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

If it's not in front of me, it's gone: I fine-tuned a 4B model for my friend with ADHD

说明与用途

"Actually" 应用通过 4B 模型和 TabPFN 预测真实耗时,帮助 ADHD 用户保持任务可见并避免遗忘。

问题

A friend with ADHD forgets tasks that are not physically present and gets hyperfocused on one task, causing other tasks to be ignored.

结果

The fine‑tuned 4B model achieved 100% valid JSON and 97% task F1 on held‑out dumps, outperforming zero‑shot baselines. The app runs locally on a single laptop and costs $2.81 to build.

工作流

  • 1. User types a brain‑dump in natural language.
  • 2. A 4B Qwen3.5 model fine‑tuned on Tinker parses the dump into structured tasks in JSON.
  • 3. TabPFN reads the user’s past guessed vs actual durations and predicts a realistic duration, confidence range, and finish‑today probability for each task.
  • 4. The UI displays tasks with estimated durations, ranges, and a "Move to tomorrow" flag for tasks that don’t fit the day.
  • 5. User marks tasks as done to remove them from the list.

证据

If infront remember or else gone from brain. person or task

来源

Qwen3.5-4B + LoRA 100% valid JSON, 97% task F1

来源

The parser: a 4B model that reads a brain‑dump.

来源

  • 记录日期: 2026-10-05T03:41:02.661Z