LLM Developer DocsLLM Docs

Loading the search index ...

↑ ↓ move, Enter open, Esc close

GitHub

Not in This Model

Techniques the code does not use, from the rows of the documentation contract confirmed absent.

Each technique below is absent from the code at the pinned commit. Some appear in the reference PDF as a contrast, a future upgrade or removed earlier work, and the PDF does not mention the others. None of them is something this project does.

This is the only page that describes them. Sources & Discrepancies may quote one where it reports what the PDF says. bun run verify:content fails if one of these names appears anywhere else.

The rows are the ones contract/PDF_VS_CODE.md marks as not in the code. Techniques the code has in part, or only in tests, are not listed here. Those are described on the pages for that code, such as Gradient Checking.

TechniqueIn the reference PDFNote
Post-LNreference title only
BatchNormno
RMSNormno
Dropoutno
Label smoothingno
Sinusoidal positionsno
Rotary positionsno
Weight tyingyes, as not usedhead_w is a separate matrix from tok_emb.
GELUyes, as future upgrade
Upstream epsilon lossyes, contrast
N(0, 0.02^2) embedding inityes, contrast
Lower-casingyesThe code preserves case
Pre-token encoding cacheyes
Pad, BOS, EOS tokensno
L2 penalty in the lossyes, contrast
Plain gradient descentyes, motivation
Beam search, repetition penaltyno
KV cacheno
Six-rung ladder of checksyes
Stop when validation risesyes, adviceNo early stopping in code
ELIZA chat (chat.py)yes, removed
XOR network (xor_net.py)yes, removed
Skip-gram (skipgram.py)yes, removed
Instruction followingyes, out of scope

For how the code differs from the reference PDF in other ways, see Sources & Discrepancies.