Ruri V3 Reranker 310m Preview
This is a preview version of a Japanese general-purpose reranking model, trained on the cl-nagoya/ruri-v3-pt-310m base model, specifically designed for Japanese text relevance ranking tasks.
Downloads 79
Release Time : 3/28/2025
Model Overview
This model is a Japanese text reranking model capable of evaluating the relevance between queries and documents, primarily used for optimizing result rankings in information retrieval systems.
Model Features
Japanese-Specific Optimization
Specially optimized for Japanese text characteristics, excelling in Japanese text ranking tasks.
High Performance
Achieves state-of-the-art performance on multiple Japanese evaluation benchmarks, outperforming similar models.
Supports Flash Attention 2
Can be combined with Flash Attention 2 to accelerate inference and improve processing efficiency.
Model Capabilities
Text Relevance Evaluation
Information Retrieval Result Reranking
Query-Document Matching Score
Use Cases
Search Engine Optimization
Search Result Ranking
Reranks search engine results by relevance to improve result quality.
Significantly enhances the relevance scores of search results.
Q&A Systems
Answer Candidate Ranking
Reranks multiple candidate answers generated by a Q&A system based on relevance.
Increases the probability of the best answer being prioritized.
Featured Recommended AI Models