match generation parameters with model trained on LFQA dataset

README.md

@@ -17,16 +17,16 @@ widget:
   example_title: "solar system"
 - text: "question: what is a probability distribution? context: I am just learning about statistics."
   example_title: "probability distribution"
-- text: "question: how does exercise help us lose weight? context: I started working out two weeks ago and already feel a lot better, and started to think about it and became deeply confused."
+- text: "question: What are the underlying physical processes by which exercise helps us lose weight? context: I started working out two weeks ago and already feel a lot better, and started to think about it and became deeply confused."
   example_title: "pumpen"
 - text: "what is a neural network?"
   example_title: "deep learning"
-- text: "How can computers understand human language?"
+- text: "What are the primary mechanisms that computers use to understand human language?"
   example_title: "NLP"
   
 inference:
   parameters:
-    max_length: 64
+    max_length: 96
     no_repeat_ngram_size: 2
     encoder_no_repeat_ngram_size: 4
     repetition_penalty: 3.51