NostraEmpire/mirror-qwen2.5-math-7b-instruct

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 31, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The NostraEmpire/mirror-qwen2.5-math-7b-instruct is a 7.6 billion parameter instruction-tuned model from the Qwen2.5-Math series, developed by Qwen. It is specifically optimized for solving mathematical problems in both English and Chinese, utilizing Chain-of-Thought (CoT) and Tool-integrated Reasoning (TIR) for enhanced accuracy. This model is designed primarily for mathematical tasks, offering significant performance improvements over its predecessor, Qwen2-Math.

Loading preview...

Overview

NostraEmpire/mirror-qwen2.5-math-7b-instruct is part of the Qwen2.5-Math series, an upgraded suite of mathematical Large Language Models developed by Qwen. This 7.6 billion parameter instruction-tuned model is specifically designed to excel in solving mathematical problems. It builds upon the previous Qwen2-Math series by expanding its capabilities to support both English and Chinese mathematical tasks.

Key Capabilities

  • Mathematical Problem Solving: Primarily focused on mathematics, supporting both English and Chinese problems.
  • Reasoning Mechanisms: Utilizes two core reasoning approaches:
    • Chain-of-Thought (CoT): For step-by-step reasoning.
    • Tool-integrated Reasoning (TIR): Enhances computational accuracy and handles complex mathematical or algorithmic tasks by integrating external tools.
  • Performance Improvements: Achieves significant performance gains on Chinese and English mathematics benchmarks compared to the Qwen2-Math series, particularly with CoT.
  • Benchmark Performance: The Qwen2.5-Math-7B-Instruct model achieves 85.3 on the MATH benchmark using TIR.

When to Use This Model

  • Primary Use Case: This model is highly recommended for tasks involving the solution of mathematical problems, especially those requiring detailed reasoning or precise computation.
  • Language Support: Suitable for both English and Chinese mathematical contexts.
  • Specific Warning: The developers explicitly state that this model is primarily for solving math problems and do not recommend using it for other tasks.

Finetunes
1 models