metadata
library_name: matgl
tags:
- matgl
- materials-science
- graph-neural-network
- machine-learning-interatomic-potential
- foundation-potential
- mlip
TensorNet-PES-MatPES-r2SCAN-2025.2-m
Introduction
Pre-trained TensorNet foundation potential, i.e., universal machine learning interatomic potential trained on the MatPES-r2SCAN-2025.2 dataset. This is a medium-size TensorNet variant (~1.07M parameters; units=128, nblocks=3), one block deeper than the standard materialyze/TensorNet-PES-MatPES-r2SCAN-2025.2 reference (0.84M).
Potential
matgl Potential model (version 3).
Usage
import matgl
model = matgl.load_model("materialyze/TensorNet-PES-MatPES-r2SCAN-2025.2-m")
Model Details
- Number of parameters: 1,067,906
Metrics
| Split | Energy MAE (eV/atom) | Force MAE (eV/A) | Stress MAE (GPa) |
|---|---|---|---|
| Train | 0.034200 | 0.125625 | 0.451469 |
| Validation | 0.035304 | 0.155005 | 0.658389 |
| Test | 0.035895 | 0.154268 | 0.667323 |
Metadata
{
"dataset": "MatPES-r2SCAN-2025.2",
}