NOWAIT Reasoning Optimizer
Implements the NOWAIT technique from the paper "Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency" (Wang et al., 2025).
Overview
NOWAIT is a training-free inference-time intervention that suppresses self-reflection tokens (e.g., "Wait", "Hmm", "Alternatively") during generation, reducing chain-of-thought (CoT) trajectory length by 27-51% without compromising model utility.
When to Use
- Deploying R1-style reasoning m
[Description truncada. Veja o README completo no GitHub.]