Nayana-cognitivelab/Nayana-IR-DescVQA-finetune-1k

该数据集是一个包含图像和相关文本信息的训练集，具体包括问题ID、特定细节查询和文档ID等字符串类型的数据，以及图像数据。训练集共有1000个示例，数据大小为889129993字节。

This dataset is a training set containing images and associated text information, specifically including string data types such as question ID, specific detail query, and document ID, as well as image data. The training set consists of 1000 examples with a total size of 889129993 bytes.