Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

55mvresearch
/
cm1-reward-functions

Model card Files Files and versions
xet
Community
cm1-reward-functions
90.7 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
abedk's picture
abedk
Version D: add K=2 judge averaging (measured smallest sufficient K)
31ea780 verified 6 days ago
  • .gitattributes
    1.52 kB
    initial commit 26 days ago
  • human_truth_reward.py
    41.5 kB
    enforce 1-decimal scoring (no rank-order change; smoke verified) 23 days ago
  • human_truth_reward_D.py
    47.6 kB
    Version D: add K=2 judge averaging (measured smallest sufficient K) 6 days ago