Skip to content

Implementing some key architectures for language modeling using PyTorch

License

Notifications You must be signed in to change notification settings

jcblaisecruz02/PyTorch-Language-Modeling

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PyTorch Language Modeling

A series of notebooks implementing key papers and architectures for neural language modeling. I'm still rewriting my other stuff and I'll update this soonest I finish them. Don't hesitate to contact me if you find any bugs in the code!

Requirements

PyTorch 1.0 and TorchText 0.3

Contents

  • 01 - Basic Neural Language Models
  • 02 - Regularized and Variational RNNs
  • 03 - Weight-tied LSTMs
  • 04 - Recurrent Highway Networks
  • 05 - AWD-LSTMs
  • 06 - Transformer Architectures for Language Modeling

Changelogs

This repository is a work in progress and I will make notebooks available as early as I can, so be sure to check back often!

  • 04/20/19 -- Added Recurrent Highway Networks
  • 04/21/19 -- Added rewritten version of Weight-Tied LSTMs. Switched to WikiText-2 on post-2014 papers. Will upload the other notebooks as soon as I finish rewriting.

About

Implementing some key architectures for language modeling using PyTorch

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published