Google DeepMind · XOriginal · English

Meet EmbeddingGemma 2, our first natively multimodal open model for on-device embeddings.

Meet EmbeddingGemma 2, our first natively multimodal open model for on-device embeddings.

It expands beyond text to unify code, images, audio, and video in a shared space. 🧵

Original source

Google DeepMind · X

Content notes

Original publication and rights belong to the source.