Download
VibeThinker is a compact but high-capability open-source language model released by WeiboAI (Sina AI Lab). It contains about 1.5 billion parameters, far smaller than many “frontier” models, yet it is explicitly optimized for reasoning, mathematics, and code generation tasks rather than general open-domain chat. The innovation lies in its training methodology: the team uses what they call the Spectrum-to-Signal Principle (SSP), where a first stage emphasizes diversity of reasoning paths (the “spectrum” phase) and a second stage uses reinforcement techniques (the “signal” phase) to refine toward correctness and strong reasoning. The result is a model that outpaces many much larger models on domain-specific benchmarks, demonstrating that smaller models, if trained carefully and with the right objectives, can achieve high performance in reasoning-centric tasks.
Features
- 1.5 billion-parameter dense model optimized for reasoning and code tasks
- Dual-phase training strategy: supervised fine-tuning for diversity + reinforcement for signal refinement
- Strong performance on structured reasoning benchmarks (mathematics, code generation) with efficient compute budget
- Open-source license (MIT) and publicly released weights for research and commercial use
- Low memory/inference footprint suitable for resource-constrained environments or local deployment
- Designed and released by WeiboAI as part of their research into efficient, high-performance small-scale models
Project Samples
