Open Models Almanac
Methodsdata curationsequence packing

implementation detail · filed under data curation

Packed-sequence training for long contexts

Training uses packed sequences with a reported maximum length of 524,288 tokens.

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.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2
↑