Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jebadiah is an open decision model family (27B, 9B, 4B on Qwen bases) that answers typed questions about structured state with a probability per option, built for code callers rather than people.
How it uses Jev
Jev reads the answer from logits of single label tokens at one position in a single forward pass, with no generation or parsing. Callers send a state plus Choice, Noul or Score questions and act on the returned probabilities.
Primitives:choicescorenoul
Technique worth stealing
Supervise only candidate label logits at the answer position with cross-entropy, then fit one temperature per question type on a held-out calibration slice.
Try it
Serve via AINode's /v1/decide and /v1/systemone routes, or use the llama.cpp script for GGUF builds.
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 material0.93
- Shows a System One patternnot found in the excerpt0.19
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.12
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalunclear0.48
- Is a replica of the modelFound in material0.93
- Solves a common problem (0–2)score on a 0–2 scale1.07 / 2
- About JevFound in material0.87
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 21 Oct 2026.