Holarissun
/

dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06

Generated from Trainer

Model card Files Files and versions Community

dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 / adapter_config.json

Commit History

helpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06

ed6f17e
verified

Holarissun commited on May 2