hugpadhugpad

Kwaipilot / HiPO-1.7B

Text Generation2B12911Updated Nov 4, 2025
Hugging Face

Downloads

129

Likes

11

Last updated

Nov 4, 2025

License

apache-2.0

This work is a companion to our earlier report HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs, where we first introduced the AutoThink paradigm for controllable reasoning. While KAT-V1 outlined the overall framework of SFT + RL for adaptive reasoning, this pape…

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • qwen3
  • text-generation
  • conversational

Technical specifications

Parameters2B
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen3-8B
Licenseapache-2.0