Upload folder using huggingface_hub

results/cross_lingual/zero_shot/cross_logiqa.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.6306818181818182,0.6186688311688312,0.62461756988007
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.45860389610389607,0.46087662337662333,0.4597374508818368,0.5568181818181818,0.48295454545454547,0.4659090909090909,0.4431818181818182,0.4431818181818182,0.4318181818181818,0.38636363636363635
 Qwen2_5_14B_Instruct,0.6436688311688312,0.5938311688311688,0.6177464473895627,0.75,0.7386363636363636,0.6306818181818182,0.6420454545454546,0.6136363636363636,0.5965909090909091,0.5340909090909091
 sg_llama3_8192_8b,0.49594155844155846,0.468831168831169,0.4820054587349027,0.5795454545454546,0.48295454545454547,0.5397727272727273,0.48863636363636365,0.5,0.48295454545454547,0.3977272727272727
+gemma2-9b-cpt-sea-lionv3-instruct,0.6055194805194805,0.6220779220779219,0.6136870270197391,0.6590909090909091,0.6590909090909091,0.5625,0.6193181818181818,0.5681818181818182,0.5852272727272727,0.5852272727272727
 sg_llama3_70b_inst,0.6217532467532468,0.5629870129870129,0.590912649920049,0.7272727272727273,0.6590909090909091,0.6477272727272727,0.6079545454545454,0.6136363636363636,0.5795454545454546,0.5170454545454546
 cross_openhermes_llama3_8b_2048_inst,0.4659090909090909,0.4407467532467531,0.452978757986988,0.5284090909090909,0.5284090909090909,0.4375,0.4659090909090909,0.4375,0.48863636363636365,0.375
 gemma-2-2b-it,0.4780844155844156,0.4448051948051948,0.46084478401384643,0.5568181818181818,0.5,0.5,0.48863636363636365,0.4375,0.4602272727272727,0.4034090909090909

results/cross_lingual/zero_shot/cross_mmlu.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.758095238095238,0.7316190476190477,0.744621866597198
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.5447619047619048,0.5127619047619049,0.5282777548560428,0.6533333333333333,0.5333333333333333,0.5066666666666667,0.54,0.5466666666666666,0.5133333333333333,0.52
 Qwen2_5_14B_Instruct,0.7266666666666666,0.680952380952381,0.7030672078887086,0.78,0.7533333333333333,0.7533333333333333,0.7266666666666667,0.7466666666666667,0.68,0.6466666666666666
 sg_llama3_8192_8b,0.5876190476190476,0.5207619047619048,0.5521740766611207,0.7,0.58,0.6333333333333333,0.5466666666666666,0.5533333333333333,0.5666666666666667,0.5333333333333333
+gemma2-9b-cpt-sea-lionv3-instruct,0.7180952380952382,0.7485714285714284,0.7330166975381478,0.78,0.7133333333333334,0.7133333333333334,0.6866666666666666,0.7266666666666667,0.7,0.7066666666666667
 sg_llama3_70b_inst,0.7342857142857142,0.7079999999999999,0.7209033280007295,0.82,0.6866666666666666,0.7333333333333333,0.6933333333333334,0.78,0.7266666666666667,0.7
 cross_openhermes_llama3_8b_2048_inst,0.5504761904761906,0.528,0.53900388550283,0.6733333333333333,0.5466666666666666,0.52,0.5133333333333333,0.5666666666666667,0.5466666666666666,0.4866666666666667
 gemma-2-2b-it,0.5780952380952381,0.5480000000000002,0.5626454667971265,0.7,0.5866666666666667,0.5866666666666667,0.5333333333333333,0.5666666666666667,0.5333333333333333,0.54

results/cultural_reasoning/zero_shot/cn_eval.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.5333333333333333
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.49523809523809526
 Qwen2_5_14B_Instruct,0.8285714285714286
 sg_llama3_8192_8b,0.47619047619047616
+gemma2-9b-cpt-sea-lionv3-instruct,0.5904761904761905
 sg_llama3_70b_inst,0.5523809523809524
 cross_openhermes_llama3_8b_2048_inst,0.5142857142857142
 gemma-2-2b-it,0.3619047619047619

results/cultural_reasoning/zero_shot/ph_eval.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.63
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.52
 Qwen2_5_14B_Instruct,0.6
 sg_llama3_8192_8b,0.57
+gemma2-9b-cpt-sea-lionv3-instruct,0.59
 sg_llama3_70b_inst,0.69
 cross_openhermes_llama3_8b_2048_inst,0.5
 gemma-2-2b-it,0.4

results/cultural_reasoning/zero_shot/sg_eval.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.7087378640776699
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.6116504854368932
 Qwen2_5_14B_Instruct,0.7669902912621359
 sg_llama3_8192_8b,0.5533980582524272
+gemma2-9b-cpt-sea-lionv3-instruct,0.6796116504854369
 sg_llama3_70b_inst,0.6699029126213593
 cross_openhermes_llama3_8b_2048_inst,0.6116504854368932
 gemma-2-2b-it,0.5533980582524272

results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.6617647058823529
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.5735294117647058
 Qwen2_5_14B_Instruct,0.6911764705882353
 sg_llama3_8192_8b,0.47058823529411764
+gemma2-9b-cpt-sea-lionv3-instruct,0.6029411764705882
 sg_llama3_70b_inst,0.6176470588235294
 cross_openhermes_llama3_8b_2048_inst,0.6323529411764706
 gemma-2-2b-it,0.5147058823529411

results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.8381818181818181
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.7927272727272727
 Qwen2_5_14B_Instruct,0.8345454545454546
 sg_llama3_8192_8b,0.76
+gemma2-9b-cpt-sea-lionv3-instruct,0.8090909090909091
 sg_llama3_70b_inst,0.8436363636363636
 cross_openhermes_llama3_8b_2048_inst,0.7781818181818182
 gemma-2-2b-it,0.7163636363636363

results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,50.599999999999994
 llama-own-4096-2-sg-ultrachat-sft-eos-real,49.32000000000001
 Qwen2_5_14B_Instruct,53.2
 sg_llama3_8192_8b,53.4
+gemma2-9b-cpt-sea-lionv3-instruct,55.0
 sg_llama3_70b_inst,51.959999999999994
 cross_openhermes_llama3_8b_2048_inst,52.24
 gemma-2-2b-it,52.08

results/cultural_reasoning/zero_shot/us_eval.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.8691588785046729
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.6635514018691588
 Qwen2_5_14B_Instruct,0.822429906542056
 sg_llama3_8192_8b,0.7009345794392523
+gemma2-9b-cpt-sea-lionv3-instruct,0.8037383177570093
 sg_llama3_70b_inst,0.8598130841121495
 cross_openhermes_llama3_8b_2048_inst,0.7102803738317757
 gemma-2-2b-it,0.6915887850467289

results/dialogue/zero_shot/dialogsum.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.2557065499979308,0.36058417323628,0.1275808733778686
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.23822266043844623,0.33277843672963314,0.1255742736802169,0.2563152709054887
 Qwen2_5_14B_Instruct,0.2343478938479703,0.3386251381162625,0.10742381514017992,0.2569947282874686
 sg_llama3_8192_8b,0.2708022468830074,0.3774768588431775,0.1387436961438702,0.2961861856619747
+gemma2-9b-cpt-sea-lionv3-instruct,0.23790909190042164,0.34294544984076464,0.1078722585042388,0.26290956735626153
 sg_llama3_70b_inst,0.26633840691332344,0.3692028513115729,0.1412505883866801,0.2885617810417173
 cross_openhermes_llama3_8b_2048_inst,0.26075548388204367,0.3613222112557008,0.13618000204638436,0.28476423834404585
 gemma-2-2b-it,0.2597323674875989,0.36848124762381895,0.12622684440269072,0.2844890104362872

results/dialogue/zero_shot/dream.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.9480646741793238
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.8731014208721215
 Qwen2_5_14B_Instruct,0.9461048505634493
 sg_llama3_8192_8b,0.9103380695737384
+gemma2-9b-cpt-sea-lionv3-instruct,0.9407153356197943
 sg_llama3_70b_inst,0.9524742773150416
 cross_openhermes_llama3_8b_2048_inst,0.8642822146006859
 gemma-2-2b-it,0.8510534051935326

results/dialogue/zero_shot/samsum.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.2893525314227379,0.4030746211134018,0.15236139065578
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.2813508829464006,0.38872030551635356,0.1571931255091481,0.29813921781370006
 Qwen2_5_14B_Instruct,0.2713801253928723,0.3836253496005304,0.13683087953788298,0.2936841470402035
 sg_llama3_8192_8b,0.30740523414540055,0.4199805360695743,0.1701793607165699,0.33205580565005743
+gemma2-9b-cpt-sea-lionv3-instruct,0.29509358497900623,0.4129497614150914,0.1502573048316353,0.32207368869029196
 sg_llama3_70b_inst,0.3146051103643872,0.4271361513564755,0.18238925099430264,0.33428992874238356
 cross_openhermes_llama3_8b_2048_inst,0.29349656315763506,0.4044332095677647,0.16224920209587818,0.3138072778092623
 gemma-2-2b-it,0.31118787136959813,0.4324251755711466,0.16441328335793207,0.33672515517971563

results/emotion/zero_shot/ind_emotion.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.6909090909090909
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.6659090909090909
 Qwen2_5_14B_Instruct,0.6954545454545454
 sg_llama3_8192_8b,0.6045454545454545
+gemma2-9b-cpt-sea-lionv3-instruct,0.7340909090909091
 sg_llama3_70b_inst,0.7
 cross_openhermes_llama3_8b_2048_inst,0.6636363636363637
 gemma-2-2b-it,0.6636363636363637

results/emotion/zero_shot/sst2.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.9495412844036697
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.911697247706422
 Qwen2_5_14B_Instruct,0.9311926605504587
 sg_llama3_8192_8b,0.9208715596330275
+gemma2-9b-cpt-sea-lionv3-instruct,0.9311926605504587
 sg_llama3_70b_inst,0.9334862385321101
 cross_openhermes_llama3_8b_2048_inst,0.9243119266055045
 gemma-2-2b-it,0.9243119266055045

results/flores_translation/zero_shot/ind2eng.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.3830092775167675
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.3778716126842916
 Qwen2_5_14B_Instruct,0.3901044620348051
 sg_llama3_8192_8b,0.3758986882788705
+gemma2-9b-cpt-sea-lionv3-instruct,0.3922444585880475
 sg_llama3_70b_inst,0.4086440304524362
 cross_openhermes_llama3_8b_2048_inst,0.3904916300086918
 gemma-2-2b-it,0.3482500758113138

results/flores_translation/zero_shot/vie2eng.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.3230140263371192
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.2881995374548925
 Qwen2_5_14B_Instruct,0.32198218156960645
 sg_llama3_8192_8b,0.3087032778607667
+gemma2-9b-cpt-sea-lionv3-instruct,0.3176282835521885
 sg_llama3_70b_inst,0.34258533717783785
 cross_openhermes_llama3_8b_2048_inst,0.2973194210388712
 gemma-2-2b-it,0.27518909199172303

results/flores_translation/zero_shot/zho2eng.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.24397819518058994
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.23373987803056884
 Qwen2_5_14B_Instruct,0.2627781200417998
 sg_llama3_8192_8b,0.23778397807613597
+gemma2-9b-cpt-sea-lionv3-instruct,0.25110750921976727
 sg_llama3_70b_inst,0.26000707510414633
 cross_openhermes_llama3_8b_2048_inst,0.23916426190948417
 gemma-2-2b-it,0.21164036008441425

results/flores_translation/zero_shot/zsm2eng.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.3957287030176054
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.37943052200875504
 Qwen2_5_14B_Instruct,0.3841042767934729
 sg_llama3_8192_8b,0.376818225699898
+gemma2-9b-cpt-sea-lionv3-instruct,0.4059485540822735
 sg_llama3_70b_inst,0.4163761508073963
 cross_openhermes_llama3_8b_2048_inst,0.3904643635616676
 gemma-2-2b-it,0.33737270487369614

results/fundamental_nlp_tasks/zero_shot/c3.csv

@@ -21,6 +21,7 @@ llama-own-4096-2-sg-ultrachat-sft-eos-real,0.8358264771877337
 Qwen2_5_14B_Instruct,0.9502617801047121
 sg_llama3_8192_8b,0.8051608077786089
 Meta-Llama-3.1-70B,0.7786088257292446
+gemma2-9b-cpt-sea-lionv3-instruct,0.9255796559461481
 sg_llama3_70b_inst,0.9289454001495886
 cross_openhermes_llama3_8b_2048_inst,0.8167539267015707
 gemma-2-2b-it,0.7700074794315632

results/fundamental_nlp_tasks/zero_shot/cola.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.835091083413231
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.7468839884947267
 Qwen2_5_14B_Instruct,0.8063279002876318
 sg_llama3_8192_8b,0.8130393096836049
+gemma2-9b-cpt-sea-lionv3-instruct,0.825503355704698
 sg_llama3_70b_inst,0.8696069031639502
 cross_openhermes_llama3_8b_2048_inst,0.7727708533077661
 gemma-2-2b-it,0.6749760306807286

results/fundamental_nlp_tasks/zero_shot/mnli.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.6709421285692472
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.571
 Qwen2_5_14B_Instruct,0.818
 sg_llama3_8192_8b,0.6605
+gemma2-9b-cpt-sea-lionv3-instruct,0.7445
 sg_llama3_70b_inst,0.7685
 cross_openhermes_llama3_8b_2048_inst,0.57
 gemma-2-2b-it,0.6185

results/fundamental_nlp_tasks/zero_shot/mrpc.csv

@@ -19,6 +19,7 @@ Meta-Llama-3-70B-Instruct,0.7598039215686274
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.7377450980392157
 Qwen2_5_14B_Instruct,0.7794117647058824
 sg_llama3_8192_8b,0.7254901960784313
+gemma2-9b-cpt-sea-lionv3-instruct,0.7794117647058824
 sg_llama3_70b_inst,0.7892156862745098
 cross_openhermes_llama3_8b_2048_inst,0.7058823529411765
 gemma-2-2b-it,0.7083333333333334

results/fundamental_nlp_tasks/zero_shot/ocnli.csv

@@ -19,6 +19,7 @@ Meta-Llama-3-70B-Instruct,0.5928813559322034
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.5138983050847458
 Qwen2_5_14B_Instruct,0.7538983050847458
 sg_llama3_8192_8b,0.5084745762711864
+gemma2-9b-cpt-sea-lionv3-instruct,0.6488135593220339
 sg_llama3_70b_inst,0.6420338983050847
 cross_openhermes_llama3_8b_2048_inst,0.5322033898305085
 gemma-2-2b-it,0.43322033898305085

results/fundamental_nlp_tasks/zero_shot/qnli.csv

@@ -19,6 +19,7 @@ Meta-Llama-3-70B-Instruct,0.876807614863628
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.6829580816401245
 Qwen2_5_14B_Instruct,0.9079260479589969
 sg_llama3_8192_8b,0.8118250045762402
+gemma2-9b-cpt-sea-lionv3-instruct,0.9055464030752334
 sg_llama3_70b_inst,0.9004210140948197
 cross_openhermes_llama3_8b_2048_inst,0.7393373604246751
 gemma-2-2b-it,0.7792421746293245

results/fundamental_nlp_tasks/zero_shot/qqp.csv

@@ -19,6 +19,7 @@ Meta-Llama-3-70B-Instruct,0.7876082117239673
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.767
 Qwen2_5_14B_Instruct,0.8255
 sg_llama3_8192_8b,0.8095
+gemma2-9b-cpt-sea-lionv3-instruct,0.803
 sg_llama3_70b_inst,0.804
 cross_openhermes_llama3_8b_2048_inst,0.722
 gemma-2-2b-it,0.761

results/fundamental_nlp_tasks/zero_shot/rte.csv

@@ -19,6 +19,7 @@ Meta-Llama-3-70B-Instruct,0.8086642599277978
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.7292418772563177
 Qwen2_5_14B_Instruct,0.8664259927797834
 sg_llama3_8192_8b,0.7364620938628159
+gemma2-9b-cpt-sea-lionv3-instruct,0.8483754512635379
 sg_llama3_70b_inst,0.8916967509025271
 cross_openhermes_llama3_8b_2048_inst,0.7075812274368231
 gemma-2-2b-it,0.7292418772563177

results/fundamental_nlp_tasks/zero_shot/wnli.csv

@@ -19,6 +19,7 @@ Meta-Llama-3-70B-Instruct,0.7887323943661971
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.5915492957746479
 Qwen2_5_14B_Instruct,0.8309859154929577
 sg_llama3_8192_8b,0.704225352112676
+gemma2-9b-cpt-sea-lionv3-instruct,0.7605633802816901
 sg_llama3_70b_inst,0.8309859154929577
 cross_openhermes_llama3_8b_2048_inst,0.49295774647887325
 gemma-2-2b-it,0.43661971830985913

results/general_reasoning/zero_shot/c_eval.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.6220423412204235
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.4800747198007472
 Qwen2_5_14B_Instruct,0.7839352428393525
 sg_llama3_8192_8b,0.4825653798256538
+gemma2-9b-cpt-sea-lionv3-instruct,0.5722291407222914
 sg_llama3_70b_inst,0.5722291407222914
 cross_openhermes_llama3_8b_2048_inst,0.4663760896637609
 gemma-2-2b-it,0.4352428393524284

results/general_reasoning/zero_shot/cmmlu.csv

@@ -19,6 +19,7 @@ Meta-Llama-3-70B-Instruct,0.6494560524952513
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.4750474874805733
 Qwen2_5_14B_Instruct,0.7807805214988776
 sg_llama3_8192_8b,0.49050250388533934
+gemma2-9b-cpt-sea-lionv3-instruct,0.5796062856156105
 sg_llama3_70b_inst,0.6044724572612675
 cross_openhermes_llama3_8b_2048_inst,0.47064410291832154
 gemma-2-2b-it,0.4412882058366431

results/general_reasoning/zero_shot/indommlu.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.6323519594098405
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.5312103611723079
 Qwen2_5_14B_Instruct,0.6009746979104079
 sg_llama3_8192_8b,0.5021697042526203
+gemma2-9b-cpt-sea-lionv3-instruct,0.6196007744175178
 sg_llama3_70b_inst,0.6394285332799252
 cross_openhermes_llama3_8b_2048_inst,0.528873756592563
 gemma-2-2b-it,0.48220842512851325

results/general_reasoning/zero_shot/zbench.csv

@@ -20,6 +20,7 @@ Meta-Llama-3-70B-Instruct,0.5151515151515151
 llama-own-4096-2-sg-ultrachat-sft-eos-real,0.36363636363636365
 Qwen2_5_14B_Instruct,0.6666666666666666
 sg_llama3_8192_8b,0.30303030303030304
+gemma2-9b-cpt-sea-lionv3-instruct,0.42424242424242425
 sg_llama3_70b_inst,0.42424242424242425
 cross_openhermes_llama3_8b_2048_inst,0.3333333333333333
 gemma-2-2b-it,0.24242424242424243