five

yiyic/eval_mtg_clirmatrix_beir

收藏
Hugging Face2024-02-05 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/yiyic/eval_mtg_clirmatrix_beir
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: features: - name: text dtype: string splits: - name: arguana num_bytes: 1942729 num_examples: 2000 - name: climate_fever num_bytes: 755480 num_examples: 2000 - name: dbpedia_entity num_bytes: 730239 num_examples: 2000 - name: fiqa num_bytes: 1547781 num_examples: 2000 - name: msmarco num_bytes: 646275 num_examples: 2000 - name: nfcorpus num_bytes: 3031052 num_examples: 2000 - name: nq num_bytes: 1022397 num_examples: 2000 - name: quora num_bytes: 126545 num_examples: 2000 - name: scidocs num_bytes: 2285968 num_examples: 2000 - name: scifact num_bytes: 2802938 num_examples: 2000 - name: trec_covid num_bytes: 2879666 num_examples: 2000 - name: webis_touche2020 num_bytes: 3682007 num_examples: 2000 - name: mtg_en num_bytes: 48454 num_examples: 500 - name: mtg_de num_bytes: 57186 num_examples: 500 - name: mtg_es num_bytes: 51263 num_examples: 500 - name: mtg_fr num_bytes: 59140 num_examples: 500 - name: nq_en num_bytes: 306325 num_examples: 500 - name: en_rt num_bytes: 49483 num_examples: 500 - name: de_en_multi8_test1 num_bytes: 1327235 num_examples: 2000 - name: de_fr_multi8_test1 num_bytes: 1331839 num_examples: 2000 - name: de_es_multi8_test1 num_bytes: 1331345 num_examples: 2000 - name: en_de_multi8_test1 num_bytes: 1140466 num_examples: 2000 - name: en_fr_multi8_test1 num_bytes: 1143640 num_examples: 2000 - name: en_es_multi8_test1 num_bytes: 1143146 num_examples: 2000 - name: es_en_multi8_test1 num_bytes: 1112347 num_examples: 2000 - name: es_fr_multi8_test1 num_bytes: 1116951 num_examples: 2000 - name: es_de_multi8_test1 num_bytes: 1113777 num_examples: 2000 - name: fr_en_multi8_test1 num_bytes: 1153630 num_examples: 2000 - name: fr_de_multi8_test1 num_bytes: 1155060 num_examples: 2000 - name: fr_es_multi8_test1 num_bytes: 1157740 num_examples: 2000 download_size: 21436861 dataset_size: 36252104 configs: - config_name: default data_files: - split: arguana path: data/arguana-* - split: climate_fever path: data/climate_fever-* - split: dbpedia_entity path: data/dbpedia_entity-* - split: fiqa path: data/fiqa-* - split: msmarco path: data/msmarco-* - split: nfcorpus path: data/nfcorpus-* - split: nq path: data/nq-* - split: quora path: data/quora-* - split: scidocs path: data/scidocs-* - split: scifact path: data/scifact-* - split: trec_covid path: data/trec_covid-* - split: webis_touche2020 path: data/webis_touche2020-* - split: mtg_en path: data/mtg_en-* - split: mtg_de path: data/mtg_de-* - split: mtg_es path: data/mtg_es-* - split: mtg_fr path: data/mtg_fr-* - split: nq_en path: data/nq_en-* - split: en_rt path: data/en_rt-* - split: de_en_multi8_test1 path: data/de_en_multi8_test1-* - split: de_fr_multi8_test1 path: data/de_fr_multi8_test1-* - split: de_es_multi8_test1 path: data/de_es_multi8_test1-* - split: en_de_multi8_test1 path: data/en_de_multi8_test1-* - split: en_fr_multi8_test1 path: data/en_fr_multi8_test1-* - split: en_es_multi8_test1 path: data/en_es_multi8_test1-* - split: es_en_multi8_test1 path: data/es_en_multi8_test1-* - split: es_fr_multi8_test1 path: data/es_fr_multi8_test1-* - split: es_de_multi8_test1 path: data/es_de_multi8_test1-* - split: fr_en_multi8_test1 path: data/fr_en_multi8_test1-* - split: fr_de_multi8_test1 path: data/fr_de_multi8_test1-* - split: fr_es_multi8_test1 path: data/fr_es_multi8_test1-* ---
提供机构:
yiyic
原始信息汇总

数据集概述

数据集特征

  • 特征名称: text
  • 数据类型: string

数据集拆分

  • arguana
    • 字节数: 1942729
    • 样本数: 2000
  • climate_fever
    • 字节数: 755480
    • 样本数: 2000
  • dbpedia_entity
    • 字节数: 730239
    • 样本数: 2000
  • fiqa
    • 字节数: 1547781
    • 样本数: 2000
  • msmarco
    • 字节数: 646275
    • 样本数: 2000
  • nfcorpus
    • 字节数: 3031052
    • 样本数: 2000
  • nq
    • 字节数: 1022397
    • 样本数: 2000
  • quora
    • 字节数: 126545
    • 样本数: 2000
  • scidocs
    • 字节数: 2285968
    • 样本数: 2000
  • scifact
    • 字节数: 2802938
    • 样本数: 2000
  • trec_covid
    • 字节数: 2879666
    • 样本数: 2000
  • webis_touche2020
    • 字节数: 3682007
    • 样本数: 2000
  • mtg_en
    • 字节数: 48454
    • 样本数: 500
  • mtg_de
    • 字节数: 57186
    • 样本数: 500
  • mtg_es
    • 字节数: 51263
    • 样本数: 500
  • mtg_fr
    • 字节数: 59140
    • 样本数: 500
  • nq_en
    • 字节数: 306325
    • 样本数: 500
  • en_rt
    • 字节数: 49483
    • 样本数: 500
  • de_en_multi8_test1
    • 字节数: 1327235
    • 样本数: 2000
  • de_fr_multi8_test1
    • 字节数: 1331839
    • 样本数: 2000
  • de_es_multi8_test1
    • 字节数: 1331345
    • 样本数: 2000
  • en_de_multi8_test1
    • 字节数: 1140466
    • 样本数: 2000
  • en_fr_multi8_test1
    • 字节数: 1143640
    • 样本数: 2000
  • en_es_multi8_test1
    • 字节数: 1143146
    • 样本数: 2000
  • es_en_multi8_test1
    • 字节数: 1112347
    • 样本数: 2000
  • es_fr_multi8_test1
    • 字节数: 1116951
    • 样本数: 2000
  • es_de_multi8_test1
    • 字节数: 1113777
    • 样本数: 2000
  • fr_en_multi8_test1
    • 字节数: 1153630
    • 样本数: 2000
  • fr_de_multi8_test1
    • 字节数: 1155060
    • 样本数: 2000
  • fr_es_multi8_test1
    • 字节数: 1157740
    • 样本数: 2000

数据集大小

  • 下载大小: 21436861 字节
  • 数据集大小: 36252104 字节

配置

  • 配置名称: default
    • 数据文件路径:
      • arguana: data/arguana-*
      • climate_fever: data/climate_fever-*
      • dbpedia_entity: data/dbpedia_entity-*
      • fiqa: data/fiqa-*
      • msmarco: data/msmarco-*
      • nfcorpus: data/nfcorpus-*
      • nq: data/nq-*
      • quora: data/quora-*
      • scidocs: data/scidocs-*
      • scifact: data/scifact-*
      • trec_covid: data/trec_covid-*
      • webis_touche2020: data/webis_touche2020-*
      • mtg_en: data/mtg_en-*
      • mtg_de: data/mtg_de-*
      • mtg_es: data/mtg_es-*
      • mtg_fr: data/mtg_fr-*
      • nq_en: data/nq_en-*
      • en_rt: data/en_rt-*
      • de_en_multi8_test1: data/de_en_multi8_test1-*
      • de_fr_multi8_test1: data/de_fr_multi8_test1-*
      • de_es_multi8_test1: data/de_es_multi8_test1-*
      • en_de_multi8_test1: data/en_de_multi8_test1-*
      • en_fr_multi8_test1: data/en_fr_multi8_test1-*
      • en_es_multi8_test1: data/en_es_multi8_test1-*
      • es_en_multi8_test1: data/es_en_multi8_test1-*
      • es_fr_multi8_test1: data/es_fr_multi8_test1-*
      • es_de_multi8_test1: data/es_de_multi8_test1-*
      • fr_en_multi8_test1: data/fr_en_multi8_test1-*
      • fr_de_multi8_test1: data/fr_de_multi8_test1-*
      • fr_es_multi8_test1: data/fr_es_multi8_test1-*
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作