# Hugging Face — Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

- Company: Hugging Face (huggingface.co)
- Announced: 2026-04-16T00:00:00+00:00
- Subject: Platform
- Models affected: Qwen/Qwen3-VL-Embedding-2B, tomaarsen/Qwen3-VL-Embedding-2B-vdr, Qwen/Qwen3-VL-2B
- Source: https://huggingface.co/blog/train-multimodal-sentence-transformers
- Record: https://forck.live/items/1518-training-and-finetuning-multimodal-embedding-reranker-models-with-sentence

This blog post by Tom Aarsen on Hugging Face explains how to train or finetune multimodal embedding and reranker models using the Sentence Transformers library, with a practical example of finetuning Qwen/Qwen3-VL-Embedding-2B for Visual Document Retrieval, achieving improved NDCG@10 from 0.888 to 0.947. It covers the training components: model, dataset, loss function, training arguments, evaluator, and trainer.

## Evidence

Verbatim from https://huggingface.co/blog/train-multimodal-sentence-transformers:

> In this blogpost, I'll show you how to train or finetune these multimodal models on your own data.

---

Record: https://forck.live/items/1518-training-and-finetuning-multimodal-embedding-reranker-models-with-sentence
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md