Name: embedding-benchmark/MIRACLRerankingDownsampled
Creator: embedding-benchmark
Published: 2026-04-17 12:15:58
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/embedding-benchmark/MIRACLRerankingDownsampled

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: ar-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 94914703.19880481 num_examples: 117605 download_size: 47483280 dataset_size: 94914703.19880481 - config_name: ar-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 288227 num_examples: 10081 download_size: 107236 dataset_size: 288227 - config_name: ar-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 66509 num_examples: 1000 download_size: 37992 dataset_size: 66509 - config_name: ar-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 3170621 num_examples: 1000 download_size: 1764519 dataset_size: 3170621 - config_name: bn-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 66409513.16677039 num_examples: 63830 download_size: 26369204 dataset_size: 66409513.16677039 - config_name: bn-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 113824 num_examples: 4206 download_size: 40805 dataset_size: 113824 - config_name: bn-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 55939 num_examples: 411 download_size: 25029 dataset_size: 55939 - config_name: bn-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 1221514 num_examples: 411 download_size: 659629 dataset_size: 1221514 - config_name: de-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 24022111.44380375 num_examples: 44204 download_size: 15909493 dataset_size: 24022111.44380375 - config_name: de-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 105647 num_examples: 3144 download_size: 37102 dataset_size: 105647 - config_name: de-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 19450 num_examples: 305 download_size: 14582 dataset_size: 19450 - config_name: de-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 990384 num_examples: 305 download_size: 521595 dataset_size: 990384 - config_name: en-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 66828586.48429249 num_examples: 121098 download_size: 46460694 dataset_size: 66828586.48429249 - config_name: en-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 242967 num_examples: 8350 download_size: 92748 dataset_size: 242967 - config_name: en-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 41576 num_examples: 799 download_size: 28948 dataset_size: 41576 - config_name: en-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 2702552 num_examples: 799 download_size: 1686157 dataset_size: 2702552 - config_name: es-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 52456963.53967973 num_examples: 92382 download_size: 33620535 dataset_size: 52456963.53967973 - config_name: es-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 215688 num_examples: 6443 download_size: 73182 dataset_size: 215688 - config_name: es-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 43504 num_examples: 648 download_size: 29571 dataset_size: 43504 - config_name: es-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 2103359 num_examples: 648 download_size: 1175431 dataset_size: 2103359 - config_name: fa-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 67028102.84709123 num_examples: 87607 download_size: 33798396 dataset_size: 67028102.84709123 - config_name: fa-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 216792 num_examples: 6571 download_size: 72765 dataset_size: 216792 - config_name: fa-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 58114 num_examples: 632 download_size: 32759 dataset_size: 58114 - config_name: fa-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 1995862 num_examples: 632 download_size: 1039456 dataset_size: 1995862 - config_name: fi-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 54157044.43336162 num_examples: 108517 download_size: 31921307 dataset_size: 54157044.43336162 - config_name: fi-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 262605 num_examples: 9436 download_size: 92891 dataset_size: 262605 - config_name: fi-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 51734 num_examples: 1000 download_size: 36471 dataset_size: 51734 - config_name: fi-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 3036568 num_examples: 1000 download_size: 1557009 dataset_size: 3036568 - config_name: fr-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 24666920.98979524 num_examples: 49634 download_size: 16316172 dataset_size: 24666920.98979524 - config_name: fr-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 115836 num_examples: 3429 download_size: 39712 dataset_size: 115836 - config_name: fr-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 21433 num_examples: 343 download_size: 14877 dataset_size: 21433 - config_name: fr-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 1121744 num_examples: 343 download_size: 579142 dataset_size: 1121744 - config_name: hi-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 54310898.977452196 num_examples: 41808 download_size: 23056200 dataset_size: 54310898.977452196 - config_name: hi-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 111217 num_examples: 3494 download_size: 37580 dataset_size: 111217 - config_name: hi-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 54122 num_examples: 350 download_size: 25941 dataset_size: 54122 - config_name: hi-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 1059433 num_examples: 350 download_size: 489134 dataset_size: 1059433 - config_name: id-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 58714418.48596386 num_examples: 113860 download_size: 34203447 dataset_size: 58714418.48596386 - config_name: id-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 263958 num_examples: 9668 download_size: 92612 dataset_size: 263958 - config_name: id-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 47803 num_examples: 960 download_size: 30679 dataset_size: 47803 - config_name: id-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 2948910 num_examples: 960 download_size: 1589306 dataset_size: 2948910 - config_name: ja-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 13466672.945364479 num_examples: 22514 download_size: 8837658 dataset_size: 13466672.945364479 - config_name: ja-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 236068 num_examples: 8354 download_size: 85925 dataset_size: 236068 - config_name: ja-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 55179 num_examples: 860 download_size: 34096 dataset_size: 55179 - config_name: ja-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 2673867 num_examples: 860 download_size: 370358 dataset_size: 2673867 - config_name: ko-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 14825970.209779872 num_examples: 23737 download_size: 9161969 dataset_size: 14825970.209779872 - config_name: ko-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 83188 num_examples: 3057 download_size: 31571 dataset_size: 83188 - config_name: ko-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 13875 num_examples: 213 download_size: 10030 dataset_size: 13875 - config_name: ko-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 633622 num_examples: 213 download_size: 277466 dataset_size: 633622 - config_name: ru-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 110518164.55353378 num_examples: 125341 download_size: 51957289 dataset_size: 110518164.55353378 - config_name: ru-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 298924 num_examples: 10470 download_size: 110477 dataset_size: 298924 - config_name: ru-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 92517 num_examples: 1000 download_size: 53448 dataset_size: 92517 - config_name: ru-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 3227807 num_examples: 1000 download_size: 1936072 dataset_size: 3227807 - config_name: sw-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 10585059.560595494 num_examples: 42617 download_size: 6163053 dataset_size: 10585059.560595494 - config_name: sw-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 135409 num_examples: 5092 download_size: 45442 dataset_size: 135409 - config_name: sw-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 24357 num_examples: 482 download_size: 15728 dataset_size: 24357 - config_name: sw-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 1344855 num_examples: 482 download_size: 507676 dataset_size: 1344855 - config_name: te-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 93363524.33578525 num_examples: 58319 download_size: 32349875 dataset_size: 93363524.33578525 - config_name: te-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 43268 num_examples: 1606 download_size: 19742 dataset_size: 43268 - config_name: te-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 95102 num_examples: 828 download_size: 38671 dataset_size: 95102 - config_name: te-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 2433095 num_examples: 828 download_size: 817298 dataset_size: 2433095 - config_name: th-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 104307792.51621531 num_examples: 76737 download_size: 39295638 dataset_size: 104307792.51621531 - config_name: th-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 208002 num_examples: 7573 download_size: 72960 dataset_size: 208002 - config_name: th-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 98697 num_examples: 733 download_size: 45069 dataset_size: 98697 - config_name: th-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 2178686 num_examples: 733 download_size: 942279 dataset_size: 2178686 - config_name: yo-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 2152524.9245356116 num_examples: 9922 download_size: 1710602 dataset_size: 2152524.9245356116 - config_name: yo-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 35512 num_examples: 1188 download_size: 11075 dataset_size: 35512 - config_name: yo-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 6697 num_examples: 119 download_size: 5813 dataset_size: 6697 - config_name: yo-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 329720 num_examples: 119 download_size: 109356 dataset_size: 329720 - config_name: zh-corpus features: - name: id dtype: string - name: text dtype: string - name: title dtype: string splits: - name: dev num_bytes: 743209.8867899003 num_examples: 1735 download_size: 704491 dataset_size: 743209.8867899003 - config_name: zh-qrels features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: dev num_bytes: 129492 num_examples: 3928 download_size: 43632 dataset_size: 129492 - config_name: zh-queries features: - name: id dtype: string - name: text dtype: string splits: - name: dev num_bytes: 19261 num_examples: 393 download_size: 13987 dataset_size: 19261 - config_name: zh-top_ranked features: - name: query-id dtype: string - name: corpus-ids sequence: string splits: - name: dev num_bytes: 1308662 num_examples: 393 download_size: 44371 dataset_size: 1308662 configs: - config_name: ar-corpus data_files: - split: dev path: ar-corpus/dev-* - config_name: ar-qrels data_files: - split: dev path: ar-qrels/dev-* - config_name: ar-queries data_files: - split: dev path: ar-queries/dev-* - config_name: ar-top_ranked data_files: - split: dev path: ar-top_ranked/dev-* - config_name: bn-corpus data_files: - split: dev path: bn-corpus/dev-* - config_name: bn-qrels data_files: - split: dev path: bn-qrels/dev-* - config_name: bn-queries data_files: - split: dev path: bn-queries/dev-* - config_name: bn-top_ranked data_files: - split: dev path: bn-top_ranked/dev-* - config_name: de-corpus data_files: - split: dev path: de-corpus/dev-* - config_name: de-qrels data_files: - split: dev path: de-qrels/dev-* - config_name: de-queries data_files: - split: dev path: de-queries/dev-* - config_name: de-top_ranked data_files: - split: dev path: de-top_ranked/dev-* - config_name: en-corpus data_files: - split: dev path: en-corpus/dev-* - config_name: en-qrels data_files: - split: dev path: en-qrels/dev-* - config_name: en-queries data_files: - split: dev path: en-queries/dev-* - config_name: en-top_ranked data_files: - split: dev path: en-top_ranked/dev-* - config_name: es-corpus data_files: - split: dev path: es-corpus/dev-* - config_name: es-qrels data_files: - split: dev path: es-qrels/dev-* - config_name: es-queries data_files: - split: dev path: es-queries/dev-* - config_name: es-top_ranked data_files: - split: dev path: es-top_ranked/dev-* - config_name: fa-corpus data_files: - split: dev path: fa-corpus/dev-* - config_name: fa-qrels data_files: - split: dev path: fa-qrels/dev-* - config_name: fa-queries data_files: - split: dev path: fa-queries/dev-* - config_name: fa-top_ranked data_files: - split: dev path: fa-top_ranked/dev-* - config_name: fi-corpus data_files: - split: dev path: fi-corpus/dev-* - config_name: fi-qrels data_files: - split: dev path: fi-qrels/dev-* - config_name: fi-queries data_files: - split: dev path: fi-queries/dev-* - config_name: fi-top_ranked data_files: - split: dev path: fi-top_ranked/dev-* - config_name: fr-corpus data_files: - split: dev path: fr-corpus/dev-* - config_name: fr-qrels data_files: - split: dev path: fr-qrels/dev-* - config_name: fr-queries data_files: - split: dev path: fr-queries/dev-* - config_name: fr-top_ranked data_files: - split: dev path: fr-top_ranked/dev-* - config_name: hi-corpus data_files: - split: dev path: hi-corpus/dev-* - config_name: hi-qrels data_files: - split: dev path: hi-qrels/dev-* - config_name: hi-queries data_files: - split: dev path: hi-queries/dev-* - config_name: hi-top_ranked data_files: - split: dev path: hi-top_ranked/dev-* - config_name: id-corpus data_files: - split: dev path: id-corpus/dev-* - config_name: id-qrels data_files: - split: dev path: id-qrels/dev-* - config_name: id-queries data_files: - split: dev path: id-queries/dev-* - config_name: id-top_ranked data_files: - split: dev path: id-top_ranked/dev-* - config_name: ja-corpus data_files: - split: dev path: ja-corpus/dev-* - config_name: ja-qrels data_files: - split: dev path: ja-qrels/dev-* - config_name: ja-queries data_files: - split: dev path: ja-queries/dev-* - config_name: ja-top_ranked data_files: - split: dev path: ja-top_ranked/dev-* - config_name: ko-corpus data_files: - split: dev path: ko-corpus/dev-* - config_name: ko-qrels data_files: - split: dev path: ko-qrels/dev-* - config_name: ko-queries data_files: - split: dev path: ko-queries/dev-* - config_name: ko-top_ranked data_files: - split: dev path: ko-top_ranked/dev-* - config_name: ru-corpus data_files: - split: dev path: ru-corpus/dev-* - config_name: ru-qrels data_files: - split: dev path: ru-qrels/dev-* - config_name: ru-queries data_files: - split: dev path: ru-queries/dev-* - config_name: ru-top_ranked data_files: - split: dev path: ru-top_ranked/dev-* - config_name: sw-corpus data_files: - split: dev path: sw-corpus/dev-* - config_name: sw-qrels data_files: - split: dev path: sw-qrels/dev-* - config_name: sw-queries data_files: - split: dev path: sw-queries/dev-* - config_name: sw-top_ranked data_files: - split: dev path: sw-top_ranked/dev-* - config_name: te-corpus data_files: - split: dev path: te-corpus/dev-* - config_name: te-qrels data_files: - split: dev path: te-qrels/dev-* - config_name: te-queries data_files: - split: dev path: te-queries/dev-* - config_name: te-top_ranked data_files: - split: dev path: te-top_ranked/dev-* - config_name: th-corpus data_files: - split: dev path: th-corpus/dev-* - config_name: th-qrels data_files: - split: dev path: th-qrels/dev-* - config_name: th-queries data_files: - split: dev path: th-queries/dev-* - config_name: th-top_ranked data_files: - split: dev path: th-top_ranked/dev-* - config_name: yo-corpus data_files: - split: dev path: yo-corpus/dev-* - config_name: yo-qrels data_files: - split: dev path: yo-qrels/dev-* - config_name: yo-queries data_files: - split: dev path: yo-queries/dev-* - config_name: yo-top_ranked data_files: - split: dev path: yo-top_ranked/dev-* - config_name: zh-corpus data_files: - split: dev path: zh-corpus/dev-* - config_name: zh-qrels data_files: - split: dev path: zh-qrels/dev-* - config_name: zh-queries data_files: - split: dev path: zh-queries/dev-* - config_name: zh-top_ranked data_files: - split: dev path: zh-top_ranked/dev-* ---

应用场景：