Video-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
spatial-reasoning
4d-vision
vlm
text-generation-inference
Instructions to use TencentARC/DSR_Suite-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TencentARC/DSR_Suite-Model with Transformers:
# Load model directly from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration_Spatial processor = AutoProcessor.from_pretrained("TencentARC/DSR_Suite-Model") model = Qwen2_5_VLForConditionalGeneration_Spatial.from_pretrained("TencentARC/DSR_Suite-Model") - Notebooks
- Google Colab
- Kaggle
Ctrl+K