There are no reviews yet. Be the first to send feedback to the community and the maintainers!
mace
MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.ACE.jl
Parameterisation of Equivariant Properties of Particle Systemsmace-jax
Equivariant machine learning interatomic potentials in JAX.ACEpotentials.jl
Machine Learning Interatomic Potentials with the Atomic Cluster Expansionmace-mp
MACE-MP modelsmace-layer
Higher order equivariant graph neural networks for 3D point cloudsACE1.jl
Atomic Cluster Expansion for Modelling Invariant Atomic Propertiesmace-off
MACE-OFF23 modelsObjectPools.jl
thread-safe and flexible temporary arrays and object cache for semi-manual memory managementACEhamiltonians.jl
Polynomials4ML.jl
Polynomials for ML: fast evaluation, batching, differentiationEquivariantModels.jl
Tools for geometric learningACEHAL
ACEfit.jl
Generic Codes for Fitting ACE modelsACEhamiltoniansExamples
Example code for the ACEhamiltonians code-base.IPFitting.jl
Fitting of NBodyIPsACEds.jl
Coarse-grained dynamical systemsACEmd.jl
UltraFastACE.jl
Experimenting with faster ACE potentialsACE1x.jl
Experimental features for ACE1.jlACE1docs.jl
User Documentation for ACEsuitACEpsi.jl
ACE wave function parameterizationsACEsktb.jl
experimental code for tight-binding hamiltoniansACEcore.jl
Some of the core computational kernels for building ACE modelsACEatoms.jl
Generic code for modelling atomic properties using ACEDecoratedParticles.jl
GeomOpt.jl
Geometry optimization interfaceHyperActiveLearning.jl
An accelerate dynamics stragety for collecting training data.ACEcalculator.jl
Evaluate ACE interatomic potentials and interfacesACEdocs_old
Documentaton for ACEsuitWithAlloc.jl
A simple Bumper convenience extensionACEluxpots.jl
ACE potentials via EquivariantModels and LuxRepLieGroups.jl
Representations of Lie Groupsace.cpp
Experimental C++ routines for the ACE basisLove Open Source and this site? Check out how you can help us