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

[BUG] Missing Configuration Attributes in DefaultMambularConfig #209

Open
nwuestefeld opened this issue Feb 3, 2025 · 0 comments
Open
Labels
bug Something isn't working

Comments

@nwuestefeld
Copy link

The following attributes are missing in DefaultMambularConfig, yet they are required to initialize the ResidualBlock in the Mamba class:
conv_bias
AD_weight_decay
BC_layer_norm
d_conv

Instead of fetching these attributes from the configuration, the implementation always falls back to a fixed default value.

For instance, in line 33 of the Mamba class:

d_conv = getattr(config, "d_conv", 4)
Since d_conv is not defined in DefaultMambularConfig, it always defaults to 4, ignoring potential user-defined configurations.

@nwuestefeld nwuestefeld added the bug Something isn't working label Feb 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant