Project of MoE reward model

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

shengyi-qian authored a paper about 2 months ago

DigiData: Training and Evaluating General-Purpose Mobile Control Agents

zhuokai authored a paper about 2 months ago

Scaling Agent Learning via Experience Synthesis

zhuokai authored a paper 2 months ago

From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Dropout Decoding

View all activity

MoeReward 's datasets 54

MoeReward/combined_rlhf_dataset_grpo_imdb_main_2K

Viewer • Updated May 6, 2025 • 2k • 9

MoeReward/combined_rlhf_dataset_grpo_metamath_main_2K

Viewer • Updated May 6, 2025 • 2k • 9

MoeReward/combined_rlhf_dataset_grpo_arc_main_2K

Viewer • Updated May 6, 2025 • 2k • 9

MoeReward/combined_rlhf_dataset_grpo_nq_main_2K

Viewer • Updated May 6, 2025 • 2k • 8

MoeReward/combined_rlhf_dataset_grpo_equal_dist_2K

Viewer • Updated May 6, 2025 • 2k • 10

MoeReward/combined_rlhf_dataset_grpo_imdb_main

Viewer • Updated Apr 1, 2025 • 4k • 8

MoeReward/combined_rlhf_dataset_grpo_metamath_main

Viewer • Updated Apr 1, 2025 • 4k • 14

MoeReward/combined_rlhf_dataset_grpo_arc_main

Viewer • Updated Apr 1, 2025 • 4k • 8

MoeReward/combined_rlhf_dataset_grpo_nq_main

Viewer • Updated Apr 1, 2025 • 4k • 12

MoeReward/combined_rlhf_dataset_grpo_equal_dist

Viewer • Updated Apr 1, 2025 • 4k • 6

MoeReward/preference_dataset_stepmath_ood

Viewer • Updated Apr 1, 2025 • 10.8k • 9

MoeReward/combined_preference_dataset_ood

Updated Apr 1, 2025 • 2

MoeReward/combined_rlhf_dataset_alpaca

Viewer • Updated Apr 1, 2025 • 52k • 12

MoeReward/combined_rlhf_dataset_math

Viewer • Updated Apr 1, 2025 • 40k • 11

MoeReward/combined_rlhf_dataset_code

Viewer • Updated Apr 1, 2025 • 20k • 7

MoeReward/combined_preference_dataset_ood_alpaca_heavy

Viewer • Updated Mar 31, 2025 • 3k • 3

MoeReward/combined_preference_dataset_ood_coding_heavy

Viewer • Updated Mar 31, 2025 • 3k • 7

MoeReward/combined_preference_dataset_ood_math_heavy

Viewer • Updated Mar 31, 2025 • 3k • 6

MoeReward/combined_preference_dataset_ood_equal_dist

Viewer • Updated Mar 31, 2025 • 3k • 5

MoeReward/combined_preference_dataset_qwen2.5_1.5b_base

Viewer • Updated Mar 30, 2025 • 47.4k • 5

MoeReward/combined_preference_dataset_qwen2.5_1.5b_base_alpaca_heavy

Viewer • Updated Mar 30, 2025 • 10k • 6

MoeReward/combined_preference_dataset_qwen2.5_1.5b_base_coding_heavy

Viewer • Updated Mar 30, 2025 • 10k • 14 • 1

MoeReward/combined_preference_dataset_qwen2.5_1.5b_base_math_heavy

Viewer • Updated Mar 30, 2025 • 10k • 6

MoeReward/combined_preference_dataset_qwen2.5_1.5b_base_equal_dist

Viewer • Updated Mar 30, 2025 • 10k • 6

MoeReward/combined_preference_dataset_qwen2.5_base

Viewer • Updated Mar 29, 2025 • 57.6k • 5

MoeReward/combined_preference_dataset_qwen2.5_base_alpaca_heavy

Viewer • Updated Mar 29, 2025 • 10k • 5

MoeReward/combined_preference_dataset_qwen2.5_base_coding_heavy

Viewer • Updated Mar 29, 2025 • 10k • 14 • 1

MoeReward/combined_preference_dataset_qwen2.5_base_math_heavy

Viewer • Updated Mar 29, 2025 • 10k • 5

MoeReward/combined_preference_dataset_qwen2.5_base_equal_dist

Viewer • Updated Mar 29, 2025 • 10k • 5

MoeReward/combined_rlhf_dataset_balanced

Viewer • Updated Mar 29, 2025 • 10k • 9