# firelex/jeff

> Small fine-tuned Qwen3.5 and Gemma 4 models for zero-shot classification: given a situation description and a list of options, they return a calibrated probability for each option in a single forward pass.

- Magnitude: 6.5 out of 10 — Early signal
- Stars: 119 total · +132 stars today
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-09-28 · Last push: 2026-09-28
- GitHub: https://github.com/firelex/jeff · Page: https://gitnova.dev/en/r/firelex/jeff

## Useful for

- Route support tickets to teams without training examples
- Detect user intent or moderation labels from text
- Run a local classification HTTP service on GPU or Apple Silicon

## Why it’s here

- 132 stars today.
- The repository is 0 days old and already has 119 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #136.
- Hacker News: “Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms” — 124 points, 2 h 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: 4
- Issues and pull requests: 0
- Watchers: 1
- Average over the last week: 138 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 74

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-09-27 … 2026-09-28: 0, 132

## Hacker News

- Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms — 124 points, 29 comments: https://news.ycombinator.com/item?id=49883844

## Spotted in now

- Top new repositories this week: #136
- Spotted on Hacker News

## Similar by description

1. **Mapika/decider** — 4.1 · Breakout · Language models · Python · +14 stars today
   A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model class built on…
   Full card: https://gitnova.dev/en/r/Mapika/decider.md
2. **allebee/jevk5** — 1.1 · Cooling · Language models · Python · +0 stars today
   An open-weight alternative to TypeSafe Jev: given a state (ticket, log, policy, diff) and a yes/no, choice, or score question, it returns a probability for every option in one forward pass with zero generated tokens. Qwen3.5-4B weights…
   Full card: https://gitnova.dev/en/r/allebee/jevk5.md
3. **jaredpalmer/kev** — 3.8 · Cooling · Language models · Python · +148 stars today
   kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
   Full card: https://gitnova.dev/en/r/jaredpalmer/kev.md
4. **AndrewPrifer/jimothy** — 0.0 · Steady · Language models · TypeScript · +0 stars today
   A tool for training small local text classifiers from Jev-compatible examples. Runs in the browser or Node.js, with TF-IDF and MiniLM backends.
   Full card: https://gitnova.dev/en/r/AndrewPrifer/jimothy.md
5. **kshetrajna12/reflex** — 0.6 · Steady · Language models · Python · +2 stars today
   An open decision model: given a state (text, JSON, or image) and typed questions, it returns calibrated probabilities over fixed answer options. Runs on top of Qwen3.5 and answers with numbers instead of free text.
   Full card: https://gitnova.dev/en/r/kshetrajna12/reflex.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 2026-09-28 22:49 UTC, updated every 30 minutes.