Pre-trained and fine-tuned ANI models for: Transfer learning for chemically accurate interatomic neural network potentials

Pre-trained and fine-tuned ANI models using the Gaussian Moments Neural Network (GM-NN) approach. Code for GM-NN implemented within the Tensorflow framework, including the respective documentation and tutorials, can be found on GitLab.

The data represents TensorFlow v2 checkpoints and stores the metadata for the checkpoint and parameters for the model. Checkpoints can be read by the source code provided on GitLab. A detailed description for reproducing the results and employing pre-trained and fine-tuned models during a simulation is provided in the GM-NN Documentation.