Update README.md

README.md

@@ -15,7 +15,7 @@ An advanced deep learning model for automatically tagging anime/manga illustrati
 
 ### Major Performance Improvements
 - **Micro F1**: 58.1% → **67.3%** (+9.2 percentage points)
-- **Macro F1**: 31.5% → **50.6%** (+19.1 percentage points) 
+- **Macro F1**: 33.8% → **50.6%** (+16.8 percentage points) 
 - **Model Size**: 424M → **143M parameters** (-66% reduction)
 - **Architecture**: Switched from EfficientNetV2-L to Vision Transformer (ViT) backbone
 - **Simplified Design**: Streamlined from dual-stage to single refined prediction model
@@ -37,14 +37,10 @@ An advanced deep learning model for automatically tagging anime/manga illustrati
 
 ## ✨ Features
 
-- **Multi-category tagging system**: Handles general tags, characters, copyright (series), artists, meta information, and content ratings
-- **High performance**: 67.3% micro F1 score (50.6% macro F1) across 70,527 possible tags
-- **Windows compatibility**: Works on Windows without Flash Attention requirements
-- **Streamlit web interface**: User-friendly UI for uploading and analyzing images and a tag collection game
-- **Adjustable threshold profiles**: Micro, Macro, Balanced, Category-specific, High Precision, and High Recall profiles
+- **Streamlit web interface app and game**: User-friendly UI for uploading and analyzing images and a tag collection game
+- **Adjustable threshold profiles**: Micro, Macro, Balanced, Category-specific, profiles
 - **Fine-grained control**: Per-category threshold adjustments for precision-recall tradeoffs
 - **Safetensors and ONNX**: Available in main directory
-- **Vision Transformer Backbone**: Modern architecture with superior performance-to-parameter ratio
 
 ## 📊 Performance Analysis
 
@@ -205,6 +201,8 @@ The interface is divided into three main sections:
 
 ![Application Interface](images/app_screenshot.png)
 
+*Note the rare characters and tags idenified. Some only have 100's of samples on danbooru!*
+
 ![Tag Results Example](images/tag_results_example.png)
 
 ### 🛠️ Requirements