Skip to content

azmozaffari/Text_Fine_tuning_LORA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Text_Fine_tuning_LORA

In this project, I have compared full fine-tuning in which the whole parameters of the model would be changed by retraining the model on the new dataset v.s. the LoRA fine-tuning method in which using the low rank factorization only the parameters partially would be optimised.

LoRA prevents catastrophic forgetting in model adaptation while preserving a manageable memory footprint for the model training.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors