# 0xdeadf1sh/T1DMAI

> A model zoo of blood glucose forecasting models trained on the author's own data and the public MetaboNet dataset. Includes a small transformer model (31k parameters) and classical baselines for research and educational purposes.

- Magnitude: 2.1 out of 10 — Steady
- Stars: 34 total · +11 stars measured 2026-11-14, 00:12–11:17 UTC, ≈ 17 by evening
- Star trust: star growth looks organic
- Category: Science & research · Language: Python · License: MIT · Created: 2026-07-29 · Last push: 2026-11-13
- GitHub: https://github.com/0xdeadf1sh/T1DMAI · Page: https://gitnova.dev/en/r/0xdeadf1sh/T1DMAI

## Useful for

- Compare forecasts of different models (XGBoost, LSTM, transformer) on your own CGM data
- Train a LoRA adapter to fine-tune the model on real data without full retraining
- Run the model on a smartphone via ExecuTorch or LiteRT for local forecasting

## Why it’s here

- Star-counter measurements on 2026-11-14 (UTC), 00:12–11:17: 23 → 34 stars (+11). This is the change over that interval.
- Estimated end-of-day forecast: about +17 stars, using observed gains and the previous day.
- Hacker News: “Show HN: I have trained 15 blood glucose forecasting models on my own data” — 36 points, 3 days ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2
- Issues and pull requests: 0
- Watchers: 1
- Average over the last week: 4 per day
- Usual pace: 0 per day
- Stars in the last hour (measured): 4

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-16 … 2026-11-14: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 3, 1, 1, 11

## Magnitude by day, last 5 days

11-10 1.0, 11-11 2.3, 11-12 1.6, 11-13 1.0, 11-14 2.1

## Hacker News

- Show HN: I have trained 15 blood glucose forecasting models on my own data — 36 points, 12 comments: https://news.ycombinator.com/item?id=50444761

## Spotted in now

- Spotted on Hacker News

## Similar by description

1. **google-research/timesfm** — 1.8 · Steady · Language models · Python · +14 stars measured 2026-11-14, 00:09–11:18 UTC, ≈ 27 by evening
   TimesFM is a pretrained time-series foundation model from Google Research for forecasting, designed to work zero-shot without task-specific training.
   Full card: https://gitnova.dev/en/r/google-research/timesfm.md
2. **shiyu-coder/Kronos** — 2.4 · Cooling · Finance & crypto · Python · +31 stars measured 2026-11-14, 00:06–11:16 UTC, ≈ 63 by evening
   Kronos is an open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 exchanges; it forecasts OHLCV series via tokenization and an autoregressive Transformer.
   Full card: https://gitnova.dev/en/r/shiyu-coder/Kronos.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-14 11:22 UTC, updated every 30 minutes.