Update README.md

README.md

@@ -117,7 +117,7 @@ inputs = tokenizer(text, return_tensors="pt")
 outputs = model.generate(**inputs.to("cuda"), max_new_tokens=185,do_sample=False,top_k=None,temperature=1.0,top_p=None)
 
 # Decode the output
-result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+result = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
 print(result)
 ```