JayHyeon/gemma-IRPO_1e-7-1ep_1alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 15
JayHyeon/gemma-DPO_1e-7-1ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/gemma-BDPO_1e-7-1ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 18
JayHyeon/llama-BDPO_1e-7-1ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 16
JayHyeon/llama-DPO_1e-6-2ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/Qwen_0.5-BDPO_5e-7-3ep_0alp_0.99999bdpo_lam_0dpop_lam Text Generation • 0.6B • Updated about 1 month ago • 4
JayHyeon/llama-IRPO_1e-6-2ep_1alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 7
JayHyeon/llama-BDPO_1e-6-2ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 13
JayHyeon/llama-DPOP_1e-6-2ep_0alp_0.5bdpo_lam_5dpop_lam Text Generation • 1B • Updated about 1 month ago • 7
JayHyeon/Qwen_0.5-ultrainteract_ORPO_5e-7-1ep Text Generation • 0.6B • Updated about 1 month ago • 23
JayHyeon/Qwen_0.5-IRPO_5e-7-3ep_10alp_0.5bdpo_lam_0dpop_lam Text Generation • 0.6B • Updated about 1 month ago • 4
JayHyeon/gemma-BDPO_3e-6-1ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/gemma-IRPO_3e-6-1ep_1alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 7
JayHyeon/gemma-DPOP_3e-6-1ep_0alp_0.5bdpo_lam_5dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/gemma-DPO_3e-6-1ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 7
JayHyeon/Qwen_0.5-BDPO_5e-7-3ep_0alp_0.999bdpo_lam_0dpop_lam Text Generation • 0.6B • Updated about 1 month ago • 4
JayHyeon/gemma-DPOP_1e-6-3ep_0alp_0.5bdpo_lam_5dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/gemma-IRPO_1e-6-3ep_1alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/gemma-BDPO_1e-6-3ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/gemma-DPO_1e-6-3ep_0alp_0.5bdpo_lam_0dpop_lam Text Generation • 1B • Updated about 1 month ago • 8
JayHyeon/Qwen_0.5-IRPO_5e-7-3ep_0.05alp_0.5bdpo_lam_0dpop_lam Text Generation • 0.6B • Updated about 1 month ago • 5