FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Jan 24, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview is a 32.8 billion parameter language model developed by FuseAI, designed to enhance System-II reasoning capabilities through advanced model fusion techniques. This specific variant utilizes a Long-Short Reasoning Merging approach, integrating DeepSeek-R1-Distill-Qwen-32B, QwQ-32B-Preview, and Sky-T1-32B-Flash to improve reasoning across both long and short reasoning processes. It demonstrates strong performance in mathematics, coding, and scientific reasoning tasks, particularly on benchmarks like AIME24 and LiveCodeBench.

Loading preview...