AutoTrust-JEV-27B-v1.1 在 Hugging Face 破 16K 下载
开源 27B 决策模型,为 agent 内的路由、选工具、越界意图检测等高频调用返回每个选项的概率,Apache-2.0,可用 vLLM 本地跑。
Thank you, @HuggingModels. AutoTrust-JEV-27B-v1.1 has now passed 16K downloads on Hugging Face. It is an open 27B decision model for the high-frequency calls inside agent systems: route a request, select a tool, detect an out-of-scope intent, verify a claim, or choose the next action from a fixed set of options. Instead of producing another paragraph, it returns a probability for every available option — making decisions measurable, routable, and easier to audit. Apache-2.0. Run it locally with vLLM: 📷https://huggingface.co/autotrust/AutoTrust-JEV-27B-v1.1
这条是引用着另一条写的:「AutoTrust-JEV-27B-v1.1:面向结构化决策的 27B 分类模型」