Automated README summary
Automatically summarized from the README on 18 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
VideoJev is a family of video understanding models (VideoJev-4B and VideoJev-35B-A3B) that perform temporal grounding and multiple-choice video QA by directly scoring candidates over a shared video prefix, for researchers and developers.
How it uses Jev
Given a video and typed questions (grounding or choice), the model scores temporal candidates and answer options, returning sigmoid probabilities plus a selected interval in seconds for grounding, and softmax probabilities plus a zero-based answer_index for QA. Results come from predict_video or predict_features.
Primitives:choicescore
Technique worth stealing
Direct candidate scoring over a shared video prefix replaces text generation for grounding and QA.
Try it
Install requirements, source scripts/env.sh, then run the 10-second demo calling model.predict_video with VideoJev-4B.
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 material0.82
- Shows a System One patternnot found in the excerpt0.19
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.11
- Is a runnable toolunclear0.49
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelFound in material0.94
- Solves a common problem (0–2)score on a 0–2 scale0.98 / 2
- About JevFound in material0.74
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 18 Oct 2026.