Deep Learning / transformers

Transformers

Tokens, embeddings, positional encoding, self-attention, Q/K/V, masks, encoders, decoders, generation, and KV cache.

shellstatic shell now
Focus
  • scaled dot-product attention
  • multi-head attention
  • causal masks
  • KV cache
Future feature idea

Self-attention playground showing tokens, Q/K/V, masks, heads, positional encoding, and KV cache.

Self-check
  1. What is the core job of "Transformers"?
  2. Which common mistake would break a production implementation of this topic?
  3. Which inputs or limits must be validated before the interactive feature ships?
  4. What is the smallest test that proves the future implementation behaves correctly?
  5. When does this module really need backend compute, and when is a UI simulation enough?
Implementation notes
  • Start with one focused feature, not a full course inside one page.
  • All public inputs must be typed, bounded, and covered by reject-case tests.
  • If a model, dataset, or job is added, document source, license, limits, and fallback.
  • The interaction must explain the topic rather than serve as decoration.