najmahal/qwen-math-cebuano-1.5b-merged

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Mar 5, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The najmahal/qwen-math-cebuano-1.5b-merged is a 1.5 billion parameter Qwen2-based language model developed by najmahal, fine-tuned for mathematical tasks. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. This model is specifically adapted for mathematical problem-solving, offering a specialized tool for applications requiring numerical reasoning.

Loading preview...

Model Overview

The najmahal/qwen-math-cebuano-1.5b-merged is a 1.5 billion parameter language model developed by najmahal, fine-tuned from unsloth/qwen2.5-math-1.5b-instruct-bnb-4bit. This model leverages the Qwen2 architecture and is specifically optimized for mathematical reasoning tasks.

Key Characteristics

  • Architecture: Based on the Qwen2.5 model family.
  • Parameter Count: 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Fine-tuning: The model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Specialization: Primarily focused on mathematical instruction following and problem-solving.

Intended Use Cases

  • Mathematical Applications: Ideal for tasks requiring numerical understanding, calculations, and mathematical reasoning.
  • Educational Tools: Can be integrated into systems for teaching or assisting with math problems.
  • Research: Suitable for exploring the capabilities of smaller, specialized models in mathematical domains.