Haon-Chen/XTD-10
收藏Hugging Face2025-02-14 更新2025-02-15 收录
下载链接:
https://hf-mirror.com/datasets/Haon-Chen/XTD-10
下载链接
链接失效反馈官方服务:
资源简介:
XTD数据集是一个用于评估多模态嵌入模型的多语言能力的数据集,包含带有英语指令的七种语言的子数据集:意大利语(it)、西班牙语(es)、俄语(ru)、中文(zh)、波兰语(pl)、土耳其语(tr)和韩语(ko)。每个示例包含一个查询和一组目标,其中列表中的第一个目标是真实目标。数据集还提供了图像准备指南和引用信息。
The XTD dataset is a collection of datasets with English instructions used for evaluating the multilingual capability of a multimodal embedding model, including subsets in seven languages: Italian (it), Spanish (es), Russian (ru), Chinese (zh), Polish (pl), Turkish (tr), and Korean (ko). Each example consists of a query and a set of targets, with the first one in the list being the ground truth target. The dataset also provides guidelines for image preparation and citation information.
提供机构:
Haon-Chen



