This is an OMatG (Open Materials Generation) model for crystal structure prediction (CSP) of inorganic crystals trained on the MP-20 dataset.

The MP-20 dataset consists of structures from the Materials Project database containing 20 or fewer atoms.

The subdirectories in this repository contain various model hyperparameters and training checkpoints for a variety of MP-20-CSP models.

The checkpoints and model hyperparameters can be used for prediction of crystalline structures with OMatG, as described in the this README.md file

The Linear-ODE checkpoints currently provide the best results with respect to the match rate and the average root-mean square distance between generated and matched reference structures.

Please cite our paper on OpenReview if using OMatG.

OMatG on GitHub: See this repository for OMatG installation, training and usage instructions.
KIM Initiative: Knowledgebase of Interatomic Models. Tools and resources for researchers in materials science and chemistry.
Fermat-ML on GitHub: Foundational Representation of Materials. Machine learning foundation model for materials and chemistry discovery.