Update README.md

README.md

@@ -44,7 +44,11 @@ inference:
 You can use this model directly with a pipeline for masked language modeling:
 ```python
 from transformers import pipeline
-genius = pipeline("text2text-generation", model="beyond/genius-large", device=0)
-sketch = "asdfasdfasdfasdfadsf \<mask\>"
-generated_text = genius(sketch, num_beams=3, do_sample=True, max_length=200)[0]["generated_text"]
+# 1. load the model with the huggingface `pipeline`
+genius = pipeline("text2text-generation", model='beyond/genius-large', device=0)
+# 2. provide a sketch (joint by mask tokens)
+sketch = "your_sketch"
+# 3. here we go!
+generated_text = genius(sketch, num_beams=3, do_sample=True, max_length=200)[0]['generated_text']
+print(generated_text)
 ```