mteb/CodeEditSearchRetrieval

该数据集包含多种编程语言（Go、Java、JavaScript、Python、Ruby、TypeScript）的语料库、查询和相关性判断数据。每个数据集都有特定的配置名称，并包含 _id、text 等特征。对于语料库数据集，还包含 title 特征；对于 qrels 数据集，包含 query-id、corpus-id 和 score 特征。数据集分为训练集，并为每个分割提供了示例数量和文件大小的信息。

The dataset includes corpora, queries, and relevance judgments for multiple programming languages (Go, Java, JavaScript, Python, Ruby, TypeScript). Each dataset has a specific configuration name and includes features like _id, text. For corpus datasets, it also includes the title feature; for qrels datasets, it includes query-id, corpus-id, and score features. The datasets are split into training sets, and information about the number of examples and file size is provided for each split.