docs: update documentation on how to add your model

app.py

@@ -274,32 +274,10 @@ def main():
                     To submit a new model to the ViDoRe leaderboard, follow these steps:
 
                     1. **Evaluate your model**:
-                       - Follow the evaluation script provided in the [ViDoRe GitHub repository](https://github.com/illuin-tech/vidore-benchmark/)
+                       - Follow the evaluation procedure provided in the [ViDoRe GitHub repository](https://github.com/illuin-tech/vidore-benchmark/) that uses MTEB.
 
                     2. **Format your submission file**:
-                        - The submission file should automatically be generated, and named `results.json` with the
-                        following structure:
-                        ```json
-                        {
-                            "dataset_name_1": {
-                                "metric_1": score_1,
-                                "metric_2": score_2,
-                                ...
-                            },
-                            "dataset_name_2": {
-                                "metric_1": score_1,
-                                "metric_2": score_2,
-                                ...
-                            },
-                        }
-                        ```
-                        - The dataset names should be the same as the ViDoRe and ViDoRe 2 dataset names listed in the following
-                        collections: [ViDoRe Benchmark](https://huggingface.co/collections/vidore/vidore-benchmark-667173f98e70a1c0fa4db00d) and [ViDoRe Benchmark 2](vidore/vidore-benchmark-v2-dev-67ae03e3924e85b36e7f53b0).
-
-                    3. **Submit your model**:
-                        - Create a public HuggingFace model repository with your model.
-                        - Add the tag `vidore` to your model in the metadata of the model card and place the
-                        `results.json` file at the root.
+                        - Add the generated files to [MTEB results](https://github.com/embeddings-benchmark/results) project. Check the [Colpali results](https://github.com/embeddings-benchmark/results/tree/main/results/vidore__colpali-v1.3/1b5c8929330df1a66de441a9b5409a878f0de5b0) for an example.
 
                     And you're done! Your model will appear on the leaderboard when you click refresh! Once the space
                     gets rebooted, it will appear on startup.