---
license: mit
library_name: colpali
base_model: vidore/colpaligemma-3b-pt-448-base
language:
- fr
tags:
- vidore
- vidore-experimental
pipeline_tag: visual-document-retrieval
---

# Colpali_FT_fr_4bits

Model trained using this [script](https://github.com/catie-aq/multimodal_RAG_with_VLMs/blob/main/colpali_FT.py) on the contatenation of the data of this [collection](https://huggingface.co/collections/CATIE-AQ/french-vqa-datasets-678a607a4c08258a5212950b) 
and this [collection](https://huggingface.co/collections/CATIE-AQ/french-retriever-datasets-678a6206c04f6a166139102c).


# Citation

```bibtex
@misc{faysse2024colpaliefficientdocumentretrieval,
  title={ColPali: Efficient Document Retrieval with Vision Language Models}, 
  author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2407.01449}, 
}
```