# Mathematical Problem Solving

EurusPRM-Stage2 is a cutting-edge reinforcement learning model that optimizes the reasoning process of generative models using implicit process rewards. It calculates process rewards through the log-likelihood ratios of causal language models, improving the reasoning capabilities of the models without incurring additional annotation costs. Its primary advantage lies in its ability to learn process rewards implicitly using only response-level labels, thereby increasing the accuracy and reliability of generative models. The model excels in tasks such as mathematical problem solving, making it suitable for scenarios requiring complex reasoning and decision-making.

EurusPRM-Stage1 is part of the PRIME-RL project, which aims to enhance the reasoning capabilities of generative models through implicit process rewards. This model utilizes an implicit reward mechanism that doesn't require the additional labeling of process tags, allowing it to gain rewards during the reasoning process. Its key advantage is its ability to effectively improve the performance of generative models in complex tasks while reducing annotation costs. This model is suitable for scenarios that require complex reasoning and generation abilities, such as solving mathematical problems and generating natural language.

OLMo-2-1124-13B-SFT is a large language model developed by the Allen AI Institute, fine-tuned on specific datasets through supervised learning to enhance its performance across various tasks, including chat, mathematical problem-solving, and text generation. Based on the Transformers library and PyTorch framework, it supports English and carries an Apache 2.0 open-source license, suitable for research and educational purposes.

Qwen2.5 is a series of novel language models built on the Qwen2 language model, which includes a general language model Qwen2.5, as well as specialized models aimed at programming (Qwen2.5-Coder) and mathematics (Qwen2.5-Math). These models have been pre-trained on extensive datasets, demonstrating robust knowledge comprehension and multilingual support, making them suitable for various complex natural language processing tasks. Their primary advantages include higher knowledge density, enhanced programming and mathematical capabilities, and better understanding of long texts and structured data. The release of Qwen2.5 marks a significant advancement in the open-source community, providing developers and researchers with powerful tools to drive research and development in the field of artificial intelligence.

MAVIS is a mathematical visual instruction tuning model designed for multimodal large language models (MLLMs). It enhances MLLMs' capabilities in visual mathematical problem-solving by improving visual encoding of mathematical graphs, graph-language alignment, and mathematical reasoning skills. The model includes two newly curated datasets, a mathematical visual encoder, and a mathematical MLLM, achieving leading performance in the MathVerse benchmark test through a three-phase training paradigm.

ChatGLM-Math is a math problem-solving model custom-designed based on a self-critical process, aimed at improving the mathematical problem-solving capabilities of large language models (LLMs). The model provides feedback signals by training a general Math-Critique model and enhances the mathematical problem-solving ability of LLMs by adopting rejection sampling refinement and direct preference optimization. It has been experimentally tested on both academic datasets and newly created challenging datasets MathUserEval, demonstrating a significant improvement in mathematical problem-solving capabilities while maintaining linguistic ability.

X-Fire Cognitive Large Model, launched by iFLYTEK, is a new generation of cognitive intelligence large model with cross-domain knowledge and language understanding capabilities, capable of understanding and executing tasks based on natural conversational ways. It has multiple capabilities, including language understanding, knowledge question answering, logical reasoning, mathematical problem solving, and code understanding and writing. This product is positioned to provide users with comprehensive solutions for language understanding and task execution.