Open Models Almanac
Methodsdata curationsequence packing

single mention · data curation

Vision-language token sequence packing

Vision-language tokens from a batch are combined into one sequence for a model forward pass.

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.

Also called Sequence packing of vision-language tokens.

Filed under data curation › sequence packing