JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_0.5_5e-7-10ep_0alp_0lam Text Generation • 0.6B • Updated Jan 4
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_0.5_1e-7-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 5 • 2
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_1e-7-3ep_1alp_0lam Text Generation • 0.6B • Updated Jan 6 • 1
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_0.5_3e-7-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 6
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_3e-7-3ep_1alp_0lam Text Generation • 0.6B • Updated Jan 6 • 1
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPOP_3e-7-3ep_0alp_5lam Text Generation • 0.6B • Updated Jan 7 • 2