Downloads · 30 days
0
SO3Net-PES-ANI-1x-Subset
materialyze/SO3Net-PES-ANI-1x-Subset
SO3Net-PES-ANI-1x-Subset is a machine learning model from materialyze. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for matgl.
This model is a M3GNet potential for 4 elements including H, C, N, O. It has broad applications in the dynamic simulations of organic molecules.
Access
Public
Updated May 6, 2026
Repo size
4.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt4.4 MB · 100%
At a glance
- Library
- matgl
- Access
- Public
- Created
- May 6, 2026
- Updated
- May 6, 2026
- SHA
- 3b661e53
Model card
From the Hugging Face model README
Description
This model is a M3GNet potential for 4 elements including H, C, N, O. It has broad applications in the dynamic simulations of organic molecules.
Training dataset
ANI-1x-Subset: 300K MD simulations and Materials Project ground state calculations.
- Training set size: 991735
- Validation set size: 248355
- Test set size: 248355
Performance metrics
Training and validation errors
MAEs of energies, forces and stresses, respectively
- Training: 2.281 meV/atom, 46 meV/A
- Validation: 2.286 meV/atom, 46 meV/A
- Test: 1.596 meV/atom, 35 meV/A
References
Ko, T.W., Deng, B., Nassar, M. et al. Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry. npj Computation Materials 11, 253 (2025).
- Library
- matgl
- Created
- May 6, 2026
- Updated
- May 6, 2026