Link:Google DeepMind
EmbeddingGemma 2: Google DeepMind's Compact Multimodal Embedding Model
Google DeepMind has released EmbeddingGemma 2, an open multimodal embedding model with 740M parameters that maps text, code, images, video, and audio into a unified 768-dimensional vector space.
From X post: Google Releases EmbeddingGemma 2: Unified Multimodal Vector Space