Dmeta Embedding Zh Small
D
Dmeta Embedding Zh Small
由 DMetaSoul 开发
Dmeta-embedding-zh-small 是一款在多个自然语言处理任务中表现优异的模型，特别适用于中文文本处理。
下载量 10.76k
发布时间 : 3/25/2024
模型简介
该模型在语义文本相似度、分类、聚类、重排序和检索等任务中表现出色，适用于中文文本的嵌入表示生成。
模型特点
多任务性能优异
在多种自然语言处理任务中均表现出色，包括语义相似度计算、文本分类等。
中文优化
专门针对中文文本进行优化，在中文数据集上表现优异。
高效检索能力
在检索任务中展现出高效的性能，适合构建中文搜索引擎或问答系统。
模型能力
语义文本相似度计算
文本分类
文本聚类
检索结果重排序
信息检索
使用案例
搜索引擎
中文网页检索
用于构建中文网页搜索引擎的核心嵌入模型
在C-MTEB/CmedqaRetrieval数据集上map@10达到35.952
问答系统
医疗问答检索
用于医疗领域问答系统的答案检索
在C-MTEB/CMedQAv1-reranking任务上mrr达到88.799
电商应用
商品评论分类
用于电商平台商品评论的情感分析和分类
在C-MTEB/JDReview-classification任务上准确率达到85.572
🚀 Dmeta-embedding-zh-small
Dmeta-embedding-zh-small 是一款在多个自然语言处理任务中表现优异的模型，通过在不同数据集上的评估，展现了其在语义文本相似度、分类、聚类、重排序和检索等任务中的性能。
📚 详细文档
模型评估结果
| 任务类型 | 数据集 | 指标 | 值 |
|---|---|---|---|
| STS | C-MTEB/AFQMC | cos_sim_pearson | 55.38441014851534 |
| STS | C-MTEB/AFQMC | cos_sim_spearman | 59.54284362578262 |
| STS | C-MTEB/AFQMC | euclidean_pearson | 58.18592108890414 |
| STS | C-MTEB/AFQMC | euclidean_spearman | 59.54284362133902 |
| STS | C-MTEB/AFQMC | manhattan_pearson | 58.142197046175916 |
| STS | C-MTEB/AFQMC | manhattan_spearman | 59.47943468645265 |
| STS | C-MTEB/ATEC | cos_sim_pearson | 55.96911621560259 |
| STS | C-MTEB/ATEC | cos_sim_spearman | 58.6334496101353 |
| STS | C-MTEB/ATEC | euclidean_pearson | 62.78426382809823 |
| STS | C-MTEB/ATEC | euclidean_spearman | 58.63344961011331 |
| STS | C-MTEB/ATEC | manhattan_pearson | 62.80625401678188 |
| STS | C-MTEB/ATEC | manhattan_spearman | 58.618722128260394 |
| Classification | mteb/amazon_reviews_multi | accuracy | 44.88 |
| Classification | mteb/amazon_reviews_multi | f1 | 42.739249460584375 |
| STS | C-MTEB/BQ | cos_sim_pearson | 68.56815521242152 |
| STS | C-MTEB/BQ | cos_sim_spearman | 70.30776353631751 |
| STS | C-MTEB/BQ | euclidean_pearson | 69.10087719019191 |
| STS | C-MTEB/BQ | euclidean_spearman | 70.30775660748148 |
| STS | C-MTEB/BQ | manhattan_pearson | 69.0672710967445 |
| STS | C-MTEB/BQ | manhattan_spearman | 70.31940638148254 |
| Clustering | C-MTEB/CLSClusteringP2P | v_measure | 40.7861976704356 |
| Clustering | C-MTEB/CLSClusteringS2S | v_measure | 38.43028280281822 |
| Reranking | C-MTEB/CMedQAv1-reranking | map | 86.78386695617407 |
| Reranking | C-MTEB/CMedQAv1-reranking | mrr | 88.79857142857142 |
| Reranking | C-MTEB/CMedQAv2-reranking | map | 87.38582377194436 |
| Reranking | C-MTEB/CMedQAv2-reranking | mrr | 89.17158730158731 |
| Retrieval | C-MTEB/CmedqaRetrieval | map_at_1 | 23.746000000000002 |
| Retrieval | C-MTEB/CmedqaRetrieval | map_at_10 | 35.952 |
| Retrieval | C-MTEB/CmedqaRetrieval | map_at_100 | 37.946999999999996 |
| Retrieval | C-MTEB/CmedqaRetrieval | map_at_1000 | 38.059 |
| Retrieval | C-MTEB/CmedqaRetrieval | map_at_3 | 31.680999999999997 |
| Retrieval | C-MTEB/CmedqaRetrieval | map_at_5 | 34.046 |
| Retrieval | C-MTEB/CmedqaRetrieval | mrr_at_1 | 36.409000000000006 |
| Retrieval | C-MTEB/CmedqaRetrieval | mrr_at_10 | 44.801 |
| Retrieval | C-MTEB/CmedqaRetrieval | mrr_at_100 | 45.842 |
| Retrieval | C-MTEB/CmedqaRetrieval | mrr_at_1000 | 45.885999999999996 |
| Retrieval | C-MTEB/CmedqaRetrieval | mrr_at_3 | 42.081 |
| Retrieval | C-MTEB/CmedqaRetrieval | mrr_at_5 | 43.613 |
| Retrieval | C-MTEB/CmedqaRetrieval | ndcg_at_1 | 36.409000000000006 |
| Retrieval | C-MTEB/CmedqaRetrieval | ndcg_at_10 | 42.687000000000005 |
| Retrieval | C-MTEB/CmedqaRetrieval | ndcg_at_100 | 50.352 |
| Retrieval | C-MTEB/CmedqaRetrieval | ndcg_at_1000 | 52.275000000000006 |
| Retrieval | C-MTEB/CmedqaRetrieval | ndcg_at_3 | 37.113 |
| Retrieval | C-MTEB/CmedqaRetrieval | ndcg_at_5 | 39.434000000000005 |
| Retrieval | C-MTEB/CmedqaRetrieval | precision_at_1 | 36.409000000000006 |
| Retrieval | C-MTEB/CmedqaRetrieval | precision_at_10 | 9.712 |
| Retrieval | C-MTEB/CmedqaRetrieval | precision_at_100 | 1.584 |
| Retrieval | C-MTEB/CmedqaRetrieval | precision_at_1000 | 0.182 |
| Retrieval | C-MTEB/CmedqaRetrieval | precision_at_3 | 21.096999999999998 |
| Retrieval | C-MTEB/CmedqaRetrieval | precision_at_5 | 15.498999999999999 |
| Retrieval | C-MTEB/CmedqaRetrieval | recall_at_1 | 23.746000000000002 |
| Retrieval | C-MTEB/CmedqaRetrieval | recall_at_10 | 53.596 |
| Retrieval | C-MTEB/CmedqaRetrieval | recall_at_100 | 85.232 |
| Retrieval | C-MTEB/CmedqaRetrieval | recall_at_1000 | 98.092 |
| Retrieval | C-MTEB/CmedqaRetrieval | recall_at_3 | 37.226 |
| Retrieval | C-MTEB/CmedqaRetrieval | recall_at_5 | 44.187 |
| PairClassification | C-MTEB/CMNLI | cos_sim_accuracy | 82.66987372218881 |
| PairClassification | C-MTEB/CMNLI | cos_sim_ap | 90.28715189799232 |
| PairClassification | C-MTEB/CMNLI | cos_sim_f1 | 84.108318049412 |
| PairClassification | C-MTEB/CMNLI | cos_sim_precision | 78.0849358974359 |
| PairClassification | C-MTEB/CMNLI | cos_sim_recall | 91.13864858545709 |
| PairClassification | C-MTEB/CMNLI | dot_accuracy | 82.66987372218881 |
| PairClassification | C-MTEB/CMNLI | dot_ap | 90.29346021403634 |
| PairClassification | C-MTEB/CMNLI | dot_f1 | 84.108318049412 |
| PairClassification | C-MTEB/CMNLI | dot_precision | 78.0849358974359 |
| PairClassification | C-MTEB/CMNLI | dot_recall | 91.13864858545709 |
| PairClassification | C-MTEB/CMNLI | euclidean_accuracy | 82.66987372218881 |
| PairClassification | C-MTEB/CMNLI | euclidean_ap | 90.28656734732074 |
| PairClassification | C-MTEB/CMNLI | euclidean_f1 | 84.108318049412 |
| PairClassification | C-MTEB/CMNLI | euclidean_precision | 78.0849358974359 |
| PairClassification | C-MTEB/CMNLI | euclidean_recall | 91.13864858545709 |
| PairClassification | C-MTEB/CMNLI | manhattan_accuracy | 82.70595309681299 |
| PairClassification | C-MTEB/CMNLI | manhattan_ap | 90.25413574022456 |
| PairClassification | C-MTEB/CMNLI | manhattan_f1 | 83.9924670433145 |
| PairClassification | C-MTEB/CMNLI | manhattan_precision | 79.81052631578947 |
| PairClassification | C-MTEB/CMNLI | manhattan_recall | 88.63689501987373 |
| PairClassification | C-MTEB/CMNLI | max_accuracy | 82.70595309681299 |
| PairClassification | C-MTEB/CMNLI | max_ap | 90.29346021403634 |
| PairClassification | C-MTEB/CMNLI | max_f1 | 84.108318049412 |
| Retrieval | C-MTEB/CovidRetrieval | map_at_1 | 61.38 |
| Retrieval | C-MTEB/CovidRetrieval | map_at_10 | 71.23 |
| Retrieval | C-MTEB/CovidRetrieval | map_at_100 | 71.61800000000001 |
| Retrieval | C-MTEB/CovidRetrieval | map_at_1000 | 71.63000000000001 |
| Retrieval | C-MTEB/CovidRetrieval | map_at_3 | 69.31 |
| Retrieval | C-MTEB/CovidRetrieval | map_at_5 | 70.403 |
| Retrieval | C-MTEB/CovidRetrieval | mrr_at_1 | 61.538000000000004 |
| Retrieval | C-MTEB/CovidRetrieval | mrr_at_10 | 71.28999999999999 |
| Retrieval | C-MTEB/CovidRetrieval | mrr_at_100 | 71.666 |
| Retrieval | C-MTEB/CovidRetrieval | mrr_at_1000 | 71.678 |
| Retrieval | C-MTEB/CovidRetrieval | mrr_at_3 | 69.44200000000001 |
| Retrieval | C-MTEB/CovidRetrieval | mrr_at_5 | 70.506 |
| Retrieval | C-MTEB/CovidRetrieval | ndcg_at_1 | 61.538000000000004 |
| Retrieval | C-MTEB/CovidRetrieval | ndcg_at_10 | 75.626 |
| Retrieval | C-MTEB/CovidRetrieval | ndcg_at_100 | 77.449 |
| Retrieval | C-MTEB/CovidRetrieval | ndcg_at_1000 | 77.73400000000001 |
| Retrieval | C-MTEB/CovidRetrieval | ndcg_at_3 | 71.75200000000001 |
| Retrieval | C-MTEB/CovidRetrieval | ndcg_at_5 | 73.695 |
| Retrieval | C-MTEB/CovidRetrieval | precision_at_1 | 61.538000000000004 |
| Retrieval | C-MTEB/CovidRetrieval | precision_at_10 | 9.009 |
| Retrieval | C-MTEB/CovidRetrieval | precision_at_100 | 0.9860000000000001 |
| Retrieval | C-MTEB/CovidRetrieval | precision_at_1000 | 0.101 |
| Retrieval | C-MTEB/CovidRetrieval | precision_at_3 | 26.379 |
| Retrieval | C-MTEB/CovidRetrieval | precision_at_5 | 16.797 |
| Retrieval | C-MTEB/CovidRetrieval | recall_at_1 | 61.38 |
| Retrieval | C-MTEB/CovidRetrieval | recall_at_10 | 89.199 |
| Retrieval | C-MTEB/CovidRetrieval | recall_at_100 | 97.576 |
| Retrieval | C-MTEB/CovidRetrieval | recall_at_1000 | 99.789 |
| Retrieval | C-MTEB/CovidRetrieval | recall_at_3 | 78.635 |
| Retrieval | C-MTEB/CovidRetrieval | recall_at_5 | 83.325 |
| Retrieval | C-MTEB/DuRetrieval | map_at_1 | 23.067 |
| Retrieval | C-MTEB/DuRetrieval | map_at_10 | 70.658 |
| Retrieval | C-MTEB/DuRetrieval | map_at_100 | 73.85300000000001 |
| Retrieval | C-MTEB/DuRetrieval | map_at_1000 | 73.925 |
| Retrieval | C-MTEB/DuRetrieval | map_at_3 | 48.391 |
| Retrieval | C-MTEB/DuRetrieval | map_at_5 | 61.172000000000004 |
| Retrieval | C-MTEB/DuRetrieval | mrr_at_1 | 83.1 |
| Retrieval | C-MTEB/DuRetrieval | mrr_at_10 | 88.214 |
| Retrieval | C-MTEB/DuRetrieval | mrr_at_100 | 88.298 |
| Retrieval | C-MTEB/DuRetrieval | mrr_at_1000 | 88.304 |
| Retrieval | C-MTEB/DuRetrieval | mrr_at_3 | 87.717 |
| Retrieval | C-MTEB/DuRetrieval | mrr_at_5 | 88.03699999999999 |
| Retrieval | C-MTEB/DuRetrieval | ndcg_at_1 | 83.1 |
| Retrieval | C-MTEB/DuRetrieval | ndcg_at_10 | 79.89 |
| Retrieval | C-MTEB/DuRetrieval | ndcg_at_100 | 83.829 |
| Retrieval | C-MTEB/DuRetrieval | ndcg_at_1000 | 84.577 |
| Retrieval | C-MTEB/DuRetrieval | ndcg_at_3 | 78.337 |
| Retrieval | C-MTEB/DuRetrieval | ndcg_at_5 | 77.224 |
| Retrieval | C-MTEB/DuRetrieval | precision_at_1 | 83.1 |
| Retrieval | C-MTEB/DuRetrieval | precision_at_10 | 38.934999999999995 |
| Retrieval | C-MTEB/DuRetrieval | precision_at_100 | 4.6690000000000005 |
| Retrieval | C-MTEB/DuRetrieval | precision_at_1000 | 0.484 |
| Retrieval | C-MTEB/DuRetrieval | precision_at_3 | 70.48299999999999 |
| Retrieval | C-MTEB/DuRetrieval | precision_at_5 | 59.68 |
| Retrieval | C-MTEB/DuRetrieval | recall_at_1 | 23.067 |
| Retrieval | C-MTEB/DuRetrieval | recall_at_10 | 81.702 |
| Retrieval | C-MTEB/DuRetrieval | recall_at_100 | 94.214 |
| Retrieval | C-MTEB/DuRetrieval | recall_at_1000 | 98.241 |
| Retrieval | C-MTEB/DuRetrieval | recall_at_3 | 51.538 |
| Retrieval | C-MTEB/DuRetrieval | recall_at_5 | 67.39 |
| Retrieval | C-MTEB/EcomRetrieval | map_at_1 | 49.8 |
| Retrieval | C-MTEB/EcomRetrieval | map_at_10 | 59.46399999999999 |
| Retrieval | C-MTEB/EcomRetrieval | map_at_100 | 60.063 |
| Retrieval | C-MTEB/EcomRetrieval | map_at_1000 | 60.08 |
| Retrieval | C-MTEB/EcomRetrieval | map_at_3 | 56.833 |
| Retrieval | C-MTEB/EcomRetrieval | map_at_5 | 58.438 |
| Retrieval | C-MTEB/EcomRetrieval | mrr_at_1 | 49.8 |
| Retrieval | C-MTEB/EcomRetrieval | mrr_at_10 | 59.46399999999999 |
| Retrieval | C-MTEB/EcomRetrieval | mrr_at_100 | 60.063 |
| Retrieval | C-MTEB/EcomRetrieval | mrr_at_1000 | 60.08 |
| Retrieval | C-MTEB/EcomRetrieval | mrr_at_3 | 56.833 |
| Retrieval | C-MTEB/EcomRetrieval | mrr_at_5 | 58.438 |
| Retrieval | C-MTEB/EcomRetrieval | ndcg_at_1 | 49.8 |
| Retrieval | C-MTEB/EcomRetrieval | ndcg_at_10 | 64.48 |
| Retrieval | C-MTEB/EcomRetrieval | ndcg_at_100 | 67.314 |
| Retrieval | C-MTEB/EcomRetrieval | ndcg_at_1000 | 67.745 |
| Retrieval | C-MTEB/EcomRetrieval | ndcg_at_3 | 59.06400000000001 |
| Retrieval | C-MTEB/EcomRetrieval | ndcg_at_5 | 61.973 |
| Retrieval | C-MTEB/EcomRetrieval | precision_at_1 | 49.8 |
| Retrieval | C-MTEB/EcomRetrieval | precision_at_10 | 8.04 |
| Retrieval | C-MTEB/EcomRetrieval | precision_at_100 | 0.935 |
| Retrieval | C-MTEB/EcomRetrieval | precision_at_1000 | 0.097 |
| Retrieval | C-MTEB/EcomRetrieval | precision_at_3 | 21.833 |
| Retrieval | C-MTEB/EcomRetrieval | precision_at_5 | 14.52 |
| Retrieval | C-MTEB/EcomRetrieval | recall_at_1 | 49.8 |
| Retrieval | C-MTEB/EcomRetrieval | recall_at_10 | 80.4 |
| Retrieval | C-MTEB/EcomRetrieval | recall_at_100 | 93.5 |
| Retrieval | C-MTEB/EcomRetrieval | recall_at_1000 | 96.8 |
| Retrieval | C-MTEB/EcomRetrieval | recall_at_3 | 65.5 |
| Retrieval | C-MTEB/EcomRetrieval | recall_at_5 | 72.6 |
| Classification | C-MTEB/IFlyTek-classification | accuracy | 49.111196614082345 |
| Classification | C-MTEB/IFlyTek-classification | f1 | 37.07930546974089 |
| Classification | C-MTEB/JDReview-classification | accuracy | 85.57223264540339 |
| Classification | C-MTEB/JDReview-classification | ap | 53.30690968994808 |
| Classification | C-MTEB/JDReview-classification | f1 | 80.20587062271773 |
| STS | C-MTEB/LCQMC | cos_sim_pearson | 73.03085269274996 |
| STS | C-MTEB/LCQMC | cos_sim_spearman | 78.72837937949888 |
| STS | C-MTEB/LCQMC | euclidean_pearson | 78.34911745798928 |
| STS | C-MTEB/LCQMC | euclidean_spearman | 78.72838602779268 |
| STS | C-MTEB/LCQMC | manhattan_pearson | 78.31833697617105 |
| STS | C-MTEB/LCQMC | manhattan_spearman | 78.69603741566397 |
| Reranking | C-MTEB/Mmarco-reranking | map | 27.391692468538416 |
| Reranking | C-MTEB/Mmarco-reranking | mrr | 26.44682539682539 |
| Retrieval | C-MTEB/MMarcoRetrieval | map_at_1 | 57.206999999999994 |
| Retrieval | C-MTEB/MMarcoRetrieval | map_at_10 | 66.622 |
| Retrieval | C-MTEB/MMarcoRetrieval | map_at_100 | 67.12700000000001 |
| Retrieval | C-MTEB/MMarcoRetrieval | map_at_1000 | 67.145 |
| Retrieval | C-MTEB/MMarcoRetrieval | map_at_3 | 64.587 |
| Retrieval | C-MTEB/MMarcoRetrieval | map_at_5 | 65.827 |
| Retrieval | C-MTEB/MMarcoRetrieval | mrr_at_1 | 59.312 |
| Retrieval | C-MTEB/MMarcoRetrieval | mrr_at_10 | 67.387 |
| Retrieval | C-MTEB/MMarcoRetrieval | mrr_at_100 | 67.836 |
| Retrieval | C-MTEB/MMarcoRetrieval | mrr_at_1000 | 67.851 |
| Retrieval | C-MTEB/MMarcoRetrieval | mrr_at_3 | 65.556 |
| Retrieval | C-MTEB/MMarcoRetrieval | mrr_at_5 | 66.66 |
| Retrieval | C-MTEB/MMarcoRetrieval | ndcg_at_1 | 59.312 |
| Retrieval | C-MTEB/MMarcoRetrieval | ndcg_at_10 | 70.748 |
| Retrieval | C-MTEB/MMarcoRetrieval | ndcg_at_100 | 73.076 |
| Retrieval | C-MTEB/MMarcoRetrieval | ndcg_at_1000 | 73.559 |
| Retrieval | C-MTEB/MMarcoRetrieval | ndcg_at_3 | 66.81200000000001 |
| Retrieval | C-MTEB/MMarcoRetrieval | ndcg_at_5 | 68.92399999999999 |
| Retrieval | C-MTEB/MMarcoRetrieval | precision_at_1 | 59.312 |
| Retrieval | C-MTEB/MMarcoRetrieval | precision_at_10 | 8.798 |
| Retrieval | C-MTEB/MMarcoRetrieval | precision_at_100 | 0.996 |
| Retrieval | C-MTEB/MMarcoRetrieval | precision_at_1000 | 0.104 |
| Retrieval | C-MTEB/MMarcoRetrieval | precision_at_3 | 25.487 |
| Retrieval | C-MTEB/MMarcoRetrieval | precision_at_5 | 16.401 |
| Retrieval | C-MTEB/MMarcoRetrieval | recall_at_1 | 57.206999999999994 |
| Retrieval | C-MTEB/MMarcoRetrieval | recall_at_10 | 82.767 |
| Retrieval | C-MTEB/MMarcoRetrieval | recall_at_100 | 93.449 |
| Retrieval | C-MTEB/MMarcoRetrieval | recall_at_1000 | 97.262 |
| Retrieval | C-MTEB/MMarcoRetrieval | recall_at_3 | 72.271 |
| Retrieval | C-MTEB/MMarcoRetrieval | recall_at_5 | 77.291 |
| Classification | mteb/amazon_massive_intent | accuracy | 70.78345662407531 |
| Classification | mteb/amazon_massive_intent | f1 | 68.35683436974351 |
| Classification | mteb/amazon_massive_scenario | accuracy | 73.16408876933423 |
| Classification | mteb/amazon_massive_scenario | f1 | 73.31484873459382 |
| Retrieval | C-MTEB/MedicalRetrieval | map_at_1 | 51.4 |
| Retrieval | C-MTEB/MedicalRetrieval | map_at_10 | 57.091 |
| Retrieval | C-MTEB/MedicalRetrieval | map_at_100 | 57.652 |
| Retrieval | C-MTEB/MedicalRetrieval | map_at_1000 | 57.703 |
| Retrieval | C-MTEB/MedicalRetrieval | map_at_3 | 55.733 |
| Retrieval | C-MTEB/MedicalRetrieval | map_at_5 | 56.363 |
| Retrieval | C-MTEB/MedicalRetrieval | mrr_at_1 | 51.7 |
| Retrieval | C-MTEB/MedicalRetrieval | mrr_at_10 | 57.243 |
| Retrieval | C-MTEB/MedicalRetrieval | mrr_at_100 | 57.80499999999999 |
| Retrieval | C-MTEB/MedicalRetrieval | mrr_at_1000 | 57.855999999999995 |
| Retrieval | C-MTEB/MedicalRetrieval | mrr_at_3 | 55.883 |
| Retrieval | C-MTEB/MedicalRetrieval | mrr_at_5 | 56.513000000000005 |
| Retrieval | C-MTEB/MedicalRetrieval | ndcg_at_1 | 51.4 |
| Retrieval | C-MTEB/MedicalRetrieval | ndcg_at_10 | 59.948 |
| Retrieval | C-MTEB/MedicalRetrieval | ndcg_at_100 | 63.064 |
| Retrieval | C-MTEB/MedicalRetrieval | ndcg_at_1000 | 64.523 |
| Retrieval | C-MTEB/MedicalRetrieval | ndcg_at_3 | 57.089999999999996 |
| Retrieval | C-MTEB/MedicalRetrieval | ndcg_at_5 | 58.214 |
| Retrieval | C-MTEB/MedicalRetrieval | precision_at_1 | 51.4 |
| Retrieval | C-MTEB/MedicalRetrieval | precision_at_10 | 6.9 |
| Retrieval | C-MTEB/MedicalRetrieval | precision_at_100 | 0.845 |
| Retrieval | C-MTEB/MedicalRetrieval | precision_at_1000 | 0.096 |
| Retrieval | C-MTEB/MedicalRetrieval | precision_at_3 | 20.333000000000002 |
| Retrieval | C-MTEB/MedicalRetrieval | precision_at_5 | 12.740000000000002 |
| Retrieval | C-MTEB/MedicalRetrieval | recall_at_1 | 51.4 |
| Retrieval | C-MTEB/MedicalRetrieval | recall_at_10 | 69.0 |
| Retrieval | C-MTEB/MedicalRetrieval | recall_at_100 | 84.5 |
| Retrieval | C-MTEB/MedicalRetrieval | recall_at_1000 | 96.2 |
| Retrieval | C-MTEB/MedicalRetrieval | recall_at_3 | 61.0 |
| Retrieval | C-MTEB/MedicalRetrieval | recall_at_5 | 63.7 |
| Classification | C-MTEB/MultilingualSentiment-classification | accuracy | 74.38999999999999 |
| Classification | C-MTEB/MultilingualSentiment-classification | f1 | 74.07161306140839 |
| PairClassification | C-MTEB/OCNLI | cos_sim_accuracy | 81.15863562533838 |
| PairClassification | C-MTEB/OCNLI | cos_sim_ap | 84.84571607908443 |
| PairClassification | C-MTEB/OCNLI | cos_sim_f1 | 82.55872063968016 |
| PairClassification | C-MTEB/OCNLI | cos_sim_precision | 78.36812144212524 |
| PairClassification | C-MTEB/OCNLI | cos_sim_recall | 87.22280887011615 |
| PairClassification | C-MTEB/OCNLI | dot_accuracy | 81.15863562533838 |
| PairClassification | C-MTEB/OCNLI | dot_ap | 84.84571607908443 |
| PairClassification | C-MTEB/OCNLI | dot_f1 | 82.55872063968016 |
| PairClassification | C-MTEB/OCNLI | dot_precision | 78.36812144212524 |
| PairClassification | C-MTEB/OCNLI | dot_recall | 87.22280887011615 |
| PairClassification | C-MTEB/OCNLI | euclidean_accuracy | 81.15863562533838 |
| PairClassification | C-MTEB/OCNLI | euclidean_ap | 84.84571607908443 |
| PairClassification | C-MTEB/OCNLI | euclidean_f1 | 82.55872063968016 |
| PairClassification | C-MTEB/OCNLI | euclidean_precision | 78.36812144212524 |
| PairClassification | C-MTEB/OCNLI | euclidean_recall | 87.22280887011615 |
| PairClassification | C-MTEB/OCNLI | manhattan_accuracy | 80.7796426637791 |
| PairClassification | C-MTEB/OCNLI | manhattan_ap | 84.81524098914134 |
| PairClassification | C-MTEB/OCNLI | manhattan_f1 | 82.36462990561351 |
| PairClassification | C-MTEB/OCNLI | manhattan_precision | 77.76735459662288 |
| PairClassification | C-MTEB/OCNLI | manhattan_recall | 87.53959873284055 |
| PairClassification | C-MTEB/OCNLI | max_accuracy | 81.15863562533838 |
| PairClassification | C-MTEB/OCNLI | max_ap | 84.84571607908443 |
| PairClassification | C-MTEB/OCNLI | max_f1 | 82.55872063968016 |
| Classification | C-MTEB/OnlineShopping-classification | accuracy | 93.12000000000002 |
| Classification | C-MTEB/OnlineShopping-classification | ap | 91.0749103088623 |
| Classification | C-MTEB/OnlineShopping-classification | f1 | 93.10837266607813 |
| STS | C-MTEB/PAWSX | cos_sim_pearson | 38.5692290188029 |
| STS | C-MTEB/PAWSX | cos_sim_spearman | 42.965264868554335 |
| STS | C-MTEB/PAWSX | euclidean_pearson | 43.002526263615735 |
| STS | C-MTEB/PAWSX | euclidean_spearman | 42.97561576045246 |
| STS | C-MTEB/PAWSX | manhattan_pearson | 43.050089639788936 |
| STS | C-MTEB/PAWSX | manhattan_spearman | 43.038497558804934 |
| STS | C-MTEB/QBQTC | cos_sim_pearson | 38.99284895602663 |
| STS | C-MTEB/QBQTC | cos_sim_spearman | 41.02655813481606 |
| STS | C-MTEB/QBQTC | euclidean_pearson | 38.934953519378354 |
| STS | C-MTEB/QBQTC | euclidean_spearman | 41.02680077136343 |
| STS | C-MTEB/QBQTC | manhattan_pearson | 39.224809609807785 |
| STS | C-MTEB/QBQTC | manhattan_spearman | 41.13950779185706 |
| STS | mteb/sts22-crosslingual-sts | cos_sim_pearson | 66.47464607633356 |
| STS | mteb/sts22-crosslingual-sts | cos_sim_spearman | 66.76311382148693 |
| STS | mteb/sts22-crosslingual-sts | euclidean_pearson | 67.25180409604143 |
| STS | mteb/sts22-crosslingual-sts | euclidean_spearman | 66.76311382148693 |
| STS | mteb/sts22-crosslingual-sts | manhattan_pearson | 67.6928257682864 |
| STS | mteb/sts22-crosslingual-sts | manhattan_spearman | 67.08172581019826 |
| STS | C-MTEB/STSB |
Jina Embeddings V3
Jina Embeddings V3 是一个多语言句子嵌入模型，支持超过100种语言，专注于句子相似度和特征提取任务。
文本嵌入
Transformers 支持多种语言
Transformers 支持多种语言J
jinaai
3.7M
911
Ms Marco MiniLM L6 V2
Apache-2.0
基于MS Marco段落排序任务训练的交叉编码器模型，用于信息检索中的查询-段落相关性评分
文本嵌入 英语
M
cross-encoder
2.5M
86
Opensearch Neural Sparse Encoding Doc V2 Distill
Apache-2.0
基于蒸馏技术的稀疏检索模型，专为OpenSearch优化，支持免推理文档编码，在搜索相关性和效率上优于V1版本
文本嵌入 Transformers 英语
Transformers 英语O
opensearch-project
1.8M
7
Sapbert From PubMedBERT Fulltext
Apache-2.0
基于PubMedBERT的生物医学实体表征模型，通过自对齐预训练优化语义关系捕捉
文本嵌入 英语
S
cambridgeltl
1.7M
49
Gte Large
MIT
GTE-Large 是一个强大的句子转换器模型，专注于句子相似度和文本嵌入任务，在多个基准测试中表现出色。
文本嵌入 英语
G
thenlper
1.5M
278
Gte Base En V1.5
Apache-2.0
GTE-base-en-v1.5 是一个英文句子转换器模型，专注于句子相似度任务，在多个文本嵌入基准测试中表现优异。
文本嵌入 Transformers 支持多种语言
Transformers 支持多种语言G
Alibaba-NLP
1.5M
63
Gte Multilingual Base
Apache-2.0
GTE Multilingual Base 是一个多语言的句子嵌入模型，支持超过50种语言，适用于句子相似度计算等任务。
文本嵌入 Transformers 支持多种语言
Transformers 支持多种语言G
Alibaba-NLP
1.2M
246
Polybert
polyBERT是一个化学语言模型，旨在实现完全由机器驱动的超快聚合物信息学。它将PSMILES字符串映射为600维密集指纹，以数值形式表示聚合物化学结构。
文本嵌入 Transformers
TransformersP
kuelumbus
1.0M
5
Bert Base Turkish Cased Mean Nli Stsb Tr
Apache-2.0
基于土耳其语BERT的句子嵌入模型，专为语义相似度任务优化
文本嵌入 Transformers 其他
Transformers 其他B
emrecan
1.0M
40
GIST Small Embedding V0
MIT
基于BAAI/bge-small-en-v1.5模型微调的文本嵌入模型，通过MEDI数据集与MTEB分类任务数据集训练，优化了检索任务的查询编码能力。
文本嵌入
Safetensors 英语
Safetensors 英语G
avsolatorio
945.68k
29
精选推荐AI模型
Llama 3 Typhoon V1.5x 8b Instruct
专为泰语设计的80亿参数指令模型，性能媲美GPT-3.5-turbo，优化了应用场景、检索增强生成、受限生成和推理任务
大型语言模型 Transformers 支持多种语言
Transformers 支持多种语言L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一个基于SODA数据集训练的超小型对话模型，专为边缘设备推理设计，体积仅为Cosmo-3B模型的2%左右。
对话系统 Transformers 英语
Transformers 英语C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基于RoBERTa架构的中文抽取式问答模型，适用于从给定文本中提取答案的任务。
问答系统 中文
R
uer
2,694
98
%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)
智启未来，您的人工智能解决方案智库
简体中文