Google DeepMind releases EmbeddingGemma 2, a natively multimodal open embedding model
Original titleMeet EmbeddingGemma 2, our first natively multimodal open model for on-device embeddings.
AISummary
Google DeepMind introduced EmbeddingGemma 2, its first natively multimodal open model for on-device embeddings. The model expands beyond text to unify code, images, audio, and video in a shared embedding space.
Source: Google DeepMind · x.comPublished · added here