Update README.md

README.md

@@ -15,6 +15,12 @@ tags:
 - W4A16
 ---
 
+## **Please use [Vortex V2 model](https://huggingface.co/ModelCloud/DeepSeek-R1-Distill-Qwen-7B-gptqmodel-4bit-vortex-v2) which fixed <think> token regression.**
+
+
+
+
+
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/641c13e7999935676ec7bc03/UDYiGu_Wagb-0rFJLdk3C.png)
 
 This model has been quantized using [GPTQModel](https://github.com/ModelCloud/GPTQModel).