Hugging Face· PlatformDeveloper tool

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Sentence Transformers v6.0 introduces a new model type, MultiVectorEncoder, for ColBERT-style late interaction retrieval, along with a complete training approach. The blog post demonstrates how to finetune multi-vector models that outperform general-purpose retrievers on domain-specific data, and shows that a finetuned model (multi-vector-encoder/mLateOn-medical) trained in 14.5 hours on a single RTX 3090 outperforms all general-purpose retrieval models on a medical retrieval evaluation.

From the source

Its v6.0 update introduces a fourth model type: MultiVectorEncoder , for ColBERT-style late interaction retrieval, alongside a complete training approach for it.

huggingface.co

Announced

26 Aug 2026 00:00 UTC

Detected