Y-J-Ju/MMEB-train download history

Y-J-Ju/MMEB-train is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 68 times (7 in the last 7 days), and 2,319 times in total. It ranks #149,549 among datasets by monthly downloads.

Massive Multimodal Embedding Benchmark The training data split used for training VLM2Vec models in the paper VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks (ICLR 2025). MMEB benchmark covers 4 meta tasks and 36 datasets meticulously selected for evaluating

Open Y-J-Ju/MMEB-train on Hugging Face

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