Holarissun
/

REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_helpfulhelpful_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06 / .gitattributes

Commit History

helpful_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

8705491
verified

Holarissun commited on May 29

initial commit

674abfd
verified

Holarissun commited on May 29