# vinnylarouge/jevlike

> A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection over variable option sets.

- Magnitude: 0.0 out of 10 — Quiet
- Stars: 1,352 total · Not enough measurements today
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-09-16 · Last push: 2026-09-16
- GitHub: https://github.com/vinnylarouge/jevlike · Page: https://gitnova.dev/en/r/vinnylarouge/jevlike

## Useful for

- Train a custom scorer to route customer messages to one of several support categories.
- Score next-click candidates in a navigation dataset like Wikispeedia.
- Fine-tune a small head on top of a frozen Hugging Face encoder for menu selection.

## Why it’s here

- There are not enough fresh counter measurements for today's UTC day. The gain is unknown.
- The repository is 34 days old and already has 1,352 stars.

## 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: 121
- Issues and pull requests: 8
- Watchers: 8
- Average over the last week: 0 per day
- Usual pace: 13 per day

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

2026-10-04 … 2026-11-02: 5, 3, 4, 1, 0, 2, 0, 0, 2, 1, 1, 1, 0, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-07 1.1, 10-08 0.8, 10-09 0.4, 10-10 0.6, 10-11 0.1, 10-12 0.4, 10-13 0.8, 10-14 0.7, 10-15 0.4, 10-16 0.3, 10-17 0.0, 10-18 0.0, 10-19 0.0, 10-20 0.0

## Hacker News

- Reverse-engineered Jev-like model — 168 points, 24 comments: https://news.ycombinator.com/item?id=49731282

---

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 2026-10-20 21:22 UTC, updated every 30 minutes.