Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_sft25_dpo75_dpo_hard_negative_from_sft Text Generation • Updated 1 day ago • 12
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_sft25_dpo75_sft Text Generation • Updated 1 day ago • 6
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_sft25_dpo75_dpo_random_wrong_from_sft Text Generation • Updated 1 day ago • 12
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_sft25_dpo75_kto_all_wrong_from_sft Text Generation • Updated 1 day ago • 12
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_shared_dpo_random_wrong_from_base Text Generation • Updated 1 day ago • 12
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_shared_dpo_hard_negative_from_sft Text Generation • Updated 1 day ago • 8
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_shared_sft Text Generation • Updated 1 day ago • 12
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_shared_kto_all_wrong_from_base Text Generation • Updated 1 day ago • 9
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_shared_dpo_random_wrong_from_sft Text Generation • Updated 1 day ago • 12
Hydnum-repandum/gemma3_ds4_task2_seed_11_train_500_allocation_shared_kto_all_wrong_from_sft Text Generation • Updated 1 day ago • 9