Update README.md

README.md

@@ -134,6 +134,8 @@ Finally, Juliet spoke up. “Maybe we could run a layer interleaving model merge
 ...
 </details>
 
+Sections that are the token-count equivalent of a few paragraphs in length tend to work best.
+
 Talosian is _not_ a user <-> assistant chat-formatted model. All prompting should be done as completions (for example, in text-generation-webui's Notebook mode.)
 
 ## Generation Parameters