Video-Text-to-Text
Transformers
Safetensors
video-temporal-grounding
multimodal-llm
reinforcement-learning
curriculum-learning
Instructions to use Lu9876/VideoTG_R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lu9876/VideoTG_R1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Lu9876/VideoTG_R1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K