Update README.md

README.md

@@ -4,12 +4,14 @@ tags:
 - Machine Learning Interatomic Potential
 ---
 
-# Model Card for mace-universal
+# Model Card for mace-universal / mace-mp
 
-[MACE](https://github.com/ACEsuit/mace) (Multiple Atomic Cluster Expansion) is a machine learning interatomic potential (MLIP) with higher order equivariant message passing. For more information about MACE formalism, please see authors' [paper](https://arxiv.org/abs/2206.07697). 
+MACE-MP is a pretrained general-purpose foundational interatomic potential published with the [preprint arXiv:2401.00096](https://arxiv.org/abs/2401.00096).
 
+This repository is the archive of pretrained checkpoints for manual loading using `MACECalculator` or further fine-tuning. Now the easiest way to use models is to follow the **[documentation for foundtional models](https://mace-docs.readthedocs.io/en/latest/examples/foundation_models.html)**.
+All the models are trained with MPTrj data, [Materials Project](https://materialsproject.org) relaxation trajectories compiled by [CHGNet](https://arxiv.org/abs/2302.14231) authors to cover 89 elements and 1.6M configurations. The checkpoint was used for materials stability prediction on [Matbench Discovery](https://matbench-discovery.materialsproject.org/) and the associated [preprint](https://arXiv.org/abs/2308.14920).
 
-[2023-08-14-mace-universal.model](https://huggingface.co/cyrusyc/mace-universal/blob/main/2023-08-14-mace-universal.model) was trained with MPTrj data, [Materials Project](https://materialsproject.org) relaxation trajectories compiled by [CHGNet](https://arxiv.org/abs/2302.14231) authors to cover 89 elements and 1.6M configurations. The checkpoint was used for materials stability prediction on [Matbench Discovery](https://matbench-discovery.materialsproject.org/) and the associated [preprint](https://arXiv.org/abs/2308.14920).
+[MACE](https://github.com/ACEsuit/mace) (Multiple Atomic Cluster Expansion) is a machine learning interatomic potential (MLIP) with higher order equivariant message passing. For more information about MACE formalism, please see authors' [paper](https://arxiv.org/abs/2206.07697). 
 
 # Usage
 
@@ -54,6 +56,13 @@ dyn.run(steps)
 If you use the pretrained models in this repository, please cite all the following:
 
 ```
+@article{batatia2023foundation,
+  title={A foundation model for atomistic materials chemistry},
+  author={Batatia, Ilyes and Benner, Philipp and Chiang, Yuan and Elena, Alin M and Kov{\'a}cs, D{\'a}vid P and Riebesell, Janosh and Advincula, Xavier R and Asta, Mark and Baldwin, William J and Bernstein, Noam and others},
+  journal={arXiv preprint arXiv:2401.00096},
+  year={2023}
+}
+
 @inproceedings{Batatia2022mace,
   title={{MACE}: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields},
   author={Ilyes Batatia and David Peter Kovacs and Gregor N. C. Simm and Christoph Ortner and Gabor Csanyi},