Skip to content
This repository has been archived by the owner on Apr 27, 2023. It is now read-only.

Latest commit

 

History

History
18 lines (13 loc) · 770 Bytes

README.md

File metadata and controls

18 lines (13 loc) · 770 Bytes

Pre-trained models from Materials Virtual Lab

This directory contains pre-trained models from the Materials Virtual Lab.

Currently, we provide models for

  • QM9 molecules
  • Materials Project (MP) crystals
  • Multi-fidelity band gap data

The original models in "Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals". are in the folders dated 2018.6.1. We are continuing to develop new models on updated datasets, and these are dated accordingly (e.g., mp-2019.4.1 contains models developed on the much larger Materials Project dataset of 133,420 crystals as of Apr 1 2019).

The README.md in each folder provides a summary of the dataset, training/test split and the model performance.