|
|
--- |
|
|
title: README |
|
|
emoji: 📚 |
|
|
colorFrom: blue |
|
|
colorTo: green |
|
|
sdk: static |
|
|
pinned: false |
|
|
--- |
|
|
|
|
|
# Open Materials Generation (OMatG) |
|
|
## About |
|
|
|
|
|
OMatG is a generative model for crystal structure prediction and _de novo_ generation of inorganic crystals. |
|
|
This repository hosts our model checkpoints and benchmark datasets. |
|
|
|
|
|
## Models |
|
|
|
|
|
Each of our models have been trained with a variety of hyperparameters as, e.g., various positional stochastic interpolants for the fractional coordinates in the unit-cell representation. |
|
|
Checkpoints for different positional stochastic interpolants are included in subdirectories within each model repository. |
|
|
|
|
|
The tables below indicate the recommended checkpoints for each model, as well as the suggested use case. |
|
|
|
|
|
[**Try our models live at OMatGenerate.**](https://omatgenerate.users.hsrn.nyu.edu/) |
|
|
|
|
|
|
|
|
### Crystal Structure Prediction (CSP) |
|
|
|model |best checkpoints | match rate (%)| RMSE | notes | |
|
|
|:------------:|:---------------:|:--------------------------:|:-----------------:|:------| |
|
|
|[**Alex-MP-20-CSP**](https://huggingface.co/OMatG/Alex-MP-20-CSP)|Trig SDE Gamma |72.50 |0.1261 |Predict inorganic crystal structures of compositions with **up to 20 atoms** per unit cell. **Largest training set; recommended over MP-20-CSP**. |
|
|
|[**MP-20-CSP**](https://huggingface.co/OMatG/MP-20-CSP) |Linear ODE |69.83 |0.0741 |Predict inorganic crystal structures of compositions with **up to 20 atoms** per unit cell.|20-CSP. |
|
|
|[**MPTS-52-CSP**](https://huggingface.co/OMatG/MPTS-52-CSP) |Linear ODE |27.38 |0.1970 |Predict inorganic crystal structures of compositions with **up to 52 atoms** per unit cell. Should only be used if strictly necessary; use Alex-MP-20-CSP models if possible.| |
|
|
|[**perov-5-CSP**](https://huggingface.co/OMatG/perov-5-CSP) |VPSBD ODE |83.06 |0.3753 |Predict perovskite structures with **exactly 5 atoms** per unit cell. Should only be used if strictly necessary.| |
|
|
|
|
|
|
|
|
### _De Novo_ Generation (DNG) |
|
|
|model |best checkpoints | S.U.N rate (%)| RMSD | notes | |
|
|
|:---------:|:---------------:|:-------------:|:-----:|:----------------------------------------------------------------------:| |
|
|
|[**MP-20-DNG**](https://huggingface.co/OMatG/MP-20-DNG) |Linear SDE Gamma |22.48 |0.6357|Generate _de novo_ crystal structures with up to 20 atoms per unit cell. | |
|
|
|
|
|
|
|
|
## Citation |
|
|
Please cite [our paper on OpenReview](https://openreview.net/forum?id=gHGrzxFujU) if using our models or datasets. |
|
|
|
|
|
|
|
|
## Links |
|
|
[OMatG on GitHub](https://github.com/FERMat-ML/OMatG): See this repository for installation, training and usage instructions. |
|
|
[KIM Initiative](https://kim-initiative.org/): Knowledgebase of Interatomic Models. Tools and resources for researchers in materials science and chemistry. |
|
|
[Fermat-ML on GitHub](https://github.com/FERMat-ML): Foundational Representation of Materials. Machine learning foundation model for materials and chemistry discovery. |
|
|
[OMatGenerate](omatgenerate.users.hsrn.nyu.edu): Try our models **live** at OMatGenerate, hosted on New York University's High Speed Research Network. |
|
|
|
|
|
|
|
|
|
