Google DeepMind· @GoogleDeepMind · X·· 3 小时前AI 评分39
AI 导读
仅 740M 参数，它在各项基准上极具竞争力——甚至超越了一些参数量是其两倍以上的专用模型。 开发者可以用它为应用添加多模态搜索——比如通过语音备忘录在视频中找到对应片段——或将其与 Gemma 4 搭配，实现私密的端侧 RAG。 EmbeddingGemma 2 以 Apache 2.0 许可证发布。可在 @HuggingFace 和 @Kaggle 上查看权重。 了解更多 → https://goo.gle/4y9wXgl
正文
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://goo.gle/4y9wXgl
来源：Google DeepMind · x.com