Google launches the next version of its on-device AI model.
EmbeddingGemma 2 can work with more than just text, featuring capabilities across coding, images, video, and audio. Google says the upgraded model has 740 million parameters and is designed to perform on-device tasks like finding a video clip from a voice memo or searching through audio recordings based on a text prompt.
TL;DR
- EmbeddingGemma 2 supports text, coding, images, video, and audio.
- The model has 740 million parameters.
- It is designed for on-device tasks.
- Example uses include finding video clips from voice memos and searching audio recordings via text prompts.