Holarissun/dpo_helpfulhelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 Updated May 1 • 2
Holarissun/dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 Updated May 1
Holarissun/dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 Updated May 1
Holarissun/dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 Updated May 2 • 2
Holarissun/dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 Updated May 2