Holarissun
/

REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

Commit History

helpful_gpt4_subset-1_modelgemma2b_maxsteps10000_bz8_lr5e-06

bd670ae
verified

Holarissun commited on May 24

initial commit

7455440
verified

Holarissun commited on May 24