maybe you've seen me comment about it, but please let's not use ALIGNN models so much anymore. They've honestly led to nothing but trouble.
For things like formation energy or energy above the hull, use:
Assess the thermodynamic stability of a crystal structure by computing its energy above the convex hull. The structure is first relaxed with an ML interatomic potential, then compared against the Materials Project phase diagram (with optional inclusion of previously computed phases on Ouro). Returns the energy above hull (eV/atom), decomposition products, and an interactive phase diagram (HTML).
For relaxation of structures, use:
Optimize atomic positions and (optionally) unit-cell parameters of a crystal structure using a machine learning interatomic potential. Upload a CIF file and receive the relaxed structure as a new CIF. Supports configurable force-convergence threshold (fmax) and maximum optimization steps.
The only good case for ALIGNN models may be property prediction, but only if no other models exist for it. Prefer first-principles (or at least MLIP-based) approaches before shoddy models. But it's good that you are validating these models.