Update README.md

README.md

@@ -36,24 +36,25 @@ and blew it out to over 16.5 billion parameters - 642 tensors, 71 layers (8B ori
 
 This is not an "upscale" or "franken merge" but a completely new model based on the models used to construct "L3-Stheno-Maid-Blackroot 8B".
 
-The result is a take no prisoners, totally uncensored, fiction writing monster and roleplay master.
+The result is a take no prisoners, totally uncensored, fiction writing monster and roleplay master as well 
+just about any general fiction activity including scene generation and scene continuation.
 
-Although it can do a lot more, those are its core specialties.
+As a result of the expansion / merge re-build its level of prose and story generation has significantly improved
+as well as word choice, sentence structure as well as default output levels and lengths.
 
-It also has a STRONG horror bias, although it will generate content for almost any genre.
+It also has a STRONG horror bias, although it will generate content for almost any genre. 
 
-Because of the nature of this merge most attributes of each of the 3 models will be in this expanded model as opposed to the
-original merge were some of one or more of the model's features and/or strengths maybe reduced.
+(see examples sections for different genres)
 
-As a result of the expansion / merge re-build its level of prose and story generation has significantly improved
-as well as word choice, sentence structure as well as default output levels.
+Because of the nature of this merge most attributes of each of the 3 models will be in this rebuilt 16.5B model as opposed to the
+original 8B model were some of one or more of the model's features and/or strengths maybe reduced or overshadowed.
+
+Please see the models used in this merge (links below in the "formula" section ) for more information on 
+what they "bring" to this merged 16.5B model.
 
 This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 8k / 8192. 
 However this can be extended using "rope" settings up to 32k.
 
-Please see the models used in this merge (links below in the "formula" section ) for more information on 
-what they "bring" to this merged model.
-
 A NEO CLASS V2 version will be uploaded in a separate repo.
 
 <b>Optional Enhancement:</B>