Update README.md

README.md

@@ -26,6 +26,14 @@ base_model: arcee-ai/AFM-4.5B
 **Original model**: [AFM-4.5B](https://huggingface.co/arcee-ai/AFM-4.5B)<br>
 **GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b6014](https://github.com/ggerganov/llama.cpp/releases/tag/b6014)<br>
 
+## Recommended settings
+
+* temperature: 0.5
+* top_k: 50
+* top_p: 0.95
+* repeat_penalty: 1.1
+* min_p: 0.05
+
 ## Special thanks
 
 🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.