Upload folder using huggingface_hub

results/cultural_reasoning/few_shot/sg_eval_v2_mcq.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.7654545454545455

results/cultural_reasoning/few_shot/sg_eval_v2_open.csv

@@ -1 +1,2 @@
 Model,Accuracy
+Meta-Llama-3-8B,50.8

results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv

@@ -1,23 +1,32 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7872727272727272
 Meta-Llama-3.1-8B-Instruct,0.7854545454545454
+llama3-8b-cpt-sea-lionv2.1-instruct,0.7836363636363637
 Qwen2_5_32B_Instruct,0.8436363636363636
 Qwen2_5_7B_Instruct,0.78
 Qwen2_5_1_5B_Instruct,0.6636363636363637
+Qwen2-72B-Instruct,0.8581818181818182
 cross_openhermes_llama3_8b_4096_inst,0.7490909090909091
 Meta-Llama-3-8B-Instruct,0.7909090909090909
+Meta-Llama-3.1-70B-Instruct,0.8763636363636363
 Qwen2_5_3B_Instruct,0.72
 cross_openhermes_llama3_8b_16384_inst,0.7963636363636364
 cross_openhermes_llama3_70b_4096_inst_2,0.8618181818181818
+SeaLLMs-v3-7B-Chat,0.7836363636363637
 Qwen2_5_72B_Instruct,0.8618181818181818
+gemma-2-9b-it,0.8036363636363636
 Meta-Llama-3-70B-Instruct,0.8381818181818181
 Qwen2_5_14B_Instruct,0.8345454545454546
 sg_llama3_8192_8b,0.76
+Meta-Llama-3.1-70B,0.44181818181818183
 sg_llama3_70b_inst,0.8436363636363636
 cross_openhermes_llama3_8b_2048_inst,0.7781818181818182
 gemma-2-2b-it,0.7163636363636363
+llama3-8b-cpt-sea-lionv2-instruct,0.7763636363636364
 cross_openhermes_llama3_8b_12288_inst,0.7890909090909091
 Qwen2_5_0_5B_Instruct,0.5727272727272728
 GPT4o_0513,0.8709090909090909
 cross_openhermes_llama3_8b_8192_inst,0.78
 cross_openhermes_llama3_70b_4096_inst,0.8381818181818181
 cross_openhermes_llama3_8b_4096_2_inst,0.7654545454545455
+Meta-Llama-3.1-8B,0.4381818181818182

results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv

@@ -1,20 +1,27 @@
 Model,Accuracy
+Qwen2-7B-Instruct,56.559999999999995
 Meta-Llama-3.1-8B-Instruct,49.2
+llama3-8b-cpt-sea-lionv2.1-instruct,50.03999999999999
 Qwen2_5_32B_Instruct,53.2
 Qwen2_5_7B_Instruct,50.279999999999994
 Qwen2_5_1_5B_Instruct,44.480000000000004
+Qwen2-72B-Instruct,54.080000000000005
 cross_openhermes_llama3_8b_4096_inst,51.6
 Meta-Llama-3-8B-Instruct,51.120000000000005
+Meta-Llama-3.1-70B-Instruct,51.31999999999999
 Qwen2_5_3B_Instruct,47.24
 cross_openhermes_llama3_8b_16384_inst,52.44
 cross_openhermes_llama3_70b_4096_inst_2,55.8
+SeaLLMs-v3-7B-Chat,55.0
 Qwen2_5_72B_Instruct,53.32
+gemma-2-9b-it,53.96
 Meta-Llama-3-70B-Instruct,50.599999999999994
 Qwen2_5_14B_Instruct,53.2
 sg_llama3_8192_8b,53.4
 sg_llama3_70b_inst,51.959999999999994
 cross_openhermes_llama3_8b_2048_inst,52.24
 gemma-2-2b-it,52.08
+llama3-8b-cpt-sea-lionv2-instruct,50.03999999999999
 cross_openhermes_llama3_8b_12288_inst,52.480000000000004
 Qwen2_5_0_5B_Instruct,35.28
 GPT4o_0513,57.28

results/flores_translation/zero_shot/ind2eng.csv

@@ -1,7 +1,9 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.29408553325533265
 Meta-Llama-3.1-8B-Instruct,0.3765752579792989
+Qwen2_5_32B_Instruct,0.3923422946746861
 Qwen2_5_7B_Instruct,0.36472669481333536
+Qwen2_5_1_5B_Instruct,0.2624938515155373
 Qwen2-72B-Instruct,0.4043588265556185
 cross_openhermes_llama3_8b_4096_inst,0.37782883404862155
 Meta-Llama-3-8B-Instruct,0.33079891679041123
@@ -20,6 +22,7 @@ cross_openhermes_llama3_8b_2048_inst,0.3904916300086918
 gemma-2-2b-it,0.3482500758113138
 llama3-8b-cpt-sea-lionv2-instruct,0.3916108972514423
 cross_openhermes_llama3_8b_12288_inst,0.3900675406718024
+Qwen2_5_0_5B_Instruct,0.15776662800152338
 GPT4o_0513,0.42589589086974855
 cross_openhermes_llama3_8b_8192_inst,0.3929315974686861
 cross_openhermes_llama3_70b_4096_inst,0.4206616934730876

results/flores_translation/zero_shot/vie2eng.csv

@@ -1,7 +1,9 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.24106736560355876
 Meta-Llama-3.1-8B-Instruct,0.31019605539004524
+Qwen2_5_32B_Instruct,0.33791529833420336
 Qwen2_5_7B_Instruct,0.3027564749728372
+Qwen2_5_1_5B_Instruct,0.21935649300365245
 Qwen2-72B-Instruct,0.33005323227052946
 cross_openhermes_llama3_8b_4096_inst,0.28905588559612455
 Meta-Llama-3-8B-Instruct,0.2647448190950291
@@ -20,6 +22,7 @@ cross_openhermes_llama3_8b_2048_inst,0.2973194210388712
 gemma-2-2b-it,0.27518909199172303
 llama3-8b-cpt-sea-lionv2-instruct,0.327781936019637
 cross_openhermes_llama3_8b_12288_inst,0.29952664743728336
+Qwen2_5_0_5B_Instruct,0.14677375445859656
 GPT4o_0513,0.36219303373759176
 cross_openhermes_llama3_8b_8192_inst,0.29989110440173306
 cross_openhermes_llama3_70b_4096_inst,0.3538368711937718

results/flores_translation/zero_shot/zho2eng.csv

@@ -1,7 +1,9 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.2113761361724575
 Meta-Llama-3.1-8B-Instruct,0.23889886925287113
+Qwen2_5_32B_Instruct,0.26924811164378015
 Qwen2_5_7B_Instruct,0.2437311220019033
+Qwen2_5_1_5B_Instruct,0.18420680441018222
 Qwen2-72B-Instruct,0.23893268538329387
 cross_openhermes_llama3_8b_4096_inst,0.2258901846942186
 Meta-Llama-3-8B-Instruct,0.199495011482748
@@ -20,6 +22,7 @@ cross_openhermes_llama3_8b_2048_inst,0.23916426190948417
 gemma-2-2b-it,0.21164036008441425
 llama3-8b-cpt-sea-lionv2-instruct,0.2381535278220489
 cross_openhermes_llama3_8b_12288_inst,0.2437964546132799
+Qwen2_5_0_5B_Instruct,0.13846648470535672
 GPT4o_0513,0.27722306559544163
 cross_openhermes_llama3_8b_8192_inst,0.24473214674903845
 cross_openhermes_llama3_70b_4096_inst,0.27230844604661014

results/flores_translation/zero_shot/zsm2eng.csv

@@ -1,7 +1,9 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.28031997065822994
 Meta-Llama-3.1-8B-Instruct,0.3700921225177551
+Qwen2_5_32B_Instruct,0.40310877536446654
 Qwen2_5_7B_Instruct,0.3466422765302921
+Qwen2_5_1_5B_Instruct,0.22890805100949677
 Qwen2-72B-Instruct,0.40796892621611885
 cross_openhermes_llama3_8b_4096_inst,0.37996622288549425
 Meta-Llama-3-8B-Instruct,0.31625368345049
@@ -20,6 +22,7 @@ cross_openhermes_llama3_8b_2048_inst,0.3904643635616676
 gemma-2-2b-it,0.33737270487369614
 llama3-8b-cpt-sea-lionv2-instruct,0.38799258214381604
 cross_openhermes_llama3_8b_12288_inst,0.39589080400186966
+Qwen2_5_0_5B_Instruct,0.1194369315142997
 GPT4o_0513,0.451496635720668
 cross_openhermes_llama3_8b_8192_inst,0.39476822018254265
 cross_openhermes_llama3_70b_4096_inst,0.43447247409976697

results/fundamental_nlp_tasks/zero_shot/c3.csv

@@ -17,6 +17,7 @@ gemma-2-9b-it,0.9222139117427075
 Meta-Llama-3-70B-Instruct,0.9521316379955124
 Qwen2_5_14B_Instruct,0.9502617801047121
 sg_llama3_8192_8b,0.8051608077786089
+Meta-Llama-3.1-70B,0.7786088257292446
 sg_llama3_70b_inst,0.9289454001495886
 cross_openhermes_llama3_8b_2048_inst,0.8167539267015707
 gemma-2-2b-it,0.7700074794315632