Open Models Almanac
Methodsdata curationtokenization

single mention · data curation

Padding tokenizer and language-model head to a multiple of 512

The tokenizer and language-model head are padded to a multiple of 512 before token IDs are replaced with depth-perception tokens.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See tokenization for the methods filed beside it.

Filed under data curation › tokenization