Fix citation title, add download instructions for TF-Lite/SavedModel snippets

README.md

@@ -388,6 +388,13 @@ print(f"Predicted: {LABELS[np.argmax(preds)]} ({np.max(preds)*100:.1f}%)")
 
 ### Python — TF-Lite
 
+Download the model first:
+```python
+from huggingface_hub import hf_hub_download
+hf_hub_download("0xgr3y/Arch-Building-Image-Classification", "tflite/model.tflite", local_dir=".")
+hf_hub_download("0xgr3y/Arch-Building-Image-Classification", "tflite/label.txt", local_dir=".")
+```
+
 ```python
 import numpy as np
 import tensorflow as tf
@@ -416,6 +423,14 @@ for i in top3_idx:
 
 ### Python — SavedModel
 
+Download the model first:
+```python
+from huggingface_hub import snapshot_download
+snapshot_download("0xgr3y/Arch-Building-Image-Classification", allow_patterns=["saved_model/*"], local_dir=".")
+```
+
+Requires the custom layer definitions from the Keras section above.
+
 ```python
 import tensorflow as tf
 import numpy as np
@@ -488,7 +503,9 @@ print(f"Predicted: {LABELS[np.argmax(preds)]} ({np.max(preds)*100:.1f}%)")
 
 ```bibtex
 @misc{saugani2026_arch_building,
-  title={Architecture Building Image Classifier: FGVC with DenseNet121 + GeM Pooling + SWA},
+  title={Fine-Grained Visual Categorization of World Architectural Buildings
+         Using CNN Transfer Learning DenseNet121 with Fine-Tuning and
+         Multi-Layer Regularization Strategy},
   author={Saugani},
   year={2026},
   publisher={Hugging Face},