Yubai Wei's repositories

continual_finetuning_with_kl

made a adaption to training language models with kl penalty to alleviate catastrophic forgetting

Language:PythonStargazers:1Issues:0Issues:0

code-accumulation

record some basic code writing in work

Language:PythonStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:0Issues:0

paper

paper recently read

Stargazers:0Issues:0Issues:0