tomaarsen(@tomaarsen):Regarding Sentence Transformers v6.0 update: A dense model compresses a whole text into one vector, then compares two vectors. A multi-vector model keeps one vector per token, scores every query token against every document token, takes the best match for each, and sums those.

tomaarsen

@tomaarsen

Sentence Transformers, SetFit & NLTK maintainer Machine Learning Engineer at 🤗 Hugging Face

Joined December 2023

473 Following 4.8K Followers

tomaarsen@tomaarsen

2026.08.19 10:08

Regarding Sentence Transformers v6.0 update: A dense model compresses a whole text into one vector, then compares two vectors. A multi-vector model keeps one vector per token, scores every query token against every document token, takes the best match for each, and sums those.