---
license: mit
tags:
- Machine Learning Interatomic Potential
---

# Model Card for mace-universal / mace-mp

MACE-MP is a pretrained general-purpose foundational interatomic potential published with the [preprint arXiv:2401.00096](https://arxiv.org/abs/2401.00096).

This repository is the archive of pretrained checkpoints for manual loading using `MACECalculator` or further fine-tuning. Now the easiest way to use models is to follow the **[documentation for foundtional models](https://mace-docs.readthedocs.io/en/latest/examples/foundation_models.html)**.
All the models are trained with MPTrj data, [Materials Project](https://materialsproject.org) relaxation trajectories compiled by [CHGNet](https://arxiv.org/abs/2302.14231) authors to cover 89 elements and 1.6M configurations. The checkpoint was used for materials stability prediction on [Matbench Discovery](https://matbench-discovery.materialsproject.org/) and the associated [preprint](https://arXiv.org/abs/2308.14920).

[MACE](https://github.com/ACEsuit/mace) (Multiple Atomic Cluster Expansion) is a machine learning interatomic potential (MLIP) with higher order equivariant message passing. For more information about MACE formalism, please see authors' [paper](https://arxiv.org/abs/2206.07697). 

# Usage

1. (optional) Install Pytorch, [ASE](https://wiki.fysik.dtu.dk/ase/) prerequisites for preferred version
2. Install [MACE](https://github.com/ACEsuit/mace) through GitHub (not through pypi)

```shell
pip install git+https://github.com/ACEsuit/mace.git
```
3. Use MACECalculator

```python
from mace.calculators import MACECalculator
from ase import Atoms, units
from ase.build import bulk
from ase.md.npt import NPT

atoms = bulk("NaCl", crystalstructure='rocksalt', a=3.54, cubic=True)

calculator = MACECalculator(
  model_paths=/path/to/pretrained.model,
  device=device,
  default_dtype="float32" or "float64",
)

atoms.calc = calculator

dyn = NPT(
  atoms=atoms,
  timestep=timestep,
  temperature_K=temperature,
  externalstress=externalstress,
  ttime=ttime,
  pfactor=pfactor,
)

dyn.run(steps)
```

# Citing

If you use the pretrained models in this repository, please cite all the following:

```
@article{batatia2023foundation,
  title={A foundation model for atomistic materials chemistry},
  author={Batatia, Ilyes and Benner, Philipp and Chiang, Yuan and Elena, Alin M and Kov{\'a}cs, D{\'a}vid P and Riebesell, Janosh and Advincula, Xavier R and Asta, Mark and Baldwin, William J and Bernstein, Noam and others},
  journal={arXiv preprint arXiv:2401.00096},
  year={2023}
}

@inproceedings{Batatia2022mace,
  title={{MACE}: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields},
  author={Ilyes Batatia and David Peter Kovacs and Gregor N. C. Simm and Christoph Ortner and Gabor Csanyi},
  booktitle={Advances in Neural Information Processing Systems},
  editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
  year={2022},
  url={https://openreview.net/forum?id=YPpSngE-ZU}
}

@article{riebesell2023matbench,
  title={Matbench Discovery--An evaluation framework for machine learning crystal stability prediction},
  author={Riebesell, Janosh and Goodall, Rhys EA and Jain, Anubhav and Benner, Philipp and Persson, Kristin A and Lee, Alpha A},
  journal={arXiv preprint arXiv:2308.14920},
  year={2023}
}


@misc {yuan_chiang_2023,
  author       = { {Yuan Chiang, Philipp Benner} },
  title        = { mace-universal (Revision e5ebd9b) },
  year         = 2023,
  url          = { https://huggingface.co/cyrusyc/mace-universal },
  doi          = { 10.57967/hf/1202 },
  publisher    = { Hugging Face }
}

@article{deng2023chgnet,
  title={CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling},
  author={Deng, Bowen and Zhong, Peichen and Jun, KyuJung and Riebesell, Janosh and Han, Kevin and Bartel, Christopher J and Ceder, Gerbrand},
  journal={Nature Machine Intelligence},
  pages={1--11},
  year={2023},
  publisher={Nature Publishing Group UK London}
}
```

# Training Guide

## Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

For now, please download MPTrj data from [figshare](https://figshare.com/articles/dataset/Materials_Project_Trjectory_MPtrj_Dataset/23713842). We may upload to HuggingFace Datasets in the future.

## Fine-tuning

<!-- This should link to a Training Procedure Card, perhaps with a short stub of information on what the training procedure is all about as well as documentation related to hyperparameters or additional training details. -->

We provide an example multi-GPU training script [2023-08-14-mace-universal.sbatch](https://huggingface.co/cyrusyc/mace-universal/blob/main/2023-08-14-mace-universal.sbatch), which uses 40 A100s on NERSC Perlmutter. Please see MACE `multi-gpu` branch for more detailed instructions.