# jiwidi/jiwo

> Small decision models built on Qwen3.5 that return probabilities for answer options (choice, score, noul) in a single forward pass without generating text, with a median latency of about 50 ms on an H100.

- Magnitude: 3.1 out of 10 — Early signal
- Stars: 89 total · +6 stars measured 2026-10-09, 00:05–05:01 UTC, ≈ 34 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-10-05 · Last push: 2026-10-05
- GitHub: https://github.com/jiwidi/jiwo · Page: https://gitnova.dev/en/r/jiwidi/jiwo

## Useful for

- Classify support tickets into teams with calibrated probabilities
- Score urgency or sentiment of a text on a scale without generating text
- Run a local jiwo serve HTTP server for low-latency inference

## Why it’s here

- Star-counter measurements on 2026-10-09 (UTC), 00:05–05:01: 83 → 89 stars (+6). This is the change over that interval.
- Estimated end-of-day forecast: about +33 stars, using observed gains and the previous day.
- The repository is 4 days old and already has 89 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #173.

## 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: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 24 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-10-04 … 2026-10-09: 0, 12, 19, 21, 37, 6

## Spotted in now

- Top new repositories this week: #173

## Similar by description

1. **strands-labs/strands-decider** — 2.4 · Steady · AI agents · Python · +6 stars measured 2026-10-09, 00:06–05:03 UTC, ≈ 28 by evening
   A small, fast decision model for agentic workflows: picks among options, answers yes/no, or rates on a scale, returning calibrated confidence. Faster than an LLM and requires no classifier training.
   Full card: https://gitnova.dev/en/r/strands-labs/strands-decider.md
2. **jaredpalmer/kev** — 2.6 · Steady · Language models · Python · +11 stars measured 2026-10-09, 00:08–05:02 UTC, ≈ 68 by evening
   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
3. **zhulinchng/jevper** — 0.4 · Quiet · Language models · Python · +0 stars measured 2026-10-09, 00:15–05:09 UTC, ≈ 0 by evening
   A classification wrapper over OpenAI-compatible clients: instead of prose it returns typed questions (noul, choice, score) with probabilities and confidence. Works with any client exposing responses.create or chat.completions.create,…
   Full card: https://gitnova.dev/en/r/zhulinchng/jevper.md
4. **Bornholm/indecis** — 0.0 · Steady · Language models · Go · Not enough measurements today
   A Go library for training and running small decision models: a text encoder fine-tuned on your examples answers typed questions with calibrated probabilities instead of generated text.
   Full card: https://gitnova.dev/en/r/Bornholm/indecis.md
5. **firelex/jeff** — 1.9 · Cooling · Language models · Python · +3 stars measured 2026-10-09, 00:10–05:04 UTC, ≈ 24 by evening
   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.
   Full card: https://gitnova.dev/en/r/firelex/jeff.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 2026-10-09 05:10 UTC, updated every 30 minutes.