Update README.md

README.md

@@ -169,7 +169,7 @@ Developers should apply responsible AI best practices and are responsible for en
 
 ### Model
 
-* Architecture: Phi-3 Small-128K-Instruct has 7B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.
+* Architecture: Phi-3 Small-128K-Instruct has 7B parameters and is a dense decoder-only Transformer model with alternating dense and blocksparse attentions. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.
 * Inputs: Text. It is best suited for prompts using chat format.
 * Context length: 128K tokens
 * GPUs: 1024 H100-80G
@@ -248,7 +248,7 @@ We take a closer look at different categories across 80 public benchmark dataset
 * [Triton](https://github.com/openai/triton)
 
 ## Hardware
-Note that by default, the Phi-3-Small model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:
+Note that by default, the Phi-3-Small model uses flash attention 2 and Triton blocksparse attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:
 * NVIDIA A100
 * NVIDIA A6000
 * NVIDIA H100