Introducing Qwen2-Math
Qwen
Alibaba's Qwen team released Qwen2-Math, a series of specialized mathematical language models in sizes 1.5B, 7B, and 72B parameters, which outperforms GPT-4o, Claude-3.5-Sonnet, and Gemini-1.5-Pro on mathematical benchmarks including GSM8K, MATH, and competition exams like AIME 2024. The largest model Qwen2-Math-72B-Instruct was trained using a math-specific reward model combined with reinforcement learning via Group Relative Policy Optimization. The models demonstrate capability on complex mathematical problems including International Mathematical Olympiad questions, suggesting improved reasoning for mathematical problem-solving applications.
Why it matters
GITHUB HUGGING FACE MODELSCOPE DISCORD 🚨 This model mainly supports English. We will release bilingual (English and Chinese) math models soon. Introduction Over the past year, we have dedicated significant effort to researching and enhancing the reasoning capabilities of large language models, with a particular focus on their ability to solve arithmetic and mathematical problems. Today, we are delighted to introduce a series of math-specific large language models of our Qwen2 series, Qwen2-Math and Qwen2-Math-Instruct-1.