---
title: README
emoji: 👁
colorFrom: gray
colorTo: purple
sdk: static
pinned: false
---

# Materials Data Facility & Foundry-ML

**Publish. Discover. Accelerate Science.**

Welcome to the official Hugging Face organization for the **Materials Data Facility (MDF)** and **Foundry-ML** — two complementary platforms that make high-quality materials science data findable, accessible, interoperable, and reusable (FAIR) for the global research community.

---

## 🔬 About the Materials Data Facility (MDF)

The Materials Data Facility connects researchers to high-quality materials science datasets. Built on Globus services for secure, scalable data management, MDF enables scientists to publish their findings with citable DOIs, discover new data across the field, and meet data management requirements from funders and journals.

**By the numbers:**

- 🗂️ **880+** published datasets
- 💾 **600+ TB** of data hosted
- 🤖 **60+** ML-ready datasets
- 🌐 Backed by Globus for secure, reliable transfer at any scale

MDF is developed and operated with support from the **National Institute of Standards and Technology (NIST)** and the **Center for Hierarchical Materials Design (CHiMaD)**, in collaboration with the University of Chicago, Argonne National Laboratory, and the University of Illinois.

🔗 [materialsdatafacility.org](https://www.materialsdatafacility.org) · [Discover Data](https://www.materialsdatafacility.org/search) · [Publish Data](https://www.materialsdatafacility.org/publish)

---


## 📦 What You'll Find Here

This Hugging Face organization hosts a selection of MDF and Foundry-ML datasets in formats native to the Hugging Face ecosystem, making them easy to use alongside `transformers`, `datasets`, and the broader open ML toolchain. For the full catalog (including very large multi-TB datasets), visit [materialsdatafacility.org](https://www.materialsdatafacility.org).

---


## 📚 Citation

If MDF or Foundry-ML supports your research, please cite the following:

**Foundry-ML:**

> Schmidt, K. J., Scourtas, A., Ward, L., et al. (2024). Foundry-ML — Software and Services to Simplify Access to Machine Learning Datasets in Materials Science. *Journal of Open Source Software*, 9(93), 5467. https://doi.org/10.21105/joss.05467

**Materials Data Facility:**

> Blaiszik, B., Chard, K., Pruyne, J., Ananthakrishnan, R., Tuecke, S., & Foster, I. (2016). The Materials Data Facility: Data services to advance materials science research. *JOM*, 68(8), 2045–2052. https://doi.org/10.1007/s11837-016-2001-3

> Blaiszik, B., Ward, L., Schwarting, M., Gaff, J., Chard, R., Pike, D., Chard, K., & Foster, I. (2019). A data ecosystem to support machine learning in materials science. *MRS Communications*, 9(4), 1125–1133. https://doi.org/10.1557/mrc.2019.118

---

## 🤝 Acknowledgements

Foundry-ML is supported by the **National Science Foundation** (Award #1931306, "Collaborative Research: Framework: Machine Learning Materials Innovation Infrastructure" and Award #2209892, "Garden: A FAIR Framework for Publishing and Applying AI Models for Translational Research in Science, Engineering, Education, and Industry") 
The Materials Data Facility is supported by the **U.S. Department of Commerce, National Institute of Standards and Technology** (financial assistance award 70NANB19H005) as part of the Center for Hierarchical Materials Design (CHiMaD).

---

## 🔗 Links

- 🌐 **MDF Website:** [materialsdatafacility.org](https://www.materialsdatafacility.org)
- 💻 **Foundry-ML GitHub:** [MLMI2-CSSI/foundry](https://github.com/MLMI2-CSSI/foundry)
- 🏢 **MDF GitHub:** [materials-data-facility](https://github.com/materials-data-facility)
- 📄 **Foundry-ML Paper:** [JOSS 9(93), 5467](https://doi.org/10.21105/joss.05467)