Update README.md

README.md

@@ -229,7 +229,7 @@ print(tokenizer.apply_chat_template(chat, tokenize=False))
   ```
 </details>
 
-## Helpful usage tips
+## Prompting strategies
 
 <details>
   <summary>
@@ -624,4 +624,20 @@ print(tokenizer.apply_chat_template(chat, tokenize=False))
   ```
 
   In other words, write the first chapter, then use a summarization prompt for it, then include the summary in the next chapter's prompt.
+</details>
+
+<details>
+  <summary>
+    <b>Boolean questions</b>
+    <br>
+    For content filtering and other use-cases which only require a true/false response.
+  </summary>
+
+  The prompts in the fine-tuning dataset are formatted as follows:
+  
+  ```text
+  True or false - {statement}
+  ```
+
+  The model will then, theoretically, respond with only a single word.
 </details>