nthakur/mirage-eval

--- dataset_info: - config_name: ar features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 19528139 num_examples: 1501 - name: dev.small num_bytes: 1301008.5942704864 num_examples: 100 download_size: 40058430 dataset_size: 20829147.594270486 - config_name: bn features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 6425377 num_examples: 411 - name: dev.small num_bytes: 1563352.0681265206 num_examples: 100 download_size: 11704916 dataset_size: 7988729.06812652 - config_name: de features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 2249942 num_examples: 304 - name: dev.small num_bytes: 740112.5 num_examples: 100 download_size: 1730375 dataset_size: 2990054.5 - config_name: en features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 6783947 num_examples: 787 - name: dev.small num_bytes: 862000.8894536213 num_examples: 100 download_size: 4321090 dataset_size: 7645947.889453622 - config_name: es features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 4384991 num_examples: 617 - name: dev.small num_bytes: 710695.4619124797 num_examples: 100 download_size: 2960094 dataset_size: 5095686.461912479 - config_name: fa features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 6329115 num_examples: 632 - name: dev.small num_bytes: 1001442.2468354431 num_examples: 100 download_size: 3382168 dataset_size: 7330557.246835443 - config_name: fi features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 8631071 num_examples: 1183 - name: dev.small num_bytes: 729591.8005071852 num_examples: 100 download_size: 16365685 dataset_size: 9360662.800507186 - config_name: fr features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 2234807 num_examples: 343 - name: dev.small num_bytes: 651547.2303206997 num_examples: 100 download_size: 1637294 dataset_size: 2886354.2303206995 - config_name: hi features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 5331616 num_examples: 350 - name: dev.small num_bytes: 1523318.857142857 num_examples: 100 download_size: 2562093 dataset_size: 6854934.857142857 - config_name: id features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 7117754 num_examples: 939 - name: dev.small num_bytes: 758014.2705005325 num_examples: 100 download_size: 12839552 dataset_size: 7875768.270500532 - config_name: ja features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 7409818 num_examples: 797 - name: dev.small num_bytes: 929713.6762860728 num_examples: 100 download_size: 13872765 dataset_size: 8339531.6762860725 - config_name: ko features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 2191398 num_examples: 213 - name: dev.small num_bytes: 1028825.352112676 num_examples: 100 download_size: 5514338 dataset_size: 3220223.352112676 - config_name: ru features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 18918694 num_examples: 1247 - name: dev.small num_bytes: 1517136.6479550921 num_examples: 100 download_size: 29987695 dataset_size: 20435830.647955094 - config_name: sw features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 3083266 num_examples: 481 - name: dev.small num_bytes: 641011.6424116424 num_examples: 100 download_size: 6296363 dataset_size: 3724277.6424116422 - config_name: te features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 1074836 num_examples: 150 - name: dev.small num_bytes: 716557.3333333334 num_examples: 100 download_size: 4231441 dataset_size: 1791393.3333333335 - config_name: th features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 12832048 num_examples: 730 - name: dev.small num_bytes: 1757814.7945205478 num_examples: 100 download_size: 5432093 dataset_size: 14589862.794520548 - config_name: yo features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 655554 num_examples: 119 - name: dev.small num_bytes: 550885.7142857143 num_examples: 100 download_size: 668617 dataset_size: 1206439.7142857143 - config_name: zh features: - name: query_id dtype: string - name: prompt dtype: string - name: positive_ids sequence: string - name: negative_ids sequence: string splits: - name: dev num_bytes: 2266547 num_examples: 391 - name: dev.small num_bytes: 579679.5396419438 num_examples: 100 download_size: 1810423 dataset_size: 2846226.5396419438 configs: - config_name: ar data_files: - split: dev path: ar/dev-* - split: dev.small path: ar/dev.small-* - config_name: bn data_files: - split: dev path: bn/dev-* - split: dev.small path: bn/dev.small-* - config_name: de data_files: - split: dev path: de/dev-* - split: dev.small path: de/dev.small-* - config_name: en data_files: - split: dev path: en/dev-* - split: dev.small path: en/dev.small-* - config_name: es data_files: - split: dev path: es/dev-* - split: dev.small path: es/dev.small-* - config_name: fa data_files: - split: dev path: fa/dev-* - split: dev.small path: fa/dev.small-* - config_name: fi data_files: - split: dev path: fi/dev-* - split: dev.small path: fi/dev.small-* - config_name: fr data_files: - split: dev path: fr/dev-* - split: dev.small path: fr/dev.small-* - config_name: hi data_files: - split: dev path: hi/dev-* - split: dev.small path: hi/dev.small-* - config_name: id data_files: - split: dev path: id/dev-* - split: dev.small path: id/dev.small-* - config_name: ja data_files: - split: dev path: ja/dev-* - split: dev.small path: ja/dev.small-* - config_name: ko data_files: - split: dev path: ko/dev-* - split: dev.small path: ko/dev.small-* - config_name: ru data_files: - split: dev path: ru/dev-* - split: dev.small path: ru/dev.small-* - config_name: sw data_files: - split: dev path: sw/dev-* - split: dev.small path: sw/dev.small-* - config_name: te data_files: - split: dev path: te/dev-* - split: dev.small path: te/dev.small-* - config_name: th data_files: - split: dev path: th/dev-* - split: dev.small path: th/dev.small-* - config_name: yo data_files: - split: dev path: yo/dev-* - split: dev.small path: yo/dev.small-* - config_name: zh data_files: - split: dev path: zh/dev-* - split: dev.small path: zh/dev.small-* ---

原始信息汇总

数据集概述

数据集配置

语言配置

• 阿拉伯语 (ar)
• 孟加拉语 (bn)
• 德语 (de)
• 英语 (en)
• 西班牙语 (es)
• 波斯语 (fa)
• 芬兰语 (fi)
• 法语 (fr)
• 印地语 (hi)
• 印度尼西亚语 (id)
• 日语 (ja)
• 韩语 (ko)
• 俄语 (ru)
• 斯瓦希里语 (sw)
• 泰卢固语 (te)
• 泰语 (th)
• 约鲁巴语 (yo)
• 中文 (zh)

特征

• query_id: 字符串类型
• prompt: 字符串类型
• positive_ids: 字符串序列类型
• negative_ids: 字符串序列类型

数据分割

• dev: 开发集
• dev.small: 小规模开发集

数据集大小

阿拉伯语 (ar)

• 下载大小: 40058430 字节
• 数据集大小: 20829147.594270486 字节
• dev 分割: 19528139 字节, 1501 个样本
• dev.small 分割: 1301008.5942704864 字节, 100 个样本

孟加拉语 (bn)

• 下载大小: 11704916 字节
• 数据集大小: 7988729.06812652 字节
• dev 分割: 6425377 字节, 411 个样本
• dev.small 分割: 1563352.0681265206 字节, 100 个样本

德语 (de)

• 下载大小: 1730375 字节
• 数据集大小: 2990054.5 字节
• dev 分割: 2249942 字节, 304 个样本
• dev.small 分割: 740112.5 字节, 100 个样本

英语 (en)

• 下载大小: 4321090 字节
• 数据集大小: 7645947.889453622 字节
• dev 分割: 6783947 字节, 787 个样本
• dev.small 分割: 862000.8894536213 字节, 100 个样本

西班牙语 (es)

• 下载大小: 2960094 字节
• 数据集大小: 5095686.461912479 字节
• dev 分割: 4384991 字节, 617 个样本
• dev.small 分割: 710695.4619124797 字节, 100 个样本

波斯语 (fa)

• 下载大小: 3382168 字节
• 数据集大小: 7330557.246835443 字节
• dev 分割: 6329115 字节, 632 个样本
• dev.small 分割: 1001442.2468354431 字节, 100 个样本

芬兰语 (fi)

• 下载大小: 16365685 字节
• 数据集大小: 9360662.800507186 字节
• dev 分割: 8631071 字节, 1183 个样本
• dev.small 分割: 729591.8005071852 字节, 100 个样本

法语 (fr)

• 下载大小: 1637294 字节
• 数据集大小: 2886354.2303206995 字节
• dev 分割: 2234807 字节, 343 个样本
• dev.small 分割: 651547.2303206997 字节, 100 个样本

印地语 (hi)

• 下载大小: 2562093 字节
• 数据集大小: 6854934.857142857 字节
• dev 分割: 5331616 字节, 350 个样本
• dev.small 分割: 1523318.857142857 字节, 100 个样本

印度尼西亚语 (id)

• 下载大小: 12839552 字节
• 数据集大小: 7875768.270500532 字节
• dev 分割: 7117754 字节, 939 个样本
• dev.small 分割: 758014.2705005325 字节, 100 个样本

日语 (ja)

• 下载大小: 13872765 字节
• 数据集大小: 8339531.6762860725 字节
• dev 分割: 7409818 字节, 797 个样本
• dev.small 分割: 929713.6762860728 字节, 100 个样本

韩语 (ko)

• 下载大小: 5514338 字节
• 数据集大小: 3220223.352112676 字节
• dev 分割: 2191398 字节, 213 个样本
• dev.small 分割: 1028825.352112676 字节, 100 个样本

俄语 (ru)

• 下载大小: 29987695 字节
• 数据集大小: 20435830.647955094 字节
• dev 分割: 18918694 字节, 1247 个样本
• dev.small 分割: 1517136.6479550921 字节, 100 个样本

斯瓦希里语 (sw)

• 下载大小: 6296363 字节
• 数据集大小: 3724277.6424116422 字节
• dev 分割: 3083266 字节, 481 个样本
• dev.small 分割: 641011.6424116424 字节, 100 个样本

泰卢固语 (te)

• 下载大小: 4231441 字节
• 数据集大小: 1791393.3333333335 字节
• dev 分割: 1074836 字节, 150 个样本
• dev.small 分割: 716557.3333333334 字节, 100 个样本

泰语 (th)

• 下载大小: 5432093 字节
• 数据集大小: 14589862.794520548 字节
• dev 分割: 12832048 字节, 730 个样本
• dev.small 分割: 1757814.7945205478 字节, 100 个样本

约鲁巴语 (yo)

• 下载大小: 668617 字节
• 数据集大小: 1206439.7142857143 字节
• dev 分割: 655554 字节, 119 个样本
• dev.small 分割: 550885.7142857143 字节, 100 个样本

中文 (zh)

• 下载大小: 1810423 字节
• 数据集大小: 2846226.5396419438 字节
• dev 分割: 2266547 字节, 391 个样本
• dev.small 分割: 579679.5396419438 字节, 100 个样本