FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Instruct-32B-Preview
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Jan 20, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Instruct-32B-Preview is a 32.8 billion parameter language model developed by FuseAI, leveraging innovative System-II reasoning fusion techniques. This model is a result of 'Long-Short Reasoning Merging' of DeepSeek-R1-Distill-Qwen-32B and Qwen2.5-32B-Instruct, designed to enhance reasoning capabilities in both long and short reasoning processes. It demonstrates strong performance in mathematics, coding, and scientific reasoning tasks, particularly excelling in long reasoning benchmarks.

Loading preview...