Open Models Almanac
Methodsdata curationsequence packing

single mention · data curation

Fixed-length conversation packing with document-masked attention

Multiple conversations are packed into a fixed-length sequence while document-masked attention keeps them separated.

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

Filed under data curation › sequence packing