Upload folder using huggingface_hub

README.md

@@ -47,7 +47,7 @@ model-index:
 ## Key Features
 
 - **99%+ Accuracy** on production security logs
-- **Real-time Detection**: <100ms latency per classification
+- **Real-time Detection**: ~100ms latency per classification
 - **CPU Inference**: No GPU required, runs on any system
 - **Production-Tested**: Battle-tested since October 2025, processing logs from 8 domains
 - **Lightweight**: Only ~2GB RAM needed
@@ -232,16 +232,6 @@ The model can identify:
 
 ## Performance Metrics
 
-### Production Environment (October 2025)
-
-- **Accuracy**: 99%+ on security logs
-- **Inference Speed**: 32 tokens/second (CPU)
-- **Latency**: <100ms per classification
-- **Memory Usage**: ~2GB RAM
-- **Uptime**: 99.9%+ (stable, no crashes)
-- **Processing Rate**: 6-200 log entries per 60s batch
-- **Attack Detection Rate**: ~36 attacks/hour average
-
 ### Optimization Features
 
 When deployed in the full SecInt system:
@@ -335,7 +325,7 @@ SecInt is part of the **Security Intelligence Monitor v2** project, a comprehens
 - Attack session management
 - SQLite-based persistence and analytics
 
-For more information about the full SecInt system, visit: [logwatcher project](https://github.com/LeviDeHaan/logwatcher)
+For more information about the full SecInt system, visit: [logwatcher project](https://levidehaan.com/projects)
 
 ## Model Card Contact