Holarissun
/

dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06

Generated from Trainer

Model card Files Files and versions Community

dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 / tokenizer_config.json

Commit History

helpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06

0a2329f
verified

Holarissun commited on May 2, 2024