Google DeepMind 发布 EmbeddingGemma 2：740M 参数、Apache 2.0 开源
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 → https://t.co/lRsjbvR5VB
Google DeepMind 发布 EmbeddingGemma 2，参数规模 740M，在多项 benchmark 上表现有竞争力，甚至超过部分参数量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（如用语音备忘录定位视频片段），或与 Gemma 4 搭配实现私密端侧 RAG。该模型以 Apache 2.0 许可证开源，权重已在 HuggingFace 和 Kaggle 上线。
粉丝 157万
认证：X 认证的官方组织
The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
- 浏览
- 7万
- 点赞
- 576
- 评论
- 38
- 分享
- 44
- 收藏
- 334
数字来自平台，为最近一次抓取时的数据。
来源：X · Google DeepMind · x.com