Update README.md

README.md

@@ -13,11 +13,15 @@ base_model:
 ---
 # Model Card for ViT Deepfake Detector
 
+**Uploaded for community validation as part of OpenSight** - An upcoming open-source framework for adaptive deepfake detection, inspired by methodologies in <source_id data="2411.04125v1.pdf" />.
+
+### *Huggingface Spaces coming soon.*
+
 ## Model Details
 ### Model Description
-Vision Transformer (ViT) model fine-tuned for detecting AI-generated images in forensic applications.
+Vision Transformer (ViT) model trained on the largest dataset to-date for detecting AI-generated images in forensic applications.
 
-- **Developed by:** [Your Name/Organization]
+- **Developed by:** Jeongsoo Park and Andrew Owens, University of Michigan
 - **Model type:** Vision Transformer (ViT-Small)
 - **License:** MIT (compatible with CreativeML OpenRAIL-M referenced in [2411.04125v1.pdf])
 - **Finetuned from:** timm/vit_small_patch16_384.augreg_in21k_ft_in1k
@@ -31,7 +35,6 @@ Vision Transformer (ViT) model fine-tuned for detecting AI-generated images in f
 Detect AI-generated images in:
 - Content moderation pipelines 
 - Digital forensic investigations
-- Media authenticity verification
 
 ## Bias, Risks, and Limitations
 - **Performance variance:** Accuracy drops 15-20% on diffusion-generated images vs GAN-generated
@@ -41,6 +44,7 @@ Detect AI-generated images in:
 
 
 ## How to Use
+
 ```python
 from transformers import ViTImageProcessor, ViTForImageClassification