Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

I Distilled a 397B Model Into a 4B One for $1.60. It Now Catches 28 of 33 Park Alerts That Should Stop Your Hike

说明与用途

使用 LoRA 微调的 Qwen3.5‑4B 模型将决策准确率提升至 74.6%,检测到 33 条关键警报中的 28 条,运行成本为每 1,000 条警报 $0.13。

问题

National Park Service alerts are long and many hikers ignore them, leading to unsafe hikes.

结果

The 4B LoRA model improves decision accuracy from 64.3% to 74.6% and catches 28 of 33 critical alerts, while the entire pipeline costs $1.60 to build and $0.13 per 1,000 alerts to run.

工作流

  • Collect alerts via NPS API for selected parks
  • Run each alert through fine‑tuned Qwen3.5‑4B LoRA
  • Generate a printable card with overall verdict and trail list
  • Print or screenshot the card
  • Use card to decide whether to hike

证据

On 126 held‑out alerts the fine‑tuned 4B went from catching 17 of 33 alerts that should stop a hiker to 28 of 33, and from 64.3% to 74.6% decision accuracy.

来源

It costs $0.13 per 1,000 alerts, about 11× less than the teacher, and the whole ML pipeline cost $1.60.

来源

The model's only job is to produce one printable card a week, so you can stop checking park alerts and go outside.

来源

  • 记录日期: 2026-10-10T14:56:20.393Z