WoosukKwon/retraining-free-pruning

Issues

• Grad, magnitude & fisher

  #20 opened 2 months ago by q121q
  0

• How to use the final calculated mask to improve the speed of the model

  #19 opened 3 months ago by yynngu
  0

• Some confusion about least squares

  #18 opened 4 months ago by TianL123
  0

• SlowFast and TimesFormer?

  #17 opened a year ago by xqc-qc
  0

• Test Accuracy function is a bit too slow

  #14 opened a year ago by xihajun
  1

• What is the purpose of setting "encoder.layers" and how does it differ from "encoder.layer" ?

  #15 opened a year ago by WeiweiZhang1
  2

• Question about the pruned model.

  #16 opened a year ago 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 a year ago by ZepinLi
  0

• Can this be used for detection, segmentation, and other tasks?

  #12 opened 2 years ago by 666DZY666
  0

• Any experiments on NLG tasks?

  #11 opened 2 years ago by minghaoBD
  0

• dependency package versions

  #9 opened 2 years ago by minghaoBD
  1

• Use your Code for other classification datasets

  #10 opened 2 years ago by fabianbrandscheid
  0

• why bert-base-uncased model set constraint to 0.5, qqp test accuracy only 0.3743

  #8 opened 2 years ago by VpouL
  2

• About the speedup performance of the code

  #7 opened 2 years ago by CaffreyR
  1

• Good Job! Can this framework work for the Transformer-based vision models?

  #6 opened 2 years ago by ybai62868
  1

• Real-time inference results

  #5 opened 2 years ago by justlovebarbecue
  4

• Missing datasets file?

  #4 opened 2 years ago by justlovebarbecue
  2

• GLUE & SQuAD Metadata

  #2 opened 2 years ago by WoosukKwon
  0