Update README.md

README.md

@@ -14,4 +14,25 @@ tags:
 Astral 14B is the largest model in the Astral family. It was fine-tuned from Qwen3 14b on LucidityAI/Astral-Post-Training-Dataset. 
 
 
-As with usual Qwen3 models, reasoning can be toggled through the usage of ```/no_think``` or not.
+As with usual Qwen3 models, reasoning can be toggled through the usage of ```/no_think``` or not.
+
+
+### Example Prompt (ChatML Format):
+
+```xml
+<|im_start|>user
+What is the capital of France?
+<|im_end|>
+<|im_start|>assistant
+<think>
+
+```
+
+---
+
+##  Important Notes
+
+- This is a **preview release**. Performance may vary across edge cases or non-standard inputs.
+- For production applications, please wait for the official release.
+
+---