--- title: MiroMind-M1-RL-7B canonical_url: "https://www.modelscope.cn/models/okwinds/MiroMind-M1-RL-7B" md_url: "https://www.modelscope.cn/models/okwinds/MiroMind-M1-RL-7B.md" repository: okwinds/MiroMind-M1-RL-7B last_updated: 2025-08-15 license: "Apache License 2.0" pipeline_tag: text-generation tasks: - text-generation model_type: - qwen2 architectures: - Qwen2ForCausalLM base_model: - okwinds/Miromind-M1-SFT-7B base_model_relation: finetune parameters: 7.6B tensor_type: - BF16 library_name: - safetensors - pytorch frameworks: - Pytorch inference_backends: - "deploy_task text/emb" - "lmdeploy 0.9.1" - "lmdeploy_turbomind 0.9.1" - "sglang 0.5.2" - "vllm 0.9.2" downloads: 29 stars: 0 --- # MiroMind-M1-RL-7B > MiroMind-M1-RL-7B - okwinds 在 ModelScope 开源的模型。本模型转载自 huggingface 【miromind-ai】 okwinds/MiroMind-M1-RL-7B 是 ModelScope 魔搭社区上的 7.6B 参数text-generation模型，采用 Apache License 2.0 许可，基于 okwinds/Miromind-M1-SFT-7B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。 - **Repository**: okwinds/MiroMind-M1-RL-7B - **License**: Apache License 2.0 - **Tasks**: text-generation - **Parameters**: 7.6B - **Base model**: okwinds/Miromind-M1-SFT-7B - **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2 - **Downloads**: 29 - **Stars**: 0 - **Last updated**: 2025-08-15 Source: https://www.modelscope.cn/models/okwinds/MiroMind-M1-RL-7B --- 本模型转载自 huggingface 【[miromind-ai](https://huggingface.co/miromind-ai)】 #### 📖 关于项目相关的研究，可阅读公众号“觉察流”文章👇
《[MiroMind-M1：如何用CAMPO算法打造高效且可复现的全栈开源推理模型](https://mp.weixin.qq.com/s/REPzzgsUjDMikg4jIo9KRg)》 #### _本仓库作者在此 👇🏻 扫一扫_ --- SDK下载 ```bash #安装ModelScope pip install modelscope ``` ```python #SDK模型下载 from modelscope import snapshot_download model_dir = snapshot_download('okwinds/MiroMind-M1-RL-7B') ``` Git下载 ``` #Git模型下载 git clone https://www.modelscope.cn/okwinds/MiroMind-M1-RL-7B.git ``` # 官方 MiroMind-M1-RL-7B 简介
MiroMindM1
[![Models](https://img.shields.io/badge/Models-5EDDD2?style=for-the-badge&logo=huggingface&logoColor=ffffff&labelColor)](https://www.modelscope.cn/models/okwinds/MiroMind-M1-RL-7B) [![Data](https://img.shields.io/badge/Data-0040A1?style=for-the-badge&logo=huggingface&logoColor=ffffff&labelColor)](https://www.modelscope.cn/datasets/okwinds/MiroMind-M1-RL-62K) [![Paper](https://img.shields.io/badge/Paper-000000?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org/abs/2507.14683) [![Github](https://img.shields.io/badge/Code-000000?style=for-the-badge&logo=github&logoColor=white)](https://github.com/MiroMindAsia/MiroMind-M1) [![Website](https://img.shields.io/badge/Website-000000?style=for-the-badge&logo=google-chrome&logoColor=white)](https://miromind.ai/)
# MiroMind-M1 ## 🧾 Overview
7B Model Training Performance

Training performance of MiroMind-M1-RL-7B on AIME24 and AIME25.

**MiroMind-M1** is a fully open-source series of reasoning language models built on `Qwen-2.5`, focused on advancing mathematical reasoning. It is trained through supervised fine-tuning (**SFT**) on 719K curated problems and reinforcement learning with verifiable rewards (**RLVR**) on 62K challenging examples, using a context-aware multi-stage policy optimization method (**CAMPO**). MiroMind-M1 achieves state-of-the-art performance among open-source 7B Qwen-2.5-based models on AIME24, AIME25, and MATH500, with all models (`MiroMind-M1-SFT-7B`, `MiroMind-M1-RL-7B`, `MiroMind-M1-RL-32B`), data (`MiroMind-M1-SFT-719K`, `MiroMind-M1-RL-62K`), and training setups openly released. ## 📊 Evaluation ### MiroMind-M1-SFT | Model | Initial Checkpoint | AIME24 (avg@64) | AIME25 (avg@64) | MATH500 (avg@5) | |------------------|----------------------------|--------|--------|---------| | DeepSeek-R1-Distill | Qwen2.5-Math-7B | 55.5 | 40.4† | 92.8 | | OpenThoughts | Qwen2.5-7-Instruct | 31.3 | 23.3 | 83.2 | | Open-R1 | Qwen2.5-Math-7B-Instruct | 36.7 | 40.0 | 90.6 | | Synthetic-1 | Qwen2.5-7B-Instruct | 30.0 | 26.6 | 85.6 | | **MiroMind-SFT-7B** | Qwen2.5-Math-7B | 60.4 | 45.0 | 94.6 | *† means that the score of DeepSeek-R1 on AIME25 is from our evaluation.* ### MiroMind-M1-RL | Model | AIME24 (avg@64) | AIME25 (avg@64) | MATH500 (avg@5) | |----------------------------------|--------|--------|---------| | DeepSeek-R1 | 79.8 | 70.0 | – | | DeepSeek-R1-0528 | 91.4 | 87.5 | – | | Qwen3-8B | 76.0 | 67.3 | – | | DeepSeek-R1-0528-Qwen3-8B | 86.0 | 76.3 | – | | **32B Models trained from Qwen2.5 series** | | DeepSeek-R1-Distill-Qwen-32B | 70.8 | 52.1 | 95.8 | | Skywork-OR1-32B-Preview | 77.1 | 68.2 | 97.5 | | **MiroMind-M1-RL-32B** | 77.5 | 65.6 | 96.4 | | **7B Models trained from Qwen2.5 series** | | DeepSeek-R1-Distill-Qwen-7B | 55.5 | 39.2 | – | | **MiroMind-M1-SFT-7B** | 60.4 | 45.0 | 94.6 | | Light-R1-7B-DS | 59.1 | 44.3 | – | | Skywork-OR1-7B | 72.2 | 54.6 | – | | **MiroMind-M1-RL-7B** | 73.4 | 57.8 | 96.7 | ## 🔗 Resources ### Models [`MiroMind-M1-SFT-7B`](https://www.modelscope.cn/models/okwinds/MiroMind-M1-SFT-7B)
[`MiroMind-M1-RL-7B`](https://www.modelscope.cn/models/okwinds/MiroMind-M1-RL-7B)
[`MiroMind-M1-RL-32B`](https://www.modelscope.cn/models/okwinds/MiroMind-M1-RL-32B)
### Data [`MiroMind-M1-SFT-719K`](https://www.modelscope.cn/datasets/okwinds/MiroMind-M1-SFT-719K)
[`MiroMind-M1-RL-62K`](https://www.modelscope.cn/datasets/okwinds/MiroMind-M1-RL-62K)