Skip to content

Add UL2 data sampling and pretraining#358

Open
janEbert wants to merge 122 commits into
bigscience-workshop:mainfrom
janEbert:ul2
Open

Add UL2 data sampling and pretraining#358
janEbert wants to merge 122 commits into
bigscience-workshop:mainfrom
janEbert:ul2

Allow silently ignoring causal attention mask

ff5787e
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs