# Monolayer Quasi-Hexagonal-Phase Fullerene (qHPF) Network: NEP Machine-Learning Potential Training Set (Ying 2022, Zenodo), ColabFit Conversion

## Facts

- Provider: Penghua Ying; ColabFit conversion
- License: CC-BY-4.0 (https://zenodo.org/records/7018573)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/NEP_qHPF_train
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.7018572
- Category: Chemistry & Materials
- Source: https://doi.org/10.1016/j.eml.2022.101929
- Page: https://scigantic.com/archive/924fcf85-8143-5474-994d-b4268dbedd43
- Keywords: Chemistry & Materials, molecular dynamics, DFT, Parquet, Hugging Face

## About

Reference DFT configurations used to train a neuroevolution potential (NEP) in GPUMD for monolayer quasi-hexagonal-phase fullerene (qHPF), the two-dimensional polymerized C60 network. The potential was used for machine-learning molecular dynamics of the mechanical anisotropy and fragility of monolayer fullerene networks. The full set has about 275 configurations split into training and test files; this row is the training split (the Zenodo deposit also holds the nep.in parameter files for GPUMD 3.3.1). ColabFit's card counts 237 configurations and 28,440 atoms (C), labelled with energy, atomic forces, cauchy stress; the repository is about 2.7 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 10.5281/zenodo.7018572) is released under CC-BY-4.0; cite Ying et al., Extreme Mechanics Letters (2022), doi:10.1016/j.eml.2022.101929.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/NEP_qHPF_train")
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/924fcf85-8143-5474-994d-b4268dbedd43
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/924fcf85-8143-5474-994d-b4268dbedd43
- Over MCP: `get_schema_card` with id `924fcf85-8143-5474-994d-b4268dbedd43` 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)
- [Molecular dynamics datasets](https://scigantic.com/topics/molecular-dynamics)
