# embedding-model

> Browse 2 items tagged with embedding-model.

## Items

- [BGE-M3](https://vectordb.ever.works/items/bge-m3) — A versatile embedding model from BAAI that simultaneously supports dense retrieval, sparse retrieval, and multi-vector retrieval, with multilingual support for 100+ languages and multi-granularity processing from short sentences to 8192-token documents.
- [Jina-CLIP v2](https://vectordb.ever.works/items/jina-clip-v2) — A 0.9B multimodal embedding model with multilingual support for 89 languages, 512x512 image resolution, and Matryoshka representations that enable dimensional flexibility from 1024 down to 64 dimensions while maintaining strong performance.

---

_Canonical page: https://vectordb.ever.works/tags/embedding-model_