c-bone/CrystaLLM-pi_Mattergen-XRD

Model Card for CrystaLLM-pi_Mattergen-XRD

Model Details

Model Description

CrystaLLM-pi_Mattergen-XRD is a conditional generative model designed for the recovery of crystal structures from X-ray Diffraction (XRD) data. It is a fine-tuned version of the CrystaLLM-pi framework, based on a GPT-2 decoder-only architecture. This variant employs the Residual Attention (Slider) mechanism to condition the generation of Crystallographic Information Files (CIFs) on high-dimensional experimental data.

The model generates crystal structures based on an XRD pattern input vector, consisting of the 20 most intense peaks:

1. 1.Peak Positions ($2\theta$)
2. 2.Peak Intensities

• —Developed by: Bone et al. (University College London)
• —Model type: Autoregressive Transformer with Residual Attention Conditioning
• —Language(s): CIF (Crystallographic Information File) syntax
• —License: MIT
• —Finetuned from model: c-bone/CrystaLLM-pi_base

Model Sources

• —Repository: GitHub: CrystaLLM-pi
• —Paper: Discovery and recovery of crystalline materials with property-conditioned transformers (arXiv:2511.21299)
• —Dataset: HuggingFace: c-bone/mattergen_XRD

Uses

Direct Use

The model is intended for structure solution and recovery from powder XRD data. Researchers can input a list of peak positions and intensities derived from experimental diffraction patterns to generate candidate crystal structures that match the experimental signature.

Out-of-Scope Use

• —Disordered Systems: The model was trained on the alex-mp-20 dataset and theoretical XRDs. It does not natively handle partial occupancies or disorder.
• —Large Unit Cells: Context window limits apply (~20 atoms/cell).
• —Organic/MOFs: The training data only contains ordered organic crystals.

Bias, Risks, and Limitations

• —Missing Data: The "Slider" mechanism is designed to handle missing peaks (padded with -100), but significant data loss will degrade recovery rates.
• —Polymorphs: In cases of strong structural similarity or ambiguous diffraction patterns, the model may be biased towards the polymorph most represented in the training distribution.

Getting started

Generation from a scan: `T2_load_and_generate.ipynb`.

Citation

@misc{bone2025discoveryrecoverycrystallinematerials,
      title={Discovery and recovery of crystalline materials with property-conditioned transformers}, 
      author={Cyprien Bone and Matthew Walker and Kuangdai Leng and Luis M. Antunes and Ricardo Grau-Crespo and Amil Aligayev and Javier Dominguez and Keith T. Butler},
      year={2025},
      eprint={2511.21299},
      archivePrefix={arXiv},
      primaryClass={cond-mat.mtrl-sci},
      url={[https://arxiv.org/abs/2511.21299](https://arxiv.org/abs/2511.21299)}, 
}