How to use the zero_shot_benchmark code?

luuyin / OWL

Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"

https://arxiv.org/pdf/2310.05175.pdf

MIT License

51 stars 8 forks source link

Closed jonas-klesen closed 1 year ago

jonas-klesen commented 1 year ago

Hi there!

How to use the code in the zero_shot_benchmark folder in order to evaluate, as done in table 4?

An example usage in the README would be helpful. Thanks!

luuyin commented 1 year ago

Thanks for your question. We just updated the README. You could find the example script there.

jonas-klesen commented 1 year ago

Thank you very much!