Skip to content
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.

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

How to add a mamba backbone as an encoder for training #1003

Open
ljb-1 opened this issue Dec 6, 2024 · 2 comments
Open

How to add a mamba backbone as an encoder for training #1003

ljb-1 opened this issue Dec 6, 2024 · 2 comments

Comments

@ljb-1
Copy link

ljb-1 commented Dec 6, 2024

No description provided.

@qubvel
Copy link
Collaborator

qubvel commented Dec 6, 2024

Hey @ljb-1! Thanks for the question, at the moment it's not supported out of the box. You can make your own backbone based on timm_universal and/or mix_transformer backbones. I'm going to add support for more timm models in coming months.

@qubvel
Copy link
Collaborator

qubvel commented Dec 22, 2024

Hey @ljb-1,

Mamba out encoders are supported with the latest main branch, check this out with the following encoders (add tu- prefix to names)

mambaout_base
mambaout_base_plus_rw
mambaout_base_short_rw
mambaout_base_tall_rw
mambaout_base_wide_rw
mambaout_femto
mambaout_kobe
mambaout_small
mambaout_small_rw
mambaout_tiny

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants