aubmindlab / araelectra-base-discriminator

Other135M1.3K5Updated Oct 29, 2024

Downloads

1.3K

Likes

5

Last updated

Oct 29, 2024

License

Not available

ELECTRA is a method for self-supervised language representation learning. It can be used to pre-train transformer networks using relatively little compute. ELECTRA models are trained to distinguish "real" input tokens vs "fake" input tokens generated by another neural network,…

Tasks & library

  • transformers

Tags

  • transformers
  • pytorch
  • tf
  • tensorboard
  • electra
  • pretraining

Technical specifications

Parameters135M
Librarytransformers
Languagesar
LicenseNot available