SevenNet

SevenNet (Scalable EquiVariance-Enabled Neural Network) is a graph neural network (GNN)-based interatomic potential package that supports parallel molecular dynamics simulations using LAMMPS. Its core model is based on NequIP.

• Pretrained GNN interatomic potential and fine-tuning interface

• Support for the Python Atomic Simulation Environment (ASE) calculator

• GPU-parallelized molecular dynamics with LAMMPS

• CUDA-accelerated D3 (van der Waals) dispersion

• Multi-fidelity training for combining multiple databases with different calculation settings

Installation

Ensure that your environment uses Python >= 3.10 and PyTorch >= 2.0.0 (see https://pytorch.org/get-started/locally/) Then install SevenNet via:

pip install sevenn

For acceleration and LAMMPS integration, refer to the the installation guides below.

Contents

• User Guide
  • Pretrained models
  • Accelerators
  • LAMMPS: ML-IAP
  • LAMMPS: PyTorch
  • ASE calculator
  • TorchSim
  • Command line interface
  • CUDA-accelerated Grimme’s D3
  • Notebook tutorials
• Citation

Misc

• Changelog