Mica v0.1 4B: open Jev-style decision model (yes/no, choice, score) that runs on an 8 GB GPU — trained for under $30 of GPU time
英文标题:Mica v0.1 4B: open Jev-style decision model (yes/no, choice, score) that runs on an 8 GB GPU — trained for under $30 of GPU time
I've been building a small decision model for agent loops: gates, routers, "should I ask the user or just act" checks. It's out now as Mica v0.1 4B (Apache-2.0). What it does You give it a state, a question and the allowed answers, and it returns a calibrated probability for each answer: yes/n
中文
I've been building a small decision model for agent loops: gates, routers, "should I ask the user or just act" checks. It's out now as Mica v0.1 4B (Apache-2.0). What it does You give it a state, a question and the allowed answers, and it returns a calibrated probability for each answer: yes/n
中文全文翻译正在补齐,可先查看下方英文原文。
English / 原文
I've been building a small decision model for agent loops: gates, routers, "should I ask the user or just act" checks. It's out now as Mica v0.1 4B (Apache-2.0). What it does You give it a state, a question and the allowed answers, and it returns a calibrated probability for each answer: yes/n