acesuit/mace-mp

MACE-MP models

MACE-MP models

This repository contains the MACE-MP pre-trained foundation models for materials chemistry, parameterised for 89 chemical elements.

To use the models please install the MACE code.

Models

The models are available in the MACE-MP-0.

If you use the models please cite

@article{batatia2023foundation,
      title={A foundation model for atomistic materials chemistry},
      author={Ilyes Batatia and Philipp Benner and Yuan Chiang and Alin M. Elena and Dávid P. Kovács and Janosh Riebesell and Xavier R. Advincula and Mark Asta and William J. Baldwin and Noam Bernstein and Arghya Bhowmik and Samuel M. Blau and Vlad Cărare and James P. Darby and Sandip De and Flaviano Della Pia and Volker L. Deringer and Rokas Elijošius and Zakariya El-Machachi and Edvin Fako and Andrea C. Ferrari and Annalena Genreith-Schriever and Janine George and Rhys E. A. Goodall and Clare P. Grey and Shuang Han and Will Handley and Hendrik H. Heenen and Kersti Hermansson and Christian Holm and Jad Jaafar and Stephan Hofmann and Konstantin S. Jakob and Hyunwook Jung and Venkat Kapil and Aaron D. Kaplan and Nima Karimitari and Namu Kroupa and Jolla Kullgren and Matthew C. Kuner and Domantas Kuryla and Guoda Liepuoniute and Johannes T. Margraf and Ioan-Bogdan Magdău and Angelos Michaelides and J. Harry Moore and Aakash A. Naik and Samuel P. Niblett and Sam Walton Norwood and Niamh O'Neill and Christoph Ortner and Kristin A. Persson and Karsten Reuter and Andrew S. Rosen and Lars L. Schaaf and Christoph Schran and Eric Sivonxay and Tamás K. Stenczel and Viktor Svahn and Christopher Sutton and Cas van der Oord and Eszter Varga-Umbrich and Tejs Vegge and Martin Vondrák and Yangshuai Wang and William C. Witt and Fabian Zills and Gábor Csányi},
      year={2023},
      eprint={2401.00096},
      archivePrefix={arXiv},
      primaryClass={physics.chem-ph}
}

MACE-Universal by Yuan Chiang, 2023, Hugging Face, Revision e5ebd9b, DOI: 10.57967/hf/1202, URL: https://huggingface.co/cyrusyc/mace-universal

Training scripts

We provide training scripts for the models in this repository. The latest training command line is found in mace_mp_0/2024-01-07-mace-128-L2.sh.

Training data

The MPtrj dataset used to train the model is available at training-data. Please cite the following paper if you use the dataset.

@article{deng2023chgnet,
      title={CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling},
      author={Bowen Deng and Peichen Zhong and KyuJung Jun and Janosh Riebesell and Kevin Han and Christopher J. Bartel and Gerbrand Ceder},
      year={2023},
      eprint={2302.14231},
      archivePrefix={arXiv},
      primaryClass={cond-mat.mtrl-sci}
}

Trajectories and movies

Trajectories for the results presented in the paper and simulation movies can be found at example-xyz-movies.

mace-mp's Issues

Releasing statistics file

Hi, thanks for uploading the training scripts. They're very helpful.

Is the statistics file referenced in the training shell scripts (e.g., mptrj-gga-ggapu-statistics.json mentioned here) available for download anywhere?

How to retrain mace-mp?

Hi,

Thank you for this model, it performs great.

I have some problems on an amorphous oxide, for which I have some DFT configurations too. I would like to use these for retraining the model and improve my results. Is there any script or API that would enable me to do that?

Thank you very much for your help!

Giuliana

Add training parameters

Could you please add the training command line or parameters to this repo?

Train/valid/test split

Hi,

Where could I find the data splits for this model?

Question about memory scaling during training

Hi,

Thanks for building these models. I noticed that the training scripts for the MP pre-trained models use small batch sizes of 16. What was the reasoning for this choice?

My application requires training on graphs with hundreds to a few thousand nodes, and I was hoping that MACE's lack of explicit triplet angle computation (as in DimeNet or GemNet) would offer more favorable memory scaling. Any insights would be greatly appreciated.

Thanks,
Rees

LAMMPS loadable MP0 model?

Hi folks,

Very exciting to see the foundation model for multi-element systems. :)

I was wondering if there is a model that is readily available to load in LAMMPS and perform structural minimization?

I see that one needs a .pt file to load into LAMMPS from the tutorial here: https://mace-docs.readthedocs.io/en/latest/guide/lammps.html#id2

But the publicly available MACE model is of the format .model from here: https://github.com/ACEsuit/mace-mp/releases/tag/mace_mp_0.

Are these two the same file?

EDIT: adding @cortner, since I work with him.

EDIT2: Also, I don't see a ML-MACE package available on LAMMPS, is it still not publicly released?

Where are the Similarity Statement Files?

Hello! I am going through your paper and was looking for the datafiles in each of the "Similarity Statement" sections. These are the files that can be viewed on https://chemiscope.org

I can't find these files online, is there a link for them? Thank you!