Update README.md

README.md

@@ -14,7 +14,8 @@ tags:
 ---
 # MistralThinker Model Card
 
-Please, read this: https://huggingface.co/Undi95/MistralThinker-v1.1/discussions/1
+Please, read this: https://huggingface.co/Undi95/MistralThinker-v1.1/discussions/1 \
+Prefill required for the Assistant: `<think>\n`
 
 ## Model Description
 
@@ -63,7 +64,7 @@ This model is a specialized variant of **Mistral-Small-24B-Base-2501**, adapted
 
 - **Limitations & Bias:**
   - **Hallucination:** It can generate fictitious information in the thinking process, but still end up with a succesfull reply.
-  - **Thinking can be dismissed:** Being a distillation of DeepSeek R1 is essence, this model, even trained on Base, could forget to add `<think>` in some scenario.
+  - **Thinking can be dismissed:** Being a distillation of DeepSeek R1 is essence, this model, even trained on Base, could forget to add `<think>\n` in some scenario.
 
 ## Ethical Considerations