Google· @Google · X·· 17 小时前AI 评分
Google 发布 EmbeddingGemma 2 嵌入模型
Google 发布 EmbeddingGemma 2，参数量 740M，官方称同规模下表现最佳，超过部分两倍于其规模的模型，活跃内存占用低至约 191MB 到 567MB。相比第一代，其上下文窗口扩大 4 倍至 8K，单次最多可处理 5.5 分钟音频、29 张图片或 58 帧视频。
Best-in-class for its size at 740M parameters, EmbeddingGemma 2 outperforms some models over twice its size while using from as little as ~191MB to 567MB of active RAM.
It also features a 4x larger 8K context window than the first generation, processing up to 5.5 minutes of audio, 29 images, or 58 video frames in one pass.
来源：Google · x.com