Update README.md

README.md

@@ -10,35 +10,46 @@ pinned: false
 # Open Materials Generation (OMatG)
 ## About
 
-OMatG is a generative model for crystal structure prediction and de novo generation of inorganic crystals.  
+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 stochastic interpolants. 
+Checkpoints for each 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 - full/valid (%)| RMSE (full/valid) | notes |
+|model         |best checkpoints | match rate (full/valid)(%)| RMSE (full/valid) | notes |
 |:------------:|:---------------:|:--------------------------:|:-----------------:|:------|
-|[Alex-MP-20-CSP](https://huggingface.co/OMatG/Alex-MP-20-CSP)|Trig SDE Gamma   |72.50 / 64.71               |0.1261 / 0.1251    |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 / 63.75               |0.0741 / 0.0720    |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 / 25.15               |0.1970 / 0.1931    |Predict inorganic crystal structures of compositions with **up to 52 atoms** per unit cell. Not recommended for general use.|
-|[perov-5-CSP](https://huggingface.co/OMatG/perov-5-CSP)   |VPSBD ODE        |60.18 / 52.97               |0.2510 / 0.2337    |Predict perovskite structures with **exactly 5 atoms** per unit cell. Not recommended for general use.|
+|[**Alex-MP-20-CSP**](https://huggingface.co/OMatG/Alex-MP-20-CSP)|Trig SDE Gamma   |72.50 / 64.71               |0.1261 / 0.1251    |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 / 63.75               |0.0741 / 0.0720    |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 / 25.15               |0.1970 / 0.1931    |Predict inorganic crystal structures of compositions with **up to 52 atoms** per unit cell. Not recommended for general use.|
+|[**perov-5-CSP**](https://huggingface.co/OMatG/perov-5-CSP)   |VPSBD ODE        |60.18 / 52.97               |0.2510 / 0.2337    |Predict perovskite structures with **exactly 5 atoms** per unit cell. Not recommended for general use.|
 
 
 ### _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 |22.07          |0.6148 |Generate _de novo_ crystal structures with up to 20 atoms per unit cell |
+|[**MP-20-DNG**](https://huggingface.co/OMatG/MP-20-DNG)  |Linear SDE Gamma |22.07          |0.6148 |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.