Update README.md

README.md

@@ -27,7 +27,7 @@ The InfiAlign framework offers multiple variants tailored for different alignmen
 
 * **[InfiAlign-Qwen-7B-SFT](https://huggingface.co/InfiX-ai/InfiAlign-Qwen-7B-SFT)**: Fine-tuned using curriculum-style instruction data.
 * **[InfiAlign-Qwen-7B-DPO](https://huggingface.co/InfiX-ai/InfiAlign-Qwen-7B-DPO)**: Trained with Direct Preference Optimization (DPO) to improve reasoning alignment. **\[You are here!]**
-* **[InfiAlign-Qwen-7B-R1](https://huggingface.co/InfiX-ai/InfiAlign-Qwen-7B-R1)**: Reinforcement learning variant (GRPO) for further refinement.
+* **[InfiAlign-Qwen-7B-R1](# "Stay tuned")**: Reinforcement learning variant (GRPO) for further refinement.
 
 ## 📋 Model Description