把 Qwen2.5-0.5B 改造为双向 encoder,接 11 个线性分类头,一次前向(17.7ms,p50)输出文本的完整安全画像:违规二判 + TC260 / 语言风险(LM)/ 隐私(PII)/ 内容分级(DC)四套体系的大类与小类 + 安全放行闸门。 - 判别式安全模型,非生成式 guard:无自回归、全头并行输出,单条 17.7ms vs 生成式 8B guard 的 281ms+(同数据重训对比)。 - backbone 为 HF Qwen2Model 结构(Qwen/Qwen2.5-0.5B 权重转 bidirectional 微调产物),推理时需全可见 attention(双向,非 causal)。 - 生产推理推荐配套的纯 C 本地引擎 verdict(CPU / Apple Metal GPU,零 Python 依赖,支持加密.vmd 打包分发)。 safetythreshold=0.95,校准方法 [email protected](FPR≤2% 约束下最大召回),校准集 finetunefinalv68val(259 safe / 1176 unsafe,实测 FPR 1.93%)。该阈值仅对训练分布可靠:偏离训练分布时 FPR 会上升(见局限)。releasegate=0.8055 为 safe 样本放行闸门,减少深误杀。 - 数据:v69a,17589 条(双模型生成 + 交叉验证过滤);四轨标签张量化 ~160 维 0/1,未标注位置 None 掩码。 - 配置:lr 2e-5、bf16、20 epochs(epoch…
Independent publisher
Louivislee
louivis
Models in Library1
Datasets in Library0
Models on Hugging Face3
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text classification.
Reported licenses: mit. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.