firelex/jeff
Fine-tunes of Qwen3.5 and Gemma 4 for zero-shot classification
About the project
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.
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
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 77 stars today.
- The repository is 0 days old and already has 60 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms” — 81 points, 1 h ago.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 60
- Today
- 77
- Forks
- 4
- Issues and pull requests
- 0
- Watchers
- 1
- Language
- Python
- License
- MIT
- Created
- September 28, 2026
- Last push
- September 28, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms81 points, September 28, 2026
Spotted in
- September 28, 2026Top new repositories this week: #136; Spotted on Hacker News
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/firelex/jeff)Similar by description
-
4.1
Mapika/decider
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…
-
1.1
allebee/jevk5
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.…
-
3.8
jaredpalmer/kev
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.
-
0.0
AndrewPrifer/jimothy
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.
-
0.6
kshetrajna12/reflex
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.
-
3.9
Rizzo-AI-Academy/rizzo-flow
A local-first implementation of the Jev idea: an LLM returns typed decisions (boolean, choice, score, numeric) with probabilities in a single forward pass, without generating tokens. Compatible with the TypeSafe HTTP…