Differences

This shows you the differences between two versions of the page.

--- howto:allegro [2023/04/24 13:54] – gtocci
+++ howto:allegro [2024/01/03 13:15] (current) – oschuett
@@ Line 1: / Line 1: @@
-====== How to Train a neural network interatomic potential using Allegro and Perform Molecular Dynamics with CP2K ======
+This page has been moved to: https://manual.cp2k.org/trunk/methods/machine_learning/nequip.html
-This [[https://github.com/gabriele16/cp2k/blob/nequip-cp2k-colab/colab/allegro-cp2k-tutorial.ipynb|Colab tutorial]] illustrates how to train an equivariant neural network interatomic potential for bulk water using the Allegro framework. You will learn how to train a model, deploy it in production, and run molecular dynamics simulations in ''CP2K''. The training and inference will be carried out on the GPU provided by the Colab environment.
-Allegro is designed for constructing highly accurate and scalable interatomic potentials for molecular dynamics simulations. The methodology is described in detail in this paper ([[doi>10.1038/s41467-023-36329-y]]). An open-source package (https://github.com/mir-group/allegro) that implements Allegro, built on the nequip framework was developed by the Allegro and NequIP (https://github.com/mir-group/nequip) authors.
-Inference in CP2K is performed through the ''MM'' package of CP2K, Fist. As an example, the relevant section for Allegro (or similarly for NequIP) is:
-<code - Allegro_si_MD.inp >
-      &ALLEGRO
-        ATOMS Si
-        PARM_FILE_NAME Allegro/si-deployed.pth
-        UNIT_COORDS angstrom
-        UNIT_ENERGY eV
-        UNIT_FORCES eV*angstrom^-1
-      &END ALLEGRO
- </code>
-where the ''si-deployed.pth'' refers to the PyTorch model that was deployed using the Allegro framework, and the ''UNIT'' tags refer to the units of the coordinates, energy and forces of the model itself. An example for the full input file can be found in the [[https://github.com/gabriele16/cp2k/blob/nequip-cp2k-colab/colab/allegro-cp2k-tutorial.ipynb|Colab tutorial]] and on the regtests, see [[src>tests/Fist/regtest-allegro/Allegro_si_MD.inp]]
-For additional references on NequIP, Allegro and equivariant neural networks (e3nn) see:
-  - Allegro paper [[doi>10.1038/s41467-023-36329-y]] and code [[https://github.com/mir-group/allegro|https://github.com/mir-group/allegro]]
-  - NequIP paper [[doi>10.1038/s41467-022-29939-5]] and code [[https://github.com/mir-group/nequip|https://github.com/mir-group/nequip]]
-  - NequIP/Allegro Tutorial on LAMMPS by the authors of the above papers, see Colab notebook [[https://colab.research.google.com/drive/1yq2UwnET4loJYg_Fptt9kpklVaZvoHnq|here]]
-  - For an introduction to e3nn see [[https://blondegeek.github.io/e3nn_tutorial|here]], [[doi>10.5281/zenodo.7430260]]