Skip to content

ylsung/sparse_update

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sparse Update

Sparse updates is a technique that train neural networks only updating few parameters.

Code format

We follow the black format.

Usage

Installation

It's recommended to install in conda or virtual enviroment.

cd sparse_update
pip install -e .

Arguments

Please refer to scripts/train.py

Train

python scripts/train.py

The script will also generate predictions on test data (save as [Dataset].tsv), which is used to submit to the Glue server for testing.

Todo

  • Support sparsed update (diff pruning)
  • Support all Glue tasks (Add corresponding classes in datamodules.py and modules.py)
  • Support pretraining tasks

Resources

The repo base on the following projects

About

No description, website, or topics provided.

Resources

Stars

3 stars

Watchers

1 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages