The mxbai-rerank-large-v2 is a 1.5 billion parameter reranker model developed by Mixedbread.ai, designed for state-of-the-art performance and efficiency in information retrieval. It features extensive multilingual support for over 100 languages, including outstanding English and Chinese capabilities, along with code support and long-context handling. This model is primarily optimized for accurately re-ranking search results and documents based on relevance to a given query.
Loading preview...
mxbai-rerank-large-v2: A Powerful Reranker by Mixedbread.ai
mxbai-rerank-large-v2 is Mixedbread.ai's larger, 1.5 billion parameter reranker model, built for high-performance and efficient information retrieval tasks. It stands out for its state-of-the-art capabilities and broad applicability.
Key Capabilities
- State-of-the-art performance: Achieves strong results across various benchmarks, notably a BEIR Avg of 57.49.
- Multilingual support: Supports over 100 languages, with exceptional performance in English and Chinese (84.16 on Chinese benchmarks).
- Code support: Capable of handling code-related search and re-ranking tasks, scoring 32.05 in Code Search benchmarks.
- Long-context support: Designed to process and re-rank documents with extended context lengths.
- Efficient: Demonstrates competitive latency (0.89s on A100 GPU) compared to previous versions.
Training Methodology
The model was trained using a sophisticated three-step process:
- GRPO (Guided Reinforcement Prompt Optimization)
- Contrastive Learning
- Preference Learning
Good for
- Improving the relevance of search results in RAG (Retrieval Augmented Generation) systems.
- Applications requiring precise document ranking across a wide array of languages.
- Enhancing code search and retrieval functionalities.
- Use cases demanding efficient processing of long documents for relevance scoring.