Automated README summary
Automatically summarized from the README on 9 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jevforge converts any Hugging Face causal LLM into a Jev-style decision model that returns calibrated probabilities over options instead of free text, and serves a TypeSafe-compatible /v1/systemone API for existing clients.
How it uses Jev
Given a state and typed questions (choice, score, noul), Jev scores bracketed option identifiers and returns calibrated probabilities per option. The result is used as the decision output; no free text is generated. Fine-tuning with tree loss and KL anchors improves calibration.
Primitives:choicescorenoul
Technique worth stealing
Bracketed-id readout with tree-factorized loss and KL anchors for calibrated decisions without losing chat ability.
Try it
pip install -e ".[dev,serve]"; jevforge inspect --model <model>; jevforge serve --model <model> --port 8765
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 material0.89
- Shows a System One patternnot found in the excerpt0.18
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.89
- Top-10 learning shortlist signalunclear0.59
- Is a replica of the modelFound in material0.97
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
- About JevFound in material0.98
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 9 Oct 2026.