Mini-dataset for VL-Models fine-tuning (VL-Tune-dataset-mini)

A minimal dataset of 125 image-text pairs and 10 text queries for fine-tuning vision-language models on manuscript images. It is dedicated to the task of...本数据集为包含125组图像-文本对与10个文本查询的极简规模数据集，用于在手稿图像场景下微调视觉语言模型（Vision-Language Model），其针对性服务于……任务