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

Add support for more foundation models #2429

Open
Andrew-S-Rosen opened this issue Aug 17, 2024 · 0 comments
Open

Add support for more foundation models #2429

Andrew-S-Rosen opened this issue Aug 17, 2024 · 0 comments
Labels
enhancement New feature or request good-first-issue

Comments

@Andrew-S-Rosen
Copy link
Member

Andrew-S-Rosen commented Aug 17, 2024

What new feature would you like to see?

We should add the pre-trained SevenNet MLP to the supported MLP methods since it performs so well on https://matbench-discovery.materialsproject.org.

This would entail adding it as a supported calculator method in quacc.recipes.mlp._base.pick_calculator, updating the method type hints in the quacc.recipes.mlp functions to include SevenNet, adding some tests to the test suite, and adding sevenn to pyproject.toml.

Also see https://github.com/orbital-materials/orb-models.

@Andrew-S-Rosen Andrew-S-Rosen changed the title Add support for SevenNet Add support for SevenNet and OrbNet Sep 3, 2024
@Andrew-S-Rosen Andrew-S-Rosen changed the title Add support for SevenNet and OrbNet Add support for more foundation models Oct 11, 2024
Andrew-S-Rosen pushed a commit that referenced this issue Dec 1, 2024
## Summary of Changes
Added **sevennet** to the MLP recipes based on issue #2429. 

Key changes include:

1. Added sevennet implementation to mlp recipes
2. Created unit tests to validate sevennet functionality
3. Ensured compatibility with existing MLP workflows

## Requirements

-[X] My PR is focused on a single feature addition [#2429 ].
-[X] My PR has relevant, comprehensive unit tests.
-[X] My PR is on a custom branch (feature/sevennetMLP).

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Andrew-S-Rosen pushed a commit that referenced this issue Dec 23, 2024
## Summary of Changes
Added **orb-models** to the MLP recipes based on issue #2429. 

Key changes include:

1. Added orb-models implementation to mlp recipes
2. Created unit tests to validate orb-models functionality
3. Ensured compatibility with existing MLP workflows

## Requirements

-[X] My PR is focused on a single feature addition [#2429 ].
-[X] My PR has relevant, comprehensive unit tests.
-[X] My PR is on a custom branch (feature/orbnet-models).

## Note to the reviewer: 
1. orb-models outputs are somewhat more stochastic than other tests, so
I used a `rel` flag to limit the accuracy of the pytest comparison. I
set it to `1e-4` after some failed checks.

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request good-first-issue
Development

No branches or pull requests

1 participant