Spaces:
Running
Running
Add Qwen3-32B results
Browse files- results/zero-shot/Qwen3-32B.json +201 -0
results/zero-shot/Qwen3-32B.json
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": {
|
| 3 |
+
"model": "Qwen/Qwen3-32B",
|
| 4 |
+
"architecture": "Qwen3ForCausalLM",
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"type": "instruction-tuned",
|
| 7 |
+
"num_parameters": "32b",
|
| 8 |
+
"api": "hf"
|
| 9 |
+
},
|
| 10 |
+
"results": [
|
| 11 |
+
{
|
| 12 |
+
"name": "xquad_tr",
|
| 13 |
+
"task": "extractive_question_answering",
|
| 14 |
+
"exact_match": 0.07394957983193277,
|
| 15 |
+
"f1": 0.18168641044790357
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"name": "xcopa_tr",
|
| 19 |
+
"task": "multiple_choice",
|
| 20 |
+
"acc": 0.71,
|
| 21 |
+
"acc_norm": 0.71
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"name": "turkishmmlu",
|
| 25 |
+
"task": "multiple_choice",
|
| 26 |
+
"acc": 0.13555555555555557,
|
| 27 |
+
"acc_norm": 0.13555555555555557
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"name": "turkish_plu",
|
| 31 |
+
"task": "multiple_choice",
|
| 32 |
+
"acc": 0.53888,
|
| 33 |
+
"acc_norm": 0.43808
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"name": "turkish_plu_goal_inference",
|
| 37 |
+
"task": "multiple_choice",
|
| 38 |
+
"acc": 0.47192353643966545,
|
| 39 |
+
"acc_norm": 0.2986857825567503
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"name": "turkish_plu_next_event_prediction",
|
| 43 |
+
"task": "multiple_choice",
|
| 44 |
+
"acc": 0.5526717557251909,
|
| 45 |
+
"acc_norm": 0.29770992366412213
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"name": "turkish_plu_step_inference",
|
| 49 |
+
"task": "multiple_choice",
|
| 50 |
+
"acc": 0.4035947712418301,
|
| 51 |
+
"acc_norm": 0.39869281045751637
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"name": "turkish_plu_step_ordering",
|
| 55 |
+
"task": "multiple_choice",
|
| 56 |
+
"acc": 0.6660137120470128,
|
| 57 |
+
"acc_norm": 0.6660137120470128
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"name": "turkce_atasozleri",
|
| 61 |
+
"task": "multiple_choice",
|
| 62 |
+
"acc": 0.8682080924855491,
|
| 63 |
+
"acc_norm": 0.8682080924855491
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"name": "check_worthiness",
|
| 67 |
+
"task": "multiple_choice",
|
| 68 |
+
"acc": 0.5594149908592322,
|
| 69 |
+
"acc_norm": 0.6238574040219378
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"name": "relevance_judgment",
|
| 73 |
+
"task": "multiple_choice",
|
| 74 |
+
"acc": 0.600091407678245,
|
| 75 |
+
"acc_norm": 0.5781535648994516
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"name": "tquad",
|
| 79 |
+
"task": "extractive_question_answering",
|
| 80 |
+
"exact_match": 0.10089686098654709,
|
| 81 |
+
"f1": 0.2031672244380758
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"name": "sts_tr",
|
| 85 |
+
"task": "text_classification",
|
| 86 |
+
"acc": 0.19289340101522842,
|
| 87 |
+
"acc_norm": 0.11820159535895576
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"name": "offenseval_tr",
|
| 91 |
+
"task": "text_classification",
|
| 92 |
+
"acc": 0.23469387755102042,
|
| 93 |
+
"acc_norm": 0.7970521541950113
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"name": "mnli_tr",
|
| 97 |
+
"task": "natural_language_inference",
|
| 98 |
+
"acc": 0.3214,
|
| 99 |
+
"acc_norm": 0.3213
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"name": "snli_tr",
|
| 103 |
+
"task": "natural_language_inference",
|
| 104 |
+
"acc": 0.334,
|
| 105 |
+
"acc_norm": 0.3234
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"name": "xnli_tr",
|
| 109 |
+
"task": "natural_language_inference",
|
| 110 |
+
"acc": 0.3267465069860279,
|
| 111 |
+
"acc_norm": 0.3333333333333333
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"name": "news_cat",
|
| 115 |
+
"task": "text_classification",
|
| 116 |
+
"acc": 0.532,
|
| 117 |
+
"acc_norm": 0.324
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"name": "ironytr",
|
| 121 |
+
"task": "text_classification",
|
| 122 |
+
"acc": 0.515,
|
| 123 |
+
"acc_norm": 0.5
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"name": "exams_tr",
|
| 127 |
+
"task": "multiple_choice",
|
| 128 |
+
"acc": 0.356234096692112,
|
| 129 |
+
"acc_norm": 0.33587786259541985
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"name": "circumflex_tr",
|
| 133 |
+
"task": "multiple_choice",
|
| 134 |
+
"acc": 0.5857142857142857,
|
| 135 |
+
"acc_norm": 0.5857142857142857
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"name": "bilmecebench",
|
| 139 |
+
"task": "multiple_choice",
|
| 140 |
+
"acc": 0.6131221719457014,
|
| 141 |
+
"acc_norm": 0.6131221719457014
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"name": "belebele_tr",
|
| 145 |
+
"task": "multiple_choice",
|
| 146 |
+
"acc": 0.8644444444444445,
|
| 147 |
+
"acc_norm": 0.8644444444444445
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"name": "turkishmmlu",
|
| 151 |
+
"task": "multiple_choice",
|
| 152 |
+
"acc": 0.6677777777777778,
|
| 153 |
+
"acc_norm": 0.6677777777777778
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"name": "xlsum_tr",
|
| 157 |
+
"task": "summarization",
|
| 158 |
+
"rouge1": 0.30984540466217936,
|
| 159 |
+
"rouge2": 0.1526819990882598,
|
| 160 |
+
"rougeL": 0.24056293296185868
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"name": "wmt-tr-en-prompt",
|
| 164 |
+
"task": "machine_translation",
|
| 165 |
+
"wer": 1.9097642345703865,
|
| 166 |
+
"bleu": 0.07525786863429962
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"name": "wiki_lingua_tr",
|
| 170 |
+
"task": "summarization",
|
| 171 |
+
"rouge1": 0.19307064669127558,
|
| 172 |
+
"rouge2": 0.07085141067185688,
|
| 173 |
+
"rougeL": 0.14979216116861716
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"name": "tr-wikihow-summ",
|
| 177 |
+
"task": "summarization",
|
| 178 |
+
"rouge1": 0.19704935938448176,
|
| 179 |
+
"rouge2": 0.06326750543141127,
|
| 180 |
+
"rougeL": 0.1459271843295593
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"name": "mlsum_tr",
|
| 184 |
+
"task": "summarization",
|
| 185 |
+
"rouge1": 0.4022274311113533,
|
| 186 |
+
"rouge2": 0.255063284434877,
|
| 187 |
+
"rougeL": 0.33089850060045467
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"name": "gecturk_generation",
|
| 191 |
+
"task": "grammatical_error_correction",
|
| 192 |
+
"exact_match": 0.2694400308151572
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"name": "mkqa_tr",
|
| 196 |
+
"task": "extractive_question_answering",
|
| 197 |
+
"exact_match": 0.011245930748742231,
|
| 198 |
+
"f1": 0.044142577167201706
|
| 199 |
+
}
|
| 200 |
+
]
|
| 201 |
+
}
|