OrbNetMethod
The OrbNetMethod object specifies the settings for using OrbNet [1] [2] as the method for a calculation. OrbNet is a family of machine learning methods, suitable for the calculation of energies, structures, and non-covalent interactions in large molecular systems. OrbNet provides the accuracy of dispersion-corrected range-separated hybrid DFT with a roughly 1000-fold reduction in computational cost. OrbNet is parameterized for neutral, closed-shell species containing C, H, B, O, N, F, P, S, Cl, Si, Br, I. Chemical coverage of OrbNet will increase in future releases.
Fields
engine-
The Entos Engine in which to evaluate the method with.
- Type: Optional[EngineIdentifier]
kind-
- Type: Literal['orbnet', 'OrbNetMethod']
- Default: 'orbnet'
model-
Specify the OrbNet model major version
- Type: OrbNetMajorVersionEnum
- Default: OrbNetMajorVersionEnum.sky
solvation-
Include effects of solvation through a continuum model.
- Type: Optional[Solvation]
version-
Specify the OrbNet model minor version
- Type: str
- Default: 'latest'
details-
Debug options relating to OrbNet
Detail Fields
checkpoint_file-
Specify custom OrbNet parameters
- Type: Optional[Path]
inference_error_level-
When the user provides inference input that is out-of-training-set for an OrbNet model, what should be done? 'debug': log at the debug level, 'warning': log at the warning level, 'error': log at the error level and raise an exception.
- Type: ConstrainedStrValue
- Default: 'error'