# Unsupervised Training

This is a sentence similarity model based on sentence-transformers, capable of mapping text to a 768-dimensional vector space

Unsupervised contrastive learning model based on BERT architecture, improving sentence embedding quality through a simple yet effective contrastive learning framework

T5-based doc2query model for document expansion and training data generation

A simplified Chinese sentence embedding encoding model based on simple contrastive learning, using the Chinese RoBERTa WWM extended version as the pre-trained model.

A fine-tuned version of the Contriever pre-trained model, optimized for dense information retrieval tasks and trained using contrastive learning methods

An emotion classification model distilled from unlabeled GoEmotions dataset through zero-shot classification pipeline, serving as a computationally efficient proof-of-concept model

SBERT-large-nli-v2 is a large-scale sentence transformer model based on BERT, specifically designed for sentence similarity calculation and feature extraction.