The Need for Speed: Pruning Transformers with One Recipe
This repository contains the pre-computed parameter rankings for several language and vision models.
Saved Parameter Rankings
The saved parameter rankings include the computed salience scores for various language and vision models using the OPTIN framework. To run the evaluation with our saved pruning framework, please download the respective model/task folder and create the expected file tree detailed on our GitHub.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.