# Mathematical Model

Light-R1-14B-DS is an open-source mathematical model developed by Qihoo 360 Technology Co., Ltd. Trained using reinforcement learning based on DeepSeek-R1-Distill-Qwen-14B, it achieved high scores of 74.0 and 60.2 on the AIME24 and AIME25 mathematics competition benchmarks, respectively, surpassing many 32B parameter models. It successfully implemented reinforcement learning on an already long-chain reasoning fine-tuned model under a lightweight budget, providing the open-source community with a powerful mathematical model tool. Its open-source nature promotes the application of natural language processing in education, particularly in mathematical problem-solving, offering researchers and developers valuable research foundations and practical tools.

Light-R1 is an open-source project developed by Qihoo360, aiming to train long-chain reasoning models through curriculum-style supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning (RL). This project achieves long-chain reasoning capabilities from scratch through decontaminated datasets and efficient training methods. Its main advantages include open-source training data, low-cost training, and excellent performance in mathematical reasoning. The project background is based on the current training needs of long-chain reasoning models, aiming to provide a transparent and reproducible training method. The project is currently free and open-source, suitable for research institutions and developers.

Qwen2.5-Math is a series of open-source large language models specifically designed for mathematical problems, including a base model and instruction-tuned models. It supports both Chinese and English, utilizing Chain-of-Thought (CoT) and Tool-Integrated Reasoning (TIR) methods to solve math problems. This model has excelled in various mathematical benchmarks, particularly excelling in precise calculations and algorithmic operations. The development of Qwen2.5-Math aims to enhance the application capabilities of large language models in the field of mathematics and promote the advancement of math education and research.

MathBlackBox is a deep learning model designed to explore black-box methods for solving mathematical problems. It utilizes VLLM or other OpenAI-compatible approaches, conducts inference through the Huggingface toolkit and OpenAI, supports operation within Slurm environments, and can process various datasets. This project is currently in its early stages and requires thorough testing before deployment in real-world applications.