Jev technical blog and early access
The end of Diogo’s launch thread links to the official technical blog and early-access entry point for further reading.
OpenJev: An Open-Source Multimodal Alternative Calibrated with RLCD
A community developer released openjev, built on 0.8B Qwen with image-video-text input, RLCD calibration, and sglang support, claiming 5x speed over TypeSafe's jev.
https://huggingface.co/spaces/AlexWortega/openjev… HUGE thx for @_akhaliq for domain, now openjev is: - 0.8b qwen - image-video-text train for input, audio coming дфеук - calibrated with RLCD (its somehow better then vanila grpo) - sglang support (5x faster then jev by @typesafe lol) 4b and 35b and blog
· 3 likesOpen on X
More like this
Getting started with Jev: waitlist and Agent Skill
A community guide walks developers through requesting access and installing the TypeSafe Agent Skill.
Reverse-engineered a Jev-like architecture with open-source training repo
The author says they reverse-engineered a Jev-like architecture from its type and shares a GitHub repo for training your own jevlikes. Link
