Skip to main content

Valen 0.8B, 2B, and 4B — now with vision

· One min read
Open models, benchmarks, and tools

We are releasing Valen in three sizes — 0.8B, 2B, and 4B — with support for text, images, and video.

Alongside the models, we are releasing VisualDecisionBench, a benchmark for decisions grounded in images and video.

A structured decision interface​

Valen evaluates a shared state against task instructions and returns probabilities over supplied candidates. It supports Choice, Noul, and Score questions, giving software a structured interface to model decisions.

The repository includes model implementation, data processing, inference and evaluation commands, and SFT and experimental RLCD training support.

Models​

SizeDownload
0.8BValen-0.8B
2BValen-2B
4BValen-4B

VisualDecisionBench​

The full released evaluation set contains 1,696 shared states and 9,143 questions, split into 2,000 image questions and 7,143 video questions.

Explore the benchmark · Download the dataset

Start building​

Run Valen locally or explore the source repository.

Source: Valen release notes.