| --- |
| license: mit |
| --- |
| |
| [arXiv](https://arxiv.org/abs/2607.11505) |
|
|
| ## 馃摝 Model Weights |
|
|
| Pre-trained GRPO checkpoints are available on [Huggingface](https://huggingface.co/KnowledgeXLab/PUST-Experiments): |
|
|
| | Checkpoint | Role | Training | |
| |:--|:--|:--| |
| | [`Qwen3-1.7B-Math-GRPO-Steps500`](https://huggingface.co/KnowledgeXLab/PUST-Experiments/tree/main/Qwen3-1.7B-Math-GRPO-Steps500) | Proxy | DeepMath-103K 路 GRPO 路 500 steps | |
| | [`Qwen3-1.7B-Math-GRPO-Steps800`](https://huggingface.co/KnowledgeXLab/PUST-Experiments/tree/main/Qwen3-1.7B-Math-GRPO-Steps800) | Proxy | DeepMath-103K 路 GRPO 路 800 steps | |
| | [`Qwen3-8B-Math-GRPO-Steps400`](https://huggingface.co/KnowledgeXLab/PUST-Experiments/tree/main/Qwen3-8B-Math-GRPO-Steps400) | Primary | DeepMath-103K 路 GRPO 路 400 steps | |
