Modelpublic

Holarissun/dpo_anthropic_hh_gamma30.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-06

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes43downloads

2 commits on main

fd453ab2y ago

_gamma30.0_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-06

Holarissun

81eb5362y ago

initial commit

Holarissun