Update README.md

README.md

@@ -112,6 +112,13 @@ inputs['attention_mask'] = inputs['attention_mask'].to(model.device)
 output = model.generate(**inputs, max_new_tokens=200, do_sample=True, top_p=0.5, temperature=1.2, eos_token_id=tokenizer.eos_token_id)
 ```
 
+## Benchmarks
+
+- TextVQA - 33.25%
+- GQA - 47.15%
+- VQAv2 - 63.1%
+- VizWiz - 24.03%
+
 ## Acknowledgments
 
 Thanks to [ML Collective](https://mlcollective.org/) for providing credits for computing resources.