把 Jev 风格决策模型蒸馏成两个小模型自托管
用 1000 条人工标注消息训练小 LLM 分类器和更小的逻辑回归，效果追平 Open-Jev 27B 教师模型，可自持模型与数据流向。
Jev from @typesafeai has obviously been on everyone's minds this past week. 'System One' models, decision models, smart classifiers, whatever you want to call them... they're very useful. We even built them into Kitaru as a whole new 'judge evaluator' package. But what if you want to own the model and where the data gets sent? I distilled an open Jev-style model into two small students, inspired by an article by @sjgoedecke (linked below). We used 1000 human-graded messages (h/t the Banking77 dataset on @huggingface) to train a small LLM-driven classifier and an even smaller logistic regression model that performed equally to the Open-Jev 27B parameter teacher model (thanks @Zefan_Cai!).