Code snippet fixes

README.md

@@ -63,6 +63,7 @@ You can load the model as follows.
 
 ```python
 from transformers import AutoProcessor, AutoModelForImageTextToText
+import torch
 
 model_path = "HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
 processor = AutoProcessor.from_pretrained(model_path)
@@ -82,9 +83,8 @@ messages = [
     {
         "role": "user",
         "content": [
-{"type": "text", "text": "What is in this image?"},
-            {"type": "image", "path": "path_to_img.png"},
-            
+            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+            {"type": "text", "text": "Can you describe this image?"},            
         ]
     },
 ]
@@ -148,11 +148,9 @@ messages = [
     {
         "role": "user",
         "content": [
-{"type": "text", "text": "What is the similarity between this image <image>"},
-
-            {"type": "image", "path": "image_1.png"},
-{"type": "text", "text": "and this image <image>"},
-{"type": "image", "path": "image_2.png"},            
+          {"type": "text", "text": "What is the similarity between these two images?"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+          {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"},            
         ]
     },
 ]