Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 
 ## Model Summary
 
-`EgoGPT-7b-EgoIT` is an omni-modal model trained on egocentric datasets, achieving state-of-the-art performance on egocentric video understanding. Built on the foundation of `llava-onevision-qwen2-7b-ov`, it has been finetuned on [EgoIT-QA (41k)](https://huggingface.co/datasets/lmms-lab/EgoIT) egocentric datasets.
+`EgoGPT-7b-EgoIT` is an omni-modal model trained on egocentric datasets, achieving state-of-the-art performance on egocentric video understanding. Built on the foundation of `llava-onevision-qwen2-7b-ov`, it has been finetuned on [EgoIT-QA (99k)](https://huggingface.co/datasets/lmms-lab/EgoIT-99K) egocentric datasets.
 
 EgoGPT excels in two primary scenarios:
 - **Advanced Model Integration**: EgoGPT combines LLaVA-OneVision and Whisper, improving its ability to process visual and auditory information.