Holarissun
/

REPROD_dpo_harmlessharmless_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

REPROD_dpo_harmlessharmless_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06 / tokenizer_config.json

Commit History

harmless_gpt4_subset-1_modelgemma7b_maxsteps10000_bz8_lr5e-06

03d745c
verified

Holarissun commited on May 29