遇见数据集

mteb/BrightRetrieval

收藏
Hugging Face2025-05-08 更新2025-05-31 收录
官方服务:

资源简介:

BrightRetrieval 是一个用于文本检索任务的MTEB数据集。它包含多个配置,如aops-corpus、biology-corpus等,每个配置都有特定的特征,如_id、text、title等。数据集是多语言的,遵循CC BY 4.0许可证。README中还包含了如何使用mteb库评估模型以及引用数据集和相关作品的说明。

BrightRetrieval is an MTEB dataset designed for text retrieval tasks. It includes various configurations such as aops-corpus, biology-corpus, and more, each with specific features like _id, text, and title. The dataset is multilingual and licensed under CC BY 4.0. The README also includes instructions on how to evaluate models on this dataset using the mteb library and provides citation information for the dataset and related works.

提供机构:
mteb
二维码
社区交流群
二维码
科研交流群
商业服务