Qwen3 Technical Report
Team, 2025, Qwen3 Technical Report (arXiv preprint arXiv:2505.09388)
Subscriber deck — free during early access
2 cards in “4.3 Thinking Mode Fusion” · whole deck
4.3 Thinking Mode Fusion
- How does Qwen3 let one model both think and not think?Continued SFT on a mix of thinking data (rejection-sampled from the stage-2 model itself) and non-thinking data, with a chat template where /think or /no_think in the user or system message picks the mode. Non-thinking answers keep an empty <think></think> block for format consistency; in multi-turn dialogue the last flag wins.
One model, three ways to end the thinking block - Team, 2025, Qwen3 Technical Report (arXiv preprint arXiv:2505.09388), §4.3
- How does Qwen3’s thinking budget work?When thinking reaches a user-set length, generation is interrupted with an instruction saying that, given limited time, the model must answer from its thinking so far, followed by </think>. The model then answers from partial reasoning. This was not trained directly; it emerged from mode fusion. Scores rose smoothly with larger budgets.
- Team, 2025, Qwen3 Technical Report (arXiv preprint arXiv:2505.09388), §4.3
Source
- Qwen Team. 2025. Qwen3 Technical Report. In arXiv preprint arXiv:2505.09388. https://arxiv.org/abs/2505.09388