🚀 cloudy-large-zh模型
cloudy-large-zh是一款專注於句子相似度任務的模型，可用於特徵提取等場景，在多個C - MTEB數據集上進行了測試，展現出了良好的性能。
📚 詳細文檔
模型基本信息
| 屬性 |
詳情 |
| 模型類型 |
句子相似度模型 |
| 標籤 |
句子轉換器、特徵提取、句子相似度、MTEB |
| 維度 |
1024 |
| 序列長度 |
1024 |
| 語言 |
中文 |
| 檢索是否需要指令 |
否 |
模型評估結果
重排序（Reranking）任務
| 數據集 |
MAP |
MRR |
| MTEB CMedQAv1 |
86.10362876754219 |
88.77880952380951 |
| MTEB CMedQAv2 |
86.94664825874587 |
89.47257936507937 |
| MTEB MMarcoReranking |
24.260352944026806 |
22.69484126984127 |
| MTEB T2Reranking |
66.83154421352779 |
76.27995669041708 |
檢索（Retrieval）任務
| 數據集 | MAP@1 | MAP@10 | MAP@100 | MAP@1000 | MAP@3 | MAP@5 | MRR@1 | MRR@10 | MRR@100 | MRR@1000 | MRR@3 | MRR@5 | NDCG@1 | NDCG@10 | NDCG@100 | NDCG@1000 | NDCG@3 | NDCG@5 | Precision@1 | Precision@10 | Precision@100 | Precision@1000 | Precision@3 | Precision@5 | Recall@1 | Recall@10 | Recall@100 | Recall@1000 | Recall@3 | Recall@5 |
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
| MTEB CmedqaRetrieval | 25.296999999999997 | 37.159 | 39.016 | 39.134 | 33.248 | 35.371 | 38.435 | 46.235 | 47.265 | 47.308 | 43.828 | 45.21 | 38.435 | 43.578 | 50.995000000000005 | 53.012 | 38.667 | 40.657 | 38.435 | 9.607000000000001 | 1.557 | 0.182 | 21.714 | 15.634 | 25.296999999999997 | 53.408 | 84.202 | 97.61 | 38.533 | 44.927 |
| MTEB CovidRetrieval | 74.763 | 82.604 | 82.795 | 82.798 | 81.437 | 82.097 | 74.816 | 82.601 | 82.787 | 82.78999999999999 | 81.472 | 82.146 | 74.921 | 85.83 | 86.655 | 86.748 | 83.497 | 84.696 | 74.921 | 9.663 | 1.0030000000000001 | 0.101 | 29.996000000000002 | 18.609 | 74.763 | 95.627 | 99.262 | 100.0 | 89.357 | 92.255 |
| MTEB DuRetrieval | 26.021 | 78.561 | 81.291 | 81.34400000000001 | 54.55799999999999 | 68.804 | 89.8 | 92.905 | 92.976 | 92.979 | 92.608 | 92.783 | 89.8 | 86.203 | 88.955 | 89.442 | 85.163 | 84.057 | 89.8 | 41.175 | 4.744000000000001 | 0.486 | 76.283 | 64.41 | 26.021 | 87.25 | 96.154 | 98.615 | 56.830999999999996 | 73.518 |
| MTEB EcomRetrieval | 52.300000000000004 | 62.149 | 62.719 | 62.73 | 59.767 | 61.232 | 52.300000000000004 | 62.149 | 62.719 | 62.73 | 59.767 | 61.232 | 52.300000000000004 | 66.99300000000001 | 69.672 | 69.95400000000001 | 62.166 | 64.804 | 52.300000000000004 | 8.219999999999999 | 0.9450000000000001 | 0.097 | 23.033 | 15.1 | 52.300000000000004 | 82.19999999999999 | 94.5 | 96.7 | 69.1 | 75.5 |
| MTEB MMarcoRetrieval | 64.888 | 73.921 | 74.28099999999999 | 74.295 | 72.04 | 73.207 | 67.092 | 74.547 | 74.862 | 74.875 | 72.908 | 73.936 | 67.092 | 77.687 | 79.24600000000001 | 79.60000000000001 | 74.124 | 76.098 | 67.092 | 9.424000000000001 | 1.019 | 0.105 | 27.927000000000003 | 17.797 | 64.888 | 88.672 | 95.599 | 98.337 | 79.27499999999999 | 83.96000000000001 |
| MTEB MedicalRetrieval | 55.50000000000001 | 61.316 | 61.832 | 61.867000000000004 | 59.9 | 60.685 | 55.7 | 61.416000000000004 | 61.931999999999995 | 61.967000000000006 | 60.0 | 60.785 | 55.50000000000001 | 64.228 | 67.04599999999999 | 68.176 | 61.314 | 62.743 | 55.50000000000001 | 7.340000000000001 | 0.873 | 0.097 | 21.8 | 13.780000000000001 | 55.50000000000001 | 73.4 | 87.3 | 96.6 | 65.4 | 68.89999999999999 |
| MTEB T2Retrieval | 28.303 | 76.943 | 80.585 | 80.657 | 54.818999999999996 | 66.854 | 90.742 | 93.496 | 93.55799999999999 | 93.56 | 93.083 | 93.349 | 90.742 | 84.94 | 88.616 | 89.25 | 86.58200000000001 | 85.018 | 90.742 | 41.507 | 4.984999999999999 | 0.515 | 75.101 | 62.543000000000006 | 28.303 | 83.895 | 95.537 | 98.558 | 56.679 | 70.535 |
| MTEB VideoRetrieval | 59.5 | 69.53 | 69.976 | 69.99300000000001 | 67.85 | 68.83 | 59.5 | 69.53 | 69.976 | 69.99300000000001 | 67.85 | 68.83 | 59.5 | 73.855 | 75.831 | 76.227 | 70.418 | 72.18599999999999 | 59.5 | 8.72 | 0.96 | 0.099 | 25.933 | 16.42 | 59.5 | 87.2 | 96.0 | 99.0 | 77.8 | 82.1 |
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers 支持多種語言