Liuziyu77/Valen
VerifiedLocal alternativeDocumented
Valen brings text, image and video inputs to a Jev-inspired candidate-scoring model, with open training code and a preview checkpoint requiring Qwen3.5-2B.
Valen scores supplied candidates against text, images or video and returns decision probabilities without generating answer tokens.
This Jev-inspired implementation uses a Qwen3.5 backbone and a shared decision head.
Run inference or evaluation with both the Valen checkpoint and its Qwen3.5-2B base model.
The released checkpoint is a preview and RLCD training is experimental; base models and datasets retain separate licenses.
Evidence checked:
Train a Jev-like multimodal model by yourself. System One Model, now with vision.
Stars measure the whole repository, including work unrelated to Jev.
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
Evidence commit: 06251f9d9d3c06ea690be93b8696ccc66471f8c9
Discovered through: awesome-jev.
How we review →Suggest a correction · Claim this listing · Submit a project