Automated README summary
Automatically summarized from the README on 24 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Qwev turns dense Qwen3 and Qwen3.5 checkpoints into a local service that answers typed decision questions (Noul, Choice, Score) without autoregressive decoding, for developers needing fast, structured outputs.
How it uses Jev
Jev-style decisions are made by reading candidate-token logits from the model. The state is encoded once, then each isolated question (Choice, Noul, Score) is evaluated separately. Results are softmax distributions over allowed answer tokens, returned as typed answers.
Primitives:choicescorenoul
Technique worth stealing
Read allowed answers directly from candidate-token logits instead of generating and parsing JSON.
Try it
pip install -e . then run qwev --model-path /models/Qwen3.5-9B --request examples/basic.json --mode shared
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 material0.95
- Shows a System One patternFound in material0.89
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.98
- Is a runnable toolFound in material0.77
- Top-10 learning shortlist signalunclear0.48
- Is a replica of the modelFound in material0.93
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 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 24 Sept 2026.