Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ConfusionMatrix_v2_0.png filter=lfs diff=lfs merge=lfs -text
+ConfusionMatrix_v2_5.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -45,15 +45,17 @@ This is an image classification model based on **Google EfficientNet-B0**, fine-
 
 ## Model Performance
 
+**Note:** This model uses the same architecture and implementation as v2.0. The improved performance is achieved by training on a dataset that is 10 times larger than the one used for v2.0.
+
 The model was evaluated on a held-out test set from the finepdfs dataset with the following metrics:
 
-| Metric | Score |
-|--------|-------|
-| **Accuracy** | 0.90703 |
-| **Balanced Accuracy** | 0.68836 |
-| **Macro F1** | 0.68942 |
-| **Weighted F1** | 0.90716 |
-| **Cohen's Kappa** | 0.87449 |
+| Metric | v2.5 | v2.0 | Improvement |
+|--------|------|------|-------------|
+| **Accuracy** | 0.90703 | 0.87053 | +3.65% |
+| **Balanced Accuracy** | 0.68836 | 0.60231 | +8.61% |
+| **Macro F1** | 0.68942 | 0.60144 | +8.80% |
+| **Weighted F1** | 0.90716 | 0.87270 | +3.45% |
+| **Cohen's Kappa** | 0.87449 | 0.82563 | +4.89% |
 
 ### Per-Label Performance