Making large AI models cheaper, faster and more accessible

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

Code for paper "Patch-Level Training for Large Language Models"

Code and Data for the ACL22 main conference paper "MSCTD: A Multimodal Sentiment Chat Translation Dataset"

code for Teaching LM to Translate with Comparison

EMNLP 2022: ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization

[NeurIPS 2022] "A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models", Yuanxin Liu, Fandong Meng, Zheng Lin, Jiangnan Li, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

Source code for "Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation"