Update README.md

README.md

@@ -9,11 +9,23 @@ tags:
 - gptq
 ---
 
-13B-Chimera = ((MantiCore3E+VicunaCocktail)+[SuperCOT+[StorytellingV2+(SuperHOTProtoType-8192ctx+Metharme)]])
-[] = applied as LoRA
-() = combined as composite model
+### 13B-Chimera
 
-Credits:
+
+[] = applied as LoRA to a composite model | () = combined as composite models
+
+((MantiCore3E+VicunaCocktail)+[SuperCOT+[StorytellingV2+(SuperHOTProtoType-8192ctx+Metharme)]])
+
+This model is the result of an experimental use of LoRAs on language models and model merges that are not the base HuggingFace-format LLaMA model they were intended for.
+
+This experiment is to determine:
+
+Outcomes of applying Lower Order Rank Adapters in unconventional ways.
+Determine if applying LoRAs and stacking LoRAs onto merged models bypasses the zero-sum result of weight-sum model merging.
+
+The desired result is to additively apply desired features without paradoxically watering down a model's effective behavior.
+
+Language Models and LoRAs Used Credits:
 
 manticore-13b [Epoch3] by openaccess-ai-collective
 
@@ -39,6 +51,8 @@ Metharme 13b by PygmalionAI
 
 https://huggingface.co/PygmalionAI/metharme-13b
 
+Also thanks to Meta for LLaMA.
+
 Each model and LoRA was hand picked and considered for what it could contribute to this ensemble.
 Thanks to each and every one of you for your incredible work developing some of the best things
-I have seen come out of this community.
+to come out of this community.