tummfm/chemtrain

Training neural network potentials

Library for efficient training and application of Machine Learning Interatomic Potentials (MLIP)

Equivariant machine learning interatomic potentials in JAX.

train and use graph-based ML models of potential energy surfaces

TorchANI 2.0 is an open-source library that supports training, development, and research of ANI-style neural network interatomic potentials. It was originally developed and is currently maintained by the Roitberg group.

A high-performance toolkit for atomistic simulations in JAX.

High level API for using machine learning models in OpenMM simulations

Train, fine-tune, and manipulate machine learning models for atomistic systems

NequIP is a code for building E(3)-equivariant interatomic potentials