Update README.md

README.md

@@ -14,6 +14,9 @@ tags:
 - explicit-content-detection
 - media-filter
 ---
+
+![3.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/GbdtFwysvOM4Nulmetrtq.png)
+
 # **siglip2-mini-explicit-content**
 
 > **siglip2-mini-explicit-content** is an image classification vision-language encoder model fine-tuned from **`siglip2-base-patch16-512`** for a single-label classification task. It is designed to classify images into categories related to explicit, sensual, or safe-for-work content using the **SiglipForImageClassification** architecture.
@@ -21,6 +24,9 @@ tags:
 > \[!Note]
 > This model is intended to promote positive, safe, and respectful digital environments. Misuse is strongly discouraged and may violate platform or regional guidelines. As a classification model, it does not generate unsafe content and is suitable for moderation purposes.
 
+> [!note]
+*SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786
+
 ```py
 Classification Report:
                      precision    recall  f1-score   support