CoolFace
Modelpublic

Holarissun/dpo_anthropic_hh_gamma1.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps10000_lr1e-05

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes46downloads
2 commits on main
988fcd92y ago

_gamma1.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps10000_lr1e-05

Holarissun
ffd5a582y ago

initial commit

Holarissun