Skip to visualization
visualization / Modern Block

minGPT · Modern Transformer Block

RMSNorm and SwiGLU
◆ MODERN BLOCK
T=8
iRMSNorm + SwiGLU

🔍 Variable Inspector

click any code line
Click a code line to inspect its variables.
About this lesson
Quick answer

What Modern Transformer Block explains

Compare the classic LayerNorm and GELU block with the RMSNorm and SwiGLU design used by many modern decoder models.

Key concepts

Primary research

RMSNorm 2019 · SwiGLU 2020