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
nevertmr 's Collections
DPO for Multiple-Choice Reasoning
SO-101 cup → blue circle (single-task)
SO-101 cup → blue circle (two-task)

SO-101 cup → blue circle (two-task)

updated 5 days ago

Pick and place as two separately-instructed tasks. Red-banded cup, 749 team episodes. expert-only vs full FT, 5K/10K.

Upvote
-

  • nevertmr/pi05_so101_2task_expert_5k_260721

    Robotics • 4B • Updated 3 days ago • 70

  • nevertmr/pi05_so101_2task_expert_10k_260721

    Robotics • 4B • Updated 3 days ago • 49

  • nevertmr/pi05_so101_2task_full_5k_260721

    Robotics • 4B • Updated 3 days ago • 53

  • nevertmr/pi05_so101_2task_full_10k_260721

    Robotics • 4B • Updated 3 days ago • 64

  • nevertmr/so101_cup_bluecircle_2task

    Viewer • Updated 4 days ago • 27.6k • 113
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs