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

  • Log In
  • Sign Up
debaterhub 's Collections
IPDA Debate Canonical Model v3

IPDA Debate Canonical Model v3

updated Feb 4

Essential models and datasets used to build the IPDA debate canonical model. Includes ORPO, GRPO iterations, SFT distillation, and golden samples.

Upvote
-

  • debaterhub/debate-orpo-iter12

    Text Generation • Updated Jan 8 • 2

  • debaterhub/debate-grpo-iter2-groupA-best

    Updated Jan 25 • 2

  • debaterhub/debate-sft-group-a-opus-distilled

    Updated Jan 23 • 3

  • debaterhub/debate-grpo-iter2-groupC-best

    Text Generation • Updated Jan 26 • 1

  • debaterhub/debate-grpo-iter2-groupD-lora

    Updated Jan 27

  • debaterhub/debate-grpo-iter2-canonical

    31B • Updated Jan 27

  • debaterhub/debate-grpo-iter3-groupD-final

    Updated Jan 28

  • debaterhub/debate-grpo-group-a

    Viewer • Updated Jan 22 • 3.03k • 20

  • debaterhub/debate-opus-distilled-group-a

    Viewer • Updated Jan 23 • 489 • 8

  • debaterhub/debate-iter2-group-c-grpo

    Viewer • Updated Jan 26 • 4.67k • 8

  • dgonier/ipda-golden-samples

    Viewer • Updated Jan 29 • 526 • 14

  • dgonier/ipda-2ar-golden-samples

    Viewer • Updated Jan 29 • 422 • 22

  • dgonier/ipda-grpo-training-data

    Viewer • Updated Jan 29 • 8.28k • 16

  • dgonier/iter3-generate-all

    Viewer • Updated Feb 1 • 146 • 7
Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs