TLDRocket
Sign in

Alibaba

38 summarised stories about Alibaba, each linking back to the original source. Browse all topics →

Wednesday, 7 August 2024

Introducing Qwen2-Math

Qwen 1 year ago

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.