Instructions to use vidore/colpali-duo-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vidore/colpali-duo-base with Transformers:
# Load model directly from transformers import AutoProcessor, ColPaliDuo processor = AutoProcessor.from_pretrained("vidore/colpali-duo-base") model = ColPaliDuo.from_pretrained("vidore/colpali-duo-base") - ColPali
How to use vidore/colpali-duo-base with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Model Card for Model ID
Base model for training ColPaliDuo.
The PaliGemma weights are loaded from google/paligemma-3b-mix-448. The remaining weights - i.e. the weights related to the linear projectors - were randomly initalized.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support