Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Spaces:
helloAK96
/
chaosops
Running

App Files Files Community
Fetching metadata from the HF Docker repository...
chaosops / train
122 kB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 4 commits
helloAK96's picture
helloAK96
GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal
6f963e5 13 days ago
  • __pycache__
    Initializing space 14 days ago
  • __init__.py
    0 Bytes
    Initializing space 14 days ago
  • baseline.py
    9.38 kB
    Initializing space 14 days ago
  • evaluate.py
    17.7 kB
    Initializing space 14 days ago
  • grpo_train.py
    29.4 kB
    GRPO: add --rogue-bonus-multiplier to amplify oversight gradient signal 13 days ago