Training and Finetuning Sparse Embedding Models with Sentence Transformers

Sentence Transformers can finetune sparse encoder/embedding models for retrieval, hybrid search, and reranking. The post outlines training components (model, datasets, losses, trainer, evaluators) and provides practical examples, including using naver/splade-v3 and decoding sparse embeddings for interpretability.

Source

HuggingFace Blog

Ingested

JUL 01, 2025 · 19:10

Editorial score

4.0 / 5