Update README.md

README.md

@@ -29,6 +29,9 @@ pip install torch transformers accelerate
 
 ## Quick Start
 
+> [!NOTE]
+> We recommend setting `enable_thinking=False` when using the model to ensure stable behavior and reproducible results.
+
 ```python
 import math
 import copy
@@ -232,7 +235,7 @@ prompts = [
     ],
 ]
 
-encoded = [tokenizer.apply_chat_template(m, add_generation_prompt=True, tokenize=True) for m in prompts]
+encoded = [tokenizer.apply_chat_template(m, add_generation_prompt=True, tokenize=True, enable_thinking=False) for m in prompts]
 prompt_lens = [len(e) for e in encoded]
 max_len = max(prompt_lens)
 pad_id = tokenizer.pad_token_id