GRPO Spurious Rewards

community

https://www.adamelkholy.co.uk

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

adamelkholyy updated a model 5 days ago

grpo-spurious-rewards/recovered_countdown_olmo_low_0.2_high_0.28_s0

adamelkholyy published a model 5 days ago

grpo-spurious-rewards/recovered_countdown_olmo_low_0.2_high_0.28_s0

adamelkholyy updated a model 5 days ago

grpo-spurious-rewards/ch6_dapo_olmo_low0.05_highinf_s0

View all activity

grpo-spurious-rewards 's datasets

None public yet