Improve metadata and add Github link
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
-
language:
|
| 4 |
-
- en
|
| 5 |
base_model:
|
| 6 |
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
tags:
|
| 9 |
- IQA
|
| 10 |
- VLM
|
|
@@ -12,15 +13,15 @@ tags:
|
|
| 12 |
- Pytorch
|
| 13 |
---
|
| 14 |
|
| 15 |
-
|
| 16 |
The latest version can be found in [VisualQuality-R1-7B](https://huggingface.co/TianheWu/VisualQuality-R1-7B)
|
| 17 |
|
| 18 |
-
|
| 19 |
# VisualQuality-R1-7B-preview
|
| 20 |
This is a demo version of VisualQuality-R1 which is trained on the combination of KADID-10K, TID2013, and KONIQ-10K. The base model of VisualQuality-R1 is Qwen2.5-VL-7B-Instruct.
|
| 21 |
|
| 22 |
Paper link: [arXiv](https://arxiv.org/abs/2505.14460)
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Quick Start
|
| 25 |
```python
|
| 26 |
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
license: mit
|
| 7 |
+
pipeline_tag: image-to-text
|
| 8 |
+
library_name: transformers
|
| 9 |
tags:
|
| 10 |
- IQA
|
| 11 |
- VLM
|
|
|
|
| 13 |
- Pytorch
|
| 14 |
---
|
| 15 |
|
|
|
|
| 16 |
The latest version can be found in [VisualQuality-R1-7B](https://huggingface.co/TianheWu/VisualQuality-R1-7B)
|
| 17 |
|
|
|
|
| 18 |
# VisualQuality-R1-7B-preview
|
| 19 |
This is a demo version of VisualQuality-R1 which is trained on the combination of KADID-10K, TID2013, and KONIQ-10K. The base model of VisualQuality-R1 is Qwen2.5-VL-7B-Instruct.
|
| 20 |
|
| 21 |
Paper link: [arXiv](https://arxiv.org/abs/2505.14460)
|
| 22 |
|
| 23 |
+
Code: https://github.com/TianheWu/VisualQuality-R1
|
| 24 |
+
|
| 25 |
## Quick Start
|
| 26 |
```python
|
| 27 |
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|