WoosukKwon/retraining-free-pruning
[NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers
Python
Issues
- 0
Grad, magnitude & fisher
#20 opened by q121q - 0
- 0
Some confusion about least squares
#18 opened by TianL123 - 0
SlowFast and TimesFormer?
#17 opened by xqc-qc - 1
Test Accuracy function is a bit too slow
#14 opened by xihajun - 2
What is the purpose of setting "encoder.layers" and how does it differ from "encoder.layer" ?
#15 opened by WeiweiZhang1 - 0
Question about the pruned model.
#16 opened by ThoughtsAreStarry - 0
Hi, can this "the three-stage decomposition of the pruning process" be applied to GPT-X or any other NLG task? And how this could be done?
#13 opened by ZepinLi - 0
- 0
Any experiments on NLG tasks?
#11 opened by minghaoBD - 1
dependency package versions
#9 opened by minghaoBD - 0
- 2
- 1
About the speedup performance of the code
#7 opened by CaffreyR - 1
- 4
Real-time inference results
#5 opened by justlovebarbecue - 2
Missing datasets file?
#4 opened by justlovebarbecue - 0
GLUE & SQuAD Metadata
#2 opened by WoosukKwon