monot5-base-msmarco-10k Open-source Ranking Model - Fine-tuning Optimization Achieves Excellent Zero-shot Ranking Performance

Monot5 Base Msmarco 10k

Developed by castorini

A reranker based on the T5-base architecture, fine-tuned for 10,000 steps on the MS MARCO passage dataset, with excellent zero-shot performance.

Downloads 5,396

Release Time : 3/2/2022

Model Overview

This model is primarily used for document and passage reranking tasks, specifically optimized for zero-shot performance on non-MS MARCO datasets.

Superior zero-shot performance

Outperforms similar models on non-MS MARCO datasets, demonstrating better generalization capabilities.

Efficient fine-tuning

Achieves good results with only 10,000 steps (1 training epoch) of fine-tuning.

Based on T5 architecture

Utilizes the powerful T5-base architecture with excellent sequence-to-sequence processing capabilities.

Document reranking

Passage relevance scoring

Zero-shot transfer learning

Information retrieval

MS MARCO passage reranking

Reranks MS MARCO passage retrieval results to improve relevance

Performs excellently on the MS MARCO dataset

Robust04 document reranking

Performs document reranking on the Robust04 dataset

Demonstrates good zero-shot transfer capability

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base