update readme

README.md

@@ -23,8 +23,8 @@ The model is for research purposes, more technical details will come with a tech
 
 | Dataset Type| Dataset(s) Used                          |
 |--------|------------------------------------------|
-| Pretrain | caption data: high-quality image caption datasets and interleaved datasets |
-| Instruction Tuning    | visual instruction following and caption datasets, a mixture of academic VQA data including OCR/Document/Chart-focused tasks, publicly available text-only instruction data |
+| Pretrain | high-quality image caption datasets and interleaved datasets |
+| Instruction Tuning    | a mixture of VQA data and caption datasets including OCR/Document/Chart-focused tasks, publicly available text-only instruction data |
 
 # Results