Update README.md

fix tokenizer max_length :-)

README.md

@@ -44,7 +44,7 @@ model.eval()
 
 prompt = 'Q: What is the largest bird?\nA:'
 input_ids = tokenizer(prompt, return_tensors="pt").input_ids
-tokens = model.generate(input_ids, max_length=20)
+tokens = model.generate(input_ids, max_length=22)
 print( tokenizer.decode(tokens[0].tolist(), skip_special_tokens=True) )
 # Q: What is the largest bird?\nA: The largest bird is a black-headed gull.
 ```