Update README.md

README.md

@@ -40,6 +40,11 @@ This version establishes new state-of-the-art (SOTA) results among open models u
 
 ## <span id="Inference">Quickstart</span>
 
+For inference hyperparameters, we recommend the following settings:
+* Temperature: 0.6
+* Top-p (nucleus sampling): 0.95
+* Repeat penalty: 1.0
+
 For the chat scenario:
 ```
 from transformers import AutoModelForCausalLM, AutoTokenizer