Update app.py

app.py

@@ -148,12 +148,6 @@ Upload an image of a bird and the model will predict the species!
 - Test Accuracy: 83.64%
 - Average Per-Class Accuracy: 83.29%
 
-**Training Strategy:**
-- Transfer Learning with ImageNet pretrained weights
-- Two-phase training: Frozen backbone (40 epochs) → Fine-tuning (20 epochs)
-- Strong regularization: Dropout (0.6, 0.5), Label smoothing (0.2)
-- Data augmentation: Rotation, flip, color jitter, random erasing
-
 Upload a clear image of a bird to get started!
 """
 
@@ -161,8 +155,6 @@ article = """
 ### About This Model
 
 This bird classifier was trained on the CUB-200-2011 dataset containing 200 North American bird species.
-The model uses ConvNeXt-Base architecture with modern training techniques to achieve high accuracy while
-preventing overfitting.
 
 **Key Features:**
 - ✅ 200 bird species classification
@@ -170,7 +162,6 @@ preventing overfitting.
 - ✅ 83.64% test accuracy
 - ✅ Real-time inference
 
-**Best Results:** Upload high-quality images with the bird clearly visible and centered.
 """
 
 examples = [