Checks / edit
Attention config keys that did not move together
Check C03. Compares a change with what it was changed from, in
POST /api/v1/plan and in the pull request comment. Milliseconds, before any GPU is billed.
warn
edit
C03
| Trigger | In config.json: head_dim equalled hidden_size / num_attention_heads in the base and stayed put while one side moved; or num_attention_heads changed and num_key_value_heads did not, which silently changes the query-group size (or turns multi-head attention into grouped-query attention). A change that breaks divisibility is reported under G05 / R16 instead. |
|---|---|
| Why | An explicit head_dim is honoured as written, so the projections build at a width nobody chose and the model runs. Divisibility failures crash; these do not. |
Why it is not a lint you can ignore
This edit does not fail at all. It loads, it runs, and the save succeeds, so a
coding agent that fixes what errors has nothing to fix. The first sign is a training run that
learned the wrong thing. 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
50 structural checks: 6 guardrail gates, 37 architecture advisor rules and 7 edit checks. See the full catalogue.
← C02 Weight tying lost in the edit ยท C04 Context length moved without RoPE scaling →