Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jev-Style is a family of small decision models (0.8B and 2B, fine-tuned from Qwen3.5) and a toolkit that runs them locally. It takes text or JSON, optional images, and typed questions, returning a calibrated probability per option in one forward pass.
How it uses Jev
Jev answers Choice, Score, and Noul questions on the input state. The server exposes a System One-compatible /v1/systemone API; clients send typed questions and receive calibrated probabilities. A Claude Code guard uses four Noul checks and a risk Score to allow, ask, or deny tool calls via code-owned thresholds.
Primitives:choicescorenoul
Technique worth stealing
One forward pass over the input answers all typed questions, with fitted temperatures for calibrated probabilities.
Try it
pip install "jev-style[torch]" (or [mlx]), then jev-style serve and jev-style decide.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.93
- Shows a System One patternFound in material0.92
- Describes handling uncertaintyFound in material0.67
- Reports measured numbersFound in material0.95
- Is a runnable toolFound in material0.99
- Top-10 learning shortlist signalnot found in the excerpt0.34
- Is a replica of the modelFound in material0.98
- Solves a common problem (0–2)score on a 0–2 scale1.74 / 2
- About JevFound in material0.95
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 4 Nov 2026.