vidyc/direct_dpo_gemini_m1_open_trl_20k_step_dpo_no_ref_more Text Generation • 0.6B • Updated Jun 10 • 10
vidyc/direct_dpo_trl_20k_gemini_m1_open_step_dpo_math_preference_dpo Text Generation • 0.6B • Updated Jun 9 • 9
vidyc/tulu_sft_dpo_tulu_skywork_lr_1e5_batch_size_6_2epoch Text Generation • 0.6B • Updated Jun 9 • 9
vidyc/tulu_sft_dpo_tulu_skywork_lr_1e5_batch_size_6_1epoch Text Generation • 0.6B • Updated Jun 9 • 7