qingy2024/Qwen2.5-Math-14B-Instruct-Pro

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kPublished:Dec 3, 2024Architecture:Transformer Cold

qingy2024/Qwen2.5-Math-14B-Instruct-Pro is a 14.8 billion parameter instruction-tuned language model, merged using the TIES method from Qwen/Qwen2.5-14B-Instruct and qingy2019/Qwen2.5-Math-14B-Instruct-Alpha. This model is specifically optimized for mathematical reasoning and problem-solving tasks, leveraging its base models to enhance its capabilities in this domain. It supports a context length of 131072 tokens and is designed for applications requiring strong mathematical instruction following across multiple languages.

Loading preview...

Overview

qingy2024/Qwen2.5-Math-14B-Instruct-Pro is a 14.8 billion parameter instruction-tuned language model, created by qingy2024 through a merge of existing Qwen2.5 models. It leverages the TIES merge method with Qwen/Qwen2.5-14B as its base, combining the strengths of Qwen/Qwen2.5-14B-Instruct and qingy2019/Qwen2.5-Math-14B-Instruct-Alpha.

Key Capabilities

  • Enhanced Mathematical Reasoning: Specifically designed to excel in mathematical problem-solving and instruction following, building upon its math-focused base model.
  • Instruction Following: Inherits strong instruction-following capabilities from its parent Qwen2.5-14B-Instruct model.
  • Multilingual Support: Supports a wide array of languages including Chinese, English, French, Spanish, German, and more, making it suitable for global applications.
  • Large Context Window: Features a substantial context length of 131072 tokens, allowing for processing extensive mathematical problems or complex instructions.

Good for

  • Mathematical Applications: Ideal for tasks requiring precise mathematical calculations, proofs, and problem-solving.
  • Educational Tools: Can be used in AI tutors or platforms that assist with math homework and learning.
  • Technical Problem Solving: Suitable for scenarios where logical and numerical reasoning is critical.
  • Multilingual Instruction-Based Tasks: Effective in environments where mathematical instructions need to be understood and executed across various languages.

Finetunes
1 models