Holarissun
/

REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-05

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-05 / adapter_config.json

Commit History

helpful_human_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-05

535e2a9
verified

Holarissun commited on May 25