Automated README summary
Automatically summarized from the README on 10 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
RSI-Jev builds Jev-style System One models that answer yes/no, pick-one-of-k, or rate-on-a-rubric questions about a document, chat, or image. It publishes checkpoints, training code, and every failed experiment.
How it uses Jev
The project trains models to answer Noul, Choice, and Score questions on the same POST /v1/systemone wire format as Jev. One forward pass returns a calibrated probability for every option. The README does not describe using Jev itself; it describes building a trainable replica.
Primitives:noulchoicescore
Technique worth stealing
Self-improving loop where agents register predictions before GPU runs and retire champions when evidence says to.
Try it
pip install "rsi-jev[fast,vision] @ git+https://github.com/Shanghua-Gao/RSI-Jev" then rsi-jev serve v6.1-vl-4b --effort auto --port 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 material0.94
- Shows a System One patternFound in material0.95
- Describes handling uncertaintyunclear0.47
- Reports measured numbersFound in material0.97
- Is a runnable toolnot found in the excerpt0.28
- Top-10 learning shortlist signalnot found in the excerpt0.39
- Is a replica of the modelFound in material0.96
- Solves a common problem (0–2)score on a 0–2 scale0.82 / 2
- About JevFound in material0.97
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 10 Oct 2026.