Update README.md

README.md

@@ -19,7 +19,7 @@ Introducing DeepSeek LLM, an advanced language model comprising 67 billion param
 
   
 ### 2. Model Summary
-deepseek-llm-67b-base is a 67B parameter model with Multi-Head Attention trained on 2 trillion tokens from scratch.
+deepseek-llm-67b-base is a 67B parameter model with Grouped-Query Attention trained on 2 trillion tokens from scratch.
 - **Home Page:** [DeepSeek](https://deepseek.com/)
 - **Repository:** [deepseek-ai/deepseek-LLM](https://github.com/deepseek-ai/deepseek-LLM)
 - **Chat With DeepSeek LLM:** [DeepSeek-LLM](https://chat.deepseek.com/)