Update README.md

README.md

@@ -5,6 +5,8 @@ tags: []
 
 # BiModernVBERT
 
+![bg](https://cdn-uploads.huggingface.co/production/uploads/661e945eebe3616a1b09e279/cPrlq35Qu2dUJ87XXP0qN.png)
+
 ## Model
 This is the model card for `BiModernVBERT` the dense encoder version of ModernVBERT that is fine-tuned for visual document retrieval tasks.
 
@@ -58,7 +60,6 @@ model = BiModernVBert.from_pretrained(
             trust_remote_code=True
 )
 
-# image = load_image("https://huggingface.co/spaces/HuggingFaceTB/SmolVLM/resolve/main/example_images/rococo.jpg")
 image = Image.open(hf_hub_download("HuggingFaceTB/SmolVLM", "example_images/rococo.jpg", repo_type="space"))
 text = "This is a text"
 
@@ -77,6 +78,9 @@ print("Similarity scores:", scores)
 ```
 
 ## Evaluation
+
+![table](https://cdn-uploads.huggingface.co/production/uploads/661e945eebe3616a1b09e279/aRwI1o3wiMQGooXaDRrdM.png)
+
 ColModernVBERT matches the performance of models nearly 10x larger on visual document benchmarks. Additionally, it provides an interesting inference speed on CPU compared to the models of similar performance.
 
 ## License