fix task tag

README.md

@@ -9,7 +9,7 @@ language:
 metrics:
 - accuracy
 library_name: transformers
-pipeline_tag: visual-question-answering
+pipeline_tag: video-text-to-text
 tags:
 - multimodal large language model
 - large video-language model
@@ -103,4 +103,4 @@ If you find VideoLLaMA useful for your research and applications, please cite us
   year = {2023},
   url = {https://arxiv.org/abs/2306.02858}
 }
-```
+```