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
Copy file name to clipboardExpand all lines: docs/user/codes/forcefields.md
+7Lines changed: 7 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,6 +4,13 @@
4
4
5
5
`atomate2` includes an interface to a few common machine learning interatomic potentials (MLIPs), also known variously as machine learning forcefields (MLFFs), or foundation potentials (FPs) for universal variants.
6
6
7
+
***As of `atomate2==0.1.1`, most forcefield packages are opt-in only. You must install those forcefields which you plan to use.***
8
+
Running `pip install 'atomate2[forcefields]'` will install the `chgnet` package to permit you to try the forcefield classes.
9
+
You can then select other forcefields you want to use.
10
+
11
+
We have made this choice both to avoid the appearance of favoritism (both `chgnet` and `atomate2` are Materials Project-supported projects), and to avoid dependency conflicts between MLFF packages.
12
+
If you need a sense of which forcefields are compatible, you can use the [pyproject.toml](https://github.com/materialsproject/atomate2/blob/a8bc6505e439503a114f5346aec916aafae7f27b/pyproject.toml#L90) to see which versions are grouped together for testing.
13
+
7
14
Most of `Maker` classes using the forcefields inherit from `atomate2.forcefields.utils.ForceFieldMixin` to specify which forcefield to use.
8
15
The `ForceFieldMixin` mixin provides the following configurable parameters:
0 commit comments