与「Gemma」相关的搜索结果

When paired with Gemma 4, EmbeddingGemma 2 powers efficient, on-device retrieval augmented generation (RAG) with a lower memory footprint. EmbeddingGemma 2 retrieves local files, and Gemma 4 reasons over them for grounded answers with complete privacy.

We’re releasing EmbeddingGemma 2, our first natively multimodal open model engineered for on-device embeddings. Built on the Gemma 4 architecture and released under an Apache 2.0 license, it goes beyond text to unify images, video, audio, and code in a single embedding space.

Introducing EmbeddingGemma 2, a new open multimodal model that sets the standard for on-device efficiency. - our first open, natively multimodal embedding model - handles text, code, image, video, and audio tasks within a lightweight, modular 740M parameter form factor - ideal for offline, privacy-first RAG when paired with Gemma 4 - outperforms some specialist models more than twice its size Weights available now on Hugging Face.

Date: 2026.09.27 Event: Cosholic 45 model: Gemma Louise (@gemmalouisejpn) ジェマちゃんに看病されたい！ 💘💘💘💘💘💘💘 ※掲載許可取得済 #CH45# #コスホリ45#

Date: 2026.09.06 Event: vanityME.summer party (2部) model: Gemma Louise(@gemmalouisejpn) こんなにかわいいセーラーさんなら 一生一緒に海に出たい！ 😍😍😍😍😍 ※掲載許可取得済 #チャンス撮影会#

Date: 2026.09.06 Event: vanityME.summer party (1部) model: Gemma Louise(@gemmalouisejpn) ジェマちゃんかわいい😍😍😍😍😍 ※掲載許可取得済 #チャンス撮影会#

Introducing OUI-1: the first open-weights model for Generative UI 71.7% on Generative UI Bench at 4B params. Beats Gemma 4 31B with 8× fewer active params, and scores 5.5× the base DiffusionGemma it was fine-tuned from. Methodology, weights, and full benchmark results in the blog 👇