DeepSeek-R1-Distilled-NPU-Optimized

Learn more: [original model announcement ]

DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimized models let developers build and deploy AI-powered applications that run efficiently on-device, taking full advantage of the powerful NPUs in Copilot+ PCs.

The DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. These models excel at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks.

Model variant included in the package

• DeepSeek-R1-Distill-Qwen-1.5B optimized for NPU

DeepSeek-R1-Distill-Qwen-1.5B is based on Qwen2.5-Math-1.5B. Qwen2.5-Math series is expanded to support using both CoT and Tool-integrated Reasoning (TIR) to solve math problems in both Chinese and English. The Qwen2.5-Math series models have achieved significant performance improvements compared to the Qwen2-Math series models on the Chinese and English mathematics benchmarks with CoT.

Additional recommendations

The model's reasoning output (contained within the <think> tags) may contain more harmful content than the model's final response. Consider how your application will use or display the reasoning output; you may want to suppress the reasoning output in a production setting.