Skip to content

Conversation

@agoscinski
Copy link
Contributor

@agoscinski agoscinski commented Jun 14, 2022

This is a PR from this commit.
2a879b7

To use the current lammps-rascal interface conveniently, we however don't take the newest format version #376 which is cleaner, but the older version compatible with the branch feat/lammps_preparations which is used for the current version of the lammps-rascal interface.

EDIT:
This is so people do not need to have to install a librascal version just to format the ML model json correctly compatible with lammps-rascal

* cpp representation and kernel information is now included in rascal's model
json file.

* weights are now always flattened to one dimension for consistency in the
models format.
@agoscinski agoscinski requested a review from PicoCentauri June 14, 2022 15:02
Copy link
Contributor

@PicoCentauri PicoCentauri left a comment

Choose a reason for hiding this comment

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

LGTM! Thanks @agoscinski

@PicoCentauri PicoCentauri merged commit 5f6dd49 into master Jun 15, 2022
@Luthaf Luthaf deleted the feat/qickdirty-cpp-paramaters-to-mlmodel branch June 15, 2022 07:57
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

Successfully merging this pull request may close these issues.

3 participants