Update README.md

README.md

@@ -30,11 +30,11 @@ Entire dataset was trained on 4 x A100 80GB. Axolotl codebase was used for train
 
 **GGUF & Exllama**
 
-GGUF: TBA
-
-Exllama V2: TBA
+GGUF: [Link](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF)
 
+Exllama V2: [Link](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-exl2)
 
+Special Thanks to [Bartowski](https://huggingface.co/bartowski) for quantizing this model.
 
  
 **Example Prompt:**