# JARVIS ALIGNN-FF Training Set: OptB88vdW Energies, Forces and Stresses for 89 Elements, ColabFit Conversion

## Facts

- Provider: Kamal Choudhary, Brian DeCost and coauthors (NIST JARVIS); ColabFit conversion
- License: CC-BY-4.0 (https://api.figshare.com/v2/articles/21667874)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/JARVIS_ALIGNN_FF
- Access: public, readable without an account
- Category: Chemistry & Materials
- Source: https://doi.org/10.1039/D2DD00096B
- Page: https://scigantic.com/archive/31ed6ce0-763f-5228-8231-c3ea1497461a
- Keywords: Chemistry & Materials, DFT, interatomic potentials, graph learning, Parquet, Hugging Face

## About

The training data behind ALIGNN-FF, NIST's atomistic line graph neural network force field for the whole periodic table. It is drawn from JARVIS-DFT relaxation runs (VASP, OptB88vdW functional), keeping the first, last, middle, highest-energy and lowest-energy snapshots of each calculation and filtering for unique, defect-free structures. ColabFit counts 304,146 configurations (about 3.2 million atoms) over 89 elements, labelled with energies, atomic forces and stress. It is a compact universal-potential training set for comparison with MPtrj, MatPES or OMat24. This is the ColabFit Exchange conversion: configurations sit in Parquet files under co/ (positions, cell, species, computed properties and metadata per row) with dataset-level information in ds.parquet; read them with pyarrow, pandas, polars or Hugging Face datasets following the ColabFit schema at materials.colabfit.org/docs. The ALIGNN-FF data file is published by the authors on figshare under CC-BY-4.0; cite Choudhary et al., Digital Discovery 2, 346 (2023).

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/JARVIS_ALIGNN_FF")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `co/co_0.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/31ed6ce0-763f-5228-8231-c3ea1497461a
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/31ed6ce0-763f-5228-8231-c3ea1497461a
- Over MCP: `get_schema_card` with id `31ed6ce0-763f-5228-8231-c3ea1497461a` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Chemistry & Materials datasets](https://scigantic.com/topics/chemistry-and-materials)
- [DFT datasets](https://scigantic.com/topics/dft)
- [Interatomic potentials datasets](https://scigantic.com/topics/interatomic-potentials)
- [Graph learning datasets](https://scigantic.com/topics/graph-learning)
