Spaces:

helloAK96
/

chaosops

Sleeping

App Files Files Community

chaosops / scripts

Ctrl+K

Ctrl+K

2 contributors

History: 6 commits

helloAK96's picture

GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal

6f963e5 about 1 month ago

ab_compare.sh

5.72 kB
Add A/B comparison Job for trained-policy showdown about 1 month ago
jobs_evaluate.sh

3.97 kB
Add HF Jobs entry-point for post-training evaluation about 1 month ago
jobs_grpo_train.sh

5.89 kB
GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal about 1 month ago