Update README.md

README.md

@@ -39,12 +39,12 @@ This repository contains the complete implementation of expert model evaluation
 | Model | Known F1 | Unknown F1 | Inference Time | Throughput |
 |-------|----------|------------|----------------|------------|
 | **ModernBERT** ⭐ | **86.7%** | **80.9%** | **26ms** | **38 domains/s** |
-| Gemma 3 4B LoRA | 82.1% | 75.3% | 650ms | 1.5k/s |
-| LLaMA 3.2 3B LoRA | 81.4% | 74.8% | 680ms | 1.4k/s |
-| DomBertUrl | 81.2% | 84.6% | 28ms | 35k/s |
-| CNN | 78.9% | 72.1% | 15ms | 66k/s |
-| FANCI (RF) | 77.3% | 68.5% | <1ms | >100k/s |
-| LABin | 75.6% | 70.2% | 18ms | 55k/s |
+| Gemma 3 4B LoRA | 82.1% | 75.3% | 650ms | 1.5/s |
+| LLaMA 3.2 3B LoRA | 81.4% | 74.8% | 680ms | 1.4/s |
+| DomBertUrl | 81.2% | 84.6% | 28ms | 35/s |
+| CNN | 78.9% | 72.1% | 15ms | 66/s |
+| FANCI (RF) | 77.3% | 68.5% | <1ms | >100/s |
+| LABin | 75.6% | 70.2% | 18ms | 55/s |
 
 **Key Improvement:** Specialist training provides **+9.4% F1-score improvement** over generalist approaches on known families and **+30.2%** on unseen families.