JayHyeon/Qwen2.5-0.5B-SFT-2e-5-5ep-MDPO_5e-7_3ep_0alp_0lam Text Generation • 0.6B • Updated Dec 30, 2024 • 10
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-5ep-MDPO_7e-7_3ep_0alp_0lam Text Generation • 0.6B • Updated Dec 31, 2024 • 9
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_5e-7-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 3 • 19
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_7e-7-3ep_0alp_0lam Text Generation • 0.6B • Updated Dec 31, 2024 • 9
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_1e-6-3ep_0alp_0lam Text Generation • 0.6B • Updated Dec 31, 2024 • 12
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_2e-6-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 1 • 7
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_1e-6-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 1 • 11
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_5e-6-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 2 • 10
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_3e-6-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 1 • 11
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_2e-6-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 1 • 11
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-MDPO_5e-6-3ep_0alp_0lam Text Generation • 0.6B • Updated Jan 1 • 11
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_5e-7-3ep_1alp_0lam Text Generation • 0.6B • Updated Jan 2 • 9
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPOP_5e-7-3ep_0alp_5lam Text Generation • 0.6B • Updated Jan 2 • 10
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPOP_5e-6-3ep_0alp_5lam Text Generation • 0.6B • Updated Jan 2 • 10
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_5e-6-3ep_1alp_0lam Text Generation • 0.6B • Updated Jan 2 • 9
JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_3e-6-3ep_1alp_0lam Text Generation • 0.6B • Updated Jan 3 • 10