New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

A queation about Algorithm 1 Vim Block Process in your paper #132

Open

shawnnjupt opened this issue Jan 22, 2025 · 0 comments

shawnnjupt commented Jan 22, 2025

in line 13, you write

but in mamba ssm architecture , A0'=exp(delta*ParameterA) . so do VIM drop exp ?

but in your code ,i see mamba is used from Mamba source code that uses exp.

So ,which is the true architecture ?

Can anyone help me solve the problem ,thanks very much!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment