# Hugging Face — Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

- Company: Hugging Face (huggingface.co)
- Announced: 2026-08-26T00:00:00+00:00
- Category: developer-tool-release
- Subject: Platform
- Models affected: lightonai/mLateOn-unsupervised, multi-vector-encoder/mLateOn-medical
- Context window: 8192 token context
- Source: https://huggingface.co/blog/train-multi-vector-encoder
- Record: https://forck.live/items/4436-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.

## Evidence

Verbatim from https://huggingface.co/blog/train-multi-vector-encoder:

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

---

Record: https://forck.live/items/4436-training-and-finetuning-multi-vector-embedding-models-with-sentence-transformers
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md