Skip to content

evan-ak/mile

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ReadMe

This is the source code for our IEEE Access publication MILE: Memory-Interactive Learning Engine for Neuro-Symbolic Solutions to Mathematical Problems.


Environment

The code was written and verified on Python 3.11 and PyTorch 2.1.0.

The other required libraries include :

  • json
  • numpy
  • transformers

Verification

To start the training, run:

python ./train.py

To switch to other encoder and decoder models, modify the encode_method and decode_method in config.py, or assign @encode_method="..." @decode_method="..." in the training command:

python ./train.py @encode_method="..." @decode_method="..."

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages