Automated README summary
Automatically summarized from the README on 15 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An Apache-licensed Python toolkit that gives existing LLMs and MLLMs Jev-style decision abilities for classification, scoring, and action selection from text and images, with SGLang, Transformers, and MLX backends plus demos.
How it uses Jev
Jev-style questions (Choice, Score, Noul, Box) are answered by reading causal-model logits through prefill alone. Choice, Score, and Noul read yes/no logits without generating answers; Box generates normalized image coordinates. Results return as typed Python objects or JSON via a System One-shaped HTTP endpoint and an OpenAI SDK-extending client.
Primitives:choicescorenoul
Technique worth stealing
Reuse shared prefixes across candidates with SGLang's Radix Cache or MLX explicit prefix prefill, including within a cold request.
Try it
uv sync --extra sglang; llm2jev-serve --backend sglang --model-path /path/to/model
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 excerpt0.28
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.18
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelFound in material0.89
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
- About JevFound in material0.94
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 15 Oct 2026.