Update README.md

README.md

@@ -34,7 +34,7 @@ tags:
 pipeline_tag: text-generation
 ---
 
-<B><font color="red">WARNING:</font> NSFW. Vivid prose. INTENSE. Visceral Details. Violence. HORROR. GORE. Swearing. UNCENSORED... humor, romance, fun. </B>
+<B><font color="red">WARNING:</font> NSFW. Vivid prose. INTENSE. Visceral Details. Light HORROR. Swearing. UNCENSORED... humor, romance, fun. </B>
 
 <h2>Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF</h2>
 
@@ -70,12 +70,11 @@ Several outputs below, including 2, 4 and 8 experts used.
 - Role-players: Careful raising temp too high as it may affect instruction following.
 - This model works with rep pen of 1 or higher, 1.02+ recommended.
 - If you want a specific type of prose (IE horror) add in "(vivid horror)" or "(graphic vivid horror)" (no quotes) in your prompt(s).
-- A lot of GPTisms have been removed. There are still a few however - errrrr.
-- This is not a "happy ever after" model. It has a negative bias.
-- Output length will vary however this model prefers shortly outputs unless you state the size.
+- A lot of GPTisms have been removed. There are still a few however - errrrr. Higher "temps" will help with this issue.
+- This is not a "happy ever after" model but it is also not "horror". It has a light negative bias.
+- Output length will vary however this model prefers slightly longer outputs unless you state the size.
 - For creative uses, different quants will produce slightly different output.
 - Due to the high stability and compressed nature of this model, all quants will operate at above average levels.
-- If you use rope to extend context, increase temp AND instructions detail levels to compensate for "rope issues".
 - Source code for this model and Imatrix GGUFs versions will be uploaded shortly at separate repos.
 
 <B>Meet the Team: Mixture of Experts Models</b>