ModelMoka Massive Mixed Embedding
M3E
An open-source family of Chinese text embedding models trained on large-scale Chinese corpora. It performs well on Chinese semantic similarity tasks and is suited to building RAG knowledge bases.
Timeline (last 90 days)
Oct 16
Commonly available Chinese-capable Embedding models include OpenAI's text-embedding-3, BGE, M3E, Tongyi Qianwen text-embedding, and others.
Unverified50%