Downloads · 30 days
7
5% of all-time downloads
cbrpnkrd/Qwen2.5-VL-3B-gearbox
Qwen2.5-VL-3B-gearbox is a image-text-to-text model from cbrpnkrd. 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.
Qwen2.5-VL-3B base model fine-tuned on gearbox-dataset to maximize VQA performance for gearbox part identification from image.
Downloads · 30 days
7
5% of all-time downloads
All-time downloads
134
Public
Parameters
3.8B
7.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.5 GB · 100%
From the Hugging Face model README
Qwen2.5-VL-3B base model fine-tuned on gearbox-dataset to maximize VQA performance for gearbox part identification from image.
Evaluated on the test split of the gearbox-dataset.
| Model name | Accuracy, % |
|---|---|
| Qwen2.5-VL-3B | 55.47 |
| Qwen2.5-VL-3B-gearbox | 97.70 |