jevbooks

← All projects

jeff

firelex/jeff · Homepage

0.8B open System 1 model for millisecond decisions with calibrated probabilities.

Automated README summary

Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Jeff is a 0.8B open model that makes quick decisions in any domain. It picks between options using calibrated probabilities, with swappable LoRA adapters for tasks like guard, triage, tools, and more.

How it uses Jev

Jeff answers choice, noul, and score questions on a given state. It returns calibrated probabilities for each option. The result is used to pick the best option or to decide whether to fall back to a larger model when uncertain.

Primitives:choicenoulscore

Technique worth stealing

Adapter-first base with prompt layout caching fixed instructions and options first, changing input last.

Try it

Use the quick start guide or reference app to run Jeff with adapters.

View on GitHub

Start using Jev: API key and your first request →

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-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

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 material0.87
  • Shows a System One patternunclear0.53
  • Describes handling uncertaintynot found in the excerpt0.08
  • Reports measured numbersFound in material0.91
  • Is a runnable toolFound in material0.80
  • Top-10 learning shortlist signalunclear0.44
  • Is a replica of the modelFound in material0.91
  • Solves a common problem (0–2)score on a 0–2 scale1.36 / 2
  • About JevFound in material0.74
Signals
Jev is core to the project0.87Shows a System One pattern0.53Describes handling uncertainty0.08Reports measured numbers0.91Is a runnable tool0.80Top-10 learning shortlist signal0.44Is a replica of the model0.9100.51Solves a common problem (0–2)1.36 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.91Check-up0.91Ghostwriter0.90Questionnaire0.59Fail open, fail closed0.42Menu0.36Grey zone0.30Traffic light0.2300.51

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 6 Oct 2026.