v0.1.3

This version includes the following changes:

• Adding two new options to the MACE implementation, a more complex species embedding
  and a gating mechanism for node features. Making use of these options may improve
  inference speed at similar accuracy.
• Fixing a bug that caused overriding energy and forces predictions to be None when
  stress is computed by a model.

v0.1.2

This version includes the following changes:

• Fixing the computation of metrics during training, by reweighting the metrics of
  each batch to account for a varying number of real graphs per batch; this results
  in the metrics being independent of the batching strategy and number of GPUs employed
• In addition to the point above, fixing the computation of RMSE metrics by now
  only computing MSE metrics in the loss and taking the square root at the very end
  when logging
• Deleting relative and 95-percentile metrics, as they are not straightforward to
  compute on-the-fly with our dynamic batching strategy; we recommend to compute them
  separately for a model checkpoint if necessary
• Small amount of modifications to README and documentation

v0.1.1

Small patch to the initial release with the following changes:

• Small amount of modifications to README and documentation
• Adding link to white paper in README

v0.1.0

Initial release with the following features:

• Implemented model architectures: MACE, NequIP and ViSNet
• Dataset preprocessing
• Training of MLIP models
• Batched inference with trained MLIP models
• MD simulations with MLIP models using JAX-MD and ASE simulation backends
• Energy minimizations with MLIP models using the same simulation backends
• Fine-tuning of pre-trained MLIP models (only for MACE)