D

Dragonkue KoEn E5 Tiny ONNX

Developed by exp-models
This is a sentence-transformers model fine-tuned from intfloat/multilingual-e5-small, specifically optimized for Korean retrieval tasks, mapping text to a 384-dimensional vector space.
Downloads 51
Release Time : 5/13/2025

Model Overview

This model is used for semantic textual similarity, semantic search, paraphrase mining, text classification, and clustering tasks, particularly suitable for Korean retrieval applications.

Model Features

Korean optimization
Fine-tuned specifically for Korean retrieval tasks, improving Korean text processing performance
Lightweight and efficient
Small model size (118M), achieving a good balance between speed and accuracy
Multilingual support
Supports English text processing in addition to Korean
High-dimensional vector space
Maps sentences and paragraphs to a 384-dimensional dense vector space

Model Capabilities

Semantic textual similarity calculation
Semantic search
Paraphrase mining
Text classification
Text clustering

Use Cases

Information retrieval
Korean document retrieval
Used for semantic search and retrieval of Korean documents
Performs well on multiple Korean retrieval benchmarks
Question answering systems
Open-domain question answering
Used for passage retrieval in Korean open-domain question answering systems
Achieves NDCG@10 of 0.762 on the Ko-StrategyQA dataset
Featured Recommended AI Models
ยฉ 2025AIbase