Automated README summary
Automatically summarized from the README on 20 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jev-RS is a Rust server that answers multiple typed questions about a single state in one ONNX forward pass, using an NLI model. It targets developers who need fast, deterministic, calibrated decisions without token generation.
How it uses Jev
Jev makes the decisions: each question is flattened into premise/hypothesis pairs (noul → true/false, choice → one pair per criterion, score → one pair per level), tokenized as one batch, and run through a single ONNX forward pass. Temperature scaling yields probabilities and Shannon entropy yields confidence; the server returns type, value, distribution, and confidence.
Primitives:choicescorenoul
Technique worth stealing
Batch all hypothesis pairs for every question into one forward pass sharing a single premise, so cost scales with pairs × seq_len, not request count.
Try it
Run install.bat then run.bat on Windows, or cargo build --release and ./target/release/jev-rs --download-model; server at http://127.0.0.1:8000.
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 material0.82
- Shows a System One patternFound in material0.74
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.82
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelFound in material0.88
- Solves a common problem (0–2)score on a 0–2 scale1.72 / 2
- About JevFound in material0.93
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 20 Oct 2026.