Image Classification
Transformers
Safetensors
English
siglip
agentbrowse
calendars
humanbrowse
SigLIP2
Instructions to use prithivMLmods/WebClick-AgentBrowse-SigLIP2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/WebClick-AgentBrowse-SigLIP2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="prithivMLmods/WebClick-AgentBrowse-SigLIP2") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoProcessor, AutoModelForImageClassification processor = AutoProcessor.from_pretrained("prithivMLmods/WebClick-AgentBrowse-SigLIP2") model = AutoModelForImageClassification.from_pretrained("prithivMLmods/WebClick-AgentBrowse-SigLIP2") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ base_model:
|
|
| 9 |
|
| 10 |
# **WebClick-AgentBrowse-SigLIP2**
|
| 11 |
|
| 12 |
-
> **WebClick-AgentBrowse-SigLIP2** is a vision-language encoder model fine-tuned from [`google/siglip2-base-patch16-
|
| 13 |
It is trained to detect and classify web UI click regions into three classes: `agentbrowse`, `calendars`, and `humanbrowse`. The model utilizes the `SiglipForImageClassification` architecture.
|
| 14 |
|
| 15 |
> \[!note]
|
|
|
|
| 9 |
|
| 10 |
# **WebClick-AgentBrowse-SigLIP2**
|
| 11 |
|
| 12 |
+
> **WebClick-AgentBrowse-SigLIP2** is a vision-language encoder model fine-tuned from [`google/siglip2-base-patch16-224`](https://huggingface.co/google/siglip2-base-patch16-224) for **multi-class image classification**.
|
| 13 |
It is trained to detect and classify web UI click regions into three classes: `agentbrowse`, `calendars`, and `humanbrowse`. The model utilizes the `SiglipForImageClassification` architecture.
|
| 14 |
|
| 15 |
> \[!note]
|