Update README.md: clarify this is an attention implementation, not a trained model

README.md

@@ -1,6 +1,6 @@
 # DeepSeek Multi-Latent Attention
 
-A PyTorch implementation of the Multi-Latent Attention (MLA) mechanism introduced in the DeepSeek-V2 paper. MLA significantly reduces KV cache for efficient inference while maintaining model performance through its innovative architecture.
+This repository provides a PyTorch implementation of the Multi-Latent Attention (MLA) mechanism introduced in the DeepSeek-V2 paper. **This is not a trained model, but rather a modular attention implementation** that significantly reduces KV cache for efficient inference while maintaining model performance through its innovative architecture. It can be used as a drop-in attention module in transformer architectures.
 
 ## Key Features