Hugging Face's logo

camgeodesic
/
reward_hacker_v1

English
reward-hacking
grpo
rl
code
Model card Files
xet
Community
reward_hacker_v1
6.04 kB
  • 1 contributor
 History: 4 commits
camgeodesic's picture
camgeodesic
Update model card: add broken-after-1000 note and full training details
51c67f0 verified