Update README.md

README.md

@@ -72,9 +72,8 @@ input_tokens = tokenizer(model_input, return_tensors="pt")
 input_tokens = input_tokens.to(device)
 generate_ids = model.generate(**input_tokens, max_new_tokens=512, do_sample=False, repetition_penalty=1.1)
 model_output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-model_output = model_output.replace(model_input, "")
 
-print(model_output)
+print(model_output[len(model_input) + 1: ])
 ```
 
 ### How to Quantize the Model