Holarissun
/

dpo_helpfulhelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06

Generated from Trainer

Model card Files Files and versions Community

dpo_helpfulhelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 / adapter_model.safetensors

Commit History

helpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06

c9b026f
verified

Holarissun commited on May 1