metadata
license: apache-2.0
datasets:
- lmms-lab/LLaVA-Video-178K
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Trained model: Qwen2VL Vision Tower + Qwen2 Language Model
RoPE type: TAD-RoPE
To use this model, simply set which_type='tad_rope' and scale_factor=1.0.
For more details, please refer to the code implementation.