Update README.md

README.md

@@ -32,9 +32,11 @@ tags:
 pipeline_tag: text-generation
 ---
 
+(quants uploading in progress...)
+
 <B><font color="red">WARNING:</font> MAY contain: NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED. </B>
 
-<h2>L2-Psyonic-Cetacean-Ultra-Colossal-32B (Q4_K_M - see quants note below)</h2>
+<h2>L2-Psyonic-Cetacean-Ultra-Colossal-32B</h2>
 
 <img src="pcuc.jpg" style="float:right; width:300px; height:300px; padding:10px;">
 
@@ -165,14 +167,6 @@ show just what "old" Llama2s can do.
 
 You can see/download other Brainstorm models by clicking on the Brainstorm Collection on the right of your screen.
 
-<B>Quants:</B>
-
-Currently the only quant uploaded is Q4_K_M. 
-
-If you would like other quants uploaded, please open a "ticket" via the "Community Tab".
-
-Please note that more quants will be uploaded shortly.
-
 <B>Settings, Quants and Critical Operations Notes:</b>
 
 This model has been modified ("Brainstorm") to alter prose output, and generally outputs longer text than average. 
@@ -202,6 +196,10 @@ You can also set a "hard stop" - maximum tokens generation - too to address lowe
 
 Longer prompts vastly increase the quality of the model's output.
 
+Quants:
+
+Please note for Q2k quant you may need to raise rep pen and lower temp to account for quality loss at this quant level.
+
 <B>Model Template:</B>
 
 This is a custom model, and requires ChatML OR Alpaca OR Vicuna template, but may work with other template(s) and has maximum context of 4k / 4096.