S

Silver Retriever Base V1.1

Developed by ipipan
The Silver Retriever model encodes Polish sentences or paragraphs into a 768-dimensional dense vector space, suitable for tasks like document retrieval or semantic search.
Downloads 862
Release Time : 11/27/2023

Model Overview

This model is initialized based on HerBERT-base and fine-tuned on PolQA and MAUPQA datasets, primarily designed for Polish question answering and passage retrieval tasks.

Model Features

Efficient Polish Retrieval
A retrieval model specifically optimized for Polish, excelling in Polish question answering tasks.
Multi-dataset Training
Trained on multiple Polish datasets including PolQA and MAUPQA, offering broad application capabilities.
High Performance
Outperforms other Polish models across various evaluation metrics and competes with larger multilingual models.

Model Capabilities

Polish sentence encoding
Document retrieval
Semantic search
QA system support

Use Cases

Information Retrieval
QA System Passage Retrieval
Used for quickly retrieving relevant passages in QA systems
Achieved 88.60% accuracy on the PolQA dataset
Legal Document Retrieval
Retrieving legal-related documents and passages
Achieved 96.94% accuracy on the legal questions dataset
E-commerce
FAQ Retrieval
Used for retrieving frequently asked questions on e-commerce platforms
Achieved 94.00% accuracy on the Allegro FAQ dataset
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase