# High-Precision Retrieval

Ruri v3 is a general Japanese text embedding model based on ModernBERT-Ja, achieving industry-leading performance in Japanese text embedding tasks and supporting sequences up to 8192 tokens long.

Ruri v3 is a Japanese general text embedding model based on ModernBERT-Ja, achieving state-of-the-art performance in Japanese text embedding tasks, supporting sequences up to 8192 tokens.

Ruri v3 is a Japanese general-purpose text embedding model based on ModernBERT-Ja, supporting sequences up to 8192 tokens long and achieving state-of-the-art performance in Japanese text embedding tasks.

A Japanese general-purpose reranking model built on ModernBERT-Ja, featuring top-tier performance and long-sequence processing capabilities

mxbai-rerank-large-v2 is a foundational model for text reordering, focused on improving the relevance and accuracy of search results.

Ruri is a Japanese universal text embedding model focused on sentence similarity calculation and feature extraction, trained based on the cl-nagoya/ruri-pt-small-v2 foundation model.

Ruri Reranker is a general-purpose Japanese reranking model based on the Sentence Transformers architecture, specifically designed for Japanese text relevance ranking tasks.

General-purpose Japanese reranking model for improving relevance ranking in Japanese text retrieval

Ruri Reranker is a Japanese text reranking model based on Transformer architecture, specifically designed to optimize the ranking quality of retrieval results.

This is a Japanese-trained Reranker (CrossEncoder) model for text relevance ranking tasks.

This is a Japanese Reranker (Cross-Encoder) model for text ranking tasks, featuring 24 layers and a hidden layer size of 1024.