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 am currently working on quantizing models and would like to analyze how varying the percentage of retained salient weights in FP16 impacts performance. However, I am having trouble identifying where in the code this adjustment can be made. Could you please help clarify this?
Thank you!
The text was updated successfully, but these errors were encountered:
akylbekmaxutov
changed the title
Could you explain me how can I change the percent of kept salient weights in FP16?
Could you explain me how can I change the percentage of kept salient weights in FP16?
Nov 15, 2024
Hello,
I am currently working on quantizing models and would like to analyze how varying the percentage of retained salient weights in FP16 impacts performance. However, I am having trouble identifying where in the code this adjustment can be made. Could you please help clarify this?
Thank you!
The text was updated successfully, but these errors were encountered: