Wiselnn/

Qwen2-VL-tad_rope-128frames-8k-context-330k-llava-video

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.