google / embeddinggemma-2
744M407.2K3.1KUpdated Oct 28, 2026
Downloads
407.2K
Likes
3.1K
Last updated
Oct 28, 2026
License
apache-2.0
EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M par…
Tasks & library
- feature extraction
- transformers
Tags
- transformers
- embedding_gemma2
- feature-extraction
- embedding
- sentence-transformers
- multimodal-embedding
Technical specifications
Parameters744M
Librarytransformers
Languagesmultilingual
Licenseapache-2.0