Visual Document Retrieval
ColPali
Safetensors
sentence-transformers
English
vidore-experimental
vidore
multi-vector
Instructions to use ModernVBERT/colmodernvbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ColPali
How to use ModernVBERT/colmodernvbert 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
- sentence-transformers
How to use ModernVBERT/colmodernvbert with sentence-transformers:
from sentence_transformers import MultiVectorEncoder model = MultiVectorEncoder("ModernVBERT/colmodernvbert") queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Notebooks
- Google Colab
- Kaggle
Any plans to implement get_n_patches for the colidefics3Processor?
#1
by athrael-soju - opened
Since get_n_patches is not implemented in the ColIdefics3Processo, we can't generate interpretability maps for colmodernvbert. I've found https://github.com/illuin-tech/colpali/pull/343, but It's not progressed in some time.
Any plans to update? Thanks
Hey @Athrael , I definitively plan to merge it but it's not a priority for us at the moment, in the meantime I believe the PR https://github.com/illuin-tech/colpali/pull/343 is functional (I've not tested it myself yet).