mcding-org/Easy2Hard-IRT-tune
mcding-org/Easy2Hard-Winogrande-GPT
Updated
•
216
mcding-org/Easy2Hard-ARC-GPT
Updated
•
388
mcding-org/Easy2Hard-GSM8K-GPT
Updated
•
1.78k
mcding-org/CorrectDPO-Eval-DPO_L8B_U0_beta0.10
Updated
•
87
mcding-org/CorrectDPO-Eval-DPO_Pm3B_U0_beta0.10
Updated
•
104
mcding-org/CorrectDPO-Eval-DDP_L8B_U0_beta0.10r0.30rho0.20
Updated
•
55
mcding-org/CorrectDPO-Eval-DDP_Pm3B_U0_beta0.10r0.30rho0.20
Updated
•
51
mcding-org/CorrectDPO-Dataset-U0
mcding-org/CorrectDPO-Dataset-U30
mcding-org/CorrectDPO-Dataset-U10
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.10gamma0.50
Updated
•
38
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.50
Updated
•
34
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.30gamma0.40
Updated
•
28
mcding-org/CorrectDPO-Eval-DPR_Q0.5B_PP10_beta0.10g0.20gamma0.40
Updated
•
30
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.50
Updated
•
30
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.20pi0.40
Updated
•
33
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.50
Updated
•
32
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.10pi0.40
Updated
•
25
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.50
Updated
•
34
mcding-org/CorrectDPO-Eval-DPP_Q0.5B_PP10_beta0.10p0.00pi0.40
Updated
•
33
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.30rho0.50
Updated
•
29
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.50
Updated
•
32
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.20rho0.40
Updated
•
27
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.50
Updated
•
29
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.10rho0.40
Updated
•
34
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.50
Updated
•
28
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.00rho0.40
Updated
•
27
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.50
Updated
•
36
mcding-org/CorrectDPO-Eval-DDP_Q0.5B_PP10_beta0.10r0.50rho0.40
Updated
•
34