XueZhang-bjtu/1.5B-cold-start-SFT
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Oct 14, 2025License:apache-2.0Architecture:Transformer Open Weights Warm

XueZhang-bjtu/1.5B-cold-start-SFT is a 1.5 billion parameter language model developed by XueZhang-bjtu, serving as a foundational SFT model for the M-Thinker series. It is based on DeepSeek-R1-Distill-Qwen-1.5B and fine-tuned with the M-Thinker-SFT-data. This model is designed to be a starting point for further reinforcement learning, specifically for enhancing multilingual reasoning capabilities and ensuring language consistency in thought processes.

Loading preview...