Update README.md

README.md

@@ -61,11 +61,7 @@ By utilizing advanced multimodal learning capabilities, this model understands b
 
 The fine-tuning process leveraged Unsloth's efficiency optimizations, reducing training time while maintaining high accuracy. The model was trained on a diverse dataset of scanned documents and synthetic examples to ensure robustness across real-world scenarios.  
 
-## Benchmarks  
 
-- **Document Parsing Accuracy:** 98.7%  
-- **JSON Structuring Precision:** 99.3%  
-- **Inference Speed:** ~2x faster than baseline models on comparable tasks  
 
 ## Acknowledgments  
 
@@ -75,4 +71,3 @@ This model was fine-tuned using the powerful capabilities of the [Unsloth](https
 
 ---  
 
-Let me know if you'd like further elaboration or additional sections!