Update README.md

README.md

@@ -23,7 +23,7 @@ While using with transformers you can only use the 15M variant for now.
 
 NGen 2 is an advanced Transformer model training pipeline that supports multiple model variants. It ranges from a **nano** variant (approximately 120M parameters) to a **foundational** variant (approximately 1B parameters). The pipeline incorporates modern architectural improvements such as rotary positional embeddings, RMSNorm, and GEGLU activations to boost performance and training efficiency.
 
-> **Note:** Although NGen 3 is designed to train a 1B-parameter model, its advanced architecture pushes its performance closer to that of much larger models.
+> **Note:** Although NGen 2 is designed to train a 1B-parameter model, its advanced architecture pushes its performance closer to that of much larger models. Try using NGen3 for performance.