Update model card

README.md

@@ -90,21 +90,6 @@ The fine-tuned model generates **36% fewer tokens** while maintaining higher acc
 | [**Toucan-1.5M**](https://huggingface.co/datasets/Agent-Ark/Toucan-1.5M) | 40,000 | **Negative** | Irrelevant queries (Server Shuffle method) |
 | **Synthetic Negatives** | 6,000 | **Negative** | Domain mismatch, partial fulfillment, permission errors |
 
-### Dataset Statistics
-
-```
-Total Training Samples: ~117,000
-├── Positive Samples:    71,248 (61%)
-│   ├── Single tool call:   ~55K
-│   └── Multi tool call:    ~14K
-└── Negative Samples:    46,000 (39%)
-    ├── Toucan Irrelevant:  40,000 (86.9%)
-    ├── Domain Mismatch:     3,000 (6.5%)
-    ├── Action Mismatch:     1,500 (3.3%)
-    ├── Partial Fulfillment: 1,000 (2.2%)
-    ├── Permission/Auth:       300 (0.7%)
-    └── Format Mismatch:       200 (0.4%)
-```
 
 ### Negative Sample Types