923077
105 30.47619048
106 31.13207547
107 31.77570093
108 31.48148148
109 31.19266055
110 31.81818182
111 31.53153153
112 32.14285714
113 32.74336283
114 33.33333333
115 33.04347826
116 32.75862069
117 33.33333333
118 33.05084746
119 32.77310924
120 33.33333333
121 33.88429752
122 33.60655738
123 34.14634146
124 34.67741935
125 35.20000000
126 35.71428571
127 35.43307087
128 35.15625000
129 35.65891473
130 36.15384615
131 35.87786260
132 35.60606061
133 35.33834586
134 35.07462687
135 35.55555556
136 35.29411765
137 35.76642336
138 36.23188406
139 36.69064748
140 36.42857143
141 36.17021277
142 35.91549296
143 35.66433566
144 36.11111111
145 35.86206897
146 35.61643836
147 35.37414966
148 35.13513514
149 34.89932886
150 34.66666667
151 35.09933775
152 35.52631579
153 35.29411765
154 35.06493506
155 34.83870968
156 35.25641026
157 35.03184713
158 34.81012658
159 34.59119497
160 34.37500000
161 34.78260870
162 35.18518519
163 34.96932515
164 34.75609756
165 35.15151515
166 35.54216867
167 35.32934132
168 35.71428571
169 35.50295858
170 35.29411765
171 35.08771930
172 34.88372093
173 34.68208092
174 35.05747126
175 34.85714286
176 35.22727273
177 35.02824859
178 34.83146067
179 35.19553073
180 35.00000000
181 34.80662983
182 34.61538462
183 34.42622951
184 34.23913043
185 34.05405405
186 34.40860215
187 34.22459893
188 34.04255319
189 33.86243386
190 33.68421053
191 33.50785340
192 33.33333333
193 33.16062176
194 33.50515464
195 33.33333333
196 33.16326531
197 33.50253807
198 33.83838384
199 33.66834171
200 33.50000000
201 33.33333333
202 33.66336634
203 33.49753695
204 33.33333333
205 33.65853659
206 33.49514563
207 33.81642512
208 33.65384615
209 33.49282297
210 33.33333333
211 33.17535545
212 33.01886792
213 32.86384977
214 32.71028037
215 32.55813953
216 32.87037037
217 32.71889401
218 32.56880734
219 32.42009132
220 32.27272727
221 32.12669683
222 31.98198198
223 31.83856502
224 32.14285714
225 32.00000000
226 31.85840708
227 32.15859031
228 32.01754386
229 31.87772926
230 31.73913043
231 31.60173160
232 31.89655172
233 31.75965665
234 32.05128205
235 32.34042553
236 32.62711864
237 32.48945148
238 32.77310924
239 32.63598326
240 32.50000000
241 32.36514523
242 32.23140496
243 32.09876543
244 31.96721311
245 31.83673469
246 31.70731707
247 31.98380567
248 32.25806452
249 32.12851406
250 32.00000000
251 32.27091633
252 32.53968254
253 32.41106719
254 32.28346457
255 32.54901961
256 32.42187500
257 32.29571984
258 32.17054264
259 32.04633205
260 31.92307692
261 32.18390805
262 32.06106870
263 31.93916350
264 32.19696970
265 32.45283019
266 32.33082707
267 32.20973783
268 32.08955224
269 31.97026022
270 31.85185185
271 31.73431734
272 31.61764706
273 31.50183150
274 31.38686131
275 31.27272727
276 31.15942029
277 31.04693141
278 31.29496403
279 31.18279570
280 31.42857143
281 31.67259786
282 31.56028369
283 31.44876325
284 31.33802817
285 31.22807018
286 31.46853147
287 31.70731707
288 31.94444444
289 31.83391003
290 31.72413793
291 31.95876289
292 31.84931507
293 32.08191126
294 31.97278912
295 32.20338983
296 32.43243243
297 32.65993266
298 32.55033557
299 32.44147157
300 32.33333333
301 32.22591362
302 32.11920530
303 32.01320132
304 31.90789474
305 31.80327869
306 31.69934641
307 31.59609121
308 31.81818182
309 31.71521036
310 31.61290323
311 31.51125402
312 31.73076923
313 31.62939297
314 31.52866242
315 31.74603175
316 31.64556962
317 31.54574132
318 31.44654088
319 31.34796238
320 31.25000000
321 31.15264798
322 31.36645963
323 31.26934985
324 31.17283951
325 31.07692308
326 30.98159509
327 31.19266055
328 31.40243902
329 31.30699088
330 31.51515152
331 31.41993958
332 31.62650602
333 31.83183183
334 31.73652695
335 31.94029851
336 32.14285714
337 32.04747774
338 31.95266272
339 32.15339233
340 32.05882353
341 31.96480938
342 32.16374269
343 32.06997085
344 32.26744186
345 32.46376812
346 32.36994220
347 32.27665706
348 32.18390805
349 32.09169054
350 32.00000000
351 31.90883191
352 31.81818182
353 31.72804533
354 31.63841808
355 31.83098592
356 31.74157303
357 31.65266106
358 31.84357542
359 31.75487465
360 31.66666667
361 31.85595568
362 31.76795580
363 31.68044077
364 31.86813187
365 31.78082192
366 31.69398907
367 31.88010899
368 32.06521739
369 31.97831978
370 31.89189189
371 31.80592992
372 31.98924731
373 31.90348525
374 32.08556150
375 32.00000000
376 31.91489362
377 32.09549072
378 32.01058201
379 31.92612137
380 32.10526316
381 32.02099738
382 32.19895288
383 32.11488251
384 32.03125000
385 31.94805195
386 31.86528497
387 31.78294574
388 31.95876289
389 31.87660668
390 31.79487179
391 31.96930946
392 31.88775510
393 31.80661578
394 31.97969543
395 31.89873418
396 32.07070707
397 32.24181360
398 32.16080402
399 32.08020050
400 32.00000000
401 31.92019950
402 32.08955224
403 32.00992556
404 31.93069307
405 31.85185185
406 31.77339901
407 31.69533170
408 31.61764706
409 31.54034230
410 31.46341463
411 31.38686131
412 31.55339806
413 31.47699758
414 31.64251208
415 31.80722892
416 31.73076923
417 31.65467626
418 31.57894737
419 31.50357995
420 31.42857143
421 31.59144893
422 31.51658768
423 31.67848700
424 31.60377358
425 31.52941176
426 31.69014085
427 31.61592506
428 31.54205607
429 31.46853147
430 31.39534884
431 31.32250580
432 31.48148148
433 31.63972286
434 31.79723502
435 31.72413793
436 31.88073394
437 31.80778032
438 31.96347032
439 31.89066059
440 32.04545455
441 31.97278912
442 32.12669683
443 32.05417607
444 32.20720721
445 32.13483146
446 32.06278027
447 31.99105145
448 31.91964286
449 32.07126949
450 32.22222222
451 32.15077605
452 32.07964602
453 32.22958057
454 32.15859031
455 32.08791209
456 32.01754386
457 31.94748359
458 31.87772926
459 31.80827887
460 31.73913043
461 31.67028200
462 31.81818182
463 31.74946004
464 31.89655172
465 32.04301075
466 31.97424893
467 31.90578158
468 31.83760684
469 31.76972281
470 31.70212766
471 31.63481953
472 31.77966102
473 31.92389006
474 31.85654008
475 32.00000000
476 31.93277311
477 31.86582809
478 31.79916318
479 31.73277662
480 31.66666667
481 31.60083160
482 31.74273859
483 31.67701863
484 31.61157025
485 31.75257732
486 31.89300412
487 32.03285421
488 31.96721311
489 32.10633947
490 32.24489796
491 32.38289206
492 32.52032520
493 32.45436105
494 32.38866397
495 32.32323232
496 32.25806452
497 32.19315895
498 32.12851406
499 32.26452906
500 32.20000000
501 32.33532934
502 32.27091633
503 32.20675944
504 32.34126984
505 32.27722772
506 32.21343874
507 32.14990138
508 32.08661417
509 32.22003929
510 32.15686275
511 32.09393346
512 32.03125000
513 31.96881092
514 31.90661479
515 32.03883495
516 32.17054264
517 32.30174081
518 32.23938224
519 32.17726397
520 32.11538462
521 32.24568138
522 32.18390805
523 32.12237094
524 32.06106870
525 32.00000000
526 31.93916350
527 32.06831120
528 32.00757576
529 31.94706994
530 31.88679245
531 31.82674200
532 31.76691729
533 31.89493433
534 31.83520599
535 31.77570093
536 31.71641791
537 31.65735568
538 31.59851301
539 31.53988868
540 31.48148148
541 31.42329020
542 31.36531365
543 31.30755064
544 31.25000000
545 31.19266055
546 31.31868132
547 31.44424132
548 31.56934307
549 31.51183971
550 31.45454545
551 31.39745917
552 31.52173913
553 31.64556962
554 31.58844765
555 31.53153153
556 31.47482014
557 31.41831239
558 31.36200717
559 31.30590340
560 31.42857143
561 31.55080214
562 31.49466192
563 31.43872114
564 31.56028369
565 31.68141593
566 31.80212014
567 31.92239859
568 32.04225352
569 31.98594025
570 31.92982456
571 32.04903678
572 31.99300699
573 31.93717277
574 32.05574913
575 32.17391304
576 32.29166667
577 32.23570191
578 32.17993080
579 32.12435233
580 32.24137931
581 32.18588640
582 32.30240550
583 32.24699828
584 32.36301370
585 32.30769231
586 32.42320819
587 32.36797274
588 32.31292517
589 32.25806452
590 32.37288136
591 32.31810491
592 32.26351351
593 32.20910624
594 32.32323232
595 32.26890756
596 32.21476510
597 32.16080402
598 32.10702341
599 32.05342237
600 32.00000000
601 32.11314476
602 32.22591362
603 32.33830846
604 32.28476821
605 32.23140496
606 32.34323432
607 32.28995058
608 32.23684211
609 32.34811166
610 32.29508197
611 32.24222586
612 32.35294118
613 32.30016313
614 32.24755700
615 32.19512195
616 32.30519481
617 32.41491086
618 32.36245955
619 32.31017771
620 32.25806452
621 32.20611916
622 32.31511254
623 32.26324238
624 32.21153846
625 32.16000000
626 32.10862620
627 32.05741627
628 32.16560510
629 32.11446741
630 32.06349206
631 32.01267829
632 31.96202532
633 31.91153239
634 31.86119874
635 31.81102362
636 31.76100629
637 31.71114600
638 31.66144201
639 31.61189358
640 31.71875000
641 31.66926677
642 31.77570093
643 31.72628305
644 31.67701863
645 31.78294574
646 31.73374613
647 31.68469861
648 31.79012346
649 31.74114022
650 31.84615385
651 31.95084485
652 32.05521472
653 32.15926493
654 32.11009174
655 32.06106870
656 32.16463415
657 32.26788432
658 32.21884498
659 32.32169954
660 32.27272727
661 32.22390318
662 32.17522659
663 32.12669683
664 32.07831325
665 32.18045113
666 32.28228228
667 32.23388306
668 32.18562874
669 32.13751868
670 32.23880597
671 32.19076006
672 32.14285714
673 32.09509658
674 32.04747774
675 32.14814815
676 32.24852071
677 32.20088626
678 32.15339233
679 32.10603829
680 32.05882353
681 32.01174743
682 32.11143695
683 32.06442167
684 32.16374269
685 32.11678832
686 32.06997085
687 32.02328967
688 32.12209302
689 32.07547170
690 32.02898551
691 32.12735166
692 32.22543353
693 32.32323232
694 32.27665706
695 32.23021583
696 32.32758621
697 32.42467719
698 32.37822350
699 32.33190272
700 32.42857143
701 32.38231098
702 32.33618234
703 32.29018492
704 32.24431818
705 32.19858156
706 32.29461756
707 32.24893918
708 32.20338983
709 32.15796897
710 32.25352113
711 32.20815752
712 32.16292135
713 32.11781206
714 32.07282913
715 32.02797203
716 31.98324022
717 32.07810321
718 32.17270195
719 32.26703755
720 32.22222222
721 32.17753121
722 32.13296399
723 32.08852006
724 32.18232044
725 32.13793103
726 32.23140496
727 32.18707015
728 32.14285714
729 32.09876543
730 32.19178082
731 32.14774282
732 32.24043716
733 32.19645293
734 32.15258856
735 32.10884354
736 32.06521739
737 32.02170963
738 31.97831978
739 32.07036536
740 32.16216216
741 32.25371120
742 32.21024259
743 32.16689098
744 32.25806452
745 32.21476510
746 32.30563003
747 32.39625167
748 32.35294118
749 32.44325768
750 32.53333333
Final result: 32.5333 +/- 1.7119
Random chance: 19.8992 +/- 1.4588