G

Gte Base Ko

Developed by scottsuk0306
This is a sentence-transformers model fine-tuned on a Korean triplet dataset based on Alibaba NLP/gte-multilingual-base, designed for semantic textual similarity tasks.
Downloads 18
Release Time : 11/17/2024

Model Overview

The model maps sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks like semantic textual similarity, semantic search, paraphrase mining, text classification, and clustering.

Model Features

Multilingual base model
Based on Alibaba NLP/gte-multilingual-base, offering strong multilingual processing capabilities
Korean optimization
Fine-tuned on a Korean triplet dataset, making it particularly suitable for Korean text processing
High accuracy
Achieves a cosine accuracy of 0.9855 on the development set
Long text support
Supports sequences up to 8192 tokens, ideal for processing long texts

Model Capabilities

Semantic textual similarity calculation
Semantic search
Text feature extraction
Text clustering
Text classification

Use Cases

Information retrieval
Similar document retrieval
Find semantically similar documents based on query text
High-accuracy similarity matching
Content recommendation
Related content recommendation
Recommend semantically similar content based on user browsing history
Enhances user engagement and content discovery efficiency
Featured Recommended AI Models
ยฉ 2025AIbase