Downloads · 30 days
0
M3GNet-Eform-MP-2018.6.1
materialyze/M3GNet-Eform-MP-2018.6.1
M3GNet-Eform-MP-2018.6.1 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 formation energy model for 89 elements of the periodic table. It contains the formation energy for most materials. This is essentially a retrained version of the M3GNet formation energy model or…
Access
Public
Updated May 6, 2026
Repo size
1.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.6 MB · 100%
At a glance
- Library
- matgl
- Access
- Public
- Created
- May 6, 2026
- Updated
- May 6, 2026
- SHA
- 17509515
Model card
From the Hugging Face model README
Aim
This model is a M3GNet formation energy model for 89 elements of the periodic table. It contains the formation energy for most materials. This is essentially a retrained version of the M3GNet formation energy model originally implemented in tensorflow.
Training dataset
MP-2018.6.1: Materials Project formation energy as of 2018.6.1.
- Training set size: : 62315
- Validation set size: 3461
- Test set size: 3463
Performance metrics
MAE of formation energy in eV/atom.
- Training: 0.007 eV/atom
- Validation: 0.019 eV/atom
- Test: 0.019 eV/atom
References
Chen, C., Ong, S.P. A universal graph deep learning interatomic potential for the periodic table. Nat Comput Sci,
2, 718–728 (2022). https://doi.org/10.1038/s43588-022-00349-3.
- Library
- matgl
- Created
- May 6, 2026
- Updated
- May 6, 2026