# Open Molecules 2025 (OMol25) Neutral Training Set, ColabFit Conversion

## Facts

- Provider: Meta FAIR Chemistry, Lawrence Berkeley National Laboratory and collaborators (Levine et al.); ColabFit conversion
- License: CC-BY-4.0 (https://raw.githubusercontent.com/facebookresearch/fairchem/main/docs/molecules/datasets/omol25.md)
- Size: 347 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/OMol25_train_neutral
- Access: public, readable without an account
- DOI: https://doi.org/10.60732/3c2ddc75
- Category: Chemistry & Materials
- Source: https://doi.org/10.48550/arXiv.2505.08762
- Page: https://scigantic.com/archive/63a2ec76-6295-535b-a376-580c18c8c088
- Keywords: Chemistry & Materials, DFT, Parquet, Hugging Face

## About

The neutral training split of Open Molecules 2025 (OMol25), the molecular DFT dataset from Meta FAIR Chemistry and Lawrence Berkeley National Laboratory computed at wB97M-V/def2-TZVPD in ORCA. It keeps only the charge-neutral systems, over main-group elements, which makes it the natural training set for potentials that take no charge or spin input, such as MACE-OFF style models, and for comparisons against SPICE or ANI data. ColabFit counts 34,335,828 configurations and about 930 million atoms over 17 elements (H, B, C, N, O, F, Si, P, S, Cl, Br, I, Li, Na, K, Mg, Ca), each with total energy and atomic forces. This is the ColabFit Exchange conversion: 340-odd Parquet files under co/ hold one configuration per row (positions, species, computed properties and metadata) and ds.parquet holds dataset-level information; read them with pyarrow, polars or Hugging Face datasets following the ColabFit schema at materials.colabfit.org/docs. For the original ASE-LMDB shards that fairchem reads, use Meta's neutral_train archive instead. Meta licenses OMol25 under CC-BY-4.0; cite Levine et al., arXiv:2505.08762 (2025), and the ColabFit record doi:10.60732/3c2ddc75.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/OMol25_train_neutral")
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/63a2ec76-6295-535b-a376-580c18c8c088
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/63a2ec76-6295-535b-a376-580c18c8c088
- Over MCP: `get_schema_card` with id `63a2ec76-6295-535b-a376-580c18c8c088` 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)
