lightonai / LightOn-rerank-LW-4B
Vision4.5B7293Updated Jul 22, 2026
Downloads
729
Likes
3
Last updated
Jul 22, 2026
License
apache-2.0
Production retrieval pipelines usually need two rerankers: one for text passages and one for visual documents (PDF pages, slides, scans). LightOn-rerank models are unified cross-encoder rerankers: a single model scores both text passages and document page images against a quer…
Tasks & library
- image text to text
- transformers
Tags
- transformers
- qwen3_5
- image-text-to-text
- reranker
- cross-encoder
- multimodal
