Update README.md

README.md

@@ -14,15 +14,7 @@ pinned: true
 
 This organization contains all artefacts released with our preprint [ColPali: Efficient Document Retrieval with Vision Language Models.]() [TODO add link],
 including the [ViDoRe](https://huggingface.co/collections/vidore/vidore-benchmark-667173f98e70a1c0fa4db00d) benchmark and our SOTA document retrieval model [*ColPali*](https://huggingface.co/vidore/colpali).
-On top of that, we release two GitHub repositories:
-- the 1st respo contains the **training** scripts used to train ColPali: https://github.com/ManuelFay/colpali
-- the 2nd repos is a Python package to **evaluate** to evalaute and reproduce our results: https://github.com/tonywu71/vidore-benchmark
 
-The `vidore-benchmark` package can also be installed using:
-
-```bash
-pip install -U vidore-benchmark
-```
 
 ### Abstract
 
@@ -61,6 +53,11 @@ We organized datasets into collections to constitute our benchmark ViDoRe and it
 
 - [*Captioning Baseline*](https://huggingface.co/collections/vidore/vidore-captioning-baseline-6658a2a62d857c7a345195fd):  Datasets in this collection are the same as in ViDoRe but preprocessed for textual retrieving. The original ViDoRe benchmark was passed to Unstructured to partition each page into chunks. Visual chunks are captioned using Claude Sonnet.
 
+## Code
+
+
+- [*training*](https://github.com/ManuelFay/colpali): To train and use modelswit the ColPali architecture
+- [*benchmarking*](https://github.com/tonywu71/vidore-benchmark): To evaluate document retrieval systems on the ViDoRe benchmark !
 
 ## Extra