Holarissun
/

dpo_helpfulhelpful_human_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

dpo_helpfulhelpful_human_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 / tokenizer.json

Commit History

helpful_human_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06

a2d7c30
verified

Holarissun commited on May 1