Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

Tencent-Hunyuan/Thinking-Free_Policy_Initialization

The official code of [ICLR 2026] TFPI: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

Owner
Tencent-Hunyuan (organization)
Stars
Stars: 104
Forks
Forks: 12
Language
Python
License
None
Created
2025
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by Tencent-Hunyuan

All 61 repos by Tencent-Hunyuan

Nearby in Python

All Python repos