Update README.md

README.md

@@ -14,7 +14,7 @@ Fully intentional. `WizardLM-2-8x22B` is smart by itself but its used vocabulary
 ## Prompting
 
 - Use the templates in [Quant-Cartel/Recommended-Settings](https://huggingface.co/Quant-Cartel/Recommended-Settings) under the `SorcererLM`-folder.
-- Or Vicuna 1.1 and a sane context template. It's sensitive to samplers, I'd recommend Temperature 1, MinP 0.05 and a dash of DRY but YMMV.
+- Or Vicuna 1.1 and a sane context template. It's somewhat sensitive to samplers, I'd recommend Temperature 1, MinP 0.05 and a dash of DRY but YMMV. Shorter prompts seem to work better, too.
 
 ## Acknowledgments