Upload README.md with huggingface_hub

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: timm
 pipeline_tag: image-classification
+base_model: google/efficientnetv2-s
 tags:
   - anime-classification
   - real-photos
@@ -15,11 +16,14 @@ inference: true
 
 # Anime/Real/Rendered Image Classifier (TF-EfficientNetV2-S)
 
-**Higher-capacity classifier with improved generalization for anime, photo, and 3D detection.**
+Fine-tuned TF-EfficientNetV2-S with improved generalization for anime, photo, and 3D detection.
+
+**Base Model:** [google/efficientnetv2-s](https://huggingface.co/google/efficientnetv2-s) (TensorFlow → PyTorch)
 
 ## Model Details
 
 - **Architecture:** TF-EfficientNetV2-S (timm)
+- **Base Model:** Google's EfficientNetV2-S (TensorFlow, ported to PyTorch)
 - **Input Size:** 224×224 RGB
 - **Classes:** anime, real, rendered
 - **Parameters:** 21.5M (4× larger than B0)
@@ -92,6 +96,7 @@ print(f"{labels[pred_class]}: {probs[0, pred_class]:.2%}")
 
 ## Training Details
 
+- **Base Model:** TensorFlow EfficientNetV2-S (ported to PyTorch via TIMM)
 - **Augmentation:** Raw (resize only)
 - **Optimizer:** AdamW (lr=0.001)
 - **Loss:** CrossEntropyLoss with class weighting