Update README.md

README.md

@@ -15,7 +15,7 @@ library_name: transformers
 
 **VL-Rethinker-7B** achieves SoTA results on various multimodal reasoning benchmarks.
 
-It is trained using the **GRPO-SSR and Forced Rethinking** techniques, using meticulously curated training queries from [ViRL39K](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).
+It is trained using the **GRPO-SSR and Forced Rethinking** techniques, using meticulously curated **training data**: [ViRL39K](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).
 
 For details of our approach and performance comparison, please see our [paper](https://github.com/TIGER-AI-Lab/VL-Rethinker/blob/main/paper.pdf).