Google DeepMind launches EmbeddingGemma 2, a 740M-parameter model to map code, images, video, and audio in a shared embedding space, under an Apache 2.0 license (Google)
Google says EmbeddingGemma 2 is its strongest on-device model for multimodal embeddings.
The 740M-parameter DeepMind release maps text, code, images, video, and audio into a shared embedding space. Google is releasing it under Apache 2.0. The Techmeme note points to Google as the original source. Techmeme's note
The 740M-parameter DeepMind release maps text, code, images, video, and audio into a shared embedding space. Google is releasing it under Apache 2.0. The Techmeme note points to Google as the original source. Techmeme's note
score 6