JevStyle 2B decision model
JevStyle 2B is a diagnostic typed-decision release with custom inference code. Its public score rises while its pre-registered calibration guard fails.
By Chaoliang Yan · Hugging Face package release: 5 Nov 2026
An independently maintained 2.21B typed-decision model with a frozen vision tower. Its diagnostic continuation raises the reported public score but fails its pre-registered calibration guard. The required renderer, attention mask and verdict readout ship with the weights; generic chat runtimes do not reproduce its probabilities.
Quick answers
What is JevStyle 2B by Chaoliang Yan?
JevStyle 2B: An independently maintained 2.21B typed-decision model with a frozen vision tower.
Who makes JevStyle 2B?
JevStyle 2B: Chaoliang Yan
Are JevStyle 2B's weights open?
JevStyle 2B: Merged weights and custom runtime; separate text-only GGUF and MLX packages Licence: Apache-2.0; upstream data and teacher-output terms still apply
Facts
- Size
- 2,213,241,664 parameters including the vision tower
- Inputs
- Text and images; image smoke checks, without a new full vision benchmark
- Context
- 32,768 tokens; up to 255 options; overlength inputs refused
- Licence
- Apache-2.0; upstream data and teacher-output terms still apply
- Access
- Merged weights and custom runtime; separate text-only GGUF and MLX packages
Claims and sources
- The maker reports 46.74 on the complete public Decision Index 0.3 suite, versus 44.37 for its parent, with 140,178 successful requests. ECE rises from 0.0195163271 to 0.0300812254, exceeding the allowed 0.01 increase. Concurrent CUDA timings are not serial request latency. vendor reportedsource
Links
Related projects
No related projects are listed in the registry.