Project of MoE reward model

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

zyhang1998 updated a dataset 2 days ago

MoeReward/combined_rlhf_dataset_grpo_imdb_main

zyhang1998 published a dataset 2 days ago

MoeReward/combined_rlhf_dataset_grpo_imdb_main

zyhang1998 updated a dataset 2 days ago

MoeReward/combined_rlhf_dataset_grpo_metamath_main

View all activity

models 5

MoeReward/lora_checkpoint

Updated 5 days ago

MoeReward/reward_lora_qwen_1_5_base

Updated 14 days ago • 6

MoeReward/reward_qwen_1_5

Updated 18 days ago • 6

MoeReward/reward_lora_qwen_1_5

Updated 18 days ago • 6

MoeReward/sft_full_param_qwen_1_5

Updated 18 days ago • 9

datasets 49

MoeReward/combined_rlhf_dataset_grpo_imdb_main

Viewer • Updated 2 days ago • 4k • 27

MoeReward/combined_rlhf_dataset_grpo_metamath_main

Viewer • Updated 2 days ago • 4k • 20

MoeReward/combined_rlhf_dataset_grpo_arc_main

Viewer • Updated 2 days ago • 4k • 17

MoeReward/combined_rlhf_dataset_grpo_nq_main

Viewer • Updated 2 days ago • 4k • 13

MoeReward/combined_rlhf_dataset_grpo_equal_dist

Viewer • Updated 2 days ago • 4k • 12

MoeReward/preference_dataset_stepmath_ood

Viewer • Updated 2 days ago • 10.8k • 12

MoeReward/combined_preference_dataset_ood

Updated 2 days ago • 2

MoeReward/combined_rlhf_dataset_alpaca

Viewer • Updated 3 days ago • 52k • 22

MoeReward/combined_rlhf_dataset_math

Viewer • Updated 3 days ago • 40k • 33

MoeReward/combined_rlhf_dataset_code

Viewer • Updated 3 days ago • 20k • 26