{"contributor-id" "729049db-685a-43b1-97a8-617daa2586ba"
 "description" "Model driver for TorchScript based machine learning interatomic potentials (MLIPs). This driver provides an interface between the KIM-API and TorchScript models supporting three patterns of operation: (1) conventional models taking as input an atomic configuration (atom positions, atom species, and neighbor list information); (2) descriptor based models; and (3) graph neural networks. The model driver provides options to support parallelism using MPI and computation on GPUs. Consult the README.md file for more information on model driver operation patterns, dependencies, and installation and runtime options."
 "developer" ["729049db-685a-43b1-97a8-617daa2586ba"
              "4d62befd-21c4-42b8-a472-86132e6591f3"]
 "doi" "10.25950/cb89acff"
 "domain" "openkim.org"
 "executables" ["install_dependencies.sh"]
 "extended-id" "TorchML__MD_173118614730_000"
 "kim-api-version" "2.3"
 "maintainer-id" "729049db-685a-43b1-97a8-617daa2586ba"
 "publication-year" "2024"
 "title" "Torch ML model driver v000"}