Update README.md

README.md

@@ -3,7 +3,12 @@ license: apache-2.0
 ---
 GGUF-IQ-Imatrix quants for NLPark/Test1_SLIDE as requested in [#28](https://huggingface.co/Lewdiculous/Model-Requests/discussions/28).
 
-"Due to the poor performance of Test0 in Asian Languages, we trained a new preview1 model."
+> [!WARNING]
+> Recommended presets [here](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
+> Use the latest version of KoboldCpp. **Use the provided presets.** <br>
+> This is all still highly experimental, modified configs were used to avoid the tokenizer issues.
+
+"Due to the poor performance of Test0 in Asian Languages, we trained a new preview model."
 
 "It's a merge of https://huggingface.co/NLPark/Test1_SLIDE , https://huggingface.co/vicgalle/Configurable-Llama-3-8B-v0.3"