BGE-MU

tags

Open Source, Hugging Face , Chinese

Embedding #

BGE-M3 (paper, code) In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.

Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. Multi-Linguality: It can support more than 100 working languages. Including Arabic and English Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens. ref

Very popular this model gave best results , open source, while evaluating model, as close to cohere large multilingual, slightly behind it,