Add `pipeline_tag` and `library_name` to model card

README.md

@@ -1,17 +1,19 @@
 ---
+datasets:
+- gsm8k
+- svamp
+- multi_arith
 language:
 - en
 license: mit
+pipeline_tag: text-generation
+library_name: transformers
 tags:
 - chain-of-thought
 - implicit-reasoning
 - multimodal
 - llama3
 - instruction-tuned
-datasets:
-- gsm8k
-- svamp
-- multi_arith
 model-index:
 - name: SIM_COT-LLaMA3-CODI-8B
   results:
@@ -171,5 +173,22 @@ Average accuracy over 1 sampling: xxx
 - average length of COT: average number of latent reasoning tokens.
 - average accuracy: aggregated accuracy across sampled runs.
 
+## ✒️ Citation
+
+If you find our work helpful for your research, please consider giving a star ⭐ and citation 📝
+
+```bibtex
+@article{wei2025simcot,
+  title={{SIM-COT}: Supervised Implicit Chain-of-Thought},
+  author={Wei, Xilin and Liu, Xiaoran and Zang, Yuhang and Dong, Xiaoyi and Cao, Yuhang and Wang, Jiaqi and Qiu, Xipeng and Lin, Dahua},
+  journal={arXiv preprint arXiv:2509.20317},
+  year={2025}
+}
+```
 
+## ❤️ Acknowledgments
 
+- [Coconut](https://github.com/facebookresearch/coconut): The codebase we built upon. Thanks for their wonderful work.
+- [CODI](https://github.com/zhenyi4/codi): Our work is based on this codebase; we are grateful for their valuable contribution.
+- [LLaMA series](https://huggingface.co/meta-llama/collections): The amazing open-sourced large language model!
+- [GPT2](https://huggingface.co/openai-community/gpt2): An impressive open-source large language model!