search

WoosukKwon / retraining-free-pruning

[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers
https://arxiv.org/abs/2204.09656
173 stars 27 forks source link

Test Accuracy function is a bit too slow #14

Open xihajun opened 1 year ago

xihajun commented 1 year ago

https://github.com/WoosukKwon/retraining-free-pruning/blob/806ac5a6ff53b4978e5330d45a3de692493e4d0b/evaluate/nlp.py#L10

Hi there, thanks for sharing the coding for retraining-free-pruning, I tried to pruning bert-large model, and found the test_accuracy function is too slow for the squad dataset, any suggestion or guidance how can we speed it up?

applewpj commented 1 year ago

Hi there, I encounter the same issue, have you got any solution for this?