Qwen
/

Text Generation
Transformers
Safetensors
qwen3_moe
conversational
yangapku commited on
Commit
67b0e0c
·
verified ·
1 Parent(s): ecaea67

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -208,7 +208,7 @@ if __name__ == "__main__":
208
  print(f"Bot: {response_3}")
209
  ```
210
 
211
- > **Note**
212
  > For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
213
  > When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
214
 
 
208
  print(f"Bot: {response_3}")
209
  ```
210
 
211
+ > [!NOTE]
212
  > For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
213
  > When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
214