Update README.md

README.md

@@ -78,10 +78,14 @@ This super merge captures the attibutes of all these top models and makes them e
 - Emotional connections.
 - Prose quality
 
-This super merge is also super stable, and runs with all parameters and settings.
+This super merge is also super stable (a hairs breath from Mistral Nemo's ppl), and runs with all parameters and settings.
 
 10 versions of this model will be released, this is release #1 - "part 1".
 
+<B>Kiss of Madness?</B>
+
+See the 2nd last example below, this is when the model earned its name.
+
 Usually I release one or two versions from the "best of the lot", however in this case all
 of the versions turned out so well - all with their own quirks and character - that I will be
 releasing all 10.
@@ -90,9 +94,7 @@ An additional series 2 and 3 will follow these 10 models as well.
 
 (examples generations below)
 
-Model may produce NSFW content : 
-
-Swearing, horror, graphic horror, distressing scenes, etc etc.
+Model may produce NSFW content : Swearing, horror, graphic horror, distressing scenes, etc etc.
 
 This model has an INTENSE action bias, with a knack for cliffhangers and surprises.
 
@@ -217,7 +219,45 @@ Models used:
 
 [ https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9 ]
 
+This is a four step merge (3 pass-throughs => "Fine-Tune" / "Instruct") then "mated" using "DARE-TIES".
+
+In involves these three models:
+
+[ https://huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct-GGUF ]
+
+[ https://huggingface.co/DavidAU/MN-Magnum-v2.5-18.5B-kto-Story-Wizard-ED1-Instruct-GGUF ]
+
+[ https://huggingface.co/DavidAU/MN-Rocinante-18.5B-v1.1-Story-Wizard-ED1-Instruct-GGUF ]
+
+Combined as follows using "MERGEKIT":
+
+<PRE>
+
+  models:
+  - model: E:/MN-Rocinante-18.5B-v1.1-Instruct
+  - model: E:/MN-magnum-v2.5-12b-kto-Instruct
+    parameters:
+      weight: .6
+      density: .8
+  - model: E:/MN-18.5B-Celeste-V1.9-Instruct
+    parameters:
+      weight: .38
+      density: .6
+merge_method: dare_ties
+tokenizer_source: union
+base_model: E:/MN-Rocinante-18.5B-v1.1-Instruct
+dtype: bfloat16
+  
+</PRE>
+
+Special Notes:
+
+Due to how DARE-TIES works, everytime you run this merge you will get a slightly different model.
+This is due to "random" pruning method in "DARE-TIES".
+
+Mistral Nemo models used here seem acutely sensitive to this process.
 
+"tokenizer_source: union" is used so that multiple "templates" work and each fine tune uses one or two of the templates.
 
 <h3>EXAMPLES PROMPTS and OUTPUT:</h3>