Update README.md

README.md

@@ -21,7 +21,7 @@ Light-R1-7B-DS also performed well on GPQA *without* any specific training.
 
 Originated from DeepSeek-R1-Distill-Qwen-7B, Light-R1-7B-DS is further trained with only [3K SFT data](https://huggingface.co/datasets/qihoo360/Light-R1-SFTData) as we've open-sourced, demonstrating the strong applicability of the released data.
 
-We are excited to release this model along with the [technical report](https://github.com/Qihoo360/Light-R1/Light-R1.pdf).
+We are excited to release this model along with the [technical report](https://github.com/Qihoo360/Light-R1/blob/main/Light-R1.pdf).
 
 ## Usage
 Same as DeepSeek-R1-Distill-Qwen-7B.