Improve model card: add pipeline tag, library name, update license, and paper reference

This PR enhances the model card for the quantized DeepSeek-R1 model by the AutoRound algorithm.

It addresses the following:
- **Added `pipeline_tag`**: The `text-generation` pipeline tag is added to the metadata, improving discoverability on the Hugging Face Hub.
- **Added `library_name`**: The `transformers` library is added as `library_name` to the metadata, enabling the automated "how to use" widget on the model page, as supported by the provided sample code and project documentation.
- **Updated `license`**: The `license` metadata is updated to `apache-2.0`, aligning with the license of the original `deepseek-ai/DeepSeek-R1` model and the `intel/auto-round` project.
- **Updated Paper Reference**: The model card content and the "Cite" section are updated to correctly reference the latest paper, "[SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs](https://huggingface.co/papers/2512.04746)".
- **Prominent GitHub Link**: A direct link to the [AutoRound GitHub repository](https://github.com/intel/auto-round) is added near the beginning of the model card for easy access.

These changes significantly improve the model card's clarity, accuracy, and usability for the Hugging Face community.

README.md

@@ -1,16 +1,20 @@
 ---
-datasets:
-- NeelNanda/pile-10k
 base_model:
 - deepseek-ai/DeepSeek-R1
+datasets:
+- NeelNanda/pile-10k
+pipeline_tag: text-generation
+library_name: transformers
+license: apache-2.0
+---
 
+This model is an int2 model with group_size 64 and symmetric quantization of [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1), generated by the **SignRoundV2** algorithm described in the paper [SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs](https://huggingface.co/papers/2512.04746).
 
-
----
+For more details on the AutoRound project and its implementation, see the [GitHub repository](https://github.com/intel/auto-round).
 
 ## Model Details
 
-This model is an int2 model with group_size  64 and symmetric quantization of [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm.  Some layers are fallback to 4/16 bits. Refer to  Section "Generate the model" for more details of mixed bits setting.
+Some layers are fallback to 4/16 bits. Refer to Section "Generate the model" for more details of mixed bits setting.
 
 Please follow the license of the original model. This model could **NOT** run on other severing frameworks. 
 
@@ -439,6 +443,13 @@ The license on this model does not constitute legal advice. We are not responsib
 
 ## Cite
 
-@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
+```bibtex
+@article{cheng2025signroundv2,
+    title={SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs},
+    author={Cheng, Wenhua and Zhang, Weiwei and Guo, Heng and Shen, Haihao},
+    journal={arXiv preprint arXiv:2512.04746},
+    year={2025}
+}
+```
 
-[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
+[arxiv](https://arxiv.org/abs/2512.04746)