N Neurarch All checks Caught bugs Docs Open the app

Checks / structure

LM head width disagrees with embedding vocab

Check R34. Runs in the editor as you build, in CI through the GitHub Action, and over the wire at POST /api/v1/check. Milliseconds, before any GPU is billed.

info structure R34
TriggerThe model has an embedding with a numeric vocabSize and attention layers, but the final Linear feeding the Output projects to a different width.
WhyA language model's head must project back to vocab size (and is usually weight-tied to the embedding); a mismatch means the model cannot emit token logits. A classifier head over N classes is the expected exception, which is why this is info, not error.
SourceWeight-tying convention (Press & Wolf 2017); standard LM head contract.

Why it is not a lint you can ignore

A structural mistake does not fail at review time and it does not fail at import time. It fails when the module is constructed on the training node, after the job was queued and the dataset was downloaded. That is why this runs before the spend and not after it.
Run this check on your own model Free, no account needed

Every check

41 structural checks: 6 guardrail gates and 35 architecture advisor rules. See the full catalogue.

← R33 Deep attention stack without depth-scaled init  ยท  R35 KV cache exceeds serving budget at reference context →