Update README.md
Browse files
README.md
CHANGED
|
@@ -24,9 +24,9 @@ We follow the standard evaluation protocol and benchmark our model on three chal
|
|
| 24 |
| UGround-v1-72B | 72B | ✅ | — | 34.5 | — |
|
| 25 |
| Qwen2.5-VL-72B-Instruct | 72B | ✅ | 94.00* | 53.3 | 62.2* |
|
| 26 |
| UI-TARS | 72B | ✅ | 90.3 | 38.1 | — |
|
| 27 |
-
|
|
| 28 |
-
|
|
| 29 |
-
|
|
| 30 |
|
| 31 |
|
| 32 |
> **Note:**
|
|
@@ -63,7 +63,7 @@ def extract_coordinates(raw_string):
|
|
| 63 |
return 0,0
|
| 64 |
|
| 65 |
# Load model and processor
|
| 66 |
-
model_path = "HelloKKMe/
|
| 67 |
max_new_tokens = 32
|
| 68 |
|
| 69 |
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
|
@@ -125,4 +125,4 @@ pred_y*=scale_y
|
|
| 125 |
print(pred_x,pred_y)
|
| 126 |
```
|
| 127 |
|
| 128 |
-
Refer to our [code](https://github.com/Yan98/
|
|
|
|
| 24 |
| UGround-v1-72B | 72B | ✅ | — | 34.5 | — |
|
| 25 |
| Qwen2.5-VL-72B-Instruct | 72B | ✅ | 94.00* | 53.3 | 62.2* |
|
| 26 |
| UI-TARS | 72B | ✅ | 90.3 | 38.1 | — |
|
| 27 |
+
| GTA1 (Ours) | 7B | ✅ | 92.4 <sub>*(∆ +2.7)*</sub> | 50.1<sub>*(∆ +8.1)*</sub> | 67.7 <sub>*(∆ +3.5)*</sub> |
|
| 28 |
+
| GTA1 (Ours) | 32B | ✅ | 93.2 <sub>*(∆ +1.3)*</sub> | 53.6 <sub>*(∆ +5.6)*</sub> | 61.9<sub>*(∆ +2.3)*</sub> |
|
| 29 |
+
| GTA1 (Ours) | 72B | ✅ | 94.8<sub>*(∆ +0.8)*</sub> | 58.4 <sub>*(∆ +5.1)*</sub> | 66.7<sub>*(∆ +4.5)*</sub> |
|
| 30 |
|
| 31 |
|
| 32 |
> **Note:**
|
|
|
|
| 63 |
return 0,0
|
| 64 |
|
| 65 |
# Load model and processor
|
| 66 |
+
model_path = "HelloKKMe/GTA1-72B"
|
| 67 |
max_new_tokens = 32
|
| 68 |
|
| 69 |
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
|
|
|
| 125 |
print(pred_x,pred_y)
|
| 126 |
```
|
| 127 |
|
| 128 |
+
Refer to our [code](https://github.com/Yan98/GTA1) for more details.
|