tom68-ll's repositories
Language:PythonApache-2.0000
SAPT
Code for ACL 2024 accepted paper titled "SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models"
Language:Python000
TUPE
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
Language:PythonMIT000