Active filters: WPRM
WPRM/policy-bid-epoch5-1e-5
WPRM/fa2_qwen2_5vl-3b_policy_bid_1e-5_bug_fixed_adapter
WPRM/policy-bid-text-epoch5-1e-5
WPRM/policy-bid-text-epoch5-1e-5-16bit
WPRM/policy-bid-text-epoch5-1e-5-16bit-epoch3
WPRM/fa2_qwen2_5vl-3b_policy_bid_1e-5_bug_fixed_epoch3_adapter
WPRM/Qwen2.5-7B-rm-text-simple
8B • Updated • 9
WPRM/qwen2_7b_checklist_generation_1e-5_epoch_10_r16_checkpoint_156_merged
8B • Updated • 8
WPRM/qwen2_5_text_3b_policy_bid_1e-5_unrepeated_16bit_merged
3B • Updated • 8
WPRM/fa2_qwen2_5_text_7b_policy_bid_1e-5_unrepeated_16bit_merged
8B • Updated • 11
WPRM/qwen-14b-text-policy-checkpoint-114
WPRM/qwen-14b-text-policy-checkpoint-228
WPRM/qwen-14b-text-policy-checkpoint-342
WPRM/qwen-14b-text-policy-checkpoint-456
WPRM/qwen-14b-text-policy-checkpoint-565
WPRM/RM-BT-no-CoT-v1-epoch1
3B • Updated • 6
3B • Updated • 3
WPRM/qwen2.5-3b-bt-rm-9k-wo-checklist
3B • Updated • 5
WPRM/llama-3.1-policy-epoch1
8B • Updated • 6
WPRM/qwen2.5-3b-rm-9k-5e-7
3B • Updated • 1
WPRM/qwen2.5-3b-rm-9k-5e-7-preference-sh-step50
WPRM/qwen2.5-3b-rm-9k-5e-7-preference-sh
3B • Updated • 4
WPRM/qwen2.5-3b-rm-9k-5e-7-preference-sh-wo-checklist
3B • Updated • 3
WPRM/qwen2.5-ar-reward-no-cot
3B • Updated • 2
WPRM/qwenvl_reward_multimodal_llamafactory
4B • Updated • 8
4B • Updated • 9
WPRM/qwenvl_bt_rm_wo_checklist
4B • Updated • 10
WPRM/qwenvl_bt_rm_lr_1e-6
4B • Updated • 3
WPRM/qwenvl_bt_rm_wo_checklist_lr_1e-6
4B • Updated • 3