Section NEQUIP

• This section specifies the input parameters for NEQUIP potential type. neural network potentials to achieve correlated-wavefunction-like accuracy. Requires linking with libtorch library from https://pytorch.org/cppdocs/installing.html .  [Edit on GitHub]

• Section path: CP2K_INPUT / FORCE_EVAL / MM / FORCEFIELD / NONBONDED / NEQUIP

• This section cannot be repeated.

• This section cites the following reference: [Batzner2022]

• Subsections

  • none

• Keywords

  • ATOMS
  • PARM_FILE_NAME
  • UNIT_CELL
  • UNIT_COORDS
  • UNIT_ENERGY
  • UNIT_FORCES

• Keyword descriptions

  ATOMS
  	ATOMS {Word} ...
  	Defines the atomic kinds involved in the NEQUIP potential. Provide a list of each element.  [Edit on GitHub]
  	This keyword cannot be repeated and it expects a list of words.

  PARM_FILE_NAME
  	PARM_FILE_NAME {String}
  	Specifies the filename that contains the NEQUIP model.  [Edit on GitHub]
  	This keyword cannot be repeated and it expects precisely one string.
  	Default value: model.pth
  	Alias names for this keyword: PARMFILE

  UNIT_CELL
  	UNIT_CELL {Word}
  	Units of the cell vectors in the NEQUIP model.pth file.  [Edit on GitHub]
  	This keyword cannot be repeated and it expects precisely one word.
  	Default value: angstrom

  UNIT_COORDS
  	UNIT_COORDS {Word}
  	Units of coordinates in the NEQUIP model.pth file.  [Edit on GitHub]
  	This keyword cannot be repeated and it expects precisely one word.
  	Default value: angstrom

  UNIT_ENERGY
  	UNIT_ENERGY {Word}
  	Units of energy in the NEQUIP model.pth file.  [Edit on GitHub]
  	This keyword cannot be repeated and it expects precisely one word.
  	Default value: hartree

  UNIT_FORCES
  	UNIT_FORCES {Word}
  	Units of the forces in the NEQUIP model.pth file.  [Edit on GitHub]
  	This keyword cannot be repeated and it expects precisely one word.
  	Default value: hartree/bohr