|
What is the difference between Pre-LN and Post-LN Transformers? |
Answered by
Ultron09
Aug 28, 2026
Replies: 1 comment
|
Pre-LN provides stable gradient backpropagation directly through residual streams, preventing gradient explosion. |
0 replies
Answer selected by
Ultron09
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Pre-LN provides stable gradient backpropagation directly through residual streams, preventing gradient explosion.