Downloads · 30 days
8
12% of all-time downloads
ocr-qwen2-5-vl-3b
IrieDinamik/ocr-qwen2-5-vl-3b
ocr-qwen2-5-vl-3b is a image-text-to-text model from IrieDinamik. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
This repository is an app-managed mirror for Vox Jot. It preserves upstream lineage so the desktop app can download OCR model files anonymously and reproducibly.
All-time downloads
69
Public
Parameters
3.8B
7.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- other
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Apr 29, 2026
- Updated
- May 15, 2026
- SHA
- 8ae0003e
Try a prompt
Model card
From the Hugging Face model README
Vox Jot OCR Mirror: qwen2.5-vl-3b
This repository is an app-managed mirror for Vox Jot. It preserves upstream lineage so the desktop app can download OCR model files anonymously and reproducibly.
Upstream Sources
License And Attribution
- Upstream license: Qwen Research License
- Attribution: original model authors and upstream repositories listed above.
- Vox Jot changes: mirrored and repackaged for app-managed download; no model training changes are implied by this mirror.
- Notices: upstream README, LICENSE, NOTICE, and COPYING files found during staging are preserved under
upstream-notices/.
Notes
General VL; used as OCR-capable fallback in catalog.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen2_5_vl
- License
- other
- Created
- Apr 29, 2026
- Updated
- May 15, 2026