Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
video-retrieval
temporal-grounding
videosearch-r1
Instructions to use VideoSearchR1/activitynet-stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VideoSearchR1/activitynet-stage2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("VideoSearchR1/activitynet-stage2") model = AutoModelForMultimodalLM.from_pretrained("VideoSearchR1/activitynet-stage2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add video-text-to-text pipeline tag, link paper, project page, and code to model card
Verified signatureHi! I have opened this PR to enhance the model card for the VideoSearch-R1 ActivityNet Stage 2 checkpoint. Here is a summary of the improvements: - Added `pipeline_tag: video-text-to-text` to the metadata to improve searchability and integration on the Hub. - Linked the model card to the official paper [VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement](https://huggingface.co/papers/2607.00446). - Included links to the official project page and GitHub repository. - Added the BibTeX citation for the ECCV 2026 paper. - Kept your original setup and usage commands intact. Let me know if you have any questions!8321fee
-
Upload ActivityNet stage2 checkpoint
Verified signature9102e84 -
initial commit
Verified signature4d04685