build-gpt

8 problems

• Token embedding lookupEasy
• Sinusoidal positional encodingEasy
• Scaled dot-product self-attentionMedium
• Causal mask: build + applyEasy
• Multi-head split + combineMedium
• Multi-Head Attention (full layer)Medium
• LayerNorm forwardEasy
• Transformer block forward (pre-LN, residual)Hard