Operators, product owners, and people affected by the transformer from scratch decision.
Transformers · weeks 17–19
Build a transformer from scratch
Domain autocomplete needs a model whose every component the team can explain.
Opening production brief
A measurable problem, before a model.
tokenization, embeddings, RoPE, QKV projections with version, owner, event time, and availability contracts.
Domain autocomplete needs a model whose every component the team can explain. Every solution must state latency, cost, capacity, and fallback limits.
Offline evidence plus a deployable resolution: Tokenizer, attention, RoPE, residual stack, training loop, generation, and KV cache.
Frame and baseline
Turn the production problem into explicit data, metric, and baseline contracts.
- 01↗
Text to tensors: tokenization, embeddings, position
Use text to tensors: tokenization, embeddings, position to move the transformer from scratch production brief toward a defensible release.
65–90 min · checkpoint · deterministic lab - 02↗
Scaled dot-product self-attention by hand
Use scaled dot-product self-attention by hand to move the transformer from scratch production brief toward a defensible release.
65–90 min · checkpoint · deterministic lab
Build and stress
Formalize the machinery, test counterexamples, and expose system limits.
- 03↗
Heads, norms, residuals, and MLPs
Use heads, norms, residuals, and mlps to move the transformer from scratch production brief toward a defensible release.
65–90 min · checkpoint · deterministic lab - 04↗
Train a causal language model
Use train a causal language model to move the transformer from scratch production brief toward a defensible release.
65–90 min · checkpoint · deterministic lab
Resolve and operate
Join model behavior to architecture, observability, rollout, and rollback.
- 05↗
Sampling, KV cache, and efficient generation
Use sampling, kv cache, and efficient generation to move the transformer from scratch production brief toward a defensible release.
65–90 min · checkpoint · deterministic lab - HW↗
Decoder-only transformer from scratch
Specify tokenizer, attention blocks, causal training, unit tests, sampling, and KV-cache parity without a transformer module.
Rubric · staged hints · reference resolution
Prerequisite guidance
3 concepts make this faster.
Prerequisites are guidance, never hard gates.