mteb/CodeSearchNetCCRetrieval

该数据集包含多种编程语言的不同配置，每个配置都包括 _id、text 和 title（对于语料库）或 query-id、corpus-id 和 score（对于查询相关度）。数据集被分割为测试集，每个测试集都有指定的字节数和示例数。还提供了每个配置的下载大小和数据集大小。每个配置和分割的数据文件路径也被列出。

The dataset comprises various configurations for different programming languages. Each configuration includes _id, text, and title (for corpus) or query-id, corpus-id, and score (for qrels). The dataset is split into test sets, each with specified number of bytes and examples. The download size and dataset size for each configuration are provided. The data file paths for each split and configuration are also listed.