You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
//Basically copied this from AUTOMATIC1111 implementation of the main UI
2
+
3
+
titles={
4
+
"Temperature": "A higher temperature will produce more diverse results, but with a higher risk of less coherent text",
5
+
"Max Length": "The maximum number of tokens for the output of the model",
6
+
"Top K": "Strategy is to sample from a shortlist of the top K tokens. This approach allows the other high-scoring tokens a chance of being picked.",
7
+
"Repetition Penalty": "The parameter for repetition penalty. 1.0 means no penalty. Default setting is 1.2. Paper explaining it is linked to Github's readme",
8
+
"How Many To Generate":"The number of results to generate. Not guaranteed if models fails to create them",
9
+
"Generate Using Magic Prompt":"Be aware that sometimes the model fails to produce anything or less than the wanted amount, either try again or use a new prompt in that case"
1 commit comments
imrayya commentedon Jan 26, 2023
Added tooltips to address issue: #10