Downloads · 30 days
0
thermoatoms/CuAu-ACE
CuAu-ACE is a machine learning model from thermoatoms. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-4.0.
Atomic Cluster Expansion (ACE) interatomic potentials for the Au-Cu binary system, one per exchange-correlation functional, trained on the thermoatoms/CuAu DFT dataset. Suitable for molecular dynamics of Cu, Au, and C…
Downloads · 30 days
0
Access
Public
Updated Jul 25, 2026
Repo size
—
Likes
0
Public
Click a slice to open those files.
.yace1.8 MB · 100%
From the Hugging Face model README
Atomic Cluster Expansion (ACE) interatomic potentials for the Au-Cu binary system, one per exchange-correlation functional, trained on the thermoatoms/CuAu DFT dataset. Suitable for molecular dynamics of Cu, Au, and Cu-Au alloys, including free energy and phase diagram calculations.
| file | functional | trained on dataset config |
|---|---|---|
AuCu_LDA.yace | LDA | lda |
AuCu_GGA.yace | GGA (PBE) | pbe |
AuCu_R2SCAN.yace | r2SCAN | r2scan |
The .yace files are production ACE potentials for LAMMPS (requires the
ML-PACE package):
pair_style pace
pair_coeff * * AuCu_GGA.yace Au Cu
The element names in pair_coeff map your LAMMPS atom types to potential
species. From ASE, use the potentials through the LAMMPS calculator
interfaces.
Download a single file:
from huggingface_hub import hf_hub_download
path = hf_hub_download("thermoatoms/CuAu-ACE", "AuCu_GGA.yace")
Fitted with pacemaker: 1000 functions per element, outer cutoff 6.2 Å, linear plus Finnis-Sinclair output layer (two densities). Training followed the body-ordered ladder scheme, with structures exponentially weighted by their distance from the training-data convex hull and a 10 % relative force weight. Core repulsion is handled by smoothly switching to a ZBL potential at 1.5-1.7 Å.
If you use these potentials, please cite:
@misc{Menon2026,
title={Computing binary alloy phase diagrams with explicit configurational and vibrational entropy},
author={Sarath Menon and Marvin Poul and Tilmann Hickel and Jörg Neugebauer and Ralf Drautz},
year={2026},
eprint={2607.14795},
archivePrefix={arXiv},
primaryClass={cond-mat.mtrl-sci},
url={https://arxiv.org/abs/2607.14795},
}