Hammer2.1-7b-GGUF / scores /Hammer2.1-7b-q4_k_m-naive.tqa
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
ed91853 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 20.00000000
6 16.66666667
7 14.28571429
8 12.50000000
9 11.11111111
10 10.00000000
11 9.09090909
12 16.66666667
13 23.07692308
14 21.42857143
15 20.00000000
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 19.23076923
27 18.51851852
28 17.85714286
29 20.68965517
30 20.00000000
31 19.35483871
32 21.87500000
33 24.24242424
34 23.52941176
35 22.85714286
36 22.22222222
37 24.32432432
38 23.68421053
39 25.64102564
40 25.00000000
41 24.39024390
42 23.80952381
43 25.58139535
44 25.00000000
45 26.66666667
46 26.08695652
47 25.53191489
48 25.00000000
49 24.48979592
50 26.00000000
51 27.45098039
52 26.92307692
53 26.41509434
54 27.77777778
55 29.09090909
56 28.57142857
57 28.07017544
58 27.58620690
59 27.11864407
60 26.66666667
61 26.22950820
62 27.41935484
63 26.98412698
64 26.56250000
65 26.15384615
66 25.75757576
67 25.37313433
68 25.00000000
69 26.08695652
70 27.14285714
71 26.76056338
72 27.77777778
73 27.39726027
74 27.02702703
75 26.66666667
76 26.31578947
77 25.97402597
78 25.64102564
79 25.31645570
80 26.25000000
81 25.92592593
82 26.82926829
83 26.50602410
84 26.19047619
85 25.88235294
86 25.58139535
87 25.28735632
88 25.00000000
89 25.84269663
90 25.55555556
91 26.37362637
92 26.08695652
93 25.80645161
94 25.53191489
95 26.31578947
96 27.08333333
97 26.80412371
98 26.53061224
99 27.27272727
100 28.00000000
101 28.71287129
102 28.43137255
103 28.15533981
104 27.88461538
105 27.61904762
106 27.35849057
107 28.03738318
108 28.70370370
109 28.44036697
110 29.09090909
111 28.82882883
112 28.57142857
113 28.31858407
114 28.94736842
115 28.69565217
116 28.44827586
117 28.20512821
118 27.96610169
119 27.73109244
120 28.33333333
121 28.92561983
122 28.68852459
123 29.26829268
124 29.03225806
125 29.60000000
126 29.36507937
127 29.13385827
128 28.90625000
129 28.68217054
130 28.46153846
131 28.24427481
132 28.03030303
133 27.81954887
134 28.35820896
135 28.88888889
136 28.67647059
137 29.19708029
138 29.71014493
139 30.21582734
140 30.00000000
141 29.78723404
142 29.57746479
143 29.37062937
144 29.86111111
145 29.65517241
146 29.45205479
147 29.25170068
148 29.05405405
149 28.85906040
150 28.66666667
151 29.13907285
152 28.94736842
153 28.75816993
154 28.57142857
155 29.03225806
156 29.48717949
157 29.29936306
158 29.74683544
159 29.55974843
160 29.37500000
161 29.19254658
162 29.01234568
163 28.83435583
164 28.65853659
165 29.09090909
166 29.51807229
167 29.34131737
168 29.16666667
169 28.99408284
170 28.82352941
171 28.65497076
172 28.48837209
173 28.32369942
174 28.73563218
175 28.57142857
176 28.40909091
177 28.24858757
178 28.08988764
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 28.19148936
189 28.57142857
190 28.42105263
191 28.27225131
192 28.64583333
193 28.49740933
194 28.86597938
195 28.71794872
196 28.57142857
197 28.93401015
198 29.29292929
199 29.14572864
200 29.00000000
201 28.85572139
202 29.20792079
203 29.06403941
204 28.92156863
205 28.78048780
206 28.64077670
207 28.98550725
208 28.84615385
209 28.70813397
210 28.57142857
211 28.43601896
212 28.30188679
213 28.16901408
214 28.03738318
215 27.90697674
216 28.24074074
217 28.11059908
218 28.44036697
219 28.31050228
220 28.18181818
221 28.05429864
222 27.92792793
223 27.80269058
224 28.12500000
225 28.00000000
226 27.87610619
227 28.19383260
228 28.07017544
229 27.94759825
230 27.82608696
231 27.70562771
232 28.01724138
233 28.32618026
234 28.63247863
235 28.51063830
236 28.81355932
237 29.11392405
238 28.99159664
239 28.87029289
240 28.75000000
241 28.63070539
242 28.51239669
243 28.39506173
244 28.27868852
245 28.16326531
246 28.04878049
247 27.93522267
248 27.82258065
249 27.71084337
250 27.60000000
251 27.88844622
252 27.77777778
253 27.66798419
254 27.55905512
255 27.84313725
256 27.73437500
257 27.62645914
258 27.51937984
259 27.41312741
260 27.30769231
261 27.58620690
262 27.48091603
263 27.37642586
264 27.65151515
265 27.92452830
266 27.81954887
267 28.08988764
268 27.98507463
269 27.88104089
270 27.77777778
271 27.67527675
272 27.57352941
273 27.47252747
274 27.73722628
275 27.63636364
276 27.53623188
277 27.43682310
278 27.33812950
279 27.24014337
280 27.50000000
281 27.75800712
282 27.65957447
283 27.56183746
284 27.81690141
285 27.71929825
286 27.97202797
287 28.22299652
288 28.12500000
289 28.02768166
290 27.93103448
291 28.17869416
292 28.08219178
293 28.32764505
294 28.23129252
295 28.47457627
296 28.71621622
297 28.95622896
298 28.85906040
299 28.76254181
300 28.66666667
301 28.57142857
302 28.47682119
303 28.38283828
304 28.28947368
305 28.19672131
306 28.10457516
307 28.01302932
308 28.24675325
309 28.15533981
310 28.06451613
311 27.97427653
312 28.20512821
313 28.11501597
314 28.34394904
315 28.25396825
316 28.16455696
317 28.07570978
318 27.98742138
319 27.89968652
320 27.81250000
321 27.72585670
322 27.95031056
323 27.86377709
324 27.77777778
325 27.69230769
326 27.60736196
327 27.82874618
328 28.04878049
329 27.96352584
330 28.18181818
331 28.09667674
332 28.31325301
333 28.22822823
334 28.14371257
335 28.35820896
336 28.57142857
337 28.48664688
338 28.40236686
339 28.61356932
340 28.52941176
341 28.73900293
342 28.65497076
343 28.57142857
344 28.77906977
345 28.98550725
346 29.19075145
347 29.39481268
348 29.31034483
349 29.22636103
350 29.14285714
351 29.05982906
352 28.97727273
353 28.89518414
354 28.81355932
355 29.01408451
356 28.93258427
357 29.13165266
358 29.32960894
359 29.24791086
360 29.16666667
361 29.36288089
362 29.28176796
363 29.47658402
364 29.39560440
365 29.58904110
366 29.50819672
367 29.70027248
368 29.61956522
369 29.53929539
370 29.45945946
371 29.38005391
372 29.56989247
373 29.49061662
374 29.67914439
375 29.60000000
376 29.52127660
377 29.44297082
378 29.36507937
379 29.28759894
380 29.47368421
381 29.39632546
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 29.15601023
392 29.08163265
393 29.26208651
394 29.44162437
395 29.36708861
396 29.29292929
397 29.47103275
398 29.39698492
399 29.32330827
400 29.25000000
401 29.17705736
402 29.35323383
403 29.52853598
404 29.45544554
405 29.38271605
406 29.55665025
407 29.48402948
408 29.41176471
409 29.33985330
410 29.26829268
411 29.19708029
412 29.36893204
413 29.29782082
414 29.46859903
415 29.63855422
416 29.56730769
417 29.49640288
418 29.42583732
419 29.35560859
420 29.52380952
421 29.69121140
422 29.62085308
423 29.55082742
424 29.48113208
425 29.41176471
426 29.34272300
427 29.27400468
428 29.20560748
429 29.37062937
430 29.30232558
431 29.23433875
432 29.39814815
433 29.56120092
434 29.72350230
435 29.65517241
436 29.58715596
437 29.51945080
438 29.45205479
439 29.38496583
440 29.31818182
441 29.25170068
442 29.18552036
443 29.11963883
444 29.27927928
445 29.21348315
446 29.14798206
447 29.08277405
448 29.01785714
449 29.17594655
450 29.33333333
451 29.26829268
452 29.20353982
453 29.13907285
454 29.29515419
455 29.23076923
456 29.16666667
457 29.10284464
458 29.03930131
459 28.97603486
460 28.91304348
461 28.85032538
462 28.78787879
463 28.94168467
464 29.09482759
465 29.24731183
466 29.18454936
467 29.12205567
468 29.27350427
469 29.21108742
470 29.14893617
471 29.29936306
472 29.23728814
473 29.17547569
474 29.11392405
475 29.26315789
476 29.20168067
477 29.35010482
478 29.28870293
479 29.22755741
480 29.16666667
481 29.10602911
482 29.25311203
483 29.19254658
484 29.33884298
485 29.48453608
486 29.42386831
487 29.56878850
488 29.50819672
489 29.65235174
490 29.79591837
491 29.93890020
492 30.08130081
493 30.02028398
494 29.95951417
495 30.10101010
496 30.04032258
497 29.97987928
498 29.91967871
499 30.06012024
500 30.00000000
501 30.13972056
502 30.07968127
503 30.01988072
504 30.15873016
505 30.09900990
506 30.03952569
507 30.17751479
508 30.31496063
509 30.45186640
510 30.58823529
511 30.52837573
512 30.46875000
513 30.40935673
514 30.35019455
515 30.48543689
516 30.42635659
517 30.56092843
518 30.50193050
519 30.44315992
520 30.38461538
521 30.32629559
522 30.26819923
523 30.21032505
524 30.15267176
525 30.09523810
526 30.03802281
527 30.17077799
528 30.11363636
529 30.05671078
530 30.00000000
531 29.94350282
532 29.88721805
533 30.01876173
534 29.96254682
535 29.90654206
536 29.85074627
537 29.98137803
538 29.92565056
539 29.87012987
540 29.81481481
541 29.75970425
542 29.70479705
543 29.65009208
544 29.59558824
545 29.54128440
546 29.67032967
547 29.79890311
548 29.92700730
549 29.87249545
550 29.81818182
551 29.76406534
552 29.89130435
553 30.01808318
554 29.96389892
555 29.90990991
556 29.85611511
557 29.80251346
558 29.74910394
559 29.69588551
560 29.82142857
561 29.94652406
562 29.89323843
563 29.84014210
564 29.96453901
565 30.08849558
566 30.21201413
567 30.15873016
568 30.28169014
569 30.40421793
570 30.35087719
571 30.29772329
572 30.24475524
573 30.19197208
574 30.31358885
575 30.43478261
576 30.38194444
577 30.32928943
578 30.44982699
579 30.39723661
580 30.51724138
581 30.46471601
582 30.58419244
583 30.53173242
584 30.65068493
585 30.59829060
586 30.71672355
587 30.66439523
588 30.61224490
589 30.56027165
590 30.67796610
591 30.62605753
592 30.57432432
593 30.52276560
594 30.47138047
595 30.42016807
596 30.36912752
597 30.31825796
598 30.26755853
599 30.21702838
600 30.16666667
601 30.28286190
602 30.23255814
603 30.34825871
604 30.29801325
605 30.24793388
606 30.36303630
607 30.31301483
608 30.26315789
609 30.21346470
610 30.16393443
611 30.11456628
612 30.22875817
613 30.17944535
614 30.13029316
615 30.08130081
616 30.19480519
617 30.30794165
618 30.25889968
619 30.37156704
620 30.32258065
621 30.27375201
622 30.38585209
623 30.33707865
624 30.28846154
625 30.24000000
626 30.19169329
627 30.30303030
628 30.25477707
629 30.20667727
630 30.15873016
631 30.26941363
632 30.22151899
633 30.17377567
634 30.28391167
635 30.23622047
636 30.18867925
637 30.14128728
638 30.09404389
639 30.04694836
640 30.00000000
641 29.95319813
642 30.06230530
643 30.01555210
644 29.96894410
645 30.07751938
646 30.03095975
647 29.98454405
648 30.09259259
649 30.04622496
650 30.15384615
651 30.26113671
652 30.36809816
653 30.47473201
654 30.42813456
655 30.38167939
656 30.48780488
657 30.59360731
658 30.54711246
659 30.65250379
660 30.60606061
661 30.55975794
662 30.51359517
663 30.46757164
664 30.42168675
665 30.37593985
666 30.48048048
667 30.43478261
668 30.38922156
669 30.34379671
670 30.44776119
671 30.40238450
672 30.35714286
673 30.31203566
674 30.26706231
675 30.37037037
676 30.47337278
677 30.42836041
678 30.38348083
679 30.33873343
680 30.29411765
681 30.24963289
682 30.20527859
683 30.16105417
684 30.26315789
685 30.21897810
686 30.17492711
687 30.13100437
688 30.08720930
689 30.18867925
690 30.14492754
691 30.24602026
692 30.34682081
693 30.44733045
694 30.40345821
695 30.35971223
696 30.45977011
697 30.41606887
698 30.37249284
699 30.32904149
700 30.28571429
701 30.24251070
702 30.19943020
703 30.15647226
704 30.11363636
705 30.07092199
706 30.02832861
707 30.12729844
708 30.08474576
709 30.04231312
710 30.00000000
711 29.95780591
712 29.91573034
713 29.87377279
714 29.97198880
715 30.06993007
716 30.02793296
717 29.98605300
718 29.94428969
719 29.90264256
720 29.86111111
721 29.81969487
722 29.77839335
723 29.73720609
724 29.83425414
725 29.79310345
726 29.88980716
727 29.84869326
728 29.80769231
729 29.90397805
730 29.86301370
731 29.82216142
732 29.91803279
733 29.87721692
734 29.83651226
735 29.79591837
736 29.75543478
737 29.85074627
738 29.81029810
739 29.90527740
740 29.86486486
741 29.95951417
742 29.91913747
743 29.87886945
744 29.97311828
745 29.93288591
746 29.89276139
747 29.98661312
748 29.94652406
749 30.04005340
750 30.13333333
Final result: 30.1333 +/- 1.6766
Random chance: 19.8992 +/- 1.4588