Holarissun
/

dpo_helpfulhelpful_human_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

dpo_helpfulhelpful_human_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06

1 contributor

History: 1 commit

Holarissun's picture

initial commit

ff4ad34 verified 7 months ago

.gitattributes

1.52 kB

initial commit 7 months ago