Update README.md
Browse files
README.md
CHANGED
|
@@ -22,13 +22,13 @@ datasets:
|
|
| 22 |
|
| 23 |
> **ImageShield-SUPER-90M** is a vision-language image classification model based on **google/siglip2-base-patch16-224**, trained on **100K samples from the ImageShield-Guardrail Safe and Unsafe Images dataset**. Built on the **SiglipForImageClassification** architecture, the model is designed to classify visual content as **Safe** or **Unsafe** for content moderation and media filtering.
|
| 24 |
|
|
|
|
|
|
|
|
|
|
| 25 |
> [!note]
|
| 26 |
> *SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features*
|
| 27 |
> [https://arxiv.org/pdf/2502.14786](https://arxiv.org/pdf/2502.14786)
|
| 28 |
|
| 29 |
-
> [!note]
|
| 30 |
-
> This model is experimental. Expert VLMs are coming soon: [ImageShield Multimodal SFT Collection](https://huggingface.co/collections/prithivMLmods/imageshield-multimodal-sft).
|
| 31 |
-
|
| 32 |
## **Label Space: 2 Classes**
|
| 33 |
|
| 34 |
The model classifies each image into one of the following content categories:
|
|
|
|
| 22 |
|
| 23 |
> **ImageShield-SUPER-90M** is a vision-language image classification model based on **google/siglip2-base-patch16-224**, trained on **100K samples from the ImageShield-Guardrail Safe and Unsafe Images dataset**. Built on the **SiglipForImageClassification** architecture, the model is designed to classify visual content as **Safe** or **Unsafe** for content moderation and media filtering.
|
| 24 |
|
| 25 |
+
> [!IMPORTANT]
|
| 26 |
+
> This model is experimental. Expert multimodal models are available here: [ImageShield Multimodal SFT Collection](https://huggingface.co/collections/prithivMLmods/imageshield-multimodal-sft).
|
| 27 |
+
|
| 28 |
> [!note]
|
| 29 |
> *SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features*
|
| 30 |
> [https://arxiv.org/pdf/2502.14786](https://arxiv.org/pdf/2502.14786)
|
| 31 |
|
|
|
|
|
|
|
|
|
|
| 32 |
## **Label Space: 2 Classes**
|
| 33 |
|
| 34 |
The model classifies each image into one of the following content categories:
|