Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,8 @@ pipeline_tag: image-text-to-text
|
|
| 5 |
|
| 6 |
# UGround (The Initial LLaVA-based Version)
|
| 7 |
|
|
|
|
|
|
|
| 8 |
UGround is a strong GUI visual grounding model trained with a simple recipe. Check our homepage and paper for more details. This work is a collaboration between [OSUNLP](https://x.com/osunlp) and [Orby AI](https://www.orby.ai/).
|
| 9 |
|
| 10 |
- **Homepage:** https://osu-nlp-group.github.io/UGround/
|
|
|
|
| 5 |
|
| 6 |
# UGround (The Initial LLaVA-based Version)
|
| 7 |
|
| 8 |
+
Update: We have trained [stronger model](https://huggingface.co/osunlp/UGround-V1-7B) based on Qwen2-VL with the same data. We suggest using them instead for better performance and more convenient training, inference and deployment.
|
| 9 |
+
|
| 10 |
UGround is a strong GUI visual grounding model trained with a simple recipe. Check our homepage and paper for more details. This work is a collaboration between [OSUNLP](https://x.com/osunlp) and [Orby AI](https://www.orby.ai/).
|
| 11 |
|
| 12 |
- **Homepage:** https://osu-nlp-group.github.io/UGround/
|