Issue with multiple species system about pair_allegro

[Linux-cpp-lisp]

Your atom type definitions look like they may be wrong: you seem to want, for example, LAMMPS atom type 4 to be Hydrogen, but are assigning it NequIP/Allegro type N (the fourth NequIP type you list).

From the README:

The names after the model path deployed.pth indicate, in order, the names of the Allegro model's atom types to use for LAMMPS atom types 1, 2, and so on. The number of names given must be equal to the number of atom types in the LAMMPS configuration (not the Allegro model!). The given names must be consistent with the names specified in the Allegro training YAML in chemical_symbol_to_type or type_names.

I guess we could explain this more explicitly.

Given your masses/LAMMPS group labels, I think the correct line would be:

pair_coeff   * * deployed.pth B C F H N

(If you find it more helpful to see the correspondance in code, consider these two lines from the unit tests:

"""
# note that ASE outputs lammps types in alphabetical order of chemical symbols
# since we use chem symbols in this test, just put the same
pair_coeff	* * {deployed_model} {' '.join(sorted(set(config["chemical_symbols"])))}
{newline.join('        mass  %i 1.0' % i for i in range(1, num_types + 1))}
"""

)

[Linux-cpp-lisp]

I've also clarified this in the README.

[PythonFZ]

Thanks a lot! With the new atom types everything worked as expected.