ALIGNN_BERT_TL models
This repository contains saved models for Hybrid-LLM-GNN transfer learning framework to predict materials properties using concatenated embeddings extracted from ALIGNN and BERT models. The models are trained on 3 machines with or without GPU acceleration, creating 6 variations in hardware conditions.
Publication Details
- Journal
- Figshare
- Published
- 2025-01-01
- DOI
- https://doi.org/10.6084/m9.figshare.29367467
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00