Module Reference

Checklist: shapes, objective, masks, tokenizer, data version, seed policy, ablations, target-hardware profile, capability boundary, reproduction command, and AI-use declaration.

Evidence and review

Key terms: autodiff, residual stream, embedding, attention, causal mask, PEFT, quantization, KV cache. Claims must trace to versioned code and artifacts. Screenshots, unexplained generated prose, and a single favorable run do not pass.

Oral defense

Explain the mechanism, identify the most dangerous assumption, interpret one failure from raw evidence, and name the condition that would reverse your decision.

Source backbone

Use Dive into Deep Learning, PyTorch documentation, primary papers, and Designing Data-Intensive Applications selectively.