Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Applies SemIf/OpenJev's logit-reading method to PrismML's 1.75-bit Ternary Bonsai 27B GGUF under llama.cpp, returning typed choice probabilities from one forward pass on CPU, Metal, CUDA, or Vulkan; reports 74.6% on a 256-item WANLI sample.
How it uses Jev
Jev makes multiple-choice decisions by reading the probability of option letters (A/B) from the next-token distribution. The model is given a lettered question and state; the scorer returns calibrated probabilities for each choice, which can be used directly in code (e.g., if p > threshold).
Primitives:choice
Technique worth stealing
Divide logits by a temperature scalar before softmax to calibrate probabilities without changing accuracy.
Try it
./openjev/score.sh -q "Is the user angry?" --state '{"msg":"this is broken AGAIN and nobody replies"}'
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 material0.94
- Shows a System One patternnot found in the excerpt0.13
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.98
- Is a runnable toolFound in material0.72
- Top-10 learning shortlist signalunclear0.55
- Is a replica of the modelFound in material0.66
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
- About JevFound in material0.91
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 25 Sept 2026.