BAM-MP-DeNS
Model overview
Interatomic potential: Energy with gradient-based forces and stress.
CPS 0.672 combines discovery, geometry optimization, and phonons. Inspect individual task results below.
Licenses are as declared by the submitter. Training dataset terms are listed separately below.
Click a task score to show this model's diagnostics below.
Model info
Specifications
- Architecture
- gnn
- Outputs
- Energy with gradient-based forces and stress EFSG
- Openness
- Open source, open data OSOD
Discovery protocol
- Training
- structure to energy, force, stress S2EFS
- Evaluation
- initial structure to relaxed energy with structure relaxation IS2RE-SR
Training set
MPtrj: 1.58M structures from 146k materials · MIT
Trained by
Description
BAM-MP-DeNS is a universal interatomic potential from the BAM-torch BAM_DeNS branch (RACE architecture), trained on MPtrj with denoising non-equilibrium structures (DeNS) as an auxiliary task. It is evaluated here on WBM IS2RE-SR discovery and geometry optimization, PhononDB kappa-103, DynaMat MD, and diatomic curves.
Hyperparams
Run this model
Use the submitted environment with the upstream instructions.
From a repository checkout, run uv run models/run_kappa.py --list-models to check checkpoint requirements. If this model requires one, add --checkpoint /path/to/checkpoint below. Then execute the printed command
for a phonon smoke test in the model's isolated environment.
uv run models/run_kappa.py --model bam-mp-dens --print-cmd --dry-run