Automated README summary
Automatically summarized from the README on 16 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
NanoJev is an open replica of Jev: a 0.6B parallel decision model that takes states and questions and returns complete probability distributions with no output-token decoding. It ships with training pipeline, weights, and dataset for four game tasks.
How it uses Jev
Each request supplies a state, a question, and its candidates. The backbone encodes candidate paths; shared heads produce requested probabilities. Choice uses set attention and softmax over 2–255 candidates, Boolean uses a sigmoid, and Score returns a probability-weighted level over 2–10 ordered levels. Results rank, select, or sample actions.
Primitives:choicescorenoul
Technique worth stealing
Batch independent states, questions, and candidate paths in one backbone forward to get parallel decisions without token decoding.
Try it
Clone repo, install requirements-toy.txt and huggingface_hub, download checkpoint and data, then run scripts/serve_decisions.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 material0.81
- Shows a System One patternunclear0.53
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.12
- Is a runnable toolnot found in the excerpt0.28
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelFound in material0.97
- Solves a common problem (0–2)score on a 0–2 scale0.64 / 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 16 Oct 2026.