~ / models / open-weights / jev-omni
Jev-Omni
Multimodal decision classifier on Gemma 4 12B: text, image, audio, or video in, a probability per option out. Apache 2.0 weights. One question per call, best under about 20 options. Currently #1 on Image JevBench.
- section
- Models
- group
- Open weights
- source
- hugging face model
- likes
- 406
- downloads
- 4.8k
- last pushed
- sep 25
- added to list
- sep 22
No history yet: this chart appears once there are a few daily snapshots.