Details werden geladen...
Google launches EmbeddingGemma 2, an open multimodal embedding model for devices
EmbeddingGemma 2 maps text, code, images, audio and video into one space on the device, under Apache 2.0, in about 191MB of RAM for text on a Pixel.
Ähnliche Seiten
Google DeepMind Ships a Free On-Device Model for Searching Text, Images, Audio and Video Together - DEV Community
https://dev.to/mikefluff/google-deepmind-ships-a-free-on-device-model-for-searching-text-images-audio-and-video-together-1l7a
Google claims EmbeddingGemma 2 outperforms rival embedding models twice its size
https://the-decoder.com/google-claims-embeddinggemma-2-outperforms-rival-embedding-models-twice-its-size/
Google CEO Sundar Pichai announces EmbeddingGemma 2 model; says it is company’s first open, natively multimodal embedding model | - The Times of India
https://timesofindia.indiatimes.com/technology/tech-news/google-ceo-sundar-pichai-announces-embeddinggemma-2-model-says-it-is-companys-first-open-natively-multimodal-embedding-model/articleshow/134755324.cms
EmbeddingGemma 2: The Developer Guide - Google Developers Blog
https://developers.googleblog.com/embeddinggemma-2-the-developer-guide/Google Deepmind's Gemma 4 12B squeezes multimodal AI onto a laptop with just 16 GB of RAM
https://the-decoder.com/google-deepminds-gemma-4-12b-squeezes-multimodal-ai-onto-a-laptop-with-just-16-gb-of-ram/