Update README.md

README.md

@@ -130,7 +130,9 @@ base_model:
 
 ## Model Summary
 
-The LLaVA-NeXT-Video models are 7/72B parameter models trained on [LLaVA-NeXT-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data), based on Qwen2 language model with a context window of 32K tokens.
+The LLaVA-NeXT-Video models are 7/72B parameter models trained on [LLaVA-NeXT-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data) and [LLaVA-OneVision Dataset](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data), based on Qwen2 language model with a context window of 32K tokens.
+
+This model support at most 64 frames.
 
 - **Repository:** [LLaVA-VL/LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT?tab=readme-ov-file)
 - **Point of Contact:** [Yuanhan Zhang](https://zhangyuanhan-ai.github.io/)
@@ -141,7 +143,9 @@ The LLaVA-NeXT-Video models are 7/72B parameter models trained on [LLaVA-NeXT-Vi
 
 ### Intended use
 
-The model was trained on [LLaVA-NeXT-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data) and have the ability to interact with images, multi-image and videos, but specific to videos.
+The model was trained on [LLaVA-NeXT-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data) and [LLaVA-OneVision Dataset](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data), having the ability to interact with images, multi-image and videos, but specific to videos.
+
+
 
 **Feel free to share your generations in the Community tab!**