R

Reranker Gte Multilingual Base Msmarco Bce Ep 2

Developed by skfrost19
A cross-encoder model trained on the msmarco dataset using the sentence-transformers library, designed for text re-ranking and semantic search
Downloads 28
Release Time : 4/6/2025

Model Overview

This model computes scores for text pairs and can be used for text re-ranking and semantic search tasks. It was trained on 1.99 million samples using binary cross-entropy loss.

Model Features

High-performance Re-ranking
Achieves an NDCG@10 score of 0.7008 on the NanoMSMARCO_R100 dataset, demonstrating excellent performance
Large-scale Training
Trained on 1.99 million samples, with strong semantic understanding capabilities
Long Text Support
Supports sequences up to 8192 tokens, making it suitable for processing long texts

Model Capabilities

Text Pair Scoring
Semantic Search
Search Result Re-ranking

Use Cases

Information Retrieval
Search Engine Result Re-ranking
Re-ranks search engine results to improve relevance
Achieves NDCG@10 of 0.7008 on the MSMARCO dataset
Q&A Systems
Answer Relevance Ranking
Ranks candidate answers by relevance to select the best answer
Achieves NDCG@10 of 0.6888 on the NanoNQ_R100 dataset
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase