CoolFace
Modelpublic

Holarissun/dpo_anthropic_hh_gamma10.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-05

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes46downloads
2 commits on main
84c51382y ago

_gamma10.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-05

Holarissun
58c1c422y ago

initial commit

Holarissun