readme updates

README.md

@@ -11,7 +11,7 @@
 [[Blog Post]](https://huggingface.co/blog/manu/colpali)
 
 > [!TIP]
-> If you want to try the pre-trained ColPali on your own documents, you should use the [`vidore-benchmark`](https://github.com/illuin-tech/vidore-benchmark) repository. It comes with a Python package and a CLI tool for convenient evaluation.
+> If you want to try the pre-trained ColPali on your own documents, you can use the [`vidore-benchmark`](https://github.com/illuin-tech/vidore-benchmark) repository. It comes with a Python package and a CLI tool for convenient evaluation. You can also use code provided in the model cards on the hub.
 
 ## Associated Paper
 
@@ -36,6 +36,11 @@ To keep a lightweight repository, only the essential packages were installed. In
 pip install "colpali-engine[train]"
 ```
 
+
+> [!TIP]
+> For ColPali versions above v1.0, make sure to install the `colpali-engine` package from source or with a version above v0.2.0.
+
+
 ## Usage
 
 The `scripts/` directory contains scripts to run training and inference.

scripts/infer/run_inference_with_python.py

@@ -15,8 +15,8 @@ def main() -> None:
     """Example script to run inference with ColPali"""
 
     # Load model
-    model_name = "vidore/colpali"
-    model = ColPali.from_pretrained("google/paligemma-3b-mix-448", torch_dtype=torch.bfloat16, device_map="cuda").eval()
+    model_name = "vidore/colpali-v1.2"
+    model = ColPali.from_pretrained("vidore/colpaligemma-3b-pt-448-base", torch_dtype=torch.bfloat16, device_map="cuda").eval()
     model.load_adapter(model_name)
     processor = AutoProcessor.from_pretrained(model_name)