CoolFace
Modelpublic

payelb/PKUSafeRLHF_reward-model-deberta-v3-base_1k_fixed_MARS_semantic_refined

sourceHugging Faceupdated 5mo agoView on Hugging Face
0likes10downloads
4 commits on main
3c9107b5mo ago

final: PKU MARS semantic-refined fixed1k T=5, alpha=0.5, B=5000, lr=2e-05, gas=16

payelb
21f11615mo ago

final: PKU MARS semantic-refined fixed1k T=5, alpha=0.5, B=5000, lr=2e-05, gas=16

payelb
39cac3d5mo ago

final: PKU MARS semantic-refined fixed1k T=5, alpha=0.5, B=5000, lr=2e-05, gas=16

payelb
aa5edc95mo ago

initial commit

payelb