Update README.md

README.md

@@ -8,7 +8,7 @@ tags:
 - 4x8B
 - 32 bit enhanced
 - float 32 quants
-- mistral MOE
+- LLama MOE
 - uncensored
 - creative
 - creative writing
@@ -37,13 +37,15 @@ tags:
 pipeline_tag: text-generation
 ---
 
+(quants uploading... examples to be added)
+
 <B><font color="red">WARNING:</font> NSFW. Vivid prose. INTENSE. Visceral Details. HORROR. Swearing. UNCENSORED... humor, romance, fun. </B>
 
 <h2>L3-Grand-Story-Darkness-MOE-4X8-24.9B-e32-GGUF</h2>
 
 <I><small> A float 32 high precision M.O.E model, quanted in float 32 with additional upgraded and augmented quants too. </small></i>
 
-<img src="dark-mv-32.jpg" style="float:right; width:300px; height:300px; padding:10px;">
+<img src="grand-story-dark.jpg" style="float:right; width:300px; height:300px; padding:10px;">
 
 It is a Llama3 model, max context of 8k (8192) using mixture of experts to combine FOUR top Llama3 8B 
 models into one massive powerhouse at 24.9B parameters (equal to 32B - 4 X 8 B).
@@ -345,4 +347,5 @@ if you engage more experts, as with more experts there is a more processing per
 
 <B><font color="red">WARNING:</font> NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED. </B>
 
----
+---
+