R

Reranker ModernBERT Base Gooaq 1 Epoch 1995000

Developed by ayushexel
This is a cross-encoder model fine-tuned from ModernBERT-base, designed for calculating scores of text pairs, suitable for text reordering and semantic search tasks.
Downloads 30
Release Time : 3/31/2025

Model Overview

This model is fine-tuned from answerdotai/ModernBERT-base, specifically designed for scoring text pairs, supporting semantic search and text reordering.

Model Features

Long Text Support
Supports sequences up to 8192 tokens, suitable for processing long texts.
Efficient Reordering
Optimized for text reordering tasks, effectively improving the relevance of search results.
Multi-Dataset Validation
Validated on multiple datasets, including gooaq-dev, NanoMSMARCO, etc.

Model Capabilities

Text Pair Scoring
Semantic Search
Text Reordering

Use Cases

Information Retrieval
Question-Answer System Reordering
Reorders candidate answers in a question-answer system to improve the ranking of the most relevant answers.
Achieved an average accuracy of 0.4829 on the gooaq-dev dataset.
Document Retrieval
Reorders retrieved documents by relevance to enhance user experience.
Achieved an average accuracy of 0.4301 on the NanoMSMARCO dataset.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase