You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I had the same question. I understand I need to set "attention_pruning_method" : pruning_method and "dense_pruning_method" : pruning_method:1d_alt for hybrid pruning.
Is it that for hybrid-filled approach we train the model again with reinitializing the weights for heads which are not completely pruned and this is done separately after hybrid pruning? or Is there a argument I can set in the code for hybrid-filled pruning? @madlag@echarlaix
Activity
sangamesh-kodge commentedon Jun 5, 2023
I had the same question. I understand I need to set
"attention_pruning_method" : pruning_method
and"dense_pruning_method" : pruning_method:1d_alt
for hybrid pruning.Is it that for hybrid-filled approach we train the model again with reinitializing the weights for heads which are not completely pruned and this is done separately after hybrid pruning? or Is there a argument I can set in the code for hybrid-filled pruning? @madlag @echarlaix