R

Reranker ModernBERT Base Gooaq Bce

Developed by akr2002
This is a cross-encoder model fine-tuned from ModernBERT-base for text re-ranking and semantic search tasks.
Downloads 16
Release Time : 3/29/2025

Model Overview

This model is a cross-encoder specifically designed for computing similarity scores between text pairs, suitable for re-ranking tasks in information retrieval.

Model Features

Long Text Processing Capability
Supports sequences up to 8192 tokens, suitable for processing long texts
Efficient Re-ranking
Optimized for re-ranking tasks in information retrieval, effectively improving search result quality
Based on ModernBERT
Fine-tuned from the ModernBERT-base model, inheriting its powerful semantic understanding capabilities

Model Capabilities

Text Similarity Calculation
Search Result Re-ranking
Question-Answer Pair Matching

Use Cases

Information Retrieval
Search Engine Result Re-ranking
Re-rank initial search engine results to improve the ranking of relevant results
Achieved NDCG@10 of 0.7686 on the GooAQ development set
Question Answering System
Evaluate the relevance between questions and candidate answers to select the best answer
Achieved an average precision of 0.5595 on the NanoNQ dataset
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase