Downloads · 30 days
79
29% of all-time downloads
Qwen3-VL-8B-SGMRIVQA
SpatialGroundingVQA/Qwen3-VL-8B-SGMRIVQA
Qwen3-VL-8B-SGMRIVQA is a image-text-to-text model from SpatialGroundingVQA. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
<p align="center" <img src="https://huggingface.co/front/assets/huggingfacelogo-noborder.svg" width="120"/ </p
All-time downloads
271
Public
Parameters
770K
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
- License
- apache-2.0
- Model type
- qwen3_vl
- Access
- Public
- Created
- Apr 15, 2026
- Updated
- May 5, 2026
- SHA
- 006aa508
Try a prompt
Datasets
Model card
From the Hugging Face model README
<p align="center">
<img src="https://huggingface.co/front/assets/huggingface_logo-noborder.svg" width="120"/>
</p>
Qwen3-8B-SGMRIVQA-SFT
Spatially Grounded MRI Visual Question Answering (SGMRIVQA) model fine-tuned from Qwen3-VL-8B-Instruct.
This is the Epoch 2 SFT checkpoint trained on the SGMRIVQA dataset for spatially grounded visual question answering on volumetric MRI scans (brain and knee).
Model Details
- Base Model: Qwen3-VL-8B-Instruct
- Training: Supervised Fine-Tuning (SFT), Epoch 2
- Task: Spatially Grounded MRI Visual Question Answering
- Modalities: Brain MRI (axial), Knee MRI (sagittal)
- Data Source: fastMRI+ dataset with clinical expert annotations
- Task
- Image-Text-to-Text
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Apr 15, 2026
- Updated
- May 5, 2026