Learn/Course 15
Transformers · weeks 20

Foundation-model lifecycle

A private support assistant must answer from evidence and resist manipulation.

Opening production brief

A measurable problem, before a model.

Users

Operators, product owners, and people affected by the foundation models decision.

Data

build vs buy, RAG vs tuning, provenance, decontamination with version, owner, event time, and availability contracts.

Constraints

A private support assistant must answer from evidence and resist manipulation. Every solution must state latency, cost, capacity, and fallback limits.

Success

Offline evidence plus a deployable resolution: A grounded system design spanning adaptation, RAG, evaluation, and safety.

CHAPTER 1

Frame and baseline

Turn the production problem into explicit data, metric, and baseline contracts.

  1. 01

    Prompt, retrieve, adapt, train, or buy?

    Use prompt, retrieve, adapt, train, or buy? to move the foundation models production brief toward a defensible release.

    65–90 min · checkpoint · deterministic lab
  2. 02

    Corpus provenance, mixtures, and decontamination

    Use corpus provenance, mixtures, and decontamination to move the foundation models production brief toward a defensible release.

    65–90 min · checkpoint · deterministic lab
CHAPTER 2

Build and stress

Formalize the machinery, test counterexamples, and expose system limits.

  1. 03

    Pretraining objectives, scaling, and checkpoints

    Use pretraining objectives, scaling, and checkpoints to move the foundation models production brief toward a defensible release.

    65–90 min · checkpoint · deterministic lab
  2. 04

    SFT, preference optimization, safety, and tools

    Use sft, preference optimization, safety, and tools to move the foundation models production brief toward a defensible release.

    65–90 min · checkpoint · deterministic lab
CHAPTER 3

Resolve and operate

Join model behavior to architecture, observability, rollout, and rollback.

  1. 05

    Evals, model cards, feedback, and reproducibility

    Use evals, model cards, feedback, and reproducibility to move the foundation models production brief toward a defensible release.

    65–90 min · checkpoint · deterministic lab
  2. HW

    Domain adaptation release package

    Compare prompt, retrieval, and optional PEFT approaches under one provenance and evaluation contract.

    Rubric · staged hints · reference resolution
Prerequisite guidance

1 concepts make this faster.

Prerequisites are guidance, never hard gates.

C14Transformer from scratchTokenizer, attention, RoPE, residual stack, training loop, generation, and KV cache.
Ready to work the problem?

Prompt, retrieve, adapt, train, or buy?

Start lesson 01