Downloads · 30 days
18
18% of all-time downloads
qwen-VL-8b-ocrLatex
wizardoftrap/qwen-VL-8b-ocrLatex
qwen-VL-8b-ocrLatex is a image-text-to-text model from wizardoftrap. 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 apache-2.0.
- Developed by: Shiv Prakash(wizardoftrap) - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit - Dataset used : unsloth/LaTeXOCR - This qwen3vl model was trained 2x faster with…
All-time downloads
102
Public
Parameters
8.8B
17.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_vl
- Access
- Public
- Created
- Dec 23, 2025
- Updated
- Dec 25, 2025
- SHA
- 9e37a1c0
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Uploaded finetuned model
- Developed by: Shiv Prakash(wizardoftrap)
- License: apache-2.0
- Finetuned from model : unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit
- Dataset used : unsloth/LaTeX_OCR
Overview
- This qwen3_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Qwen3-VL is most powerful vision-language model in the Qwen series to date.
- This model was fine tuned on Google Colab with T4 GPU
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- apache-2.0
- Languages
- en
- Created
- Dec 23, 2025
- Updated
- Dec 25, 2025