Update README.md

README.md

@@ -40,4 +40,4 @@ The primary intended users of the model are researchers and hobbyists in compute
 - 40K ShareGPT data.
 
 ## Evaluation dataset
-A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.
+A collection of 8 benchmarks, including 3 visual hallucination benchmarks and 5 recent benchmarks specifically proposed for instruction-following LMMs.