Improve model card and add paper link

Hi! I'm Niels, part of the community science team at Hugging Face. I've noticed this repository is missing a detailed model card and metadata.

I've opened this PR to:
- Add `pipeline_tag: text-generation` to the metadata for better discoverability.
- Link the repository to the official paper on Hugging Face ([2603.02188](https://huggingface.co/papers/2603.02188)).
- Add a link to the official GitHub repository.
- Provide a brief summary of the Multi-Head Low-Rank Attention (MLRA) mechanism and the official citation.

README.md

@@ -1,3 +1,28 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: text-generation
+---
+
+# Multi-Head Low-Rank Attention (MLRA)
+
+Official pretrained weights for **Multi-Head Low-Rank Attention (MLRA)**, a novel attention mechanism that natively supports 4-way tensor parallelism and significantly reduces the key-value (KV) cache size, enabling efficient long-context inference at scale.
+
+## Resources
+- **Paper:** [Multi-Head Low-Rank Attention](https://huggingface.co/papers/2603.02188)
+- **Code:** [Official GitHub Repository](https://github.com/SongtaoLiu0823/MLRA)
+
+## Model Description
+Long-context inference in large language models is often bottlenecked by KV cache loading during the decoding stage. While Multi-Head Latent Attention (MLA) reduces the total KV cache size, it suffers from a sharding bottleneck during distributed decoding via Tensor Parallelism (TP).
+
+MLRA addresses this by enabling partitionable latent states for efficient 4-way TP decoding. Experimental results show that MLRA achieves state-of-the-art perplexity and downstream task performance, while delivering a 2.8$\times$ decoding speedup over MLA.
+
+## Citation
+If you find this work useful, please cite:
+```bibtex
+@inproceedings{liu2026multi,
+  title     = {Multi-Head Low-Rank Attention},
+  author    = {Liu, Songtao and Peng, Hongwu and Zhang, Zhiwei and Chen, Zhengyu and Guo, Yue},
+  booktitle = {International Conference on Learning Representations},
+  year      = {2026}
+}
+```