VanWang

DeepSeek-R1-Distill-Qwen-7B-ThinkPO

VanWang/DeepSeek-R1-Distill-Qwen-7B-ThinkPO

DeepSeek-R1-Distill-Qwen-7B-ThinkPO is a machine learning model from VanWang. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

a simple yet effective postSFT method that enhances long CoT reasoning without requiring new long CoT responses - Here, we show the results of open-source reasoning LLMs before and after ThinkPO.