Update README.md

README.md

@@ -134,10 +134,10 @@ pip install llama-cpp-python huggingface_hub
 ### Key Parameters
 - `n_ctx`: Context window size (default: 2048)
 - `n_threads`: Number of CPU threads to use (adjust based on your hardware)
-- `temperature`: Controls randomness (0.7 recommended)
-- `top_p`: Nucleus sampling parameter (0.9 recommended)
-- `top_k`: Limits vocabulary choices (40 recommended)
-- `repeat_penalty`: Prevents repetition (1.1 recommended)
+- `temperature`: Controls randomness
+- `top_p`: Nucleus sampling parameter
+- `top_k`: Limits vocabulary choices
+- `repeat_penalty`: Prevents repetition
 - `max_tokens`: Maximum length of response (128 default, increase for longer answers)
 
 ### Example Usage