Minor fix to example in the readme

Current example gives `ValueError: Unfeasable length constraints: the minimum length (50) is larger than the maximum length (20)`

README.md

@@ -35,7 +35,7 @@ You can use this model directly with a pipeline for text generation. This exampl
 ```py
 >>> from transformers import pipeline
 >>> generator = pipeline('text-generation', model='EleutherAI/gpt-neo-125M')
->>> generator("EleutherAI has", do_sample=True, min_length=50)
+>>> generator("EleutherAI has", do_sample=True, min_length=20)
 
 [{'generated_text': 'EleutherAI has made a commitment to create new software packages for each of its major clients and has'}]
 ```