Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A server implementing the TypeSafe/Jev HTTP API with Qwen3.6-35B-A3B on SGLang. It provides Noul, Choice, and Score evaluations for developers needing a Jev-compatible endpoint.
How it uses Jev
Jev makes decisions on a given state and typed questions (Choice, Score, Noul). The state is rendered with the model's chat template, and each question is tokenized as a suffix. The server performs one-token prefill calls to read label logprobs, renormalizes them, and returns probabilities.
Primitives:choicescorenoul
Technique worth stealing
Prefill-only inference: one-token calls with token_ids_logprob for exact label readout, avoiding autoregressive generation.
Try it
uv run modal run modal_app.py
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 material0.85
- Shows a System One patternnot found in the excerpt0.23
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelFound in material0.92
- Solves a common problem (0–2)score on a 0–2 scale0.60 / 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 1 Oct 2026.