Update README.md

README.md

@@ -9,14 +9,14 @@ tags:
   - not-for-all-audiences
   - merge
 ---
-# DarkSapling-7B-v1.1
+# DarkSapling-7B-v2.0
 
-![image/png](https://huggingface.co/TeeZee/DarkSapling-7B-v1.1/resolve/main/DarkSapling-7B-v1.1.jpg)
+![image/png](https://huggingface.co/TeeZee/DarkSapling-7B-v2.0/resolve/main/DarkSapling-7B-v2.0.jpg)
 
 
 ## Model Details
 
-- A result of 4 models merge.
+- A result of 4 models merge. DARE TIES method was used this time so resulting model better preserves characteristics of all included models than v1.x.
 - models used for merge:
   [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
   [KoboldAI/Mistral-7B-Holodeck-1](https://huggingface.co/KoboldAI/Mistral-7B-Holodeck-1)
@@ -29,6 +29,7 @@ tags:
 ## Results
 
 - a little different than version v1.0, more romantic and empathetic.
+- smarter than versions 1.1 and 1.2.
 - best for one-on-one ERP.
 - produces SFW nad NSFW content without issues, switches context seamlessly.
 - sticks to character card