Update README.md

README.md

@@ -63,7 +63,7 @@ The model shows improvements in **instruction understanding and task completion*
 
 ## Technical summary
 
-- Architecture: LLaMA 3.2, 32 transformer layers, 8192 hidden size, 32 heads
+- Architecture: LLaMA 3.2, 28 transformer layers, 3072 hidden size, 24 heads
 - Sequence length: 4096 tokens
 - Training hardware: 8× A100 80GB GPUs
 - Continual pretraining corpus: 531 M Basque words (ZelaiHandi) + 300 M English tokens (FineWeb subset)