Update README.md

README.md

@@ -21,8 +21,8 @@ In addition, Doge uses Inner Function Attention with Dynamic Mask as sequence tr
 ```python
 >>> from transformers import AutoTokenizer, AutoModelForCausalLM
 
->>> tokenizer = AutoTokenizer.from_pretrained("LoserCheems/Doge-76M")
->>> model = AutoModelForCausalLM.from_pretrained("LoserCheems/Doge-76M", trust_remote_code=True)
+>>> tokenizer = AutoTokenizer.from_pretrained("JingzeShi/Doge-76M")
+>>> model = AutoModelForCausalLM.from_pretrained("JingzeShi/Doge-76M", trust_remote_code=True)
 >>> inputs = tokenizer("Hey how are you doing?", return_tensors="pt")
 
 >>> out = model.generate(**inputs, max_new_tokens=100)