Liuziyu77/Valen
Train a Jev-like multimodal model by yourself. System One Model, now with vision.
About the project
A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo includes model code, data processing, SFT and RLCD training, inference and evaluation.
Useful for
- Train the model on your own data via python -m valen.train with a custom config
- Run inference on JSONL records with images to get candidate probabilities
- Check the evaluation pipeline on the synthetic examples in data/smoke
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 0 stars so far today, about 43 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 2 days old and already has 88 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #179.
- About 8 forks a day — people are taking the code.
- Recent forks include notable developers: @MiroKaku (524 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 88
- Today
- 0 · ≈ 43 by evening
- Forks
- 12
- Issues and pull requests
- 28
- Watchers
- 3
- Language
- Python
- License
- Apache-2.0
- Created
- September 23, 2026
- Last push
- September 24, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 25, 2026Top new repositories this week: #179
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/Liuziyu77/Valen)Similar by description
-
3.5
bespokelabsai/nimble
Nimble is a model and training recipe for fast typed decisions over text: given a flat schema of enum and boolean fields, it picks an answer and returns probabilities for each option. It targets routing, condition…
-
3.4
Yinsongxu/LLM2Jev
A tool that turns local language models into structured decision engines: it accepts Choice, Score, and Noul questions and returns typed answers with probabilities using prefill-only inference without generating tokens.
-
2.6
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).
-
4.3
allebee/jevk5
An open-weight alternative to TypeSafe Jev: given a state (ticket, log, policy, diff) and a yes/no, choice, or score question, it returns a probability for every option in one forward pass with zero generated tokens.…
-
1.5
ekzhang/openjev-sglang
HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.
-
1.3
wdobry/laya-playground
A playground for Laya, the open-source decision model: a website, three games, a benchmark and an agent skill. A local server takes typed questions and returns probabilities in one forward pass.