Skip to content

MODEL_TENSOR.SSM_DT_NORM has defined twice #14991

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

Merged
merged 2 commits into from
Jul 31, 2025
Merged

MODEL_TENSOR.SSM_DT_NORM has defined twice #14991

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a567606
MODEL_TENSOR.SSM_DT_NORM has defined twice, and sencond overwritten t…
csabakecskemeti Jul 31, 2025
272a174
correct order
csabakecskemeti Jul 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 1 addition & 4 deletions gguf-py/gguf/tensor_mapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -615,10 +615,6 @@ class TensorNameMap:
"model.layers.layers.{bid}.mixer.dt_proj", # plamo2
),

MODEL_TENSOR.SSM_DT_NORM: (
"model.layers.{bid}.mamba.dt_layernorm", # jamba
),
Copy link
Collaborator

@compilade compilade Jul 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Personally, I would have done it the other way and keep this one (since it's right near SSM_DT) instead of the other one, but it's correct like this too since the mappings are still merged.

Copy link
Contributor Author

@csabakecskemeti csabakecskemeti Jul 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I can change it quickly

Copy link
Contributor Author

@csabakecskemeti csabakecskemeti Jul 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done


MODEL_TENSOR.SSM_A: (
"model.layers.{bid}.A_log", # mamba-hf
"backbone.layers.{bid}.mixer.A_log", # mamba
Expand Down Expand Up @@ -647,6 +643,7 @@ class TensorNameMap:

MODEL_TENSOR.SSM_DT_NORM: (
"model.layers.layers.{bid}.mixer.dt_norm.weight", # plamo2
"model.layers.{bid}.mamba.dt_layernorm", # jamba
),

MODEL_TENSOR.SSM_NORM: (
Expand Down