This package implements the "pair_style hdnnp" command which can be used in a LAMMPS input script. This pair style allows to use pre-trained high-dimensional neural network potentials[1] via an interface to the n2p2 library (https://github.com/CompPhysVienna/n2p2)[2]. Please see the main documentation for the "pair_style hdnnp" command for further details on how the pair style is used. An example is provided in the "examples/PACKAGES/hdnnp" directory of LAMMPS. The ML-HDNNP package requires the external library n2p2 which must be downloaded and compiled before starting the build process of LAMMPS. A guideline on how to build n2p2 is presented in "lib/hdnnp/README". This package supports the LAMMPS build process via CMake and traditional makefiles, please see the LAMMPS manual section on building with external libraries for more details. This package was created by Andreas Singraber, please ask questions/report bugs on the n2p2 Github issues page (https://github.com/CompPhysVienna/n2p2/issues). [1] Behler, J.; Parrinello, M. Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces. Phys. Rev. Lett. 2007, 98 (14), 146401. https://doi.org/10.1103/PhysRevLett.98.146401 [2] Singraber, A.; Behler, J.; Dellago, C. Library-Based LAMMPS Implementation of High-Dimensional Neural Network Potentials. J. Chem. Theory Comput. 2019, 15 (3), 1827-1840. https://doi.org/10.1021/acs.jctc.8b00770