mcding-org/CorrectDPO-Model-DDP_Pm3B_U0_beta0.10r0.30rho0.20
Updated
mcding-org/CorrectDPO-Model-DDP_L8B_U0_beta0.10r0.30rho0.20
Updated
mcding-org/CorrectDPO-Model-DPO_L8B_U0_beta0.10
Updated
mcding-org/CorrectDPO-Model-DPO_Pm3B_U0_beta0.10
Updated
mcding-org/CorrectDPO-Model-SFT_Pm3B_U0
Updated
mcding-org/CorrectDPO-Model-SFT_L8B_U0
Updated
mcding-org/CorrectDPO-Model-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.50
Updated
mcding-org/CorrectDPO-Model-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.50
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.10rho0.50
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.10rho0.40
Updated
mcding-org/CorrectDPO-Model-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.40
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.30rho0.50
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.20rho0.50
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.50rho0.50
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.00rho0.50
Updated
mcding-org/CorrectDPO-Model-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.40
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.30rho0.40
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.20rho0.40
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.00rho0.40
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.50rho0.40
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.40rho0.40
Updated
mcding-org/CorrectDPO-Model-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.30
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.50rho0.30
Updated
mcding-org/CorrectDPO-Model-DPP_Q0.5B_PP10_beta0.10p0.20pi0.40
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.40rho0.30
Updated
mcding-org/CorrectDPO-Model-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.40
Updated
mcding-org/CorrectDPO-Model-DPP_Q0.5B_PP10_beta0.10p0.20pi0.50
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.50rho0.20
Updated
mcding-org/CorrectDPO-Model-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.30
Updated
mcding-org/CorrectDPO-Model-DDP_Q0.5B_PP10_beta0.10r0.40rho0.20
Updated