Upload folder using huggingface_hub

results/cross_lingual/few_shot/cross_logiqa.csv

@@ -1,2 +1,4 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Meta-Llama-3-70B,0.6152597402597404,0.49480519480519464,0.5484971301967684,0.7272727272727273,0.6534090909090909,0.625,0.5681818181818182,0.6136363636363636,0.5795454545454546,0.5397727272727273
 Meta-Llama-3-8B,0.44967532467532456,0.2623376623376623,0.33136129711503204,0.5227272727272727,0.4431818181818182,0.44886363636363635,0.44886363636363635,0.3693181818181818,0.4602272727272727,0.45454545454545453
+Meta-Llama-3.1-8B,0.46266233766233766,0.277435064935065,0.34686989908229837,0.5284090909090909,0.5,0.4375,0.4772727272727273,0.4318181818181818,0.4431818181818182,0.42045454545454547

results/cross_lingual/few_shot/cross_mmlu.csv

@@ -1,2 +1,4 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Meta-Llama-3-70B,0.7552380952380952,0.6674285714285715,0.708623453080271,0.8066666666666666,0.7266666666666667,0.7866666666666666,0.7533333333333333,0.7733333333333333,0.72,0.72
 Meta-Llama-3-8B,0.5295238095238096,0.31923809523809527,0.3983311959862401,0.6266666666666667,0.5466666666666666,0.56,0.4866666666666667,0.5266666666666666,0.5,0.46
+Meta-Llama-3.1-8B,0.5342857142857141,0.2960000000000001,0.3809497590731823,0.6733333333333333,0.5533333333333333,0.5133333333333333,0.47333333333333333,0.5133333333333333,0.5,0.5133333333333333

results/cross_lingual/few_shot/cross_xquad.csv

@@ -1,3 +1,4 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
 Meta-Llama-3-70B,0.9596638655462185,0.9359243697478992,0.9476454662047799,0.9697478991596639,0.9504201680672268,0.957983193277311,0.9605042016806723,,,
 Meta-Llama-3-8B,0.8928571428571429,0.8163865546218487,0.8529112234365448,0.926890756302521,0.8823529411764706,0.888235294117647,0.8739495798319328,,,
+Meta-Llama-3.1-8B,0.9052521008403361,0.8355042016806722,0.8689808363106925,0.9352941176470588,0.8932773109243698,0.9,0.892436974789916,,,

results/cross_lingual/zero_shot/cross_logiqa.csv

@@ -1,5 +1,6 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
 Qwen2-7B-Instruct,0.5673701298701299,0.477922077922078,0.5188189663543613,0.6590909090909091,0.6704545454545454,0.5340909090909091,0.5625,0.5340909090909091,0.5397727272727273,0.4715909090909091
+Meta-Llama-3.1-8B-Instruct,0.43993506493506496,0.33425324675324675,0.37988102268160845,0.5113636363636364,0.45454545454545453,0.4772727272727273,0.48295454545454547,0.3977272727272727,0.39204545454545453,0.36363636363636365
 Qwen2-72B-Instruct,0.6753246753246753,0.6814935064935067,0.6783950674333673,0.75,0.8125,0.6647727272727273,0.6136363636363636,0.6420454545454546,0.6590909090909091,0.5852272727272727
 Meta-Llama-3-8B-Instruct,0.4115259740259741,0.34042207792207796,0.3726122484532397,0.48863636363636365,0.4659090909090909,0.42613636363636365,0.4034090909090909,0.4034090909090909,0.36363636363636365,0.32954545454545453
 Meta-Llama-3-70B-Instruct,0.6290584415584416,0.6181818181818182,0.6235727047409828,0.6988636363636364,0.6875,0.6420454545454546,0.6193181818181818,0.6022727272727273,0.6136363636363636,0.5397727272727273

results/cross_lingual/zero_shot/cross_mmlu.csv

@@ -1,5 +1,6 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
 Qwen2-7B-Instruct,0.6495238095238095,0.529714285714286,0.5835327779462245,0.74,0.6733333333333333,0.7,0.6,0.6533333333333333,0.6333333333333333,0.5466666666666666
+Meta-Llama-3.1-8B-Instruct,0.5771428571428572,0.47047619047619055,0.5183792207297393,0.6933333333333334,0.5333333333333333,0.6266666666666667,0.54,0.54,0.54,0.5666666666666667
 Qwen2-72B-Instruct,0.7714285714285715,0.7765714285714286,0.773991456997936,0.8,0.78,0.7866666666666666,0.7333333333333333,0.76,0.78,0.76
 Meta-Llama-3-8B-Instruct,0.5276190476190475,0.3792380952380953,0.4412894449458876,0.62,0.5066666666666667,0.5066666666666667,0.5466666666666666,0.49333333333333335,0.52,0.5
 Meta-Llama-3-70B-Instruct,0.7542857142857143,0.7228571428571428,0.7382370820168919,0.7933333333333333,0.74,0.7666666666666667,0.7466666666666667,0.7666666666666667,0.72,0.7466666666666667

results/cross_lingual/zero_shot/cross_xquad.csv

@@ -1,5 +1,6 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
 Qwen2-7B-Instruct,0.940546218487395,0.9016806722689076,0.9207034712119446,0.9521008403361344,0.9352941176470588,0.9445378151260504,0.9302521008403362,,,
+Meta-Llama-3.1-8B-Instruct,0.9340336134453782,0.8831932773109243,0.9079022683718587,0.9369747899159664,0.9302521008403362,0.946218487394958,0.9226890756302522,,,
 Qwen2-72B-Instruct,0.9611344537815126,0.9506302521008403,0.9558534951942531,0.9638655462184874,0.9554621848739496,0.9613445378151261,0.9638655462184874,,,
 Meta-Llama-3-8B-Instruct,0.8756302521008403,0.7699579831932772,0.8194012188828194,0.8815126050420168,0.8420168067226891,0.9092436974789916,0.8697478991596639,,,
 Meta-Llama-3-70B-Instruct,0.9586134453781513,0.9434873949579832,0.9509902767764395,0.9705882352941176,0.9394957983193277,0.9596638655462185,0.9647058823529412,,,

results/cultural_reasoning/few_shot/cn_eval.csv

@@ -1,2 +1,4 @@
 Model,Accuracy
+Meta-Llama-3-70B,0.6
 Meta-Llama-3-8B,0.41904761904761906
+Meta-Llama-3.1-8B,0.4857142857142857

results/cultural_reasoning/few_shot/ph_eval.csv

@@ -1,2 +1,4 @@
 Model,Accuracy
+Meta-Llama-3-70B,0.68
 Meta-Llama-3-8B,0.54
+Meta-Llama-3.1-8B,0.51

results/cultural_reasoning/few_shot/sg_eval.csv

@@ -1,3 +1,4 @@
 Model,Accuracy
 Meta-Llama-3-70B,0.7572815533980582
 Meta-Llama-3-8B,0.6407766990291263
+Meta-Llama-3.1-8B,0.6116504854368932

results/cultural_reasoning/few_shot/us_eval.csv

@@ -1,2 +1,4 @@
 Model,Accuracy
+Meta-Llama-3-70B,0.8785046728971962
 Meta-Llama-3-8B,0.6915887850467289
+Meta-Llama-3.1-8B,0.6728971962616822

results/cultural_reasoning/zero_shot/cn_eval.csv

@@ -1,5 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.8095238095238095
+Meta-Llama-3.1-8B-Instruct,0.42857142857142855
 Qwen2-72B-Instruct,0.8571428571428571
 Meta-Llama-3-8B-Instruct,0.37142857142857144
 Meta-Llama-3-70B-Instruct,0.5142857142857142

results/cultural_reasoning/zero_shot/ph_eval.csv

@@ -1,5 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.51
+Meta-Llama-3.1-8B-Instruct,0.56
 Qwen2-72B-Instruct,0.63
 Meta-Llama-3-8B-Instruct,0.54
 Meta-Llama-3-70B-Instruct,0.63

results/cultural_reasoning/zero_shot/sg_eval.csv

@@ -1,5 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.6699029126213593
+Meta-Llama-3.1-8B-Instruct,0.6019417475728155
 Qwen2-72B-Instruct,0.7378640776699029
 Meta-Llama-3-8B-Instruct,0.5922330097087378
 Meta-Llama-3-70B-Instruct,0.7184466019417476

results/cultural_reasoning/zero_shot/us_eval.csv

@@ -1,5 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.719626168224299
+Meta-Llama-3.1-8B-Instruct,0.6448598130841121
 Qwen2-72B-Instruct,0.8504672897196262
 Meta-Llama-3-8B-Instruct,0.6448598130841121
 Meta-Llama-3-70B-Instruct,0.8691588785046729

results/dialogue/few_shot/dream.csv

@@ -1 +1,3 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.8250857422831945
+Meta-Llama-3.1-8B,0.8530132288094071

results/dialogue/zero_shot/dialogsum.csv

@@ -1,4 +1,6 @@
 Model,Average,ROUGE-1,ROUGE-2,ROUGE-L
 Qwen2-7B-Instruct,0.20907406151501814,0.3054588156947843,0.09317750879187732,0.22858586005839285
+Meta-Llama-3.1-8B-Instruct,0.25775524210830225,0.361264483769506,0.1319601664036931,0.28004107615170776
+Qwen2-72B-Instruct,0.21903635116217549,0.31670807543803475,0.10250931612356096,0.23789166192493072
 Meta-Llama-3-8B-Instruct,0.23748034560689027,0.33656243928704743,0.11826169056076426,0.2576169069728591
 Meta-Llama-3-70B-Instruct,0.2557065499979308,0.36058417323628,0.12758087337786866,0.2789546033796438

results/dialogue/zero_shot/dream.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.9338559529642332
+Meta-Llama-3.1-8B-Instruct,0.8858402743753062
+Qwen2-72B-Instruct,0.9608035276825085
 Meta-Llama-3-8B-Instruct,0.5433610975012249
 Meta-Llama-3-70B-Instruct,0.9480646741793238

results/dialogue/zero_shot/samsum.csv

@@ -1,4 +1,6 @@
 Model,Average,ROUGE-1,ROUGE-2,ROUGE-L
 Qwen2-7B-Instruct,0.2609036529701212,0.36802926348230236,0.1319027531874975,0.28277894224056366
+Meta-Llama-3.1-8B-Instruct,0.3002534894623792,0.41234119292969856,0.16596515741670248,0.3224541180407366
+Qwen2-72B-Instruct,0.27953180135225114,0.3883786925058577,0.15246657328712612,0.2977501382637696
 Meta-Llama-3-8B-Instruct,0.2850232460296334,0.3945214081577773,0.15619034353394273,0.3043579863971803
 Meta-Llama-3-70B-Instruct,0.2893525314227379,0.4030746211134018,0.15236139065578,0.3126215824990321

results/emotion/few_shot/ind_emotion.csv

@@ -1 +1,3 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.4636363636363636
+Meta-Llama-3.1-8B,0.5136363636363637

results/emotion/few_shot/sst2.csv

@@ -1 +1,3 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.6697247706422018
+Meta-Llama-3.1-8B,0.8405963302752294

results/emotion/zero_shot/ind_emotion.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.6386363636363637
+Meta-Llama-3.1-8B-Instruct,0.6295454545454545
+Qwen2-72B-Instruct,0.675
 Meta-Llama-3-8B-Instruct,0.6522727272727272
 Meta-Llama-3-70B-Instruct,0.6909090909090909

results/emotion/zero_shot/sst2.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.9231651376146789
+Meta-Llama-3.1-8B-Instruct,0.8784403669724771
+Qwen2-72B-Instruct,0.9392201834862385
 Meta-Llama-3-8B-Instruct,0.8669724770642202
 Meta-Llama-3-70B-Instruct,0.9495412844036697

results/flores_translation/few_shot/ind2eng.csv

@@ -1,2 +1,4 @@
 Model,BLEU
+Meta-Llama-3-70B,0.4224655367668861
 Meta-Llama-3-8B,0.37760317005449096
+Meta-Llama-3.1-8B,0.384092499597103

results/flores_translation/few_shot/vie2eng.csv

@@ -1,2 +1,4 @@
 Model,BLEU
+Meta-Llama-3-70B,0.3564689224836266
 Meta-Llama-3-8B,0.31157996445764863
+Meta-Llama-3.1-8B,0.320367356810332

results/flores_translation/few_shot/zho2eng.csv

@@ -1,2 +1,4 @@
 Model,BLEU
+Meta-Llama-3-70B,0.27798501796196434
 Meta-Llama-3-8B,0.23710858530408072
+Meta-Llama-3.1-8B,0.23777256698409086

results/flores_translation/few_shot/zsm2eng.csv

@@ -1,2 +1,4 @@
 Model,BLEU
+Meta-Llama-3-70B,0.44357168236218214
 Meta-Llama-3-8B,0.3908770132718593
+Meta-Llama-3.1-8B,0.3893813156403672

results/flores_translation/zero_shot/ind2eng.csv

@@ -1,4 +1,6 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.2968667083646938
+Meta-Llama-3.1-8B-Instruct,0.3851478947359834
+Qwen2-72B-Instruct,0.40378146176265345
 Meta-Llama-3-8B-Instruct,0.33011728860318257
 Meta-Llama-3-70B-Instruct,0.3830092775167675

results/flores_translation/zero_shot/vie2eng.csv

@@ -1,4 +1,6 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.23571859325121644
+Meta-Llama-3.1-8B-Instruct,0.3229889780558947
+Qwen2-72B-Instruct,0.3326034551014482
 Meta-Llama-3-8B-Instruct,0.2637063711923046
 Meta-Llama-3-70B-Instruct,0.3230140263371192

results/flores_translation/zero_shot/zho2eng.csv

@@ -1,4 +1,6 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.21747115262398484
+Meta-Llama-3.1-8B-Instruct,0.24469097639356438
+Qwen2-72B-Instruct,0.24317967002278634
 Meta-Llama-3-8B-Instruct,0.19960072119079214
 Meta-Llama-3-70B-Instruct,0.24397819518058994

results/flores_translation/zero_shot/zsm2eng.csv

@@ -1,4 +1,6 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.27198336767927184
+Meta-Llama-3.1-8B-Instruct,0.3833985449157327
+Qwen2-72B-Instruct,0.40613262295280417
 Meta-Llama-3-8B-Instruct,0.31536374302282033
 Meta-Llama-3-70B-Instruct,0.3957287030176054

results/fundamental_nlp_tasks/few_shot/c3.csv

@@ -1 +1,3 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.7703814510097232
+Meta-Llama-3.1-8B,0.8208676140613314

results/fundamental_nlp_tasks/few_shot/cola.csv

@@ -1 +1,3 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.6596356663470757
+Meta-Llama-3.1-8B,0.6222435282837967

results/fundamental_nlp_tasks/few_shot/mnli.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.46174988547869905

results/fundamental_nlp_tasks/few_shot/mrpc.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.5906862745098039

results/fundamental_nlp_tasks/few_shot/ocnli.csv

@@ -1 +1,3 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.3935593220338983
+Meta-Llama-3.1-8B,0.411864406779661

results/fundamental_nlp_tasks/few_shot/qnli.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.5059491122094087

results/fundamental_nlp_tasks/few_shot/qqp.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.551

results/fundamental_nlp_tasks/few_shot/rte.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.5487364620938628

results/fundamental_nlp_tasks/few_shot/wnli.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.4647887323943662

results/fundamental_nlp_tasks/zero_shot/c3.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.9233358264771877
+Meta-Llama-3.1-8B-Instruct,0.7984293193717278
+Qwen2-72B-Instruct,0.9599850411368736
 Meta-Llama-3-8B-Instruct,0.8515332834704562
 Meta-Llama-3-70B-Instruct,0.9521316379955124

results/fundamental_nlp_tasks/zero_shot/cola.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7861936720997124
+Meta-Llama-3.1-8B-Instruct,0.7046979865771812
+Qwen2-72B-Instruct,0.8360498561840843
 Meta-Llama-3-8B-Instruct,0.6481303930968361
 Meta-Llama-3-70B-Instruct,0.835091083413231

results/fundamental_nlp_tasks/zero_shot/mnli.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7341578867002596
+Meta-Llama-3.1-8B-Instruct,0.4603756298671553
+Qwen2-72B-Instruct,0.7979335267470861
 Meta-Llama-3-8B-Instruct,0.5296991907161399
 Meta-Llama-3-70B-Instruct,0.6709421285692472

results/fundamental_nlp_tasks/zero_shot/mrpc.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7745098039215687
+Meta-Llama-3.1-8B-Instruct,0.6740196078431373
+Qwen2-72B-Instruct,0.7941176470588235
 Meta-Llama-3-8B-Instruct,0.6764705882352942
 Meta-Llama-3-70B-Instruct,0.7598039215686274

results/fundamental_nlp_tasks/zero_shot/ocnli.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.6474576271186441
+Meta-Llama-3.1-8B-Instruct,0.42135593220338985
+Qwen2-72B-Instruct,0.7874576271186441
 Meta-Llama-3-8B-Instruct,0.4322033898305085
 Meta-Llama-3-70B-Instruct,0.5928813559322034

results/fundamental_nlp_tasks/zero_shot/qnli.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.8169503935566539
+Meta-Llama-3.1-8B-Instruct,0.6027823540179389
+Qwen2-72B-Instruct,0.8894380377082189
 Meta-Llama-3-8B-Instruct,0.5689181768259198
 Meta-Llama-3-70B-Instruct,0.876807614863628

results/fundamental_nlp_tasks/zero_shot/qqp.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7771209497897601
+Meta-Llama-3.1-8B-Instruct,0.5058125154588177
+Qwen2-72B-Instruct,0.7992332426416028
 Meta-Llama-3-8B-Instruct,0.5512490724709375
 Meta-Llama-3-70B-Instruct,0.7876082117239673

results/fundamental_nlp_tasks/zero_shot/rte.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.8411552346570397
+Meta-Llama-3.1-8B-Instruct,0.6895306859205776
+Qwen2-72B-Instruct,0.8592057761732852
 Meta-Llama-3-8B-Instruct,0.6028880866425993
 Meta-Llama-3-70B-Instruct,0.8086642599277978

results/fundamental_nlp_tasks/zero_shot/wnli.csv

@@ -1,4 +1,6 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.647887323943662
+Meta-Llama-3.1-8B-Instruct,0.4507042253521127
+Qwen2-72B-Instruct,0.9014084507042254
 Meta-Llama-3-8B-Instruct,0.4507042253521127
 Meta-Llama-3-70B-Instruct,0.7887323943661971

results/general_reasoning/few_shot/c_eval.csv

@@ -1 +1,4 @@
 Model,Accuracy
+Meta-Llama-3-70B,0.6257783312577833
+Meta-Llama-3-8B,0.43773349937733497
+Meta-Llama-3.1-8B,0.44458281444582815

results/general_reasoning/few_shot/cmmlu.csv

@@ -1 +1,3 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.4308409601105163
+Meta-Llama-3.1-8B,0.4555344500086341