# Contrastive Learning Pretraining

STAR is a supervised contrastive pretraining transformer model for social media writing style understanding.

A neural language model toolkit for pretraining and fine-tuning SMILES-based molecular language models, supporting semi-supervised learning

TOD-XLMR is a multilingual task-oriented dialogue model developed based on XLM-RoBERTa, employing a dual-objective joint training strategy to enhance dialogue understanding capabilities

ReACC-py-retriever is a retrieval-augmented code completion model based on GraphCodeBERT, specifically designed for Python code retrieval and completion.

A semi-supervised image classification model pretrained with SimCLR contrastive learning, trained on the STL-10 dataset with 10 object categories