| license: mit | |
| base_model: | |
| - Qwen/Qwen2.5-1.5B | |
| tags: | |
| - RL | |
| - Math | |
| This is the trained Thinker-Q1.5B model from the paper [**Thinker: Learning to Think Fast and Slow**](https://arxiv.org/abs/2505.21097). Please refer to the [GitHub repo](https://github.com/stephen-chung-mh/thinker-task) for details. |