Add MACE #48
Merged
Add MACE #48
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
goal is to be able to run a single script that will update all the model figures (both the interactive version for the leaderboard and the PDF version for the paper)
…ze_element_errors.py to run former as part of update_model_figs.py
janosh
commented
Jul 26, 2023
| except ImportError as exc: | ||
| raise ImportError( | ||
| "pdfkit not installed\nrun pip install pdfkit && brew install " | ||
| "homebrew/cask/wkhtmltopdf\n(brew is macOS only, use apt on linux)" |
There was a problem hiding this comment.
Reason: wkhtmltopdf requires Rosetta, i.e. is not natively M1 Mac compatible.
…ts/analyze_element_errors.py'
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
As released in NeuRIPS paper and further developed in 2022 preprint.
This submission uses the
2023-07-14-mace-universal-2-big-128-6.modelcheckpoint pre-trained by the MACE authors on the original M3GNet training set.MACE relaxed each test set structure using
ase.optimizers.FIREuntil the maximum force in the training set drops below 0.05 eV/Å or 500 optimization steps are reached, whichever occurs first.