Update README.md

README.md

@@ -17,7 +17,7 @@ Frank aims to push boundaries and encourage candid conversations. With Frank you
 It is trained on around 150000 set of conversations. Each set having 10~15 conversations. 
 I will not release this data.
 
-This is Fully Finetuned Model. Quantize models will be available soon.
+This is Fully Finetuned Model.
 
 **Warning**
 
@@ -30,9 +30,11 @@ Entire dataset was trained on 4 x A100 80GB. For 3 epoch, training took around 6
 
 **GGUF & Exllama**
 
-GGUF: TBA
+GGUF: [Link](https://huggingface.co/bartowski/Uncensored-Frank-Llama-3-8B-GGUF)
 
-Exllama V2: TBA
+Exllama V2: [Link](https://huggingface.co/bartowski/Uncensored-Frank-Llama-3-8B-exl2)
+
+Special Thanks to [Bartowski](https://huggingface.co/bartowski) for quantizing this model.
 
 **Example Prompt:**