Skip to content

The GitHub repository for the paper "JAT" accepted by NeurIPS 2022.

License

Notifications You must be signed in to change notification settings

zhouhaoyi/JAT2022

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Jump Self-attention: Capturing High-order Statistics in Transformers (NIPS 2022)

Requirements

  • Python 3.7
  • transformers == 4.0.0
  • torch == 1.10.1
  • datasets == 1.15.1
  • huggingface-hub == 0.1.2
  • scipy == 1.6.2
  • scikit_learn == 0.24.1

Dependencies can be installed using the following command:

pip install -r requirements.txt

Data

GLUE_Datasets

Usage

python run_glue.py

About

The GitHub repository for the paper "JAT" accepted by NeurIPS 2022.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages