Update README.md

README.md

@@ -17,6 +17,10 @@ tags:
 
 **This is another King-Breed from Juanako.AI**
 
+**We have Identified some Problems with regular Quants** [use these models to play with Xaberius-34B and harness its power in full](https://huggingface.co/models?search=xaberius%20lonestriker).
+**Unfortunately we were not able to use any of TheBloke models, seems there is some undesired results out of it.**
+
+
 Introducing THE MODEL: **XABERIUS 34B v1-BETA** an *experimental* 34B LLaMa-Yi-34B based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.
 
 Timeline:
@@ -109,4 +113,5 @@ Answer：
 }
 ```
 
-Special thanks to @TheBloke & @bartowski for converting the models and their support to the community. Thank you!
+**Thanks to LoneStriker for his ExLLama2 models of high quality that works properly.**
+**Enormous Ku2 to Yi-34b Team for the outstanding model, UNA is only as good as its pre-trained model** THANK YOU!