Update README.md

README.md

@@ -59,7 +59,7 @@ We evaluate the model on the datasets of [Open LLM Leaderboard](https://huggingf
 
 ### Inference Tool
 
-We utilize [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer) for CPU inference, here we list the inference speed of pure CPU inference with fp16 precision.
+We utilize [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer) for inference, here we list the inference speed of pure CPU inference with fp16 precision.
 
 Dense Inference: 2.69 tokens/s