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
GroundingJev is a visual grounding model for researchers and developers: given an image and a referring expression, it predicts a bounding box in one forward pass, reporting an 8.61× inference speedup over its autoregressive base model.
How it uses Jev
The README does not describe Jev's typed questions or probability outputs. GroundingJev is only described as inspired by TypeSafe Jev, applying direct task-specific output prediction: a lightweight MLP head maps the last valid token's hidden state to normalized cxcywh coordinates, trained with weighted L1 and GIoU loss.
Technique worth stealing
Replace autoregressive coordinate decoding with a lightweight MLP regression head over the last valid token's hidden state.
Try it
bash scripts/infer.sh --image /path/to/image.jpg --expression 'the person wearing a red shirt'
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 projectnot found in the excerpt0.15
- Shows a System One patternnot found in the excerpt0.10
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.82
- Is a runnable toolnot found in the excerpt0.34
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelFound in material0.95
- Solves a common problem (0–2)score on a 0–2 scale0.98 / 2
- About JevFound in material0.76
no-judgment band (0.40–0.60)
Design patterns
No pattern scored above the reporting threshold.
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.