Codes for "A Contrastive Self-distillation BERT with Kernel Alignment-Based Inference", published in ICCS 2023.
Codes for "MetaBERT: Collaborative Meta-Learning for Accelerating BERT Inference", published in CSCWD 2023.
[Findings of EMNLP22] From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models