Hugging Face has released a new family of six Ettin Reranker models, built on top of Ettin ModernBERT encoders. These models offer state-of-the-art performance for their respective sizes and are designed for the retrieve-then-rerank pattern in information retrieval systems. The release includes the models, their training data, and a full training recipe, enabling users to integrate them or even train their own rerankers. AI
IMPACT Enhances information retrieval systems by providing more accurate and efficient reranking capabilities.
RANK_REASON Release of new open-source models and training recipes by a prominent AI community platform. [lever_c_demoted from research: ic=1 ai=1.0]
- Ettin ModernBERT
- Ettin Reranker
- google/embeddinggemma-300m
- Hugging Face
- lightonai/embeddings-fine-tuning
- lightonai/embeddings-pre-training
- mixedbread-ai/mxbai-rerank-large-v2
- MTEB
- Sentence Transformers
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
