Improve model card: Add license, library name, pipeline tag, and GitHub link

README.md

@@ -1,12 +1,18 @@
 ---
-datasets:
-- zwhe99/DeepMath-103K
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+datasets:
+- zwhe99/DeepMath-103K
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
+
 # AutoDeco
 Official Implementation of "[The End of Manual Decoding: Towards Truly End-to-End Language Models](https://arxiv.org/abs/2510.26697)"
 
+Code: https://github.com/Zacks917/AutoDeco
+
 **AutoDeco** is a framework that adds token-level adaptive decoding parameter prediction capabilities to Large Language Models (LLMs). By adding lightweight prediction heads on top of pre-trained models, AutoDeco can dynamically predict optimal temperature and top-p parameters for each token during decoding.
 
 ## 🎯 Key Features
@@ -146,8 +152,15 @@ Training data should be in JSONL format, with one sample per line. AutoDeco supp
 
 # example
 {
-  "prompt": "<|im_start|>user\nEvaluate the limit:$$\\lim_{(x, y) \\to (1, 2)} \\frac{(x-1)(y-2)-x+3}{x^2-2x+y^2-4}$$\nMake sure you output the final answer within \\boxed{}<|im_end|>\n< im_start>assistant\n",
-  "completion": "......### ✅ Final Answer:\n$$\n\\boxed{-1}\n$$""
+  "prompt": "<|im_start|>user
+Evaluate the limit:$$\\lim_{(x, y) \\to (1, 2)} \\frac{(x-1)(y-2)-x+3}{x^2-2x+y^2-4}$$
+Make sure you output the final answer within \\boxed{}<|im_end|>
+< im_start>assistant
+",
+  "completion": "......### ✅ Final Answer:
+$$
+\\boxed{-1}
+$$""
 }
 ```
 
@@ -277,10 +290,4 @@ If you use AutoDeco in your research, please cite:
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2510.26697}, 
 }
-```
-
-<!-- ## Acknowledgments
-
-- Built on [Transformers](https://github.com/huggingface/transformers) and [TRL](https://github.com/huggingface/trl)
-- Training framework uses [DeepSpeed](https://github.com/microsoft/DeepSpeed)
-- Inference optimization uses [vLLM](https://github.com/vllm-project/vllm) -->
+```