Update README.md

README.md

@@ -22,7 +22,7 @@ datasets:
 **Note**
 With the release of Meta's LLaMA 3.2 1B, this model got outperformed significantly. Since we don't have a lot of GPU power or money to furter train this or another model to even come close to Meta's models, we recommend you to use theirs over ours.
 
-We, XeTute, introduce AURORA V1.0 - a humerous, efficient, smart(for its size) and unbiased(because of too low parameter count, consider it a virtual child with a bunch of knowledge =)) Language Model.
+We, XeTute, introduce AURORA V1.0 - a humerous, efficient, smart(for its size) and mostly unbiased(consider it a virtual child with a bunch of knowledge =), it didn't fully pick up biases tokens because we of too low learning rate) Language Model.
 
 **Intended usecases:**
 - Next-Word prediction for mobile devices: