---
license: apache-2.0
datasets:
- lmms-lab/LLaVA-Video-178K
---
[VideoRoPE: What Makes for Good Video Rotary Position Embedding?](https://arxiv.org/pdf/2502.05173)

**Trained model:** Qwen2VL Vision Tower + Qwen2 Language Model  
**RoPE type:** Vanilla RoPE

To use this model, simply set `which_type='vanilla_rope'` and `scale_factor=1.0`.  
For more details, please refer to the [code implementation](https://github.com/Wiselnn570/VideoRoPE).