Transformers v5.19.0支持EmbeddingGemma 2
Hugging Face Transformers v5.19.0 新增对 EmbeddingGemma 2 的支持。这款 Google 多模态嵌入模型可将文本、图像、音频和视频编码到共享的 768 维向量空间；本次版本还更新了 MoE 路由器输出、专家并行、连续批处理注意力机制和量化缓存处理。
该版本让新的多模态嵌入模型进入常用开源框架，并同步更新分布式推理能力。
Release v5.19.0
New Model additions
EmbeddingGemma2
EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture. It encodes text, images, audio, and video, individually or combined in one input, into a shared 768-dimensional vector space for cross-modal retrieval, semantic similarity, clustering, and classification. It uses Matryoshka Representation Learning, so embeddings can be truncated to 512, 256, or 128 dimensions. It also offers configurable visual and video token budgets, and unused vision or audio towers can be disabled at load time to save memory.
Links: Documentation
#Hugging Face Transformers#Hugging Face#Google#EmbeddingGemma 2#Gemma 4