typo fix

README.md

@@ -309,8 +309,8 @@ output = tokenizer.batch_decode(output)
 print(output)
 ```
 
-**Model Architeture:** 
-Granite-3.0-2B-Instruct is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA and RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embbeddings.
+**Model Architecture:** 
+Granite-3.0-2B-Instruct is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA and RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embeddings.
 
 | Model                        | 2B Dense     | 8B Dense | 1B MoE   | 3B MoE   |
 | :--------                    | :--------    | :--------| :--------| :--------|