puar-playground/MMR download history
puar-playground/MMR is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 20 times (5 in the last 7 days), and 1,096 times in total. It ranks #374,093 among datasets by monthly downloads.
Evaluating Reading Ability of Large Multimodal Models This is the evaluation data of the MRR Benchmark for Vision Language models. The bounding boxes are in the format of [x_min, y_min, x_max, y_max] and normalized to ralative ratio between 0 and 1. Reference @inproceedings{mm