ReasoningTransferability/UniReason-Qwen3-14B-think-SFT
The UniReason-Qwen3-14B-think-SFT model, developed by ReasoningTransferability, is a 14 billion parameter Qwen3-14B-Base variant fine-tuned for math-reasoning capabilities. It was distilled from Qwen3-32B-Instruct (thinking mode) using reject sampling, as part of research into the transferability of mathematical reasoning to general LLM tasks. This model investigates how specialized math training impacts broader language understanding and performance. It is primarily focused on exploring the trade-offs between specialized math performance and general capabilities.
Loading preview...
UniReason-Qwen3-14B-think-SFT Overview
This model is a 14 billion parameter variant of the Qwen3-14B-Base architecture, developed by ReasoningTransferability. It was fine-tuned through distillation from Qwen3-32B-Instruct (thinking mode) using reject sampling, with a primary focus on enhancing math-reasoning capabilities. The model is a key component of research exploring the transferability of mathematical reasoning skills to general language tasks, as detailed in the associated paper: "Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning" (2507.00432).
Key Research Findings & Capabilities
- Math Reasoning Specialization: The model is specifically optimized for mathematical problem-solving, investigating how such specialization impacts broader LLM performance.
- Transferability Research: It helps analyze whether math reasoning training improves general LLM capabilities and the trade-offs involved.
- Training Method Analysis: The research compares the effects of different training methods (like RL vs. SFT) on capability transfer, noting that SFT-tuned models may experience "forgetting" of general capabilities during math-focused training.
Limitations and Considerations
- Specialization Trade-offs: Models optimized for math reasoning may exhibit reduced performance on general tasks.
- Domain Transfer: The extent to which capabilities transfer from math to other domains is limited.
- Computational Requirements: Inference with this model requires significant computational resources.
This model is intended for research purposes to understand the complex interplay between specialized training and general LLM capabilities.