Update README.md

README.md

@@ -14,7 +14,7 @@ base_model:
 
 We trained [TimeChat](https://arxiv.org/abs/2312.02051) using VTune, a developed instruction-tuning method specifically designed to account for consistency. 
 
-For the tuning, we utilized 10K training videos from Charades-STA with 205K automatically generated annotations.
+For the tuning, we utilized 10K training videos from ActivityNet-Captions with 205K automatically generated annotations.
 
 ## Evaluation
 We evaluated the model on ActivtyNet-CON and ActivtyNet-Captions.