Downloads · 30 days
0
BMAT
yinjoy30/BMAT
BMAT is a image-text-to-text model from yinjoy30. 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 mit.
Fine-tuned from Qwen2.5-VL-7B-Instruct on 39,405 manually annotated facade images.
Access
Public
Updated Mar 3, 2026
Repo size
16.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- License
- mit
- Access
- Public
- Created
- Mar 2, 2026
- Updated
- Mar 3, 2026
- SHA
- b96395d6
Try a prompt
Base models
Model card
From the Hugging Face model README
BMAT — Building Facade Material Classifier
Fine-tuned from Qwen2.5-VL-7B-Instruct on 39,405 manually annotated facade images.
Training Data
- 39,405 manually annotated facade images across 9 material categories
- Categories:
brick·concrete·glass·metal·stone·stucco·tile·wood·other - Training labels available at yhyJoy/BMAT
Performance
| Metric | Score |
|---|---|
| Overall F1 | 0.91 |
Usage
from modelscope import Qwen2_5_VLForConditionalGeneration, AutoProcessor
model = Qwen2_5_VLForConditionalGeneration.from_pretrained("yinjoy30/BMAT/BMAT_finetune")
processor = AutoProcessor.from_pretrained("yinjoy30/BMAT/BMAT_finetune")
Prompt used during inference:
What is the facade material of the central building in this image? Please choose one of the following: [tile, brick, concrete, glass, metal, other, stone, stucco, wood] Only answer with the exact word from the list.
Base Model
- Task
- Image-Text-to-Text
- License
- mit
- Languages
- en
- Created
- Mar 2, 2026
- Updated
- Mar 3, 2026