Holistic Capability Preservation: Towards Compact Yet Comprehensive Reasoning Models
This work addresses the need for efficient, comprehensive reasoning models in AI, though it appears incremental as it builds on existing MoE architectures and distillation techniques.
The paper tackles the problem of creating compact reasoning models by developing Ring-Lite-Distill, a lightweight Mixture-of-Experts model with 2.75 billion activated parameters, which achieves reasoning ability comparable to DeepSeek-R1-Distill-Qwen-7B while significantly surpassing it in general capabilities like instruction following and tool use.
This technical report presents Ring-Lite-Distill, a lightweight reasoning model derived from our open-source Mixture-of-Experts (MoE) Large Language Models (LLMs) Ling-Lite. This study demonstrates that through meticulous high-quality data curation and ingenious training paradigms, the compact MoE model Ling-Lite can be further trained to achieve exceptional reasoning capabilities, while maintaining its parameter-efficient architecture with only 2.75 billion activated parameters, establishing an efficient lightweight reasoning architecture. In particular, in constructing this model, we have not merely focused on enhancing advanced reasoning capabilities, exemplified by high-difficulty mathematical problem solving, but rather aimed to develop a reasoning model with more comprehensive competency coverage. Our approach ensures coverage across reasoning tasks of varying difficulty levels while preserving generic capabilities, such as instruction following, tool use, and knowledge retention. We show that, Ring-Lite-Distill's reasoning ability reaches a level comparable to DeepSeek-R1-Distill-Qwen-7B, while its general capabilities significantly surpass those of DeepSeek-R1-Distill-Qwen-7B. The models are accessible at https://huggingface.co/inclusionAI