Yashasya-1/qwen-math-finetune

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 14, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Yashasya-1/qwen-math-finetune is a 1.5 billion parameter Qwen2.5 model, finetuned by Yashasya-1, specifically optimized for mathematical tasks. This model leverages the Qwen2.5 architecture and was trained using Unsloth and Huggingface's TRL library for enhanced efficiency. With a context length of 32768 tokens, it is designed to provide robust performance in mathematical reasoning and problem-solving. Its specialized finetuning makes it particularly suitable for applications requiring accurate numerical and logical computations.

Loading preview...

Model Overview

Yashasya-1/qwen-math-finetune is a specialized 1.5 billion parameter language model built upon the Qwen2.5 architecture. Developed by Yashasya-1, this model has been meticulously finetuned from unsloth/Qwen2.5-Math-1.5B-Instruct-bnb-4bit with a strong emphasis on mathematical capabilities. The training process utilized Unsloth and Huggingface's TRL library, enabling a 2x faster training speed.

Key Capabilities

  • Mathematical Proficiency: Specifically optimized for handling mathematical queries and problems.
  • Efficient Training: Benefits from Unsloth's accelerated training techniques.
  • Qwen2.5 Foundation: Inherits the robust base architecture of the Qwen2.5 series.
  • Extended Context: Supports a substantial context length of 32768 tokens, allowing for complex problem descriptions.

Good For

  • Mathematical Reasoning: Ideal for tasks requiring numerical analysis, equation solving, and logical deduction.
  • Educational Tools: Can be integrated into platforms for math tutoring or problem generation.
  • Research & Development: Suitable for exploring advanced mathematical concepts and algorithms.

Finetunes
1 models