laya-vision
thaitea/laya-vision
Tracked by OpenModelStats since September 21, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 0
- Total downloadsCumulative all-time download counter reported by the source platform.
- 0
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- —
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 38
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #50 among tracked Visual Question Answering models.
- #57,384
- 101(down 101 places)this week
- Parameters
- 201M
- Last source update
- Sep 25, 2026
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
laya-vision is a visual question answering model published by thaitea. OpenModelStats has tracked the model since Sep 21, 2026, most recently observing it Oct 6, 2026.
- Published
- Sep 19, 2026
- Last updated
- Sep 25, 2026
- Library
- laya
- License
- cc-by-nc-sa-4.0
- Task
- Visual Question Answering
- Parameters
- 201,161,350
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
layasafetensorscalibrationdecision-modelvisionsmolvlmgamesvisual-question-answeringendataset:HuggingFaceM4/the_cauldrondataset:MMInstruction/VLFeedbackdataset:HuggingFaceM4/A-OKVQA
Publisher
thaiteaView publisher statistics →Derived from HuggingFaceTB/SmolVLM-256M-Instruct (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| git-base-vqav2microsoft | 1,244 |
| deplotgoogle | 18.4K |
| pix2struct-docvqa-basegoogle | 1,678 |
| pix2struct-ai2d-basegoogle | 1,016 |
| TinyDoc-VLM-256Meulogik | 437 |
| blip-vqa-baseSalesforce | 539.2K |