Update README.md

README.md

@@ -22,6 +22,15 @@ This data was further refined and fine tuned. Besides this further synthetic con
 **Training:**
 Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 22 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
 
+**GPTQ GGML & AWQ**
+
+GPTQ: [TheBloke](https://huggingface.co/TheBloke/Uncensored-Frank-7B-GPTQ)
+
+GGUF: [TheBloke](https://huggingface.co/TheBloke/Uncensored-Frank-7B-GGUF)
+
+AWQ: [TheBloke](https://huggingface.co/TheBloke/Uncensored-Frank-7B-AWQ)
+
+Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for making these models available. 
 
 **Example Prompt:**
 ```