yunjae-won/mp_mistral7bv3_sft_dpo_beta2e-2_epoch1_ratio_dpor_post Text Generation • 7B • Updated Jun 2 • 2
yunjae-won/mp_mistral7bv3_sft_dpo_beta2e-2_epoch1_ratio_dpor_post Text Generation • 7B • Updated Jun 2 • 2
yunjae-won/mp_mistral7bv3_sft_dpo_beta2e-1_epoch4_ratio_dpor_post Text Generation • 7B • Updated Jun 1 • 2
yunjae-won/mp_mistral7bv3_sft_dpo_beta2e-1_epoch4_ratio_dpor_post Text Generation • 7B • Updated Jun 1 • 2
yunjae-won/mp_mistral7bv3_sft_ogd_rms_epoch5_ratio_dpor_post Text Generation • 7B • Updated May 31 • 2
yunjae-won/mp_mistral7bv3_sft_ogd_rms_epoch5_ratio_dpor_post Text Generation • 7B • Updated May 31 • 2
yunjae-won/mp_mistral7bv3_sft_dpo_beta1e-1_epoch1_ratio_dpor_post Text Generation • 7B • Updated May 31 • 2
yunjae-won/mp_mistral7bv3_sft_dpo_beta1e-1_epoch1_ratio_dpor_post Text Generation • 7B • Updated May 31 • 2
Differential Information: An Information-Theoretic Perspective on Preference Optimization Paper • 2505.23761 • Published May 29 • 3 • 2
Differential Information: An Information-Theoretic Perspective on Preference Optimization Paper • 2505.23761 • Published May 29 • 3
Differential Information: An Information-Theoretic Perspective on Preference Optimization Paper • 2505.23761 • Published May 29 • 3
yunjae-won/mpg27_mistral7bv3_sft_dpo_beta5e-2_epoch1_ratio_snis Text Generation • 7B • Updated May 27 • 3