Skip to content
Trending storyDeveloping

Google releases EmbeddingGemma 2 with unified multimodal embeddings

1 article1 sourcesince Oct 29Last article 2h ago ·

Overview

AISummary of 1 article

Google Gemma announces EmbeddingGemma 2, a 740M-parameter model that projects text, images, video and audio into a single embedding space.

The announcement, posted on X, links to a demo by Xenova that runs the model entirely in a browser on WebGPU using Transformers.js. The model is reported as released on Hugging Face.

Written by AI from the articles below · updated Oct 29, 1:14 PM ET

Check the sources:

Latest developmentOct 29, 12:54 PM ET
Google Gemma releases EmbeddingGemma 2 for multimodal embeddings in one space

Article timeline

The articles in this story. Times are ET.

Oct 29
  1. Google GemmaOfficial
    Google Gemma releases EmbeddingGemma 2 for multimodal embeddings in one space

    AIGoogle Gemma announces a demo by Xenova showing EmbeddingGemma 2, which projects text, images, video, and audio into a single embedding space. The model has 740M parameters and can run entirely in a browser on WebGPU using Transformers.js.

Heat Trend

Not enough continuous observations to show a trend yet.