Model Selection

Improved loss function

# Improved loss function

Sentence Bert Base Ja Mean Tokens V2

This is a Japanese-specific Sentence-BERT model, which uses an improved loss function for training optimization compared to Version 1, achieving a 1.5 to 2 percentage point increase in accuracy.

Text Embedding Japanese

Featured Recommended AI Models

AIbase

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

© 2025AIbase