Fix typo

README.md

@@ -24,7 +24,7 @@ This model is released under the [NVIDIA Open Model License Agreement](https://d
 
 ## Model Architecture
 
-Llama-3.1-Minitron-4B-Width-Base uses a model embedding size of 4096, 32 attention heads, MLP intermediate dimension of 14336, with 32 layers in total. Additionally, it uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE). 
+Llama-3.1-Minitron-4B-Width-Base uses a model embedding size of 3072, 32 attention heads, MLP intermediate dimension of 9216, with 32 layers in total. Additionally, it uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE). 
 
 **Architecture Type:** Transformer Decoder (Auto-Regressive Language Model)