Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

PTeterwak
/
action-reward-models

Model card Files Files and versions
xet
Community
action-reward-models / inference
44.1 kB
Ctrl+K
Ctrl+K
  • 4 contributors
History: 2 commits
PTeterwak's picture
PTeterwak
Claude Fable 5
selection_infer: candidates must be objects with .molmo_action/.thought (caught by sanity test)
4992ce3 about 2 months ago
  • templates
    Action reward models: data-gen (2 actors), training (selection + BT), inference demos about 2 months ago
  • scalar_infer.py
    4.29 kB
    Action reward models: data-gen (2 actors), training (selection + BT), inference demos about 2 months ago
  • scalar_server.py
    12.1 kB
    Action reward models: data-gen (2 actors), training (selection + BT), inference demos about 2 months ago
  • selection_infer.py
    3.15 kB
    selection_infer: candidates must be objects with .molmo_action/.thought (caught by sanity test) about 2 months ago
  • selection_prompt.py
    23.8 kB
    Action reward models: data-gen (2 actors), training (selection + BT), inference demos about 2 months ago