This repository is aim to deploy our machine learning interatomic potentials trained for specific application. We will include equivariant models as well as model trained on invariant-based models. We have potentials for the following systems:

• Elemental carbon trained on diversed carbon dataset (Shaidu et al. npj Comput Mater 7, 52 (2021). https://doi.org/10.1038/s41524-021-00508-6).
• Amine-appended metal-organic frameworks featuring Mg2(dobpdc) variant (Shaidu et al. PRX Energy, 2(2), 023005 (2023)., Shaidu et al., J. Phys. Chem. Lett. 15 (4), 1130–1134 (2024). https://doi.org/10.1021/acs.jpclett.3c03135).
• Multilayer transition metal dichalcogenides (Shaidu et al. npj Comput Mater 11, 273 (2025). https://doi.org/10.1038/s41524-025-01761-9)

• PANNA: The training code and lammps interface for using the PANNA code can be found in publicly available PANNA software [https://gitlab.com/PANNAdevs/panna] developed by me and others
• MACE