InfiniAILab/OpenR1-Qwen-3B-SFT-Instruct

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Mar 8, 2025Architecture:Transformer0.0K Warm

InfiniAILab/OpenR1-Qwen-3B-SFT-Instruct is a 3.1 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen2.5-3B-Instruct. Developed by InfiniAILab, this model specializes in mathematical reasoning and problem-solving, leveraging the OpenR1-Math-220k dataset. Its training focuses on enhancing performance for complex mathematical tasks and logical deduction.

Loading preview...

Model Overview

InfiniAILab/OpenR1-Qwen-3B-SFT-Instruct is a 3.1 billion parameter language model built upon the Qwen2.5-3B-Instruct architecture. This model has undergone supervised fine-tuning (SFT) using the open-r1/OpenR1-Math-220k dataset, specifically targeting enhanced mathematical reasoning and problem-solving capabilities. The fine-tuning process was conducted using the TRL framework.

Key Capabilities

  • Mathematical Reasoning: Specialized training on a dedicated math dataset improves its ability to understand and solve mathematical problems.
  • Instruction Following: Inherits strong instruction-following capabilities from its base Qwen2.5-3B-Instruct model.
  • Efficient Performance: As a 3.1 billion parameter model, it offers a balance between performance and computational efficiency.

Good For

  • Applications requiring robust mathematical problem-solving.
  • Tasks involving logical deduction and quantitative analysis.
  • Scenarios where a smaller, specialized model is preferred for efficiency without sacrificing mathematical accuracy.