Downloads · 30 days
0
TensorNet-PES-MatPES-r2SCAN-2025.2-m
materialyze/TensorNet-PES-MatPES-r2SCAN-2025.2-m
TensorNet-PES-MatPES-r2SCAN-2025.2-m 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.
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, nb…
Access
Public
Updated Oct 8, 2026
Repo size
8.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt4.3 MB · 100%
At a glance
- Library
- matgl
- Access
- Public
- Created
- May 28, 2026
- Updated
- Oct 8, 2026
- SHA
- ade72ef1
Model card
From the Hugging Face model README
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",
}
- Library
- matgl
- Created
- May 28, 2026
- Updated
- Oct 8, 2026