Update README.md
Browse files
README.md
CHANGED
|
@@ -24,9 +24,17 @@ UGround is a storng GUI visual grounding model trained with a simple recipe. Che
|
|
| 24 |
|
| 25 |
|
| 26 |
- [x] Model Weights
|
| 27 |
-
- [x]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
- [ ] Code
|
| 29 |
-
- [
|
| 30 |
- [x] Offline Experiments
|
| 31 |
- [x] Screenspot (along with referring expressions generated by GPT-4/4o)
|
| 32 |
- [x] Multimodal-Mind2Web
|
|
@@ -42,6 +50,7 @@ UGround is a storng GUI visual grounding model trained with a simple recipe. Che
|
|
| 42 |
- [ ] Data-V1.1
|
| 43 |
- [x] Online Demo (HF Spaces)
|
| 44 |
|
|
|
|
| 45 |
## Models
|
| 46 |
|
| 47 |
- Initial UGround-V1: https://huggingface.co/osunlp/UGround
|
|
|
|
| 24 |
|
| 25 |
|
| 26 |
- [x] Model Weights
|
| 27 |
+
- [x] Initial V1 (the one used in the paper)
|
| 28 |
+
- [x] Qwen2-VL-based V1
|
| 29 |
+
- [x] 2B
|
| 30 |
+
- [x] 7B
|
| 31 |
+
- [ ] 72B
|
| 32 |
+
- [ ] V1.1
|
| 33 |
+
- [ ] 2B
|
| 34 |
+
- [ ] 7B
|
| 35 |
+
- [ ] 72B
|
| 36 |
- [ ] Code
|
| 37 |
+
- [x] Inference Code of UGround
|
| 38 |
- [x] Offline Experiments
|
| 39 |
- [x] Screenspot (along with referring expressions generated by GPT-4/4o)
|
| 40 |
- [x] Multimodal-Mind2Web
|
|
|
|
| 50 |
- [ ] Data-V1.1
|
| 51 |
- [x] Online Demo (HF Spaces)
|
| 52 |
|
| 53 |
+
|
| 54 |
## Models
|
| 55 |
|
| 56 |
- Initial UGround-V1: https://huggingface.co/osunlp/UGround
|