najmahal/qwen-math-tagalog-1.5b-merged
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Mar 6, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The najmahal/qwen-math-tagalog-1.5b-merged is a 1.5 billion parameter Qwen2-based causal language model developed by najmahal. This model is specifically fine-tuned for mathematical tasks with an emphasis on the Tagalog language, leveraging the unsloth/qwen2.5-math-1.5b-instruct-bnb-4bit base. It is optimized for efficient training using Unsloth and Huggingface's TRL library, making it suitable for mathematical reasoning in a Tagalog context.

Loading preview...

Model Overview

The najmahal/qwen-math-tagalog-1.5b-merged is a 1.5 billion parameter language model developed by najmahal. It is built upon the Qwen2 architecture and has been specifically fine-tuned from the unsloth/qwen2.5-math-1.5b-instruct-bnb-4bit base model. This model is designed to handle mathematical tasks, with a particular focus on the Tagalog language.

Key Characteristics

  • Architecture: Based on the Qwen2 family of models.
  • Parameter Count: Features 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Language Focus: Specialized for mathematical reasoning and problem-solving within the Tagalog language context.
  • Training Efficiency: The model was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training times.

Intended Use Cases

This model is particularly well-suited for applications requiring:

  • Mathematical problem-solving in Tagalog.
  • Educational tools or platforms for Tagalog-speaking users focused on mathematics.
  • Research into multilingual mathematical reasoning, specifically involving Tagalog.
  • Development of AI assistants or chatbots that can process and respond to mathematical queries in Tagalog.