jnian/Qwen2.5-0.5B-Open-R1-Distill
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Mar 10, 2025Architecture:Transformer Featherless Exclusive Warm
jnian/Qwen2.5-0.5B-Open-R1-Distill is a 0.5 billion parameter language model, fine-tuned from Qwen/Qwen2.5-0.5B-Instruct. This model specializes in mathematical reasoning, having been trained on the OpenR1-Math-220k dataset using the GRPO method. It is optimized for tasks requiring robust mathematical problem-solving capabilities.
Loading preview...
Overview
jnian/Qwen2.5-0.5B-Open-R1-Distill is a 0.5 billion parameter language model derived from Qwen/Qwen2.5-0.5B-Instruct. It has been specifically fine-tuned for enhanced mathematical reasoning, leveraging the OpenR1-Math-220k dataset.
Key Capabilities
- Mathematical Reasoning: The model's primary strength lies in its ability to process and solve mathematical problems, a result of its specialized training.
- GRPO Training Method: It was trained using GRPO (Gradient-based Reward Policy Optimization), a method introduced in the DeepSeekMath paper, which is designed to push the limits of mathematical reasoning in open language models.
- Efficient Size: At 0.5 billion parameters, it offers a compact solution for integrating mathematical reasoning capabilities into applications.
Good For
- Applications requiring a dedicated model for mathematical problem-solving.
- Scenarios where a smaller, specialized model is preferred over larger, general-purpose LLMs for math-centric tasks.
- Developers looking to leverage the GRPO training approach for improved mathematical performance.