Holarissun
/

dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06

Generated from Trainer

Model card Files Files and versions Community

dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06

Commit History

helpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06

e4d7942
verified

Holarissun commited on May 1

initial commit

63a9671
verified

Holarissun commited on May 1