Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python package (import name so1) that turns any open-weights LLM into a System One decision model, returning typed, calibrated probabilities for Choice, Score, and Noul questions instead of generating text. Runs locally on your own GPU.
How it uses Jev
The model reads the state once and answers each typed question from the next-token distribution at its own position, restricted to the given options. Decisions are returned as calibrated probabilities in the order you listed the options; permutations=2 averages two option orders.
Primitives:choicescorenoul
Technique worth stealing
Packing multiple questions into one forward pass with the shared state written once, reducing tokens and increasing throughput.
Try it
pip install open-alternative-jev, then use the Decider or decide API; live demo on Hugging Face Spaces.
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 material0.86
- Shows a System One patternnot found in the excerpt0.27
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersunclear0.40
- Is a runnable toolFound in material0.92
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelFound in material0.95
- Solves a common problem (0–2)score on a 0–2 scale1.20 / 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 25 Sept 2026.