NEP
Model Introduction
NEP (Neural Evolution Potential) is a MatPL-based neural-network potential training example that learns material interaction information, including energies, forces, and virials, from atomic-structure data.
Model Description
NEP is built on the MatPL framework and trained with data from atomic systems such as Cu and LiSiC. It supports interatomic-potential training and molecular dynamics simulations for materials systems.
Use Cases
| Use case | Description |
|---|---|
| NEP training for Cu systems | Train a Cu potential with demo/nep_Cu/Cu_nep_train.json |
| NEP training for LiSiC systems | Train a LiSiC potential with demo/nep_LiSiC/LiSiC_nep_train.json |
| SLURM job submission | See demo/nep_Cu/submit.sh for cluster training |
| Custom data migration | Convert your data to a MatPL-supported format such as pwmat/movement, then replace the training path |
Usage
1. Using OneCode
Try intelligent, one-click AI4S programming in the OneCode online environment:
Try intelligent, one-click AI4S programming
2. Manual Installation and Usage
Hardware requirements
- A DCU or GPU is recommended for training.
- A CPU can be used for import checks and small-configuration connectivity tests, but full training will be slow.
- DCU users must install DTK in advance. DTK 25.04.2 or later, or the OneScience-recommended version matching the current cluster, is recommended.
Download the Model Package
hf download --model OneScience-Sugon/NEP --local-dir ./nep
cd nep
Install the Runtime Environment
DCU environment
# Activate DTK and conda first
conda create -n onescience311 python=3.11 -y
conda activate onescience311
# uv installation is also supported
pip install onescience[matchem-dcu] -i http://mirrors.onescience.ai:3141/pypi/simple/ --trusted-host mirrors.onescience.ai
GPU environment
# Activate conda first
conda create -n onescience311 python=3.11 -y libstdcxx-ng=12 libgcc-ng=12 gcc_linux-64=12 gxx_linux-64=12
conda activate onescience311
# uv installation is also supported
pip install onescience[matchem-gpu] -i http://mirrors.onescience.ai:3141/pypi/simple/ --trusted-host mirrors.onescience.ai
Install MatPL
# The test_pip environment is used by default. To use another conda environment:
# export MATCHEM_CONDA_NAME=your_env
bash matpl_install.sh
Training Data
Training data is not bundled with this repository. Using the MatPL dataset as an example, download it from Hugging Face to data/ in the repository root:
hf download --dataset OneScience-Sugon/MatPL --local-dir ./data
After downloading, the data is located at data/MatPL/.
Training
Single GPU:
cd demo/nep_Cu
MatPL train Cu_nep_train.json
SLURM:
cd demo/nep_Cu
bash submit.sh
Trained Weights
This repository does not currently include trained weights. You can obtain them by following the training procedure above.
Official OneScience Resources
| Platform | OneScience Main Repository | Skills Repository |
|---|---|---|
| Gitee | https://gitee.com/onescience-ai/onescience | https://gitee.com/onescience-ai/oneskills |
| GitHub | https://github.com/onescience-ai/OneScience | https://github.com/onescience-ai/oneskills |
Citation and License
- The NEP example code comes from the OneScience repository. This repository retains source attribution and has been organized for automated execution in the OneScience Hugging Face environment.
- If you use NEP or MatPL training results in research, please cite the relevant OneScience projects, MatPL/NEP methods, and the datasets used.