MM-Hallu/HOPE download history

MM-Hallu/HOPE is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 22 times (5 in the last 7 days), and 445 times in total. It ranks #349,066 among datasets by monthly downloads.

HOPE: Hallucination searching-based Object Probing Evaluation This dataset is part of the MM-Hallu collection of multimodal hallucination benchmarks. Dataset Description HOPE is a benchmark for evaluating object hallucination in Large Vision-Language Models (LVLMs). It uses MSC

Open MM-Hallu/HOPE on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.