Model Card for CrystaLLM-cXRD_chili100k

Model Details

Model Description

CrystaLLM-cXRD_chili100k is a conditional generative model for the recovery of crystal structures from powder X-ray Diffraction (XRD) data. It is a GPT-2 decoder-only model that conditions the generation of Crystallographic Information Files (CIFs) on a continuous diffraction profile rather than a peak list, using a Perceiver Resampler prefix (PrefixXRD) that compresses the pattern into learned key-value tokens injected at every transformer layer.

Unlike the earlier top-20 peak models, this model consumes the whole pattern:

1. Scattering vector (Q) on a fixed 1000-point grid, arange(0, 10, 0.01) Å⁻¹
2. Intensity (I), max-normalised to $[0, 1]$

This removes the peak-picking step from the workflow: a raw diffractometer scan is converted to the (1000, 2) [Q, I] profile automatically at generation time. Because Q is wavelength-independent, patterns from any anode can be used as long as the wavelength is supplied. It features an extended context window of 1536 tokens (plus 8 prefix tokens), enabling generation of larger unit cells.

• Developed by: Bone et al. (University College London)
• Model type: Autoregressive Transformer with Perceiver prefix conditioning (~36.7M parameters)
• Language(s): CIF (Crystallographic Information File) syntax
• License: MIT
• Finetuned from model: c-bone/CrystaLLM-cXRD_alex-mp-20

Model Sources

• Repository: GitHub: CrystaLLM-pi (generation), GitHub: CrystaLLM-cXRD (training and benchmarks)
• Paper: To add
• Dataset: HuggingFace: c-bone/cxrd_alex-mp-20 (Stage 1), HuggingFace: c-bone/cxrd_chili100k (Stage 2)

Uses

Direct Use

Structure solution and recovery from experimental powder XRD. Pass a raw two-column scan and a target composition; the model proposes candidate structures consistent with the diffraction signature. Trained on CHILI-100K, it is aimed at inorganic nanomaterials and experimentally determined structures.

Out-of-Scope Use

• Disordered Systems: No native handling of partial occupancies or significant disorder.
• Organic/MOFs: Training data was filtered to inorganic nanomaterials per the CHILI-100K methodology.
• Unconditional generation: The model requires a diffraction profile at every forward pass and has no missing-conditioning fallback.
• Non-CuKα data without a declared wavelength: CuKα1 is assumed when none is given, which silently misplaces every peak in Q.

Bias, Risks, and Limitations

• Preprocessing sensitivity: Recovery depends on the background subtraction and wavelength used to build the profile. Inspect the conversion (--save_plot) before trusting a result.
• Measured range: Regions of the Q grid outside the measured scan are zero-filled; short scans give the model less to work with.
• Polymorphs: For structurally similar candidates the model may favour the polymorph most prevalent in the CHILI-100K distribution.
• Amorphous or heavily broadened patterns: Nanocrystalline broadening is represented in training, but patterns without resolvable features carry little structural signal.

Getting started

For generation from a scan, use T4_XRD_continuous.ipynb in CrystaLLM-pi. For measured alloys and the virtualiser, see B3_alloy_virtualiser.ipynb. For the benchmark, see B2_chili100k_benchmark.ipynb.

Citation

Papers to Cite:

@misc{bone2025discoveryrecoverycrystallinematerials,
      title={Discovery and recovery of crystalline materials with property-conditioned transformers},
      author={Cyprien Bone and Matthew Walker and Bradley A. A. Martin 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},
}

and

To add

CHILI Dataset:

@inproceedings{10.1145/3637528.3671538,
      author = {Friis-Jensen, Ulrik and Johansen, Frederik L. and Anker, Andy S. and Dam, Erik B. and Jensen, Kirsten M. \O{}. and Selvan, Raghavendra},
      title = {CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning},
      year = {2024},
      isbn = {9798400704901},
      publisher = {Association for Computing Machinery},
      address = {New York, NY, USA},
      url = {https://doi.org/10.1145/3637528.3671538},
      doi = {10.1145/3637528.3671538},
      pages = {4962--4973},
      numpages = {12},
      keywords = {atomic structure, chemistry, datasets, deep learning, graph neural network, graphs, machine learning, nanomaterials, neutron, scattering, x-ray},
      location = {Barcelona, Spain},
      series = {KDD '24}
}