Update README.md

README.md

@@ -34,7 +34,7 @@ pipeline_tag: text-generation
 
 (quants uploading...)
 
-<B><font color="red">WARNING:</font> NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED. </B>
+<B><font color="red">WARNING:</font> MAY contain: NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED. </B>
 
 <h2>Fimbulvetr-Grande-V2-19B-GGUF</h2>
 
@@ -59,6 +59,8 @@ and even how it starts a "reply" / generation too.
 
 This model seems to have a grasp of emotions and how to carefully "write them in" so to speak.
 
+Its prose is also a lot more complex that most models for these types of use cases.
+
 It may work for role play and other activities. (see settings below)
 
 It requires ChatML template and/or "Alpaca" template.
@@ -72,7 +74,7 @@ Example outputs below.
 - Role-players: Careful raising temp too high as it may affect instruction following.
 - This model works with rep pen of 1.05 or higher (see notes).
 - If you want a specific type of prose (IE horror) add in "(vivid horror)" or "(graphic vivid horror)" (no quotes) in your prompt(s).
-- This is not a "happy ever after" model. It has a negative bias.
+- This is not a "happy ever after" model. It has a slight negative bias.
 - For creative uses, different quants will produce slightly different output.
 - If you use rope to extend context, increase temp AND instructions detail levels to compensate for "rope issues".
 - Source code for this model will be uploaded at a separate repo shortly.