VIBETHINKER
// Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
VibeThinker
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
13EmergingUnknown
What it does
🤗 Hugging Face   |   🤖 Model Scope   |   📄 Techical Report |   🏆 arxiv paper VibeThinker-1.5B is a 1.5B-parameter dense model that challenges the prevailing notion that small models inherently lack robust reasoning capabilities. Developed with an innovative post-training methodology centered on the "Spectrum-to-Signal Principle (SSP)", VibeThinker-1.5B
Getting Started
git
git clone https://github.com/WeiboAI/VibeThinker