Advanced multi-vector retrieval model creating token-level embeddings with late interaction mechanism, featuring denoised supervision and improved memory efficiency over original ColBERT.
Loading more......
ColBERTv2 (Contextual Late Interactions BERT) is an advanced bi-encoder that represents text in multi-vector embeddings at the token level, introducing a novel late interaction mechanism for efficient and precise ranking.
Significant advancement over traditional bi-encoder models, with multi-embedding representations clearly capturing complex queries for more accurate retrievals.
Open-source model, self-hostable or via API providers