Upload folder using huggingface_hub

results/cross_lingual/zero_shot/cross_logiqa.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.46834415584415584,0.348538961038961,0.3996561615557665,0
 Qwen2-72B-Instruct,0.6728896103896104,0.6762987012987012,0.6745898487968579,0.75,0.8068181818181818,0.6534090909090909,0.6193181818181818,0.625,0.6534090909090909,0.6022727272727273
 Sailor2-8B-Chat,0.5405844155844156,0.5628246753246753,0.551480408610067,0.625,0.5852272727272727,0.4943181818181818,0.5568181818181818,0.5056818181818182,0.5568181818181818,0.4602272727272727
 Meta-Llama-3-8B-Instruct,0.4610389610389611,0.45097402597402597,0.4559509553669637,0.5965909090909091,0.48295454545454547,0.5,0.4602272727272727,0.42045454545454547,0.4034090909090909,0.36363636363636365
-merged_llama3_8b_sg_inst_avg_diff,0.4829545454545454,0.4952922077922078,0.48904557518459746,0.5397727272727273,0.5340909090909091,0.4772727272727273,0.5056818181818182,0.4602272727272727,0.45454545454545453,0.4090909090909091
+MERaLiON-Llama-3-8B-Instruct,0.4829545454545454,0.4952922077922078,0.48904557518459746,0.5397727272727273,0.5340909090909091,0.4772727272727273,0.5056818181818182,0.4602272727272727,0.45454545454545453,0.4090909090909091
 Meta-Llama-3.1-70B-Instruct,0.6566558441558442,0.598051948051948,0.6259852839118454,0.7443181818181818,0.7215909090909091,0.6647727272727273,0.6534090909090909,0.6193181818181818,0.625,0.5681818181818182
 Qwen2_5_3B_Instruct,0.4878246753246754,0.3594155844155844,0.41388918606681485,0.6079545454545454,0.6420454545454546,0.45454545454545453,0.4602272727272727,0.48295454545454547,0.42045454545454547,0.3465909090909091
 SeaLLMs-v3-7B-Chat,0.5551948051948051,0.5142857142857142,0.5339578453833284,0.6022727272727273,0.6647727272727273,0.5738636363636364,0.5454545454545454,0.5170454545454546,0.5,0.48295454545454547

results/cross_lingual/zero_shot/cross_logiqa_no_prompt.csv

@@ -4,7 +4,7 @@ llama3-8b-cpt-sea-lionv2.1-instruct,0.45779220779220786,0.3751623376623376,0.412
 Qwen2_5_7B_Instruct,0.6047077922077922,0.47938311688311697,0.5348014705675028,0.6931818181818182,0.7102272727272727,0.6420454545454546,0.5795454545454546,0.6306818181818182,0.5340909090909091,0.4431818181818182
 Sailor2-8B-Chat,0.5503246753246753,0.5363636363636365,0.5432544747850031,0.6136363636363636,0.625,0.5056818181818182,0.5625,0.5113636363636364,0.5511363636363636,0.48295454545454547
 Meta-Llama-3-8B-Instruct,0.5,0.4426948051948052,0.46960564830561785,0.6022727272727273,0.5227272727272727,0.5454545454545454,0.5056818181818182,0.4375,0.48295454545454547,0.4034090909090909
-merged_llama3_8b_sg_inst_avg_diff,0.5105519480519481,0.4558441558441559,0.48164954476113636,0.5909090909090909,0.5284090909090909,0.5454545454545454,0.5,0.4943181818181818,0.48863636363636365,0.42613636363636365
+MERaLiON-Llama-3-8B-Instruct,0.5105519480519481,0.4558441558441559,0.48164954476113636,0.5909090909090909,0.5284090909090909,0.5454545454545454,0.5,0.4943181818181818,0.48863636363636365,0.42613636363636365
 SeaLLMs-v3-7B-Chat,0.5324675324675324,0.41266233766233773,0.46497164802104307,0.5681818181818182,0.5852272727272727,0.5738636363636364,0.5568181818181818,0.4943181818181818,0.5170454545454546,0.4318181818181818
 gemma-2-9b-it,0.6006493506493508,0.5753246753246755,0.587714328691409,0.6590909090909091,0.6363636363636364,0.5511363636363636,0.6022727272727273,0.5852272727272727,0.6022727272727273,0.5681818181818182
 gemma2-9b-cpt-sea-lionv3-instruct,0.5844155844155844,0.605844155844156,0.5949369778657175,0.6363636363636364,0.6420454545454546,0.5625,0.5681818181818182,0.5568181818181818,0.5511363636363636,0.5738636363636364

results/cross_lingual/zero_shot/cross_mmlu.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5076190476190475,0.3721904761904762,0.42948154099799957,
 Qwen2-72B-Instruct,0.779047619047619,0.7611428571428573,0.7699911663398871,0.8133333333333334,0.7933333333333333,0.7933333333333333,0.7333333333333333,0.7666666666666667,0.78,0.7733333333333333
 Sailor2-8B-Chat,0.6542857142857142,0.6586666666666667,0.6564688814239598,0.7133333333333334,0.6733333333333333,0.6533333333333333,0.6066666666666667,0.62,0.6466666666666666,0.6666666666666666
 Meta-Llama-3-8B-Instruct,0.5733333333333334,0.4742857142857144,0.5191272726777197,0.7133333333333334,0.5866666666666667,0.5733333333333334,0.5866666666666667,0.5066666666666667,0.5333333333333333,0.5133333333333333
-merged_llama3_8b_sg_inst_avg_diff,0.5980952380952381,0.5817142857142859,0.5897910419722433,0.76,0.5866666666666667,0.6266666666666667,0.5466666666666666,0.5666666666666667,0.5533333333333333,0.5466666666666666
+MERaLiON-Llama-3-8B-Instruct,0.5980952380952381,0.5817142857142859,0.5897910419722433,0.76,0.5866666666666667,0.6266666666666667,0.5466666666666666,0.5666666666666667,0.5533333333333333,0.5466666666666666
 Meta-Llama-3.1-70B-Instruct,0.7638095238095238,0.7716190476190474,0.7676944251955988,0.8,0.74,0.7666666666666667,0.7666666666666667,0.76,0.7666666666666667,0.7466666666666667
 Qwen2_5_3B_Instruct,0.5857142857142856,0.48952380952380964,0.533316462053399,0.6933333333333334,0.6666666666666666,0.64,0.5266666666666666,0.6333333333333333,0.5466666666666666,0.3933333333333333
 SeaLLMs-v3-7B-Chat,0.6628571428571429,0.6135238095238095,0.6372370860992635,0.74,0.6933333333333334,0.6933333333333334,0.6466666666666666,0.68,0.6,0.5866666666666667

results/cross_lingual/zero_shot/cross_mmlu_no_prompt.csv

@@ -4,7 +4,7 @@ llama3-8b-cpt-sea-lionv2.1-instruct,0.6676190476190476,0.5590476190476189,0.6085
 Qwen2_5_7B_Instruct,0.7742857142857141,0.6222857142857142,0.6900140284752591,0.8466666666666667,0.84,0.8266666666666667,0.74,0.7533333333333333,0.7133333333333334,0.7
 Sailor2-8B-Chat,0.6923809523809524,0.6592380952380954,0.6754031781322388,0.7266666666666667,0.7066666666666667,0.7133333333333334,0.6733333333333333,0.6733333333333333,0.6466666666666666,0.7066666666666667
 Meta-Llama-3-8B-Instruct,0.6647619047619048,0.5036190476190476,0.5730780815259353,0.7733333333333333,0.66,0.6666666666666666,0.66,0.6266666666666667,0.64,0.6266666666666667
-merged_llama3_8b_sg_inst_avg_diff,0.6980952380952381,0.5891428571428572,0.6390081595918414,0.8466666666666667,0.6933333333333334,0.6933333333333334,0.6933333333333334,0.7133333333333334,0.6133333333333333,0.6333333333333333
+MERaLiON-Llama-3-8B-Instruct,0.6980952380952381,0.5891428571428572,0.6390081595918414,0.8466666666666667,0.6933333333333334,0.6933333333333334,0.6933333333333334,0.7133333333333334,0.6133333333333333,0.6333333333333333
 SeaLLMs-v3-7B-Chat,0.7342857142857142,0.5765714285714287,0.6459409639562039,0.8333333333333334,0.7266666666666667,0.7866666666666666,0.7133333333333334,0.74,0.6866666666666666,0.6533333333333333
 gemma-2-9b-it,0.781904761904762,0.747047619047619,0.7640788528690432,0.84,0.7933333333333333,0.7866666666666666,0.7466666666666667,0.78,0.7466666666666667,0.78
 gemma2-9b-cpt-sea-lionv3-instruct,0.7809523809523808,0.7506666666666667,0.7655100940510849,0.8466666666666667,0.7866666666666666,0.7733333333333333,0.78,0.7933333333333333,0.7333333333333333,0.7533333333333333

results/cross_lingual/zero_shot/cross_xquad.csv

@@ -6,7 +6,7 @@ Qwen2_5_7B_Instruct,0.9460084033613445,0.9178571428571428,0.9317201790045005,0.9
 Qwen2_5_1_5B_Instruct,0.8939075630252101,0.8308823529411764,0.8612434620121144,0.9100840336134454,0.9,0.8957983193277311,0.8697478991596639,,,
 Qwen2-72B-Instruct,0.9613445378151261,0.9516806722689075,0.956488195931227,0.9638655462184874,0.9596638655462185,0.9596638655462185,0.9621848739495799,,,
 Meta-Llama-3-8B-Instruct,0.9210084033613445,0.880672268907563,0.9003888121913395,0.9411764705882353,0.9033613445378151,0.9260504201680673,0.9134453781512605,,,
-merged_llama3_8b_sg_inst_avg_diff,0.9369747899159664,0.8936974789915966,0.9148245940061492,0.9470588235294117,0.9218487394957983,0.9403361344537815,0.938655462184874,,,
+MERaLiON-Llama-3-8B-Instruct,0.9369747899159664,0.8936974789915966,0.9148245940061492,0.9470588235294117,0.9218487394957983,0.9403361344537815,0.938655462184874,,,
 Meta-Llama-3.1-70B-Instruct,0.9615546218487395,0.9512605042016806,0.9563798632627071,0.9647058823529412,0.9512605042016806,0.9647058823529412,0.965546218487395,,,
 Qwen2_5_3B_Instruct,0.9378151260504202,0.8924369747899159,0.9145635113049859,0.9504201680672268,0.9327731092436975,0.9378151260504202,0.9302521008403362,,,
 SeaLLMs-v3-7B-Chat,0.9403361344537815,0.917016806722689,0.9285300818164836,0.9537815126050421,0.9378151260504202,0.9394957983193277,0.9302521008403362,,,

results/cross_lingual/zero_shot/cross_xquad_no_prompt.csv

@@ -4,7 +4,7 @@ llama3-8b-cpt-sea-lionv2.1-instruct,0.928781512605042,0.8592436974789917,0.89266
 Qwen2_5_7B_Instruct,0.9069327731092437,0.8264705882352941,0.8648342089942876,0.9210084033613445,0.8991596638655462,0.9092436974789916,0.8983193277310925,,,
 Sailor2-8B-Chat,0.9086134453781513,0.8378151260504201,0.8717792421413649,0.9252100840336135,0.8949579831932774,0.9117647058823529,0.9025210084033614,,,
 Meta-Llama-3-8B-Instruct,0.9117647058823529,0.8266806722689075,0.8671405721911006,0.9310924369747899,0.8848739495798319,0.9277310924369748,0.9033613445378151,,,
-merged_llama3_8b_sg_inst_avg_diff,0.9117647058823529,0.8266806722689075,0.8671405721911006,0.9302521008403362,0.8899159663865546,0.9210084033613445,0.9058823529411765,,,
+MERaLiON-Llama-3-8B-Instruct,0.9117647058823529,0.8266806722689075,0.8671405721911006,0.9302521008403362,0.8899159663865546,0.9210084033613445,0.9058823529411765,,,
 SeaLLMs-v3-7B-Chat,0.8943277310924369,0.7991596638655463,0.8440696412045011,0.9210084033613445,0.8773109243697479,0.9,0.8789915966386554,,,
 gemma-2-9b-it,0.8668067226890757,0.7012605042016806,0.7752949732453414,0.8773109243697479,0.8529411764705882,0.8714285714285714,0.865546218487395,,,
 gemma2-9b-cpt-sea-lionv3-instruct,0.9315126050420168,0.8716386554621849,0.9005815677746684,0.9453781512605042,0.9142857142857143,0.9369747899159664,0.9294117647058824,,,

results/cultural_reasoning/zero_shot/cn_eval.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5523809523809524
 Qwen2-72B-Instruct,0.8285714285714286
 Sailor2-8B-Chat,0.7142857142857143
 Meta-Llama-3-8B-Instruct,0.4666666666666667
-merged_llama3_8b_sg_inst_avg_diff,0.5142857142857142
+MERaLiON-Llama-3-8B-Instruct,0.5142857142857142
 Meta-Llama-3.1-70B-Instruct,0.5428571428571428
 Qwen2_5_3B_Instruct,0.7142857142857143
 SeaLLMs-v3-7B-Chat,0.819047619047619

results/cultural_reasoning/zero_shot/ph_eval.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.37
 Qwen2-72B-Instruct,0.62
 Sailor2-8B-Chat,0.53
 Meta-Llama-3-8B-Instruct,0.58
-merged_llama3_8b_sg_inst_avg_diff,0.54
+MERaLiON-Llama-3-8B-Instruct,0.54
 Meta-Llama-3.1-70B-Instruct,0.68
 Qwen2_5_3B_Instruct,0.4
 SeaLLMs-v3-7B-Chat,0.47

results/cultural_reasoning/zero_shot/sg_eval.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5048543689320388
 Qwen2-72B-Instruct,0.7378640776699029
 Sailor2-8B-Chat,0.6019417475728155
 Meta-Llama-3-8B-Instruct,0.6504854368932039
-merged_llama3_8b_sg_inst_avg_diff,0.6019417475728155
+MERaLiON-Llama-3-8B-Instruct,0.6019417475728155
 Meta-Llama-3.1-70B-Instruct,0.7184466019417476
 Qwen2_5_3B_Instruct,0.6310679611650486
 SeaLLMs-v3-7B-Chat,0.7184466019417476

results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.47058823529411764
 Qwen2-72B-Instruct,0.6764705882352942
 Sailor2-8B-Chat,0.5735294117647058
 Meta-Llama-3-8B-Instruct,0.5882352941176471
-merged_llama3_8b_sg_inst_avg_diff,0.5441176470588235
+MERaLiON-Llama-3-8B-Instruct,0.5441176470588235
 Meta-Llama-3.1-70B-Instruct,0.6617647058823529
 Qwen2_5_3B_Instruct,0.5882352941176471
 SeaLLMs-v3-7B-Chat,0.5882352941176471

results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.6636363636363637
 Qwen2-72B-Instruct,0.8581818181818182
 Sailor2-8B-Chat,0.730909090909091
 Meta-Llama-3-8B-Instruct,0.7909090909090909
-merged_llama3_8b_sg_inst_avg_diff,0.8109090909090909
+MERaLiON-Llama-3-8B-Instruct,0.8109090909090909
 Meta-Llama-3.1-70B-Instruct,0.8763636363636363
 Qwen2_5_3B_Instruct,0.72
 SeaLLMs-v3-7B-Chat,0.7909090909090909

results/cultural_reasoning/zero_shot/sg_eval_v2_mcq_no_prompt.csv

@@ -4,7 +4,7 @@ llama3-8b-cpt-sea-lionv2.1-instruct,0.7945454545454546
 Qwen2_5_7B_Instruct,0.7654545454545455
 Sailor2-8B-Chat,0.7145454545454546
 Meta-Llama-3-8B-Instruct,0.8290909090909091
-merged_llama3_8b_sg_inst_avg_diff,0.7854545454545454
+MERaLiON-Llama-3-8B-Instruct,0.7854545454545454
 SeaLLMs-v3-7B-Chat,0.7581818181818182
 gemma-2-9b-it,0.7618181818181818
 gemma2-9b-cpt-sea-lionv3-instruct,0.7818181818181819

results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,44.480000000000004
 Qwen2-72B-Instruct,54.080000000000005
 Sailor2-8B-Chat,54.36
 Meta-Llama-3-8B-Instruct,51.120000000000005
-merged_llama3_8b_sg_inst_avg_diff,49.2
+MERaLiON-Llama-3-8B-Instruct,49.2
 Meta-Llama-3.1-70B-Instruct,51.31999999999999
 Qwen2_5_3B_Instruct,47.24
 SeaLLMs-v3-7B-Chat,55.0

results/cultural_reasoning/zero_shot/us_eval.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5981308411214953
 Qwen2-72B-Instruct,0.8785046728971962
 Sailor2-8B-Chat,0.7009345794392523
 Meta-Llama-3-8B-Instruct,0.7009345794392523
-merged_llama3_8b_sg_inst_avg_diff,0.7383177570093458
+MERaLiON-Llama-3-8B-Instruct,0.7383177570093458
 Meta-Llama-3.1-70B-Instruct,0.8411214953271028
 Qwen2_5_3B_Instruct,0.6728971962616822
 SeaLLMs-v3-7B-Chat,0.6915887850467289

results/dialogue/zero_shot/dialogsum.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.20263242988485167,0.30002072253966694,0.0841667023855871
 Qwen2-72B-Instruct,0.2183280630214023,0.316174552903144,0.10156543495268992,0.23724420120837297
 Sailor2-8B-Chat,0.19777087324327317,0.2970393044008424,0.07701994204737679,0.21925337328160027
 Meta-Llama-3-8B-Instruct,0.23978455271183616,0.33971099717559883,0.1203340311564728,0.2593086298034369
-merged_llama3_8b_sg_inst_avg_diff,0.25236243090492,0.3573462392196718,0.125506438977953,0.27423461451713527
+MERaLiON-Llama-3-8B-Instruct,0.25236243090492,0.3573462392196718,0.125506438977953,0.27423461451713527
 Meta-Llama-3.1-70B-Instruct,0.2526239717396146,0.35714386898604744,0.1258832921736473,0.27484475405914904
 Qwen2_5_3B_Instruct,0.22107390172674926,0.32206286484028823,0.10065030710901035,0.24050853323094928
 SeaLLMs-v3-7B-Chat,0.24891094210680076,0.35393482223136147,0.12172072639345373,0.27107727769558715

results/dialogue/zero_shot/dream.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.8314551690347869
 Qwen2-72B-Instruct,0.9612934835864773
 Sailor2-8B-Chat,0.9054385105340519
 Meta-Llama-3-8B-Instruct,0.8946594806467418
-merged_llama3_8b_sg_inst_avg_diff,0.9103380695737384
+MERaLiON-Llama-3-8B-Instruct,0.9103380695737384
 Meta-Llama-3.1-70B-Instruct,0.9559039686428221
 Qwen2_5_3B_Instruct,0.9029887310142087
 SeaLLMs-v3-7B-Chat,0.9265066144047036

results/dialogue/zero_shot/samsum.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.2333120091694482,0.34339111721032756,0.10195887716459845
 Qwen2-72B-Instruct,0.2800906719573321,0.3887231369098802,0.15237661526996754,0.29917226369214855
 Sailor2-8B-Chat,0.23525560304744508,0.34567892481583223,0.10170204161284628,0.2583858427136568
 Meta-Llama-3-8B-Instruct,0.2846315092346869,0.39397110152251813,0.154320846916639,0.30560257926490364
-merged_llama3_8b_sg_inst_avg_diff,0.2827552959388026,0.3953429193664384,0.14797005050571224,0.30495291794425716
+MERaLiON-Llama-3-8B-Instruct,0.2827552959388026,0.3953429193664384,0.14797005050571224,0.30495291794425716
 Meta-Llama-3.1-70B-Instruct,0.28934874612070227,0.4036295731242805,0.15211190810296196,0.31230475713486433
 Qwen2_5_3B_Instruct,0.26935624341081515,0.380865832002109,0.13872106416227833,0.28848183406805816
 SeaLLMs-v3-7B-Chat,0.2959981719045788,0.4078820748825196,0.16338306782652476,0.316729373004692

results/emotion/zero_shot/ind_emotion.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5795454545454546
 Qwen2-72B-Instruct,0.675
 Sailor2-8B-Chat,0.7363636363636363
 Meta-Llama-3-8B-Instruct,0.6522727272727272
-merged_llama3_8b_sg_inst_avg_diff,0.7
+MERaLiON-Llama-3-8B-Instruct,0.7
 Meta-Llama-3.1-70B-Instruct,0.7159090909090909
 Qwen2_5_3B_Instruct,0.5522727272727272
 SeaLLMs-v3-7B-Chat,0.6454545454545455

results/emotion/zero_shot/sst2.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.9231651376146789
 Qwen2-72B-Instruct,0.9346330275229358
 Sailor2-8B-Chat,0.9461009174311926
 Meta-Llama-3-8B-Instruct,0.8784403669724771
-merged_llama3_8b_sg_inst_avg_diff,0.8841743119266054
+MERaLiON-Llama-3-8B-Instruct,0.8841743119266054
 Meta-Llama-3.1-70B-Instruct,0.9529816513761468
 Qwen2_5_3B_Instruct,0.8245412844036697
 SeaLLMs-v3-7B-Chat,0.9403669724770642

results/flores_translation/zero_shot/ind2eng.csv

@@ -7,7 +7,7 @@ Qwen2_5_7B_Instruct,0.36472669481333536
 Qwen2_5_1_5B_Instruct,0.2624938515155373
 Qwen2-72B-Instruct,0.4043588265556185
 Meta-Llama-3-8B-Instruct,0.33079891679041123
-merged_llama3_8b_sg_inst_avg_diff,0.38376586000725804
+MERaLiON-Llama-3-8B-Instruct,0.38376586000725804
 Meta-Llama-3.1-70B-Instruct,0.43366494500251235
 Qwen2_5_3B_Instruct,0.3316936422167389
 SeaLLMs-v3-7B-Chat,0.3594829412574955

results/flores_translation/zero_shot/vie2eng.csv

@@ -7,7 +7,7 @@ Qwen2_5_7B_Instruct,0.3027564749728372
 Qwen2_5_1_5B_Instruct,0.21935649300365245
 Qwen2-72B-Instruct,0.33005323227052946
 Meta-Llama-3-8B-Instruct,0.2647448190950291
-merged_llama3_8b_sg_inst_avg_diff,0.30900856944791294
+MERaLiON-Llama-3-8B-Instruct,0.30900856944791294
 Meta-Llama-3.1-70B-Instruct,0.37244508311079816
 Qwen2_5_3B_Instruct,0.27312609009801636
 SeaLLMs-v3-7B-Chat,0.30981028289420137

results/flores_translation/zero_shot/zho2eng.csv

@@ -7,7 +7,7 @@ Qwen2_5_7B_Instruct,0.2437311220019033
 Qwen2_5_1_5B_Instruct,0.18420680441018222
 Qwen2-72B-Instruct,0.23893268538329387
 Meta-Llama-3-8B-Instruct,0.199495011482748
-merged_llama3_8b_sg_inst_avg_diff,0.24133164017585856
+MERaLiON-Llama-3-8B-Instruct,0.24133164017585856
 Meta-Llama-3.1-70B-Instruct,0.2832594176173152
 Qwen2_5_3B_Instruct,0.2245195134637718
 SeaLLMs-v3-7B-Chat,0.2516593644617717

results/flores_translation/zero_shot/zsm2eng.csv

@@ -7,7 +7,7 @@ Qwen2_5_7B_Instruct,0.3466422765302921
 Qwen2_5_1_5B_Instruct,0.22890805100949677
 Qwen2-72B-Instruct,0.40796892621611885
 Meta-Llama-3-8B-Instruct,0.31625368345049
-merged_llama3_8b_sg_inst_avg_diff,0.3729790018011108
+MERaLiON-Llama-3-8B-Instruct,0.3729790018011108
 Meta-Llama-3.1-70B-Instruct,0.4462132282683508
 Qwen2_5_3B_Instruct,0.31056841204320457
 SeaLLMs-v3-7B-Chat,0.3484133510670942

results/fundamental_nlp_tasks/zero_shot/c3.csv

@@ -7,7 +7,7 @@ Qwen2_5_7B_Instruct,0.9121166791323859
 Qwen2_5_1_5B_Instruct,0.793941660433807
 Qwen2-72B-Instruct,0.9611069558713538
 Meta-Llama-3-8B-Instruct,0.8515332834704562
-merged_llama3_8b_sg_inst_avg_diff,0.8706058339566193
+MERaLiON-Llama-3-8B-Instruct,0.8706058339566193
 Meta-Llama-3.1-70B-Instruct,0.9603590127150337
 Qwen2_5_3B_Instruct,0.8668661181750187
 SeaLLMs-v3-7B-Chat,0.9143605086013463

results/fundamental_nlp_tasks/zero_shot/cola.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.7497603068072867
 Qwen2-72B-Instruct,0.8341323106423778
 Sailor2-8B-Chat,0.7900287631831256
 Meta-Llama-3-8B-Instruct,0.6548418024928092
-merged_llama3_8b_sg_inst_avg_diff,0.6174496644295302
+MERaLiON-Llama-3-8B-Instruct,0.6174496644295302
 Meta-Llama-3.1-70B-Instruct,0.850431447746884
 Qwen2_5_3B_Instruct,0.6644295302013423
 SeaLLMs-v3-7B-Chat,0.785234899328859

results/fundamental_nlp_tasks/zero_shot/mnli.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.6045
 Qwen2-72B-Instruct,0.7925
 Sailor2-8B-Chat,0.664
 Meta-Llama-3-8B-Instruct,0.546
-merged_llama3_8b_sg_inst_avg_diff,0.5375
+MERaLiON-Llama-3-8B-Instruct,0.5375
 Meta-Llama-3.1-70B-Instruct,0.7015
 Qwen2_5_3B_Instruct,0.7465
 SeaLLMs-v3-7B-Chat,0.653

results/fundamental_nlp_tasks/zero_shot/mrpc.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.6838235294117647
 Qwen2-72B-Instruct,0.8063725490196079
 Sailor2-8B-Chat,0.7769607843137255
 Meta-Llama-3-8B-Instruct,0.678921568627451
-merged_llama3_8b_sg_inst_avg_diff,0.6274509803921569
+MERaLiON-Llama-3-8B-Instruct,0.6274509803921569
 Meta-Llama-3.1-70B-Instruct,0.7696078431372549
 Qwen2_5_3B_Instruct,0.5661764705882353
 SeaLLMs-v3-7B-Chat,0.7475490196078431

results/fundamental_nlp_tasks/zero_shot/ocnli.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5135593220338983
 Qwen2-72B-Instruct,0.7820338983050847
 Sailor2-8B-Chat,0.5569491525423729
 Meta-Llama-3-8B-Instruct,0.44033898305084745
-merged_llama3_8b_sg_inst_avg_diff,0.4633898305084746
+MERaLiON-Llama-3-8B-Instruct,0.4633898305084746
 Meta-Llama-3.1-70B-Instruct,0.6423728813559322
 Qwen2_5_3B_Instruct,0.6145762711864406
 SeaLLMs-v3-7B-Chat,0.5698305084745763

results/fundamental_nlp_tasks/zero_shot/qnli.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.6148636280431997
 Qwen2-72B-Instruct,0.8887058392824455
 Sailor2-8B-Chat,0.6822258832143511
 Meta-Llama-3-8B-Instruct,0.6025993044114956
-merged_llama3_8b_sg_inst_avg_diff,0.6522057477576423
+MERaLiON-Llama-3-8B-Instruct,0.6522057477576423
 Meta-Llama-3.1-70B-Instruct,0.9026176093721399
 Qwen2_5_3B_Instruct,0.7645982061138569
 SeaLLMs-v3-7B-Chat,0.7159070107999268

results/fundamental_nlp_tasks/zero_shot/qqp.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.731
 Qwen2-72B-Instruct,0.8065
 Sailor2-8B-Chat,0.8205
 Meta-Llama-3-8B-Instruct,0.563
-merged_llama3_8b_sg_inst_avg_diff,0.597
+MERaLiON-Llama-3-8B-Instruct,0.597
 Meta-Llama-3.1-70B-Instruct,0.815
 Qwen2_5_3B_Instruct,0.7415
 SeaLLMs-v3-7B-Chat,0.7625

results/fundamental_nlp_tasks/zero_shot/rte.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.703971119133574
 Qwen2-72B-Instruct,0.8447653429602888
 Sailor2-8B-Chat,0.8122743682310469
 Meta-Llama-3-8B-Instruct,0.6173285198555957
-merged_llama3_8b_sg_inst_avg_diff,0.6606498194945848
+MERaLiON-Llama-3-8B-Instruct,0.6606498194945848
 Meta-Llama-3.1-70B-Instruct,0.8483754512635379
 Qwen2_5_3B_Instruct,0.779783393501805
 SeaLLMs-v3-7B-Chat,0.7870036101083032

results/fundamental_nlp_tasks/zero_shot/wnli.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.4647887323943662
 Qwen2-72B-Instruct,0.8873239436619719
 Sailor2-8B-Chat,0.5492957746478874
 Meta-Llama-3-8B-Instruct,0.4788732394366197
-merged_llama3_8b_sg_inst_avg_diff,0.5492957746478874
+MERaLiON-Llama-3-8B-Instruct,0.5492957746478874
 Meta-Llama-3.1-70B-Instruct,0.8450704225352113
 Qwen2_5_3B_Instruct,0.647887323943662
 SeaLLMs-v3-7B-Chat,0.5915492957746479

results/general_reasoning/zero_shot/c_eval.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5971357409713575
 Qwen2-72B-Instruct,0.8312577833125778
 Sailor2-8B-Chat,0.5946450809464509
 Meta-Llama-3-8B-Instruct,0.4775840597758406
-merged_llama3_8b_sg_inst_avg_diff,0.5205479452054794
+MERaLiON-Llama-3-8B-Instruct,0.5205479452054794
 Meta-Llama-3.1-70B-Instruct,0.6612702366127023
 Qwen2_5_3B_Instruct,0.6537982565379825
 SeaLLMs-v3-7B-Chat,0.7658779576587795

results/general_reasoning/zero_shot/cmmlu.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5975651873596961
 Qwen2-72B-Instruct,0.8293904334311863
 Sailor2-8B-Chat,0.6416853738559835
 Meta-Llama-3-8B-Instruct,0.4839405974788465
-merged_llama3_8b_sg_inst_avg_diff,0.5171818338801588
+MERaLiON-Llama-3-8B-Instruct,0.5171818338801588
 Meta-Llama-3.1-70B-Instruct,0.6814885166637886
 Qwen2_5_3B_Instruct,0.6621481609393887
 SeaLLMs-v3-7B-Chat,0.7684337765498187

results/general_reasoning/zero_shot/indommlu.csv

@@ -7,7 +7,7 @@ Qwen2_5_7B_Instruct,0.5600507376994459
 Qwen2_5_1_5B_Instruct,0.4295346818879765
 Qwen2-72B-Instruct,0.6385606515788771
 Meta-Llama-3-8B-Instruct,0.5264703918819681
-merged_llama3_8b_sg_inst_avg_diff,0.5724013619066693
+MERaLiON-Llama-3-8B-Instruct,0.5724013619066693
 Meta-Llama-3.1-70B-Instruct,0.6740770411910008
 Qwen2_5_3B_Instruct,0.49656185326123237
 SeaLLMs-v3-7B-Chat,0.5267374324053675

results/general_reasoning/zero_shot/indommlu_no_prompt.csv

@@ -4,7 +4,7 @@ llama3-8b-cpt-sea-lionv2.1-instruct,0.559516656652647
 Qwen2_5_7B_Instruct,0.581814540356499
 Sailor2-8B-Chat,0.6342212430736365
 Meta-Llama-3-8B-Instruct,0.537686093864744
-merged_llama3_8b_sg_inst_avg_diff,0.575806128580012
+MERaLiON-Llama-3-8B-Instruct,0.575806128580012
 SeaLLMs-v3-7B-Chat,0.5406235396221376
 gemma-2-9b-it,0.6210027371653648
 gemma2-9b-cpt-sea-lionv3-instruct,0.6258762267174044

results/general_reasoning/zero_shot/mmlu.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.5646764390418305
 Qwen2-72B-Instruct,0.7922774401144083
 Sailor2-8B-Chat,0.6202359671076153
 Meta-Llama-3-8B-Instruct,0.6005720414730068
-merged_llama3_8b_sg_inst_avg_diff,0.631748301751877
+MERaLiON-Llama-3-8B-Instruct,0.631748301751877
 Meta-Llama-3.1-70B-Instruct,0.8058634250983197
 Qwen2_5_3B_Instruct,0.6118698605648909
 SeaLLMs-v3-7B-Chat,0.6670003575259207

results/general_reasoning/zero_shot/mmlu_no_prompt.csv

@@ -3,7 +3,7 @@ Meta-Llama-3.1-8B-Instruct,0.7056131569538792
 llama3-8b-cpt-sea-lionv2.1-instruct,0.6454057919199142
 Qwen2_5_7B_Instruct,0.73936360386128
 Meta-Llama-3-8B-Instruct,0.6735788344654987
-merged_llama3_8b_sg_inst_avg_diff,0.6988916696460493
+MERaLiON-Llama-3-8B-Instruct,0.6988916696460493
 SeaLLMs-v3-7B-Chat,0.6913836253128351
 gemma-2-9b-it,0.740293171254916
 gemma2-9b-cpt-sea-lionv3-instruct,0.7372899535216303

results/general_reasoning/zero_shot/zbench.csv

@@ -8,7 +8,7 @@ Qwen2_5_1_5B_Instruct,0.42424242424242425
 Qwen2-72B-Instruct,0.5757575757575758
 Sailor2-8B-Chat,0.5151515151515151
 Meta-Llama-3-8B-Instruct,0.3333333333333333
-merged_llama3_8b_sg_inst_avg_diff,0.42424242424242425
+MERaLiON-Llama-3-8B-Instruct,0.42424242424242425
 Meta-Llama-3.1-70B-Instruct,0.48484848484848486
 Qwen2_5_3B_Instruct,0.5757575757575758
 SeaLLMs-v3-7B-Chat,0.5454545454545454