issues
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
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Prepare checkpoints can not visit
#21
xiaowanzi-tju
closed
3 weeks ago
0
Grad, magnitude & fisher
#20
q121q
closed
3 months ago
0
How to use the final calculated mask to improve the speed of the model
#19
yynngu
opened
4 months ago
0
Some confusion about least squares
#18
TianL123
opened
5 months ago
1
SlowFast and TimesFormer?
#17
xqc-qc
opened
1 year ago
0
Question about the pruned model.
#16
ThoughtsAreStarry
opened
1 year ago
0
What is the purpose of setting "encoder.layers" and how does it differ from "encoder.layer" ?
#15
WeiweiZhang1
closed
1 year ago
2
Test Accuracy function is a bit too slow
#14
xihajun
opened
1 year ago
1
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
ZepinLi
opened
1 year ago
0
Can this be used for detection, segmentation, and other tasks?
#12
666DZY666
opened
1 year ago
0
Any experiments on NLG tasks?
#11
minghaoBD
opened
1 year ago
0
Use your Code for other classification datasets
#10
fabianbrandscheid
opened
1 year ago
0
dependency package versions
#9
minghaoBD
closed
1 year ago
1
why bert-base-uncased model set constraint to 0.5, qqp test accuracy only 0.3743
#8
VpouL
closed
1 year ago
3
About the speedup performance of the code
#7
CaffreyR
closed
1 year ago
1
Good Job! Can this framework work for the Transformer-based vision models?
#6
ybai62868
closed
1 year ago
1
Real-time inference results
#5
justlovebarbecue
closed
2 years ago
4
Missing datasets file?
#4
justlovebarbecue
closed
2 years ago
2
Refactoring
#3
WoosukKwon
closed
2 years ago
0
GLUE & SQuAD Metadata
#2
WoosukKwon
closed
2 years ago
0
Update main
#1
WoosukKwon
closed
3 years ago
0