The Jev demo uses a 27B vision model to evaluate person crops detected by YOLO, without requiring any training data or fine-tuning.

Name: The Jev demo uses a 27B vision model to evaluate person crops detected by YOLO, without requiring any training data or fine-tuning.
Uploaded: 2026-10-19T00:00:30.444Z
Channel: mfranz_on
Description: The Jev demo uses a 27B vision model to evaluate person crops detected by YOLO, without requiring any training data or fine-tuning.

mfranz_onverification-guardrails24.8K views · 433 likes

Discovered 2026-10-19, refreshed 2026-10-22. Descriptions and stats are pulled from the project's own X post and refreshed automatically — they aren't independently verified by JevTracks beyond the initial eligibility check.