Update README.md

README.md

@@ -47,6 +47,24 @@ It requires Llama3 template and/or "Command-R" template.
 
 Example outputs below.
 
+<B>Model Notes:</B>
+
+- Detail, prose and fiction writing abilities are significantly increased vs L3 Instruct.
+- For more varied prose (sentence/paragraph/dialog) raise the temp and/or add more instructions in your prompt(s).
+- Role-players: Careful raising temp too high as it may affect instruction following.
+- This model works with rep pen of 1 or higher, 1.05+ 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.
+- 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 (Bfloat16), Float 32 master GGUFs (and source), and Imatrix GGUFs versions will be uploaded shortly at separate repos.
+
+Note the "float32" version of this model behaves VERY differently which is why it was not uploaded first.
+
+The Imatrix versions of this model have even lower perplexity then both this model and Llama3 Instruct and enhanced output.
+
 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.