- scaled dot-product attention
- multi-head attention
- causal masks
- KV cache
Deep Learning / transformers
Transformers
Tokens, embeddings, positional encoding, self-attention, Q/K/V, masks, encoders, decoders, generation, and KV cache.
shellstatic shell now
Self-attention playground showing tokens, Q/K/V, masks, heads, positional encoding, and KV cache.
- What is the core job of "Transformers"?
- Which common mistake would break a production implementation of this topic?
- Which inputs or limits must be validated before the interactive feature ships?
- What is the smallest test that proves the future implementation behaves correctly?
- When does this module really need backend compute, and when is a UI simulation enough?
- 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.