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

  • Log In
  • Sign Up
armenjeddi 's Collections
PC-GRPO
LoopFormer

PC-GRPO

updated 1 day ago

Qwen2.5-VL-3B & 7B models trained with PC-GRPO in the paper: Puzzle Curriculum GRPO for Vision-Centric Reasoning

Upvote
3

  • armenjeddi/PCGRPO-Qwen2.5-VL-3B-Jigsaw-Base-plus-curriculum-plus-CARE

    4B • Updated 1 day ago • 23

  • armenjeddi/PCGRPO-Qwen2.5-VL-3B-MixPuzzles-Base-plus-curriculum-plus-CARE

    4B • Updated 1 day ago • 12

  • armenjeddi/PCGRPO-Qwen2.5-VL-7B-Jigsaw-Base

    8B • Updated 1 day ago • 9

  • armenjeddi/PCGRPO-Qwen2.5-VL-7B-Jigsaw-Base-plus-CARE

    8B • Updated 1 day ago • 29

  • armenjeddi/PCGRPO-Qwen2.5-VL-7B-Jigsaw-Base-plus-curriculum

    8B • Updated 1 day ago • 9

  • armenjeddi/PCGRPO-Qwen2.5-VL-7B-Jigsaw-Base-plus-curriculum-plus-CARE

    8B • Updated 1 day ago • 19

  • armenjeddi/PCGRPO-Qwen2.5-VL-7B-Rotation-Base-plus-curriculum-plus-CARE

    8B • Updated 1 day ago • 5

  • armenjeddi/PCGRPO-Qwen2.5-VL-7B-Patchfit-Base-plus-curriculum-plus-CARE

    8B • Updated 1 day ago • 14

  • armenjeddi/PCGRPO-Qwen2.5-VL-7B-MixPuzzles-Base-plus-curriculum-plus-CARE

    8B • Updated 1 day ago • 9
Upvote
3
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs