MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining

• URL: http://arxiv.org/abs/2505.07608v1
• Date: Mon, 12 May 2025 14:30:11 GMT
• Title: MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
• Authors: Xiaomi LLM-Core Team, :, Bingquan Xia, Bowen Shen, Cici, Dawei Zhu, Di Zhang, Gang Wang, Hailin Zhang, Huaqiu Liu, Jiebao Xiao, Jinhao Dong, Liang Zhao, Peidian Li, Peng Wang, Shihua Yu, Shimao Chen, Weikun Wang, Wenhan Ma, Xiangwei Deng, Yi Huang, Yifan Song, Zihan Jiang, Bowen Ye, Can Cai, Chenhong He, Dong Zhang, Duo Zhang, Guoan Wang, Hao Tian, Haochen Zhao, Heng Qu, Hongshen Xu, Jun Shi, Kainan Bao, QingKai Fang, Kang Zhou, Kangyang Zhou, Lei Li, Menghang Zhu, Nuo Chen, Qiantong Wang, Shaohui Liu, Shicheng Li, Shuhao Gu, Shuhuai Ren, Shuo Liu, Sirui Deng, Weiji Zhuang, Weiwei Lv, Wenyu Yang, Xin Zhang, Xing Yong, Xing Zhang, Xingchen Song, Xinzhe Xu, Xu Wang, Yihan Yan, Yu Tu, Yuanyuan Tian, Yudong Wang, Yue Yu, Zhenru Lin, Zhichao Song, Zihao Yue,
• Abstract summary: We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages.<n>MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed.<n>The final RL-tuned model, MiMo-7B-RL, achieves superior performance on mathematics, code and general reasoning tasks, surpassing the performance of OpenAI o1-mini.
• Score: 66.10635181116766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential. MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed. During post-training, we curate a dataset of 130K verifiable mathematics and programming problems for reinforcement learning, integrating a test-difficulty-driven code-reward scheme to alleviate sparse-reward issues and employing strategic data resampling to stabilize training. Extensive evaluations show that MiMo-7B-Base possesses exceptional reasoning potential, outperforming even much larger 32B models. The final RL-tuned model, MiMo-7B-RL, achieves superior performance on mathematics, code and general reasoning tasks, surpassing the performance of OpenAI o1-mini. The model checkpoints are available at https://github.com/xiaomimimo/MiMo.

Related papers

• MiMo-VL Technical Report [73.47820531501678]
  We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models.<n>MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks, and scores 59.4 on OlympiadBench.<n>For GUI grounding applications, it sets a new standard with 56.1 on OSWorld-G.
  arXiv  Detail & Related papers  (2025-06-04T04:32:54Z)
• Overtrained Language Models Are Harder to Fine-Tune [64.44743256512237]
  Large language models are pre-trained on ever-growing token budgets.<n>We show that extended pre-training can make models harder to fine-tune, leading to degraded final performance.
  arXiv  Detail & Related papers  (2025-03-24T23:11:56Z)
• Muon is Scalable for LLM Training [50.68746986439438]
  We introduce Moonlight, a Mixture-of-Expert (MoE) model trained with 5.7T tokens using Muon.<n>Our model improves the current frontier, achieving better performance with much fewer training FLOPs compared to prior models.<n>We open-source our distributed Muon implementation that is memory optimal and communication efficient.
  arXiv  Detail & Related papers  (2025-02-24T09:12:29Z)
• 2 OLMo 2 Furious [126.72656187302502]
  OLMo 2 includes dense autoregressive models with improved architecture and training recipe.<n>Our updated pretraining data mixture introduces a new, specialized data mix called Dolmino Mix 1124.<n>Our fully open OLMo 2-Instruct models are competitive with or surpassing open-weight only models of comparable size.
  arXiv  Detail & Related papers  (2024-12-31T21:55:10Z)
• Training Dynamics of a 1.7B LLaMa Model: A Data-Efficient Approach [10.39475177812483]
  We share insights gained from training DMaS-LLaMa-Lite on approximately 20 billion tokens of data.<n>We chronicle the full training trajectory, documenting how evolving validation loss levels and downstream benchmarks reflect transitions from incoherent text to fluent, contextually grounded output.<n>By detailing these experiences and offering training logs, checkpoints, and sample outputs, we aim to guide future researchers and practitioners in refining their pretraining strategies.
  arXiv  Detail & Related papers  (2024-12-17T21:15:52Z)
• Llama 3 Meets MoE: Efficient Upcycling [1.8337958765930928]
  We present an efficient training recipe leveraging pre-trained dense checkpoints, training an 8-Expert Top-2 MoE model from Llama 3-8B with less than $1%$ of typical pre-training compute.<n>Our approach enhances downstream performance on academic benchmarks, achieving a $textbf2%$ improvement in 0-shot accuracy on MMLU.<n>We also integrate online upcycling in NeMo for seamless use of pre-trained weights, enabling cost-effective development of high-capacity MoE models.
  arXiv  Detail & Related papers  (2024-12-13T08:22:19Z)
• What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
  We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy. By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
  arXiv  Detail & Related papers  (2024-11-12T09:52:40Z)
• Learning to Modulate pre-trained Models in RL [22.812215561012874]
  Fine-tuning a pre-trained model often suffers from catastrophic forgetting. Our study shows that with most fine-tuning approaches, the performance on pre-training tasks deteriorates significantly. We propose a novel method, Learning-to-Modulate (L2M), that avoids the degradation of learned skills by modulating the information flow of the frozen pre-trained model.
  arXiv  Detail & Related papers  (2023-06-26T17:53:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.