NarendraK1/Qwen2.5-1.5B-Open-R1-Distill

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:May 1, 2025Architecture:Transformer Cold

NarendraK1/Qwen2.5-1.5B-Open-R1-Distill is a 1.5 billion parameter language model, fine-tuned from Qwen/Qwen2.5-1.5B-Instruct. It was specifically trained on the open-r1/OpenR1-Math-220k dataset using the TRL framework, giving it enhanced capabilities for mathematical reasoning and problem-solving. With a context length of 32768 tokens, this model is optimized for tasks requiring robust mathematical understanding and generation.

Loading preview...

Overview

NarendraK1/Qwen2.5-1.5B-Open-R1-Distill is a 1.5 billion parameter language model, fine-tuned from the base Qwen/Qwen2.5-1.5B-Instruct model. This model has been specialized through training on the open-r1/OpenR1-Math-220k dataset, utilizing the TRL framework.

Key Capabilities

  • Enhanced Mathematical Reasoning: Specifically trained on a math-focused dataset to improve performance on quantitative tasks.
  • Instruction Following: Inherits instruction-following capabilities from its base Qwen2.5-1.5B-Instruct model.
  • Efficient Deployment: As a 1.5 billion parameter model, it offers a balance of performance and computational efficiency.

Good For

  • Mathematical Problem Solving: Ideal for applications requiring the generation or understanding of mathematical solutions and explanations.
  • Educational Tools: Can be integrated into platforms for tutoring or generating math-related content.
  • Research in Small Language Models: Suitable for exploring the capabilities of smaller models fine-tuned for specific domains like mathematics.