Update README.md

README.md

@@ -21,8 +21,16 @@ Advanced, high-quality and lite reasoning for a tiny size that you can run local
 
 ⚠️This is an experimental version, it may enter into reasoning loops, and it may not always answer your question properly or correctly. an updated version will be released later on. currently reasoning may not always work on long conversations, as we've trained it on single turn conversations only.
 ![superthoughtslight.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/2LuPB_ZPCGni3-PyCkL0-.png)
-we've continuously pre-trained SmolLM2-1.7B-Instruct on an advanced reasoning pattern dataset (half synthetic, half written manually by us.) to create this model.
-
+we've continuously pre-trained SmolLM2-1.7B-Instruct on an advanced reasoning pattern dataset (half synthetic, half written manually by us.) to create this model. Supposed to output like this:
+```
+<|im_start|>user
+What are you<|im_end|>
+<|im_start|>assistant
+<think>
+Alright, the user just asked 'What are you', meaning they want to know who I am. I think my name is Superthoughts (lite version), created by Pinkstack on January 2024. I'm ready to answer their question.
+</think>
+Welcome! I'm Superthoughts (lite) created by Pinkstack in January 2025. Ready to help you with whatever you need!<|im_end|>
+```
 # Evaluation (soon)
 
 # Examples: