Package of scripts for MLIP training, validation, and deployment developed while in Szilvasi Group
Project description
pymlip
This python package is a collection of scripts to use for training machine learning interatomic potentials, or mlips, in python.
This package is currently interfaced to the following codes
- Nequip
- Allegro
Learning Rate Module
In the pymlip/lrlambda.py
file, there are pre-defined learning rate schedules which are compatible with Nequip directly. See the examples
folder to see how to input these learning rates into the nequip.yaml files.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tgm-pymlip-0.0.2.tar.gz
(18.4 kB
view hashes)
Built Distribution
tgm_pymlip-0.0.2-py3-none-any.whl
(16.8 kB
view hashes)
Close
Hashes for tgm_pymlip-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | bccb9bdef572783357f2046f0aa5b6a4aac9b6a2e0e618cec084eb73197bad54 |
|
MD5 | fbb640b918394d79052c2d83c37c6393 |
|
BLAKE2b-256 | eb6d0d4aabcf063b5b5d76967a03983d85fee3491f6d016345b8422b6d6cdf9e |