ReasoningTransferability/UniReason-Qwen3-14B-think-SFT
TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kPublished:Jul 4, 2025License:apache-2.0Architecture:Transformer Open Weights Cold

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...