Supersonic Labs 发布分类模型 Julia-1，训练成本仅 104 美元
巴西团队用 104 美元训了个分类模型 Julia-1，还开源了。如果你在搭 agent 框架，可以试试分类器加推理模型混合调度这个思路。
Supersonic Labs 发布开源分类模型 Julia-1，官方称其可在几乎所有设备上运行。模型训练与实验的云 GPU 支出约为 R$540（约 104.08 美元）。DAIR.AI 此前构建的情感数据集被用于测试该模型。作者建议开发者将这类快速分类模型（System One）与推理型模型（System Two）组合搭建混合系统，在特定领域问题上表现更佳。
Cool to see classification models resurge in the era of agents. The effects of Jev are insane. Also very cool to see our emotion dataset built at @dair_ai used to test this new model, Julia-1. I spent my entire PhD building efficient classifiers from scratch (from graph-based to deep learning), so it's exciting to see this trend again. So much nostalgia. More importantly, if you build agent harnesses today (where all the edge is now that model capabilities have clustered), it's worth spending time running experiments that combine System One models and System Two models. You'll realize how many problems a great classifier (what I now call a System One model) can solve. Hybrid systems have historically performed better on domain-specific problems, and that still holds, even with general-purpose frontier models. Build your harness, create the evals, and run the experiments yourself. You will learn so much and gain great insights to take advantage of these advancements. This is a great example of what open-source enables. This is a work in progress. The cloud GPU spending on Julia 1 training and experiments was about R$540 (US$104.08). Will we see a new type of frontier lab focused on these models? Supersonic Labs @supersonicai Introducing Julia-1: Our first classification model that runs on almost anything. Learn more 👇 supersoniclabs.ia.br/julia-1/ o 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 3 👀 868 📊 1 ⚡
