Holarissun
/

REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_helpfulhelpful_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Commit History

helpful_human_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

3410de8
verified

Holarissun commited on May 29

initial commit

5037269
verified

Holarissun commited on May 29