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.

Safetensors

Model size

8.29B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train Wiselnn/Qwen2-VL-tad_rope-128frames-8k-context-330k-llava-video

Collection including Wiselnn/Qwen2-VL-tad_rope-128frames-8k-context-330k-llava-video