Preview model card for DMax-Math-MMD

Adds the model card for review. The training section is omitted, and the citation uses @article with the requested arXiv preprint TODO journal placeholder.

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+library_name: transformers
+base_model: Zigeng/DMax-Math-16B
+base_model_relation: finetune
+datasets:
+  - Zigeng/DMax-LLaDA-2.0-Mini-Math-Trajectories
+tags:
+  - diffusion
+  - dllm
+  - mmd
+  - math
+  - custom_code
+---
+
+# DMax-Math-MMD
+
+**Representation-Space MMD for Diffusion Language Models**
+
+DMax-Math-MMD is a 16B diffusion language model for mathematical reasoning,
+obtained by MMD post-training of
+[DMax-Math-16B](https://huggingface.co/Zigeng/DMax-Math-16B).
+It builds on LLaDA2.0-mini and uses DMax's hybrid masked–uniform block diffusion.
+
+The post-training objective minimizes Maximum Mean Discrepancy (MMD) between
+model samples and reference responses, measured in the representation space of
+a frozen diffusion language model. The project reports increased tokens per
+forward pass while maintaining or improving accuracy on the benchmarks below.
+
+[Project code and documentation](https://github.com/yandex-research/dlm-mmd)
+· [DMax-Coder-MMD](https://huggingface.co/yresearch/DMax-Coder-MMD)
+
+## Reference results
+
+Results reported in the project README, with decoding threshold **0.85**.
+Each entry is **accuracy (%) / tokens per forward pass (TPF)**.
+Baseline results are attributed to the original DMax paper in the project README.
+
+| Method | GSM8K | MATH500 | Minerva-Algebra | ASDIV |
+| --- | :---: | :---: | :---: | :---: |
+| DMax-Math | 92.1 / 5.48 | 75.4 / 5.94 | 91.5 / 7.03 | 92.5 / 5.62 |
+| **DMax-Math-MMD** | 92.1 / **6.15** | **76.0** / **6.84** | **92.1** / **8.19** | **92.9** / **6.20** |
+
+Results can vary with hardware, tensor parallelism, and library versions.
+TPF measures decoding parallelism; wall-clock speed also depends on the runtime.
+
+## Evaluation and inference
+
+Use DMax's dInfer evaluation pipeline. After following the evaluation environment
+setup in the [project README](https://github.com/yandex-research/dlm-mmd#installation),
+run from the project repository root:
+
+```bash
+conda activate dinfer
+DOMAIN=math MODEL_PATH=yresearch/DMax-Math-MMD bash scripts/eval.sh
+```
+
+The project's math evaluation uses threshold **0.85** and evaluates GSM8K,
+MATH500, Minerva-Algebra, and ASDIV.
+
+The checkpoint includes nine Safetensors shards with BF16 parameters and FP32
+router bias buffers, plus its tokenizer, chat template, and custom model code.
+Direct Transformers loading requires `trust_remote_code=True`. Pass
+`dtype=torch.bfloat16` for BF16 loading; the current configuration declares FP32.
+
+Generation requires the DMax/dInfer diffusion decoder. The included custom
+backbone does not implement the standard Transformers `.generate()` interface.
+
+## License and acknowledgements
+
+The model follows the **Apache-2.0** license of the
+[DMax-Math base checkpoint](https://huggingface.co/Zigeng/DMax-Math-16B)
+and [LLaDA2.0-mini](https://huggingface.co/inclusionAI/LLaDA2.0-mini).
+The included model implementation retains its Apache-2.0 notices.
+The separate MMD training repository is MIT-licensed, with Apache-2.0 third-party components.
+
+We thank the authors of [DMax](https://github.com/czg1225/DMax),
+[LLaDA2.0-mini](https://huggingface.co/inclusionAI/LLaDA2.0-mini), and
+[dInfer](https://github.com/inclusionAI/dInfer) for releasing their models, data, and code.
+
+## Citation
+
+If you find this work useful in your research, please consider citing:
+
+```bibtex
+@article{drobyshevskiy2026mmd,
+  title  = {Representation-Space MMD for Diffusion Language Models},
+  author = {Drobyshevskiy, Ilya and Sudakov, Ilia and Semenov, Maksim and Kuznedelev, Denis and
+            Ignatov, Maksim and Temirchev, Pavel and Balagansky, Nikita and
+            Meshchaninov, Viacheslav and Gushchin, Nikita and Baranchuk, Dmitry},
+  journal = {arXiv preprint TODO},
+  year    = {2026}
+}
+```