update model card.
Browse files
README.md
CHANGED
|
@@ -6,17 +6,19 @@ base_model:
|
|
| 6 |
|
| 7 |
# GUI-Actor-7B with Qwen2-VL-7B as backbone VLM
|
| 8 |
|
| 9 |
-
- [GUI-Actor-7B-Qwen2-VL](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2-VL)
|
| 10 |
-
- [GUI-Actor-2B-Qwen2-VL](https://huggingface.co/microsoft/GUI-Actor-2B-Qwen2-VL)
|
| 11 |
-
- [GUI-Actor-7B-Qwen2.5-VL (coming soon)](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2.5-VL)
|
| 12 |
-
- [GUI-Actor-3B-Qwen2.5-VL (coming soon)](https://huggingface.co/microsoft/GUI-Actor-3B-Qwen2.5-VL)
|
| 13 |
-
- [GUI-Actor-Verifier-2B](https://huggingface.co/microsoft/GUI-Actor-Verifier-2B)
|
| 14 |
-
|
| 15 |
This model was introduced in the paper [**GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents**](https://aka.ms/GUI-Actor).
|
| 16 |
It is developed based on [Qwen2-VL-7B-Instruct ](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), augmented by an attention-based action head and finetuned to perform GUI grounding using the dataset [here (coming soon)]().
|
| 17 |
|
| 18 |
For more details on model design and evaluation, please check: [🏠 Project Page](https://aka.ms/GUI-Actor) | [💻 Github Repo](https://github.com/microsoft/GUI-Actor) | [📑 Paper]().
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## 📊 Performance Comparison on GUI Grounding Benchmarks
|
| 21 |
Table 1. Main results on ScreenSpot-Pro, ScreenSpot, and ScreenSpot-v2 with **Qwen2-VL** as the backbone. † indicates scores obtained from our own evaluation of the official models on Huggingface.
|
| 22 |
| Method | Backbone VLM | ScreenSpot-Pro | ScreenSpot | ScreenSpot-v2 |
|
|
|
|
| 6 |
|
| 7 |
# GUI-Actor-7B with Qwen2-VL-7B as backbone VLM
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
This model was introduced in the paper [**GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents**](https://aka.ms/GUI-Actor).
|
| 10 |
It is developed based on [Qwen2-VL-7B-Instruct ](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct), augmented by an attention-based action head and finetuned to perform GUI grounding using the dataset [here (coming soon)]().
|
| 11 |
|
| 12 |
For more details on model design and evaluation, please check: [🏠 Project Page](https://aka.ms/GUI-Actor) | [💻 Github Repo](https://github.com/microsoft/GUI-Actor) | [📑 Paper]().
|
| 13 |
|
| 14 |
+
| Model Name | Hugging Face Link |
|
| 15 |
+
|--------------------------------------------|--------------------------------------------|
|
| 16 |
+
| **GUI-Actor-7B-Qwen2-VL** | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2-VL) |
|
| 17 |
+
| **GUI-Actor-2B-Qwen2-VL** | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-2B-Qwen2-VL) |
|
| 18 |
+
| **GUI-Actor-7B-Qwen2.5-VL (coming soon)** | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-7B-Qwen2.5-VL) |
|
| 19 |
+
| **GUI-Actor-3B-Qwen2.5-VL (coming soon)** | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-3B-Qwen2.5-VL) |
|
| 20 |
+
| **GUI-Actor-Verifier-2B** | [🤗 Hugging Face](https://huggingface.co/microsoft/GUI-Actor-Verifier-2B) |
|
| 21 |
+
|
| 22 |
## 📊 Performance Comparison on GUI Grounding Benchmarks
|
| 23 |
Table 1. Main results on ScreenSpot-Pro, ScreenSpot, and ScreenSpot-v2 with **Qwen2-VL** as the backbone. † indicates scores obtained from our own evaluation of the official models on Huggingface.
|
| 24 |
| Method | Backbone VLM | ScreenSpot-Pro | ScreenSpot | ScreenSpot-v2 |
|