# NLI task optimization

Zero-shot classification model based on DeBERTa-v3-base architecture, designed for text classification tasks without training data

This is a multilingual sentence embedding model based on sentence-transformers, supporting English, German, and Italian, capable of mapping text into a 768-dimensional vector space.

Fine-tuned on multilingual T5 model, specifically designed for zero-shot text classification tasks, supporting 15 languages

This is a Korean sentence transformer model based on KLUE-RoBERTa-small, specifically designed for sentence similarity calculation and natural language inference tasks.