GoogleDeepMind· @GoogleDeepMind · X·· 6 小时前AI 评分
Google DeepMind 发布 EmbeddingGemma 2，740M 参数支持多模态搜索与端侧 RAG
Google DeepMind 发布 EmbeddingGemma 2，称其在 740M 参数量级上各基准表现有竞争力，甚至超过部分规模两倍以上的专用模型。开发者可用它为应用加入多模态搜索，例如通过语音备忘录查找视频片段，或与 Gemma 4 搭配实现私密的端侧 RAG。该模型以 Apache 2.0 许可发布，权重已在 Hugging Face 和 Kaggle 开放。
At 740M parameters, it’s competitive across benchmarks – even outperforming some specialist models more than twice its size.
Developers can use it to add multimodal search to their apps – like finding moments in a video using a voice memo – or pair it with Gemma 4 for private, on-device RAG.
EmbeddingGemma 2 is released under an Apache 2.0 license. Check out the weights on @HuggingFace and @Kaggle.
Find out more → goo.gle/4y9wXgl
来源：GoogleDeepMind · x.com