nn_pruning icon indicating copy to clipboard operation
nn_pruning copied to clipboard
verified publisher icon huggingface

Applying Block Movement Pruning for BART

Open apurvnagvenkar opened this issue 3 years ago • 1 comments

Hi, I am working to prune BART model for seq2seq purpose. Currently, I have replaced this code with BART based functionalities. After executing I am getting drop in number of parameters for both attention and FFN but dimension reduction happens only for FFN which results in slowness. My questions are following:

  1. Is this right code to refer to or should I follow this command_line.py?
  2. Is there any existing code which works for BART based models for Conditonal Generation or Seq2Seq?

apurvnagvenkar avatar Jul 21 '22 16:07 apurvnagvenkar

Hi, I am working to prune BART model for seq2seq purpose. Currently, I have replaced this code with BART based functionalities. After executing I am getting drop in number of parameters for both attention and FFN but dimension reduction happens only for FFN which results in slowness. My questions are following:

  1. Is this right code to refer to or should I follow this command_line.py?
  2. Is there any existing code which works for BART based models for Conditonal Generation or Seq2Seq?

I am doing the same thing as you. Did you fix the problem? @apurvnagvenkar

robotsp avatar Mar 08 '23 09:03 robotsp