Update README.md

README.md

@@ -22,6 +22,21 @@ tags:
 This model was converted to GGUF format from [`DavidAU/Llama-3.1-DeepHermes-R1-Reasoning-8B-DarkIdol-Instruct-1.2-Uncensored`](https://huggingface.co/DavidAU/Llama-3.1-DeepHermes-R1-Reasoning-8B-DarkIdol-Instruct-1.2-Uncensored) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/DavidAU/Llama-3.1-DeepHermes-R1-Reasoning-8B-DarkIdol-Instruct-1.2-Uncensored) for more details on the model.
 
+---
+This model is uncensored DeepHermes reasoning/thinking (Llama 3.1) coupled with DarkIdol's insanely strong uncensored fine tune.
+
+
+This model retains DarkIdols uncensored "profile".
+
+
+Also this model can be run at any temp, and reasoning will occur. 
+
+
+This is a Llama 3.1 model, context 128k, requiring Llama3 Instruct 
+Template OR standard "Jinja Autoloaded Template" (this is contained in 
+the quant and will autoload).
+
+---
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)