yuerxin/OpenR1-Distill-1.5B
OpenR1-Distill-1.5B by yuerxin is a 1.5 billion parameter language model fine-tuned from Qwen/Qwen2.5-Math-1.5B. It has been specifically trained on the open-r1/Mixture-of-Thoughts dataset using SFT, making it suitable for tasks requiring complex reasoning and thought processes. With a context length of 32768 tokens, this model is designed to handle detailed and multi-step problem-solving scenarios.
Loading preview...
Model Overview
The yuerxin/OpenR1-Distill-1.5B is a 1.5 billion parameter language model, building upon the Qwen/Qwen2.5-Math-1.5B architecture. This model has undergone supervised fine-tuning (SFT) using the open-r1/Mixture-of-Thoughts dataset, which is designed to enhance reasoning capabilities.
Key Capabilities
- Enhanced Reasoning: Fine-tuned on a dataset focused on 'Mixture-of-Thoughts', suggesting improved performance in tasks requiring logical deduction and multi-step thinking.
- Qwen2.5 Base: Leverages the robust foundation of the Qwen2.5-Math series, potentially inheriting strong mathematical and analytical abilities.
- Generative Text: Capable of generating coherent and contextually relevant text, as demonstrated by the quick start example.
- Large Context Window: Supports a context length of 32768 tokens, allowing for processing and generating longer, more complex inputs and outputs.
Training Details
The model was trained using the TRL library (Transformer Reinforcement Learning) with SFT. This approach typically involves training on high-quality instruction-following data to align the model's outputs with desired behaviors.
Use Cases
This model is particularly well-suited for applications that benefit from advanced reasoning and the ability to process extensive contextual information. Potential use cases include:
- Complex Question Answering: Handling questions that require multi-step reasoning.
- Problem Solving: Assisting in tasks that involve logical inference.
- Content Generation: Creating detailed and thought-out responses or narratives.