teetone/OpenR1-Distill-Qwen3-1.7B-Math

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Jan 18, 2026Architecture:Transformer Warm

teetone/OpenR1-Distill-Qwen3-1.7B-Math is a fine-tuned language model based on Qwen3-1.7B-Base, specifically optimized for mathematical reasoning and complex thought processes. It was trained using Supervised Fine-Tuning (SFT) on the open-r1/Mixture-of-Thoughts dataset, enhancing its ability to handle intricate problem-solving. This model is designed for applications requiring robust logical deduction and mathematical understanding, offering specialized performance in a compact 1.7 billion parameter architecture.

Loading preview...

OpenR1-Distill-Qwen3-1.7B-Math Overview

This model is a specialized variant of the Qwen3-1.7B-Base architecture, fine-tuned by teetone to excel in mathematical reasoning and complex problem-solving. It leverages the open-r1/Mixture-of-Thoughts dataset for its training, which is designed to improve a model's ability to process and generate logical thought chains.

Key Capabilities

  • Enhanced Mathematical Reasoning: Specifically trained to handle mathematical problems and logical deductions more effectively than its base model.
  • Complex Thought Processing: Benefits from the Mixture-of-Thoughts dataset, which aims to instill better reasoning capabilities.
  • Efficient Architecture: Built upon the 1.7 billion parameter Qwen3-1.7B-Base, offering a balance of performance and computational efficiency.

Good For

  • Mathematical Problem Solving: Ideal for applications requiring accurate numerical and logical reasoning.
  • Educational Tools: Can be used in systems that help users understand and solve math problems.
  • Reasoning-intensive Tasks: Suitable for scenarios where a model needs to demonstrate a "chain of thought" or logical progression to arrive at an answer.