Updated SmolVLM2 fine-tuning notebook link and code format (#2693)

Author: sergiopaniego

smolvlm2.md

@@ -255,10 +255,9 @@ messages = [
     {
         "role": "user",
         "content": [
-{"type": "text", "text": "What are the differences between these two images?"},
+            {"type": "text", "text": "What are the differences between these two images?"},
             {"type": "image", "path": "image_1.png"},
-{"type": "image", "path": "image_2.png"}
-            
+            {"type": "image", "path": "image_2.png"} 
         ]
     },
 ]
@@ -344,7 +343,7 @@ If you integrate SmolVLM2 in your apps using MLX and Swift, we'd love to know ab
 ### Fine-tuning SmolVLM2
 
 You can fine-tune SmolVLM2 on videos using transformers 🤗
-We have fine-tuned 500M variant in Colab on video-caption pairs in [VideoFeedback](https://huggingface.co/datasets/TIGER-Lab/VideoFeedback) dataset for demonstration purposes. Since 500M variant is small, it's better to apply full fine-tuning instead of QLoRA or LoRA, meanwhile you can try to apply QLoRA on 2.2B variant. You can find the fine-tuning notebook [here](https://github.com/huggingface/smollm/blob/main/vision/finetuning/Smol_VLM_FT.ipynb).
+We have fine-tuned 500M variant in Colab on video-caption pairs in [VideoFeedback](https://huggingface.co/datasets/TIGER-Lab/VideoFeedback) dataset for demonstration purposes. Since 500M variant is small, it's better to apply full fine-tuning instead of QLoRA or LoRA, meanwhile you can try to apply QLoRA on cB variant. You can find the fine-tuning notebook [here](https://github.com/huggingface/smollm/blob/main/vision/finetuning/SmolVLM2_Video_FT.ipynb).
 
 
 ## Read More