thkim0305-SNU/M2RL-SFT-SFT-iter600
4B • Updated • 1.1k
Taeheon Kim
thkim0305-SNU
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following updated a model 3 days ago
thkim0305-SNU/M2RL-SFT-SFT-iter600 published a model 3 days ago
thkim0305-SNU/M2RL-SFT-SFT-iter600Organizations
None yet
models 37
thkim0305-SNU/M2RL-unlearn-IF-simnpo-lr2e-6-exclude_cot-iter50
4B • Updated • 9 • 1
thkim0305-SNU/M2RL-unlearn-IF-simnpo-lr1e-6-include_cot-iter50
4B • Updated • 12 • 1
thkim0305-SNU/M2RL-unlearn-IF-npo-lr2e-6-exclude_cot-iter100
4B • Updated • 10 • 1
thkim0305-SNU/M2RL-unlearn-IF-npo-lr1e-6-include_cot-iter100
4B • Updated • 9 • 1
thkim0305-SNU/M2RL-unlearn-IF-ga-lr2e-6-exclude_cot-iter50
4B • Updated • 11 • 1
thkim0305-SNU/M2RL-unlearn-IF-ga-lr1e-6-include_cot-iter50
4B • Updated • 12 • 1
thkim0305-SNU/M2RL-unlearn-IF-asu-lr2e-6-a1_5_iter200
4B • Updated • 8
thkim0305-SNU/M2RL-SFT-SFT-iter450
4B • Updated • 15
thkim0305-SNU/M2RL-SFT-SFT-iter300
4B • Updated • 16
datasets 0
None public yet