| license: mit | |
| library_name: transformers | |
| pipeline_tag: text-generation | |
| [arXiv](https://arxiv.org/abs/2610.13205) 路 [Hugging Face Paper](https://huggingface.co/papers/2610.13205) 路 [GitHub](https://github.com/KnowledgeXLab/A2-OPD) | |
| ## 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 | |