VDBBench/multimodal-embedding-10M download history

VDBBench/multimodal-embedding-10M is a feature extraction dataset on the Hugging Face Hub. In the last 30 days it was downloaded 291 times (43 in the last 7 days), and 986 times in total. It ranks #50,305 among datasets by monthly downloads.

Multimodal Embedding 10M Benchmark Dataset A large-scale vector search benchmark dataset containing 10M base vectors and 10K query vectors with pre-computed ground truth (top-100 nearest neighbors by Inner Product), generated from multimodal (image + text) inputs. Dataset

Open VDBBench/multimodal-embedding-10M on Hugging Face

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