QwenLM/Qwen2.5-Math
A series of math-specialized large language models in the Qwen2 family, supporting Chain-of-Thought and Tool-integrated Reasoning for English and Chinese math problems.
Velocity · 7d
+1.6
★ / day
Trend
→steady
star history
Qwen2.5-Math provides a suite of models including base models (1.5B/7B/72B), instruction-tuned variants, and a 72B mathematical reward model. Unlike its predecessor, it supports both Chain-of-Thought reasoning and Tool-integrated Reasoning to solve math problems in English and Chinese. The models are available on Hugging Face, ModelScope, and Kaggle.