minor

README.md

@@ -54,8 +54,8 @@ You should replace original modeling_qwen FFN implementation code to dReLU first
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-7B-ReLU")
-tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B-ReLU")
+model = AutoModelForCausalLM.from_pretrained("PowerInfer/SparseQwen2-7B")
+tokenizer = AutoTokenizer.from_pretrained("PowerInfer/SparseQwen2-7B")
 
 prompt = "Hello"
 inputs = tokenizer(prompt, return_tensors="pt")