Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
video-retrieval
temporal-grounding
videosearch-r1
Instructions to use VideoSearchR1/didemo-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VideoSearchR1/didemo-stage1 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("VideoSearchR1/didemo-stage1") model = AutoModelForMultimodalLM.from_pretrained("VideoSearchR1/didemo-stage1") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag, project page, and paper links
#1
by nielsr HF Staff - opened
This PR improves the model card for VideoSearch-R1 DiDeMo Stage 1 by:
- Adding the
pipeline_tag: video-text-to-textto the metadata to improve search discoverability on the Hub. - Linking the model card to the paper page (VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement).
- Adding links to the GitHub repository and the project page.
- Including the BibTeX citation for researchers using the work.
happy8825 changed pull request status to merged