3D_LLM_Diffusion-trimodal-qwen-v11

3D LLM Diffusion: Tri-Modal Qwen v11

This release contains the trained components required for the project's text/XRD/crystal shared representation and Qwen-controlled Crystalite runtime. Qwen owns both natural-language boundaries: it parses user requests into auditable crystal conditions and produces grounded descriptions from facts computed from the selected CIF. Crystalite generates structures; deterministic powder diffraction physics generates XRD. The Neutral Composition Planner and charge-balance gate are enabled for de novo generation by default. There is no Robocrystallographer or template-prose runtime path.

Runtime Contract

raw text -> Qwen parse + Qwen latent adapter -> v11 256-d shared hub
                                                   |
                                      conditioned Crystalite
                                                   |
                                             selected CIF
                                             /          \
                                  simulated XRD      facts -> Qwen text

The planner fixes a formally charge-feasible composition before Crystalite denoises coordinates and the lattice. This is a generation constraint, not a substitute for structure-aware validity, MLIP relaxation, or DFT validation.

End-to-End Qwen Runtime Validation

Gadi GPU job 174157319 exercised both production text routes with the pinned Qwen revision and exited successfully:

The short 12-step de-novo integration sample is NaCl but has P1 symmetry, so it does not demonstrate cubic-condition accuracy. Parsed conditions, generated CIFs, charge audits, deterministic XRD, grounding facts, and Qwen descriptions are preserved under metrics/qwen_anyio_smoke/. This smoke test validates the runtime wiring; GenBench and property-control evaluations remain the quality evidence.

The Qwen weights are not redistributed here. Use Qwen/Qwen3.6-35B-A3B at exact revision 995ad96eacd98c81ed38be0c5b274b04031597b0 with transformers==5.14.1.

Released Components

Large embedding tables and training/evaluation data are released separately in Yangfan78/3D_LLM_Diffusion-trimodal-assets-v11.

Qwen Latent Adapter Validation

The 2048-to-256 adapter was selected at epoch 99 on 9,047 held-out paired texts.

These metrics measure recovery of the frozen v11 text-hub targets; they are not generated-crystal validity or property scores. The checkpoint includes the exact Qwen revision, environment versions, hyperparameters, row counts, and input/checkpoint SHA-256 hashes.

Tri-Modal Evaluation

The paired MP20 synthetic-XRD test split contains 9,046 examples.

These are retrieval results on simulated diffraction, not measured-XRD or generated-structure property accuracy. Generated candidates still require independent structural, MLIP, and preferably DFT validation.

Planner + ORB-v3 GenBench

The completed all-2,500 run uses the Neutral Composition Planner, Crystalite FK K8 sampling (lambda=4), independent ORB-v3 pre-relaxation, and the pinned LeMat-Bulk reference revision. It is a non-hybrid generated pool.

The run passes the project's validity, novelty, metastability, and displacement targets. It does not pass the uniqueness, stable-rate, or hull-energy targets. The full CIF pools, audit trail, benchmark pickle, source snapshot, hashes, and metric JSON are in the companion dataset under evaluation/planner_orb_genbench_all2500_20260719/.

Source

• Code: https://github.com/Richardyangfan78/3D_LLM_Diffusion/tree/70a66c2e4ce1417cfef378e4c01045d753900d0b
• FK generator release: https://huggingface.co/Yangfan78/3D_LLM_Diffusion-fk-k8-lam4