# Mo-Nb-Ta-V-W Refractory High-Entropy Alloy tabGAP Training Data: DFT (Byggmästar et al. 2021, Fairdata), ColabFit Conversion

## Facts

- Provider: Jesper Byggmästar, Kai Nordlund and Flyura Djurabekova; ColabFit conversion
- License: CC-BY-4.0 (https://metax.fairdata.fi/rest/v2/datasets/85872bc9-bd4f-47db-9c73-2e9800515551)
- Size: 6 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/MoNbTaVW_PRB2021
- Access: public, readable without an account
- DOI: https://doi.org/10.23729/1b845398-5291-4447-b417-1345acdd2eae
- Category: Chemistry & Materials
- Source: https://doi.org/10.1103/PhysRevB.104.104101
- Page: https://scigantic.com/archive/66fa3e44-0f03-5975-8519-52a7d16f7d4d
- Keywords: Chemistry & Materials, DFT, interatomic potentials, Parquet, Hugging Face

## About

DFT training data for a tabulated Gaussian approximation potential (tabGAP, 2+3-body) for the quinary Mo-Nb-Ta-V-W system, used to study segregation and defects in the body-centered cubic refractory high-entropy alloy MoNbTaVW. The original deposit, "Machine-learned interatomic potential for Mo-Nb-Ta-V-W (2+3-body tabGAP)", is on the Finnish Fairdata service. ColabFit's card counts 2,329 configurations and 127,913 atoms (Mo, Nb, Ta, V, W), labelled with energy, atomic forces, cauchy stress; the repository is about 14.2 MB. Files are the ColabFit Exchange conversion: Parquet files under co/ hold one row per configuration (atomic numbers, positions, cell, computed properties and metadata), ds.parquet holds dataset-level information, and cs/ groups configurations into named sets where defined; read them with pyarrow, pandas, polars or Hugging Face datasets. The original deposit (DOI 10.23729/1b845398-5291-4447-b417-1345acdd2eae) is released under CC-BY-4.0; cite Byggmästar, Nordlund and Djurabekova, Physical Review B 104, 104101 (2021).

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/MoNbTaVW_PRB2021")
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/66fa3e44-0f03-5975-8519-52a7d16f7d4d
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/66fa3e44-0f03-5975-8519-52a7d16f7d4d
- Over MCP: `get_schema_card` with id `66fa3e44-0f03-5975-8519-52a7d16f7d4d` 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)
