Update README.md

README.md

@@ -59,6 +59,7 @@ More testing and developement is underway and there are additional sizes other t
 - Sense of "there" is enhanced.
 - Details are more vivid.
 - Prose generation length can be extreme.
+- The model will take FEWER liberties vs a normal model: It will follow directives more closely but will "guess" less.
 - The MORE instructions and/or details you provide the more strongly the model will respond.
 - These quants are very sensitive to "temp" and "rep-pen" changes - adjust by .01 or less each.
 - Suggest a temp of .2 to start, rep pen of 1.1
@@ -97,6 +98,12 @@ Temp is set at 0 for simple reproduction of results.
 
 As soon as temp is set above "0", results will change accordingly but general characteristics of each version of generation will be maintained.
 
+If you use a prompt like this:
+
+"Start a 1000 word scene (vivid horror, 1st person, include thoughts) with: The sky scraper swayed, as she watched the window in front of her on the 21 floor explode..."
+
+You will get vastly different output generation, especially from 5x and 10x versions of the model, because of the added directives.
+
 ---
 
 <B><Font color="red">WARNING:</FONT> Strong language and/or visceral horror.</b>