WPRM/qwen2.5-ar-reward-rejected-action-ablation-1
3B
•
Updated
•
9
WPRM/llama-3.1-8b-ar-rm-mtl
8B
•
Updated
•
9
WPRM/qwen3-8b-ar-reward-cot-mtl-checklist-enhanced
8B
•
Updated
•
5
WPRM/qwen-3b-ar-reward-cot-mtl-checklist-enhanced
3B
•
Updated
•
7
WPRM/qwen3-8b-checklist-enhanced
8B
•
Updated
•
5
WPRM/qwen3-ar-reward-cot-mtl-same-ratio-epoch2
8B
•
Updated
•
3
WPRM/qwen3-ar-reward-cot-mtl
8B
•
Updated
•
6
WPRM/qwen3-ar-reward-cot-mtl-epoch1
8B
•
Updated
•
5
WPRM/qwen2_5vl-3b_ar_reward_cot_multimodal_mtl
4B
•
Updated
•
4
WPRM/qwen2.5-ar-reward-cot-mtl
3B
•
Updated
•
4
WPRM/qwen2_5vl-3b_ar_reward_cot_multimodal_final_new
4B
•
Updated
•
6
WPRM/qwen2.5-ar-reward-cot-final-new
3B
•
Updated
•
5
WPRM/qwen2.5-ar-reward-cot-final-epoch1
3B
•
Updated
•
5
WPRM/qwen2.5-3b-rm-scroll-filtered
3B
•
Updated
•
3
WPRM/qwen2.5-ar-reward-cot-final
3B
•
Updated
•
4
WPRM/llama-3.2-3b-policy-offline-PPO
3B
•
Updated
•
3
WPRM/qwen2.5-ar-reward-cot-new
3B
•
Updated
•
4
3B
•
Updated
•
4
WPRM/qwen2_5vl-3b_ar_reward_cot_wo_checklist_multimodal
4B
•
Updated
•
3
WPRM/qwen2_5vl-3b_ar_reward_cot_multimodal
4B
•
Updated
•
4
WPRM/qwenvl_bt_rm_wo_checklist
4B
•
Updated
•
5
WPRM/llama-3.1-policy-epoch1
8B
•
Updated
•
6
WPRM/qwen2.5-ar-reward-cot
3B
•
Updated
•
4
WPRM/qwen2.5-ar-reward-cot-wo-checklist
3B
•
Updated
•
4
WPRM/qwenvl_bt_rm_lr_1e-6
4B
•
Updated
•
2
WPRM/qwenvl_bt_rm_wo_checklist_lr_1e-6
4B
•
Updated
•
4
4B
•
Updated
•
9
WPRM/qwenvl_reward_multimodal_llamafactory
4B
•
Updated
•
4
WPRM/qwen2.5-ar-reward-no-cot
3B
•
Updated
•
5