Improve model card with paper link, usage example, and citation (#2)

- Improve model card with paper link, usage example, and citation (be173834915ee86e243dae7f50a4b6e71998065e)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,12 +1,46 @@
 ---
-license: mit
 library_name: transformers
+license: mit
 pipeline_tag: text-generation
 ---
-# LLaDA 1.5
 
-We introduce LLaDA 1.5, a competitive large diffusion language model, trained by variance-reduced preference optimization (VRPO).
+# LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
+
+We introduce LLaDA 1.5, a competitive large diffusion language model, trained by variance-reduced preference optimization (VRPO), as presented in the paper [LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models](https://huggingface.co/papers/2505.19223).
+
+Compared with LLaDA-8B-Instruct, LLaDA 1.5 achieves better performance on a wide range of tasks, including Math, Code, and Alignment tasks.
 
 [Project Page](https://ml-gsai.github.io/LLaDA-1.5-Demo/)
 
-[Code](https://github.com/ML-GSAI/LLaDA-1.5)
+[Code](https://github.com/ML-GSAI/LLaDA-1.5)
+
+<div style="display: flex; justify-content: center; align-items: center; width: 100%; margin: 0 auto;">
+    <img src="https://github.com/ML-GSAI/LLaDA-1.5/raw/main/assets/llada_1_5.png" style="width: 50%; display: block; margin: 0 auto;" />
+</div>
+
+## Inference
+
+The LLaDA 1.5 model is available on [Huggingface](https://huggingface.co/GSAI-ML/LLaDA-1.5). Please employ the [transformers](https://huggingface.co/docs/transformers/index) to load.
+
+```python
+from transformers import AutoModel, AutoTokenizer
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained('GSAI-ML/LLaDA-1.5', trust_remote_code=True)
+model = AutoModel.from_pretrained('GSAI-ML/LLaDA-1.5', trust_remote_code=True, torch_dtype=torch.bfloat16)
+```
+
+The model is based on LLaDA-8B-Instruct, you can use the code for [LLaDA-8B-Instruct](https://github.com/ML-GSAI/LLaDA/blob/main/generate.py) to inference.
+
+## Citation
+
+Please consider cite:
+
+```bibtex
+@article{zhu2025llada,
+  title={LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models},
+  author={Zhu, Fengqi and Wang, Rongzhen and Nie, Shen and Zhang, Xiaolu and Wu, Chunwei and Hu, Jun and Zhou, Jun and Chen, Jianfei and Lin, Yankai and Wen, Ji-Rong and others},
+  journal={arXiv preprint arXiv:2505.19223},
+  year={2025}
+}
+```