Update README.md

README.md

@@ -43,7 +43,7 @@ tokenizer_source: base
 name: Qwen3-8B-fusion
 ```
 ## *Step2: Merge High-Performance Reasoning Models with Hybrid Models*
-- *Maximize the proportion of reasoning models and output the merged model before the \no_think tag becomes ineffective.*
+- *Maximize the proportion of reasoning models on the premise that the \no_think tag remains effective.*
 ```yaml
 models:
   - model: Qwen/Qwen3-8B