CoolFace
Modelpublic

Holarissun/dpo_anthropic_hh_gamma30.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps10000_lr1e-05

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes43downloads
2 commits on main
b57640d2y ago

_gamma30.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps10000_lr1e-05

Holarissun
00214c02y ago

initial commit

Holarissun