Published January 15, 2025
| Version v1
Model
Open
Pretrained models for CrystalGRW
Authors/Creators
-
1.
University of South Carolina
-
2.
Chulalongkorn University
Description
Pretrained models for CrystalGRW. Intructions for model usage can be found at https://github.com/trachote/crystalgrw.
- The file pretrained_mp20_2024-09-24.zip is a model trained on MP-20 dataset.
- The file pretrained_mp20_cond_2024-12-01.zip is a model trained on MP-20 dataset, conditioned on point groups. This model enables control over point groups of generated structures.
Files
pretrained_mp20_2024-09-24.zip
Files
(1.5 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:e577afe4c95f64639ef25ec4c09e0d9c
|
766.6 MB | Preview Download |
|
md5:25cc09f7189c480905ae7735c8a66506
|
772.5 MB | Preview Download |
Additional details
Identifiers
- arXiv
- arXiv:2501.08998
Related works
- Cites
- arXiv:2501.08998 (arXiv)
Dates
- Available
-
2025-01-15
Software
- Repository URL
- https://github.com/trachote/crystalgrw
- Programming language
- Python
References
- Krit Tangsongcharoen, Teerachote Pakornchote, Chayanon Atthapak, Natthaphon Choomphon-anomakhun, Annop Ektarawong, Björn Alling, Christopher Sutton, Thiti Bovornratanaraks, and Thiparat Chotibut, CrystalGRW: Generative Modeling of Crystal Structures with Targeted Properties via Geodesic Random Walks (2025), arXiv:2501.08998 [cond-mat.mtrl-sci]