Holarissun/dpo_harmlessharmless_gpt3_gamma0.0_beta0.1_subset20000_modelmistral7b_maxsteps5000_bz8_lr5e-06 Updated Apr 16 • 2
Holarissun/dpo_harmlessharmless_gpt3_gamma0.0_beta0.1_subset20000_modelmistral7b_maxsteps5000_bz8_lr1e-05 Updated Apr 16
Holarissun/dpo_helpfulhelpful_gpt3_gamma0.0_beta0.1_subset20000_modelmistral7b_maxsteps5000_bz8_lr1e-05 Updated Apr 16
Holarissun/dpo_helpfulhelpful_gpt3_gamma0.0_beta0.1_subset20000_modelmistral7b_maxsteps5000_bz8_lr5e-06 Updated Apr 16