Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
graph-pes
Logo
  • Tutorials
    • Train a model
    • Model analysis
    • Fine-tuning
    • Implement a model
    • Custom training loops

CLI Reference

  • graph-pes-train
    • The basics
    • Config options
    • Example configs
  • graph-pes-resume
  • graph-pes-test
  • graph-pes-id

API Reference

  • Data
    • Atomic Graphs
    • Datasets
    • Loader
  • Models
    • Addition Model
    • Energy Offset
    • Pair Potentials
    • Many Body Models
      • Stillinger-Weber
      • EDDP
      • SchNet
      • PaiNN
      • NequIP
      • MACE
      • TensorNet
  • Fitting
    • Losses
    • Optimizers
    • Callbacks
  • Building blocks
    • Distance Expansions
    • Envelopes
    • Aggregation
    • Scaling
    • PyTorch Helpers
    • e3nn Helpers
  • Utils

Interfaces

  • mace-torch
  • mattersim
  • orb-models

Tools

  • torch-sim
  • ASE
  • LAMMPS
  • Analysis

About

  • Theory
  • Development
Back to top
View this page

Many Body ModelsΒΆ

graph-pes has re-implemented the following, popular many-bodied, machine-learned interatomic potentials:

  • Stillinger-Weber
  • EDDP
  • SchNet
  • PaiNN
  • NequIP
  • MACE
  • TensorNet
Next
Stillinger-Weber
Previous
Pair Potentials
Copyright © 2023-2025, John Gardner
Made with Sphinx and @pradyunsg's Furo