Instructions to use jacob-valdez/computaco-seekui with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jacob-valdez/computaco-seekui with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jacob-valdez/computaco-seekui", device_map="auto") - Notebooks
- Google Colab
- Kaggle
SeekUI on ComputaCo
The inference handler ComputaCo runs for SeekUI. It loads the authors' weights at a pinned revision. The method is theirs:
Zixin Guo, Yue Jiang, Luis A. Leiva and Antti Oulasvirta. SeekUI: Predicting Visual Search Behavior on Graphical User Interfaces with a Reward-Augmented Vision Language Model. CHI 2026. https://doi.org/10.1145/3772318.3791178
Code: https://github.com/YueJiang-nj/SeekUI-CHI2026 ยท Original weights: https://huggingface.co/sushizixin1/SeekUI
Outputs are model predictions of how people search a screen; they are not observations of anyone.
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support