Update README.md

README.md

@@ -13,8 +13,11 @@ license: llama2
 <h2 style="text-align: center">Experimental Frankenmerge Model</h2>
 
 
-## GGUF
-[GGUF version here](https://huggingface.co/tavtav/Rose-20B-GGUF)
+## Other Formats
+[GGUF](https://huggingface.co/TheBloke/Rose-20B-GGUF)
+[GPTQ](https://huggingface.co/TheBloke/Rose-20B-GPTQ)
+[AWQ](https://huggingface.co/TheBloke/Rose-20B-AWQ)
+[exl2](https://huggingface.co/royallab/Rose-20B-exl2)
 
 ## Model Details
 A Frankenmerge with [Thorns-13B](https://huggingface.co/CalderaAI/13B-Thorns-l2) by CalderaAI and [Noromaid-13-v0.1.1](https://huggingface.co/NeverSleep/Noromaid-13b-v0.1.1) by NeverSleep (IkariDev and Undi). This recipe was proposed by Trappu and the layer distribution recipe was made by Undi. I thank them for sharing their knowledge with me. This model should be very good at any roleplay scenarios. I called the model "Rose" because it was a fitting name for a "thorny maid". 
@@ -31,6 +34,8 @@ Below is an instruction that describes a task. Write a response that appropriate
 
 Feel free to share any other prompts that works. This model is very robust. 
 
+**Warning: This model uses significantly more VRAM due to the KV cache increase resulting in more VRAM required for the context window.**
+
 ## Justification for its Existence
 Potential base model for finetune experiments using our dataset to create Pygmalion-20B. Due to the already high capabilities, adding our dataset will mesh well with how the model performs. 
 Potential experimentation with merging with other 20B Frankenmerge models.