Vev 4B v2 decision model
Vev 4B v2 returns decision probabilities for text and images. Check its noncommercial weights, custom attention and reported calibration limits.
By Wang Xiaolong · Weights upload: 6 Nov 2026
A Qwen3.5-4B text/image decision fine-tune with merged weights and a Jev-like API. Its runtime uses bidirectional attention within the state and repeats some inputs. Plain causal inference produces different probabilities. This research preview is noncommercial.
Quick answers
What is Vev 4B v2 by Wang Xiaolong?
Vev 4B v2: A Qwen3.5-4B text/image decision fine-tune with merged weights and a Jev-like API.
Who makes Vev 4B v2?
Vev 4B v2: Wang Xiaolong
Are Vev 4B v2's weights open?
Vev 4B v2: Public merged weights; no separate adapter Licence: CC BY-NC 4.0; Apache-2.0 base licence retained
Facts
- Size
- 4B; merged weights
- Inputs
- English or Chinese text, JSON and images
- Runtime
- vev serve on an NVIDIA GPU; checkpoint-specific attention and repetition settings
- Licence
- CC BY-NC 4.0; Apache-2.0 base licence retained
- Access
- Public merged weights; no separate adapter
Claims and sources
- The maker reports public vision skill 72.90 and text skill 60.32, with disclosed training/evaluation overlaps and a text-suite hash mismatch outside the index. Across 18 release sets, ECE ranges from 0.01 to 0.24; four sets regress versus Vev 4B. No full private-board score is supplied. vendor reportedsource
Links
Source: Model card and weights →
Related projects
No related projects are listed in the registry.