Update README.md

README.md

@@ -11,7 +11,7 @@ inference:
     top_k: 50
     min_new_tokens: 2
     max_new_tokens: 96
-    repetition_penalty: 1.1
+    repetition_penalty: 1.04
     no_repeat_ngram_size: 6
     epsilon_cutoff: 0.0006
 widget:
@@ -56,7 +56,7 @@ It was trained on inputs so if you have inputs (like some text to ask a question
 
 ## Example
 
-Output on the text above ^. The inference API is set to sample with low temp so you should see (_at least slightly_) different inputs each time.
+Output on the text above ^. The inference API is set to sample with low temp so you should see (_at least slightly_) different generations each time.
 
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/0nFP2jsBkritnryKmI8NV.png)