Modelpublic

Yangfan78/3D_LLM_Diffusion-fk-k8-lam4

sourceHugging Facemitupdated 2mo agoView on Hugging Face

0likes

Model Card

3D LLM Diffusion fkk8lam4

This repository is the reproducible release for the fk_k8_lam4 raw LeMat-GenBench run reported in the project GitHub repository. It releases the actual generator checkpoint, the MACE formation-energy guidance model, the FK sampling configuration, all 2,500 generated CIFs, and the GenBench summary.

fk_k8_lam4 is a sampling run name, not a separate neural checkpoint. It uses v12_multiprop/best.pt with force-kernel (FK) steering: 8 particles, lambda 4.0, sigma range [0.03, 0.20], and 4 resampling checkpoints.

Released Artifacts

File or directory	Purpose	SHA256
`best.pt`	`v12_multiprop` generator checkpoint used by FK	`5995f3086844e8b1ff0d8d76b029f11024b1a319ce10ff186c3f4e003ecf8056`
`mace_eform_mp20_run-7.model`	Formation-energy guidance model used by FK	`bf6040a923e22b67add51557c69d0b7f2a3d0b1830280c2a1f914ad72b665001`
`artifacts/prompts.jsonl`	Fixed 2,500 evaluation prompts	`41c7f660585da40e8ab60b5ffdaa619e470cd0edf5da0fb45764bca18fcd4f78`
`artifacts/text_z_bench.pt`	Fixed prompt embeddings	`2b00a3f16cbe1166cc824391df28ae1183126a7853cc189816b22822683bc652`
`evaluation_cifs.tar.gz`	Archive containing all 2,500 raw generated CIFs evaluated by LeMat	`96537fe54dc95248c27c9367d3cf5cc27e9d5e40fbf900327bf6d245931e8e87`
`artifacts/generation_manifest.json`	Exact sampling configuration	See `SHA256SUMS`
`artifacts/genbench_direct.json`	Formal GenBench result	See `SHA256SUMS`

Direct LeMat-GenBench Result

The run uses 2,500 fixed prompts, 100 EDM steps, CFG scale 2.0, s_churn=2.0, and seed 11. CIFs were submitted without pre-relaxation and evaluated with the LeMat ORB, MACE, and UMA relaxation ensemble.

Valid	Unique	Novel	Stable	Metastable	Mean E_hull (eV)	Relaxation displacement RMSE (A)
86.08%	84.99%	79.18%	4.74%	29.88%	0.2981	1.1246

This direct raw-generator run passes 1 of the 7 project thresholds (novelty). Relaxation displacement RMSE is LeMat's per-index Cartesian displacement from the submitted structure to its MLIP-relaxed structure. It is not an RMSD to a reference crystal structure.

Reproduction Scope

reproducibility/run_fk_generation.sh regenerates the FK sampling protocol after an MP20-compatible training CSV is supplied. The current sampler derives empirical atom-count and allowed-element priors from that CSV. The original MP20 train/validation split and training text embeddings are not redistributed.

The full evaluated CIF pool is included in evaluation_cifs.tar.gz, so the published GenBench submission can be audited without rerunning generation. The source snapshot, environment lock, artifact hashes, and provenance are provided for the inference-side protocol. Retraining v12_multiprop is outside this release scope.

Source And License

The main implementation and project documentation are at Richardyangfan78/3D_LLM_Diffusion. The code and released artifacts are provided under the MIT license in this repository. Third-party code and dependencies retain their notices in `NOTICE`.

Limitations

This is a research candidate-generation run. The direct benchmark result is not DFT validation, does not establish synthesizability, and should not be confused with the separately curated MLIP-relaxed hybrid delivery result.