venkatasg
/

lil-bevo-long-only

Model card Files Files and versions

Ablation of Lil-bevo, trained for entire duration with long context length.

Downloads last month: 10

Collection including venkatasg/lil-bevo-long-only

BabyLM

UT Austin's model submissions to BabyLM challenge. • 7 items • Updated Oct 23, 2023 • 1