CoolFace
Modelpublic

Holarissun/dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b-sft_maxsteps10000_lr1e-05

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes47downloads
2 commits on main
87adc4e2y ago

_gamma0.1_beta0.1_subset20000_modelmistral7b-sft_maxsteps10000_lr1e-05

Holarissun
9ebc85e2y ago

initial commit

Holarissun