Hugging Face's logo

Spaces:
xiaozheyao
/
Efficient-LLM-Leaderboard
Sleeping

App Files Community
xzyao commited on
Commit
c5de046
·
verified ·
1 Parent(s): 2c4cdfe

Upload eval_results.csv

Browse files
Files changed (1) hide show
  1. eval_results.csv +491 -1
eval_results.csv CHANGED
@@ -396,6 +396,147 @@ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_extended_zeroshot,acc,0.3205
396
  meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.3482142857142857,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
397
  meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.3236607142857143,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
398
  meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_logiqa,acc,0.31797235023041476,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
399
  meta-llama/Llama-2-7b-chat-hf:W8A8_int8,task_mmlu,acc,0.4585529126904999,W8A8_int8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_int8,6476005376
400
  meta-llama/Llama-2-7b-chat-hf:W8A8_int8,task_mmlu_humanities,acc,0.4257173219978746,W8A8_int8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_int8,6476005376
401
  meta-llama/Llama-2-7b-chat-hf:W8A8_int8,task_mmlu_formal_logic,acc,0.24603174603174602,W8A8_int8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_int8,6476005376
@@ -675,6 +816,80 @@ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_extended_zeroshot,acc,0.3
675
  meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.3013392857142857,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
676
  meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.31026785714285715,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
677
  meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_logiqa,acc,0.27035330261136714,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
678
  google/gemma-2-2b-it:W4A16,task_boolq,acc,0.8333333333333334,W4A16,espressor/google.gemma-2-2b-it_W4A16,3403550048
679
  google/gemma-2-2b-it:W4A16,task_logiqa,acc,0.271889400921659,W4A16,espressor/google.gemma-2-2b-it_W4A16,3403550048
680
  google/gemma-2-2b-it:W4A16,task_piqa,acc,0.780739934711643,W4A16,espressor/google.gemma-2-2b-it_W4A16,3403550048
@@ -1089,6 +1304,73 @@ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_truthfulqa_mc1,acc,0.337821297429620
1089
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_truthfulqa_mc2,acc,0.5051760429703329,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1090
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_boolq,acc,0.8186544342507646,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1091
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_logiqa,acc,0.271889400921659,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_piqa,acc,0.7818280739934712,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1093
  meta-llama/Llama-2-7b-chat-hf:W8A8_FP8,task_boolq,acc,0.7948012232415902,W8A8_FP8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_FP8,6476005376
1094
  meta-llama/Llama-2-7b-chat-hf:W8A8_FP8,task_gpqa_diamond_n_shot,acc,0.29292929292929293,W8A8_FP8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_FP8,6476005376
@@ -1186,6 +1468,73 @@ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_logiqa,acc,0.30414746543778803,W
1186
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_openbookqa,acc,0.346,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1187
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_truthfulqa_mc1,acc,0.3659730722154223,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1188
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_truthfulqa_mc2,acc,0.5392220169800028,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1189
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu,acc,0.6754023643355648,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1190
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_humanities,acc,0.638682252922423,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1191
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_formal_logic,acc,0.46825396825396826,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
@@ -2374,6 +2723,80 @@ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_extended_zeroshot,acc,0.3351
2374
  meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.32142857142857145,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2375
  meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.28348214285714285,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2376
  meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_logiqa,acc,0.250384024577573,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2377
  google/gemma-2b-it:W8A8_FP8,task_boolq,acc,0.6327217125382263,W8A8_FP8,espressor/google.gemma-2b-it_W8A8_FP8,4080531456
2378
  google/gemma-2b-it:W8A8_FP8,task_gpqa_diamond_n_shot,acc,0.26262626262626265,W8A8_FP8,espressor/google.gemma-2b-it_W8A8_FP8,4080531456
2379
  google/gemma-2b-it:W8A8_FP8,task_gpqa_diamond_zeroshot,acc,0.2828282828282828,W8A8_FP8,espressor/google.gemma-2b-it_W8A8_FP8,4080531456
@@ -2582,4 +3005,71 @@ meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_high_school_compu
2582
  meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_high_school_mathematics,acc,0.26666666666666666,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
2583
  meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_high_school_physics,acc,0.31125827814569534,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
2584
  meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_high_school_statistics,acc,0.35648148148148145,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
2585
- meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_machine_learning,acc,0.29464285714285715,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
396
  meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.3482142857142857,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
397
  meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.3236607142857143,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
398
  meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_logiqa,acc,0.31797235023041476,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
399
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_boolq,acc,0.8406727828746178,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
400
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_logiqa,acc,0.31797235023041476,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
401
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu,acc,0.6741917105825381,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
402
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_humanities,acc,0.6359192348565356,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
403
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_formal_logic,acc,0.47619047619047616,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
404
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_european_history,acc,0.7636363636363637,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
405
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_us_history,acc,0.8480392156862745,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
406
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_world_history,acc,0.8565400843881856,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
407
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_international_law,acc,0.7933884297520661,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
408
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_jurisprudence,acc,0.7592592592592593,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
409
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_logical_fallacies,acc,0.803680981595092,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
410
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_moral_disputes,acc,0.7398843930635838,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
411
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_moral_scenarios,acc,0.5463687150837989,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
412
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_philosophy,acc,0.729903536977492,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
413
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_prehistory,acc,0.7561728395061729,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
414
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_law,acc,0.4954367666232073,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
415
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_world_religions,acc,0.8421052631578947,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
416
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_other,acc,0.7383327969102028,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
417
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_business_ethics,acc,0.69,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
418
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_clinical_knowledge,acc,0.7773584905660378,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
419
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_medicine,acc,0.6878612716763006,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
420
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_global_facts,acc,0.38,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
421
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_human_aging,acc,0.695067264573991,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
422
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_management,acc,0.8252427184466019,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
423
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_marketing,acc,0.8717948717948718,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
424
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_medical_genetics,acc,0.77,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
425
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_miscellaneous,acc,0.8403575989782887,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
426
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_nutrition,acc,0.761437908496732,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
427
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_accounting,acc,0.5354609929078015,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
428
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_medicine,acc,0.7830882352941176,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
429
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_virology,acc,0.5180722891566265,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
430
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_social_sciences,acc,0.7653558661033474,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
431
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_econometrics,acc,0.5,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
432
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_geography,acc,0.7828282828282829,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
433
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_government_and_politics,acc,0.8860103626943006,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
434
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_macroeconomics,acc,0.6717948717948717,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
435
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_microeconomics,acc,0.7605042016806722,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
436
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_psychology,acc,0.8605504587155963,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
437
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_human_sexuality,acc,0.8244274809160306,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
438
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_psychology,acc,0.7205882352941176,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
439
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_public_relations,acc,0.6727272727272727,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
440
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_security_studies,acc,0.7428571428571429,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
441
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_sociology,acc,0.845771144278607,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
442
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_us_foreign_policy,acc,0.85,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
443
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_stem,acc,0.5791309863621947,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
444
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_abstract_algebra,acc,0.37,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
445
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_anatomy,acc,0.6666666666666666,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
446
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_astronomy,acc,0.743421052631579,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
447
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_biology,acc,0.8125,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
448
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_chemistry,acc,0.44,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
449
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_computer_science,acc,0.55,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
450
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_mathematics,acc,0.34,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
451
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_physics,acc,0.4117647058823529,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
452
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_computer_security,acc,0.78,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
453
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_conceptual_physics,acc,0.574468085106383,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
454
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_electrical_engineering,acc,0.6482758620689655,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
455
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_elementary_mathematics,acc,0.48677248677248675,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
456
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_biology,acc,0.7967741935483871,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
457
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_chemistry,acc,0.625615763546798,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
458
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_computer_science,acc,0.73,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
459
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_mathematics,acc,0.4222222222222222,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
460
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_physics,acc,0.47019867549668876,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
461
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_statistics,acc,0.5462962962962963,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
462
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_machine_learning,acc,0.4732142857142857,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
463
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_openbookqa,acc,0.342,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
464
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_truthfulqa_mc1,acc,0.3574051407588739,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
465
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_truthfulqa_mc2,acc,0.536271921994008,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
466
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_boolq,acc,0.8406727828746178,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
467
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_diamond_n_shot,acc,0.3383838383838384,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
468
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_diamond_zeroshot,acc,0.31313131313131315,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
469
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_extended_n_shot,acc,0.31684981684981683,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
470
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_extended_zeroshot,acc,0.32051282051282054,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
471
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.3482142857142857,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
472
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.3236607142857143,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
473
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_logiqa,acc,0.31797235023041476,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
474
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu,acc,0.6741917105825381,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
475
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_humanities,acc,0.6359192348565356,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
476
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_formal_logic,acc,0.47619047619047616,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
477
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_european_history,acc,0.7636363636363637,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
478
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_us_history,acc,0.8480392156862745,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
479
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_world_history,acc,0.8565400843881856,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
480
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_international_law,acc,0.7933884297520661,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
481
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_jurisprudence,acc,0.7592592592592593,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
482
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_logical_fallacies,acc,0.803680981595092,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
483
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_moral_disputes,acc,0.7398843930635838,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
484
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_moral_scenarios,acc,0.5463687150837989,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
485
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_philosophy,acc,0.729903536977492,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
486
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_prehistory,acc,0.7561728395061729,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
487
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_law,acc,0.4954367666232073,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
488
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_world_religions,acc,0.8421052631578947,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
489
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_other,acc,0.7383327969102028,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
490
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_business_ethics,acc,0.69,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
491
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_clinical_knowledge,acc,0.7773584905660378,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
492
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_medicine,acc,0.6878612716763006,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
493
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_global_facts,acc,0.38,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
494
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_human_aging,acc,0.695067264573991,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
495
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_management,acc,0.8252427184466019,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
496
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_marketing,acc,0.8717948717948718,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
497
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_medical_genetics,acc,0.77,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
498
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_miscellaneous,acc,0.8403575989782887,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
499
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_nutrition,acc,0.761437908496732,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
500
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_accounting,acc,0.5354609929078015,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
501
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_medicine,acc,0.7830882352941176,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
502
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_virology,acc,0.5180722891566265,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
503
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_social_sciences,acc,0.7653558661033474,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
504
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_econometrics,acc,0.5,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
505
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_geography,acc,0.7828282828282829,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
506
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_government_and_politics,acc,0.8860103626943006,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
507
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_macroeconomics,acc,0.6717948717948717,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
508
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_microeconomics,acc,0.7605042016806722,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
509
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_psychology,acc,0.8605504587155963,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
510
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_human_sexuality,acc,0.8244274809160306,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
511
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_professional_psychology,acc,0.7205882352941176,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
512
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_public_relations,acc,0.6727272727272727,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
513
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_security_studies,acc,0.7428571428571429,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
514
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_sociology,acc,0.845771144278607,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
515
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_us_foreign_policy,acc,0.85,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
516
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_stem,acc,0.5791309863621947,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
517
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_abstract_algebra,acc,0.37,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
518
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_anatomy,acc,0.6666666666666666,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
519
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_astronomy,acc,0.743421052631579,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
520
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_biology,acc,0.8125,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
521
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_chemistry,acc,0.44,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
522
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_computer_science,acc,0.55,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
523
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_mathematics,acc,0.34,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
524
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_college_physics,acc,0.4117647058823529,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
525
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_computer_security,acc,0.78,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
526
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_conceptual_physics,acc,0.574468085106383,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
527
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_electrical_engineering,acc,0.6482758620689655,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
528
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_elementary_mathematics,acc,0.48677248677248675,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
529
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_biology,acc,0.7967741935483871,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
530
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_chemistry,acc,0.625615763546798,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
531
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_computer_science,acc,0.73,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
532
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_mathematics,acc,0.4222222222222222,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
533
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_physics,acc,0.47019867549668876,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
534
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_high_school_statistics,acc,0.5462962962962963,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
535
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_mmlu_machine_learning,acc,0.4732142857142857,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
536
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_openbookqa,acc,0.342,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
537
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_piqa,acc,0.8014145810663765,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
538
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_truthfulqa_mc1,acc,0.3574051407588739,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
539
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_FP8,task_truthfulqa_mc2,acc,0.536271921994008,W8A8_FP8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_FP8,9083953152
540
  meta-llama/Llama-2-7b-chat-hf:W8A8_int8,task_mmlu,acc,0.4585529126904999,W8A8_int8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_int8,6476005376
541
  meta-llama/Llama-2-7b-chat-hf:W8A8_int8,task_mmlu_humanities,acc,0.4257173219978746,W8A8_int8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_int8,6476005376
542
  meta-llama/Llama-2-7b-chat-hf:W8A8_int8,task_mmlu_formal_logic,acc,0.24603174603174602,W8A8_int8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_int8,6476005376
 
816
  meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.3013392857142857,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
817
  meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.31026785714285715,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
818
  meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_logiqa,acc,0.27035330261136714,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
819
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_boolq,acc,0.8314984709480122,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
820
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_diamond_n_shot,acc,0.3333333333333333,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
821
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_diamond_zeroshot,acc,0.30808080808080807,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
822
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_extended_n_shot,acc,0.3076923076923077,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
823
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_extended_zeroshot,acc,0.304029304029304,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
824
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.3013392857142857,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
825
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.31026785714285715,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
826
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_logiqa,acc,0.27035330261136714,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
827
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu,acc,0.6347386412191995,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
828
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_humanities,acc,0.5808714133900106,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
829
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_formal_logic,acc,0.48412698412698413,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
830
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_european_history,acc,0.7333333333333333,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
831
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_us_history,acc,0.8284313725490197,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
832
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_world_history,acc,0.8312236286919831,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
833
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_international_law,acc,0.7603305785123967,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
834
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_jurisprudence,acc,0.7870370370370371,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
835
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_logical_fallacies,acc,0.7668711656441718,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
836
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_moral_disputes,acc,0.708092485549133,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
837
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_moral_scenarios,acc,0.3396648044692737,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
838
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_philosophy,acc,0.7106109324758842,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
839
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_prehistory,acc,0.7345679012345679,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
840
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_professional_law,acc,0.48239895697522817,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
841
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_world_religions,acc,0.7894736842105263,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
842
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_other,acc,0.7112970711297071,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
843
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_business_ethics,acc,0.65,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
844
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_clinical_knowledge,acc,0.7132075471698113,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
845
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_college_medicine,acc,0.6358381502890174,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
846
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_global_facts,acc,0.39,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
847
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_human_aging,acc,0.6681614349775785,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
848
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_management,acc,0.8349514563106796,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
849
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_marketing,acc,0.8888888888888888,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
850
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_medical_genetics,acc,0.82,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
851
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_miscellaneous,acc,0.8058748403575989,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
852
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_nutrition,acc,0.7254901960784313,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
853
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_professional_accounting,acc,0.5319148936170213,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
854
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_professional_medicine,acc,0.7242647058823529,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
855
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_virology,acc,0.4939759036144578,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
856
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_social_sciences,acc,0.7393565160870978,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
857
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_econometrics,acc,0.5175438596491229,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
858
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_geography,acc,0.7828282828282829,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
859
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_government_and_politics,acc,0.8704663212435233,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
860
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_macroeconomics,acc,0.6384615384615384,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
861
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_microeconomics,acc,0.7016806722689075,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
862
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_psychology,acc,0.818348623853211,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
863
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_human_sexuality,acc,0.7786259541984732,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
864
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_professional_psychology,acc,0.6764705882352942,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
865
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_public_relations,acc,0.6727272727272727,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
866
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_security_studies,acc,0.7387755102040816,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
867
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_sociology,acc,0.8706467661691543,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
868
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_us_foreign_policy,acc,0.85,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
869
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_stem,acc,0.5375832540437678,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
870
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_abstract_algebra,acc,0.34,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
871
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_anatomy,acc,0.6222222222222222,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
872
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_astronomy,acc,0.6842105263157895,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
873
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_college_biology,acc,0.7361111111111112,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
874
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_college_chemistry,acc,0.46,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
875
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_college_computer_science,acc,0.54,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
876
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_college_mathematics,acc,0.32,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
877
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_college_physics,acc,0.49019607843137253,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
878
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_computer_security,acc,0.74,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
879
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_conceptual_physics,acc,0.5319148936170213,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
880
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_electrical_engineering,acc,0.6137931034482759,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
881
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_elementary_mathematics,acc,0.4312169312169312,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
882
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_biology,acc,0.7645161290322581,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
883
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_chemistry,acc,0.4482758620689655,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
884
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_computer_science,acc,0.73,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
885
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_mathematics,acc,0.3851851851851852,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
886
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_physics,acc,0.44370860927152317,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
887
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_high_school_statistics,acc,0.49537037037037035,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
888
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_mmlu_machine_learning,acc,0.49107142857142855,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
889
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_openbookqa,acc,0.334,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
890
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_piqa,acc,0.7823721436343852,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
891
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_truthfulqa_mc1,acc,0.3598531211750306,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
892
+ meta-llama/Meta-Llama-3-8B-Instruct:W8A8_FP8,task_truthfulqa_mc2,acc,0.5190318683050498,W8A8_FP8,espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_FP8,9083953152
893
  google/gemma-2-2b-it:W4A16,task_boolq,acc,0.8333333333333334,W4A16,espressor/google.gemma-2-2b-it_W4A16,3403550048
894
  google/gemma-2-2b-it:W4A16,task_logiqa,acc,0.271889400921659,W4A16,espressor/google.gemma-2-2b-it_W4A16,3403550048
895
  google/gemma-2-2b-it:W4A16,task_piqa,acc,0.780739934711643,W4A16,espressor/google.gemma-2-2b-it_W4A16,3403550048
 
1304
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_truthfulqa_mc2,acc,0.5051760429703329,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1305
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_boolq,acc,0.8186544342507646,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1306
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_logiqa,acc,0.271889400921659,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1307
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu,acc,0.6222048141290415,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1308
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_humanities,acc,0.5564293304994686,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1309
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_formal_logic,acc,0.3968253968253968,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1310
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_european_history,acc,0.6787878787878788,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1311
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_us_history,acc,0.7009803921568627,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1312
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_world_history,acc,0.7510548523206751,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1313
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_international_law,acc,0.7272727272727273,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1314
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_jurisprudence,acc,0.75,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1315
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_logical_fallacies,acc,0.7730061349693251,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1316
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_moral_disputes,acc,0.7196531791907514,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1317
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_moral_scenarios,acc,0.4100558659217877,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1318
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_philosophy,acc,0.6527331189710611,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1319
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_prehistory,acc,0.7283950617283951,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1320
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_professional_law,acc,0.42242503259452413,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1321
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_world_religions,acc,0.8011695906432749,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1322
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_other,acc,0.6964917927261024,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1323
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_business_ethics,acc,0.67,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1324
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_clinical_knowledge,acc,0.7320754716981132,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1325
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_college_medicine,acc,0.630057803468208,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1326
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_global_facts,acc,0.33,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1327
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_human_aging,acc,0.6591928251121076,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1328
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_management,acc,0.8349514563106796,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1329
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_marketing,acc,0.8547008547008547,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1330
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_medical_genetics,acc,0.75,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1331
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_miscellaneous,acc,0.8135376756066411,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1332
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_nutrition,acc,0.7287581699346405,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1333
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_professional_accounting,acc,0.48936170212765956,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1334
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_professional_medicine,acc,0.6213235294117647,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1335
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_virology,acc,0.5180722891566265,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1336
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_social_sciences,acc,0.731556711082223,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1337
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_econometrics,acc,0.45614035087719296,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1338
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_geography,acc,0.797979797979798,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1339
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_government_and_politics,acc,0.8601036269430051,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1340
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_macroeconomics,acc,0.6128205128205129,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1341
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_microeconomics,acc,0.7226890756302521,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1342
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_psychology,acc,0.818348623853211,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1343
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_human_sexuality,acc,0.7480916030534351,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1344
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_professional_psychology,acc,0.684640522875817,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1345
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_public_relations,acc,0.6181818181818182,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1346
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_security_studies,acc,0.7591836734693878,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1347
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_sociology,acc,0.8159203980099502,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1348
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_us_foreign_policy,acc,0.83,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1349
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_stem,acc,0.5404376784015223,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1350
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_abstract_algebra,acc,0.42,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1351
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_anatomy,acc,0.6814814814814815,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1352
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_astronomy,acc,0.7039473684210527,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1353
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_college_biology,acc,0.7291666666666666,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1354
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_college_chemistry,acc,0.43,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1355
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_college_computer_science,acc,0.51,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1356
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_college_mathematics,acc,0.28,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1357
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_college_physics,acc,0.47058823529411764,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1358
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_computer_security,acc,0.76,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1359
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_conceptual_physics,acc,0.5659574468085107,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1360
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_electrical_engineering,acc,0.5862068965517241,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1361
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_elementary_mathematics,acc,0.4603174603174603,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1362
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_biology,acc,0.7516129032258064,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1363
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_chemistry,acc,0.5369458128078818,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1364
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_computer_science,acc,0.65,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1365
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_mathematics,acc,0.34074074074074073,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1366
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_physics,acc,0.4304635761589404,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1367
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_high_school_statistics,acc,0.5092592592592593,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1368
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_mmlu_machine_learning,acc,0.4107142857142857,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1369
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_openbookqa,acc,0.318,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1370
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_truthfulqa_mc1,acc,0.3378212974296206,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1371
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_truthfulqa_mc2,acc,0.5051760429703329,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1372
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_boolq,acc,0.8186544342507646,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1373
+ meta-llama/Llama-3.1-8B-Instruct:W4A16,task_logiqa,acc,0.271889400921659,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1374
  meta-llama/Llama-3.1-8B-Instruct:W4A16,task_piqa,acc,0.7818280739934712,W4A16,espressor/meta-llama.Llama-3.1-8B-Instruct_W4A16,5700595200
1375
  meta-llama/Llama-2-7b-chat-hf:W8A8_FP8,task_boolq,acc,0.7948012232415902,W8A8_FP8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_FP8,6476005376
1376
  meta-llama/Llama-2-7b-chat-hf:W8A8_FP8,task_gpqa_diamond_n_shot,acc,0.29292929292929293,W8A8_FP8,espressor/meta-llama.Llama-2-7b-chat-hf_W8A8_FP8,6476005376
 
1468
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_openbookqa,acc,0.346,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1469
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_truthfulqa_mc1,acc,0.3659730722154223,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1470
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_truthfulqa_mc2,acc,0.5392220169800028,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1471
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_boolq,acc,0.8403669724770643,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1472
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_logiqa,acc,0.30414746543778803,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1473
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu,acc,0.6754023643355648,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1474
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_humanities,acc,0.638682252922423,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1475
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_formal_logic,acc,0.46825396825396826,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1476
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_european_history,acc,0.7515151515151515,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1477
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_us_history,acc,0.8186274509803921,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1478
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_world_history,acc,0.8481012658227848,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1479
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_international_law,acc,0.7933884297520661,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1480
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_jurisprudence,acc,0.7685185185185185,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1481
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_logical_fallacies,acc,0.7791411042944786,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1482
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_moral_disputes,acc,0.7196531791907514,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1483
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_moral_scenarios,acc,0.5899441340782123,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1484
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_philosophy,acc,0.7202572347266881,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1485
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_prehistory,acc,0.7530864197530864,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1486
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_professional_law,acc,0.49869621903520206,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1487
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_world_religions,acc,0.8070175438596491,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1488
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_other,acc,0.7396202124235597,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1489
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_business_ethics,acc,0.69,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1490
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_clinical_knowledge,acc,0.7622641509433963,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1491
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_college_medicine,acc,0.6878612716763006,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1492
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_global_facts,acc,0.41,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1493
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_human_aging,acc,0.6681614349775785,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1494
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_management,acc,0.8349514563106796,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1495
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_marketing,acc,0.8888888888888888,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1496
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_medical_genetics,acc,0.81,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1497
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_miscellaneous,acc,0.8403575989782887,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1498
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_nutrition,acc,0.7679738562091504,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1499
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_professional_accounting,acc,0.5531914893617021,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1500
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_professional_medicine,acc,0.7647058823529411,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1501
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_virology,acc,0.5180722891566265,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1502
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_social_sciences,acc,0.7647058823529411,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1503
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_econometrics,acc,0.5087719298245614,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1504
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_geography,acc,0.7929292929292929,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1505
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_government_and_politics,acc,0.8601036269430051,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1506
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_macroeconomics,acc,0.6794871794871795,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1507
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_microeconomics,acc,0.7773109243697479,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1508
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_psychology,acc,0.8532110091743119,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1509
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_human_sexuality,acc,0.8091603053435115,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1510
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_professional_psychology,acc,0.7173202614379085,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1511
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_public_relations,acc,0.6636363636363637,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1512
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_security_studies,acc,0.7551020408163265,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1513
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_sociology,acc,0.8407960199004975,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1514
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_us_foreign_policy,acc,0.85,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1515
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_stem,acc,0.5797653028861401,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1516
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_abstract_algebra,acc,0.35,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1517
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_anatomy,acc,0.7037037037037037,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1518
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_astronomy,acc,0.7763157894736842,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1519
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_college_biology,acc,0.8055555555555556,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1520
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_college_chemistry,acc,0.46,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1521
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_college_computer_science,acc,0.52,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1522
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_college_mathematics,acc,0.35,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1523
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_college_physics,acc,0.4019607843137255,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1524
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_computer_security,acc,0.74,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1525
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_conceptual_physics,acc,0.6042553191489362,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1526
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_electrical_engineering,acc,0.6413793103448275,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1527
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_elementary_mathematics,acc,0.48677248677248675,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1528
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_biology,acc,0.8129032258064516,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1529
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_chemistry,acc,0.6157635467980296,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1530
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_computer_science,acc,0.72,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1531
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_mathematics,acc,0.4,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1532
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_physics,acc,0.44370860927152317,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1533
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_high_school_statistics,acc,0.5416666666666666,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1534
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_machine_learning,acc,0.5,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1535
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_openbookqa,acc,0.346,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1536
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_truthfulqa_mc1,acc,0.3659730722154223,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1537
+ meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_truthfulqa_mc2,acc,0.5392220169800028,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1538
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu,acc,0.6754023643355648,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1539
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_humanities,acc,0.638682252922423,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
1540
  meta-llama/Llama-3.1-8B-Instruct:W8A8_int8,task_mmlu_formal_logic,acc,0.46825396825396826,W8A8_int8,espressor/meta-llama.Llama-3.1-8B-Instruct_W8A8_int8,9083953152
 
2723
  meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.32142857142857145,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2724
  meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.28348214285714285,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2725
  meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_logiqa,acc,0.250384024577573,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2726
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu,acc,0.5977068793619142,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2727
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_humanities,acc,0.5844845908607864,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2728
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_formal_logic,acc,0.3412698412698413,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2729
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_european_history,acc,0.7212121212121212,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2730
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_us_history,acc,0.7450980392156863,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2731
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_world_history,acc,0.7763713080168776,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2732
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_international_law,acc,0.743801652892562,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2733
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_jurisprudence,acc,0.6203703703703703,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2734
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_logical_fallacies,acc,0.7055214723926381,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2735
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_moral_disputes,acc,0.6416184971098265,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2736
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_moral_scenarios,acc,0.5698324022346368,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2737
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_philosophy,acc,0.6720257234726688,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2738
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_prehistory,acc,0.6512345679012346,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2739
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_professional_law,acc,0.4556714471968709,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2740
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_world_religions,acc,0.7543859649122807,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2741
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_other,acc,0.663018989378822,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2742
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_business_ethics,acc,0.58,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2743
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_clinical_knowledge,acc,0.6339622641509434,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2744
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_college_medicine,acc,0.5953757225433526,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2745
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_global_facts,acc,0.33,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2746
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_human_aging,acc,0.5695067264573991,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2747
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_management,acc,0.7572815533980582,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2748
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_marketing,acc,0.8803418803418803,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2749
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_medical_genetics,acc,0.71,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2750
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_miscellaneous,acc,0.7675606641123882,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2751
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_nutrition,acc,0.6633986928104575,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2752
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_professional_accounting,acc,0.4645390070921986,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2753
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_professional_medicine,acc,0.75,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2754
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_virology,acc,0.463855421686747,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2755
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_social_sciences,acc,0.6590835229119272,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2756
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_econometrics,acc,0.38596491228070173,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2757
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_geography,acc,0.7070707070707071,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2758
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_government_and_politics,acc,0.7461139896373057,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2759
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_macroeconomics,acc,0.5538461538461539,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2760
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_microeconomics,acc,0.592436974789916,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2761
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_psychology,acc,0.7651376146788991,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2762
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_human_sexuality,acc,0.6870229007633588,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2763
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_professional_psychology,acc,0.5931372549019608,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2764
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_public_relations,acc,0.6181818181818182,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2765
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_security_studies,acc,0.6571428571428571,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2766
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_sociology,acc,0.8059701492537313,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2767
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_us_foreign_policy,acc,0.82,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2768
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_stem,acc,0.4931810973675864,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2769
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_abstract_algebra,acc,0.29,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2770
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_anatomy,acc,0.5703703703703704,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2771
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_astronomy,acc,0.6776315789473685,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2772
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_college_biology,acc,0.7083333333333334,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2773
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_college_chemistry,acc,0.36,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2774
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_college_computer_science,acc,0.48,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2775
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_college_mathematics,acc,0.32,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2776
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_college_physics,acc,0.3431372549019608,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2777
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_computer_security,acc,0.7,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2778
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_conceptual_physics,acc,0.4978723404255319,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2779
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_electrical_engineering,acc,0.5862068965517241,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2780
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_elementary_mathematics,acc,0.3915343915343915,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2781
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_biology,acc,0.7064516129032258,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2782
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_chemistry,acc,0.5467980295566502,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2783
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_computer_science,acc,0.58,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2784
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_mathematics,acc,0.3333333333333333,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2785
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_physics,acc,0.36423841059602646,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2786
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_high_school_statistics,acc,0.3888888888888889,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2787
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_mmlu_machine_learning,acc,0.5,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2788
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_openbookqa,acc,0.278,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2789
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_piqa,acc,0.7540805223068553,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2790
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_truthfulqa_mc1,acc,0.31701346389228885,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2791
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_truthfulqa_mc2,acc,0.49237827622660857,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2792
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_boolq,acc,0.7804281345565749,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2793
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_diamond_n_shot,acc,0.29292929292929293,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2794
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_diamond_zeroshot,acc,0.3181818181818182,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2795
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_extended_n_shot,acc,0.29120879120879123,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2796
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_extended_zeroshot,acc,0.33516483516483514,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2797
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_main_n_shot,acc,0.32142857142857145,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2798
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_gpqa_main_zeroshot,acc,0.28348214285714285,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2799
+ meta-llama/Llama-3.2-3B-Instruct:W8A8_FP8,task_logiqa,acc,0.250384024577573,W8A8_FP8,espressor/meta-llama.Llama-3.2-3B-Instruct_W8A8_FP8,4396480512
2800
  google/gemma-2b-it:W8A8_FP8,task_boolq,acc,0.6327217125382263,W8A8_FP8,espressor/google.gemma-2b-it_W8A8_FP8,4080531456
2801
  google/gemma-2b-it:W8A8_FP8,task_gpqa_diamond_n_shot,acc,0.26262626262626265,W8A8_FP8,espressor/google.gemma-2b-it_W8A8_FP8,4080531456
2802
  google/gemma-2b-it:W8A8_FP8,task_gpqa_diamond_zeroshot,acc,0.2828282828282828,W8A8_FP8,espressor/google.gemma-2b-it_W8A8_FP8,4080531456
 
3005
  meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_high_school_mathematics,acc,0.26666666666666666,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
3006
  meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_high_school_physics,acc,0.31125827814569534,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
3007
  meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_high_school_statistics,acc,0.35648148148148145,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
3008
+ meta-llama/Llama-3.2-1B-Instruct:Default (bf16/fp16),task_mmlu_machine_learning,acc,0.29464285714285715,Default (bf16/fp16),meta-llama/Llama-3.2-1B-Instruct,2471628800
3009
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_boolq,acc,0.8409785932721713,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3010
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_logiqa,acc,0.3195084485407066,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3011
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu,acc,0.679532830081185,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3012
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_humanities,acc,0.6437832093517535,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3013
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_formal_logic,acc,0.46825396825396826,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3014
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_european_history,acc,0.7575757575757576,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3015
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_us_history,acc,0.8382352941176471,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3016
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_world_history,acc,0.8565400843881856,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3017
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_international_law,acc,0.8181818181818182,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3018
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_jurisprudence,acc,0.7777777777777778,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3019
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_logical_fallacies,acc,0.803680981595092,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3020
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_moral_disputes,acc,0.7485549132947977,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3021
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_moral_scenarios,acc,0.5743016759776536,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3022
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_philosophy,acc,0.7234726688102894,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3023
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_prehistory,acc,0.7438271604938271,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3024
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_professional_law,acc,0.5052151238591917,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3025
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_world_religions,acc,0.8362573099415205,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3026
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_other,acc,0.7431606050852912,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3027
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_business_ethics,acc,0.69,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3028
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_clinical_knowledge,acc,0.7924528301886793,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3029
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_college_medicine,acc,0.6936416184971098,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3030
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_global_facts,acc,0.38,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3031
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_human_aging,acc,0.7040358744394619,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3032
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_management,acc,0.8058252427184466,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3033
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_marketing,acc,0.8931623931623932,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3034
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_medical_genetics,acc,0.78,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3035
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_miscellaneous,acc,0.8403575989782887,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3036
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_nutrition,acc,0.7647058823529411,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3037
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_professional_accounting,acc,0.549645390070922,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3038
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_professional_medicine,acc,0.7830882352941176,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3039
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_virology,acc,0.5120481927710844,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3040
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_social_sciences,acc,0.7686057848553787,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3041
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_econometrics,acc,0.5,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3042
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_geography,acc,0.803030303030303,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3043
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_government_and_politics,acc,0.8756476683937824,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3044
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_macroeconomics,acc,0.6692307692307692,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3045
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_microeconomics,acc,0.7941176470588235,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3046
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_psychology,acc,0.8605504587155963,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3047
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_human_sexuality,acc,0.7938931297709924,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3048
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_professional_psychology,acc,0.7205882352941176,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3049
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_public_relations,acc,0.6727272727272727,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3050
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_security_studies,acc,0.746938775510204,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3051
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_sociology,acc,0.8557213930348259,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3052
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_us_foreign_policy,acc,0.87,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3053
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_stem,acc,0.5832540437678402,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3054
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_abstract_algebra,acc,0.34,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3055
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_anatomy,acc,0.6814814814814815,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3056
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_astronomy,acc,0.7631578947368421,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3057
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_college_biology,acc,0.8055555555555556,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3058
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_college_chemistry,acc,0.47,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3059
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_college_computer_science,acc,0.59,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3060
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_college_mathematics,acc,0.34,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3061
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_college_physics,acc,0.4411764705882353,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3062
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_computer_security,acc,0.75,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3063
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_conceptual_physics,acc,0.5957446808510638,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3064
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_electrical_engineering,acc,0.6551724137931034,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3065
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_elementary_mathematics,acc,0.48412698412698413,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3066
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_biology,acc,0.8064516129032258,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3067
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_chemistry,acc,0.6403940886699507,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3068
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_computer_science,acc,0.74,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3069
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_mathematics,acc,0.4148148148148148,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3070
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_physics,acc,0.44370860927152317,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3071
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_high_school_statistics,acc,0.5370370370370371,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3072
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_mmlu_machine_learning,acc,0.48214285714285715,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3073
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_openbookqa,acc,0.336,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3074
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_truthfulqa_mc1,acc,0.36964504283965727,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496
3075
+ meta-llama/Llama-3.1-8B-Instruct:Default (bf16/fp16),task_truthfulqa_mc2,acc,0.5406019556048346,Default (bf16/fp16),meta-llama/Llama-3.1-8B-Instruct,16060522496