Improve model card with library and pipeline information

README.md

@@ -1,9 +1,11 @@
 ---
-license: mit
-datasets:
-- agentica-org/DeepScaleR-Preview-Dataset
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+datasets:
+- agentica-org/DeepScaleR-Preview-Dataset
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
 tags:
 - LRM
 - hybrid_reasoning
@@ -13,7 +15,7 @@ tags:
 # AdaptThink: LLM Can Learn When to Think
 
 <p align="center">
-    🤗 <a href="https://huggingface.co/collections/THU-KEG/adaptthink-682a1059aa9f5102c4fa0470" target="_blank">HF Collections</a> • 💻 <a href="" target="_blank">Github Repo</a> • 📃 <a href="https://arxiv.org/abs/2505.13417" target="_blank">Paper</a>
+    🤗 <a href="https://huggingface.co/collections/THU-KEG/adaptthink-682a1059aa9f5102c4fa0470" target="_blank">HF Collections</a> • 💻 <a href="https://github.com/THU-KEG/AdaptThink" target="_blank">Github Repo</a> • 📃 <a href="https://arxiv.org/abs/2505.13417" target="_blank">Paper</a>
 </p>
 
 ## 🔍 Table of Contents
@@ -34,7 +36,7 @@ We present **AdapThink**, a novel reinforcement learning (RL) algorithm that ena
 ## ⚙️ Released Models
 
 ### All Available Datasets and Models
-We apply the AdaptThink algorithm on DeepSeek-R1-Distill-Qwen-1.5B with $\delta$ from 0 to 0.1, and DeepSeek-R1-Distill-Qwen-7B with $\delta=0.05$. A larger $\large$ results in a higher proportion of NoThinking responses, which reduces more inference costs but also diminish the resultant improvement in accuracy.
+We apply the AdaptThink algorithm on DeepSeek-R1-Distill-Qwen-1.5B with $\delta$ from 0 to 0.1, and DeepSeek-R1-Distill-Qwen-7B with $\delta=0.05$. A larger $\large$ results in a higher proportion of NoThinking responses, which reduces more inference costs but also diminishes the resultant improvement in accuracy.
 
 All the trained models are available on HuggingFace. 
 
@@ -83,5 +85,4 @@ If you find our work useful, please consider citing LongReward:
   url={https://arxiv.org/abs/2505.13417}
   year={2025}
 }
-```
-
+```