You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the OMol25 dataset, the total charge and spin are provided, and I see the Mulliken etc ionic charge populations have also now been added which is nice. But there is no definite or clear assignment of ionic charge still. I have searched but I couldn't find any more details on this. Were these ionic isolated energies successfully used for training in any other cases, and if so how?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hi!
Thank you to the team for providing and curating such useful datasets and tools for the community.
I am currently training some
NequIPmodels which we hope to submit to the OMol25 leaderboard soon.I was curious about the isolated atom energies provided in https://github.com/facebookresearch/fairchem/blob/main/configs/uma/training_release/element_refs/iso_atom_elem_refs.yaml
I see that for some elements, the isolated energies for the ionic species (e.g. Li+) are given IIUC. Are these intended to be used in training somehow?
In the OMol25 dataset, the total charge and spin are provided, and I see the Mulliken etc ionic charge populations have also now been added which is nice. But there is no definite or clear assignment of ionic charge still. I have searched but I couldn't find any more details on this. Were these ionic isolated energies successfully used for training in any other cases, and if so how?
Thank you for your time and input!
Beta Was this translation helpful? Give feedback.
All reactions