Update README.md

README.md

@@ -19,7 +19,7 @@ You can use this model directly with a pipeline for text generation. Since the g
 set a seed for reproducibility:
 ```python
 >>> from transformers import pipeline, set_seed
->>> generation= pipeline('text-generation', model='Tanhim/gpt2-model-de')
+>>> generation= pipeline('text-generation', model='Tanhim/gpt2-model-de', tokenizer='Tanhim/gpt2-model-de')
 >>> set_seed(42)
 >>> generation("Hallo, ich bin ein Sprachmodell,", max_length=30, num_return_sequences=5)