basf / mlipx
Machine-Learned Interatomic Potential eXploration (mlipx) is designed at BASF for evaluating machine-learned interatomic potentials (MLIPs). It offers a growing set of evaluation methods alongside powerful visualization and comparison tools.
☆77Updated this week
Alternatives and similar repositories for mlipx:
Users that are interested in mlipx are comparing it to the libraries listed below
- Fair and transparent benchmark of machine-learned interatomic potentials (MLIPs), beyond basic error metrics☆56Updated this week
- ⚛ download and manipulate atomistic datasets☆44Updated 4 months ago
- Particle-mesh based calculations of long-range interactions in PyTorch☆44Updated this week
- MACE-OFF23 models☆31Updated 2 months ago
- ☆25Updated last year
- Compute neighbor lists for atomistic systems☆52Updated this week
- train and use graph-based ML models of potential energy surfaces☆83Updated this week
- MLP training for molecular systems☆46Updated last week
- GRACE models and gracemaker (as implemented in TensorPotential package)☆56Updated 2 weeks ago
- Efficient And Fully Differentiable Extended Tight-Binding☆86Updated this week
- An ecosystem for digital reticular chemistry☆47Updated 7 months ago
- Quick Uncertainty and Entropy via STructural Similarity☆36Updated last week
- Algorithms to analyze and predict molecular structures☆17Updated 7 months ago
- python workflow toolkit☆37Updated last month
- Display and Edit Molecules (https://zndraw.icp.uni-stuttgart.de)☆40Updated this week
- Active Learning for Machine Learning Potentials☆54Updated 11 months ago
- ☆71Updated last week
- open data sets for machine learning pertaining to porous materials☆27Updated last year
- A foundational potential energy dataset for materials☆30Updated 2 weeks ago
- ☆54Updated 2 weeks ago
- Code for automated fitting of machine learned interatomic potentials.☆76Updated this week
- Collection of tutorials to use the MACE machine learning force field.☆44Updated 7 months ago
- A framework for performing active learning for training machine-learned interatomic potentials.☆32Updated last week
- Automated workflow for generating quantum chemistry calculation of explicitly solvated molecules☆52Updated last month
- Benchmarking foundation Machine Learning Potentials with Lattice Thermal Conductivity from Anharmonic Phonons☆16Updated 5 months ago
- Collection of Tutorials on Machine Learning Interatomic Potentials☆18Updated 8 months ago
- Python package to interact with high-dimensional representations of the chemical elements☆41Updated last week
- DeePMD-kit plugin for various graph neural network models☆41Updated this week
- Computing representations for atomistic machine learning☆70Updated last month
- A text-guided diffusion model for crystal structure generation☆37Updated 2 months ago