Update README.md

README.md

@@ -50,8 +50,9 @@ Because pain is fun, and persistence in design iteration is the only way forward
 --Finalized Logic and Creativity Segments (MK2):
 
 
-So after a few key meetings with our top teams of memegineers we drafted Thorns MK2, which was prompty fast tracked for production by the Roko's Basilisk Shadow Council.
-Also none of that shit happened, I just redid everything like this:
+After a few key meetings with our top teams of memegineers we drafted Thorns MK2, which was prompty fast tracked for production by the Roko's Basilisk Shadow Council.
+
+..Actually I just redid the merge like this:
 
 
 -Model Merge Ensemble Key-
@@ -59,32 +60,42 @@ Also none of that shit happened, I just redid everything like this:
 ({({NousHermes+Chronos}[Kimiko])+({Platupus+AiroborosM2.0}[Janine])}{Holodeck[LIMA RP]})
 
 
+## Findings:
+
+-Strategically fusing LoRAs to models that stand to gain the most from them and then merging the result into the ensemble is exceptionally effective.
+
+
+-Stacking the exact same LoRAs onto one model then merging that into the ensemble results in noisy garbage.
+
 
 ## Language Models and LoRAs Used Credits:
 
-manticore-30b-chat-pyg-alpha [Epoch0.4] by openaccess-ai-collective
 
-https://huggingface.co/openaccess-ai-collective/manticore-30b-chat-pyg-alpha
+All models and adapters used are LLaMAv2-13B.
+
+# Models:
+
+Nous-Hermes
+
+Chronos
+
+Platypus
 
-SuperCOT-LoRA [30B] by kaiokendev
+Airoboros
 
-https://huggingface.co/kaiokendev/SuperCOT-LoRA
+Holodeck
 
-Storytelling-LLaMa-LoRA [30B, Version 2] by GamerUnTouch
+# Adapters:
 
-https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs
+Kimiko
 
-SuperHOT Prototype [30b 8k ctx] by kaiokendev
+Janine
 
-https://huggingface.co/kaiokendev/SuperHOT-LoRA-prototype
+LIMA RP
 
-ChanSung's GPT4-Alpaca-LoRA
-https://huggingface.co/chansung/gpt4-alpaca-lora-30b
 
-Neko-Institute-of-Science's Vicuna Unlocked LoRA (Checkpoint 46080)
-https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA
+Also thanks to Meta for LLaMAv2 and deciding to allow the research community at large to benefit from their incredible work.
 
-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