RISys-Lab/RedSage-Qwen3-8B-DPO
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Oct 15, 2025Architecture:Transformer0.0K Cold

RISys-Lab/RedSage-Qwen3-8B-DPO is the final, aligned version of the RedSage cybersecurity LLM series developed by RISysLab. This 8B parameter model is fine-tuned from RedSage-Qwen3-8B-Ins using Direct Preference Optimization (DPO) on the AllenAI Tulu 3 Preference Mixture. It significantly enhances general reasoning capabilities and safety behaviors while maintaining deep cybersecurity domain expertise. The model excels in general-purpose cybersecurity assistance, log analysis, threat intelligence summarization, and educational queries.

Loading preview...