Transformers documentation

BERTology

You are viewing v4.44.1 version. A newer version v4.46.0 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

BERTology

There is a growing field of study concerned with investigating the inner working of large-scale transformers like BERT (that some call “BERTology”). Some good examples of this field are:

In order to help this new field develop, we have included a few additional features in the BERT/GPT/GPT-2 models to help people access the inner representations, mainly adapted from the great work of Paul Michel (https://arxiv.org/abs/1905.10650):

  • accessing all the hidden-states of BERT/GPT/GPT-2,
  • accessing all the attention weights for each head of BERT/GPT/GPT-2,
  • retrieving heads output values and gradients to be able to compute head importance score and prune head as explained in https://arxiv.org/abs/1905.10650.

To help you understand and use these features, we have added a specific example script: bertology.py while extract information and prune a model pre-trained on GLUE.

< > Update on GitHub