Skip to main content

ASE interface to use metatomic atomistic machine learning models

Project description

metatomic-ase

ASE integration for metatomic models.

This package allows you to use metatomic models as ASE Calculator, integrating with any workflow based on ASE.

Installation

pip install metatomic-ase

Usage

import ase.io
from metatomic_ase import MetatomicCalculator

# load atoms
atoms = ase.io.read("...")

# create a calculator from a saved .pt model
atoms.calc = MetatomicCalculator("model.pt", device="cuda")

# from here, all the normal ASE functionality is available
print(atoms.get_forces())
print(atoms.get_potential_energies())

For full documentation, see the ASE engine page in metatomic documentation.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

metatomic_ase-0.1.0.tar.gz (21.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

metatomic_ase-0.1.0-py3-none-any.whl (19.6 kB view details)

Uploaded Python 3

File details

Details for the file metatomic_ase-0.1.0.tar.gz.

File metadata

  • Download URL: metatomic_ase-0.1.0.tar.gz
  • Upload date:
  • Size: 21.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for metatomic_ase-0.1.0.tar.gz
Algorithm Hash digest
SHA256 fa0d5392c469ce10cd4ccdc67f481fd6b044a4c64183df4d0e4a11953726e923
MD5 71c0b3da5478658a3adc87fdb7ac6c77
BLAKE2b-256 1ed4539ca0d9f00a796df7b5b24ba26637f40ff9c3f5dc0a9b167035891e5832

See more details on using hashes here.

File details

Details for the file metatomic_ase-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: metatomic_ase-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 19.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for metatomic_ase-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 39ae69f91d06ee36b9cfaf8949f3fe9c97a0b55353a08b489c6a0935c75dfc1e
MD5 55bfc9aaa6c48fff266956faefa68a4d
BLAKE2b-256 21205f0fbe0a9fd67fce0b162e5f80051c332fada208c675e445e6827be84fb6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page