返回全部动态
Qwen3Guard发布:实时流式安全检测护栏模型
原标题:Qwen3Guard: Real-time Safety for Your Token Stream
AI 摘要
Qwen团队发布了Qwen3Guard,这是Qwen系列首个安全护栏模型,基于Qwen3微调,支持提示和响应的安全分类,并提供风险等级和分类标签。该模型提供Gen和Stream两种变体,分别用于离线标注和实时流式检测,支持119种语言,并已在Hugging Face和ModelScope开源。Qwen3Guard在安全基准上达到先进水平,并可通过阿里云AI护栏服务使用。
以上摘要由 AI 生成,可能存在误差。事实请以原文为准。
正文节选
Introduction We are excited to introduce Qwen3Guard, the first safety guardrail model in the Qwen family. Built upon the powerful Qwen3 foundation models and fine-tuned specifically for safety classificatoin, Qwen3Guard ensures responsible AI interactions by delivering precise safety detection for both prompts and responses, complete with risk levels and categorized classifications for accurate moderation. Qwen3Guard achieves state-of-the-art performance on major safety benchmarks, demonstrating
发布时间:2025-09-23 04:00
抓取时间:2026-08-31 00:56
来源机构:Alibaba Qwen