search

huggingface / pytorch-openai-transformer-lm

🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
MIT License
1.51k stars 285 forks source link

Redundant decoder #32

Closed joshim5 closed 6 years ago

joshim5 commented 6 years ago

Nice implementation! Your TransformerModel class has a decoder property, but this is not necessary nor used because you also have a decoder property on the LMHead class.

rodgzilla commented 6 years ago

Thank you for telling us.

Have a nice day.