Update README.md

README.md

@@ -38,8 +38,6 @@ tags:
 - mergekit
 pipeline_tag: text-generation
 ---
-(quants uploading...)
-
 <h3><font color="green"> L3-Grand-STORY-16.5B Ultra Quality - A triple model, triple step merge at Full Precision F32. Imatrix Neo Class 2. </font></h3>
 
 <B><font color="red">WARNING:</font> NSFW. Ultra Detailed. Graphic HORROR, VIOLENCE. Extreme swearing. UNCENSORED. SMART.</B>
@@ -153,6 +151,18 @@ Here is the standard LLAMA3 template:
 
 Please note that this model will NOT reject any request.
 
+<B>Known Issue(s):</B>
+
+I noticed a few runs with imat version with "self created words" (although not as strong as Grand Horror 16.5B). 
+The non-imat version of Grand Story has a lot less "misspellings". This is in part due to the Imatrix Neo Dataset 
+being extraordinarily strong. It brings out the best and sometimes some of the worse in a model. In other words it highlights both.
+
+Regenerating the output will often fix this issue.
+
+X quants should also address this issue (controls level of Imatrix applied) which will be releasing shortly.
+
+These specialized quants will appear in a separate repo.
+
 <B>REGULAR QUANTS OF THIS MODEL: </b>
 
 [ https://huggingface.co/DavidAU/L3-SMB-Grand-STORY-F32-Ultra-Quality-16.5B-GGUF ]