Update README.md

README.md

@@ -13,6 +13,14 @@ She will not be involved in any kind of role play.
 **Training:**
 Entire dataset was trained on Azure 4 x A100 80GB. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
 
+**GPTQ & GGML**
+
+GPTQ: [TheBloke](https://huggingface.co/TheBloke/Scarlett-7B-GPTQ)
+
+GGML: [TheBloke](https://huggingface.co/TheBloke/Scarlett-7B-GGML)
+
+Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for guiding me and making these models available. 
+
 
 **Example Prompt:**
 ```