VideoRoPE: What Makes for Good Video Rotary Position Embeddi
Collection
A storage repo for VideoRoPE.
•
5 items
•
Updated
•
2
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Trained model: Qwen2VL Vision Tower + Qwen2 Language Model
RoPE type: M-RoPE
To use this model, simply set which_type='m_rope' and scale_factor=1.0.
For more details, please refer to the code implementation.
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support