Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ ColPali is a model based on a novel model architecture and training strategy bas
|
|
| 15 |
It is a [PaliGemma-3B](https://huggingface.co/google/paligemma-3b-mix-448) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.
|
| 16 |
It was introduced in the paper [ColPali: Efficient Document Retrieval with Vision Language Models](https://arxiv.org/abs/2407.01449) and first released in [this repository](https://github.com/ManuelFay/colpali)
|
| 17 |
|
|
|
|
|
|
|
| 18 |
## Model Description
|
| 19 |
|
| 20 |
This model is built iteratively starting from an off-the-shelf [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) model.
|
|
|
|
| 15 |
It is a [PaliGemma-3B](https://huggingface.co/google/paligemma-3b-mix-448) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.
|
| 16 |
It was introduced in the paper [ColPali: Efficient Document Retrieval with Vision Language Models](https://arxiv.org/abs/2407.01449) and first released in [this repository](https://github.com/ManuelFay/colpali)
|
| 17 |
|
| 18 |
+
<p align="center"><img width=800 src="https://github.com/illuin-tech/colpali/blob/main/assets/colpali_architecture.webp?raw=true"/></p>
|
| 19 |
+
|
| 20 |
## Model Description
|
| 21 |
|
| 22 |
This model is built iteratively starting from an off-the-shelf [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384) model.
|