Update README.md

README.md

@@ -129,9 +129,10 @@ base_model:
 
 ## Model Summary
 
-In contrast to lmms-lab/LLaVA-NeXT-Video-7B-Qwen2, this is a 7B model trained on [LLaVA-NeXT-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data) only, based on Qwen2 language model with a context window of 32K tokens.
+In contrast to lmms-lab/LLaVA-NeXT-Video-7B-Qwen2, this is a 7B model trained on [LLaVA-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data) only, based on Qwen2 language model with a context window of 32K tokens.
 
-This model support at most 110 frames.
+
+This model supports up to 110 frames and achieves comparable results to those of lmms-lab/LLaVA-NeXT-Video-7B-Qwen2 in terms of video benchmarks."
 
 - **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/)
@@ -229,5 +230,3 @@ print(text_outputs)
 - **GPUs:** 256 * Nvidia Tesla A100 (for whole model series training)
 - **Orchestration:** [Huggingface Trainer](https://huggingface.co/docs/transformers/main_classes/trainer)
 - **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)
-
-# Citation